Commit 980fe2fd authored by Thomas Gleixner's avatar Thomas Gleixner Committed by Paolo Bonzini

x86/fpu: Extend fpu_xstate_prctl() with guest permissions

KVM requires a clear separation of host user space and guest permissions
for dynamic XSTATE components.

Add a guest permissions member to struct fpu and a separate set of prctl()
arguments: ARCH_GET_XCOMP_GUEST_PERM and ARCH_REQ_XCOMP_GUEST_PERM.

The semantics are equivalent to the host user space permission control
except for the following constraints:

  1) Permissions have to be requested before the first vCPU is created

  2) Permissions are frozen when the first vCPU is created to ensure
     consistency. Any attempt to expand permissions via the prctl() after
     that point is rejected.
Signed-off-by: default avatarThomas Gleixner <tglx@linutronix.de>
Signed-off-by: default avatarJing Liu <jing2.liu@intel.com>
Signed-off-by: default avatarYang Zhong <yang.zhong@intel.com>
Message-Id: <20220105123532.12586-2-yang.zhong@intel.com>
Signed-off-by: default avatarPaolo Bonzini <pbonzini@redhat.com>
parent 96c1a628
......@@ -132,6 +132,8 @@ 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);
......
......@@ -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:
*
......
......@@ -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 */
......@@ -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(&current->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(&current->sighand->siglock);
}
}
......
......@@ -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
......@@ -1605,9 +1605,10 @@ static int __xstate_request_perm(u64 permitted, u64 requested)
*/
bool compacted = cpu_feature_enabled(X86_FEATURE_XSAVES);
struct fpu *fpu = &current->group_leader->thread.fpu;
struct fpu_state_perm *perm;
unsigned int ksize, usize;
u64 mask;
int ret;
int ret = 0;
/* Check whether fully enabled */
if ((permitted & requested) == requested)
......@@ -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(&current->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(&current->sighand->siglock);
return ret;
}
......@@ -1713,12 +1722,18 @@ 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 +1757,7 @@ 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 +1776,20 @@ 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;
......
......@@ -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 = &current->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 {
......
......@@ -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);
}
......
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment