* [PATCH v18 01/11] x86/hvm/ioreq: maintain an array of ioreq servers rather than a list
2018-03-22 11:55 [PATCH v18 00/11] x86: guest resource mapping Paul Durrant
@ 2018-03-22 11:55 ` Paul Durrant
2018-03-26 11:21 ` Jan Beulich
2018-03-22 11:55 ` [PATCH v18 02/11] x86/hvm/ioreq: simplify code and use consistent naming Paul Durrant
` (9 subsequent siblings)
10 siblings, 1 reply; 30+ messages in thread
From: Paul Durrant @ 2018-03-22 11:55 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>
---
Cc: Jan Beulich <jbeulich@suse.com>
Cc: Andrew Cooper <andrew.cooper3@citrix.com>
v18:
- non-trivial re-base.
- small modification to FOR_EACH... macro to iterate backwards, to main-
tain a previous undocumented but useful semantic that secondary
emulators are selected in favour of qemu.
- dropped R-b's because of change.
v10:
- modified FOR_EACH... macro as suggested by Jan.
- check for NULL in IS_DEFAULT macro as suggested by Jan.
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 | 539 +++++++++++++++++++--------------------
xen/include/asm-x86/hvm/domain.h | 11 +-
2 files changed, 265 insertions(+), 285 deletions(-)
diff --git a/xen/arch/x86/hvm/ioreq.c b/xen/arch/x86/hvm/ioreq.c
index 44d029499d..d8d4e96a80 100644
--- a/xen/arch/x86/hvm/ioreq.c
+++ b/xen/arch/x86/hvm/ioreq.c
@@ -33,6 +33,37 @@
#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) && (s) == GET_IOREQ_SERVER((s)->target, DEFAULT_IOSERVID))
+
+/* Iterate over all possible ioreq servers */
+#define FOR_EACH_IOREQ_SERVER(d, id, s) \
+ for ( (id) = MAX_NR_IOREQ_SERVERS; (id) != 0; ) \
+ if ( !(s = GET_IOREQ_SERVER(d, --(id))) ) \
+ continue; \
+ else
+
static ioreq_t *get_ioreq(struct hvm_ioreq_server *s, struct vcpu *v)
{
shared_iopage_t *p = s->ioreq.va;
@@ -47,10 +78,9 @@ 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 +157,9 @@ 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 +272,12 @@ 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 +330,7 @@ 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;
@@ -316,7 +344,8 @@ static int hvm_ioreq_server_add_vcpu(struct hvm_ioreq_server *s,
spin_lock(&s->lock);
rc = alloc_unbound_xen_event_channel(v->domain, v->vcpu_id,
- s->emulator->domain_id, NULL);
+ s->emulator->domain_id,
+ NULL);
if ( rc < 0 )
goto fail2;
@@ -332,7 +361,7 @@ 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;
}
@@ -432,7 +461,6 @@ 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->target;
@@ -440,7 +468,7 @@ 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
@@ -469,8 +497,7 @@ 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->target;
bool handle_bufioreq = !!s->bufioreq.va;
@@ -480,7 +507,7 @@ 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);
@@ -489,12 +516,11 @@ 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++ )
@@ -502,19 +528,21 @@ 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" :
@@ -538,13 +566,12 @@ 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->target;
struct hvm_ioreq_vcpu *sv;
@@ -555,7 +582,7 @@ 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);
@@ -574,8 +601,7 @@ 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->target;
bool handle_bufioreq = !!s->bufioreq.va;
@@ -585,7 +611,7 @@ 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);
@@ -600,14 +626,13 @@ 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, bool is_default,
- int bufioreq_handling, ioservid_t id)
+ struct domain *d, int bufioreq_handling,
+ ioservid_t id)
{
struct domain *currd = current->domain;
struct vcpu *v;
int rc;
- s->id = id;
s->target = d;
get_knownalive_domain(currd);
@@ -617,7 +642,7 @@ 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;
@@ -625,13 +650,13 @@ 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;
}
@@ -640,102 +665,87 @@ 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);
put_domain(s->emulator);
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);
+ hvm_ioreq_server_unmap_pages(s);
+ hvm_ioreq_server_free_rangesets(s);
put_domain(s->emulator);
}
-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;
-}
-
int hvm_create_ioreq_server(struct domain *d, bool is_default,
int bufioreq_handling, 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, 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, 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;
}
@@ -744,41 +754,38 @@ 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);
- rc = -EPERM;
- if ( s->emulator != current->domain )
- break;
+ rc = -ENOENT;
+ if ( !s )
+ goto out;
- domain_pause(d);
+ ASSERT(!IS_DEFAULT(s));
- p2m_set_ioreq_server(d, 0, s);
+ rc = -EPERM;
+ if ( s->emulator != current->domain )
+ goto out;
- 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;
@@ -792,35 +799,34 @@ 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;
- rc = -EPERM;
- if ( s->emulator != current->domain )
- break;
+ ASSERT(!IS_DEFAULT(s));
- *ioreq_gfn = s->ioreq.gfn;
+ rc = -EPERM;
+ if ( s->emulator != current->domain )
+ goto out;
- 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;
@@ -831,55 +837,53 @@ 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 ( start > end )
return -EINVAL;
+ 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 )
- {
- struct rangeset *r;
+ 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));
- rc = -EPERM;
- if ( s->emulator != current->domain )
- break;
+ rc = -EPERM;
+ if ( s->emulator != current->domain )
+ goto out;
- 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;
@@ -890,55 +894,53 @@ 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 ( start > end )
return -EINVAL;
+ 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 )
- {
- struct rangeset *r;
+ if ( !s )
+ goto out;
- if ( s == d->arch.hvm_domain.default_ioreq_server )
- continue;
+ ASSERT(!IS_DEFAULT(s));
- if ( s->id != id )
- continue;
+ rc = -EPERM;
+ if ( s->emulator != current->domain )
+ goto out;
- rc = -EPERM;
- if ( s->emulator != current->domain )
- 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;
- 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 )
+ goto out;
- rc = -EINVAL;
- if ( !r )
- break;
+ rc = -ENOENT;
+ if ( !rangeset_contains_range(r, start, end) )
+ goto out;
- rc = -ENOENT;
- if ( !rangeset_contains_range(r, start, end) )
- break;
-
- 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;
@@ -958,6 +960,9 @@ 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;
@@ -966,25 +971,21 @@ int hvm_map_mem_type_to_ioreq_server(struct domain *d, ioservid_t id,
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 )
- continue;
+ ASSERT(!IS_DEFAULT(s));
- rc = -EPERM;
- if ( s->emulator != current->domain )
- break;
+ rc = -EPERM;
+ if ( s->emulator != current->domain )
+ goto out;
- rc = p2m_set_ioreq_server(d, flags, s);
- break;
- }
+ rc = p2m_set_ioreq_server(d, flags, s);
+ out:
spin_unlock_recursive(&d->arch.hvm_domain.ioreq_server.lock);
if ( rc == 0 && flags == 0 )
@@ -1001,42 +1002,38 @@ 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));
- rc = -EPERM;
- if ( s->emulator != current->domain )
- break;
+ rc = -EPERM;
+ if ( s->emulator != current->domain )
+ goto out;
- 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;
}
@@ -1044,17 +1041,14 @@ 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;
}
@@ -1064,10 +1058,15 @@ 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);
@@ -1077,12 +1076,11 @@ 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);
@@ -1090,28 +1088,19 @@ 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);
}
@@ -1125,12 +1114,10 @@ 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;
@@ -1168,16 +1155,11 @@ 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];
@@ -1210,7 +1192,7 @@ 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)
@@ -1369,13 +1351,13 @@ 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;
}
@@ -1395,7 +1377,6 @@ 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 6e03d024c8..2e4d85f6fe 100644
--- a/xen/include/asm-x86/hvm/domain.h
+++ b/xen/include/asm-x86/hvm/domain.h
@@ -52,13 +52,11 @@ struct hvm_ioreq_vcpu {
#define MAX_NR_IO_RANGES 256
struct hvm_ioreq_server {
- struct list_head list_entry;
struct domain *target, *emulator;
/* Lock to serialize toolstack modifications */
spinlock_t lock;
- ioservid_t id;
struct hvm_ioreq_page ioreq;
struct list_head ioreq_vcpu_list;
struct hvm_ioreq_page bufioreq;
@@ -98,6 +96,9 @@ 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 {
@@ -107,11 +108,9 @@ 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.xenproject.org
https://lists.xenproject.org/mailman/listinfo/xen-devel
^ permalink raw reply related [flat|nested] 30+ messages in thread* Re: [PATCH v18 01/11] x86/hvm/ioreq: maintain an array of ioreq servers rather than a list
2018-03-22 11:55 ` [PATCH v18 01/11] x86/hvm/ioreq: maintain an array of ioreq servers rather than a list Paul Durrant
@ 2018-03-26 11:21 ` Jan Beulich
2018-03-28 14:44 ` Paul Durrant
0 siblings, 1 reply; 30+ messages in thread
From: Jan Beulich @ 2018-03-26 11:21 UTC (permalink / raw)
To: Paul Durrant; +Cc: Andrew Cooper, xen-devel
>>> On 22.03.18 at 12:55, <paul.durrant@citrix.com> wrote:
> v18:
> - non-trivial re-base.
> - small modification to FOR_EACH... macro to iterate backwards, to main-
> tain a previous undocumented but useful semantic that secondary
> emulators are selected in favour of qemu.
If this is intentional (and necessary), I think there should be a
code comment saying why (and implicitly preventing people from
wanting to change it).
I'm also having difficulty to see why that was the case before
this patch: hvm_create_ioreq_server() doesn't insert the default
one at the list tail. Are you perhaps basing this solely on the
assumption that secondary ones would be created after the
default one?
> @@ -316,7 +344,8 @@ static int hvm_ioreq_server_add_vcpu(struct hvm_ioreq_server *s,
> spin_lock(&s->lock);
>
> rc = alloc_unbound_xen_event_channel(v->domain, v->vcpu_id,
> - s->emulator->domain_id, NULL);
> + s->emulator->domain_id,
> + NULL);
Stray change?
> int hvm_create_ioreq_server(struct domain *d, bool is_default,
> int bufioreq_handling, 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, 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, bufioreq_handling, i);
Is it safe to do the init only after the insertion? I guess all lock-less
array traversals happen in context of the guest (which is paused
here), but the old code did things the other way around anyway.
So unless something breaks with the inverse order, I'd suggest to
use that. If the order is required to be the way you have it, I'd
again like to suggest to add a comment clarifying this is intentional.
> @@ -744,41 +754,38 @@ 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);
>
> - rc = -EPERM;
> - if ( s->emulator != current->domain )
> - break;
> + rc = -ENOENT;
> + if ( !s )
> + goto out;
>
> - domain_pause(d);
> + ASSERT(!IS_DEFAULT(s));
>
> - p2m_set_ioreq_server(d, 0, s);
> + rc = -EPERM;
> + if ( s->emulator != current->domain )
> + goto out;
>
> - 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);
Same here then for the deinit vs list_del() / set_ioreq_server()
ordering. Also (but perhaps less relevant) in
hvm_destroy_all_ioreq_servers().
> @@ -1168,16 +1155,11 @@ 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;
Do you really mean the "enabled" check to go away here? If so, why?
> @@ -1369,13 +1351,13 @@ 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++;
> + }
Which in turn makes me wonder - should broadcasts really be sent
to disabled servers?
Jan
_______________________________________________
Xen-devel mailing list
Xen-devel@lists.xenproject.org
https://lists.xenproject.org/mailman/listinfo/xen-devel
^ permalink raw reply [flat|nested] 30+ messages in thread* Re: [PATCH v18 01/11] x86/hvm/ioreq: maintain an array of ioreq servers rather than a list
2018-03-26 11:21 ` Jan Beulich
@ 2018-03-28 14:44 ` Paul Durrant
2018-03-28 15:06 ` Paul Durrant
0 siblings, 1 reply; 30+ messages in thread
From: Paul Durrant @ 2018-03-28 14:44 UTC (permalink / raw)
To: 'Jan Beulich'; +Cc: Andrew Cooper, xen-devel
> -----Original Message-----
> From: Jan Beulich [mailto:JBeulich@suse.com]
> Sent: 26 March 2018 12:22
> To: Paul Durrant <Paul.Durrant@citrix.com>
> Cc: Andrew Cooper <Andrew.Cooper3@citrix.com>; xen-
> devel@lists.xenproject.org
> Subject: Re: [PATCH v18 01/11] x86/hvm/ioreq: maintain an array of ioreq
> servers rather than a list
>
> >>> On 22.03.18 at 12:55, <paul.durrant@citrix.com> wrote:
> > v18:
> > - non-trivial re-base.
> > - small modification to FOR_EACH... macro to iterate backwards, to main-
> > tain a previous undocumented but useful semantic that secondary
> > emulators are selected in favour of qemu.
>
> If this is intentional (and necessary), I think there should be a
> code comment saying why (and implicitly preventing people from
> wanting to change it).
>
Ok.
> I'm also having difficulty to see why that was the case before
> this patch: hvm_create_ioreq_server() doesn't insert the default
> one at the list tail. Are you perhaps basing this solely on the
> assumption that secondary ones would be created after the
> default one?
>
It's not really about default vs. non-default. I was running my toy emulators from shell after starting up the guest paused. So I relied on (upstream) qemu being the first emulator to create its ioreq server, and then my toy emulator would be inserted ahead of it in the list.
> > @@ -316,7 +344,8 @@ static int hvm_ioreq_server_add_vcpu(struct
> hvm_ioreq_server *s,
> > spin_lock(&s->lock);
> >
> > rc = alloc_unbound_xen_event_channel(v->domain, v->vcpu_id,
> > - s->emulator->domain_id, NULL);
> > + s->emulator->domain_id,
> > + NULL);
>
> Stray change?
>
Oh yes.
> > int hvm_create_ioreq_server(struct domain *d, bool is_default,
> > int bufioreq_handling, 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, 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, bufioreq_handling, i);
>
> Is it safe to do the init only after the insertion? I guess all lock-less
> array traversals happen in context of the guest (which is paused
> here), but the old code did things the other way around anyway.
> So unless something breaks with the inverse order, I'd suggest to
> use that. If the order is required to be the way you have it, I'd
> again like to suggest to add a comment clarifying this is intentional.
Yes, it's safe for the reason you mention but I will switch it round since it does indeed look suspicious. I don't think there is any reason for it to be ordered this way now... it's possible I needed get_ioreq_server() to work correctly during some intermediate development step.
>
> > @@ -744,41 +754,38 @@ 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);
> >
> > - rc = -EPERM;
> > - if ( s->emulator != current->domain )
> > - break;
> > + rc = -ENOENT;
> > + if ( !s )
> > + goto out;
> >
> > - domain_pause(d);
> > + ASSERT(!IS_DEFAULT(s));
> >
> > - p2m_set_ioreq_server(d, 0, s);
> > + rc = -EPERM;
> > + if ( s->emulator != current->domain )
> > + goto out;
> >
> > - 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);
>
> Same here then for the deinit vs list_del() / set_ioreq_server()
> ordering. Also (but perhaps less relevant) in
> hvm_destroy_all_ioreq_servers().
>
I'll switch it round.
> > @@ -1168,16 +1155,11 @@ 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;
>
> Do you really mean the "enabled" check to go away here? If so, why?
>
No, that check should still be there. I don't know how it got removed.
> > @@ -1369,13 +1351,13 @@ 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++;
> > + }
>
> Which in turn makes me wonder - should broadcasts really be sent
> to disabled servers?
>
I can't think of a reason why we'd need them to be. I'll add a check there.
Paul
> Jan
_______________________________________________
Xen-devel mailing list
Xen-devel@lists.xenproject.org
https://lists.xenproject.org/mailman/listinfo/xen-devel
^ permalink raw reply [flat|nested] 30+ messages in thread* Re: [PATCH v18 01/11] x86/hvm/ioreq: maintain an array of ioreq servers rather than a list
2018-03-28 14:44 ` Paul Durrant
@ 2018-03-28 15:06 ` Paul Durrant
0 siblings, 0 replies; 30+ messages in thread
From: Paul Durrant @ 2018-03-28 15:06 UTC (permalink / raw)
To: Paul Durrant, 'Jan Beulich'; +Cc: Andrew Cooper, xen-devel
> -----Original Message-----
> From: Xen-devel [mailto:xen-devel-bounces@lists.xenproject.org] On Behalf
> Of Paul Durrant
> Sent: 28 March 2018 15:44
> To: 'Jan Beulich' <JBeulich@suse.com>
> Cc: Andrew Cooper <Andrew.Cooper3@citrix.com>; xen-
> devel@lists.xenproject.org
> Subject: Re: [Xen-devel] [PATCH v18 01/11] x86/hvm/ioreq: maintain an
> array of ioreq servers rather than a list
>
> > -----Original Message-----
> > From: Jan Beulich [mailto:JBeulich@suse.com]
> > Sent: 26 March 2018 12:22
> > To: Paul Durrant <Paul.Durrant@citrix.com>
> > Cc: Andrew Cooper <Andrew.Cooper3@citrix.com>; xen-
> > devel@lists.xenproject.org
> > Subject: Re: [PATCH v18 01/11] x86/hvm/ioreq: maintain an array of ioreq
> > servers rather than a list
> >
> > >>> On 22.03.18 at 12:55, <paul.durrant@citrix.com> wrote:
> > > v18:
> > > - non-trivial re-base.
