This series spins off from CET KVM virtualization enabling series [1].
The purpose is to get these preparation work resolved ahead of KVM part
landing. There was a discussion about introducing CET supervisor state
support [2] [3].
CET supervisor state, i.e., IA32_PL{0,1,2}_SSP, are xsave-managed MSRs,
it can be enabled via IA32_XSS[bit 12]. KVM relies on host side CET
supervisor state support to fully enable guest CET MSR contents storage.
The benefits are: 1) No need to manually save/restore the 3 MSRs when
vCPU fpu context is sched in/out. 2) Omit manually swapping the three
MSRs at VM-Exit/VM-Entry for guest/host. 3) Make guest CET user/supervisor
states managed in a consistent manner within host kernel FPU framework.
This series tries to:
1) Fix existing issue regarding enabling guest supervisor states support.
2) Add CET supervisor state support in core kernel.
3) Introduce new FPU config for guest fpstate setup.
With the preparation work landed, for guest fpstate, we have xstate_bv[12]
== xcomp_bv[12] == 1 and CET supervisor state is saved/reloaded when
xsaves/xrstors executes on guest fpstate.
For non-guest/normal fpstate, we have xstate_bv[12] == xcomp_bv[12] == 0,
then HW can optimize xsaves/xrstors operations.
Patch1: Preserve guest supervisor xfeatures in __state_perm.
Patch2: Enable CET supervisor xstate support.
Patch3: Introduce kernel dynamic xfeature set.
Patch4: Initialize fpu_guest_cfg settings.
Patch5: Create guest fpstate with fpu_guest_cfg.
Patch6: Check invalid fpstate config before executes xsaves.
[1]: https://lore.kernel.org/all/[email protected]/
[2]: https://lore.kernel.org/all/[email protected]/
[3]: https://lore.kernel.org/all/[email protected]/
Sean Christopherson (1):
x86/fpu/xstate: Always preserve non-user xfeatures/flags in
__state_perm
Yang Weijiang (5):
x86/fpu/xstate: Add CET supervisor mode state support
x86/fpu/xstate: Introduce XFEATURE_MASK_KERNEL_DYNAMIC xfeature set
x86/fpu/xstate: Introduce fpu_guest_cfg for guest FPU configuration
x86/fpu/xstate: Create guest fpstate with guest specific config
x86/fpu/xstate: Warn if CET supervisor state is detected in normal
fpstate
arch/x86/include/asm/fpu/types.h | 16 ++++++++--
arch/x86/include/asm/fpu/xstate.h | 11 ++++---
arch/x86/kernel/fpu/core.c | 53 ++++++++++++++++++++++++-------
arch/x86/kernel/fpu/xstate.c | 35 +++++++++++++++-----
arch/x86/kernel/fpu/xstate.h | 2 ++
5 files changed, 90 insertions(+), 27 deletions(-)
base-commit: 1613e604df0cd359cf2a7fbd9be7a0bcfacfabd0
--
2.43.0
Add supervisor mode state support within FPU xstate management framework.
Although supervisor shadow stack is not enabled/used today in kernel,KVM
requires the support because when KVM advertises shadow stack feature to
guest, architecturally it claims the support for both user and supervisor
modes for guest OSes(Linux or non-Linux).
CET supervisor states not only includes PL{0,1,2}_SSP but also IA32_S_CET
MSR, but the latter is not xsave-managed. In virtualization world, guest
IA32_S_CET is saved/stored into/from VM control structure. With supervisor
xstate support, guest supervisor mode shadow stack state can be properly
saved/restored when 1) guest/host FPU context is swapped 2) vCPU
thread is sched out/in.
The alternative is to enable it in KVM domain, but KVM maintainers NAKed
the solution. The external discussion can be found at [*], it ended up
with adding the support in kernel instead of KVM domain.
Note, in KVM case, guest CET supervisor state i.e., IA32_PL{0,1,2}_MSRs,
are preserved after VM-Exit until host/guest fpstates are swapped, but
since host supervisor shadow stack is disabled, the preserved MSRs won't
hurt host.
