moritzruth/void-packages
1
0
Fork 0
Code Releases Activity Actions 2

xen: update to 4.6.3.

Browse source
This commit is contained in:
Juan RP 2016-06-21 07:34:15 +02:00
parent fea0191f58
commit f8f6c883dc
6 changed files with 3 additions and 614 deletions
Download patch file Download diff file Expand all files Collapse all files

359
srcpkgs/xen/patches/xsa154-4.6.patch
View file

@ -1,359 +0,0 @@
x86: enforce consistent cachability of MMIO mappings
We've been told by Intel that inconsistent cachability between
multiple mappings of the same page can affect system stability only
when the affected page is an MMIO one. Since the stale data issue is
of no relevance to the hypervisor (since all guest memory accesses go
through proper accessors and validation), handling of RAM pages
remains unchanged here. Any MMIO mapped by domains however needs to be
done consistently (all cachable mappings or all uncachable ones), in
order to avoid Machine Check exceptions. Since converting existing
cachable mappings to uncachable (at the time an uncachable mapping
gets established) would in the PV case require tracking all mappings,
allow MMIO to only get mapped uncachable (UC, UC-, or WC).
This also implies that in the PV case we mustn't use the L1 PTE update
fast path when cachability flags get altered.
Since in the HVM case at least for now we want to continue honoring
pinned cachability attributes for pages not mapped by the hypervisor,
special case handling of r/o MMIO pages (forcing UC) gets added there.
Arguably the counterpart change to p2m-pt.c may not be necessary, since
UC- (which already gets enforced there) is probably strict enough.
Note that the shadow code changes include fixing the write protection
of r/o MMIO ranges: shadow_l1e_remove_flags() and its siblings, other
than l1e_remove_flags() and alike, return the new PTE (and hence
ignoring their return values makes them no-ops).
This is CVE-2016-2270 / XSA-154.
Signed-off-by: Jan Beulich <jbeulich@suse.com>
Acked-by: Andrew Cooper <andrew.cooper3@citrix.com>
--- a/docs/misc/xen-command-line.markdown
+++ b/docs/misc/xen-command-line.markdown
@@ -1080,6 +1080,15 @@ limit is ignored by Xen.
Specify if the MMConfig space should be enabled.
+### mmio-relax
+> `= <boolean> | all`
+
+> Default: `false`
+
+By default, domains may not create cached mappings to MMIO regions.
+This option relaxes the check for Domain 0 (or when using `all`, all PV
+domains), to permit the use of cacheable MMIO mappings.
+
### msi
> `= <boolean>`
--- a/xen/arch/x86/hvm/mtrr.c
+++ b/xen/arch/x86/hvm/mtrr.c
@@ -807,8 +807,17 @@ int epte_get_entry_emt(struct domain *d,
if ( v->domain != d )
v = d->vcpu ? d->vcpu[0] : NULL;
- if ( !mfn_valid(mfn_x(mfn)) )
+ if ( !mfn_valid(mfn_x(mfn)) ||
+ rangeset_contains_range(mmio_ro_ranges, mfn_x(mfn),
