aboutsummaryrefslogtreecommitdiffstats
path: root/security/selinux
diff options
context:
space:
mode:
authorJiri Kosina <jkosina@suse.cz>2011-04-26 04:22:15 -0400
committerJiri Kosina <jkosina@suse.cz>2011-04-26 04:22:59 -0400
commit07f9479a40cc778bc1462ada11f95b01360ae4ff (patch)
tree0676cf38df3844004bb3ebfd99dfa67a4a8998f5 /security/selinux
parent9d5e6bdb3013acfb311ab407eeca0b6a6a3dedbf (diff)
parentcd2e49e90f1cae7726c9a2c54488d881d7f1cd1c (diff)
Merge branch 'master' into for-next
Fast-forwarded to current state of Linus' tree as there are patches to be applied for files that didn't exist on the old branch.
Diffstat (limited to 'security/selinux')
-rw-r--r--security/selinux/avc.c36
-rw-r--r--security/selinux/hooks.c39
-rw-r--r--security/selinux/include/avc.h18
-rw-r--r--security/selinux/netlabel.c2
-rw-r--r--security/selinux/ss/services.c6
5 files changed, 69 insertions, 32 deletions
diff --git a/security/selinux/avc.c b/security/selinux/avc.c
index 9da6420e205..1d027e29ce8 100644
--- a/security/selinux/avc.c
+++ b/security/selinux/avc.c
@@ -471,6 +471,7 @@ static void avc_audit_post_callback(struct audit_buffer *ab, void *a)
471 * @avd: access vector decisions 471 * @avd: access vector decisions
472 * @result: result from avc_has_perm_noaudit 472 * @result: result from avc_has_perm_noaudit
473 * @a: auxiliary audit data 473 * @a: auxiliary audit data
474 * @flags: VFS walk flags
474 * 475 *
475 * Audit the granting or denial of permissions in accordance 476 * Audit the granting or denial of permissions in accordance
476 * with the policy. This function is typically called by 477 * with the policy. This function is typically called by
@@ -481,9 +482,10 @@ static void avc_audit_post_callback(struct audit_buffer *ab, void *a)
481 * be performed under a lock, to allow the lock to be released 482 * be performed under a lock, to allow the lock to be released
482 * before calling the auditing code. 483 * before calling the auditing code.
483 */ 484 */
484void avc_audit(u32 ssid, u32 tsid, 485int avc_audit(u32 ssid, u32 tsid,
485 u16 tclass, u32 requested, 486 u16 tclass, u32 requested,
486 struct av_decision *avd, int result, struct common_audit_data *a) 487 struct av_decision *avd, int result, struct common_audit_data *a,
488 unsigned flags)
487{ 489{
488 struct common_audit_data stack_data; 490 struct common_audit_data stack_data;
489 u32 denied, audited; 491 u32 denied, audited;
@@ -515,11 +517,24 @@ void avc_audit(u32 ssid, u32 tsid,
515 else 517 else
516 audited = requested & avd->auditallow; 518 audited = requested & avd->auditallow;
517 if (!audited) 519 if (!audited)
518 return; 520 return 0;
521
519 if (!a) { 522 if (!a) {
520 a = &stack_data; 523 a = &stack_data;
521 COMMON_AUDIT_DATA_INIT(a, NONE); 524 COMMON_AUDIT_DATA_INIT(a, NONE);
522 } 525 }
526
527 /*
528 * When in a RCU walk do the audit on the RCU retry. This is because
529 * the collection of the dname in an inode audit message is not RCU
530 * safe. Note this may drop some audits when the situation changes
531 * during retry. However this is logically just as if the operation
532 * happened a little later.
533 */
534 if ((a->type == LSM_AUDIT_DATA_FS) &&
535 (flags & IPERM_FLAG_RCU))
536 return -ECHILD;
537
523 a->selinux_audit_data.tclass = tclass; 538 a->selinux_audit_data.tclass = tclass;
524 a->selinux_audit_data.requested = requested; 539 a->selinux_audit_data.requested = requested;
525 a->selinux_audit_data.ssid = ssid; 540 a->selinux_audit_data.ssid = ssid;
@@ -529,6 +544,7 @@ void avc_audit(u32 ssid, u32 tsid,
529 a->lsm_pre_audit = avc_audit_pre_callback; 544 a->lsm_pre_audit = avc_audit_pre_callback;
530 a->lsm_post_audit = avc_audit_post_callback; 545 a->lsm_post_audit = avc_audit_post_callback;
531 common_lsm_audit(a); 546 common_lsm_audit(a);
547 return 0;
532} 548}
533 549
534/** 550/**
@@ -793,6 +809,7 @@ int avc_has_perm_noaudit(u32 ssid, u32 tsid,
793 * @tclass: target security class 809 * @tclass: target security class
794 * @requested: requested permissions, interpreted based on @tclass 810 * @requested: requested permissions, interpreted based on @tclass
795 * @auditdata: auxiliary audit data 811 * @auditdata: auxiliary audit data
812 * @flags: VFS walk flags
796 * 813 *
797 * Check the AVC to determine whether the @requested permissions are granted 814 * Check the AVC to determine whether the @requested permissions are granted
798 * for the SID pair (@ssid, @tsid), interpreting the permissions 815 * for the SID pair (@ssid, @tsid), interpreting the permissions
@@ -802,14 +819,19 @@ int avc_has_perm_noaudit(u32 ssid, u32 tsid,
802 * permissions are granted, -%EACCES if any permissions are denied, or 819 * permissions are granted, -%EACCES if any permissions are denied, or
803 * another -errno upon other errors. 820 * another -errno upon other errors.
804 */ 821 */
805int avc_has_perm(u32 ssid, u32 tsid, u16 tclass, 822int avc_has_perm_flags(u32 ssid, u32 tsid, u16 tclass,
806 u32 requested, struct common_audit_data *auditdata) 823 u32 requested, struct common_audit_data *auditdata,
824 unsigned flags)
807{ 825{
808 struct av_decision avd; 826 struct av_decision avd;
809 int rc; 827 int rc, rc2;
810 828
811 rc = avc_has_perm_noaudit(ssid, tsid, tclass, requested, 0, &avd); 829 rc = avc_has_perm_noaudit(ssid, tsid, tclass, requested, 0, &avd);
812 avc_audit(ssid, tsid, tclass, requested, &avd, rc, auditdata); 830
831 rc2 = avc_audit(ssid, tsid, tclass, requested, &avd, rc, auditdata,
832 flags);
833 if (rc2)
834 return rc2;
813 return rc; 835 return rc;
814} 836}
815 837
diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c
index 6475e1f0223..f7cf0ea6fae 100644
--- a/security/selinux/hooks.c
+++ b/security/selinux/hooks.c
@@ -79,6 +79,7 @@
79#include <linux/mutex.h> 79#include <linux/mutex.h>
80#include <linux/posix-timers.h> 80#include <linux/posix-timers.h>
81#include <linux/syslog.h> 81#include <linux/syslog.h>
82#include <linux/user_namespace.h>
82 83
83#include "avc.h" 84#include "avc.h"
84#include "objsec.h" 85#include "objsec.h"
@@ -1445,8 +1446,11 @@ static int task_has_capability(struct task_struct *tsk,
1445 } 1446 }
1446 1447
1447 rc = avc_has_perm_noaudit(sid, sid, sclass, av, 0, &avd); 1448 rc = avc_has_perm_noaudit(sid, sid, sclass, av, 0, &avd);
1448 if (audit == SECURITY_CAP_AUDIT) 1449 if (audit == SECURITY_CAP_AUDIT) {
1449 avc_audit(sid, sid, sclass, av, &avd, rc, &ad); 1450 int rc2 = avc_audit(sid, sid, sclass, av, &avd, rc, &ad, 0);
1451 if (rc2)
1452 return rc2;
1453 }
1450 return rc; 1454 return rc;
1451} 1455}
1452 1456
@@ -1466,7 +1470,8 @@ static int task_has_system(struct task_struct *tsk,
1466static int inode_has_perm(const struct cred *cred, 1470static int inode_has_perm(const struct cred *cred,
1467 struct inode *inode, 1471 struct inode *inode,
1468 u32 perms, 1472 u32 perms,
1469 struct common_audit_data *adp) 1473 struct common_audit_data *adp,
1474 unsigned flags)
1470{ 1475{
1471 struct inode_security_struct *isec; 1476 struct inode_security_struct *isec;
1472 struct common_audit_data ad; 1477 struct common_audit_data ad;
@@ -1486,7 +1491,7 @@ static int inode_has_perm(const struct cred *cred,
1486 ad.u.fs.inode = inode; 1491 ad.u.fs.inode = inode;
1487 } 1492 }
1488 1493
1489 return avc_has_perm(sid, isec->sid, isec->sclass, perms, adp); 1494 return avc_has_perm_flags(sid, isec->sid, isec->sclass, perms, adp, flags);
1490} 1495}
1491 1496
1492/* Same as inode_has_perm, but pass explicit audit data containing 1497/* Same as inode_has_perm, but pass explicit audit data containing
@@ -1503,7 +1508,7 @@ static inline int dentry_has_perm(const struct cred *cred,
1503 COMMON_AUDIT_DATA_INIT(&ad, FS); 1508 COMMON_AUDIT_DATA_INIT(&ad, FS);
1504 ad.u.fs.path.mnt = mnt; 1509 ad.u.fs.path.mnt = mnt;
1505 ad.u.fs.path.dentry = dentry; 1510 ad.u.fs.path.dentry = dentry;
1506 return inode_has_perm(cred, inode, av, &ad); 1511 return inode_has_perm(cred, inode, av, &ad, 0);
1507} 1512}
1508 1513
1509/* Check whether a task can use an open file descriptor to 1514/* Check whether a task can use an open file descriptor to
@@ -1539,7 +1544,7 @@ static int file_has_perm(const struct cred *cred,
1539 /* av is zero if only checking access to the descriptor. */ 1544 /* av is zero if only checking access to the descriptor. */
1540 rc = 0; 1545 rc = 0;
1541 if (av) 1546 if (av)
1542 rc = inode_has_perm(cred, inode, av, &ad); 1547 rc = inode_has_perm(cred, inode, av, &ad, 0);
1543 1548
1544out: 1549out:
1545 return rc; 1550 return rc;
@@ -1846,11 +1851,11 @@ static int selinux_capset(struct cred *new, const struct cred *old,
1846 */ 1851 */
1847 1852
1848static int selinux_capable(struct task_struct *tsk, const struct cred *cred, 1853static int selinux_capable(struct task_struct *tsk, const struct cred *cred,
1849 int cap, int audit) 1854 struct user_namespace *ns, int cap, int audit)
1850{ 1855{
1851 int rc; 1856 int rc;
1852 1857
1853 rc = cap_capable(tsk, cred, cap, audit); 1858 rc = cap_capable(tsk, cred, ns, cap, audit);
1854 if (rc) 1859 if (rc)
1855 return rc; 1860 return rc;
1856 1861
@@ -1931,7 +1936,8 @@ static int selinux_vm_enough_memory(struct mm_struct *mm, long pages)
1931{ 1936{
1932 int rc, cap_sys_admin = 0; 1937 int rc, cap_sys_admin = 0;
1933 1938
1934 rc = selinux_capable(current, current_cred(), CAP_SYS_ADMIN, 1939 rc = selinux_capable(current, current_cred(),
1940 &init_user_ns, CAP_SYS_ADMIN,
1935 SECURITY_CAP_NOAUDIT); 1941 SECURITY_CAP_NOAUDIT);
1936 if (rc == 0) 1942 if (rc == 0)
1937 cap_sys_admin = 1; 1943 cap_sys_admin = 1;
@@ -2101,7 +2107,7 @@ static inline void flush_unauthorized_files(const struct cred *cred,
2101 file = file_priv->file; 2107 file = file_priv->file;
2102 inode = file->f_path.dentry->d_inode; 2108 inode = file->f_path.dentry->d_inode;
2103 if (inode_has_perm(cred, inode, 2109 if (inode_has_perm(cred, inode,
2104 FILE__READ | FILE__WRITE, NULL)) { 2110 FILE__READ | FILE__WRITE, NULL, 0)) {
2105 drop_tty = 1; 2111 drop_tty = 1;
2106 } 2112 }
2107 } 2113 }
@@ -2633,7 +2639,7 @@ static int selinux_inode_follow_link(struct dentry *dentry, struct nameidata *na
2633 return dentry_has_perm(cred, NULL, dentry, FILE__READ); 2639 return dentry_has_perm(cred, NULL, dentry, FILE__READ);
2634} 2640}
2635 2641