[*]: https://lore.kernel.org/all/[email protected]/
Signed-off-by: Yang Weijiang <[email protected]>
Reviewed-by: Rick Edgecombe <[email protected]>
Reviewed-by: Maxim Levitsky <[email protected]>
---
arch/x86/include/asm/fpu/types.h | 14 ++++++++++++--
arch/x86/include/asm/fpu/xstate.h | 6 +++---
arch/x86/kernel/fpu/xstate.c | 6 +++++-
3 files changed, 20 insertions(+), 6 deletions(-)
diff --git a/arch/x86/include/asm/fpu/types.h b/arch/x86/include/asm/fpu/types.h
index eb17f31b06d2..d633cf833411 100644
--- a/arch/x86/include/asm/fpu/types.h
+++ b/arch/x86/include/asm/fpu/types.h
@@ -118,7 +118,7 @@ enum xfeature {
XFEATURE_PKRU,
XFEATURE_PASID,
XFEATURE_CET_USER,
- XFEATURE_CET_KERNEL_UNUSED,
+ XFEATURE_CET_KERNEL,
XFEATURE_RSRVD_COMP_13,
XFEATURE_RSRVD_COMP_14,
XFEATURE_LBR,
@@ -141,7 +141,7 @@ enum xfeature {
#define XFEATURE_MASK_PKRU (1 << XFEATURE_PKRU)
#define XFEATURE_MASK_PASID (1 << XFEATURE_PASID)
#define XFEATURE_MASK_CET_USER (1 << XFEATURE_CET_USER)
-#define XFEATURE_MASK_CET_KERNEL (1 << XFEATURE_CET_KERNEL_UNUSED)
+#define XFEATURE_MASK_CET_KERNEL (1 << XFEATURE_CET_KERNEL)
#define XFEATURE_MASK_LBR (1 << XFEATURE_LBR)
#define XFEATURE_MASK_XTILE_CFG (1 << XFEATURE_XTILE_CFG)
#define XFEATURE_MASK_XTILE_DATA (1 << XFEATURE_XTILE_DATA)
@@ -266,6 +266,16 @@ struct cet_user_state {
u64 user_ssp;
};
+/*
+ * State component 12 is Control-flow Enforcement supervisor states
+ */
+struct cet_supervisor_state {
+ /* supervisor ssp pointers */
+ u64 pl0_ssp;
+ u64 pl1_ssp;
+ u64 pl2_ssp;
+};
+
/*
* State component 15: Architectural LBR configuration state.
* The size of Arch LBR state depends on the number of LBRs (lbr_depth).
diff --git a/arch/x86/include/asm/fpu/xstate.h b/arch/x86/include/asm/fpu/xstate.h
index d4427b88ee12..3b4a038d3c57 100644
--- a/arch/x86/include/asm/fpu/xstate.h
+++ b/arch/x86/include/asm/fpu/xstate.h
@@ -51,7 +51,8 @@
/* All currently supported supervisor features */
#define XFEATURE_MASK_SUPERVISOR_SUPPORTED (XFEATURE_MASK_PASID | \
- XFEATURE_MASK_CET_USER)
+ XFEATURE_MASK_CET_USER | \
+ XFEATURE_MASK_CET_KERNEL)
/*
* A supervisor state component may not always contain valuable information,
@@ -78,8 +79,7 @@
* Unsupported supervisor features. When a supervisor feature in this mask is
* supported in the future, move it to the supported supervisor feature mask.
*/
-#define XFEATURE_MASK_SUPERVISOR_UNSUPPORTED (XFEATURE_MASK_PT | \
- XFEATURE_MASK_CET_KERNEL)
+#define XFEATURE_MASK_SUPERVISOR_UNSUPPORTED (XFEATURE_MASK_PT)
/* All supervisor states including supported and unsupported states. */
#define XFEATURE_MASK_SUPERVISOR_ALL (XFEATURE_MASK_SUPERVISOR_SUPPORTED | \
diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c
index bc66183c7df2..84d4fcaeff35 100644
--- a/arch/x86/kernel/fpu/xstate.c
+++ b/arch/x86/kernel/fpu/xstate.c
@@ -51,7 +51,7 @@ static const char *xfeature_names[] =
"Protection Keys User registers",
"PASID state",
"Control-flow User registers",
- "Control-flow Kernel registers (unused)",
+ "Control-flow Kernel registers",
"unknown xstate feature",
"unknown xstate feature",
"unknown xstate feature",
@@ -74,6 +74,7 @@ static unsigned short xsave_cpuid_features[] __initdata = {
[XFEATURE_PKRU] = X86_FEATURE_OSPKE,
[XFEATURE_PASID] = X86_FEATURE_ENQCMD,
[XFEATURE_CET_USER] = X86_FEATURE_SHSTK,
+ [XFEATURE_CET_KERNEL] = X86_FEATURE_SHSTK,
[XFEATURE_XTILE_CFG] = X86_FEATURE_AMX_TILE,
[XFEATURE_XTILE_DATA] = X86_FEATURE_AMX_TILE,
};
@@ -279,6 +280,7 @@ static void __init print_xstate_features(void)
print_xstate_feature(XFEATURE_MASK_PKRU);
print_xstate_feature(XFEATURE_MASK_PASID);
print_xstate_feature(XFEATURE_MASK_CET_USER);
+ print_xstate_feature(XFEATURE_MASK_CET_KERNEL);
print_xstate_feature(XFEATURE_MASK_XTILE_CFG);
print_xstate_feature(XFEATURE_MASK_XTILE_DATA);
}
@@ -348,6 +350,7 @@ static __init void os_xrstor_booting(struct xregs_state *xstate)
XFEATURE_MASK_BNDCSR | \
XFEATURE_MASK_PASID | \
XFEATURE_MASK_CET_USER | \
+ XFEATURE_MASK_CET_KERNEL | \
XFEATURE_MASK_XTILE)
/*
@@ -548,6 +551,7 @@ static bool __init check_xstate_against_struct(int nr)
case XFEATURE_PASID: return XCHECK_SZ(sz, nr, struct ia32_pasid_state);
case XFEATURE_XTILE_CFG: return XCHECK_SZ(sz, nr, struct xtile_cfg);
case XFEATURE_CET_USER: return XCHECK_SZ(sz, nr, struct cet_user_state);
+ case XFEATURE_CET_KERNEL: return XCHECK_SZ(sz, nr, struct cet_supervisor_state);
case XFEATURE_XTILE_DATA: check_xtile_data_against_struct(sz); return true;
default:
XSTATE_WARN_ON(1, "No structure for xstate: %d\n", nr);
--
2.43.0
Define a new XFEATURE_MASK_KERNEL_DYNAMIC mask to specify the features
that can be optionally enabled by kernel components. This is similar to
XFEATURE_MASK_USER_DYNAMIC in that it contains optional xfeatures that
can allows the FPU buffer to be dynamically sized. The difference is that
the KERNEL variant contains supervisor features and will be enabled by
kernel components that need them, and not directly by the user. Currently
it's used by KVM to configure guest dedicated fpstate for calculating
the xfeature and fpstate storage size etc.
The kernel dynamic xfeatures now only contain XFEATURE_CET_KERNEL, which
is supported by host as they're enabled in kernel XSS MSR setting but
relevant CPU feature, i.e., supervisor shadow stack, is not enabled in
host kernel therefore it can be omitted for normal fpstate by default.
Remove the kernel dynamic feature from fpu_kernel_cfg.default_features
so that the bits in xstate_bv and xcomp_bv are cleared and xsaves/xrstors
can be optimized by HW for normal fpstate.