> > > - small modification to FOR_EACH... macro to iterate backwards, to main-
> > > tain a previous undocumented but useful semantic that secondary
> > > emulators are selected in favour of qemu.
> >
> > If this is intentional (and necessary), I think there should be a
> > code comment saying why (and implicitly preventing people from
> > wanting to change it).
> >
>
> Ok.
>
> > I'm also having difficulty to see why that was the case before
> > this patch: hvm_create_ioreq_server() doesn't insert the default
> > one at the list tail. Are you perhaps basing this solely on the
> > assumption that secondary ones would be created after the
> > default one?
> >
>
> It's not really about default vs. non-default. I was running my toy emulators
> from shell after starting up the guest paused. So I relied on (upstream) qemu
> being the first emulator to create its ioreq server, and then my toy emulator
> would be inserted ahead of it in the list.
>
> > > @@ -316,7 +344,8 @@ static int hvm_ioreq_server_add_vcpu(struct
> > hvm_ioreq_server *s,
> > > spin_lock(&s->lock);
> > >
> > > rc = alloc_unbound_xen_event_channel(v->domain, v->vcpu_id,
> > > - s->emulator->domain_id, NULL);
> > > + s->emulator->domain_id,
> > > + NULL);
> >
> > Stray change?
> >
>
> Oh yes.
>
> > > int hvm_create_ioreq_server(struct domain *d, bool is_default,
> > > int bufioreq_handling, 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, 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, bufioreq_handling, i);
> >
> > Is it safe to do the init only after the insertion? I guess all lock-less
> > array traversals happen in context of the guest (which is paused
> > here), but the old code did things the other way around anyway.
> > So unless something breaks with the inverse order, I'd suggest to
> > use that. If the order is required to be the way you have it, I'd
> > again like to suggest to add a comment clarifying this is intentional.
>
> Yes, it's safe for the reason you mention but I will switch it round since it does
> indeed look suspicious. I don't think there is any reason for it to be ordered
> this way now... it's possible I needed get_ioreq_server() to work correctly
> during some intermediate development step.
>
No, it still needs to be this way round. I need IS_DEFAULT() to work correctly in some sub-functions. I'll add comments.
Paul
> >
> > > @@ -744,41 +754,38 @@ 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);
> > >
> > > - rc = -EPERM;
> > > - if ( s->emulator != current->domain )
> > > - break;
> > > + rc = -ENOENT;
> > > + if ( !s )
> > > + goto out;
> > >
> > > - domain_pause(d);
> > > + ASSERT(!IS_DEFAULT(s));
> > >
> > > - p2m_set_ioreq_server(d, 0, s);
> > > + rc = -EPERM;
> > > + if ( s->emulator != current->domain )
> > > + goto out;
> > >
> > > - 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);
> >
> > Same here then for the deinit vs list_del() / set_ioreq_server()
> > ordering. Also (but perhaps less relevant) in
> > hvm_destroy_all_ioreq_servers().
> >
>
> I'll switch it round.
>
> > > @@ -1168,16 +1155,11 @@ 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;
> >
> > Do you really mean the "enabled" check to go away here? If so, why?
> >
>
> No, that check should still be there. I don't know how it got removed.
>
> > > @@ -1369,13 +1351,13 @@ 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++;
> > > + }
> >
> > Which in turn makes me wonder - should broadcasts really be sent
> > to disabled servers?
> >
>
> I can't think of a reason why we'd need them to be. I'll add a check there.
>
> Paul
>
> > Jan
>
> _______________________________________________
> Xen-devel mailing list
> Xen-devel@lists.xenproject.org
> https://lists.xenproject.org/mailman/listinfo/xen-devel
_______________________________________________
Xen-devel mailing list
Xen-devel@lists.xenproject.org
https://lists.xenproject.org/mailman/listinfo/xen-devel
^ permalink raw reply [flat|nested] 30+ messages in thread
* [PATCH v18 02/11] x86/hvm/ioreq: simplify code and use consistent naming
2018-03-22 11:55 [PATCH v18 00/11] x86: guest resource mapping Paul Durrant
2018-03-22 11:55 ` [PATCH v18 01/11] x86/hvm/ioreq: maintain an array of ioreq servers rather than a list Paul Durrant
@ 2018-03-22 11:55 ` Paul Durrant
2018-03-22 11:55 ` [PATCH v18 03/11] x86/hvm/ioreq: use gfn_t in struct hvm_ioreq_page Paul Durrant
` (8 subsequent siblings)
10 siblings, 0 replies; 30+ messages in thread
From: Paul Durrant @ 2018-03-22 11:55 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>
v18:
- Trivial re-base.
v3:
- Re-based 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 d8d4e96a80..bd141db0d5 100644
--- a/xen/arch/x86/hvm/ioreq.c
+++ b/xen/arch/x86/hvm/ioreq.c
@@ -210,63 +210,75 @@ 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->target;
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->target;
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->target;
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)
@@ -279,8 +291,7 @@ 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;
@@ -292,20 +303,30 @@ 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->target;
+ 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->target;
+ 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),
@@ -442,78 +463,25 @@ 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->target;
- 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->target;
- 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)
@@ -573,22 +541,15 @@ 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->target;
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;
@@ -603,21 +564,13 @@ 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->target;
- 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;
@@ -642,6 +595,9 @@ 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;
@@ -649,7 +605,7 @@ 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.xenproject.org
https://lists.xenproject.org/mailman/listinfo/xen-devel
^ permalink raw reply related [flat|nested] 30+ messages in thread* [PATCH v18 03/11] x86/hvm/ioreq: use gfn_t in struct hvm_ioreq_page
2018-03-22 11:55 [PATCH v18 00/11] x86: guest resource mapping Paul Durrant
2018-03-22 11:55 ` [PATCH v18 01/11] x86/hvm/ioreq: maintain an array of ioreq servers rather than a list Paul Durrant
2018-03-22 11:55 ` [PATCH v18 02/11] x86/hvm/ioreq: simplify code and use consistent naming Paul Durrant
@ 2018-03-22 11:55 ` Paul Durrant
2018-03-22 11:55 ` [PATCH v18 04/11] x86/hvm/ioreq: defer mapping gfns until they are actually requested Paul Durrant
` (7 subsequent siblings)
10 siblings, 0 replies; 30+ messages in thread
From: Paul Durrant @ 2018-03-22 11:55 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>
v18:
- Trivial re-base.
---
xen/arch/x86/hvm/ioreq.c | 46 ++++++++++++++++++++--------------------
xen/include/asm-x86/hvm/domain.h | 2 +-
2 files changed, 24 insertions(+), 24 deletions(-)
diff --git a/xen/arch/x86/hvm/ioreq.c b/xen/arch/x86/hvm/ioreq.c
index bd141db0d5..d5f0e24b98 100644
--- a/xen/arch/x86/hvm/ioreq.c
+++ b/xen/arch/x86/hvm/ioreq.c
@@ -210,7 +210,7 @@ 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->target;
unsigned int i;
@@ -220,20 +220,19 @@ 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->target;
- 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);
}
@@ -242,7 +241,7 @@ 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);
@@ -251,7 +250,7 @@ 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)
@@ -264,16 +263,17 @@ 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);
@@ -309,10 +309,10 @@ static void hvm_remove_ioreq_gfn(struct hvm_ioreq_server *s, bool buf)
struct domain *d = s->target;
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);
@@ -324,15 +324,15 @@ 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_pfn_dirty(d, _pfn(iorp->gfn));
+ paging_mark_pfn_dirty(d, _pfn(gfn_x(iorp->gfn)));
return rc;
}
@@ -595,8 +595,8 @@ 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 )
@@ -772,11 +772,11 @@ int hvm_get_ioreq_server_info(struct domain *d, ioservid_t id,
if ( s->emulator != current->domain )
goto out;
- *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 2e4d85f6fe..9b73e80777 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.xenproject.org
https://lists.xenproject.org/mailman/listinfo/xen-devel
^ permalink raw reply related [flat|nested] 30+ messages in thread* [PATCH v18 04/11] x86/hvm/ioreq: defer mapping gfns until they are actually requested
2018-03-22 11:55 [PATCH v18 00/11] x86: guest resource mapping Paul Durrant
` (2 preceding siblings ...)
2018-03-22 11:55 ` [PATCH v18 03/11] x86/hvm/ioreq: use gfn_t in struct hvm_ioreq_page Paul Durrant
@ 2018-03-22 11:55 ` Paul Durrant
2018-03-22 11:55 ` [PATCH v18 05/11] x86/mm: add HYPERVISOR_memory_op to acquire guest resources Paul Durrant
` (6 subsequent siblings)
10 siblings, 0 replies; 30+ messages in thread
From: Paul Durrant @ 2018-03-22 11:55 UTC (permalink / raw)
To: xen-devel
Cc: Stefano Stabellini, George Dunlap, Andrew Cooper, Ian Jackson,
Tim Deegan, Paul Durrant, Chao Gao
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>
Reviewed-by: Jan Beulich <jbeulich@suse.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: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Cc: Stefano Stabellini <sstabellini@kernel.org>
Cc: Tim Deegan <tim@xen.org>
Cc: Chao Gao <chao.gao@intel.com>
v18:
- Trivial re-base.
v17:
- Fix typo in commit comment.
v16:
- Leave call to map pages in hvm_ioreq_server_init() for default ioreq
server instance, as pointed out by Chao (cc-ed). This is small and
obvious change which reduces the size of the patch, so I have left
existent R-bs and A-bs in place.
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 | 49 ++++++++++++++++---------
xen/include/asm-x86/hvm/domain.h | 2 +-
xen/include/public/hvm/dm_op.h | 32 +++++++++-------
6 files changed, 69 insertions(+), 37 deletions(-)
diff --git a/tools/libs/devicemodel/core.c b/tools/libs/devicemodel/core.c
index 23924e9a38..f76e3d305e 100644
--- a/tools/libs/devicemodel/core.c
+++ b/tools/libs/devicemodel/core.c
@@ -204,6 +204,14 @@ 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 7629c35df7..08cb0d4374 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 96b0d13f2f..ce18754442 100644
--- a/xen/arch/x86/hvm/dm.c
+++ b/xen/arch/x86/hvm/dm.c
@@ -420,16 +420,19 @@ 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 d5f0e24b98..ce53d883e9 100644
--- a/xen/arch/x86/hvm/ioreq.c
+++ b/xen/arch/x86/hvm/ioreq.c
@@ -350,6 +350,9 @@ 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)
{
@@ -372,7 +375,7 @@ 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->target;
@@ -424,7 +427,7 @@ 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);
@@ -451,7 +454,7 @@ 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);
@@ -462,14 +465,13 @@ 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 )
@@ -602,13 +604,14 @@ 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;
+ s->bufioreq_handling = bufioreq_handling;
- rc = hvm_ioreq_server_map_pages(
- s, bufioreq_handling != HVM_IOREQSRV_BUFIOREQ_OFF);
- if ( rc )
- goto fail_map;
+ if ( id == DEFAULT_IOSERVID )
+ {
+ rc = hvm_ioreq_server_map_pages(s);
+ if ( rc )
+ goto fail_map;
+ }
for_each_vcpu ( d, v )
{
@@ -772,12 +775,23 @@ int hvm_get_ioreq_server_info(struct domain *d, ioservid_t id,
if ( s->emulator != current->domain )
goto out;
- *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;
@@ -1226,7 +1240,8 @@ 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 9b73e80777..f6db8586c5 100644
--- a/xen/include/asm-x86/hvm/domain.h
+++ b/xen/include/asm-x86/hvm/domain.h
@@ -66,7 +66,7 @@ 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 04c6324397..9823726d79 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.xenproject.org
https://lists.xenproject.org/mailman/listinfo/xen-devel
^ permalink raw reply related [flat|nested] 30+ messages in thread* [PATCH v18 05/11] x86/mm: add HYPERVISOR_memory_op to acquire guest resources
2018-03-22 11:55 [PATCH v18 00/11] x86: guest resource mapping Paul Durrant
` (3 preceding siblings ...)
2018-03-22 11:55 ` [PATCH v18 04/11] x86/hvm/ioreq: defer mapping gfns until they are actually requested Paul Durrant
@ 2018-03-22 11:55 ` Paul Durrant
2018-03-26 11:41 ` Jan Beulich
2018-03-22 11:55 ` [PATCH v18 06/11] x86/hvm/ioreq: add a new mappable resource type Paul Durrant
` (5 subsequent siblings)
10 siblings, 1 reply; 30+ messages in thread
From: Paul Durrant @ 2018-03-22 11:55 UTC (permalink / raw)
To: xen-devel
Cc: Stefano Stabellini, Wei Liu, George Dunlap, Andrew Cooper,
Ian Jackson, Tim Deegan, Julien Grall, 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.
Signed-off-by: Paul Durrant <paul.durrant@citrix.com>
Acked-by: Daniel De Graaf <dgdegra@tycho.nsa.gov>
---
Cc: Jan Beulich <jbeulich@suse.com>
Cc: George Dunlap <george.dunlap@eu.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: 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>
Cc: Julien Grall <julien.grall@arm.com>
v18:
- Allow the resource page owner to be specified by a returned flag.
- Drop Jan's R-b due to change.
v14:
- Addressed more comments from Jan.
v13:
- Use xen_pfn_t for mfn_list.
- Addressed further comments from Jan and Julien.
v12:
- Addressed more comments form Jan.
- Removed #ifdef CONFIG_X86 from common code and instead introduced a
stub set_foreign_p2m_entry() in asm-arm/p2m.h returning -EOPNOTSUPP.
- Restricted mechanism for querying implementation limit on nr_frames
and simplified compat code.
v11:
- Addressed more comments from Jan.
v9:
- Addressed more comments from Jan.
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().
---
tools/flask/policy/modules/xen.if | 4 +-
xen/arch/x86/mm/p2m.c | 3 +-
xen/common/compat/memory.c | 100 ++++++++++++++++++++++++++++++++++++
xen/common/memory.c | 93 +++++++++++++++++++++++++++++++++
xen/include/asm-arm/p2m.h | 10 ++++
xen/include/asm-x86/p2m.h | 3 ++
xen/include/public/memory.h | 55 +++++++++++++++++++-
xen/include/xlat.lst | 1 +
xen/include/xsm/dummy.h | 6 +++
xen/include/xsm/xsm.h | 6 +++
xen/xsm/dummy.c | 1 +
xen/xsm/flask/hooks.c | 6 +++
xen/xsm/flask/policy/access_vectors | 2 +
13 files changed, 286 insertions(+), 4 deletions(-)
diff --git a/tools/flask/policy/modules/xen.if b/tools/flask/policy/modules/xen.if
index 459880bb01..7aefd0061e 100644
--- a/tools/flask/policy/modules/xen.if
+++ b/tools/flask/policy/modules/xen.if
@@ -52,7 +52,8 @@ define(`create_domain_common', `
settime setdomainhandle getvcpucontext set_misc_info };
allow $1 $2:domain2 { set_cpuid settsc setscheduler setclaim
set_max_evtchn set_vnumainfo get_vnumainfo cacheflush
- psr_cmt_op psr_alloc soft_reset set_gnttab_limits };
+ psr_cmt_op psr_alloc soft_reset set_gnttab_limits
+ resource_map };
allow $1 $2:security check_context;
allow $1 $2:shadow enable;
allow $1 $2:mmu { map_read map_write adjust memorymap physmap pinpage mmuext_op updatemp };
@@ -152,6 +153,7 @@ define(`device_model', `
allow $1 $2_target:domain { getdomaininfo shutdown };
allow $1 $2_target:mmu { map_read map_write adjust physmap target_hack };
allow $1 $2_target:hvm { getparam setparam hvmctl dm };
+ allow $1 $2_target:domain2 resource_map;
')
# make_device_model(priv, dm_dom, hvm_dom)
diff --git a/xen/arch/x86/mm/p2m.c b/xen/arch/x86/mm/p2m.c
index 48e50fb5d8..55693eba59 100644
--- a/xen/arch/x86/mm/p2m.c
+++ b/xen/arch/x86/mm/p2m.c
@@ -1132,8 +1132,7 @@ 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..13fd64ddf5 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 +397,57 @@ int compat_memory_op(unsigned int cmd, XEN_GUEST_HANDLE_PARAM(void) compat)
}
#endif
+ case XENMEM_acquire_resource:
+ {
+ xen_pfn_t *xen_frame_list;
+ unsigned int max_nr_frames;
+
+ if ( copy_from_guest(&cmp.mar, compat, 1) )
+ return -EFAULT;
+
+ /*
+ * The number of frames handled is currently limited to a
+ * small number by the underlying implementation, so the
+ * scratch space should be sufficient for bouncing the
+ * frame addresses.