2636static int selinux_inode_permission(struct inode *inode, int mask) 2642static int selinux_inode_permission(struct inode *inode, int mask, unsigned flags)
2637{ 2643{
2638 const struct cred *cred = current_cred(); 2644 const struct cred *cred = current_cred();
2639 struct common_audit_data ad; 2645 struct common_audit_data ad;
@@ -2655,7 +2661,7 @@ static int selinux_inode_permission(struct inode *inode, int mask)
2655 2661
2656 perms = file_mask_to_av(inode->i_mode, mask); 2662 perms = file_mask_to_av(inode->i_mode, mask);
2657 2663
2658 return inode_has_perm(cred, inode, perms, &ad); 2664 return inode_has_perm(cred, inode, perms, &ad, flags);
2659} 2665}
2660 2666
2661static int selinux_inode_setattr(struct dentry *dentry, struct iattr *iattr) 2667static int selinux_inode_setattr(struct dentry *dentry, struct iattr *iattr)
@@ -2723,7 +2729,7 @@ static int selinux_inode_setxattr(struct dentry *dentry, const char *name,
2723 if (!(sbsec->flags & SE_SBLABELSUPP)) 2729 if (!(sbsec->flags & SE_SBLABELSUPP))
2724 return -EOPNOTSUPP; 2730 return -EOPNOTSUPP;
2725 2731
2726 if (!is_owner_or_cap(inode)) 2732 if (!inode_owner_or_capable(inode))
2727 return -EPERM; 2733 return -EPERM;
2728 2734
2729 COMMON_AUDIT_DATA_INIT(&ad, FS); 2735 COMMON_AUDIT_DATA_INIT(&ad, FS);
@@ -2834,7 +2840,8 @@ static int selinux_inode_getsecurity(const struct inode *inode, const char *name
2834 * and lack of permission just means that we fall back to the 2840 * and lack of permission just means that we fall back to the
2835 * in-core context value, not a denial. 2841 * in-core context value, not a denial.
2836 */ 2842 */
2837 error = selinux_capable(current, current_cred(), CAP_MAC_ADMIN, 2843 error = selinux_capable(current, current_cred(),
2844 &init_user_ns, CAP_MAC_ADMIN,
2838 SECURITY_CAP_NOAUDIT); 2845 SECURITY_CAP_NOAUDIT);
2839 if (!error) 2846 if (!error)
2840 error = security_sid_to_context_force(isec->sid, &context, 2847 error = security_sid_to_context_force(isec->sid, &context,
@@ -2968,7 +2975,7 @@ static int selinux_file_ioctl(struct file *file, unsigned int cmd,
2968 case KDSKBENT: 2975 case KDSKBENT:
2969 case KDSKBSENT: 2976 case KDSKBSENT:
2970 error = task_has_capability(current, cred, CAP_SYS_TTY_CONFIG, 2977 error = task_has_capability(current, cred, CAP_SYS_TTY_CONFIG,
2971 SECURITY_CAP_AUDIT); 2978 SECURITY_CAP_AUDIT);
2972 break; 2979 break;
2973 2980
2974 /* default case assumes that the command will go 2981 /* default case assumes that the command will go
@@ -3202,7 +3209,7 @@ static int selinux_dentry_open(struct file *file, const struct cred *cred)
3202 * new inode label or new policy. 3209 * new inode label or new policy.
3203 * This check is not redundant - do not remove. 3210 * This check is not redundant - do not remove.
3204 */ 3211 */
3205 return inode_has_perm(cred, inode, open_file_to_av(file), NULL); 3212 return inode_has_perm(cred, inode, open_file_to_av(file), NULL, 0);
3206} 3213}
3207 3214
3208/* task security operations */ 3215/* task security operations */
diff --git a/security/selinux/include/avc.h b/security/selinux/include/avc.h
index 5615081b73e..e77b2ac2908 100644
--- a/security/selinux/include/avc.h
+++ b/security/selinux/include/avc.h
@@ -54,11 +54,11 @@ struct avc_cache_stats {
54 54
55void __init avc_init(void); 55void __init avc_init(void);
56 56
57void avc_audit(u32 ssid, u32 tsid, 57int avc_audit(u32 ssid, u32 tsid,
58 u16 tclass, u32 requested, 58 u16 tclass, u32 requested,
59 struct av_decision *avd, 59 struct av_decision *avd,
60 int result, 60 int result,
61 struct common_audit_data *a); 61 struct common_audit_data *a, unsigned flags);
62 62
63#define AVC_STRICT 1 /* Ignore permissive mode. */ 63#define AVC_STRICT 1 /* Ignore permissive mode. */
64int avc_has_perm_noaudit(u32 ssid, u32 tsid, 64int avc_has_perm_noaudit(u32 ssid, u32 tsid,
@@ -66,9 +66,17 @@ int avc_has_perm_noaudit(u32 ssid, u32 tsid,
66 unsigned flags, 66 unsigned flags,
67 struct av_decision *avd); 67 struct av_decision *avd);
68 68
69int avc_has_perm(u32 ssid, u32 tsid, 69int avc_has_perm_flags(u32 ssid, u32 tsid,
70 u16 tclass, u32 requested, 70 u16 tclass, u32 requested,
71 struct common_audit_data *auditdata); 71 struct common_audit_data *auditdata,
72 unsigned);
73
74static inline int avc_has_perm(u32 ssid, u32 tsid,
75 u16 tclass, u32 requested,
76 struct common_audit_data *auditdata)
77{
78 return avc_has_perm_flags(ssid, tsid, tclass, requested, auditdata, 0);
79}
72 80
73u32 avc_policy_seqno(void); 81u32 avc_policy_seqno(void);
74 82
diff --git a/security/selinux/netlabel.c b/security/selinux/netlabel.c
index 1c2fc46544b..c3bf3ed07b0 100644
--- a/security/selinux/netlabel.c
+++ b/security/selinux/netlabel.c
@@ -151,7 +151,7 @@ void selinux_netlbl_sk_security_free(struct sk_security_struct *sksec)
151 * 151 *
152 * Description: 152 * Description:
153 * Called when the NetLabel state of a sk_security_struct needs to be reset. 153 * Called when the NetLabel state of a sk_security_struct needs to be reset.
154 * The caller is responsibile for all the NetLabel sk_security_struct locking. 154 * The caller is responsible for all the NetLabel sk_security_struct locking.
155 * 155 *
156 */ 156 */
157void selinux_netlbl_sk_security_reset(struct sk_security_struct *sksec) 157void selinux_netlbl_sk_security_reset(struct sk_security_struct *sksec)
diff --git a/security/selinux/ss/services.c b/security/selinux/ss/services.c
index 3e7544d2a07..6ef4af47dac 100644
--- a/security/selinux/ss/services.c
+++ b/security/selinux/ss/services.c
@@ -213,7 +213,7 @@ static u16 map_class(u16 pol_value)
213 return i; 213 return i;
214 } 214 }
215 215
216 return pol_value; 216 return SECCLASS_NULL;
217} 217}
218 218
219static void map_decision(u16 tclass, struct av_decision *avd, 219static void map_decision(u16 tclass, struct av_decision *avd,
@@ -2806,7 +2806,7 @@ int selinux_audit_rule_init(u32 field, u32 op, char *rulestr, void **vrule)
2806 case AUDIT_SUBJ_CLR: 2806 case AUDIT_SUBJ_CLR:
2807 case AUDIT_OBJ_LEV_LOW: 2807 case AUDIT_OBJ_LEV_LOW:
2808 case AUDIT_OBJ_LEV_HIGH: 2808 case AUDIT_OBJ_LEV_HIGH:
2809 /* we do not allow a range, indicated by the presense of '-' */ 2809 /* we do not allow a range, indicated by the presence of '-' */
2810 if (strchr(rulestr, '-')) 2810 if (strchr(rulestr, '-'))
2811 return -EINVAL; 2811 return -EINVAL;
2812 break; 2812 break;
@@ -3075,7 +3075,7 @@ static void security_netlbl_cache_add(struct netlbl_lsm_secattr *secattr,
3075 * Description: 3075 * Description:
3076 * Convert the given NetLabel security attributes in @secattr into a 3076 * Convert the given NetLabel security attributes in @secattr into a
3077 * SELinux SID. If the @secattr field does not contain a full SELinux 3077 * SELinux SID. If the @secattr field does not contain a full SELinux
3078 * SID/context then use SECINITSID_NETMSG as the foundation. If possibile the 3078 * SID/context then use SECINITSID_NETMSG as the foundation. If possible the
3079 * 'cache' field of @secattr is set and the CACHE flag is set; this is to 3079 * 'cache' field of @secattr is set and the CACHE flag is set; this is to
3080 * allow the @secattr to be used by NetLabel to cache the secattr to SID 3080 * allow the @secattr to be used by NetLabel to cache the secattr to SID
3081 * conversion for future lookups. Returns zero on success, negative values on 3081 * conversion for future lookups. Returns zero on success, negative values on
'n3203' href='#n3203'>3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843 3844 3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857 3858 3859 3860 3861 3862 3863 3864 3865 3866 3867 3868 3869 3870 3871 3872 3873 3874 3875 3876 3877 3878 3879 3880 3881 3882 3883 3884 3885 3886 3887 3888 3889 3890 3891 3892 3893 3894 3895 3896 3897 3898 3899 3900 3901 3902 3903 3904 3905 3906 3907 3908 3909 3910 3911 3912 3913 3914 3915 3916 3917 3918 3919 3920 3921 3922 3923 3924 3925 3926 3927 3928 3929 3930 3931 3932 3933 3934 3935 3936 3937 3938 3939 3940 3941 3942 3943 3944 3945 3946 3947 3948 3949 3950 3951 3952 3953 3954 3955 3956 3957 3958 3959 3960 3961 3962 3963 3964 3965 3966 3967 3968 3969 3970 3971 3972 3973 3974 3975 3976 3977 3978 3979 3980 3981 3982 3983 3984 3985 3986 3987 3988 3989 3990 3991 3992 3993 3994 3995 3996 3997 3998 3999 4000 4001 4002 4003 4004 4005 4006 4007 4008 4009 4010 4011 4012 4013 4014 4015 4016 4017 4018 4019 4020 4021 4022 4023 4024 4025 4026 4027 4028 4029 4030 4031 4032 4033 4034 4035 4036 4037 4038 4039 4040 4041 4042 4043 4044 4045 4046 4047 4048 4049 4050 4051 4052 4053 4054 4055 4056 4057 4058 4059 4060 4061 4062 4063 4064 4065 4066 4067 4068 4069 4070 4071 4072 4073 4074 4075 4076 4077 4078 4079 4080 4081 4082 4083 4084 4085 4086 4087 4088 4089 4090 4091 4092 4093 4094 4095 4096 4097 4098 4099 4100 4101 4102 4103 4104 4105 4106 4107 4108 4109 4110 4111 4112 4113 4114 4115 4116 4117 4118 4119 4120 4121 4122 4123 4124 4125 4126 4127 4128 4129 4130 4131 4132 4133 4134 4135 4136 4137 4138 4139 4140 4141 4142 4143 4144 4145 4146 4147 4148 4149 4150 4151 4152 4153 4154 4155 4156 4157 4158 4159 4160 4161 4162 4163 4164 4165 4166 4167 4168 4169 4170 4171 4172 4173 4174 4175 4176 4177 4178 4179 4180 4181 4182 4183 4184 4185 4186 4187 4188 4189 4190 4191 4192 4193 4194 4195 4196 4197 4198 4199 4200 4201 4202 4203 4204 4205 4206 4207 4208 4209 4210 4211 4212 4213 4214 4215 4216 4217 4218 4219 4220 4221 4222 4223 4224 4225 4226 4227 4228 4229 4230 4231 4232 4233 4234 4235 4236 4237 4238 4239 4240 4241 4242 4243 4244 4245 4246 4247 4248 4249 4250 4251 4252 4253 4254 4255 4256 4257 4258 4259 4260 4261 4262 4263 4264 4265 4266 4267 4268 4269 4270 4271 4272 4273 4274 4275 4276 4277 4278 4279 4280 4281 4282 4283 4284 4285 4286 4287 4288 4289 4290 4291 4292 4293 4294 4295 4296 4297 4298 4299 4300 4301 4302 4303 4304 4305 4306 4307 4308 4309 4310 4311 4312 4313 4314 4315 4316 4317 4318 4319 4320 4321 4322 4323 4324 4325 4326 4327 4328 4329 4330 4331 4332 4333 4334 4335 4336 4337 4338 4339 4340 4341 4342 4343 4344 4345 4346 4347 4348 4349 4350 4351 4352 4353 4354 4355 4356 4357 4358 4359 4360 4361 4362 4363 4364 4365 4366 4367 4368 4369 4370 4371 4372 4373 4374 4375 4376 4377 4378 4379 4380 4381 4382 4383 4384 4385 4386 4387 4388 4389 4390 4391 4392 