Suggested-by: Dave Hansen <[email protected]>
Signed-off-by: Yang Weijiang <[email protected]>
Reviewed-by: Rick Edgecombe <[email protected]>
---
arch/x86/include/asm/fpu/xstate.h | 5 ++++-
arch/x86/kernel/fpu/xstate.c | 1 +
2 files changed, 5 insertions(+), 1 deletion(-)
diff --git a/arch/x86/include/asm/fpu/xstate.h b/arch/x86/include/asm/fpu/xstate.h
index 3b4a038d3c57..a212d3851429 100644
--- a/arch/x86/include/asm/fpu/xstate.h
+++ b/arch/x86/include/asm/fpu/xstate.h
@@ -46,9 +46,12 @@
#define XFEATURE_MASK_USER_RESTORE \
(XFEATURE_MASK_USER_SUPPORTED & ~XFEATURE_MASK_PKRU)
-/* Features which are dynamically enabled for a process on request */
+/* Features which are dynamically enabled per userspace request */
#define XFEATURE_MASK_USER_DYNAMIC XFEATURE_MASK_XTILE_DATA
+/* Features which are dynamically enabled per kernel side request */
+#define XFEATURE_MASK_KERNEL_DYNAMIC XFEATURE_MASK_CET_KERNEL
+
/* All currently supported supervisor features */
#define XFEATURE_MASK_SUPERVISOR_SUPPORTED (XFEATURE_MASK_PASID | \
XFEATURE_MASK_CET_USER | \
diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c
index 84d4fcaeff35..1a8a187351d3 100644
--- a/arch/x86/kernel/fpu/xstate.c
+++ b/arch/x86/kernel/fpu/xstate.c
@@ -818,6 +818,7 @@ void __init fpu__init_system_xstate(unsigned int legacy_size)
/* Clean out dynamic features from default */
fpu_kernel_cfg.default_features = fpu_kernel_cfg.max_features;
fpu_kernel_cfg.default_features &= ~XFEATURE_MASK_USER_DYNAMIC;
+ fpu_kernel_cfg.default_features &= ~XFEATURE_MASK_KERNEL_DYNAMIC;
fpu_user_cfg.default_features = fpu_user_cfg.max_features;
fpu_user_cfg.default_features &= ~XFEATURE_MASK_USER_DYNAMIC;
--
2.43.0
From: Sean Christopherson <[email protected]>
When granting userspace or a KVM guest access to an xfeature, preserve the
entity's existing supervisor and software-defined permissions as tracked
by __state_perm, i.e. use __state_perm to track *all* permissions even
though all supported supervisor xfeatures are granted to all FPUs and
FPU_GUEST_PERM_LOCKED disallows changing permissions.
Effectively clobbering supervisor permissions results in inconsistent
behavior, as xstate_get_group_perm() will report supervisor features for
process that do NOT request access to dynamic user xfeatures, whereas any
and all supervisor features will be absent from the set of permissions for
any process that is granted access to one or more dynamic xfeatures (which
right now means AMX).
The inconsistency isn't problematic because fpu_xstate_prctl() already
strips out everything except user xfeatures:
case ARCH_GET_XCOMP_PERM:
/*
* Lockless snapshot as it can also change right after the
* dropping the lock.
*/
permitted = xstate_get_host_group_perm();
permitted &= XFEATURE_MASK_USER_SUPPORTED;
return put_user(permitted, uptr);
case ARCH_GET_XCOMP_GUEST_PERM:
permitted = xstate_get_guest_group_perm();
permitted &= XFEATURE_MASK_USER_SUPPORTED;
return put_user(permitted, uptr);
and similarly KVM doesn't apply the __state_perm to supervisor states
(kvm_get_filtered_xcr0() incorporates xstate_get_guest_group_perm()):
case 0xd: {
u64 permitted_xcr0 = kvm_get_filtered_xcr0();
u64 permitted_xss = kvm_caps.supported_xss;
But if KVM in particular were to ever change, dropping supervisor
permissions would result in subtle bugs in KVM's reporting of supported
CPUID settings. And the above behavior also means that having supervisor
xfeatures in __state_perm is correctly handled by all users.
Dropping supervisor permissions also creates another landmine for KVM. If
more dynamic user xfeatures are ever added, requesting access to multiple
xfeatures in separate ARCH_REQ_XCOMP_GUEST_PERM calls will result in the
second invocation of __xstate_request_perm() computing the wrong ksize, as
as the mask passed to xstate_calculate_size() would not contain *any*
supervisor features.
Commit 781c64bfcb73 ("x86/fpu/xstate: Handle supervisor states in XSTATE
permissions") fudged around the size issue for userspace FPUs, but for
reasons unknown skipped guest FPUs. Lack of a fix for KVM "works" only
because KVM doesn't yet support virtualizing features that have supervisor
xfeatures, i.e. as of today, KVM guest FPUs will never need the relevant
xfeatures.