+ */
+ max_nr_frames = (COMPAT_ARG_XLAT_SIZE - sizeof(*nat.mar)) /
+ sizeof(*xen_frame_list);
+
+ if ( cmp.mar.nr_frames > max_nr_frames )
+ return -E2BIG;
+
+ if ( compat_handle_is_null(cmp.mar.frame_list) )
+ xen_frame_list = NULL;
+ else
+ {
+ xen_frame_list = (xen_pfn_t *)(nat.mar + 1);
+
+ if ( !compat_handle_okay(cmp.mar.frame_list,
+ cmp.mar.nr_frames) )
+ return -EFAULT;
+
+ for ( i = 0; i < cmp.mar.nr_frames; i++ )
+ {
+ compat_pfn_t frame;
+
+ if ( __copy_from_compat_offset(
+ &frame, cmp.mar.frame_list, i, 1) )
+ return -EFAULT;
+
+ xen_frame_list[i] = frame;
+ }
+ }
+
+#define XLAT_mem_acquire_resource_HNDL_frame_list(_d_, _s_) \
+ set_xen_guest_handle((_d_)->frame_list, xen_frame_list)
+
+ XLAT_mem_acquire_resource(nat.mar, &cmp.mar);
+
+#undef XLAT_mem_acquire_resource_HNDL_frame_list
+
+ break;
+ }
default:
return compat_arch_memory_op(cmd, compat);
}
@@ -535,6 +588,53 @@ int compat_memory_op(unsigned int cmd, XEN_GUEST_HANDLE_PARAM(void) compat)
rc = -EFAULT;
break;
+ case XENMEM_acquire_resource:
+ {
+ const xen_pfn_t *xen_frame_list = (xen_pfn_t *)(nat.mar + 1);
+ compat_pfn_t *compat_frame_list = (compat_pfn_t *)(nat.mar + 1);
+ DEFINE_XEN_GUEST_HANDLE(compat_mem_acquire_resource_t);
+
+ if ( compat_handle_is_null(cmp.mar.frame_list) )
+ {
+ if ( __copy_field_to_guest(
+ guest_handle_cast(compat,
+ compat_mem_acquire_resource_t),
+ &cmp.mar, nr_frames) )
+ return -EFAULT;
+ }
+ else
+ {
+ /*
+ * NOTE: the smaller compat array overwrites the native
+ * array.
+ */
+ BUILD_BUG_ON(sizeof(compat_pfn_t) > sizeof(xen_pfn_t));
+
+ for ( i = 0; i < cmp.mar.nr_frames; i++ )
+ {
+ compat_pfn_t frame = xen_frame_list[i];
+
+ if ( frame != xen_frame_list[i] )
+ return -ERANGE;
+
+ compat_frame_list[i] = frame;
+ }
+
+ if ( __copy_to_compat_offset(cmp.mar.frame_list, 0,
+ compat_frame_list,
+ cmp.mar.nr_frames) )
+ return -EFAULT;
+
+ if ( __copy_field_to_guest(
+ guest_handle_cast(compat,
+ compat_mem_acquire_resource_t),
+ &cmp.mar, flags) )
+ return -EFAULT;
+ }
+
+ break;
+ }
+
default:
domain_crash(current->domain);
split = 0;
diff --git a/xen/common/memory.c b/xen/common/memory.c
index 3ed71f8f74..d56cea1590 100644
--- a/xen/common/memory.c
+++ b/xen/common/memory.c
@@ -967,6 +967,94 @@ static long xatp_permission_check(struct domain *d, unsigned int space)
return xsm_add_to_physmap(XSM_TARGET, current->domain, d);
}
+static int acquire_resource(
+ XEN_GUEST_HANDLE_PARAM(xen_mem_acquire_resource_t) arg)
+{
+ struct domain *d, *currd = current->domain;
+ xen_mem_acquire_resource_t xmar;
+ /*
+ * The mfn_list and gfn_list (below) arrays are ok on stack for the
+ * moment since they are small, but if they need to grow in future
+ * use-cases then per-CPU arrays or heap allocations may be required.
+ */
+ xen_pfn_t mfn_list[2];
+ int rc;
+
+ if ( copy_from_guest(&xmar, arg, 1) )
+ return -EFAULT;
+
+ if ( xmar.flags != 0 )
+ return -EINVAL;
+
+ if ( guest_handle_is_null(xmar.frame_list) )
+ {
+ if ( xmar.nr_frames )
+ return -EINVAL;
+
+ xmar.nr_frames = ARRAY_SIZE(mfn_list);
+
+ if ( __copy_field_to_guest(arg, &xmar, nr_frames) )
+ return -EFAULT;
+
+ return 0;
+ }
+
+ if ( xmar.nr_frames > ARRAY_SIZE(mfn_list) )
+ return -E2BIG;
+
+ rc = rcu_lock_remote_domain_by_id(xmar.domid, &d);
+ if ( rc )
+ return rc;
+
+ rc = xsm_domain_resource_map(XSM_DM_PRIV, 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(xmar.frame_list, mfn_list, xmar.nr_frames) )
+ rc = -EFAULT;
+ }
+ else
+ {
+ xen_pfn_t gfn_list[ARRAY_SIZE(mfn_list)];
+ unsigned int i;
+
+ if ( copy_from_guest(gfn_list, xmar.frame_list, xmar.nr_frames) )
+ rc = -EFAULT;
+
+ for ( i = 0; !rc && i < xmar.nr_frames; i++ )
+ {
+ rc = set_foreign_p2m_entry(currd, gfn_list[i],
+ _mfn(mfn_list[i]));
+ if ( rc )
+ /*
+ * Make sure rc is -EIO for any iteration other than
+ * the first.
+ */
+ rc = i ? -EIO : rc;
+ }
+ }
+
+ if ( xmar.flags != 0 &&
+ __copy_field_to_guest(arg, &xmar, flags) )
+ rc = -EFAULT;
+
+ out:
+ rcu_unlock_domain(d);
+ return rc;
+}
+
long do_memory_op(unsigned long cmd, XEN_GUEST_HANDLE_PARAM(void) arg)
{
struct domain *d, *curr_d = current->domain;
@@ -1422,6 +1510,11 @@ long do_memory_op(unsigned long cmd, XEN_GUEST_HANDLE_PARAM(void) arg)
}
#endif
+ case XENMEM_acquire_resource:
+ rc = acquire_resource(
+ guest_handle_cast(arg, xen_mem_acquire_resource_t));
+ break;
+
default:
rc = arch_memory_op(cmd, arg);
break;
diff --git a/xen/include/asm-arm/p2m.h b/xen/include/asm-arm/p2m.h
index 45ef2cd58b..4d036b6112 100644
--- a/xen/include/asm-arm/p2m.h
+++ b/xen/include/asm-arm/p2m.h
@@ -344,6 +344,16 @@ static inline gfn_t gfn_next_boundary(gfn_t gfn, unsigned int order)
return gfn_add(gfn, 1UL << order);
}
+static inline int set_foreign_p2m_entry(struct domain *d, unsigned long gfn,
+ mfn_t mfn)
+{
+ /*
+ * NOTE: If this is implemented then proper reference counting of
+ * foreign entries will need to be impmemented.
+ */
+ return -EOPNOTSUPP;
+}
+
#endif /* _XEN_P2M_H */
/*
diff --git a/xen/include/asm-x86/p2m.h b/xen/include/asm-x86/p2m.h
index 2e7aa8fc79..c555ccf0d9 100644
--- a/xen/include/asm-x86/p2m.h
+++ b/xen/include/asm-x86/p2m.h
@@ -621,6 +621,9 @@ 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..53d258fd92 100644
--- a/xen/include/public/memory.h
+++ b/xen/include/public/memory.h
@@ -599,6 +599,59 @@ 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/OUT - As an IN parameter number of frames of the resource
+ * to be mapped. However, if the specified value is 0 and
+ * frame_list is NULL then this field will be set to the
+ * maximum value supported by the implementation on return.
+ */
+ uint32_t nr_frames;
+ /*
+ * OUT - Must be zero on entry. On return this may contain a bitwise
+ * OR of the following values.
+ */
+ uint32_t flags;
+
+ /* The resource pages have been assigned to the tools domain */
+#define _XENMEM_resource_flag_tools_owned 0
+#define XENMEM_resource_flag_tools_owned (1u << _XENMEM_resource_flag_tools_owned)
+
+ /*
+ * IN - the index of the initial frame to be mapped. This parameter
+ * is ignored if nr_frames is 0.
+ */
+ uint64_aligned_t frame;
+ /*
+ * IN/OUT - If the tools domain is PV then, upon return, frame_list
+ * will be populated with the MFNs of the resource.
+ * If the tools domain is HVM then it is expected that, on
+ * entry, frame_list will be populated with a list of GFNs
+ * that will be mapped to the MFNs of the resource.
+ * If -EIO is returned then the frame_list has only been
+ * partially mapped and it is up to the caller to unmap all
+ * the GFNs.
+ * This parameter may be NULL if nr_frames is 0.
+ */
+ XEN_GUEST_HANDLE(xen_pfn_t) frame_list;
+};
+typedef struct xen_mem_acquire_resource xen_mem_acquire_resource_t;
+DEFINE_XEN_GUEST_HANDLE(xen_mem_acquire_resource_t);
+
#endif /* defined(__XEN__) || defined(__XEN_TOOLS__) */
/*
@@ -650,7 +703,7 @@ 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 3690b97d5d..a727ab042e 100644
--- a/xen/include/xlat.lst
+++ b/xen/include/xlat.lst
@@ -86,6 +86,7 @@
! 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
diff --git a/xen/include/xsm/dummy.h b/xen/include/xsm/dummy.h
index 466bbcbde8..ff6b2dbf39 100644
--- a/xen/include/xsm/dummy.h
+++ b/xen/include/xsm/dummy.h
@@ -740,3 +740,9 @@ static XSM_INLINE int xsm_xen_version (XSM_DEFAULT_ARG uint32_t op)
return xsm_default_action(XSM_PRIV, current->domain, NULL);
}
}
+
+static XSM_INLINE int xsm_domain_resource_map(XSM_DEFAULT_ARG struct domain *d)
+{
+ XSM_ASSERT_ACTION(XSM_DM_PRIV);
+ return xsm_default_action(action, current->domain, d);
+}
diff --git a/xen/include/xsm/xsm.h b/xen/include/xsm/xsm.h
index e3912bcc9d..f0c6fc7e29 100644
--- a/xen/include/xsm/xsm.h
+++ b/xen/include/xsm/xsm.h
@@ -180,6 +180,7 @@ struct xsm_operations {
int (*dm_op) (struct domain *d);
#endif
int (*xen_version) (uint32_t cmd);
+ int (*domain_resource_map) (struct domain *d);
};
#ifdef CONFIG_XSM
@@ -692,6 +693,11 @@ static inline int xsm_xen_version (xsm_default_t def, uint32_t op)
return xsm_ops->xen_version(op);
}
+static inline int xsm_domain_resource_map(xsm_default_t def, struct domain *d)
+{
+ return xsm_ops->domain_resource_map(d);
+}
+
#endif /* XSM_NO_WRAPPERS */
#ifdef CONFIG_MULTIBOOT
diff --git a/xen/xsm/dummy.c b/xen/xsm/dummy.c
index 479b103614..6e751199ee 100644
--- a/xen/xsm/dummy.c
+++ b/xen/xsm/dummy.c
@@ -157,4 +157,5 @@ void __init xsm_fixup_ops (struct xsm_operations *ops)
set_to_dummy_if_null(ops, dm_op);
#endif
set_to_dummy_if_null(ops, xen_version);
+ set_to_dummy_if_null(ops, domain_resource_map);
}
diff --git a/xen/xsm/flask/hooks.c b/xen/xsm/flask/hooks.c
index 1802d8dfe6..033caa5328 100644
--- a/xen/xsm/flask/hooks.c
+++ b/xen/xsm/flask/hooks.c
@@ -1712,6 +1712,11 @@ static int flask_xen_version (uint32_t op)
}
}
+static int flask_domain_resource_map(struct domain *d)
+{
+ return current_has_perm(d, SECCLASS_DOMAIN2, DOMAIN2__RESOURCE_MAP);
+}
+
long do_flask_op(XEN_GUEST_HANDLE_PARAM(xsm_op_t) u_flask_op);
int compat_flask_op(XEN_GUEST_HANDLE_PARAM(xsm_op_t) u_flask_op);
@@ -1845,6 +1850,7 @@ static struct xsm_operations flask_ops = {
.dm_op = flask_dm_op,
#endif
.xen_version = flask_xen_version,
+ .domain_resource_map = flask_domain_resource_map,
};
void __init flask_init(const void *policy_buffer, size_t policy_size)
diff --git a/xen/xsm/flask/policy/access_vectors b/xen/xsm/flask/policy/access_vectors
index 89b99966bb..3ce2a51706 100644
--- a/xen/xsm/flask/policy/access_vectors
+++ b/xen/xsm/flask/policy/access_vectors
@@ -250,6 +250,8 @@ class domain2
psr_alloc
# XEN_DOMCTL_set_gnttab_limits
set_gnttab_limits
+# XENMEM_resource_map
+ resource_map
}
# Similar to class domain, but primarily contains domctls related to HVM domains
--
2.11.0
_______________________________________________
Xen-devel mailing list
Xen-devel@lists.xenproject.org
https://lists.xenproject.org/mailman/listinfo/xen-devel
^ permalink raw reply related [flat|nested] 30+ messages in thread* Re: [PATCH v18 05/11] x86/mm: add HYPERVISOR_memory_op to acquire guest resources
2018-03-22 11:55 ` [PATCH v18 05/11] x86/mm: add HYPERVISOR_memory_op to acquire guest resources Paul Durrant
@ 2018-03-26 11:41 ` Jan Beulich
2018-03-26 12:51 ` Jan Beulich
2018-03-29 9:53 ` Paul Durrant
0 siblings, 2 replies; 30+ messages in thread
From: Jan Beulich @ 2018-03-26 11:41 UTC (permalink / raw)
To: Paul Durrant
Cc: Stefano Stabellini, Wei Liu, George Dunlap, Andrew Cooper,
IanJackson, TimDeegan, Julien Grall, xen-devel
>>> On 22.03.18 at 12:55, <paul.durrant@citrix.com> wrote:
> --- a/xen/common/memory.c
> +++ b/xen/common/memory.c
> @@ -967,6 +967,94 @@ static long xatp_permission_check(struct domain *d, unsigned int space)
> return xsm_add_to_physmap(XSM_TARGET, current->domain, d);
> }
>
> +static int acquire_resource(
> + XEN_GUEST_HANDLE_PARAM(xen_mem_acquire_resource_t) arg)
> +{
> + struct domain *d, *currd = current->domain;
> + xen_mem_acquire_resource_t xmar;
> + /*
> + * The mfn_list and gfn_list (below) arrays are ok on stack for the
> + * moment since they are small, but if they need to grow in future
> + * use-cases then per-CPU arrays or heap allocations may be required.
> + */
> + xen_pfn_t mfn_list[2];
> + int rc;
> +
> + if ( copy_from_guest(&xmar, arg, 1) )
> + return -EFAULT;
> +
> + if ( xmar.flags != 0 )
> + return -EINVAL;
> +
> + if ( guest_handle_is_null(xmar.frame_list) )
> + {
> + if ( xmar.nr_frames )
> + return -EINVAL;
> +
> + xmar.nr_frames = ARRAY_SIZE(mfn_list);
> +
> + if ( __copy_field_to_guest(arg, &xmar, nr_frames) )
> + return -EFAULT;
> +
> + return 0;
> + }
> +
> + if ( xmar.nr_frames > ARRAY_SIZE(mfn_list) )
> + return -E2BIG;
> +
> + rc = rcu_lock_remote_domain_by_id(xmar.domid, &d);
> + if ( rc )
> + return rc;
> +
> + rc = xsm_domain_resource_map(XSM_DM_PRIV, 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(xmar.frame_list, mfn_list, xmar.nr_frames) )
> + rc = -EFAULT;
> + }
> + else
> + {
> + xen_pfn_t gfn_list[ARRAY_SIZE(mfn_list)];
> + unsigned int i;
> +
> + if ( copy_from_guest(gfn_list, xmar.frame_list, xmar.nr_frames) )
> + rc = -EFAULT;
> +
> + for ( i = 0; !rc && i < xmar.nr_frames; i++ )
> + {
> + rc = set_foreign_p2m_entry(currd, gfn_list[i],
> + _mfn(mfn_list[i]));
> + if ( rc )
> + /*
> + * Make sure rc is -EIO for any iteration other than
> + * the first.
> + */
> + rc = i ? -EIO : rc;
Perhaps easier as
/*
* Make sure rc is -EIO for any iteration other than
* the first.
*/
if ( rc && i )
rc = -EIO;
? Looks like the comment could then also be a single line one.
> + }
> + }
> +
> + if ( xmar.flags != 0 &&
> + __copy_field_to_guest(arg, &xmar, flags) )
> + rc = -EFAULT;
> +
> + out:
> + rcu_unlock_domain(d);
> + return rc;
> +}
Blank line please ahead of main "return".
> --- a/xen/include/public/memory.h
> +++ b/xen/include/public/memory.h
> @@ -599,6 +599,59 @@ 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/OUT - As an IN parameter number of frames of the resource
> + * to be mapped. However, if the specified value is 0 and
> + * frame_list is NULL then this field will be set to the
> + * maximum value supported by the implementation on return.
> + */
> + uint32_t nr_frames;
> + /*
> + * OUT - Must be zero on entry. On return this may contain a bitwise
> + * OR of the following values.
> + */
> + uint32_t flags;
> +
> + /* The resource pages have been assigned to the tools domain */
> +#define _XENMEM_resource_flag_tools_owned 0
> +#define XENMEM_resource_flag_tools_owned (1u << _XENMEM_resource_flag_tools_owned)
Is "tools" really an appropriate (and "flag" a necessary) name
component here? How about e.g. XENMEM_res_acq_caller_owned?
> --- a/xen/include/xlat.lst
> +++ b/xen/include/xlat.lst
> @@ -86,6 +86,7 @@
> ! memory_map memory.h
> ! memory_reservation memory.h
> ! mem_access_op memory.h
> +! mem_acquire_resource memory.h
Why ! ? The layout doesn't appear to differ between native and
compat. Or wait, the handle does, but why is that not
XEN_GUEST_HANDLE_64()? (I've skipped the compat layer code
in this round of review for that reason.)
Jan
_______________________________________________
Xen-devel mailing list
Xen-devel@lists.xenproject.org
https://lists.xenproject.org/mailman/listinfo/xen-devel
^ permalink raw reply [flat|nested] 30+ messages in thread* Re: [PATCH v18 05/11] x86/mm: add HYPERVISOR_memory_op to acquire guest resources
2018-03-26 11:41 ` Jan Beulich
@ 2018-03-26 12:51 ` Jan Beulich
2018-03-29 9:35 ` Paul Durrant
2018-03-29 9:53 ` Paul Durrant
1 sibling, 1 reply; 30+ messages in thread
From: Jan Beulich @ 2018-03-26 12:51 UTC (permalink / raw)
To: Paul Durrant
Cc: Stefano Stabellini, Wei Liu, George Dunlap, Andrew Cooper,
IanJackson, TimDeegan, Julien Grall, xen-devel
>>> On 26.03.18 at 13:41, <JBeulich@suse.com> wrote:
>>>> On 22.03.18 at 12:55, <paul.durrant@citrix.com> wrote:
>> --- a/xen/include/public/memory.h
>> +++ b/xen/include/public/memory.h
>> @@ -599,6 +599,59 @@ 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/OUT - As an IN parameter number of frames of the resource
>> + * to be mapped. However, if the specified value is 0 and
>> + * frame_list is NULL then this field will be set to the
>> + * maximum value supported by the implementation on return.
>> + */
>> + uint32_t nr_frames;
>> + /*
>> + * OUT - Must be zero on entry. On return this may contain a bitwise
>> + * OR of the following values.
>> + */
>> + uint32_t flags;
>> +
>> + /* The resource pages have been assigned to the tools domain */
>> +#define _XENMEM_resource_flag_tools_owned 0
>> +#define XENMEM_resource_flag_tools_owned (1u <<
> _XENMEM_resource_flag_tools_owned)
>
> Is "tools" really an appropriate (and "flag" a necessary) name
> component here? How about e.g. XENMEM_res_acq_caller_owned?
Or maybe XENMEM_rsrc_acq_caller_owned.
Jan
_______________________________________________
Xen-devel mailing list
Xen-devel@lists.xenproject.org
https://lists.xenproject.org/mailman/listinfo/xen-devel
^ permalink raw reply [flat|nested] 30+ messages in thread* Re: [PATCH v18 05/11] x86/mm: add HYPERVISOR_memory_op to acquire guest resources
2018-03-26 12:51 ` Jan Beulich
@ 2018-03-29 9:35 ` Paul Durrant
0 siblings, 0 replies; 30+ messages in thread
From: Paul Durrant @ 2018-03-29 9:35 UTC (permalink / raw)
To: 'Jan Beulich'
Cc: Stefano Stabellini, Wei Liu, Andrew Cooper, Tim (Xen.org),
George Dunlap, Julien Grall, xen-devel, Ian Jackson
> -----Original Message-----
> From: Jan Beulich [mailto:JBeulich@suse.com]
> Sent: 26 March 2018 13:51
> To: Paul Durrant <Paul.Durrant@citrix.com>
> Cc: Julien Grall <julien.grall@arm.com>; 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;
> Tim (Xen.org) <tim@xen.org>
> Subject: Re: [PATCH v18 05/11] x86/mm: add HYPERVISOR_memory_op to
> acquire guest resources
>
> >>> On 26.03.18 at 13:41, <JBeulich@suse.com> wrote:
> >>>> On 22.03.18 at 12:55, <paul.durrant@citrix.com> wrote:
> >> --- a/xen/include/public/memory.h
> >> +++ b/xen/include/public/memory.h
> >> @@ -599,6 +599,59 @@ 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/OUT - As an IN parameter number of frames of the resource
> >> + * to be mapped. However, if the specified value is 0 and
> >> + * frame_list is NULL then this field will be set to the
> >> + * maximum value supported by the implementation on return.
> >> + */
> >> + uint32_t nr_frames;
> >> + /*
> >> + * OUT - Must be zero on entry. On return this may contain a bitwise
> >> + * OR of the following values.
> >> + */
> >> + uint32_t flags;
> >> +
> >> + /* The resource pages have been assigned to the tools domain */
> >> +#define _XENMEM_resource_flag_tools_owned 0
> >> +#define XENMEM_resource_flag_tools_owned (1u <<
> > _XENMEM_resource_flag_tools_owned)
> >
> > Is "tools" really an appropriate (and "flag" a necessary) name
> > component here? How about e.g. XENMEM_res_acq_caller_owned?
>
> Or maybe XENMEM_rsrc_acq_caller_owned.
>
Yes, I'm fine with that. I'll make the change.
Paul
> Jan
_______________________________________________
Xen-devel mailing list
Xen-devel@lists.xenproject.org
https://lists.xenproject.org/mailman/listinfo/xen-devel
^ permalink raw reply [flat|nested] 30+ messages in thread
* Re: [PATCH v18 05/11] x86/mm: add HYPERVISOR_memory_op to acquire guest resources
2018-03-26 11:41 ` Jan Beulich
2018-03-26 12:51 ` Jan Beulich
@ 2018-03-29 9:53 ` Paul Durrant
2018-03-29 12:28 ` Jan Beulich
1 sibling, 1 reply; 30+ messages in thread
From: Paul Durrant @ 2018-03-29 9:53 UTC (permalink / raw)
To: 'Jan Beulich'
Cc: Stefano Stabellini, Wei Liu, Andrew Cooper, Tim (Xen.org),
George Dunlap, Julien Grall, xen-devel, Ian Jackson
> -----Original Message-----
> From: Jan Beulich [mailto:JBeulich@suse.com]
> Sent: 26 March 2018 12:41
> To: Paul Durrant <Paul.Durrant@citrix.com>
> Cc: Julien Grall <julien.grall@arm.com>; 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 v18 05/11] x86/mm: add HYPERVISOR_memory_op to
> acquire guest resources
>
> >>> On 22.03.18 at 12:55, <paul.durrant@citrix.com> wrote:
> > --- a/xen/common/memory.c
> > +++ b/xen/common/memory.c
> > @@ -967,6 +967,94 @@ static long xatp_permission_check(struct domain
> *d, unsigned int space)
> > return xsm_add_to_physmap(XSM_TARGET, current->domain, d);
> > }
> >
> > +static int acquire_resource(
> > + XEN_GUEST_HANDLE_PARAM(xen_mem_acquire_resource_t) arg)
> > +{
> > + struct domain *d, *currd = current->domain;
> > + xen_mem_acquire_resource_t xmar;
> > + /*
> > + * The mfn_list and gfn_list (below) arrays are ok on stack for the
> > + * moment since they are small, but if they need to grow in future
> > + * use-cases then per-CPU arrays or heap allocations may be required.
> > + */
> > + xen_pfn_t mfn_list[2];
> > + int rc;
> > +
> > + if ( copy_from_guest(&xmar, arg, 1) )
> > + return -EFAULT;
> > +
> > + if ( xmar.flags != 0 )
> > + return -EINVAL;
> > +
> > + if ( guest_handle_is_null(xmar.frame_list) )
> > + {
> > + if ( xmar.nr_frames )
> > + return -EINVAL;
> > +
> > + xmar.nr_frames = ARRAY_SIZE(mfn_list);
> > +
> > + if ( __copy_field_to_guest(arg, &xmar, nr_frames) )
> > + return -EFAULT;
> > +
> > + return 0;
> > + }
> > +
> > + if ( xmar.nr_frames > ARRAY_SIZE(mfn_list) )
> > + return -E2BIG;
> > +
> > + rc = rcu_lock_remote_domain_by_id(xmar.domid, &d);
> > + if ( rc )
> > + return rc;
> > +
> > + rc = xsm_domain_resource_map(XSM_DM_PRIV, 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(xmar.frame_list, mfn_list, xmar.nr_frames) )
> > + rc = -EFAULT;
> > + }
> > + else
> > + {
> > + xen_pfn_t gfn_list[ARRAY_SIZE(mfn_list)];
> > + unsigned int i;
> > +
> > + if ( copy_from_guest(gfn_list, xmar.frame_list, xmar.nr_frames) )
> > + rc = -EFAULT;
> > +
> > + for ( i = 0; !rc && i < xmar.nr_frames; i++ )
> > + {
> > + rc = set_foreign_p2m_entry(currd, gfn_list[i],
> > + _mfn(mfn_list[i]));
> > + if ( rc )
> > + /*
> > + * Make sure rc is -EIO for any iteration other than
> > + * the first.
> > + */
> > + rc = i ? -EIO : rc;
>
> Perhaps easier as
>
> /*
> * Make sure rc is -EIO for any iteration other than
> * the first.
> */
> if ( rc && i )
> rc = -EIO;
>
> ? Looks like the comment could then also be a single line one.
>
Ok.
> > + }
> > + }
> > +
> > + if ( xmar.flags != 0 &&
> > + __copy_field_to_guest(arg, &xmar, flags) )
> > + rc = -EFAULT;
> > +
> > + out:
> > + rcu_unlock_domain(d);
> > + return rc;
> > +}
>
> Blank line please ahead of main "return".
>
Ok.
> > --- a/xen/include/public/memory.h
> > +++ b/xen/include/public/memory.h
> > @@ -599,6 +599,59 @@ 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/OUT - As an IN parameter number of frames of the resource
> > + * to be mapped. However, if the specified value is 0 and
> > + * frame_list is NULL then this field will be set to the
> > + * maximum value supported by the implementation on return.
> > + */
> > + uint32_t nr_frames;
> > + /*
> > + * OUT - Must be zero on entry. On return this may contain a bitwise
> > + * OR of the following values.
> > + */
> > + uint32_t flags;
> > +
> > + /* The resource pages have been assigned to the tools domain */
> > +#define _XENMEM_resource_flag_tools_owned 0
> > +#define XENMEM_resource_flag_tools_owned (1u <<
> _XENMEM_resource_flag_tools_owned)
>
> Is "tools" really an appropriate (and "flag" a necessary) name
> component here? How about e.g. XENMEM_res_acq_caller_owned?
>
> > --- a/xen/include/xlat.lst
> > +++ b/xen/include/xlat.lst
> > @@ -86,6 +86,7 @@
> > ! memory_map memory.h
> > ! memory_reservation memory.h
> > ! mem_access_op memory.h
> > +! mem_acquire_resource memory.h
>
> Why ! ? The layout doesn't appear to differ between native and
> compat. Or wait, the handle does, but why is that not
> XEN_GUEST_HANDLE_64()? (I've skipped the compat layer code
> in this round of review for that reason.)
>
It's been XEN_GUEST_HANDLE throughout all but the earliest revisions of the patch and I have not modified the compat code massively since you gave your R-b anyway... the only thing that changed was copying back the new flags value.
Paul
> Jan
_______________________________________________
Xen-devel mailing list
Xen-devel@lists.xenproject.org
https://lists.xenproject.org/mailman/listinfo/xen-devel
^ permalink raw reply [flat|nested] 30+ messages in thread* Re: [PATCH v18 05/11] x86/mm: add HYPERVISOR_memory_op to acquire guest resources
2018-03-29 9:53 ` Paul Durrant
@ 2018-03-29 12:28 ` Jan Beulich
2018-03-29 12:43 ` Paul Durrant
0 siblings, 1 reply; 30+ messages in thread
From: Jan Beulich @ 2018-03-29 12:28 UTC (permalink / raw)
To: Paul Durrant
Cc: StefanoStabellini, Wei Liu, Andrew Cooper, Tim (Xen.org),
George Dunlap, Julien Grall, xen-devel, Ian Jackson
>>> On 29.03.18 at 11:53, <Paul.Durrant@citrix.com> wrote:
>> From: Jan Beulich [mailto:JBeulich@suse.com]
>> Sent: 26 March 2018 12:41
>>
>> >>> On 22.03.18 at 12:55, <paul.durrant@citrix.com> wrote:
>> > --- a/xen/include/xlat.lst
>> > +++ b/xen/include/xlat.lst
>> > @@ -86,6 +86,7 @@
>> > ! memory_map memory.h
>> > ! memory_reservation memory.h
>> > ! mem_access_op memory.h
>> > +! mem_acquire_resource memory.h
>>
>> Why ! ? The layout doesn't appear to differ between native and
>> compat. Or wait, the handle does, but why is that not
>> XEN_GUEST_HANDLE_64()? (I've skipped the compat layer code
>> in this round of review for that reason.)
>
> It's been XEN_GUEST_HANDLE throughout all but the earliest revisions of the
> patch and I have not modified the compat code massively since you gave your
> R-b anyway... the only thing that changed was copying back the new flags
> value.
Granted I could/should have noticed this earlier, but being able to
get away without compat translation would certainly be a win, and
we have that option since this is a tools-only interface.
Jan
_______________________________________________
Xen-devel mailing list
Xen-devel@lists.xenproject.org
https://lists.xenproject.org/mailman/listinfo/xen-devel
^ permalink raw reply [flat|nested] 30+ messages in thread
* Re: [PATCH v18 05/11] x86/mm: add HYPERVISOR_memory_op to acquire guest resources
2018-03-29 12:28 ` Jan Beulich
@ 2018-03-29 12:43 ` Paul Durrant
2018-03-29 13:17 ` Paul Durrant
0 siblings, 1 reply; 30+ messages in thread
From: Paul Durrant @ 2018-03-29 12:43 UTC (permalink / raw)
To: 'Jan Beulich'
Cc: StefanoStabellini, Wei Liu, Andrew Cooper, Tim (Xen.org),
George Dunlap, Julien Grall, xen-devel, Ian Jackson
> -----Original Message-----
> From: Jan Beulich [mailto:JBeulich@suse.com]
> Sent: 29 March 2018 13:29
> To: Paul Durrant <Paul.Durrant@citrix.com>
> Cc: Julien Grall <julien.grall@arm.com>; Andrew Cooper
> <Andrew.Cooper3@citrix.com>; George Dunlap
> <George.Dunlap@citrix.com>; Ian Jackson <Ian.Jackson@citrix.com>; Wei Liu
> <wei.liu2@citrix.com>; StefanoStabellini <sstabellini@kernel.org>; xen-
> devel@lists.xenproject.org; Konrad Rzeszutek Wilk
> <konrad.wilk@oracle.com>; Tim (Xen.org) <tim@xen.org>
> Subject: RE: [PATCH v18 05/11] x86/mm: add HYPERVISOR_memory_op to
> acquire guest resources
>
> >>> On 29.03.18 at 11:53, <Paul.Durrant@citrix.com> wrote:
> >> From: Jan Beulich [mailto:JBeulich@suse.com]
> >> Sent: 26 March 2018 12:41
> >>
> >> >>> On 22.03.18 at 12:55, <paul.durrant@citrix.com> wrote:
> >> > --- a/xen/include/xlat.lst
> >> > +++ b/xen/include/xlat.lst
> >> > @@ -86,6 +86,7 @@
> >> > ! memory_map memory.h
> >> > ! memory_reservation memory.h
> >> > ! mem_access_op memory.h
> >> > +! mem_acquire_resource memory.h
> >>
> >> Why ! ? The layout doesn't appear to differ between native and
> >> compat. Or wait, the handle does, but why is that not
> >> XEN_GUEST_HANDLE_64()? (I've skipped the compat layer code
> >> in this round of review for that reason.)
> >
> > It's been XEN_GUEST_HANDLE throughout all but the earliest revisions of
> the
> > patch and I have not modified the compat code massively since you gave
> your
> > R-b anyway... the only thing that changed was copying back the new flags
> > value.
>
> Granted I could/should have noticed this earlier, but being able to
> get away without compat translation would certainly be a win, and
> we have that option since this is a tools-only interface.
>
Ok. I'll see if I can get this done today then.