4393 4394 4395 4396 4397 4398 4399 4400 4401 4402 4403 4404 4405 4406 4407 4408 4409 4410 4411 4412 4413 4414 4415 4416 4417 4418 4419 4420 4421 4422 4423 4424 4425 4426 4427 4428 4429 4430 4431 4432 4433 4434 4435 4436 4437 4438 4439 4440 4441 4442 4443 4444 4445 4446 4447 4448 4449 4450 4451 4452 4453 4454 4455 4456 4457 4458 4459 4460 4461 4462 4463 4464 4465 4466 4467 4468 4469 4470 4471 4472 4473 4474 4475 4476 4477 4478 4479 4480 4481 4482 4483 4484 4485 4486 4487 4488 4489 4490 4491 4492 4493 4494 4495 4496 4497 4498 4499 4500 4501 4502 4503 4504 4505 4506 4507 4508 4509 4510 4511 4512 4513 4514 4515 4516 4517 4518 4519 4520 4521 4522 4523 4524 4525 4526 4527 4528 4529 4530 4531 4532 4533 4534 4535 4536 4537 4538 4539 4540 4541 4542 4543 4544 4545 4546 4547 4548 4549 4550 4551 4552 4553 4554 4555 4556 4557 4558 4559 4560 4561 4562 4563 4564 4565 4566 4567 4568 4569 4570 4571 4572 4573 4574 4575 4576 4577 4578 4579 4580 4581 4582 4583 4584 4585 4586 4587 4588 4589 4590 4591 4592 4593 4594 4595 4596 4597 4598 4599 4600 4601 4602 4603 4604 4605 4606 4607 4608 4609 4610 4611 4612 4613 4614 4615 4616 4617 4618 4619 4620 4621 4622 4623 4624 4625 4626 4627 4628 4629 4630 4631 4632 4633 4634 4635 4636 4637 4638 4639 4640 4641 4642 4643 4644 4645 4646 4647 4648 4649 4650 4651 4652 4653 4654 4655 4656 4657 4658 4659 4660 4661 4662 4663 4664 4665 4666 4667 4668 4669 4670 4671 4672 4673 4674 4675 4676 4677 4678 4679 4680 4681 4682 4683 4684 4685 4686 4687 4688 4689 4690 4691 4692 4693 4694 4695 4696 4697 4698 4699 4700 4701 4702 4703 4704 4705 4706 4707 4708 4709 4710 4711 4712 4713 4714 4715 4716 4717 4718 4719 4720 4721 4722 4723 4724 4725 4726 4727 4728 4729 4730 4731 4732 4733 4734 4735 4736 4737 4738 4739 4740 4741 4742 4743 4744 4745 4746 4747 4748 4749 4750 4751 4752 4753 4754 4755 4756 4757 4758 4759 4760 4761 4762 4763 4764 4765 4766 4767 4768 4769 4770 4771 4772 4773 4774 4775 4776 4777 4778 4779 4780 4781 4782 4783 4784 4785 4786 4787 4788 4789 4790 4791 4792 4793 4794 4795 4796 4797 4798 4799 4800 4801 4802 4803 4804 4805 4806 4807 4808 4809 4810 4811 4812 4813 4814 4815 4816 4817 4818 4819 4820 4821 4822 4823 4824 4825 4826 4827 4828 4829 4830 4831 4832 4833 4834 4835 4836 4837 4838 4839 4840 4841 4842 4843 4844 4845 4846 4847 4848 4849 4850 4851 4852 4853 4854 4855 4856 4857 4858 4859 4860 4861 4862 4863 4864 4865 4866 4867 4868 4869 4870 4871 4872 4873 4874 4875 4876 4877 4878 4879 4880 4881 4882 4883 4884 4885 4886 4887 4888 4889 4890 4891 4892 4893 4894 4895 4896 4897 4898 4899 4900 4901 4902 4903 4904 4905 4906 4907 4908 4909 4910 4911 4912 4913 4914 4915 4916 4917 4918 4919 4920 4921 4922 4923 4924 4925 4926 4927 4928 4929 4930 4931 4932 4933 4934 4935 4936 4937 4938 4939 4940 4941 4942 4943 4944 4945 4946 4947 4948 4949 4950 4951 4952 4953 4954 4955 4956 4957 4958 4959 4960 4961 4962 4963 4964 4965 4966 4967 4968 4969 4970 4971 4972 4973 4974 4975 4976 4977 4978 4979 4980 4981 4982 4983 4984 4985 4986 4987 4988 4989 4990 4991 4992 4993 4994 4995 4996 4997 4998 4999 5000 5001 5002 5003 5004 5005 5006 5007 5008 5009 5010 5011 5012 5013 5014 5015 5016 5017 5018 5019 5020 5021 5022 5023 5024 5025 5026 5027 5028 5029 5030 5031 5032 5033 5034 5035 5036 5037 5038 5039 5040 5041 5042 5043 5044 5045 5046 5047 5048 5049 5050 5051 5052 5053 5054 5055 5056 5057 5058 5059 5060 5061 5062 5063 5064 5065 5066 5067 5068 5069 5070 5071 5072 5073 5074 5075 5076 5077 5078 5079 5080 5081 5082 5083 5084 5085 5086 5087 5088 5089 5090 5091 5092 5093 5094 5095 5096 5097 5098 5099 5100 5101 5102 5103 5104 5105 5106 5107 5108 5109 5110 5111 5112 5113 5114 5115 5116 5117 5118 5119 5120 5121 5122 5123 5124 5125 5126 5127 5128 5129 5130 5131 5132 5133 5134 5135 5136 5137 5138 5139 5140 5141 5142 5143 5144 5145 5146 5147 5148 5149 5150 5151 5152 5153 5154 5155 5156 5157 5158 5159 5160 5161 5162 5163 5164 5165 5166 5167 5168 5169 5170 5171 5172 5173 5174 5175 5176 5177 5178 5179 5180 5181 5182 5183 5184 5185 5186 5187 5188 5189 5190 5191 5192 5193 5194 5195 5196 5197 5198 5199 5200 5201 5202 5203 5204 5205 5206 5207 5208 5209 5210 5211 5212 5213 5214 5215 5216 5217 5218 5219 5220 5221 5222 5223 5224 5225 5226 5227 5228 5229 5230 5231 5232 5233 5234 5235 5236 5237 5238 5239 5240 5241 5242 5243 5244 5245 5246 5247 5248 5249 5250 5251 5252 5253 5254 5255 5256 5257 5258 5259 5260 5261 5262 5263 5264 5265 5266 5267 5268 5269 5270 5271 5272 5273 5274 5275 5276 5277 5278 5279 5280 5281 5282 5283 5284 5285 5286 5287 5288 5289 5290 5291 5292 5293 5294 5295 5296 5297 5298 5299 5300 5301 5302 5303 5304 5305 5306 5307 5308 5309 5310 5311 5312 5313 5314 5315 5316 5317 5318 5319 5320 5321 5322 5323 5324 5325 5326 5327 5328 5329 5330 5331 5332 5333 5334 5335 5336 5337 5338 5339 5340 5341 5342 5343 5344 5345 5346 5347 5348 5349 5350 5351 5352 5353 5354 5355 5356 5357 5358 5359 5360 5361 5362 5363 5364 5365 5366 5367 5368 5369 5370 5371 5372 5373 5374 5375 5376 5377 5378 5379 5380 5381 5382 5383 5384 5385 5386 5387 5388 5389 5390 5391 5392 5393 5394 5395 5396 5397 5398 5399 5400 5401 5402 5403 5404 5405 5406 5407 5408 5409 5410 5411 5412 5413 5414 5415 5416 5417 5418 5419 5420 5421 5422 5423 5424 5425 5426 5427 5428 5429 5430 5431 5432 5433 5434 5435 5436 5437 5438 5439 5440 5441 5442 5443 5444 5445 5446 5447 5448 5449 5450 5451 5452 5453 5454 5455 5456 5457 5458 5459 5460 5461 5462 5463 5464 5465 5466 5467 5468 5469 5470 5471 5472 5473 5474 5475 5476 5477 5478 5479 5480 5481 5482 5483 5484 5485 5486 5487 5488 5489 5490 5491 5492 5493 5494 5495 5496 5497 5498 5499 5500 5501 5502 5503 5504 5505 5506 5507 5508 5509 5510 5511 5512 5513 5514 5515 5516 5517 5518 5519 5520 5521 5522 5523 5524 5525 5526 5527 5528 5529 5530 5531 5532 5533 5534 5535 5536 5537 5538 5539 5540 5541 5542 5543 5544 5545 5546 5547 5548 5549 5550 5551 5552 5553 5554 5555 5556 5557 5558 5559 5560 5561 5562 5563 5564 5565 5566 5567 5568 5569 5570 5571 5572 5573 5574 5575 5576 5577 5578 5579 5580 5581 5582 5583 5584 5585 5586 5587 5588 5589 5590 5591 5592 5593 5594 5595 5596 5597 5598 5599 5600 5601 5602 5603 5604 5605 5606 5607 5608 5609 5610 5611 5612 5613 5614 5615 5616 5617 5618 5619 5620 5621 5622 5623 5624 5625 5626 5627 5628 5629 5630 5631 5632 5633 5634 5635 5636 5637 5638 5639 5640 5641 5642 5643 5644 5645 5646 5647 5648 5649 5650 5651 5652 5653 5654 5655 5656 5657 5658 5659 5660 5661 5662 5663 5664 5665 5666 5667 5668 5669 5670 5671 5672 5673 5674 5675 5676 5677 5678 5679 5680 5681 5682 5683 5684 5685 5686 5687 5688 5689 5690 5691 5692 5693 5694 5695 5696 5697 5698 5699 5700 5701 5702 5703 5704 5705 5706 5707 5708 5709 5710 5711 5712 5713 5714 5715 5716 5717 5718 5719 5720 5721 5722 5723 5724 5725 5726 5727 5728 5729 5730 5731 5732 5733 5734 5735 5736 5737 5738 5739 5740 5741 5742 5743 5744 5745 5746 5747 5748 5749 5750 5751 5752 5753 5754 5755 5756 5757 5758 5759 5760 5761 5762 5763 5764 5765 5766 5767 5768 5769 5770 5771 5772 5773 5774 5775 5776 5777 5778 5779 5780 5781 5782 5783 5784 5785 5786 5787 5788 5789 5790 5791 5792 5793 5794 5795 5796 5797 5798 5799 5800 5801 5802 5803 5804 5805 5806 5807 5808 5809 5810 5811 5812 5813 5814 5815 5816 5817 5818 5819 5820 5821 5822 5823 5824 5825 5826 5827 5828 5829 5830 5831 5832 5833 5834 5835 5836 5837 5838 5839 5840 5841 5842 5843 5844 5845 5846 5847 5848 5849 5850 5851 5852 5853 5854 5855 5856 5857 5858 5859 5860 5861 5862 5863 5864 5865 5866 5867 5868 5869 5870 5871 5872 5873 5874 5875 5876 5877 5878 5879 5880 5881 5882 5883 5884 5885 5886 5887 5888 5889 5890 5891 5892 5893 5894 5895 5896 5897 5898 5899 5900 5901 5902 5903 5904 5905 5906 5907 5908 5909 5910 5911 5912 5913 5914 5915 5916 5917 5918 5919 5920 5921 5922 5923 5924 5925 5926 5927 5928 5929 5930 5931 5932 5933 5934 5935 5936 5937 5938 5939 5940 5941 5942 5943 5944 5945 5946 5947 5948 5949 5950 5951 5952 5953 5954 5955 5956 5957 5958 5959 5960 5961 5962 5963 5964 5965 5966 5967 5968 5969 5970 5971 5972 5973 5974 5975 5976 5977 5978 5979 5980 5981 5982 5983 5984 5985 5986 5987 5988 5989 5990 5991 5992 5993 5994 5995 5996 5997 5998 5999 6000 6001 6002 6003 6004 6005 6006 6007 6008 6009 6010 6011 6012 6013 6014 6015 6016 6017 6018 6019 6020 6021 6022 6023 6024 6025 6026 6027 6028 6029 6030 6031 6032 6033 6034 6035 6036 6037 6038 6039 6040 6041 6042 6043 6044 6045 6046 6047 6048 6049 6050 6051 6052 6053 6054 6055 6056 6057 6058 6059 6060 6061 6062 6063 6064 6065 6066 6067 6068 6069 6070 6071 6072 6073 6074 6075 6076 6077 6078 6079 6080 6081 6082 6083 6084 6085 6086 6087 6088 6089 6090 6091 6092 6093 6094 6095 6096 6097 6098 6099 6100 6101 6102 6103 6104 6105 6106 6107 6108 6109 6110 6111 6112 6113 6114 6115 6116 6117 6118 6119 6120 6121 6122 6123 6124 6125 6126 6127 6128 6129 6130 6131 6132 6133 6134 6135 6136 6137 6138 6139 6140 6141 6142 6143 6144 6145 6146 6147 6148 6149 6150 6151 6152 6153 6154 6155 6156 6157 6158 6159 6160 6161 6162 6163 6164 6165 6166 6167 6168 6169 6170 6171 6172 6173 6174 6175 6176 6177 6178 6179 6180 6181 6182 6183 6184 6185 6186 6187 6188 6189 6190 6191 6192 6193 6194 6195 6196 6197 6198 6199 6200 6201 6202 6203 6204 6205 6206 6207 6208 6209 6210 6211 6212 6213 6214 6215 6216 6217 6218 6219 6220 6221 6222 6223 6224 6225 6226 6227 6228 6229 6230 6231 6232 6233 6234 6235 6236 6237 6238 6239 6240 6241 6242 6243 6244 6245 6246 6247 6248 6249 6250 6251 6252 6253 6254 6255 6256 6257 6258 6259 6260 6261 6262 6263 6264 6265 6266 6267 6268 6269 6270 6271 6272 6273 6274 6275 6276 6277 6278 6279 6280 6281 6282 6283 6284 6285 6286 6287 6288 6289 6290 6291 6292 6293 6294 6295 6296 6297 6298 6299 6300 6301 6302 6303 6304 6305 6306 6307 6308 6309 6310 6311 6312 6313 6314 6315 6316 6317 6318 6319 6320 6321 6322 6323 6324 6325 6326 6327
/*
 * Kernel-based Virtual Machine driver for Linux
 *
 * derived from drivers/kvm/kvm_main.c
 *
 * Copyright (C) 2006 Qumranet, Inc.
 * Copyright (C) 2008 Qumranet, Inc.
 * Copyright IBM Corporation, 2008
 * Copyright 2010 Red Hat, Inc. and/or its affiliates.
 *
 * Authors:
 *   Avi Kivity   <avi@qumranet.com>
 *   Yaniv Kamay  <yaniv@qumranet.com>
 *   Amit Shah    <amit.shah@qumranet.com>
 *   Ben-Ami Yassour <benami@il.ibm.com>
 *
 * This work is licensed under the terms of the GNU GPL, version 2.  See
 * the COPYING file in the top-level directory.
 *
 */