Simply extending the hack-a-fix for guests would temporarily solve the
ksize issue, but wouldn't address the inconsistency issue and would leave
another lurking pitfall for KVM. KVM support for virtualizing CET will
likely add CET_KERNEL as a guest-only xfeature, i.e. CET_KERNEL will not
be set in xfeatures_mask_supervisor() and would again be dropped when
granting access to dynamic xfeatures.
Note, the existing clobbering behavior is rather subtle. The @permitted
parameter to __xstate_request_perm() comes from:
permitted = xstate_get_group_perm(guest);
which is either fpu->guest_perm.__state_perm or fpu->perm.__state_perm,
where __state_perm is initialized to:
fpu->perm.__state_perm = fpu_kernel_cfg.default_features;
and copied to the guest side of things:
/* Same defaults for guests */
fpu->guest_perm = fpu->perm;
fpu_kernel_cfg.default_features contains everything except the dynamic
xfeatures, i.e. everything except XFEATURE_MASK_XTILE_DATA:
fpu_kernel_cfg.default_features = fpu_kernel_cfg.max_features;
fpu_kernel_cfg.default_features &= ~XFEATURE_MASK_USER_DYNAMIC;
When __xstate_request_perm() restricts the local "mask" variable to
compute the user state size:
mask &= XFEATURE_MASK_USER_SUPPORTED;
usize = xstate_calculate_size(mask, false);
it subtly overwrites the target __state_perm with "mask" containing only
user xfeatures:
perm = guest ? &fpu->guest_perm : &fpu->perm;
/* Pairs with the READ_ONCE() in xstate_get_group_perm() */
WRITE_ONCE(perm->__state_perm, mask);
Cc: Maxim Levitsky <[email protected]>
Cc: Weijiang Yang <[email protected]>
Cc: Dave Hansen <[email protected]>
Cc: Paolo Bonzini <[email protected]>
Cc: Peter Zijlstra <[email protected]>
Cc: Chao Gao <[email protected]>
Cc: Rick Edgecombe <[email protected]>
Cc: John Allen <[email protected]>
Cc: [email protected]
Link: https://lore.kernel.org/all/[email protected]
Signed-off-by: Sean Christopherson <[email protected]>
Signed-off-by: Yang Weijiang <[email protected]>
Reviewed-by: Maxim Levitsky <[email protected]>
Reviewed-by: Rick Edgecombe <[email protected]>
---
arch/x86/kernel/fpu/xstate.c | 18 +++++++++++-------
1 file changed, 11 insertions(+), 7 deletions(-)
diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c
index c5a026fee5e0..bc66183c7df2 100644
--- a/arch/x86/kernel/fpu/xstate.c
+++ b/arch/x86/kernel/fpu/xstate.c
@@ -1603,16 +1603,20 @@ static int __xstate_request_perm(u64 permitted, u64 requested, bool guest)
if ((permitted & requested) == requested)
return 0;
- /* Calculate the resulting kernel state size */
+ /*
+ * Calculate the resulting kernel state size. Note, @permitted also
+ * contains supervisor xfeatures even though supervisor are always
+ * permitted for kernel and guest FPUs, and never permitted for user
+ * FPUs.
+ */
mask = permitted | requested;
- /* Take supervisor states into account on the host */
- if (!guest)
- mask |= xfeatures_mask_supervisor();
ksize = xstate_calculate_size(mask, compacted);
- /* Calculate the resulting user state size */
- mask &= XFEATURE_MASK_USER_SUPPORTED;
- usize = xstate_calculate_size(mask, false);
+ /*
+ * Calculate the resulting user state size. Take care not to clobber
+ * the supervisor xfeatures in the new mask!
+ */
+ usize = xstate_calculate_size(mask & XFEATURE_MASK_USER_SUPPORTED, false);
if (!guest) {
ret = validate_sigaltstack(usize);
--
2.43.0
Use fpu_guest_cfg to calculate guest fpstate settings, open code for
__fpstate_reset() to avoid using kernel FPU config.
Below configuration steps are currently enforced to get guest fpstate:
1) Kernel sets up guest FPU settings in fpu__init_system_xstate().
2) User space sets vCPU thread group xstate permits via arch_prctl().
3) User space creates guest fpstate via __fpu_alloc_init_guest_fpstate()
for vcpu thread.
4) User space enables guest dynamic xfeatures and re-allocate guest
fpstate.
By adding kernel dynamic xfeatures in above #1 and #2, guest xstate area
size is expanded to hold (fpu_kernel_cfg.default_features | kernel dynamic
xfeatures | user dynamic xfeatures), then host xsaves/xrstors can operate
for all guest xfeatures.
The user_* fields remain unchanged for compatibility with KVM uAPIs.
Signed-off-by: Yang Weijiang <[email protected]>
Reviewed-by: Maxim Levitsky <[email protected]>
Reviewed-by: Rick Edgecombe <[email protected]>
---
arch/x86/kernel/fpu/core.c | 39 +++++++++++++++++++++++++++++---------
1 file changed, 30 insertions(+), 9 deletions(-)
diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c
index 9e2e5c46cf28..00d7dcf45b34 100644
--- a/arch/x86/kernel/fpu/core.c
+++ b/arch/x86/kernel/fpu/core.c
@@ -194,8 +194,6 @@ void fpu_reset_from_exception_fixup(void)
}
#if IS_ENABLED(CONFIG_KVM)
-static void __fpstate_reset(struct fpstate *fpstate, u64 xfd);
-
static void fpu_init_guest_permissions(struct fpu_guest *gfpu)
{
struct fpu_state_perm *fpuperm;
@@ -216,25 +214,48 @@ static void fpu_init_guest_permissions(struct fpu_guest *gfpu)
gfpu->perm = perm & ~FPU_GUEST_PERM_LOCKED;
}
-bool fpu_alloc_guest_fpstate(struct fpu_guest *gfpu)
+static struct fpstate *__fpu_alloc_init_guest_fpstate(struct fpu_guest *gfpu)
{
struct fpstate *fpstate;
unsigned int size;
- size = fpu_user_cfg.default_size + ALIGN(offsetof(struct fpstate, regs), 64);
+ /*
+ * fpu_guest_cfg.default_size is initialized to hold all enabled
+ * xfeatures except the user dynamic xfeatures. If the user dynamic
+ * xfeatures are enabled, the guest fpstate will be re-allocated to
+ * hold all guest enabled xfeatures, so omit user dynamic xfeatures
+ * here.
+ */
+ size = fpu_guest_cfg.default_size + ALIGN(offsetof(struct fpstate, regs), 64);
+
fpstate = vzalloc(size);
if (!fpstate)
- return false;
+ return NULL;
+ /*
+ * Initialize sizes and feature masks, use fpu_user_cfg.*
+ * for user_* settings for compatibility of exiting uAPIs.
+ */
+ fpstate->size = fpu_guest_cfg.default_size;
+ fpstate->xfeatures = fpu_guest_cfg.default_features;
+ fpstate->user_size = fpu_user_cfg.default_size;
+ fpstate->user_xfeatures = fpu_user_cfg.default_features;
+ fpstate->xfd = 0;
- /* Leave xfd to 0 (the reset value defined by spec) */
- __fpstate_reset(fpstate, 0);
fpstate_init_user(fpstate);
fpstate->is_valloc = true;
fpstate->is_guest = true;
gfpu->fpstate = fpstate;
- gfpu->xfeatures = fpu_user_cfg.default_features;
- gfpu->perm = fpu_user_cfg.default_features;
+ gfpu->xfeatures = fpu_guest_cfg.default_features;
+ gfpu->perm = fpu_guest_cfg.default_features;
+
+ return fpstate;
+}
+
+bool fpu_alloc_guest_fpstate(struct fpu_guest *gfpu)
+{
+ if (!__fpu_alloc_init_guest_fpstate(gfpu))
+ return false;
/*
* KVM sets the FP+SSE bits in the XSAVE header when copying FPU state
--
2.43.0
CET supervisor state bit is __ONLY__ enabled for guest fpstate, i.e.,
never for normal kernel fpstate. The bit is set when guest FPU config
is initialized.