Paul
> Jan
_______________________________________________
Xen-devel mailing list
Xen-devel@lists.xenproject.org
https://lists.xenproject.org/mailman/listinfo/xen-devel
^ permalink raw reply [flat|nested] 30+ messages in thread
* Re: [PATCH v18 05/11] x86/mm: add HYPERVISOR_memory_op to acquire guest resources
2018-03-29 12:43 ` Paul Durrant
@ 2018-03-29 13:17 ` Paul Durrant
2018-03-29 14:25 ` Jan Beulich
0 siblings, 1 reply; 30+ messages in thread
From: Paul Durrant @ 2018-03-29 13:17 UTC (permalink / raw)
To: Paul Durrant, 'Jan Beulich'
Cc: StefanoStabellini, Wei Liu, Andrew Cooper, Tim (Xen.org),
George Dunlap, Julien Grall, Ian Jackson, xen-devel
> -----Original Message-----
> From: Xen-devel [mailto:xen-devel-bounces@lists.xenproject.org] On Behalf
> Of Paul Durrant
> Sent: 29 March 2018 13:43
> To: 'Jan Beulich' <JBeulich@suse.com>
> Cc: StefanoStabellini <sstabellini@kernel.org>; Wei Liu
> <wei.liu2@citrix.com>; Andrew Cooper <Andrew.Cooper3@citrix.com>; Tim
> (Xen.org) <tim@xen.org>; George Dunlap <George.Dunlap@citrix.com>;
> Julien Grall <julien.grall@arm.com>; xen-devel@lists.xenproject.org; Ian
> Jackson <Ian.Jackson@citrix.com>
> Subject: Re: [Xen-devel] [PATCH v18 05/11] x86/mm: add
> HYPERVISOR_memory_op to acquire guest resources
>
> > -----Original Message-----
> > From: Jan Beulich [mailto:JBeulich@suse.com]
> > Sent: 29 March 2018 13:29
> > To: Paul Durrant <Paul.Durrant@citrix.com>
> > Cc: Julien Grall <julien.grall@arm.com>; Andrew Cooper
> > <Andrew.Cooper3@citrix.com>; George Dunlap
> > <George.Dunlap@citrix.com>; Ian Jackson <Ian.Jackson@citrix.com>; Wei
> Liu
> > <wei.liu2@citrix.com>; StefanoStabellini <sstabellini@kernel.org>; xen-
> > devel@lists.xenproject.org; Konrad Rzeszutek Wilk
> > <konrad.wilk@oracle.com>; Tim (Xen.org) <tim@xen.org>
> > Subject: RE: [PATCH v18 05/11] x86/mm: add HYPERVISOR_memory_op to
> > acquire guest resources
> >
> > >>> On 29.03.18 at 11:53, <Paul.Durrant@citrix.com> wrote:
> > >> From: Jan Beulich [mailto:JBeulich@suse.com]
> > >> Sent: 26 March 2018 12:41
> > >>
> > >> >>> On 22.03.18 at 12:55, <paul.durrant@citrix.com> wrote:
> > >> > --- a/xen/include/xlat.lst
> > >> > +++ b/xen/include/xlat.lst
> > >> > @@ -86,6 +86,7 @@
> > >> > ! memory_map memory.h
> > >> > ! memory_reservation memory.h
> > >> > ! mem_access_op memory.h
> > >> > +! mem_acquire_resource memory.h
> > >>
> > >> Why ! ? The layout doesn't appear to differ between native and
> > >> compat. Or wait, the handle does, but why is that not
> > >> XEN_GUEST_HANDLE_64()? (I've skipped the compat layer code
> > >> in this round of review for that reason.)
> > >
> > > It's been XEN_GUEST_HANDLE throughout all but the earliest revisions of
> > the
> > > patch and I have not modified the compat code massively since you gave
> > your
> > > R-b anyway... the only thing that changed was copying back the new flags
> > > value.
> >
> > Granted I could/should have noticed this earlier, but being able to
> > get away without compat translation would certainly be a win, and
> > we have that option since this is a tools-only interface.
> >
>
> Ok. I'll see if I can get this done today then.
>
> Paul
Actually, I'm getting confused by all this... The handle is for an array of xen_pfn_t, which means they are going to be 32-bits wide for a 32-bit tools domain. Doesn't this mean I'm going to need compat code to iterate and translate the array anyway?
Paul
>
> > Jan
>
>
> _______________________________________________
> Xen-devel mailing list
> Xen-devel@lists.xenproject.org
> https://lists.xenproject.org/mailman/listinfo/xen-devel
_______________________________________________
Xen-devel mailing list
Xen-devel@lists.xenproject.org
https://lists.xenproject.org/mailman/listinfo/xen-devel
^ permalink raw reply [flat|nested] 30+ messages in thread
* Re: [PATCH v18 05/11] x86/mm: add HYPERVISOR_memory_op to acquire guest resources
2018-03-29 13:17 ` Paul Durrant
@ 2018-03-29 14:25 ` Jan Beulich
2018-03-29 14:38 ` Paul Durrant
0 siblings, 1 reply; 30+ messages in thread
From: Jan Beulich @ 2018-03-29 14:25 UTC (permalink / raw)
To: Paul Durrant
Cc: StefanoStabellini, Wei Liu, Andrew Cooper, Tim (Xen.org),
George Dunlap, Julien Grall, xen-devel, Ian Jackson
>>> On 29.03.18 at 15:17, <Paul.Durrant@citrix.com> wrote:
>> -----Original Message-----
>> From: Xen-devel [mailto:xen-devel-bounces@lists.xenproject.org] On Behalf
>> Of Paul Durrant
>> Sent: 29 March 2018 13:43
>> To: 'Jan Beulich' <JBeulich@suse.com>
>> Cc: StefanoStabellini <sstabellini@kernel.org>; Wei Liu
>> <wei.liu2@citrix.com>; Andrew Cooper <Andrew.Cooper3@citrix.com>; Tim
>> (Xen.org) <tim@xen.org>; George Dunlap <George.Dunlap@citrix.com>;
>> Julien Grall <julien.grall@arm.com>; xen-devel@lists.xenproject.org; Ian
>> Jackson <Ian.Jackson@citrix.com>
>> Subject: Re: [Xen-devel] [PATCH v18 05/11] x86/mm: add
>> HYPERVISOR_memory_op to acquire guest resources
>>
>> > -----Original Message-----
>> > From: Jan Beulich [mailto:JBeulich@suse.com]
>> > Sent: 29 March 2018 13:29
>> > To: Paul Durrant <Paul.Durrant@citrix.com>
>> > Cc: Julien Grall <julien.grall@arm.com>; Andrew Cooper
>> > <Andrew.Cooper3@citrix.com>; George Dunlap
>> > <George.Dunlap@citrix.com>; Ian Jackson <Ian.Jackson@citrix.com>; Wei
>> Liu
>> > <wei.liu2@citrix.com>; StefanoStabellini <sstabellini@kernel.org>; xen-
>> > devel@lists.xenproject.org; Konrad Rzeszutek Wilk
>> > <konrad.wilk@oracle.com>; Tim (Xen.org) <tim@xen.org>
>> > Subject: RE: [PATCH v18 05/11] x86/mm: add HYPERVISOR_memory_op to
>> > acquire guest resources
>> >
>> > >>> On 29.03.18 at 11:53, <Paul.Durrant@citrix.com> wrote:
>> > >> From: Jan Beulich [mailto:JBeulich@suse.com]
>> > >> Sent: 26 March 2018 12:41
>> > >>
>> > >> >>> On 22.03.18 at 12:55, <paul.durrant@citrix.com> wrote:
>> > >> > --- a/xen/include/xlat.lst
>> > >> > +++ b/xen/include/xlat.lst
>> > >> > @@ -86,6 +86,7 @@
>> > >> > ! memory_map memory.h
>> > >> > ! memory_reservation memory.h
>> > >> > ! mem_access_op memory.h
>> > >> > +! mem_acquire_resource memory.h
>> > >>
>> > >> Why ! ? The layout doesn't appear to differ between native and
>> > >> compat. Or wait, the handle does, but why is that not
>> > >> XEN_GUEST_HANDLE_64()? (I've skipped the compat layer code
>> > >> in this round of review for that reason.)
>> > >
>> > > It's been XEN_GUEST_HANDLE throughout all but the earliest revisions of
>> > the
>> > > patch and I have not modified the compat code massively since you gave
>> > your
>> > > R-b anyway... the only thing that changed was copying back the new flags
>> > > value.
>> >
>> > Granted I could/should have noticed this earlier, but being able to
>> > get away without compat translation would certainly be a win, and
>> > we have that option since this is a tools-only interface.
>> >
>>
>> Ok. I'll see if I can get this done today then.
>>
>> Paul
>
> Actually, I'm getting confused by all this... The handle is for an array of
> xen_pfn_t, which means they are going to be 32-bits wide for a 32-bit tools
> domain. Doesn't this mean I'm going to need compat code to iterate and
> translate the array anyway?
Oh, yes, indeed. I'm sorry for the confusion. With the other remarks
addressed feel free to add
Reviewed-by: Jan Beulich <jbeulich@suse.com>
Jan
_______________________________________________
Xen-devel mailing list
Xen-devel@lists.xenproject.org
https://lists.xenproject.org/mailman/listinfo/xen-devel
^ permalink raw reply [flat|nested] 30+ messages in thread
* Re: [PATCH v18 05/11] x86/mm: add HYPERVISOR_memory_op to acquire guest resources
2018-03-29 14:25 ` Jan Beulich
@ 2018-03-29 14:38 ` Paul Durrant
0 siblings, 0 replies; 30+ messages in thread
From: Paul Durrant @ 2018-03-29 14:38 UTC (permalink / raw)
To: 'Jan Beulich'
Cc: StefanoStabellini, Wei Liu, Andrew Cooper, Tim (Xen.org),
George Dunlap, Julien Grall, Ian Jackson, xen-devel
> -----Original Message-----
> From: Xen-devel [mailto:xen-devel-bounces@lists.xenproject.org] On Behalf
> Of Jan Beulich
> Sent: 29 March 2018 15:25
> To: Paul Durrant <Paul.Durrant@citrix.com>
> Cc: StefanoStabellini <sstabellini@kernel.org>; Wei Liu
> <wei.liu2@citrix.com>; Andrew Cooper <Andrew.Cooper3@citrix.com>; Tim
> (Xen.org) <tim@xen.org>; George Dunlap <George.Dunlap@citrix.com>;
> Julien Grall <julien.grall@arm.com>; xen-devel@lists.xenproject.org; Ian
> Jackson <Ian.Jackson@citrix.com>
> Subject: Re: [Xen-devel] [PATCH v18 05/11] x86/mm: add
> HYPERVISOR_memory_op to acquire guest resources
>
> >>> On 29.03.18 at 15:17, <Paul.Durrant@citrix.com> wrote:
> >> -----Original Message-----
> >> From: Xen-devel [mailto:xen-devel-bounces@lists.xenproject.org] On
> Behalf
> >> Of Paul Durrant
> >> Sent: 29 March 2018 13:43
> >> To: 'Jan Beulich' <JBeulich@suse.com>
> >> Cc: StefanoStabellini <sstabellini@kernel.org>; Wei Liu
> >> <wei.liu2@citrix.com>; Andrew Cooper <Andrew.Cooper3@citrix.com>;
> Tim
> >> (Xen.org) <tim@xen.org>; George Dunlap <George.Dunlap@citrix.com>;
> >> Julien Grall <julien.grall@arm.com>; xen-devel@lists.xenproject.org; Ian
> >> Jackson <Ian.Jackson@citrix.com>
> >> Subject: Re: [Xen-devel] [PATCH v18 05/11] x86/mm: add
> >> HYPERVISOR_memory_op to acquire guest resources
> >>
> >> > -----Original Message-----
> >> > From: Jan Beulich [mailto:JBeulich@suse.com]
> >> > Sent: 29 March 2018 13:29
> >> > To: Paul Durrant <Paul.Durrant@citrix.com>
> >> > Cc: Julien Grall <julien.grall@arm.com>; Andrew Cooper
> >> > <Andrew.Cooper3@citrix.com>; George Dunlap
> >> > <George.Dunlap@citrix.com>; Ian Jackson <Ian.Jackson@citrix.com>;
> Wei
> >> Liu
> >> > <wei.liu2@citrix.com>; StefanoStabellini <sstabellini@kernel.org>; xen-
> >> > devel@lists.xenproject.org; Konrad Rzeszutek Wilk
> >> > <konrad.wilk@oracle.com>; Tim (Xen.org) <tim@xen.org>
> >> > Subject: RE: [PATCH v18 05/11] x86/mm: add HYPERVISOR_memory_op
> to
> >> > acquire guest resources
> >> >
> >> > >>> On 29.03.18 at 11:53, <Paul.Durrant@citrix.com> wrote:
> >> > >> From: Jan Beulich [mailto:JBeulich@suse.com]
> >> > >> Sent: 26 March 2018 12:41
> >> > >>
> >> > >> >>> On 22.03.18 at 12:55, <paul.durrant@citrix.com> wrote:
> >> > >> > --- a/xen/include/xlat.lst
> >> > >> > +++ b/xen/include/xlat.lst
> >> > >> > @@ -86,6 +86,7 @@
> >> > >> > ! memory_map memory.h
> >> > >> > ! memory_reservation memory.h
> >> > >> > ! mem_access_op memory.h
> >> > >> > +! mem_acquire_resource memory.h
> >> > >>
> >> > >> Why ! ? The layout doesn't appear to differ between native and
> >> > >> compat. Or wait, the handle does, but why is that not
> >> > >> XEN_GUEST_HANDLE_64()? (I've skipped the compat layer code
> >> > >> in this round of review for that reason.)
> >> > >
> >> > > It's been XEN_GUEST_HANDLE throughout all but the earliest
> revisions of
> >> > the
> >> > > patch and I have not modified the compat code massively since you
> gave
> >> > your
> >> > > R-b anyway... the only thing that changed was copying back the new
> flags
> >> > > value.
> >> >
> >> > Granted I could/should have noticed this earlier, but being able to
> >> > get away without compat translation would certainly be a win, and
> >> > we have that option since this is a tools-only interface.
> >> >
> >>
> >> Ok. I'll see if I can get this done today then.
> >>
> >> Paul
> >
> > Actually, I'm getting confused by all this... The handle is for an array of
> > xen_pfn_t, which means they are going to be 32-bits wide for a 32-bit tools
> > domain. Doesn't this mean I'm going to need compat code to iterate and
> > translate the array anyway?
>
> Oh, yes, indeed. I'm sorry for the confusion. With the other remarks
> addressed feel free to add
> Reviewed-by: Jan Beulich <jbeulich@suse.com>
Ok, thanks :-)
Paul
>
> Jan
>
>
> _______________________________________________
> Xen-devel mailing list
> Xen-devel@lists.xenproject.org
> https://lists.xenproject.org/mailman/listinfo/xen-devel
_______________________________________________
Xen-devel mailing list
Xen-devel@lists.xenproject.org
https://lists.xenproject.org/mailman/listinfo/xen-devel
^ permalink raw reply [flat|nested] 30+ messages in thread
* [PATCH v18 06/11] x86/hvm/ioreq: add a new mappable resource type...
2018-03-22 11:55 [PATCH v18 00/11] x86: guest resource mapping Paul Durrant
` (4 preceding siblings ...)
2018-03-22 11:55 ` [PATCH v18 05/11] x86/mm: add HYPERVISOR_memory_op to acquire guest resources Paul Durrant
@ 2018-03-22 11:55 ` Paul Durrant
2018-03-26 11:55 ` Jan Beulich
2018-03-22 11:55 ` [PATCH v18 07/11] x86/mm: add an extra command to HYPERVISOR_mmu_update Paul Durrant
` (4 subsequent siblings)
10 siblings, 1 reply; 30+ messages in thread
From: Paul Durrant @ 2018-03-22 11:55 UTC (permalink / raw)
To: xen-devel
Cc: Stefano Stabellini, Wei Liu, George Dunlap, Andrew Cooper,
Ian Jackson, Tim Deegan, Julien Grall, 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 emulating domain's
heap. These pages will never be present in the P2M of the guest at any
point (and are not even shared with the guest) and so are not vulnerable to
any direct attack by the guest.
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>
---
Cc: Jan Beulich <jbeulich@suse.com>
Cc: George Dunlap <George.Dunlap@eu.citrix.com>
Cc: Wei Liu <wei.liu2@citrix.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>
Cc: Julien Grall <julien.grall@arm.com>
v18:
- Revert largely back to v14, but use ioreq server emulator rather
than current->domain.
- Add missing checks spotted by Jan.
- Re-base.
v17:
- The use of xenheap pages means that freeing needs to be deferred until
domain destruction. Add an explanatory paragraph to the commit comment.
v15:
- Use xenheap pages rather than domheap pages and assign ownership to
target domain.
v14:
- Addressed more comments from Jan.
v13:
- Introduce an arch_acquire_resource() as suggested by Julien (and have
the ARM varient simply return -EOPNOTSUPP).