#include <linux/kvm_host.h>
#include "irq.h"
#include "mmu.h"
#include "i8254.h"
#include "tss.h"
#include "kvm_cache_regs.h"
#include "x86.h"
#include "cpuid.h"

#include <linux/clocksource.h>
#include <linux/interrupt.h>
#include <linux/kvm.h>
#include <linux/fs.h>
#include <linux/vmalloc.h>
#include <linux/module.h>
#include <linux/mman.h>
#include <linux/highmem.h>
#include <linux/iommu.h>
#include <linux/intel-iommu.h>
#include <linux/cpufreq.h>
#include <linux/user-return-notifier.h>
#include <linux/srcu.h>
#include <linux/slab.h>
#include <linux/perf_event.h>
#include <linux/uaccess.h>
#include <linux/hash.h>
#include <linux/pci.h>
#include <trace/events/kvm.h>

#define CREATE_TRACE_POINTS
#include "trace.h"

#include <asm/debugreg.h>
#include <asm/msr.h>
#include <asm/desc.h>
#include <asm/mtrr.h>
#include <asm/mce.h>
#include <asm/i387.h>
#include <asm/xcr.h>
#include <asm/pvclock.h>
#include <asm/div64.h>

#define MAX_IO_MSRS 256
#define KVM_MAX_MCE_BANKS 32
#define KVM_MCE_CAP_SUPPORTED (MCG_CTL_P | MCG_SER_P)

#define emul_to_vcpu(ctxt) \
	container_of(ctxt, struct kvm_vcpu, arch.emulate_ctxt)