For normal fpstate, the bit should have been removed when initializes
kernel FPU config settings, WARN_ONCE() if kernel detects normal fpstate
xfeatures contains CET supervisor state bit before xsaves operation.
Signed-off-by: Yang Weijiang <[email protected]>
---
arch/x86/kernel/fpu/xstate.h | 2 ++
1 file changed, 2 insertions(+)
diff --git a/arch/x86/kernel/fpu/xstate.h b/arch/x86/kernel/fpu/xstate.h
index 05df04f39628..b1b3e0fe02c6 100644
--- a/arch/x86/kernel/fpu/xstate.h
+++ b/arch/x86/kernel/fpu/xstate.h
@@ -189,6 +189,8 @@ static inline void os_xsave(struct fpstate *fpstate)
WARN_ON_FPU(!alternatives_patched);
xfd_validate_state(fpstate, mask, false);
+ WARN_ON_FPU(!fpstate->is_guest && (mask & XFEATURE_MASK_CET_KERNEL));
+
XSTATE_XSAVE(&fpstate->regs.xsave, lmask, hmask, err);
/* We should never fault when copying to a kernel buffer: */
--
2.43.0
Define new fpu_guest_cfg to hold all guest FPU settings so that it can
differ from generic kernel FPU settings, e.g., enabling CET supervisor
xstate by default for guest fpstate while it's remained disabled in
kernel FPU config.
The kernel dynamic xfeatures are specifically used by guest fpstate now,
add the mask for guest fpstate so that guest_perm.__state_perm ==
(fpu_kernel_cfg.default_xfeature | XFEATURE_MASK_KERNEL_DYNAMIC). And
if guest fpstate is re-allocated to hold user dynamic xfeatures, the
resulting permissions are consumed before calculate new guest fpstate.
With new guest FPU config added, there're 3 categories of FPU configs in
kernel, the usages and key fields are recapped as below.
kernel FPU config:
@fpu_kernel_cfg.max_features
- all known and CPU supported user and supervisor features except
independent kernel features
@fpu_kernel_cfg.default_features
- all known and CPU supported user and supervisor features except
dynamic kernel features, independent kernel features and dynamic
userspace features.
@fpu_kernel_cfg.max_size
- size of compacted buffer with 'fpu_kernel_cfg.max_features'
@fpu_kernel_cfg.default_size
- size of compacted buffer with 'fpu_kernel_cfg.default_features'
user FPU config:
@fpu_user_cfg.max_features
- all known and CPU supported user features
@fpu_user_cfg.default_features
- all known and CPU supported user features except dynamic userspace
features.
@fpu_user_cfg.max_size
- size of non-compacted buffer with 'fpu_user_cfg.max_features'
@fpu_user_cfg.default_size
- size of non-compacted buffer with 'fpu_user_cfg.default_features'
guest FPU config:
@fpu_guest_cfg.max_features
- all known and CPU supported user and supervisor features except
independent kernel features.
@fpu_guest_cfg.default_features
- all known and CPU supported user and supervisor features except
independent kernel features and dynamic userspace features.
