From: Yang Zhong <yang.zhong@intel.com>
To: x86@kernel.org, kvm@vger.kernel.org,
linux-kernel@vger.kernel.org, tglx@linutronix.de,
mingo@redhat.com, bp@alien8.de, dave.hansen@linux.intel.com,
pbonzini@redhat.com
Cc: seanjc@google.com, jun.nakajima@intel.com, kevin.tian@intel.com,
jing2.liu@linux.intel.com, jing2.liu@intel.com,
yang.zhong@intel.com
Subject: [PATCH 01/19] x86/fpu: Extend prctl() with guest permissions
Date: Tue, 7 Dec 2021 19:03:41 -0500 [thread overview]
Message-ID: <20211208000359.2853257-2-yang.zhong@intel.com> (raw)
In-Reply-To: <20211208000359.2853257-1-yang.zhong@intel.com>
From: Thomas Gleixner <tglx@linutronix.de>
Add guest permission control for dynamic XSTATE components, including
extension to prctl() with two new options (ARCH_GET_XCOMP_GUEST_PERM
and ARCH_REQ_XCOMP_GUEST_PERM) and to struct fpu with a new member
(guest_perm).
Userspace VMM has to request guest permissions before it exposes any
XSAVE feature using dynamic XSTATE components. The permission can be
set only once when the first vCPU is created. A new flag
FPU_GUEST_PERM_LOCKED is introduced to lock the change for this purpose
Similar to native permissions this doesn't actually enable the
permitted feature. KVM is expected to install a larger kernel buffer
and enable the feature when detecting the intention from the guest.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Jing Liu <jing2.liu@intel.com>
Signed-off-by: Yang Zhong <yang.zhong@intel.com>
---
(To Thomas) We change the definition of xstate_get_guest_group_perm()
from xstate.h to api.h since this will be called by KVM.
arch/x86/include/asm/fpu/api.h | 2 ++
arch/x86/include/asm/fpu/types.h | 9 ++++++
arch/x86/include/uapi/asm/prctl.h | 26 ++++++++--------
arch/x86/kernel/fpu/core.c | 3 ++
arch/x86/kernel/fpu/xstate.c | 50 +++++++++++++++++++++++--------
arch/x86/kernel/fpu/xstate.h | 13 ++++++--
arch/x86/kernel/process.c | 2 ++
7 files changed, 78 insertions(+), 27 deletions(-)
diff --git a/arch/x86/include/asm/fpu/api.h b/arch/x86/include/asm/fpu/api.h
index 6053674f9132..7532f73c82a6 100644
--- a/arch/x86/include/asm/fpu/api.h
+++ b/arch/x86/include/asm/fpu/api.h
@@ -138,6 +138,8 @@ static inline void fpstate_free(struct fpu *fpu) { }
/* fpstate-related functions which are exported to KVM */
extern void fpstate_clear_xstate_component(struct fpstate *fps, unsigned int xfeature);
+extern inline u64 xstate_get_guest_group_perm(void);
+
/* KVM specific functions */
extern bool fpu_alloc_guest_fpstate(struct fpu_guest *gfpu);
extern void fpu_free_guest_fpstate(struct fpu_guest *gfpu);
diff --git a/arch/x86/include/asm/fpu/types.h b/arch/x86/include/asm/fpu/types.h
index 3c06c82ab355..6ddf80637697 100644
--- a/arch/x86/include/asm/fpu/types.h
+++ b/arch/x86/include/asm/fpu/types.h
@@ -387,6 +387,8 @@ struct fpstate {
/* @regs is dynamically sized! Don't add anything after @regs! */
} __aligned(64);