/* EFER defaults:
 * - enable syscall per default because its emulated by KVM
 * - enable LME and LMA per default on 64 bit KVM
 */
#ifdef CONFIG_X86_64
static
u64 __read_mostly efer_reserved_bits = ~((u64)(EFER_SCE | EFER_LME | EFER_LMA));
#else
static u64 __read_mostly efer_reserved_bits = ~((u64)EFER_SCE);
#endif

#define VM_STAT(x) offsetof(struct kvm, stat.x), KVM_STAT_VM
#define VCPU_STAT(x) offsetof(struct kvm_vcpu, stat.x), KVM_STAT_VCPU

static void update_cr8_intercept(struct kvm_vcpu *vcpu);
static void process_nmi(struct kvm_vcpu *vcpu);

struct kvm_x86_ops *kvm_x86_ops;
EXPORT_SYMBOL_GPL(kvm_x86_ops);

int ignore_msrs = 0;
module_param_named(ignore_msrs, ignore_msrs, bool, S_IRUGO | S_IWUSR);

bool kvm_has_tsc_control;
EXPORT_SYMBOL_GPL(kvm_has_tsc_control);
u32  kvm_max_guest_tsc_khz;
EXPORT_SYMBOL_GPL(kvm_max_guest_tsc_khz);

#define KVM_NR_SHARED_MSRS 16

struct kvm_shared_msrs_global {
	int nr;
	u32 msrs[KVM_NR_SHARED_MSRS];
};

struct kvm_shared_msrs {
	struct user_return_notifier urn;
	bool registered;
	struct kvm_shared_msr_values {
		u64 host;
		u64 curr;
	} values[KVM_NR_SHARED_MSRS];
};

static struct kvm_shared_msrs_global __read_mostly shared_msrs_global;
static DEFINE_PER_CPU(struct kvm_shared_msrs, shared_msrs);

struct kvm_stats_debugfs_item debugfs_entries[] = {
	{ "pf_fixed", VCPU_STAT(pf_fixed) },
	{ "pf_guest", VCPU_STAT(pf_guest) },
	{ "tlb_flush", VCPU_STAT(tlb_flush) },
	{ "invlpg", VCPU_STAT(invlpg) },
	{ "exits", VCPU_STAT(exits) },
	{ "io_exits", VCPU_STAT(io_exits) },
	{ "mmio_exits", VCPU_STAT(mmio_exits) },
	{ "signal_exits", VCPU_STAT(signal_exits) },
	{ "irq_window", VCPU_STAT(irq_window_exits) },
	{ "nmi_window", VCPU_STAT(nmi_window_exits) },
	{ "halt_exits", VCPU_STAT(halt_exits) },
	{ "halt_wakeup", VCPU_STAT(halt_wakeup) },
	{ "hypercalls", VCPU_STAT(hypercalls) },
	{ "request_irq", VCPU_STAT(request_irq_exits) },
	{ "irq_exits", VCPU_STAT(irq_exits) },
	{ "host_state_reload", VCPU_STAT(host_state_reload) },
	{ "efer_reload", VCPU_STAT(efer_reload) },
	{ "fpu_reload", VCPU_STAT(fpu_reload) },
	{ "insn_emulation", VCPU_STAT(insn_emulation) },
	{ "insn_emulation_fail", VCPU_STAT(insn_emulation_fail) },
	{ "irq_injections", VCPU_STAT(irq_injections) },
	{ "nmi_injections", VCPU_STAT(nmi_injections) },
	{ "mmu_shadow_zapped", VM_STAT(mmu_shadow_zapped) },
	{ "mmu_pte_write", VM_STAT(mmu_pte_write) },
	{ "mmu_pte_updated", VM_STAT(mmu_pte_updated) },
	{ "mmu_pde_zapped", VM_STAT(mmu_pde_zapped) },
	{ "mmu_flooded", VM_STAT(mmu_flooded) },
	{ "mmu_recycled", VM_STAT(mmu_recycled) },
	{ "mmu_cache_miss", VM_STAT(mmu_cache_miss) },
	{ "mmu_unsync", VM_STAT(mmu_unsync) },
	{ "remote_tlb_flush", VM_STAT(remote_tlb_flush) },
	{ "largepages", VM_STAT(lpages) },
	{ NULL }
};

u64 __read_mostly host_xcr0;

int emulator_fix_hypercall(struct x86_emulate_ctxt *ctxt);

static inline void kvm_async_pf_hash_reset(struct kvm_vcpu *vcpu)
{
	int i;
	for (i = 0; i < roundup_pow_of_two(ASYNC_PF_PER_VCPU); i++)
		vcpu->arch.apf.gfns[i] = ~0;
}

static void kvm_on_user_return(struct user_return_notifier *urn)
{
	unsigned slot;
	struct kvm_shared_msrs *locals
		= container_of(urn, struct kvm_shared_msrs, urn);
	struct kvm_shared_msr_values *values;

	for (slot = 0; slot < shared_msrs_global.nr; ++slot) {
		values = &locals->values[slot];
		if (values->host != values->curr) {
			wrmsrl(shared_msrs_global.msrs[slot], values->host);
			values->curr = values->host;
		}
	}
	locals->registered = false;
	user_return_notifier_unregister(urn);
}

static void shared_msr_update(unsigned slot, u32 msr)
{
	struct kvm_shared_msrs *smsr;
	u64 value;

	smsr = &__get_cpu_var(shared_msrs);
	/* only read, and nobody should modify it at this time,
	 * so don't need lock */
	if (slot >= shared_msrs_global.nr) {
		printk(KERN_ERR "kvm: invalid MSR slot!");
		return;
	}
	rdmsrl_safe(msr, &value);
	smsr->values[slot].host = value;
	smsr->values[slot].curr = value;
}

void kvm_define_shared_msr(unsigned slot, u32 msr)
{
	if (slot >= shared_msrs_global.nr)
		shared_msrs_global.nr = slot + 1;
	shared_msrs_global.msrs[slot] = msr;
	/* we need ensured the shared_msr_global have been updated */
	smp_wmb();
}
EXPORT_SYMBOL_GPL(kvm_define_shared_msr);

static void kvm_shared_msr_cpu_online(void)
{
	unsigned i;

	for (i = 0; i < shared_msrs_global.nr; ++i)
		shared_msr_update(i, shared_msrs_global.msrs[i]);
}

void kvm_set_shared_msr(unsigned slot, u64 value, u64 mask)
{
	struct kvm_shared_msrs *smsr = &__get_cpu_var(shared_msrs);

	if (((value ^ smsr->values[slot].curr) & mask) == 0)
		return;
	smsr->values[slot].curr = value;
	wrmsrl(shared_msrs_global.msrs[slot], value);
	if (!smsr->registered) {
		smsr->urn.on_user_return = kvm_on_user_return;
		user_return_notifier_register(&smsr->urn);
		smsr->registered = true;
	}
}
EXPORT_SYMBOL_GPL(kvm_set_shared_msr);

static void drop_user_return_notifiers(void *ignore)
{
	struct kvm_shared_msrs *smsr = &__get_cpu_var(shared_msrs);

	if (smsr->registered)
		kvm_on_user_return(&smsr->urn);
}

u64 kvm_get_apic_base(struct kvm_vcpu *vcpu)
{
	if (irqchip_in_kernel(vcpu->kvm))
		return vcpu->arch.apic_base;
	else
		return vcpu->arch.apic_base;
}
EXPORT_SYMBOL_GPL(kvm_get_apic_base);

void kvm_set_apic_base(struct kvm_vcpu *vcpu, u64 data)
{
	/* TODO: reserve bits check */
	if (irqchip_in_kernel(vcpu->kvm))
		kvm_lapic_set_base(vcpu, data);
	else
		vcpu->arch.apic_base = data;
}
EXPORT_SYMBOL_GPL(kvm_set_apic_base);

#define EXCPT_BENIGN		0
#define EXCPT_CONTRIBUTORY	1
#define EXCPT_PF		2

static int exception_class(int vector)
{
	switch (vector) {
	case PF_VECTOR:
		return EXCPT_PF;
	case DE_VECTOR:
	case TS_VECTOR:
	case NP_VECTOR:
	case SS_VECTOR:
	case GP_VECTOR:
		return EXCPT_CONTRIBUTORY;
	default:
		break;
	}
	return EXCPT_BENIGN;
}

static void kvm_multiple_exception(struct kvm_vcpu *vcpu,
		unsigned nr, bool has_error, u32 error_code,
		bool reinject)
{
	u32 prev_nr;
	int class1, class2;

	kvm_make_request(KVM_REQ_EVENT, vcpu);

	if (!vcpu->arch.exception.pending) {
	queue:
		vcpu->arch.exception.pending = true;
		vcpu->arch.exception.has_error_code = has_error;
		vcpu->arch.exception.nr = nr;
		vcpu->arch.exception.error_code = error_code;
		vcpu->arch.exception.reinject = reinject;
		return;
	}