- Check for ioreq server id truncation as requested by Jan.
- Not added Jan's R-b due to substantive change from v12.
v12:
- Addressed more comments from Jan.
- Dropped George's A-b and Wei's R-b because of material change.
v11:
- Addressed more comments from Jan.
v10:
- Addressed comments from Jan.
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 | 164 ++++++++++++++++++++++++++++++++++++++++
xen/arch/x86/mm.c | 47 ++++++++++++
xen/common/memory.c | 3 +-
xen/include/asm-arm/mm.h | 8 ++
xen/include/asm-x86/hvm/ioreq.h | 2 +
xen/include/asm-x86/mm.h | 5 ++
xen/include/public/hvm/dm_op.h | 4 +
xen/include/public/memory.h | 9 +++
8 files changed, 241 insertions(+), 1 deletion(-)
diff --git a/xen/arch/x86/hvm/ioreq.c b/xen/arch/x86/hvm/ioreq.c
index ce53d883e9..ca02e6da10 100644
--- a/xen/arch/x86/hvm/ioreq.c
+++ b/xen/arch/x86/hvm/ioreq.c
@@ -259,6 +259,19 @@ 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;
@@ -281,6 +294,67 @@ 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 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 safe because the emulating
+ * domain cannot be destroyed until the ioreq server is destroyed.
+ * Also 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(s->emulator, MEMF_no_refcount);
+
+ if ( !iorp->page )
+ return -ENOMEM;
+
+ if ( !get_page_type(iorp->page, PGT_writable_page) )
+ goto fail;
+
+ iorp->va = __map_domain_page_global(iorp->page);
+ if ( !iorp->va )
+ goto fail;
+
+ clear_page(iorp->va);
+ return 0;
+
+ fail:
+ put_page_and_type(iorp->page);
+ iorp->page = NULL;
+
+ return -ENOMEM;
+}
+
+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_and_type(iorp->page);
+ iorp->page = NULL;
+}
+
bool is_ioreq_server_page(struct domain *d, const struct page_info *page)
{
const struct hvm_ioreq_server *s;
@@ -486,6 +560,27 @@ 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;
@@ -637,7 +732,19 @@ static void hvm_ioreq_server_deinit(struct hvm_ioreq_server *s)
{
ASSERT(!s->enabled);
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);
+
hvm_ioreq_server_free_rangesets(s);
put_domain(s->emulator);
@@ -802,6 +909,63 @@ 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 long idx, mfn_t *mfn)
+{
+ struct hvm_ioreq_server *s;
+ int rc;
+
+ if ( id == DEFAULT_IOSERVID )
+ return -EOPNOTSUPP;
+
+ if ( !is_hvm_domain(d) )
+ return -EINVAL;
+
+ spin_lock_recursive(&d->arch.hvm_domain.ioreq_server.lock);
+
+ s = get_ioreq_server(d, id);
+
+ rc = -ENOENT;
+ if ( !s )
+ goto out;
+
+ ASSERT(!IS_DEFAULT(s));
+
+ rc = -EPERM;
+ if ( s->emulator != current->domain )
+ goto out;
+
+ rc = hvm_ioreq_server_alloc_pages(s);
+ if ( rc )
+ goto out;
+
+ switch ( idx )
+ {
+ case XENMEM_resource_ioreq_server_frame_bufioreq:
+ rc = -ENOENT;
+ if ( !HANDLE_BUFIOREQ(s) )
+ goto out;
+
+ *mfn = _mfn(page_to_mfn(s->bufioreq.page));
+ rc = 0;
+ break;
+
+ case XENMEM_resource_ioreq_server_frame_ioreq(0):
+ *mfn = _mfn(page_to_mfn(s->ioreq.page));
+ rc = 0;
+ break;
+
+ default:
+ rc = -EINVAL;
+ break;
+ }
+
+ 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 17558e0c8c..846cc61935 100644
--- a/xen/arch/x86/mm.c
+++ b/xen/arch/x86/mm.c
@@ -123,6 +123,7 @@
#include <asm/io_apic.h>
#include <asm/pci.h>
#include <asm/guest.h>
+#include <asm/hvm/ioreq.h>
#include <asm/hvm/grant_table.h>
#include <asm/pv/grant_table.h>
@@ -4228,6 +4229,52 @@ int xenmem_add_to_physmap_one(
return rc;
}
+int arch_acquire_resource(struct domain *d, unsigned int type,
+ unsigned int id, unsigned long frame,
+ unsigned int nr_frames, xen_pfn_t mfn_list[],
+ unsigned int *flags)
+{
+ int rc;
+
+ switch ( type )
+ {
+ case XENMEM_resource_ioreq_server:
+ {
+ ioservid_t ioservid = id;
+ unsigned int i;
+
+ rc = -EINVAL;
+ if ( id != (unsigned int)ioservid )
+ break;
+
+ rc = 0;
+ for ( i = 0; i < nr_frames; i++ )
+ {
+ mfn_t mfn;
+
+ rc = hvm_get_ioreq_server_frame(d, id, frame + i, &mfn);
+ if ( rc )
+ break;
+
+ mfn_list[i] = mfn_x(mfn);
+ }
+
+ /*
+ * The frames will be assigned to the tools domain that created
+ * the ioreq server.
+ */
+ *flags |= XENMEM_resource_flag_tools_owned;
+ break;
+ }
+
+ default:
+ rc = -EOPNOTSUPP;
+ break;
+ }
+
+ return rc;
+}
+
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 d56cea1590..c09ef179e8 100644
--- a/xen/common/memory.c
+++ b/xen/common/memory.c
@@ -1013,7 +1013,8 @@ static int acquire_resource(
switch ( xmar.type )
{
default:
- rc = -EOPNOTSUPP;
+ rc = arch_acquire_resource(d, xmar.type, xmar.id, xmar.frame,
+ xmar.nr_frames, mfn_list, &xmar.flags);
break;
}
diff --git a/xen/include/asm-arm/mm.h b/xen/include/asm-arm/mm.h
index a0e922f360..5ddc287b6f 100644
--- a/xen/include/asm-arm/mm.h
+++ b/xen/include/asm-arm/mm.h
@@ -374,6 +374,14 @@ static inline void put_page_and_type(struct page_info *page)
void clear_and_clean_page(struct page_info *page);
+static inline int arch_acquire_resource(
+ struct domain *d, unsigned int type, unsigned int id,
+ unsigned long frame,unsigned int nr_frames, xen_pfn_t mfn_list[],
+ unsigned int *flags)
+{
+ return -EOPNOTSUPP;
+}
+
#endif /* __ARCH_ARM_MM__ */
/*
* Local variables:
diff --git a/xen/include/asm-x86/hvm/ioreq.h b/xen/include/asm-x86/hvm/ioreq.h
index 1bd1a02f23..bab473cf44 100644
--- a/xen/include/asm-x86/hvm/ioreq.h
+++ b/xen/include/asm-x86/hvm/ioreq.h
@@ -30,6 +30,8 @@ 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);
+int hvm_get_ioreq_server_frame(struct domain *d, ioservid_t id,
+ unsigned long 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 c115661837..d3cd5b9b22 100644
--- a/xen/include/asm-x86/mm.h
+++ b/xen/include/asm-x86/mm.h
@@ -623,4 +623,9 @@ static inline bool arch_mfn_in_directmap(unsigned long mfn)
return mfn <= (virt_to_mfn(eva - 1) + 1);
}
+int arch_acquire_resource(struct domain *d, unsigned int type,
+ unsigned int id, unsigned long frame,
+ unsigned int nr_frames, xen_pfn_t mfn_list[],
+ unsigned int *flags);
+
#endif /* __ASM_X86_MM_H__ */
diff --git a/xen/include/public/hvm/dm_op.h b/xen/include/public/hvm/dm_op.h
index 9823726d79..d3b554d019 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 53d258fd92..c5cd2ba1a2 100644
--- a/xen/include/public/memory.h
+++ b/xen/include/public/memory.h
@@ -609,9 +609,14 @@ 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;
/*
@@ -636,6 +641,10 @@ struct xen_mem_acquire_resource {
* is ignored if nr_frames is 0.
*/
uint64_aligned_t frame;
+
+#define XENMEM_resource_ioreq_server_frame_bufioreq 0
+#define XENMEM_resource_ioreq_server_frame_ioreq(n) (1 + (n))
+
/*
* IN/OUT - If the tools domain is PV then, upon return, frame_list
* will be populated with the MFNs of the resource.
--
2.11.0
_______________________________________________
Xen-devel mailing list
Xen-devel@lists.xenproject.org
https://lists.xenproject.org/mailman/listinfo/xen-devel
^ permalink raw reply related [flat|nested] 30+ messages in thread* Re: [PATCH v18 06/11] x86/hvm/ioreq: add a new mappable resource type...
2018-03-22 11:55 ` [PATCH v18 06/11] x86/hvm/ioreq: add a new mappable resource type Paul Durrant
@ 2018-03-26 11:55 ` Jan Beulich
2018-03-29 10:29 ` Paul Durrant
0 siblings, 1 reply; 30+ messages in thread
From: Jan Beulich @ 2018-03-26 11:55 UTC (permalink / raw)
To: Paul Durrant
Cc: Stefano Stabellini, Wei Liu, George Dunlap, Andrew Cooper,
Ian Jackson, Tim Deegan, JulienGrall, xen-devel
>>> On 22.03.18 at 12:55, <paul.durrant@citrix.com> wrote:
> ... 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 emulating domain's
> heap. These pages will never be present in the P2M of the guest at any
> point (and are not even shared with the guest) and so are not vulnerable to
> any direct attack by the guest.
"allocate pages from the emulating domain's heap" is a sub-optimal
(at least slightly misleading) description, due to your use of
MEMF_no_refcount together with the fact that domain's don't
really have their own heaps.
> +static int hvm_alloc_ioreq_mfn(struct hvm_ioreq_server *s, bool buf)
> +{
> + 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 safe because the emulating
> + * domain cannot be destroyed until the ioreq server is destroyed.
> + * Also 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(s->emulator, MEMF_no_refcount);
> +
> + if ( !iorp->page )
> + return -ENOMEM;
> +
> + if ( !get_page_type(iorp->page, PGT_writable_page) )
> + goto fail;
> +
> + iorp->va = __map_domain_page_global(iorp->page);
> + if ( !iorp->va )
> + goto fail;
> +
> + clear_page(iorp->va);
> + return 0;
> +
> + fail:
> + put_page_and_type(iorp->page);
This is wrong in case it's the get_page_type() which failed.
> +int arch_acquire_resource(struct domain *d, unsigned int type,
> + unsigned int id, unsigned long frame,
> + unsigned int nr_frames, xen_pfn_t mfn_list[],
> + unsigned int *flags)
> +{
> + int rc;
> +
> + switch ( type )
> + {
> + case XENMEM_resource_ioreq_server:
> + {
> + ioservid_t ioservid = id;
> + unsigned int i;
> +
> + rc = -EINVAL;
> + if ( id != (unsigned int)ioservid )
> + break;
> +
> + rc = 0;
> + for ( i = 0; i < nr_frames; i++ )
> + {
> + mfn_t mfn;
> +
> + rc = hvm_get_ioreq_server_frame(d, id, frame + i, &mfn);
> + if ( rc )
> + break;
> +
> + mfn_list[i] = mfn_x(mfn);
> + }
> +
> + /*
> + * The frames will be assigned to the tools domain that created
> + * the ioreq server.
> + */
s/will be/have been/ and perhaps drop "tools"?
> --- a/xen/include/asm-arm/mm.h
> +++ b/xen/include/asm-arm/mm.h
> @@ -374,6 +374,14 @@ static inline void put_page_and_type(struct page_info *page)
>
> void clear_and_clean_page(struct page_info *page);
>
> +static inline int arch_acquire_resource(
> + struct domain *d, unsigned int type, unsigned int id,
> + unsigned long frame,unsigned int nr_frames, xen_pfn_t mfn_list[],
Missing blank.
Jan
_______________________________________________
Xen-devel mailing list
Xen-devel@lists.xenproject.org
https://lists.xenproject.org/mailman/listinfo/xen-devel
^ permalink raw reply [flat|nested] 30+ messages in thread* Re: [PATCH v18 06/11] x86/hvm/ioreq: add a new mappable resource type...
2018-03-26 11:55 ` Jan Beulich
@ 2018-03-29 10:29 ` Paul Durrant
0 siblings, 0 replies; 30+ messages in thread
From: Paul Durrant @ 2018-03-29 10:29 UTC (permalink / raw)
To: 'Jan Beulich'
Cc: Stefano Stabellini, Wei Liu, Andrew Cooper, Tim (Xen.org),
George Dunlap, JulienGrall, xen-devel, Ian Jackson
> -----Original Message-----
> From: Jan Beulich [mailto:JBeulich@suse.com]
> Sent: 26 March 2018 12:55
> To: Paul Durrant <Paul.Durrant@citrix.com>
> Cc: JulienGrall <julien.grall@arm.com>; 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 v18 06/11] x86/hvm/ioreq: add a new mappable
> resource type...
>
> >>> On 22.03.18 at 12:55, <paul.durrant@citrix.com> wrote:
> > ... 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 emulating domain's
> > heap. These pages will never be present in the P2M of the guest at any
> > point (and are not even shared with the guest) and so are not vulnerable to
> > any direct attack by the guest.
>
> "allocate pages from the emulating domain's heap" is a sub-optimal
> (at least slightly misleading) description, due to your use of
> MEMF_no_refcount together with the fact that domain's don't
> really have their own heaps.
>
Ok, I'll say 'allocate pages which are assigned to the emulating domain' instead.
> > +static int hvm_alloc_ioreq_mfn(struct hvm_ioreq_server *s, bool buf)
> > +{
> > + 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 safe because the emulating
> > + * domain cannot be destroyed until the ioreq server is destroyed.
> > + * Also 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(s->emulator, MEMF_no_refcount);
> > +
> > + if ( !iorp->page )
> > + return -ENOMEM;
> > +
> > + if ( !get_page_type(iorp->page, PGT_writable_page) )
> > + goto fail;
> > +
> > + iorp->va = __map_domain_page_global(iorp->page);
> > + if ( !iorp->va )
> > + goto fail;
> > +
> > + clear_page(iorp->va);
> > + return 0;
> > +
> > + fail:
> > + put_page_and_type(iorp->page);
>
> This is wrong in case it's the get_page_type() which failed.
>
Oh, I thought it was safe. I'll re-work the error path.
> > +int arch_acquire_resource(struct domain *d, unsigned int type,
> > + unsigned int id, unsigned long frame,
> > + unsigned int nr_frames, xen_pfn_t mfn_list[],
> > + unsigned int *flags)
> > +{
> > + int rc;
> > +
> > + switch ( type )
> > + {
> > + case XENMEM_resource_ioreq_server:
> > + {
> > + ioservid_t ioservid = id;
> > + unsigned int i;
> > +
> > + rc = -EINVAL;
> > + if ( id != (unsigned int)ioservid )
> > + break;
> > +
> > + rc = 0;
> > + for ( i = 0; i < nr_frames; i++ )
> > + {
> > + mfn_t mfn;
> > +
> > + rc = hvm_get_ioreq_server_frame(d, id, frame + i, &mfn);
> > + if ( rc )
> > + break;
> > +
> > + mfn_list[i] = mfn_x(mfn);
> > + }
> > +
> > + /*
> > + * The frames will be assigned to the tools domain that created
> > + * the ioreq server.
> > + */
>
> s/will be/have been/ and perhaps drop "tools"?
>
Ok.
> > --- a/xen/include/asm-arm/mm.h
> > +++ b/xen/include/asm-arm/mm.h
> > @@ -374,6 +374,14 @@ static inline void put_page_and_type(struct
> page_info *page)
> >
> > void clear_and_clean_page(struct page_info *page);
> >
> > +static inline int arch_acquire_resource(
> > + struct domain *d, unsigned int type, unsigned int id,
> > + unsigned long frame,unsigned int nr_frames, xen_pfn_t mfn_list[],
>
> Missing blank.
>
Ok.
Paul
> Jan
_______________________________________________
Xen-devel mailing list
Xen-devel@lists.xenproject.org
https://lists.xenproject.org/mailman/listinfo/xen-devel
^ permalink raw reply [flat|nested] 30+ messages in thread
* [PATCH v18 07/11] x86/mm: add an extra command to HYPERVISOR_mmu_update...
2018-03-22 11:55 [PATCH v18 00/11] x86: guest resource mapping Paul Durrant
` (5 preceding siblings ...)
2018-03-22 11:55 ` [PATCH v18 06/11] x86/hvm/ioreq: add a new mappable resource type Paul Durrant
@ 2018-03-22 11:55 ` Paul Durrant
2018-03-22 11:55 ` [PATCH v18 08/11] tools/libxenforeignmemory: add support for resource mapping Paul Durrant
` (3 subsequent siblings)
10 siblings, 0 replies; 30+ messages in thread
From: Paul Durrant @ 2018-03-22 11:55 UTC (permalink / raw)
To: xen-devel
Cc: Stefano Stabellini, Wei Liu, George Dunlap, Andrew Cooper,
Ian Jackson, Tim Deegan, Paul Durrant
...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>
Reviewed-by: 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>
v13:
- Re-base.
v8:
- New in this version, replacing "allow a privileged PV domain to map
guest mfns".