+#define FPU_GUEST_PERM_LOCKED BIT_ULL(63)
+
struct fpu_state_perm {
/*
* @__state_perm:
@@ -476,6 +478,13 @@ struct fpu {
*/
struct fpu_state_perm perm;
+ /*
+ * @guest_perm:
+ *
+ * Permission related information for guest pseudo FPUs
+ */
+ struct fpu_state_perm guest_perm;
+
/*
* @__fpstate:
*
diff --git a/arch/x86/include/uapi/asm/prctl.h b/arch/x86/include/uapi/asm/prctl.h
index 754a07856817..500b96e71f18 100644
--- a/arch/x86/include/uapi/asm/prctl.h
+++ b/arch/x86/include/uapi/asm/prctl.h
@@ -2,20 +2,22 @@
#ifndef _ASM_X86_PRCTL_H
#define _ASM_X86_PRCTL_H
-#define ARCH_SET_GS 0x1001
-#define ARCH_SET_FS 0x1002
-#define ARCH_GET_FS 0x1003
-#define ARCH_GET_GS 0x1004
+#define ARCH_SET_GS 0x1001
+#define ARCH_SET_FS 0x1002
+#define ARCH_GET_FS 0x1003
+#define ARCH_GET_GS 0x1004
-#define ARCH_GET_CPUID 0x1011
-#define ARCH_SET_CPUID 0x1012
+#define ARCH_GET_CPUID 0x1011
+#define ARCH_SET_CPUID 0x1012
-#define ARCH_GET_XCOMP_SUPP 0x1021
-#define ARCH_GET_XCOMP_PERM 0x1022
-#define ARCH_REQ_XCOMP_PERM 0x1023
+#define ARCH_GET_XCOMP_SUPP 0x1021
+#define ARCH_GET_XCOMP_PERM 0x1022
+#define ARCH_REQ_XCOMP_PERM 0x1023
+#define ARCH_GET_XCOMP_GUEST_PERM 0x1024
+#define ARCH_REQ_XCOMP_GUEST_PERM 0x1025
-#define ARCH_MAP_VDSO_X32 0x2001
-#define ARCH_MAP_VDSO_32 0x2002
-#define ARCH_MAP_VDSO_64 0x2003
+#define ARCH_MAP_VDSO_X32 0x2001
+#define ARCH_MAP_VDSO_32 0x2002
+#define ARCH_MAP_VDSO_64 0x2003
#endif /* _ASM_X86_PRCTL_H */
diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c
index 8ea306b1bf8e..ab19b3d8b2f7 100644
--- a/arch/x86/kernel/fpu/core.c
+++ b/arch/x86/kernel/fpu/core.c
@@ -450,6 +450,8 @@ 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;
}
static inline void fpu_inherit_perms(struct fpu *dst_fpu)
@@ -460,6 +462,7 @@ static inline void fpu_inherit_perms(struct fpu *dst_fpu)
spin_lock_irq(¤t->sighand->siglock);
/* Fork also inherits the permissions of the parent */
dst_fpu->perm = src_fpu->perm;
+ dst_fpu->guest_perm = src_fpu->guest_perm;
spin_unlock_irq(¤t->sighand->siglock);
}
}
diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c
index d28829403ed0..9856d579aa6e 100644
--- a/arch/x86/kernel/fpu/xstate.c
+++ b/arch/x86/kernel/fpu/xstate.c
@@ -1595,7 +1595,7 @@ static int validate_sigaltstack(unsigned int usize)
return 0;
}
-static int __xstate_request_perm(u64 permitted, u64 requested)
+static int __xstate_request_perm(u64 permitted, u64 requested, bool guest)
{
/*
* This deliberately does not exclude !XSAVES as we still might
@@ -1605,6 +1605,7 @@ static int __xstate_request_perm(u64 permitted, u64 requested)
*/
bool compacted = cpu_feature_enabled(X86_FEATURE_XSAVES);
struct fpu *fpu = ¤t->group_leader->thread.fpu;
+ struct fpu_state_perm *perm;
unsigned int ksize, usize;
u64 mask;
int ret;
@@ -1621,15 +1622,18 @@ static int __xstate_request_perm(u64 permitted, u64 requested)
mask &= XFEATURE_MASK_USER_SUPPORTED;
usize = xstate_calculate_size(mask, false);
- ret = validate_sigaltstack(usize);
- if (ret)
- return ret;
+ if (!guest) {
+ ret = validate_sigaltstack(usize);
+ if (ret)
+ return ret;
+ }
+ perm = guest ? &fpu->guest_perm : &fpu->perm;
/* Pairs with the READ_ONCE() in xstate_get_group_perm() */
- WRITE_ONCE(fpu->perm.__state_perm, requested);
+ WRITE_ONCE(perm->__state_perm, requested);
/* Protected by sighand lock */
- fpu->perm.__state_size = ksize;
- fpu->perm.__user_state_size = usize;
+ perm->__state_size = ksize;
+ perm->__user_state_size = usize;
return ret;
}
@@ -1640,7 +1644,7 @@ static const u64 xstate_prctl_req[XFEATURE_MAX] = {
[XFEATURE_XTILE_DATA] = XFEATURE_MASK_XTILE_DATA,
};
-static int xstate_request_perm(unsigned long idx)
+static int xstate_request_perm(unsigned long idx, bool guest)
{
u64 permitted, requested;
int ret;
@@ -1661,14 +1665,19 @@ static int xstate_request_perm(unsigned long idx)
return -EOPNOTSUPP;
/* Lockless quick check */
- permitted = xstate_get_host_group_perm();
+ permitted = xstate_get_group_perm(guest);
if ((permitted & requested) == requested)
return 0;
/* Protect against concurrent modifications */
spin_lock_irq(¤t->sighand->siglock);
- permitted = xstate_get_host_group_perm();
- ret = __xstate_request_perm(permitted, requested);
+ permitted = xstate_get_group_perm(guest);
+
+ /* First vCPU allocation locks the permissions. */
+ if (guest && (permitted & FPU_GUEST_PERM_LOCKED))
+ ret = -EBUSY;
+ else
+ ret = __xstate_request_perm(permitted, requested, guest);
spin_unlock_irq(¤t->sighand->siglock);
return ret;
}
@@ -1713,12 +1722,17 @@ int xfd_enable_feature(u64 xfd_err)
return 0;
}
#else /* CONFIG_X86_64 */
-static inline int xstate_request_perm(unsigned long idx)
+static inline int xstate_request_perm(unsigned long idx, bool guest)
{
return -EPERM;
}
#endif /* !CONFIG_X86_64 */
+inline u64 xstate_get_guest_group_perm(void)
+{
+ return xstate_get_group_perm(true);
+}
+EXPORT_SYMBOL_GPL(xstate_get_guest_group_perm);
/**
* fpu_xstate_prctl - xstate permission operations
* @tsk: Redundant pointer to current
@@ -1742,6 +1756,7 @@ long fpu_xstate_prctl(struct task_struct *tsk, int option, unsigned long arg2)
u64 __user *uptr = (u64 __user *)arg2;
u64 permitted, supported;
unsigned long idx = arg2;
+ bool guest = false;
if (tsk != current)
return -EPERM;
@@ -1760,11 +1775,20 @@ long fpu_xstate_prctl(struct task_struct *tsk, int option, unsigned long arg2)
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);
+
+ case ARCH_REQ_XCOMP_GUEST_PERM:
+ guest = true;
+ fallthrough;
+
case ARCH_REQ_XCOMP_PERM:
if (!IS_ENABLED(CONFIG_X86_64))
return -EOPNOTSUPP;
- return xstate_request_perm(idx);
+ return xstate_request_perm(idx, guest);
default:
return -EINVAL;
diff --git a/arch/x86/kernel/fpu/xstate.h b/arch/x86/kernel/fpu/xstate.h
index 86ea7c0fa2f6..98a472775c97 100644
--- a/arch/x86/kernel/fpu/xstate.h
+++ b/arch/x86/kernel/fpu/xstate.h