	/* to check exception */
	prev_nr = vcpu->arch.exception.nr;
	if (prev_nr == DF_VECTOR) {
		/* triple fault -> shutdown */
		kvm_make_request(KVM_REQ_TRIPLE_FAULT, vcpu);
		return;
	}
	class1 = exception_class(prev_nr);
	class2 = exception_class(nr);
	if ((class1 == EXCPT_CONTRIBUTORY && class2 == EXCPT_CONTRIBUTORY)
		|| (class1 == EXCPT_PF && class2 != EXCPT_BENIGN)) {
		/* generate double fault per SDM Table 5-5 */
		vcpu->arch.exception.pending = true;
		vcpu->arch.exception.has_error_code = true;
		vcpu->arch.exception.nr = DF_VECTOR;
		vcpu->arch.exception.error_code = 0;
	} else
		/* replace previous exception with a new one in a hope
		   that instruction re-execution will regenerate lost
		   exception */
		goto queue;
}

void kvm_queue_exception(struct kvm_vcpu *vcpu, unsigned nr)
{
	kvm_multiple_exception(vcpu, nr, false, 0, false);
}
EXPORT_SYMBOL_GPL(kvm_queue_exception);

void kvm_requeue_exception(struct kvm_vcpu *vcpu, unsigned nr)
{
	kvm_multiple_exception(vcpu, nr, false, 0, true);
}
EXPORT_SYMBOL_GPL(kvm_requeue_exception);

void kvm_complete_insn_gp(struct kvm_vcpu *vcpu, int err)
{
	if (err)
		kvm_inject_gp(vcpu, 0);
	else
		kvm_x86_ops->skip_emulated_instruction(vcpu);
}
EXPORT_SYMBOL_GPL(kvm_complete_insn_gp);

void kvm_inject_page_fault(struct kvm_vcpu *vcpu, struct x86_exception *fault)
{
	++vcpu->stat.pf_guest;
	vcpu->arch.cr2 = fault->address;
	kvm_queue_exception_e(vcpu, PF_VECTOR, fault->error_code);
}
EXPORT_SYMBOL_GPL(kvm_inject_page_fault);

void kvm_propagate_fault(struct kvm_vcpu *vcpu, struct x86_exception *fault)
{
	if (mmu_is_nested(vcpu) && !fault->nested_page_fault)
		vcpu->arch.nested_mmu.inject_page_fault(vcpu, fault);
	else
		vcpu->arch.mmu.inject_page_fault(vcpu, fault);
}

void kvm_inject_nmi(struct kvm_vcpu *vcpu)
{
	atomic_inc(&vcpu->arch.nmi_queued);
	kvm_make_request(KVM_REQ_NMI, vcpu);
}
EXPORT_SYMBOL_GPL(kvm_inject_nmi);

void kvm_queue_exception_e(struct kvm_vcpu *vcpu, unsigned nr, u32 error_code)
{
	kvm_multiple_exception(vcpu, nr, true, error_code, false);
}
EXPORT_SYMBOL_GPL(kvm_queue_exception_e);

void kvm_requeue_exception_e(struct kvm_vcpu *vcpu, unsigned nr, u32 error_code)
{
	kvm_multiple_exception(vcpu, nr, true, error_code, true);
}
EXPORT_SYMBOL_GPL(kvm_requeue_exception_e);

/*
 * Checks if cpl <= required_cpl; if true, return true.  Otherwise queue
 * a #GP and return false.
 */
bool kvm_require_cpl(struct kvm_vcpu *vcpu, int required_cpl)
{
	if (kvm_x86_ops->get_cpl(vcpu) <= required_cpl)
		return true;
	kvm_queue_exception_e(vcpu, GP_VECTOR, 0);
	return false;
}
EXPORT_SYMBOL_GPL(kvm_require_cpl);

/*
 * This function will be used to read from the physical memory of the currently
 * running guest. The difference to kvm_read_guest_page is that this function
 * can read from guest physical or from the guest's guest physical memory.
 */
int kvm_read_guest_page_mmu(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu,
			    gfn_t ngfn, void *data, int offset, int len,
			    u32 access)
{
	gfn_t real_gfn;
	gpa_t ngpa;

	ngpa     = gfn_to_gpa(ngfn);
	real_gfn = mmu->translate_gpa(vcpu, ngpa, access);
	if (real_gfn == UNMAPPED_GVA)
		return -EFAULT;

	real_gfn = gpa_to_gfn(real_gfn);

	return kvm_read_guest_page(vcpu->kvm, real_gfn, data, offset, len);
}
EXPORT_SYMBOL_GPL(kvm_read_guest_page_mmu);

int kvm_read_nested_guest_page(struct kvm_vcpu *vcpu, gfn_t gfn,
			       void *data, int offset, int len, u32 access)
{
	return kvm_read_guest_page_mmu(vcpu, vcpu->arch.walk_mmu, gfn,
				       data, offset, len, access);
}

/*
 * Load the pae pdptrs.  Return true is they are all valid.
 */
int load_pdptrs(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, unsigned long cr3)
{
	gfn_t pdpt_gfn = cr3 >> PAGE_SHIFT;
	unsigned offset = ((cr3 & (PAGE_SIZE-1)) >> 5) << 2;
	int i;
	int ret;
	u64 pdpte[ARRAY_SIZE(mmu->pdptrs)];

	ret = kvm_read_guest_page_mmu(vcpu, mmu, pdpt_gfn, pdpte,
				      offset * sizeof(u64), sizeof(pdpte),
				      PFERR_USER_MASK|PFERR_WRITE_MASK);
	if (ret < 0) {
		ret = 0;
		goto out;
	}
	for (i = 0; i < ARRAY_SIZE(pdpte); ++i) {
		if (is_present_gpte(pdpte[i]) &&
		    (pdpte[i] & vcpu->arch.mmu.rsvd_bits_mask[0][2])) {
			ret = 0;
			goto out;
		}
	}
	ret = 1;

	memcpy(mmu->pdptrs, pdpte, sizeof(mmu->pdptrs));
	__set_bit(VCPU_EXREG_PDPTR,
		  (unsigned long *)&vcpu->arch.regs_avail);
	__set_bit(VCPU_EXREG_PDPTR,
		  (unsigned long *)&vcpu->arch.regs_dirty);
out:

	return ret;
}
EXPORT_SYMBOL_GPL(load_pdptrs);

static bool pdptrs_changed(struct kvm_vcpu *vcpu)
{
	u64 pdpte[ARRAY_SIZE(vcpu->arch.walk_mmu->pdptrs)];
	bool changed = true;
	int offset;
	gfn_t gfn;
	int r;

	if (is_long_mode(vcpu) || !is_pae(vcpu))
		return false;

	if (!test_bit(VCPU_EXREG_PDPTR,
		      (unsigned long *)&vcpu->arch.regs_avail))
		return true;

	gfn = (kvm_read_cr3(vcpu) & ~31u) >> PAGE_SHIFT;
	offset = (kvm_read_cr3(vcpu) & ~31u) & (PAGE_SIZE - 1);
	r = kvm_read_nested_guest_page(vcpu, gfn, pdpte, offset, sizeof(pdpte),
				       PFERR_USER_MASK | PFERR_WRITE_MASK);
	if (r < 0)
		goto out;
	changed = memcmp(pdpte, vcpu->arch.walk_mmu->pdptrs, sizeof(pdpte)) != 0;
out:

	return changed;
}

int kvm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0)
{
	unsigned long old_cr0 = kvm_read_cr0(vcpu);
	unsigned long update_bits = X86_CR0_PG | X86_CR0_WP |
				    X86_CR0_CD | X86_CR0_NW;

	cr0 |= X86_CR0_ET;

#ifdef CONFIG_X86_64
	if (cr0 & 0xffffffff00000000UL)
		return 1;
#endif

	cr0 &= ~CR0_RESERVED_BITS;

	if ((cr0 & X86_CR0_NW) && !(cr0 & X86_CR0_CD))
		return 1;

	if ((cr0 & X86_CR0_PG) && !(cr0 & X86_CR0_PE))
		return 1;

	if (!is_paging(vcpu) && (cr0 & X86_CR0_PG)) {
#ifdef CONFIG_X86_64
		if ((vcpu->arch.efer & EFER_LME)) {
			int cs_db, cs_l;

			if (!is_pae(vcpu))
				return 1;
			kvm_x86_ops->get_cs_db_l_bits(vcpu, &cs_db, &cs_l);
			if (cs_l)
				return 1;
		} else
#endif
		if (is_pae(vcpu) && !load_pdptrs(vcpu, vcpu->arch.walk_mmu,
						 kvm_read_cr3(vcpu)))
			return 1;
	}

	kvm_x86_ops->set_cr0(vcpu, cr0);

	if ((cr0 ^ old_cr0) & X86_CR0_PG) {
		kvm_clear_async_pf_completion_queue(vcpu);
		kvm_async_pf_hash_reset(vcpu);
	}

	if ((cr0 ^ old_cr0) & update_bits)
		kvm_mmu_reset_context(vcpu);
	return 0;
}
EXPORT_SYMBOL_GPL(kvm_set_cr0);

void kvm_lmsw(struct kvm_vcpu *vcpu, unsigned long msw)
{
	(void)kvm_set_cr0(vcpu, kvm_read_cr0_bits(vcpu, ~0x0eul) | (msw & 0x0f));
}
EXPORT_SYMBOL_GPL(kvm_lmsw);

int __kvm_set_xcr(struct kvm_vcpu *vcpu, u32 index, u64 xcr)
{
	u64 xcr0;

	/* Only support XCR_XFEATURE_ENABLED_MASK(xcr0) now  */
	if (index != XCR_XFEATURE_ENABLED_MASK)
		return 1;
	xcr0 = xcr;
	if (kvm_x86_ops->get_cpl(vcpu) != 0)
		return 1;
	if (!(xcr0 & XSTATE_FP))
		return 1;
	if ((xcr0 & XSTATE_YMM) && !(xcr0 & XSTATE_SSE))
		return 1;
	if (xcr0 & ~host_xcr0)
		return 1;
	vcpu->arch.xcr0 = xcr0;
	vcpu->guest_xcr0_loaded = 0;
	return 0;
}

int kvm_set_xcr(struct kvm_vcpu *vcpu, u32 index, u64 xcr)
{
	if (__kvm_set_xcr(vcpu, index, xcr)) {
		kvm_inject_gp(vcpu, 0);
		return 1;
	}
	return 0;
}
EXPORT_SYMBOL_GPL(kvm_set_xcr);

int kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
{
	unsigned long old_cr4 = kvm_read_cr4(vcpu);
	unsigned long pdptr_bits = X86_CR4_PGE | X86_CR4_PSE |
				   X86_CR4_PAE | X86_CR4_SMEP;
	if (cr4 & CR4_RESERVED_BITS)
		return 1;

	if (!guest_cpuid_has_xsave(vcpu) && (cr4 & X86_CR4_OSXSAVE))
		return 1;

	if (!guest_cpuid_has_smep(vcpu) && (cr4 & X86_CR4_SMEP))
		return 1;

	if (!guest_cpuid_has_fsgsbase(vcpu) && (cr4 & X86_CR4_RDWRGSFS))
		return 1;

	if (is_long_mode(vcpu)) {
		if (!(cr4 & X86_CR4_PAE))
			return 1;
	} else if (is_paging(vcpu) && (cr4 & X86_CR4_PAE)
		   && ((cr4 ^ old_cr4) & pdptr_bits)
		   && !load_pdptrs(vcpu, vcpu->arch.walk_mmu,
				   kvm_read_cr3(vcpu)))
		return 1;

	if (kvm_x86_ops->set_cr4(vcpu, cr4))
		return 1;

	if ((cr4 ^ old_cr4) & pdptr_bits)
		kvm_mmu_reset_context(vcpu);

	if ((cr4 ^ old_cr4) & X86_CR4_OSXSAVE)
		kvm_update_cpuid(vcpu);

	return 0;
}
EXPORT_SYMBOL_GPL(kvm_set_cr4);

int kvm_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3)
{
	if (cr3 == kvm_read_cr3(vcpu) && !pdptrs_changed(vcpu)) {
		kvm_mmu_sync_roots(vcpu);
		kvm_mmu_flush_tlb(vcpu);
		return 0;
	}

	if (is_long_mode(vcpu)) {
		if (cr3 & CR3_L_MODE_RESERVED_BITS)
			return 1;
	} else {
		if (is_pae(vcpu)) {
			if (cr3 & CR3_PAE_RESERVED_BITS)
				return 1;
			if (is_paging(vcpu) &&
			    !load_pdptrs(vcpu, vcpu->arch.walk_mmu, cr3))
				return 1;
		}
		/*
		 * We don't check reserved bits in nonpae mode, because
		 * this isn't enforced, and VMware depends on this.
		 */
	}