+ mfn_x(mfn) + (1UL << order) - 1) )
+ {
+ *ipat = 1;
return MTRR_TYPE_UNCACHABLE;
+ }
+
+ if ( rangeset_overlaps_range(mmio_ro_ranges, mfn_x(mfn),
+ mfn_x(mfn) + (1UL << order) - 1) )
+ return -1;
switch ( hvm_get_mem_pinned_cacheattr(d, gfn, order, &type) )
{
--- a/xen/arch/x86/mm/p2m-pt.c
+++ b/xen/arch/x86/mm/p2m-pt.c
@@ -107,6 +107,8 @@ static unsigned long p2m_type_to_flags(p
case p2m_mmio_direct:
if ( !rangeset_contains_singleton(mmio_ro_ranges, mfn_x(mfn)) )
flags |= _PAGE_RW;
+ else
+ flags |= _PAGE_PWT;
return flags | P2M_BASE_FLAGS | _PAGE_PCD;
}
}
--- a/xen/arch/x86/mm/shadow/multi.c
+++ b/xen/arch/x86/mm/shadow/multi.c
@@ -519,6 +519,7 @@ _sh_propagate(struct vcpu *v,
gfn_t target_gfn = guest_l1e_get_gfn(guest_entry);
u32 pass_thru_flags;
u32 gflags, sflags;
+ bool_t mmio_mfn;
/* We don't shadow PAE l3s */
ASSERT(GUEST_PAGING_LEVELS > 3 || level != 3);
@@ -559,7 +560,10 @@ _sh_propagate(struct vcpu *v,
// mfn means that we can not usefully shadow anything, and so we
// return early.
//
- if ( !mfn_valid(target_mfn)
+ mmio_mfn = !mfn_valid(target_mfn)
+ || (level == 1
+ && page_get_owner(mfn_to_page(target_mfn)) == dom_io);
+ if ( mmio_mfn
&& !(level == 1 && (!shadow_mode_refcounts(d)
|| p2mt == p2m_mmio_direct)) )
{
@@ -577,7 +581,7 @@ _sh_propagate(struct vcpu *v,
_PAGE_RW | _PAGE_PRESENT);
if ( guest_supports_nx(v) )
pass_thru_flags |= _PAGE_NX_BIT;
- if ( !shadow_mode_refcounts(d) && !mfn_valid(target_mfn) )
+ if ( level == 1 && !shadow_mode_refcounts(d) && mmio_mfn )
pass_thru_flags |= _PAGE_PAT | _PAGE_PCD | _PAGE_PWT;
sflags = gflags & pass_thru_flags;
@@ -676,10 +680,14 @@ _sh_propagate(struct vcpu *v,
}
/* Read-only memory */
- if ( p2m_is_readonly(p2mt) ||
- (p2mt == p2m_mmio_direct &&
- rangeset_contains_singleton(mmio_ro_ranges, mfn_x(target_mfn))) )
+ if ( p2m_is_readonly(p2mt) )
sflags &= ~_PAGE_RW;
+ else if ( p2mt == p2m_mmio_direct &&
+ rangeset_contains_singleton(mmio_ro_ranges, mfn_x(target_mfn)) )
+ {
+ sflags &= ~(_PAGE_RW | _PAGE_PAT);
+ sflags |= _PAGE_PCD | _PAGE_PWT;
+ }
// protect guest page tables
//
@@ -1185,22 +1193,28 @@ static int shadow_set_l1e(struct domain
&& !sh_l1e_is_magic(new_sl1e) )
{
/* About to install a new reference */
- if ( shadow_mode_refcounts(d) ) {
+ if ( shadow_mode_refcounts(d) )
+ {
+#define PAGE_FLIPPABLE (_PAGE_RW | _PAGE_PWT | _PAGE_PCD | _PAGE_PAT)
+ int rc;
+
TRACE_SHADOW_PATH_FLAG(TRCE_SFLAG_SHADOW_L1_GET_REF);
- switch ( shadow_get_page_from_l1e(new_sl1e, d, new_type) )
+ switch ( rc = shadow_get_page_from_l1e(new_sl1e, d, new_type) )
{
default:
/* Doesn't look like a pagetable. */
flags |= SHADOW_SET_ERROR;
new_sl1e = shadow_l1e_empty();
break;
- case 1:
- shadow_l1e_remove_flags(new_sl1e, _PAGE_RW);
+ case PAGE_FLIPPABLE & -PAGE_FLIPPABLE ... PAGE_FLIPPABLE:
+ ASSERT(!(rc & ~PAGE_FLIPPABLE));
+ new_sl1e = shadow_l1e_flip_flags(new_sl1e, rc);
/* fall through */
case 0:
shadow_vram_get_l1e(new_sl1e, sl1e, sl1mfn, d);
break;
}
+#undef PAGE_FLIPPABLE
}
}
--- a/xen/arch/x86/mm/shadow/types.h
+++ b/xen/arch/x86/mm/shadow/types.h
@@ -99,6 +99,9 @@ static inline u32 shadow_l4e_get_flags(s
static inline shadow_l1e_t
shadow_l1e_remove_flags(shadow_l1e_t sl1e, u32 flags)
{ l1e_remove_flags(sl1e, flags); return sl1e; }
+static inline shadow_l1e_t
+shadow_l1e_flip_flags(shadow_l1e_t sl1e, u32 flags)
+{ l1e_flip_flags(sl1e, flags); return sl1e; }
static inline shadow_l1e_t shadow_l1e_empty(void)
{ return l1e_empty(); }
--- a/xen/arch/x86/mm.c
+++ b/xen/arch/x86/mm.c
@@ -178,6 +178,18 @@ static uint32_t base_disallow_mask;
is_pv_domain(d)) ? \
L1_DISALLOW_MASK : (L1_DISALLOW_MASK & ~PAGE_CACHE_ATTRS))
+static s8 __read_mostly opt_mmio_relax;
+static void __init parse_mmio_relax(const char *s)
+{
+ if ( !*s )
+ opt_mmio_relax = 1;
+ else
+ opt_mmio_relax = parse_bool(s);
+ if ( opt_mmio_relax < 0 && strcmp(s, "all") )
+ opt_mmio_relax = 0;
+}
+custom_param("mmio-relax", parse_mmio_relax);
+
static void __init init_frametable_chunk(void *start, void *end)
{
unsigned long s = (unsigned long)start;
@@ -799,10 +811,7 @@ get_page_from_l1e(
if ( !mfn_valid(mfn) ||
(real_pg_owner = page_get_owner_and_reference(page)) == dom_io )
{
-#ifndef NDEBUG
- const unsigned long *ro_map;
- unsigned int seg, bdf;
-#endif
+ int flip = 0;
/* Only needed the reference to confirm dom_io ownership. */
if ( mfn_valid(mfn) )
@@ -836,24 +845,55 @@ get_page_from_l1e(
return -EINVAL;
}
- if ( !(l1f & _PAGE_RW) ||
- !rangeset_contains_singleton(mmio_ro_ranges, mfn) )
- return 0;
+ if ( !rangeset_contains_singleton(mmio_ro_ranges, mfn) )
+ {
+ /* MMIO pages must not be mapped cachable unless requested so. */
+ switch ( opt_mmio_relax )
+ {
+ case 0:
+ break;
+ case 1:
+ if ( is_hardware_domain(l1e_owner) )
+ case -1:
+ return 0;
+ default:
+ ASSERT_UNREACHABLE();
+ }
+ }
+ else if ( l1f & _PAGE_RW )
+ {
#ifndef NDEBUG
- if ( !pci_mmcfg_decode(mfn, &seg, &bdf) ||
- ((ro_map = pci_get_ro_map(seg)) != NULL &&
- test_bit(bdf, ro_map)) )
- printk(XENLOG_G_WARNING
- "d%d: Forcing read-only access to MFN %lx\n",
- l1e_owner->domain_id, mfn);
- else
- rangeset_report_ranges(mmio_ro_ranges, 0, ~0UL,
- print_mmio_emul_range,
- &(struct mmio_emul_range_ctxt){
- .d = l1e_owner,
- .mfn = mfn });
+ const unsigned long *ro_map;
+ unsigned int seg, bdf;
+
+ if ( !pci_mmcfg_decode(mfn, &seg, &bdf) ||
+ ((ro_map = pci_get_ro_map(seg)) != NULL &&
+ test_bit(bdf, ro_map)) )
+ printk(XENLOG_G_WARNING
+ "d%d: Forcing read-only access to MFN %lx\n",
+ l1e_owner->domain_id, mfn);
+ else
+ rangeset_report_ranges(mmio_ro_ranges, 0, ~0UL,
+ print_mmio_emul_range,
+ &(struct mmio_emul_range_ctxt){