@@ -20,10 +20,19 @@ static inline void xstate_init_xcomp_bv(struct xregs_state *xsave, u64 mask)
xsave->header.xcomp_bv = mask | XCOMP_BV_COMPACTED_FORMAT;
}
-static inline u64 xstate_get_host_group_perm(void)
+static inline u64 xstate_get_group_perm(bool guest)
{
+ struct fpu *fpu = ¤t->group_leader->thread.fpu;
+ struct fpu_state_perm *perm;
+
/* Pairs with WRITE_ONCE() in xstate_request_perm() */
- return READ_ONCE(current->group_leader->thread.fpu.perm.__state_perm);
+ perm = guest ? &fpu->guest_perm : &fpu->perm;
+ return READ_ONCE(perm->__state_perm);
+}
+
+static inline u64 xstate_get_host_group_perm(void)
+{
+ return xstate_get_group_perm(false);
}
enum xstate_copy_mode {
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index 04143a653a8a..d7bc23589062 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -993,6 +993,8 @@ long do_arch_prctl_common(struct task_struct *task, int option,
case ARCH_GET_XCOMP_SUPP:
case ARCH_GET_XCOMP_PERM:
case ARCH_REQ_XCOMP_PERM:
+ case ARCH_GET_XCOMP_GUEST_PERM:
+ case ARCH_REQ_XCOMP_GUEST_PERM:
return fpu_xstate_prctl(task, option, arg2);
}
next prev parent reply other threads:[~2021-12-07 15:09 UTC|newest]
Thread overview: 80+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-12-08 0:03 [PATCH 00/19] AMX Support in KVM Yang Zhong
2021-12-08 0:03 ` Yang Zhong [this message]
2021-12-14 0:16 ` [PATCH 01/19] x86/fpu: Extend prctl() with guest permissions Thomas Gleixner
2021-12-08 0:03 ` [PATCH 02/19] x86/fpu: Prepare KVM for dynamically enabled states Yang Zhong
2021-12-13 9:12 ` Paolo Bonzini
2021-12-13 12:00 ` Thomas Gleixner
2021-12-13 12:45 ` Paolo Bonzini
2021-12-13 19:50 ` Thomas Gleixner
2021-12-08 0:03 ` [PATCH 03/19] kvm: x86: Fix xstate_required_size() to follow XSTATE alignment rule Yang Zhong
2021-12-08 0:03 ` [PATCH 04/19] kvm: x86: Check guest xstate permissions when KVM_SET_CPUID2 Yang Zhong
2021-12-08 0:03 ` [PATCH 05/19] x86/fpu: Move xfd initialization out of __fpstate_reset() to the callers Yang Zhong
2021-12-10 22:33 ` Thomas Gleixner
2021-12-08 0:03 ` [PATCH 06/19] x86/fpu: Add reallocation mechanims for KVM Yang Zhong
2021-12-08 0:03 ` [PATCH 07/19] kvm: x86: Propagate fpstate reallocation error to userspace Yang Zhong
2021-12-10 15:44 ` Paolo Bonzini
2021-12-08 0:03 ` [PATCH 08/19] x86/fpu: Move xfd_update_state() to xstate.c and export symbol Yang Zhong
2021-12-10 22:44 ` Thomas Gleixner
2021-12-08 0:03 ` [PATCH 09/19] kvm: x86: Prepare reallocation check Yang Zhong
2021-12-13 9:16 ` Paolo Bonzini
2021-12-14 7:06 ` Tian, Kevin
2021-12-14 10:16 ` Paolo Bonzini
2021-12-14 14:41 ` Liu, Jing2
2021-12-15 7:09 ` Tian, Kevin
2021-12-08 0:03 ` [PATCH 10/19] kvm: x86: Emulate WRMSR of guest IA32_XFD Yang Zhong
2021-12-10 16:02 ` Paolo Bonzini
2021-12-13 7:51 ` Liu, Jing2
2021-12-13 9:01 ` Paolo Bonzini
2021-12-14 10:26 ` Yang Zhong
2021-12-14 11:24 ` Paolo Bonzini
2021-12-10 23:09 ` Thomas Gleixner
2021-12-13 15:06 ` Paolo Bonzini
2021-12-13 19:45 ` Thomas Gleixner
2021-12-13 21:23 ` Thomas Gleixner
2021-12-14 7:16 ` Tian, Kevin
2021-12-08 0:03 ` [PATCH 11/19] kvm: x86: Check fpstate reallocation in XSETBV emulation Yang Zhong
2021-12-08 0:03 ` [PATCH 12/19] x86/fpu: Prepare KVM for bringing XFD state back in-sync Yang Zhong
2021-12-10 23:11 ` Thomas Gleixner
2021-12-08 0:03 ` [PATCH 13/19] kvm: x86: Disable WRMSR interception for IA32_XFD on demand Yang Zhong
2021-12-08 7:23 ` Liu, Jing2
2021-12-08 0:03 ` [PATCH 14/19] x86/fpu: Prepare for KVM XFD_ERR handling Yang Zhong
2021-12-10 16:16 ` Paolo Bonzini
2021-12-10 23:20 ` Thomas Gleixner
2021-12-08 0:03 ` [PATCH 15/19] kvm: x86: Save and restore guest XFD_ERR properly Yang Zhong
2021-12-10 16:23 ` Paolo Bonzini
2021-12-10 22:01 ` Paolo Bonzini
2021-12-12 13:10 ` Yang Zhong
2021-12-11 0:10 ` Thomas Gleixner
2021-12-11 1:31 ` Paolo Bonzini
2021-12-11 3:23 ` Tian, Kevin
2021-12-11 13:10 ` Thomas Gleixner
2021-12-11 3:07 ` Tian, Kevin
2021-12-11 13:29 ` Thomas Gleixner
2021-12-12 1:50 ` Tian, Kevin
2021-12-12 9:10 ` Paolo Bonzini
2021-12-08 0:03 ` [PATCH 16/19] kvm: x86: Introduce KVM_{G|S}ET_XSAVE2 ioctl Yang Zhong
2021-12-10 16:25 ` Paolo Bonzini
2021-12-10 16:30 ` Paolo Bonzini
2021-12-10 22:13 ` Paolo Bonzini
2021-12-13 8:23 ` Wang, Wei W
2021-12-13 9:24 ` Paolo Bonzini
2021-12-14 6:06 ` Wang, Wei W
2021-12-14 6:18 ` Paolo Bonzini
2021-12-15 2:39 ` Wang, Wei W
2021-12-15 13:42 ` Paolo Bonzini
2021-12-16 8:25 ` Wang, Wei W
2021-12-16 10:28 ` Paolo Bonzini
2021-12-20 17:54 ` State Component 18 and Palette 1 (Re: [PATCH 16/19] kvm: x86: Introduce KVM_{G|S}ET_XSAVE2 ioctl) Nakajima, Jun
2021-12-22 14:44 ` Paolo Bonzini
2021-12-22 23:47 ` Nakajima, Jun
2021-12-22 14:52 ` Dave Hansen
2021-12-22 23:51 ` Nakajima, Jun
2021-12-13 10:10 ` [PATCH 16/19] kvm: x86: Introduce KVM_{G|S}ET_XSAVE2 ioctl Thomas Gleixner
2021-12-13 10:43 ` Paolo Bonzini
2021-12-13 12:40 ` Thomas Gleixner
2021-12-08 0:03 ` [PATCH 17/19] docs: virt: api.rst: Document the new KVM_{G, S}ET_XSAVE2 ioctls Yang Zhong
2021-12-08 0:03 ` [PATCH 18/19] kvm: x86: AMX XCR0 support for guest Yang Zhong
2021-12-10 16:30 ` Paolo Bonzini
2021-12-08 0:03 ` [PATCH 19/19] kvm: x86: Add AMX CPUIDs support Yang Zhong
2021-12-10 21:52 ` Paolo Bonzini
2021-12-11 21:20 ` [PATCH 00/19] AMX Support in KVM Thomas Gleixner
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20211208000359.2853257-2-yang.zhong@intel.com \
--to=yang.zhong@intel.com \
--cc=bp@alien8.de \
--cc=dave.hansen@linux.intel.com \
--cc=jing2.liu@intel.com \
--cc=jing2.liu@linux.intel.com \
--cc=jun.nakajima@intel.com \
--cc=kevin.tian@intel.com \
--cc=kvm@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=mingo@redhat.com \
--cc=pbonzini@redhat.com \
--cc=seanjc@google.com \
--cc=tglx@linutronix.de \
--cc=x86@kernel.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox
all inboxes | Powered by JetHome®