	/*
	 * Does the new cr3 value map to physical memory? (Note, we
	 * catch an invalid cr3 even in real-mode, because it would
	 * cause trouble later on when we turn on paging anyway.)
	 *
	 * A real CPU would silently accept an invalid cr3 and would
	 * attempt to use it - with largely undefined (and often hard
	 * to debug) behavior on the guest side.
	 */
	if (unlikely(!gfn_to_memslot(vcpu->kvm, cr3 >> PAGE_SHIFT)))
		return 1;
	vcpu->arch.cr3 = cr3;
	__set_bit(VCPU_EXREG_CR3, (ulong *)&vcpu->arch.regs_avail);
	vcpu->arch.mmu.new_cr3(vcpu);
	return 0;
}
EXPORT_SYMBOL_GPL(kvm_set_cr3);

int kvm_set_cr8(struct kvm_vcpu *vcpu, unsigned long cr8)
{
	if (cr8 & CR8_RESERVED_BITS)
		return 1;
	if (irqchip_in_kernel(vcpu->kvm))
		kvm_lapic_set_tpr(vcpu, cr8);
	else
		vcpu->arch.cr8 = cr8;
	return 0;
}
EXPORT_SYMBOL_GPL(kvm_set_cr8);

unsigned long kvm_get_cr8(struct kvm_vcpu *vcpu)
{
	if (irqchip_in_kernel(vcpu->kvm))
		return kvm_lapic_get_cr8(vcpu);
	else
		return vcpu->arch.cr8;
}
EXPORT_SYMBOL_GPL(kvm_get_cr8);

static int __kvm_set_dr(struct kvm_vcpu *vcpu, int dr, unsigned long val)
{
	switch (dr) {
	case 0 ... 3:
		vcpu->arch.db[dr] = val;
		if (!(vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP))
			vcpu->arch.eff_db[dr] = val;
		break;
	case 4:
		if (kvm_read_cr4_bits(vcpu, X86_CR4_DE))
			return 1; /* #UD */
		/* fall through */
	case 6:
		if (val & 0xffffffff00000000ULL)
			return -1; /* #GP */
		vcpu->arch.dr6 = (val & DR6_VOLATILE) | DR6_FIXED_1;
		break;
	case 5:
		if (kvm_read_cr4_bits(vcpu, X86_CR4_DE))
			return 1; /* #UD */
		/* fall through */
	default: /* 7 */
		if (val & 0xffffffff00000000ULL)
			return -1; /* #GP */
		vcpu->arch.dr7 = (val & DR7_VOLATILE) | DR7_FIXED_1;
		if (!(vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP)) {
			kvm_x86_ops->set_dr7(vcpu, vcpu->arch.dr7);
			vcpu->arch.switch_db_regs = (val & DR7_BP_EN_MASK);
		}
		break;
	}

	return 0;
}

int kvm_set_dr(struct kvm_vcpu *vcpu, int dr, unsigned long val)
{
	int res;

	res = __kvm_set_dr(vcpu, dr, val);
	if (res > 0)
		kvm_queue_exception(vcpu, UD_VECTOR);
	else if (res < 0)
		kvm_inject_gp(vcpu, 0);

	return res;
}
EXPORT_SYMBOL_GPL(kvm_set_dr);

static int _kvm_get_dr(struct kvm_vcpu *vcpu, int dr, unsigned long *val)
{
	switch (dr) {
	case 0 ... 3:
		*val = vcpu->arch.db[dr];
		break;
	case 4:
		if (kvm_read_cr4_bits(vcpu, X86_CR4_DE))
			return 1;
		/* fall through */
	case 6:
		*val = vcpu->arch.dr6;
		break;
	case 5:
		if (kvm_read_cr4_bits(vcpu, X86_CR4_DE))
			return 1;
		/* fall through */
	default: /* 7 */
		*val = vcpu->arch.dr7;
		break;
	}

	return 0;
}

int kvm_get_dr(struct kvm_vcpu *vcpu, int dr, unsigned long *val)
{
	if (_kvm_get_dr(vcpu, dr, val)) {
		kvm_queue_exception(vcpu, UD_VECTOR);
		return 1;
	}
	return 0;
}
EXPORT_SYMBOL_GPL(kvm_get_dr);

/*
 * List of msr numbers which we expose to userspace through KVM_GET_MSRS
 * and KVM_SET_MSRS, and KVM_GET_MSR_INDEX_LIST.
 *
 * This list is modified at module load time to reflect the
 * capabilities of the host cpu. This capabilities test skips MSRs that are
 * kvm-specific. Those are put in the beginning of the list.
 */

#define KVM_SAVE_MSRS_BEGIN	9
static u32 msrs_to_save[] = {
	MSR_KVM_SYSTEM_TIME, MSR_KVM_WALL_CLOCK,
	MSR_KVM_SYSTEM_TIME_NEW, MSR_KVM_WALL_CLOCK_NEW,
	HV_X64_MSR_GUEST_OS_ID, HV_X64_MSR_HYPERCALL,
	HV_X64_MSR_APIC_ASSIST_PAGE, MSR_KVM_ASYNC_PF_EN, MSR_KVM_STEAL_TIME,
	MSR_IA32_SYSENTER_CS, MSR_IA32_SYSENTER_ESP, MSR_IA32_SYSENTER_EIP,
	MSR_STAR,
#ifdef CONFIG_X86_64
	MSR_CSTAR, MSR_KERNEL_GS_BASE, MSR_SYSCALL_MASK, MSR_LSTAR,
#endif
	MSR_IA32_TSC, MSR_IA32_CR_PAT, MSR_VM_HSAVE_PA
};

static unsigned num_msrs_to_save;

static u32 emulated_msrs[] = {
	MSR_IA32_TSCDEADLINE,
	MSR_IA32_MISC_ENABLE,
	MSR_IA32_MCG_STATUS,
	MSR_IA32_MCG_CTL,
};

static int set_efer(struct kvm_vcpu *vcpu, u64 efer)
{
	u64 old_efer = vcpu->arch.efer;

	if (efer & efer_reserved_bits)
		return 1;

	if (is_paging(vcpu)
	    && (vcpu->arch.efer & EFER_LME) != (efer & EFER_LME))
		return 1;

	if (efer & EFER_FFXSR) {
		struct kvm_cpuid_entry2 *feat;

		feat = kvm_find_cpuid_entry(vcpu, 0x80000001, 0);
		if (!feat || !(feat->edx & bit(X86_FEATURE_FXSR_OPT)))
			return 1;
	}

	if (efer & EFER_SVME) {
		struct kvm_cpuid_entry2 *feat;

		feat = kvm_find_cpuid_entry(vcpu, 0x80000001, 0);
		if (!feat || !(feat->ecx & bit(X86_FEATURE_SVM)))
			return 1;
	}

	efer &= ~EFER_LMA;
	efer |= vcpu->arch.efer & EFER_LMA;

	kvm_x86_ops->set_efer(vcpu, efer);

	vcpu->arch.mmu.base_role.nxe = (efer & EFER_NX) && !tdp_enabled;

	/* Update reserved bits */
	if ((efer ^ old_efer) & EFER_NX)
		kvm_mmu_reset_context(vcpu);

	return 0;
}

void kvm_enable_efer_bits(u64 mask)
{
       efer_reserved_bits &= ~mask;
}
EXPORT_SYMBOL_GPL(kvm_enable_efer_bits);


/*
 * Writes msr value into into the appropriate "register".
 * Returns 0 on success, non-0 otherwise.
 * Assumes vcpu_load() was already called.
 */
int kvm_set_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 data)
{
	return kvm_x86_ops->set_msr(vcpu, msr_index, data);
}

/*
 * Adapt set_msr() to msr_io()'s calling convention
 */
static int do_set_msr(struct kvm_vcpu *vcpu, unsigned index, u64 *data)
{
	return kvm_set_msr(vcpu, index, *data);
}

static void kvm_write_wall_clock(struct kvm *kvm, gpa_t wall_clock)
{
	int version;
	int r;
	struct pvclock_wall_clock wc;
	struct timespec boot;

	if (!wall_clock)
		return;

	r = kvm_read_guest(kvm, wall_clock, &version, sizeof(version));
	if (r)
		return;

	if (version & 1)
		++version;  /* first time write, random junk */

	++version;

	kvm_write_guest(kvm, wall_clock, &version, sizeof(version));

	/*
	 * The guest calculates current wall clock time by adding
	 * system time (updated by kvm_guest_time_update below) to the
	 * wall clock specified here.  guest system time equals host
	 * system time for us, thus we must fill in host boot time here.
	 */
	getboottime(&boot);

	wc.sec = boot.tv_sec;
	wc.nsec = boot.tv_nsec;
	wc.version = version;

	kvm_write_guest(kvm, wall_clock, &wc, sizeof(wc));

	version++;
	kvm_write_guest(kvm, wall_clock, &version, sizeof(version));
}

static uint32_t div_frac(uint32_t dividend, uint32_t divisor)
{
	uint32_t quotient, remainder;

	/* Don't try to replace with do_div(), this one calculates
	 * "(dividend << 32) / divisor" */
	__asm__ ( "divl %4"
		  : "=a" (quotient), "=d" (remainder)
		  : "0" (0), "1" (dividend), "r" (divisor) );
	return quotient;
}

static void kvm_get_time_scale(uint32_t scaled_khz, uint32_t base_khz,
			       s8 *pshift, u32 *pmultiplier)
{
	uint64_t scaled64;
	int32_t  shift = 0;
	uint64_t tps64;
	uint32_t tps32;

	tps64 = base_khz * 1000LL;
	scaled64 = scaled_khz * 1000LL;
	while (tps64 > scaled64*2 || tps64 & 0xffffffff00000000ULL) {
		tps64 >>= 1;
		shift--;
	}

	tps32 = (uint32_t)tps64;
	while (tps32 <= scaled64 || scaled64 & 0xffffffff00000000ULL) {
		if (scaled64 & 0xffffffff00000000ULL || tps32 & 0x80000000)
			scaled64 >>= 1;
		else
			tps32 <<= 1;
		shift++;
	}