---
xen/arch/x86/mm.c | 13 ++++++++-----
xen/include/public/xen.h | 12 +++++++++---
2 files changed, 17 insertions(+), 8 deletions(-)
diff --git a/xen/arch/x86/mm.c b/xen/arch/x86/mm.c
index 846cc61935..8e3be1f263 100644
--- a/xen/arch/x86/mm.c
+++ b/xen/arch/x86/mm.c
@@ -1901,9 +1901,10 @@ 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, unsigned 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;
@@ -1925,7 +1926,8 @@ static int mod_l1_entry(l1_pgentry_t *pl1e, l1_pgentry_t nl1e,
}
/* Translate foreign guest address. */
- if ( paging_mode_translate(pg_dom) )
+ if ( cmd != MMU_PT_UPDATE_NO_TRANSLATE &&
+ paging_mode_translate(pg_dom) )
{
p2m_type_t p2mt;
p2m_query_t q = l1e_get_flags(nl1e) & _PAGE_RW ?
@@ -3617,6 +3619,7 @@ 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;
@@ -3676,8 +3679,7 @@ long do_mmu_update(
{
case PGT_l1_page_table:
rc = mod_l1_entry(va, l1e_from_intpte(req.val), mfn,
- cmd == MMU_PT_UPDATE_PRESERVE_AD, v,
- pg_owner);
+ cmd, v, pg_owner);
break;
case PGT_l2_page_table:
@@ -3988,7 +3990,8 @@ 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 308109f176..fb1df8f293 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'. ptr is MA. */
+ /* val never translated. */
/*
* MMU EXTENDED OPERATIONS
--
2.11.0
_______________________________________________
Xen-devel mailing list
Xen-devel@lists.xenproject.org
https://lists.xenproject.org/mailman/listinfo/xen-devel
^ permalink raw reply related [flat|nested] 30+ messages in thread* [PATCH v18 08/11] tools/libxenforeignmemory: add support for resource mapping
2018-03-22 11:55 [PATCH v18 00/11] x86: guest resource mapping Paul Durrant
` (6 preceding siblings ...)
2018-03-22 11:55 ` [PATCH v18 07/11] x86/mm: add an extra command to HYPERVISOR_mmu_update Paul Durrant
@ 2018-03-22 11:55 ` Paul Durrant
2018-03-22 11:55 ` [PATCH v18 09/11] tools/libxenforeignmemory: reduce xenforeignmemory_restrict code footprint Paul Durrant
` (2 subsequent siblings)
10 siblings, 0 replies; 30+ messages in thread
From: Paul Durrant @ 2018-03-22 11:55 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 cbe815fce8..ee5c3fd67e 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 7c8562ae74..63f12e2450 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"
static int all_restrict_cb(Xentoolcore__Active_Handle *ah, domid_t domid) {
@@ -135,6 +137,57 @@ 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 2470f3c46c..b191000b49 100644
--- a/tools/libs/foreignmemory/private.h
+++ b/tools/libs/foreignmemory/private.h
@@ -45,6 +45,37 @@ 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.xenproject.org
https://lists.xenproject.org/mailman/listinfo/xen-devel
^ permalink raw reply related [flat|nested] 30+ messages in thread* [PATCH v18 09/11] tools/libxenforeignmemory: reduce xenforeignmemory_restrict code footprint
2018-03-22 11:55 [PATCH v18 00/11] x86: guest resource mapping Paul Durrant
` (7 preceding siblings ...)
2018-03-22 11:55 ` [PATCH v18 08/11] tools/libxenforeignmemory: add support for resource mapping Paul Durrant
@ 2018-03-22 11:55 ` Paul Durrant
2018-03-22 11:55 ` [PATCH v18 10/11] common: add a new mappable resource type: XENMEM_resource_grant_table Paul Durrant
2018-03-22 11:55 ` [PATCH v18 11/11] tools/libxenctrl: use new xenforeignmemory API to seed grant table Paul Durrant
10 siblings, 0 replies; 30+ messages in thread
From: Paul Durrant @ 2018-03-22 11:55 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 b191000b49..b06ce12583 100644
--- a/tools/libs/foreignmemory/private.h
+++ b/tools/libs/foreignmemory/private.h
@@ -35,9 +35,6 @@ 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,
@@ -57,6 +54,13 @@ 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)
{
@@ -70,6 +74,8 @@ 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.xenproject.org
https://lists.xenproject.org/mailman/listinfo/xen-devel
^ permalink raw reply related [flat|nested] 30+ messages in thread* [PATCH v18 10/11] common: add a new mappable resource type: XENMEM_resource_grant_table
2018-03-22 11:55 [PATCH v18 00/11] x86: guest resource mapping Paul Durrant
` (8 preceding siblings ...)
2018-03-22 11:55 ` [PATCH v18 09/11] tools/libxenforeignmemory: reduce xenforeignmemory_restrict code footprint Paul Durrant
@ 2018-03-22 11:55 ` Paul Durrant
2018-03-26 12:16 ` Jan Beulich
2018-03-22 11:55 ` [PATCH v18 11/11] tools/libxenctrl: use new xenforeignmemory API to seed grant table Paul Durrant
10 siblings, 1 reply; 30+ messages in thread
From: Paul Durrant @ 2018-03-22 11:55 UTC (permalink / raw)
To: xen-devel
Cc: Stefano Stabellini, Wei Liu, 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.
NOTE: This patch expands the on-stack mfn_list array in acquire_resource()
but it is still small enough to remain on-stack.
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>
v18:
- Non-trivial re-base of grant table code.
- Dropped Jan's R-b because of the grant table changes.
v13:
- Re-work the internals to avoid using the XENMAPIDX_grant_table_status
hack.
v12:
- Dropped limit checks as requested by Jan.
v10:
- Addressed comments from Jan.
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 | 71 +++++++++++++++++++++++++++++++++++--------
xen/common/memory.c | 45 ++++++++++++++++++++++++++-
xen/include/public/memory.h | 9 ++++--
xen/include/xen/grant_table.h | 4 +++
4 files changed, 113 insertions(+), 16 deletions(-)
diff --git a/xen/common/grant_table.c b/xen/common/grant_table.c
index 18201912e4..c8c3661b19 100644
--- a/xen/common/grant_table.c
+++ b/xen/common/grant_table.c
@@ -3863,6 +3863,35 @@ int mem_sharing_gref_to_gfn(struct grant_table *gt, grant_ref_t ref,
}
#endif
+/* caller must hold read or write lock */
+static int gnttab_get_status_frame_mfn(struct domain *d,
+ unsigned long idx, mfn_t *mfn)
+{
+ struct grant_table *gt = d->grant_table;
+
+ if ( idx >= nr_status_frames(gt) )
+ return -EINVAL;
+
+ *mfn = _mfn(virt_to_mfn(gt->status[idx]));
+ return 0;
+}
+
+/* caller must hold write lock */
+static int gnttab_get_shared_frame_mfn(struct domain *d,
+ unsigned long idx, mfn_t *mfn)
+{
+ struct grant_table *gt = d->grant_table;
+
+ if ( (idx >= nr_grant_frames(gt)) && (idx < gt->max_grant_frames) )
+ gnttab_grow_table(d, idx + 1);
+
+ if ( idx >= nr_grant_frames(gt) )
+ return -EINVAL;
+
+ *mfn = _mfn(virt_to_mfn(gt->shared_raw[idx]));
+ return 0;
+}
+
int gnttab_map_frame(struct domain *d, unsigned long idx, gfn_t gfn,
mfn_t *mfn)
{
@@ -3880,21 +3909,11 @@ int gnttab_map_frame(struct domain *d, unsigned long idx, gfn_t gfn,
{
idx &= ~XENMAPIDX_grant_table_status;
status = true;
- if ( idx < nr_status_frames(gt) )
- *mfn = _mfn(virt_to_mfn(gt->status[idx]));
- else
- rc = -EINVAL;
- }
- else
- {
- if ( (idx >= nr_grant_frames(gt)) && (idx < gt->max_grant_frames) )
- gnttab_grow_table(d, idx + 1);
- if ( idx < nr_grant_frames(gt) )
- *mfn = _mfn(virt_to_mfn(gt->shared_raw[idx]));
- else
- rc = -EINVAL;
+ rc = gnttab_get_status_frame_mfn(d, idx, mfn);
}
+ else
+ rc = gnttab_get_shared_frame_mfn(d, idx, mfn);
if ( !rc && paging_mode_translate(d) &&
!gfn_eq(gnttab_get_frame_gfn(gt, status, idx), INVALID_GFN) )
@@ -3909,6 +3928,32 @@ int gnttab_map_frame(struct domain *d, unsigned long idx, gfn_t gfn,
return rc;
}
+int gnttab_get_shared_frame(struct domain *d, unsigned long idx,
+ mfn_t *mfn)
+{
+ struct grant_table *gt = d->grant_table;
+ int rc;
+
+ grant_write_lock(gt);
+ rc = gnttab_get_shared_frame_mfn(d, idx, mfn);
+ grant_write_unlock(gt);
+
+ return rc;
+}
+
+int gnttab_get_status_frame(struct domain *d, unsigned long idx,
+ mfn_t *mfn)
+{
+ struct grant_table *gt = d->grant_table;
+ int rc;
+
+ grant_read_lock(gt);
+ rc = gnttab_get_status_frame_mfn(d, idx, mfn);
+ grant_read_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 c09ef179e8..bc570167bb 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>
@@ -967,6 +968,43 @@ static long xatp_permission_check(struct domain *d, unsigned int space)
return xsm_add_to_physmap(XSM_TARGET, current->domain, d);
}
+static int acquire_grant_table(struct domain *d, unsigned int id,
+ unsigned long frame,
+ unsigned int nr_frames,
+ xen_pfn_t mfn_list[])
+{
+ unsigned int i = nr_frames;
+
+ /* Iterate backwards in case table needs to grow */
+ while ( i-- != 0 )
+ {
+ mfn_t mfn = INVALID_MFN;
+ int rc;
+
+ switch ( id )
+ {
+ case XENMEM_resource_grant_table_id_shared:
+ rc = gnttab_get_shared_frame(d, frame + i, &mfn);
+ break;
+
+ case XENMEM_resource_grant_table_id_status:
+ rc = gnttab_get_status_frame(d, frame + i, &mfn);
+ break;
+
+ default:
+ rc = -EINVAL;
+ break;
+ }
+
+ if ( rc )
+ return rc;
+
+ mfn_list[i] = mfn_x(mfn);
+ }
+
+ return 0;
+}
+
static int acquire_resource(
XEN_GUEST_HANDLE_PARAM(xen_mem_acquire_resource_t) arg)
{
@@ -977,7 +1015,7 @@ static int acquire_resource(
* moment since they are small, but if they need to grow in future
* use-cases then per-CPU arrays or heap allocations may be required.
*/
- xen_pfn_t mfn_list[2];
+ xen_pfn_t mfn_list[32];
int rc;
if ( copy_from_guest(&xmar, arg, 1) )
@@ -1012,6 +1050,11 @@ static int acquire_resource(
switch ( xmar.type )
{
+ case XENMEM_resource_grant_table:
+ rc = acquire_grant_table(d, xmar.id, xmar.frame, xmar.nr_frames,
+ mfn_list);
+ break;
+
default:
rc = arch_acquire_resource(d, xmar.type, xmar.id, xmar.frame,
xmar.nr_frames, mfn_list, &xmar.flags);
diff --git a/xen/include/public/memory.h b/xen/include/public/memory.h
index c5cd2ba1a2..c653772333 100644
--- a/xen/include/public/memory.h
+++ b/xen/include/public/memory.h
@@ -611,16 +611,21 @@ 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
* unless stated otherwise.
*
* type == XENMEM_resource_ioreq_server -> id == ioreq server id
+ * type == XENMEM_resource_grant_table -> id defined below
*/
uint32_t id;
- /*
- * IN/OUT - As an IN parameter number of frames of the resource
+
+#define XENMEM_resource_grant_table_id_shared 0
+#define XENMEM_resource_grant_table_id_status 1
+
+ /* IN/OUT - As an IN parameter number of frames of the resource
* to be mapped. However, if the specified value is 0 and
* frame_list is NULL then this field will be set to the
* maximum value supported by the implementation on return.
diff --git a/xen/include/xen/grant_table.h b/xen/include/xen/grant_table.h
index b3a95fda58..144d2cde35 100644
--- a/xen/include/xen/grant_table.h
+++ b/xen/include/xen/grant_table.h
@@ -55,6 +55,10 @@ 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_shared_frame(struct domain *d, unsigned long idx,
+ mfn_t *mfn);
+int gnttab_get_status_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.xenproject.org
https://lists.xenproject.org/mailman/listinfo/xen-devel
^ permalink raw reply related [flat|nested] 30+ messages in thread* Re: [PATCH v18 10/11] common: add a new mappable resource type: XENMEM_resource_grant_table
2018-03-22 11:55 ` [PATCH v18 10/11] common: add a new mappable resource type: XENMEM_resource_grant_table Paul Durrant
@ 2018-03-26 12:16 ` Jan Beulich
2018-03-26 12:54 ` Jan Beulich
0 siblings, 1 reply; 30+ messages in thread
From: Jan Beulich @ 2018-03-26 12:16 UTC (permalink / raw)
To: Paul Durrant
Cc: Stefano Stabellini, Wei Liu, George Dunlap, Andrew Cooper,
Ian Jackson, Tim Deegan, xen-devel
>>> On 22.03.18 at 12:55, <paul.durrant@citrix.com> wrote:
> --- a/xen/common/grant_table.c
> +++ b/xen/common/grant_table.c
> @@ -3863,6 +3863,35 @@ int mem_sharing_gref_to_gfn(struct grant_table *gt, grant_ref_t ref,
> }
> #endif
>
> +/* caller must hold read or write lock */
> +static int gnttab_get_status_frame_mfn(struct domain *d,
> + unsigned long idx, mfn_t *mfn)
> +{
> + struct grant_table *gt = d->grant_table;
> +
> + if ( idx >= nr_status_frames(gt) )
> + return -EINVAL;
> +
> + *mfn = _mfn(virt_to_mfn(gt->status[idx]));
> + return 0;
> +}
> +
> +/* caller must hold write lock */
> +static int gnttab_get_shared_frame_mfn(struct domain *d,
> + unsigned long idx, mfn_t *mfn)
> +{
> + struct grant_table *gt = d->grant_table;
> +
> + if ( (idx >= nr_grant_frames(gt)) && (idx < gt->max_grant_frames) )
> + gnttab_grow_table(d, idx + 1);
> +
> + if ( idx >= nr_grant_frames(gt) )
> + return -EINVAL;
> +
> + *mfn = _mfn(virt_to_mfn(gt->shared_raw[idx]));
> + return 0;
> +}
I realize the anomaly was there already before, but imo it becomes
more pronounced with the two functions differing in more than just
the shared vs status naming (IOW I find it strange that one grows
the grant table while the other doesn't). This extends to ...
> +int gnttab_get_shared_frame(struct domain *d, unsigned long idx,
> + mfn_t *mfn)
> +{
> + struct grant_table *gt = d->grant_table;
> + int rc;
> +
> + grant_write_lock(gt);
> + rc = gnttab_get_shared_frame_mfn(d, idx, mfn);
> + grant_write_unlock(gt);
> +
> + return rc;
> +}
> +
> +int gnttab_get_status_frame(struct domain *d, unsigned long idx,
> + mfn_t *mfn)
> +{
> + struct grant_table *gt = d->grant_table;
> + int rc;
> +
> + grant_read_lock(gt);
> + rc = gnttab_get_status_frame_mfn(d, idx, mfn);
> + grant_read_unlock(gt);
> +
> + return rc;
> +}
... these two acquiring the lock in different ways.
And then I'm completely missing the interaction with
gnttab_unpopulate_status_frames(). While this might not be a
practical problem at this point in time, we're liable to forget to
address this later on if there's no stop gap measure. A PV guest
mapping the obtained MFNs is going to be fine, but a HVM/PVH
one isn't, since neither x86 nor ARM refcount pages inserted into
or removed from a domain's p2m. I therefore think you need to
add a is_hvm_domain() check to acquire_grant_table(), with a
suitable fixme comment attached to it.