+ .d = l1e_owner,
+ .mfn = mfn });
#endif
- return 1;
+ flip = _PAGE_RW;
+ }
+
+ switch ( l1f & PAGE_CACHE_ATTRS )
+ {
+ case 0: /* WB */
+ flip |= _PAGE_PWT | _PAGE_PCD;
+ break;
+ case _PAGE_PWT: /* WT */
+ case _PAGE_PWT | _PAGE_PAT: /* WP */
+ flip |= _PAGE_PCD | (l1f & _PAGE_PAT);
+ break;
+ }
+
+ return flip;
}
if ( unlikely( (real_pg_owner != pg_owner) &&
@@ -1243,8 +1283,9 @@ static int alloc_l1_table(struct page_in
goto fail;
case 0:
break;
- case 1:
- l1e_remove_flags(pl1e[i], _PAGE_RW);
+ case _PAGE_RW ... _PAGE_RW | PAGE_CACHE_ATTRS:
+ ASSERT(!(ret & ~(_PAGE_RW | PAGE_CACHE_ATTRS)));
+ l1e_flip_flags(pl1e[i], ret);
break;
}
@@ -1759,8 +1800,9 @@ static int mod_l1_entry(l1_pgentry_t *pl
return -EINVAL;
}
- /* Fast path for identical mapping, r/w and presence. */
- if ( !l1e_has_changed(ol1e, nl1e, _PAGE_RW | _PAGE_PRESENT) )
+ /* Fast path for identical mapping, r/w, presence, and cachability. */
+ if ( !l1e_has_changed(ol1e, nl1e,
+ PAGE_CACHE_ATTRS | _PAGE_RW | _PAGE_PRESENT) )
{
adjust_guest_l1e(nl1e, pt_dom);
if ( UPDATE_ENTRY(l1, pl1e, ol1e, nl1e, gl1mfn, pt_vcpu,
@@ -1783,8 +1825,9 @@ static int mod_l1_entry(l1_pgentry_t *pl
return rc;
case 0:
break;
- case 1:
- l1e_remove_flags(nl1e, _PAGE_RW);
+ case _PAGE_RW ... _PAGE_RW | PAGE_CACHE_ATTRS:
+ ASSERT(!(rc & ~(_PAGE_RW | PAGE_CACHE_ATTRS)));
+ l1e_flip_flags(nl1e, rc);
rc = 0;
break;
}
@@ -5000,6 +5043,7 @@ static int ptwr_emulated_update(
l1_pgentry_t pte, ol1e, nl1e, *pl1e;
struct vcpu *v = current;
struct domain *d = v->domain;
+ int ret;
/* Only allow naturally-aligned stores within the original %cr2 page. */
if ( unlikely(((addr^ptwr_ctxt->cr2) & PAGE_MASK) || (addr & (bytes-1))) )
@@ -5047,7 +5091,7 @@ static int ptwr_emulated_update(
/* Check the new PTE. */
nl1e = l1e_from_intpte(val);
- switch ( get_page_from_l1e(nl1e, d, d) )
+ switch ( ret = get_page_from_l1e(nl1e, d, d) )
{
default:
if ( is_pv_32bit_domain(d) && (bytes == 4) && (unaligned_addr & 4) &&
@@ -5071,8 +5115,9 @@ static int ptwr_emulated_update(
break;
case 0:
break;
- case 1:
- l1e_remove_flags(nl1e, _PAGE_RW);
+ case _PAGE_RW ... _PAGE_RW | PAGE_CACHE_ATTRS:
+ ASSERT(!(ret & ~(_PAGE_RW | PAGE_CACHE_ATTRS)));
+ l1e_flip_flags(nl1e, ret);
break;
}
--- a/xen/include/asm-x86/page.h
+++ b/xen/include/asm-x86/page.h
@@ -157,6 +157,9 @@ static inline l4_pgentry_t l4e_from_padd
#define l3e_remove_flags(x, flags) ((x).l3 &= ~put_pte_flags(flags))
#define l4e_remove_flags(x, flags) ((x).l4 &= ~put_pte_flags(flags))
+/* Flip flags in an existing L1 PTE. */
+#define l1e_flip_flags(x, flags) ((x).l1 ^= put_pte_flags(flags))
+
/* Check if a pte's page mapping or significant access flags have changed. */
#define l1e_has_changed(x,y,flags) \
( !!(((x).l1 ^ (y).l1) & ((PADDR_MASK&PAGE_MASK)|put_pte_flags(flags))) )

56
srcpkgs/xen/patches/xsa155-xen-0001-xen-Add-RING_COPY_REQUEST.patch
View file

@ -1,56 +0,0 @@
From 12b11658a9d6a654a1e7acbf2f2d56ce9a396c86 Mon Sep 17 00:00:00 2001
From: David Vrabel <david.vrabel@citrix.com>
Date: Fri, 20 Nov 2015 11:59:05 -0500
Subject: [PATCH 1/3] xen: Add RING_COPY_REQUEST()
Using RING_GET_REQUEST() on a shared ring is easy to use incorrectly
(i.e., by not considering that the other end may alter the data in the
shared ring while it is being inspected). Safe usage of a request
generally requires taking a local copy.
Provide a RING_COPY_REQUEST() macro to use instead of
RING_GET_REQUEST() and an open-coded memcpy(). This takes care of
ensuring that the copy is done correctly regardless of any possible
compiler optimizations.
Use a volatile source to prevent the compiler from reordering or
omitting the copy.
This is part of XSA155.
Signed-off-by: David Vrabel <david.vrabel@citrix.com>
Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
---
v2: Add comment about GCC bug.
---
xen/include/public/io/ring.h | 14 ++++++++++++++
1 file changed, 14 insertions(+)
diff --git a/xen/include/public/io/ring.h b/xen/include/public/io/ring.h
index ba9401b..801c0da 100644
--- a/xen/include/public/io/ring.h
+++ b/xen/include/public/io/ring.h
@@ -212,6 +212,20 @@ typedef struct __name##_back_ring __name##_back_ring_t
#define RING_GET_REQUEST(_r, _idx) \
(&((_r)->sring->ring[((_idx) & (RING_SIZE(_r) - 1))].req))
+/*
+ * Get a local copy of a request.
+ *
+ * Use this in preference to RING_GET_REQUEST() so all processing is
+ * done on a local copy that cannot be modified by the other end.
+ *
+ * Note that https://gcc.gnu.org/bugzilla/show_bug.cgi?id=58145 may cause this
+ * to be ineffective where _req is a struct which consists of only bitfields.
+ */
+#define RING_COPY_REQUEST(_r, _idx, _req) do { \
+ /* Use volatile to force the copy into _req. */ \
+ *(_req) = *(volatile typeof(_req))RING_GET_REQUEST(_r, _idx); \
+} while (0)
+
#define RING_GET_RESPONSE(_r, _idx) \
(&((_r)->sring->ring[((_idx) & (RING_SIZE(_r) - 1))].rsp))
--
2.1.0

75
srcpkgs/xen/patches/xsa155-xen-0002-blktap2-Use-RING_COPY_REQUEST.patch
View file

@ -1,75 +0,0 @@
From 851ffb4eea917e2708c912291dea4d133026c0ac Mon Sep 17 00:00:00 2001
From: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Date: Fri, 20 Nov 2015 12:16:02 -0500
Subject: [PATCH 2/3] blktap2: Use RING_COPY_REQUEST
Instead of RING_GET_REQUEST. Using a local copy of the
ring (and also with proper memory barriers) will mean
we can do not have to worry about the compiler optimizing
the code and doing a double-fetch in the shared memory space.
This is part of XSA155.
Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
---
v2: Fix compile issues with tapdisk-vbd
---
tools/blktap2/drivers/block-log.c | 3 ++-
tools/blktap2/drivers/tapdisk-vbd.c | 8 ++++----
2 files changed, 6 insertions(+), 5 deletions(-)
diff --git a/tools/blktap2/drivers/block-log.c b/tools/blktap2/drivers/block-log.c
index 5330cdc..5f3bd35 100644
--- a/tools/blktap2/drivers/block-log.c
+++ b/tools/blktap2/drivers/block-log.c
@@ -494,11 +494,12 @@ static int ctl_kick(struct tdlog_state* s, int fd)
reqstart = s->bring.req_cons;
reqend = s->sring->req_prod;
+ xen_mb();
BDPRINTF("ctl: ring kicked (start = %u, end = %u)", reqstart, reqend);
while (reqstart != reqend) {
/* XXX actually submit these! */
- memcpy(&req, RING_GET_REQUEST(&s->bring, reqstart), sizeof(req));
+ RING_COPY_REQUEST(&s->bring, reqstart, &req);
BDPRINTF("ctl: read request %"PRIu64":%u", req.sector, req.count);
s->bring.req_cons = ++reqstart;
diff --git a/tools/blktap2/drivers/tapdisk-vbd.c b/tools/blktap2/drivers/tapdisk-vbd.c
index 6d1d94a..89ef9ed 100644
--- a/tools/blktap2/drivers/tapdisk-vbd.c
+++ b/tools/blktap2/drivers/tapdisk-vbd.c
@@ -1555,7 +1555,7 @@ tapdisk_vbd_pull_ring_requests(td_vbd_t *vbd)
int idx;
RING_IDX rp, rc;
td_ring_t *ring;
- blkif_request_t *req;
+ blkif_request_t req;
td_vbd_request_t *vreq;
ring = &vbd->ring;
@@ -1566,16 +1566,16 @@ tapdisk_vbd_pull_ring_requests(td_vbd_t *vbd)
xen_rmb();
for (rc = ring->fe_ring.req_cons; rc != rp; rc++) {
- req = RING_GET_REQUEST(&ring->fe_ring, rc);
+ RING_COPY_REQUEST(&ring->fe_ring, rc, &req);
++ring->fe_ring.req_cons;
- idx = req->id;
+ idx = req.id;
vreq = &vbd->request_list[idx];
ASSERT(list_empty(&vreq->next));
ASSERT(vreq->secs_pending == 0);
- memcpy(&vreq->req, req, sizeof(blkif_request_t));
+ memcpy(&vreq->req, &req, sizeof(blkif_request_t));
vbd->received++;
vreq->vbd = vbd;
--
2.1.4

41
srcpkgs/xen/patches/xsa155-xen-0003-libvchan-Read-prod-cons-only-once.patch
View file

@ -1,41 +0,0 @@
From c1fce65e2b720684ea6ba76ae59921542bd154bb Mon Sep 17 00:00:00 2001
From: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Date: Fri, 20 Nov 2015 12:22:14 -0500
Subject: [PATCH 3/3] libvchan: Read prod/cons only once.
We must ensure that the prod/cons are only read once and that
the compiler won't try to optimize the reads. That is split
the read of these in multiple instructions influencing later
branch code. As such insert barriers when fetching the cons
and prod index.
This is part of XSA155.
Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
---
tools/libvchan/io.c | 2 ++
1 file changed, 2 insertions(+)
diff --git a/tools/libvchan/io.c b/tools/libvchan/io.c
index 8a9629b..381cc05 100644
--- a/tools/libvchan/io.c
+++ b/tools/libvchan/io.c
@@ -117,6 +117,7 @@ static inline int send_notify(struct libxenvchan *ctrl, uint8_t bit)
static inline int raw_get_data_ready(struct libxenvchan *ctrl)
{
uint32_t ready = rd_prod(ctrl) - rd_cons(ctrl);
+ xen_mb(); /* Ensure 'ready' is read only once. */
if (ready > rd_ring_size(ctrl))
/* We have no way to return errors. Locking up the ring is
* better than the alternatives. */
@@ -158,6 +159,7 @@ int libxenvchan_data_ready(struct libxenvchan *ctrl)
static inline int raw_get_buffer_space(struct libxenvchan *ctrl)
{
uint32_t ready = wr_ring_size(ctrl) - (wr_prod(ctrl) - wr_cons(ctrl));
+ xen_mb(); /* Ensure 'ready' is read only once. */
if (ready > wr_ring_size(ctrl))
/* We have no way to return errors. Locking up the ring is
* better than the alternatives. */
--
2.1.0