@fpu_guest_cfg.max_size
- size of compacted buffer with 'fpu_guest_cfg.max_features'
@fpu_guest_cfg.default_size
- size of compacted buffer with 'fpu_guest_cfg.default_features'
Signed-off-by: Yang Weijiang <[email protected]>
Reviewed-by: Maxim Levitsky <[email protected]>
Reviewed-by: Rick Edgecombe <[email protected]>
---
arch/x86/include/asm/fpu/types.h | 2 +-
arch/x86/kernel/fpu/core.c | 14 +++++++++++---
arch/x86/kernel/fpu/xstate.c | 10 ++++++++++
3 files changed, 22 insertions(+), 4 deletions(-)
diff --git a/arch/x86/include/asm/fpu/types.h b/arch/x86/include/asm/fpu/types.h
index d633cf833411..0ad17b0ffbe8 100644
--- a/arch/x86/include/asm/fpu/types.h
+++ b/arch/x86/include/asm/fpu/types.h
@@ -604,6 +604,6 @@ struct fpu_state_config {
};
/* FPU state configuration information */
-extern struct fpu_state_config fpu_kernel_cfg, fpu_user_cfg;
+extern struct fpu_state_config fpu_kernel_cfg, fpu_user_cfg, fpu_guest_cfg;
#endif /* _ASM_X86_FPU_TYPES_H */
diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c
index 1209c7aebb21..9e2e5c46cf28 100644
--- a/arch/x86/kernel/fpu/core.c
+++ b/arch/x86/kernel/fpu/core.c
@@ -33,9 +33,10 @@ DEFINE_STATIC_KEY_FALSE(__fpu_state_size_dynamic);
DEFINE_PER_CPU(u64, xfd_state);
#endif
-/* The FPU state configuration data for kernel and user space */
+/* The FPU state configuration data for kernel, user space and guest. */
struct fpu_state_config fpu_kernel_cfg __ro_after_init;
struct fpu_state_config fpu_user_cfg __ro_after_init;
+struct fpu_state_config fpu_guest_cfg __ro_after_init;
/*
* Represents the initial FPU state. It's mostly (but not completely) zeroes,
@@ -536,8 +537,15 @@ void fpstate_reset(struct fpu *fpu)
fpu->perm.__state_perm = fpu_kernel_cfg.default_features;
fpu->perm.__state_size = fpu_kernel_cfg.default_size;
fpu->perm.__user_state_size = fpu_user_cfg.default_size;
- /* Same defaults for guests */
- fpu->guest_perm = fpu->perm;
+
+ /* Guest permission settings */
+ fpu->guest_perm.__state_perm = fpu_guest_cfg.default_features;
+ fpu->guest_perm.__state_size = fpu_guest_cfg.default_size;
+ /*
+ * Set guest's __user_state_size to fpu_user_cfg.default_size so that
+ * existing uAPIs can still work.
+ */
+ fpu->guest_perm.__user_state_size = fpu_user_cfg.default_size;
}
static inline void fpu_inherit_perms(struct fpu *dst_fpu)
diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c
index 1a8a187351d3..392f3ba3aa27 100644
--- a/arch/x86/kernel/fpu/xstate.c
+++ b/arch/x86/kernel/fpu/xstate.c
@@ -683,6 +683,7 @@ static int __init init_xstate_size(void)
{
/* Recompute the context size for enabled features: */
unsigned int user_size, kernel_size, kernel_default_size;
+ unsigned int guest_default_size;
bool compacted = cpu_feature_enabled(X86_FEATURE_XCOMPACTED);
/* Uncompacted user space size */
@@ -704,13 +705,18 @@ static int __init init_xstate_size(void)
kernel_default_size =
xstate_calculate_size(fpu_kernel_cfg.default_features, compacted);
+ guest_default_size =
+ xstate_calculate_size(fpu_guest_cfg.default_features, compacted);
+
if (!paranoid_xstate_size_valid(kernel_size))
return -EINVAL;
fpu_kernel_cfg.max_size = kernel_size;
fpu_user_cfg.max_size = user_size;
+ fpu_guest_cfg.max_size = kernel_size;
fpu_kernel_cfg.default_size = kernel_default_size;
+ fpu_guest_cfg.default_size = guest_default_size;
fpu_user_cfg.default_size =
xstate_calculate_size(fpu_user_cfg.default_features, false);
@@ -823,6 +829,10 @@ void __init fpu__init_system_xstate(unsigned int legacy_size)
fpu_user_cfg.default_features = fpu_user_cfg.max_features;
fpu_user_cfg.default_features &= ~XFEATURE_MASK_USER_DYNAMIC;
+ fpu_guest_cfg.max_features = fpu_kernel_cfg.max_features;
+ fpu_guest_cfg.default_features = fpu_guest_cfg.max_features;
+ fpu_guest_cfg.default_features &= ~XFEATURE_MASK_USER_DYNAMIC;
+
/* Store it for paranoia check at the end */
xfeatures = fpu_kernel_cfg.max_features;
--
2.43.0