With that (and despite the noticed anomaly)
Reviewed-by: Jan Beulich <jbeulich@suse.com>
Jan
_______________________________________________
Xen-devel mailing list
Xen-devel@lists.xenproject.org
https://lists.xenproject.org/mailman/listinfo/xen-devel
^ permalink raw reply [flat|nested] 30+ messages in thread* Re: [PATCH v18 10/11] common: add a new mappable resource type: XENMEM_resource_grant_table
2018-03-26 12:16 ` Jan Beulich
@ 2018-03-26 12:54 ` Jan Beulich
2018-03-29 11:02 ` Paul Durrant
0 siblings, 1 reply; 30+ messages in thread
From: Jan Beulich @ 2018-03-26 12:54 UTC (permalink / raw)
To: Paul Durrant
Cc: Stefano Stabellini, Wei Liu, George Dunlap, Andrew Cooper,
Ian Jackson, Tim Deegan, xen-devel
>>> On 26.03.18 at 14:16, <JBeulich@suse.com> wrote:
>>>> On 22.03.18 at 12:55, <paul.durrant@citrix.com> wrote:
>> --- a/xen/common/grant_table.c
>> +++ b/xen/common/grant_table.c
>> @@ -3863,6 +3863,35 @@ int mem_sharing_gref_to_gfn(struct grant_table *gt, grant_ref_t ref,
>> }
>> #endif
>>
>> +/* caller must hold read or write lock */
>> +static int gnttab_get_status_frame_mfn(struct domain *d,
>> + unsigned long idx, mfn_t *mfn)
>> +{
>> + struct grant_table *gt = d->grant_table;
>> +
>> + if ( idx >= nr_status_frames(gt) )
>> + return -EINVAL;
>> +
>> + *mfn = _mfn(virt_to_mfn(gt->status[idx]));
>> + return 0;
>> +}
>> +
>> +/* caller must hold write lock */
>> +static int gnttab_get_shared_frame_mfn(struct domain *d,
>> + unsigned long idx, mfn_t *mfn)
>> +{
>> + struct grant_table *gt = d->grant_table;
>> +
>> + if ( (idx >= nr_grant_frames(gt)) && (idx < gt->max_grant_frames) )
>> + gnttab_grow_table(d, idx + 1);
>> +
>> + if ( idx >= nr_grant_frames(gt) )
>> + return -EINVAL;
>> +
>> + *mfn = _mfn(virt_to_mfn(gt->shared_raw[idx]));
>> + return 0;
>> +}
>
> I realize the anomaly was there already before, but imo it becomes
> more pronounced with the two functions differing in more than just
> the shared vs status naming (IOW I find it strange that one grows
> the grant table while the other doesn't). This extends to ...
>
>> +int gnttab_get_shared_frame(struct domain *d, unsigned long idx,
>> + mfn_t *mfn)
>> +{
>> + struct grant_table *gt = d->grant_table;
>> + int rc;
>> +
>> + grant_write_lock(gt);
>> + rc = gnttab_get_shared_frame_mfn(d, idx, mfn);
>> + grant_write_unlock(gt);
>> +
>> + return rc;
>> +}
>> +
>> +int gnttab_get_status_frame(struct domain *d, unsigned long idx,
>> + mfn_t *mfn)
>> +{
>> + struct grant_table *gt = d->grant_table;
>> + int rc;
>> +
>> + grant_read_lock(gt);
>> + rc = gnttab_get_status_frame_mfn(d, idx, mfn);
>> + grant_read_unlock(gt);
>> +
>> + return rc;
>> +}
>
> ... these two acquiring the lock in different ways.
>
> And then I'm completely missing the interaction with
> gnttab_unpopulate_status_frames(). While this might not be a
> practical problem at this point in time, we're liable to forget to
> address this later on if there's no stop gap measure. A PV guest
> mapping the obtained MFNs is going to be fine, but a HVM/PVH
> one isn't, since neither x86 nor ARM refcount pages inserted into
> or removed from a domain's p2m. I therefore think you need to
> add a is_hvm_domain() check to acquire_grant_table(), with a
> suitable fixme comment attached to it.
Or perhaps better paging_mode_translate(current->domain).
Jan
_______________________________________________
Xen-devel mailing list
Xen-devel@lists.xenproject.org
https://lists.xenproject.org/mailman/listinfo/xen-devel
^ permalink raw reply [flat|nested] 30+ messages in thread* Re: [PATCH v18 10/11] common: add a new mappable resource type: XENMEM_resource_grant_table
2018-03-26 12:54 ` Jan Beulich
@ 2018-03-29 11:02 ` Paul Durrant
2018-03-29 12:31 ` Jan Beulich
0 siblings, 1 reply; 30+ messages in thread
From: Paul Durrant @ 2018-03-29 11:02 UTC (permalink / raw)
To: 'Jan Beulich'
Cc: Stefano Stabellini, Wei Liu, Andrew Cooper, Tim (Xen.org),
George Dunlap, Ian Jackson, xen-devel
> -----Original Message-----
> From: Jan Beulich [mailto:JBeulich@suse.com]
> Sent: 26 March 2018 13:55
> 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; Tim (Xen.org)
> <tim@xen.org>
> Subject: Re: [PATCH v18 10/11] common: add a new mappable resource
> type: XENMEM_resource_grant_table
>
> >>> On 26.03.18 at 14:16, <JBeulich@suse.com> wrote:
> >>>> On 22.03.18 at 12:55, <paul.durrant@citrix.com> wrote:
> >> --- a/xen/common/grant_table.c
> >> +++ b/xen/common/grant_table.c
> >> @@ -3863,6 +3863,35 @@ int mem_sharing_gref_to_gfn(struct
> grant_table *gt, grant_ref_t ref,
> >> }
> >> #endif
> >>
> >> +/* caller must hold read or write lock */
> >> +static int gnttab_get_status_frame_mfn(struct domain *d,
> >> + unsigned long idx, mfn_t *mfn)
> >> +{
> >> + struct grant_table *gt = d->grant_table;
> >> +
> >> + if ( idx >= nr_status_frames(gt) )
> >> + return -EINVAL;
> >> +
> >> + *mfn = _mfn(virt_to_mfn(gt->status[idx]));
> >> + return 0;
> >> +}
> >> +
> >> +/* caller must hold write lock */
> >> +static int gnttab_get_shared_frame_mfn(struct domain *d,
> >> + unsigned long idx, mfn_t *mfn)
> >> +{
> >> + struct grant_table *gt = d->grant_table;
> >> +
> >> + if ( (idx >= nr_grant_frames(gt)) && (idx < gt->max_grant_frames) )
> >> + gnttab_grow_table(d, idx + 1);
> >> +
> >> + if ( idx >= nr_grant_frames(gt) )
> >> + return -EINVAL;
> >> +
> >> + *mfn = _mfn(virt_to_mfn(gt->shared_raw[idx]));
> >> + return 0;
> >> +}
> >
> > I realize the anomaly was there already before, but imo it becomes
> > more pronounced with the two functions differing in more than just
> > the shared vs status naming (IOW I find it strange that one grows
> > the grant table while the other doesn't). This extends to ...
> >
> >> +int gnttab_get_shared_frame(struct domain *d, unsigned long idx,
> >> + mfn_t *mfn)
> >> +{
> >> + struct grant_table *gt = d->grant_table;
> >> + int rc;
> >> +
> >> + grant_write_lock(gt);
> >> + rc = gnttab_get_shared_frame_mfn(d, idx, mfn);
> >> + grant_write_unlock(gt);
> >> +
> >> + return rc;
> >> +}
> >> +
> >> +int gnttab_get_status_frame(struct domain *d, unsigned long idx,
> >> + mfn_t *mfn)
> >> +{
> >> + struct grant_table *gt = d->grant_table;
> >> + int rc;
> >> +
> >> + grant_read_lock(gt);
> >> + rc = gnttab_get_status_frame_mfn(d, idx, mfn);
> >> + grant_read_unlock(gt);
> >> +
> >> + return rc;
> >> +}
> >
> > ... these two acquiring the lock in different ways.
So, you want me to have gnttab_get_status_frame() grow the table accordingly? I'd really rather not do that at v19 of the series when it's never been part of the scope before.
> >
> > And then I'm completely missing the interaction with
> > gnttab_unpopulate_status_frames(). While this might not be a
> > practical problem at this point in time, we're liable to forget to
> > address this later on if there's no stop gap measure. A PV guest
> > mapping the obtained MFNs is going to be fine, but a HVM/PVH
> > one isn't, since neither x86 nor ARM refcount pages inserted into
> > or removed from a domain's p2m. I therefore think you need to
> > add a is_hvm_domain() check to acquire_grant_table(), with a
> > suitable fixme comment attached to it.
>
> Or perhaps better paging_mode_translate(current->domain).
>
Ok. I'll add the safety check and comment.
Paul
> Jan
_______________________________________________
Xen-devel mailing list
Xen-devel@lists.xenproject.org
https://lists.xenproject.org/mailman/listinfo/xen-devel
^ permalink raw reply [flat|nested] 30+ messages in thread* Re: [PATCH v18 10/11] common: add a new mappable resource type: XENMEM_resource_grant_table
2018-03-29 11:02 ` Paul Durrant
@ 2018-03-29 12:31 ` Jan Beulich
0 siblings, 0 replies; 30+ messages in thread
From: Jan Beulich @ 2018-03-29 12:31 UTC (permalink / raw)
To: Paul Durrant
Cc: Stefano Stabellini, Wei Liu, Andrew Cooper, Tim(Xen.org),
George Dunlap, Ian Jackson, xen-devel
>>> On 29.03.18 at 13:02, <Paul.Durrant@citrix.com> wrote:
>> From: Jan Beulich [mailto:JBeulich@suse.com]
>> Sent: 26 March 2018 13:55
>>
>> >>> On 26.03.18 at 14:16, <JBeulich@suse.com> wrote:
>> >>>> On 22.03.18 at 12:55, <paul.durrant@citrix.com> wrote:
>> >> --- a/xen/common/grant_table.c
>> >> +++ b/xen/common/grant_table.c
>> >> @@ -3863,6 +3863,35 @@ int mem_sharing_gref_to_gfn(struct
>> grant_table *gt, grant_ref_t ref,
>> >> }
>> >> #endif
>> >>
>> >> +/* caller must hold read or write lock */
>> >> +static int gnttab_get_status_frame_mfn(struct domain *d,
>> >> + unsigned long idx, mfn_t *mfn)
>> >> +{
>> >> + struct grant_table *gt = d->grant_table;
>> >> +
>> >> + if ( idx >= nr_status_frames(gt) )
>> >> + return -EINVAL;
>> >> +
>> >> + *mfn = _mfn(virt_to_mfn(gt->status[idx]));
>> >> + return 0;
>> >> +}
>> >> +
>> >> +/* caller must hold write lock */
>> >> +static int gnttab_get_shared_frame_mfn(struct domain *d,
>> >> + unsigned long idx, mfn_t *mfn)
>> >> +{
>> >> + struct grant_table *gt = d->grant_table;
>> >> +
>> >> + if ( (idx >= nr_grant_frames(gt)) && (idx < gt->max_grant_frames) )
>> >> + gnttab_grow_table(d, idx + 1);
>> >> +
>> >> + if ( idx >= nr_grant_frames(gt) )
>> >> + return -EINVAL;
>> >> +
>> >> + *mfn = _mfn(virt_to_mfn(gt->shared_raw[idx]));
>> >> + return 0;
>> >> +}
>> >
>> > I realize the anomaly was there already before, but imo it becomes
>> > more pronounced with the two functions differing in more than just
>> > the shared vs status naming (IOW I find it strange that one grows
>> > the grant table while the other doesn't). This extends to ...
>> >
>> >> +int gnttab_get_shared_frame(struct domain *d, unsigned long idx,
>> >> + mfn_t *mfn)
>> >> +{
>> >> + struct grant_table *gt = d->grant_table;
>> >> + int rc;
>> >> +
>> >> + grant_write_lock(gt);
>> >> + rc = gnttab_get_shared_frame_mfn(d, idx, mfn);
>> >> + grant_write_unlock(gt);
>> >> +
>> >> + return rc;
>> >> +}
>> >> +
>> >> +int gnttab_get_status_frame(struct domain *d, unsigned long idx,
>> >> + mfn_t *mfn)
>> >> +{
>> >> + struct grant_table *gt = d->grant_table;
>> >> + int rc;
>> >> +
>> >> + grant_read_lock(gt);
>> >> + rc = gnttab_get_status_frame_mfn(d, idx, mfn);
>> >> + grant_read_unlock(gt);
>> >> +
>> >> + return rc;
>> >> +}
>> >
>> > ... these two acquiring the lock in different ways.
>
> So, you want me to have gnttab_get_status_frame() grow the table
> accordingly? I'd really rather not do that at v19 of the series when it's
> never been part of the scope before.
Indeed, please only take this as a remark at this point in time.
It just so happens that when you look at something again after
a fair amount of time, you see things you haven't noticed before.
Jan
_______________________________________________
Xen-devel mailing list
Xen-devel@lists.xenproject.org
https://lists.xenproject.org/mailman/listinfo/xen-devel
^ permalink raw reply [flat|nested] 30+ messages in thread
* [PATCH v18 11/11] tools/libxenctrl: use new xenforeignmemory API to seed grant table
2018-03-22 11:55 [PATCH v18 00/11] x86: guest resource mapping Paul Durrant
` (9 preceding siblings ...)
2018-03-22 11:55 ` [PATCH v18 10/11] common: add a new mappable resource type: XENMEM_resource_grant_table Paul Durrant
@ 2018-03-22 11:55 ` Paul Durrant
10 siblings, 0 replies; 30+ messages in thread
From: Paul Durrant @ 2018-03-22 11:55 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>
v18:
- Trivial re-base.
v13:
- Re-base.
v10:
- Use new id constant for grant table.
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 491cad8114..cee2ac9901 100644
--- a/tools/libxc/include/xc_dom.h
+++ b/tools/libxc/include/xc_dom.h
@@ -332,12 +332,8 @@ 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, uint32_t domid,
- xen_pfn_t console_gmfn,
- xen_pfn_t xenstore_gmfn,
- uint32_t console_domid,
- uint32_t xenstore_domid);
-int xc_dom_gnttab_seed(xc_interface *xch, uint32_t domid,
+int xc_dom_gnttab_seed(xc_interface *xch, uint32_t guest_domid,
+ bool is_hvm,
xen_pfn_t console_gmfn,
xen_pfn_t xenstore_gmfn,
uint32_t console_domid,
diff --git a/tools/libxc/xc_dom_boot.c b/tools/libxc/xc_dom_boot.c
index 2e5681dc5d..8307ebeaf6 100644
--- a/tools/libxc/xc_dom_boot.c
+++ b/tools/libxc/xc_dom_boot.c
@@ -256,11 +256,29 @@ static xen_pfn_t xc_dom_gnttab_setup(xc_interface *xch, uint32_t domid)
return gmfn;
}
-int xc_dom_gnttab_seed(xc_interface *xch, uint32_t domid,
- xen_pfn_t console_gmfn,
- xen_pfn_t xenstore_gmfn,
- uint32_t console_domid,
- uint32_t xenstore_domid)
+static void xc_dom_set_gnttab_entry(xc_interface *xch,
+ grant_entry_v1_t *gnttab,
+ unsigned int idx,
+ uint32_t guest_domid,
+ uint32_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, uint32_t domid,
+ xen_pfn_t console_gmfn,
+ xen_pfn_t xenstore_gmfn,
+ uint32_t console_domid,
+ uint32_t xenstore_domid)
{
xen_pfn_t gnttab_gmfn;
@@ -284,18 +302,10 @@ int xc_dom_gnttab_seed(xc_interface *xch, uint32_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 )
{
@@ -313,11 +323,11 @@ int xc_dom_gnttab_seed(xc_interface *xch, uint32_t domid,
return 0;
}
-int xc_dom_gnttab_hvm_seed(xc_interface *xch, uint32_t domid,
- xen_pfn_t console_gpfn,
- xen_pfn_t xenstore_gpfn,
- uint32_t console_domid,
- uint32_t xenstore_domid)
+static int compat_gnttab_hvm_seed(xc_interface *xch, uint32_t domid,
+ xen_pfn_t console_gpfn,
+ xen_pfn_t xenstore_gpfn,
+ uint32_t console_domid,
+ uint32_t xenstore_domid)
{
int rc;
xen_pfn_t scratch_gpfn;
@@ -356,7 +366,7 @@ int xc_dom_gnttab_hvm_seed(xc_interface *xch, uint32_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)
@@ -381,18 +391,56 @@ int xc_dom_gnttab_hvm_seed(xc_interface *xch, uint32_t domid,
return 0;
}
-int xc_dom_gnttab_init(struct xc_dom_image *dom)
+int xc_dom_gnttab_seed(xc_interface *xch, uint32_t guest_domid,
+ bool is_hvm, xen_pfn_t console_gmfn,
+ xen_pfn_t xenstore_gmfn, uint32_t console_domid,
+ uint32_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,
+ XENMEM_resource_grant_table_id_shared, 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 227c48553e..4765a52f33 100644
--- a/tools/libxc/xc_sr_restore_x86_hvm.c
+++ b/tools/libxc/xc_sr_restore_x86_hvm.c
@@ -216,11 +216,11 @@ 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 d81dfdcca6..a2dbf85157 100644
--- a/tools/libxc/xc_sr_restore_x86_pv.c
+++ b/tools/libxc/xc_sr_restore_x86_pv.c
@@ -1105,7 +1105,7 @@ 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 2e29b52166..5610f0ae89 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.xenproject.org
https://lists.xenproject.org/mailman/listinfo/xen-devel
^ permalink raw reply related [flat|nested] 30+ messages in thread