79
srcpkgs/xen/patches/xsa170.patch
View file

@ -1,79 +0,0 @@
x86/VMX: sanitize rIP before re-entering guest
... to prevent guest user mode arranging for a guest crash (due to
failed VM entry). (On the AMD system I checked, hardware is doing
exactly the canonicalization being added here.)
Note that fixing this in an architecturally correct way would be quite
a bit more involved: Making the x86 instruction emulator check all
branch targets for validity, plus dealing with invalid rIP resulting
from update_guest_eip() or incoming directly during a VM exit. The only
way to get the latter right would be by not having hardware do the
injection.
Note further that there are a two early returns from
vmx_vmexit_handler(): One (through vmx_failed_vmentry()) leads to
domain_crash() anyway, and the other covers real mode only and can
neither occur with a non-canonical rIP nor result in an altered rIP,
so we don't need to force those paths through the checking logic.
This is XSA-170.
Reported-by: 刘令 <liuling-it@360.cn>
Signed-off-by: Jan Beulich <jbeulich@suse.com>
Reviewed-by: Andrew Cooper <andrew.cooper3@citrix.com>
Tested-by: Andrew Cooper <andrew.cooper3@citrix.com>
--- a/xen/arch/x86/hvm/vmx/vmx.c
+++ b/xen/arch/x86/hvm/vmx/vmx.c
@@ -2968,7 +2968,7 @@ static int vmx_handle_apic_write(void)
void vmx_vmexit_handler(struct cpu_user_regs *regs)
{
unsigned long exit_qualification, exit_reason, idtv_info, intr_info = 0;
- unsigned int vector = 0;
+ unsigned int vector = 0, mode;
struct vcpu *v = current;
__vmread(GUEST_RIP, &regs->rip);
@@ -3566,6 +3566,41 @@ void vmx_vmexit_handler(struct cpu_user_
out:
if ( nestedhvm_vcpu_in_guestmode(v) )
nvmx_idtv_handling();
+
+ /*
+ * VM entry will fail (causing the guest to get crashed) if rIP (and
+ * rFLAGS, but we don't have an issue there) doesn't meet certain
+ * criteria. As we must not allow less than fully privileged mode to have
+ * such an effect on the domain, we correct rIP in that case (accepting
+ * this not being architecturally correct behavior, as the injected #GP
+ * fault will then not see the correct [invalid] return address).
+ * And since we know the guest will crash, we crash it right away if it
+ * already is in most privileged mode.
+ */
+ mode = vmx_guest_x86_mode(v);
+ if ( mode == 8 ? !is_canonical_address(regs->rip)
+ : regs->rip != regs->_eip )
+ {
+ struct segment_register ss;
+
+ gprintk(XENLOG_WARNING, "Bad rIP %lx for mode %u\n", regs->rip, mode);
+
+ vmx_get_segment_register(v, x86_seg_ss, &ss);
+ if ( ss.attr.fields.dpl )
+ {
+ __vmread(VM_ENTRY_INTR_INFO, &intr_info);
+ if ( !(intr_info & INTR_INFO_VALID_MASK) )
+ hvm_inject_hw_exception(TRAP_gp_fault, 0);
+ /* Need to fix rIP nevertheless. */
+ if ( mode == 8 )
+ regs->rip = (long)(regs->rip << (64 - VADDR_BITS)) >>
+ (64 - VADDR_BITS);
+ else
+ regs->rip = regs->_eip;
+ }
+ else
+ domain_crash(v->domain);
+ }
}
void vmx_vmenter_helper(const struct cpu_user_regs *regs)

7
srcpkgs/xen/template
View file

@ -1,14 +1,13 @@
# Template file for 'xen' # Template file for 'xen'
pkgname=xen pkgname=xen
version=4.6.1 version=4.6.3
revision=3 revision=1
short_desc="The Xen hypervisor utilities" short_desc="The Xen hypervisor utilities"
maintainer="Juan RP <xtraeme@voidlinux.eu>" maintainer="Juan RP <xtraeme@voidlinux.eu>"
homepage="http://xen.org" homepage="http://xen.org"
license="GPL-2" license="GPL-2"
distfiles="http://bits.xensource.com/oss-xen/release/$version/xen-$version.tar.gz" distfiles="http://bits.xensource.com/oss-xen/release/$version/xen-$version.tar.gz"
checksum=44cc2fccba1e147ef4c8da0584ce0f24189c8743de0e3e9a9226da88ddb5f589 checksum=02badfce9a037bd1bd4a94210c1f6b85467746216c71795805102b514bcf1fc4
patch_args="-Np1" patch_args="-Np1"
only_for_archs="x86_64 x86_64-musl" only_for_archs="x86_64 x86_64-musl"