	*pshift = shift;
	*pmultiplier = div_frac(scaled64, tps32);

	pr_debug("%s: base_khz %u => %u, shift %d, mul %u\n",
		 __func__, base_khz, scaled_khz, shift, *pmultiplier);
}

static inline u64 get_kernel_ns(void)
{
	struct timespec ts;

	WARN_ON(preemptible());
	ktime_get_ts(&ts);
	monotonic_to_bootbased(&ts);
	return timespec_to_ns(&ts);
}

static DEFINE_PER_CPU(unsigned long, cpu_tsc_khz);
unsigned long max_tsc_khz;

static inline int kvm_tsc_changes_freq(void)
{
	int cpu = get_cpu();
	int ret = !boot_cpu_has(X86_FEATURE_CONSTANT_TSC) &&
		  cpufreq_quick_get(cpu) != 0;
	put_cpu();
	return ret;
}

u64 vcpu_tsc_khz(struct kvm_vcpu *vcpu)
{
	if (vcpu->arch.virtual_tsc_khz)
		return vcpu->arch.virtual_tsc_khz;
	else
		return __this_cpu_read(cpu_tsc_khz);
}

static inline u64 nsec_to_cycles(struct kvm_vcpu *vcpu, u64 nsec)
{
	u64 ret;

	WARN_ON(preemptible());
	if (kvm_tsc_changes_freq())
		printk_once(KERN_WARNING
		 "kvm: unreliable cycle conversion on adjustable rate TSC\n");
	ret = nsec * vcpu_tsc_khz(vcpu);
	do_div(ret, USEC_PER_SEC);
	return ret;
}

static void kvm_init_tsc_catchup(struct kvm_vcpu *vcpu, u32 this_tsc_khz)
{
	/* Compute a scale to convert nanoseconds in TSC cycles */
	kvm_get_time_scale(this_tsc_khz, NSEC_PER_SEC / 1000,
			   &vcpu->arch.tsc_catchup_shift,
			   &vcpu->arch.tsc_catchup_mult);
}

static u64 compute_guest_tsc(struct kvm_vcpu *vcpu, s64 kernel_ns)
{
	u64 tsc = pvclock_scale_delta(kernel_ns-vcpu->arch.last_tsc_nsec,
				      vcpu->arch.tsc_catchup_mult,
				      vcpu->arch.tsc_catchup_shift);
	tsc += vcpu->arch.last_tsc_write;
	return tsc;
}

void kvm_write_tsc(struct kvm_vcpu *vcpu, u64 data)
{
	struct kvm *kvm = vcpu->kvm;
	u64 offset, ns, elapsed;
	unsigned long flags;
	s64 sdiff;

	raw_spin_lock_irqsave(&kvm->arch.tsc_write_lock, flags);
	offset = kvm_x86_ops->compute_tsc_offset(vcpu, data);
	ns = get_kernel_ns();
	elapsed = ns - kvm->arch.last_tsc_nsec;
	sdiff = data - kvm->arch.last_tsc_write;
	if (sdiff < 0)
		sdiff = -sdiff;

	/*
	 * Special case: close write to TSC within 5 seconds of
	 * another CPU is interpreted as an attempt to synchronize
	 * The 5 seconds is to accommodate host load / swapping as
	 * well as any reset of TSC during the boot process.
	 *
	 * In that case, for a reliable TSC, we can match TSC offsets,
	 * or make a best guest using elapsed value.
	 */
	if (sdiff < nsec_to_cycles(vcpu, 5ULL * NSEC_PER_SEC) &&
	    elapsed < 5ULL * NSEC_PER_SEC) {
		if (!check_tsc_unstable()) {
			offset = kvm->arch.last_tsc_offset;
			pr_debug("kvm: matched tsc offset for %llu\n", data);
		} else {
			u64 delta = nsec_to_cycles(vcpu, elapsed);
			offset += delta;
			pr_debug("kvm: adjusted tsc offset by %llu\n", delta);
		}
		ns = kvm->arch.last_tsc_nsec;
	}
	kvm->arch.last_tsc_nsec = ns;
	kvm->arch.last_tsc_write = data;
	kvm->arch.last_tsc_offset = offset;
	kvm_x86_ops->write_tsc_offset(vcpu, offset);
	raw_spin_unlock_irqrestore(&kvm->arch.tsc_write_lock, flags);

	/* Reset of TSC must disable overshoot protection below */
	vcpu->arch.hv_clock.tsc_timestamp = 0;
	vcpu->arch.last_tsc_write = data;
	vcpu->arch.last_tsc_nsec = ns;
}
EXPORT_SYMBOL_GPL(kvm_write_tsc);

static int kvm_guest_time_update(struct kvm_vcpu *v)
{
	unsigned long flags;
	struct kvm_vcpu_arch *vcpu = &v->arch;
	void *shared_kaddr;
	unsigned long this_tsc_khz;
	s64 kernel_ns, max_kernel_ns;
	u64 tsc_timestamp;

	/* Keep irq disabled to prevent changes to the clock */
	local_irq_save(flags);
	tsc_timestamp = kvm_x86_ops->read_l1_tsc(v);
	kernel_ns = get_kernel_ns();
	this_tsc_khz = vcpu_tsc_khz(v);
	if (unlikely(this_tsc_khz == 0)) {
		local_irq_restore(flags);
		kvm_make_request(KVM_REQ_CLOCK_UPDATE, v);
		return 1;
	}

	/*
	 * We may have to catch up the TSC to match elapsed wall clock
	 * time for two reasons, even if kvmclock is used.
	 *   1) CPU could have been running below the maximum TSC rate
	 *   2) Broken TSC compensation resets the base at each VCPU
	 *      entry to avoid unknown leaps of TSC even when running
	 *      again on the same CPU.  This may cause apparent elapsed
	 *      time to disappear, and the guest to stand still or run
	 *	very slowly.
	 */
	if (vcpu->tsc_catchup) {
		u64 tsc = compute_guest_tsc(v, kernel_ns);
		if (tsc > tsc_timestamp) {
			kvm_x86_ops->adjust_tsc_offset(v, tsc - tsc_timestamp);
			tsc_timestamp = tsc;
		}
	}

	local_irq_restore(flags);

	if (!vcpu->time_page)
		return 0;

	/*
	 * Time as measured by the TSC may go backwards when resetting the base
	 * tsc_timestamp.  The reason for this is that the TSC resolution is
	 * higher than the resolution of the other clock scales.  Thus, many
	 * possible measurments of the TSC correspond to one measurement of any
	 * other clock, and so a spread of values is possible.  This is not a
	 * problem for the computation of the nanosecond clock; with TSC rates
	 * around 1GHZ, there can only be a few cycles which correspond to one
	 * nanosecond value, and any path through this code will inevitably
	 * take longer than that.  However, with the kernel_ns value itself,
	 * the precision may be much lower, down to HZ granularity.  If the
	 * first sampling of TSC against kernel_ns ends in the low part of the
	 * range, and the second in the high end of the range, we can get:
	 *
	 * (TSC - offset_low) * S + kns_old > (TSC - offset_high) * S + kns_new
	 *
	 * As the sampling errors potentially range in the thousands of cycles,
	 * it is possible such a time value has already been observed by the
	 * guest.  To protect against this, we must compute the system time as
	 * observed by the guest and ensure the new system time is greater.
	 */
	max_kernel_ns = 0;
	if (vcpu->hv_clock.tsc_timestamp && vcpu->last_guest_tsc) {
		max_kernel_ns = vcpu->last_guest_tsc -
				vcpu->hv_clock.tsc_timestamp;
		max_kernel_ns = pvclock_scale_delta(max_kernel_ns,
				    vcpu->hv_clock.tsc_to_system_mul,
				    vcpu->hv_clock.tsc_shift);
		max_kernel_ns += vcpu->last_kernel_ns;
	}

	if (unlikely(vcpu->hw_tsc_khz != this_tsc_khz)) {
		kvm_get_time_scale(NSEC_PER_SEC / 1000, this_tsc_khz,
				   &vcpu->hv_clock.tsc_shift,
				   &vcpu->hv_clock.tsc_to_system_mul);
		vcpu->hw_tsc_khz = this_tsc_khz;
	}

	if (max_kernel_ns > kernel_ns)
		kernel_ns = max_kernel_ns;

	/* With all the info we got, fill in the values */
	vcpu->hv_clock.tsc_timestamp = tsc_timestamp;
	vcpu->hv_clock.system_time = kernel_ns + v->kvm->arch.kvmclock_offset;
	vcpu->last_kernel_ns = kernel_ns;
	vcpu->last_guest_tsc = tsc_timestamp;
	vcpu->hv_clock.flags = 0;

	/*
	 * The interface expects us to write an even number signaling that the
	 * update is finished. Since the guest won't see the intermediate
	 * state, we just increase by 2 at the end.
	 */
	vcpu->hv_clock.version += 2;

	shared_kaddr = kmap_atomic(vcpu->time_page, KM_USER0);

	memcpy(shared_kaddr + vcpu->time_offset, &vcpu->hv_clock,
	       sizeof(vcpu->hv_clock));

	kunmap_atomic(shared_kaddr, KM_USER0);

	mark_page_dirty(v->kvm, vcpu->time >> PAGE_SHIFT);
	return 0;
}

static bool msr_mtrr_valid(unsigned msr)
{
	switch (msr) {
	case 0x200 ... 0x200 + 2 * KVM_NR_VAR_MTRR - 1:
	case MSR_MTRRfix64K_00000:
	case MSR_MTRRfix16K_80000:
	case MSR_MTRRfix16K_A0000:
	case MSR_MTRRfix4K_C0000:
	case MSR_MTRRfix4K_C8000:
	case MSR_MTRRfix4K_D0000:
	case MSR_MTRRfix4K_D8000:
	case MSR_MTRRfix4K_E0000:
	case MSR_MTRRfix4K_E8000:
	case MSR_MTRRfix4K_F0000:
	case MSR_MTRRfix4K_F8000:
	case MSR_MTRRdefType:
	case MSR_IA32_CR_PAT:
		return true;
	case 0x2f8:
		return true;
	}
	return false;
}

static bool valid_pat_type(unsigned t)
{
	return t < 8 && (1 << t) & 0xf3; /* 0, 1, 4, 5, 6, 7 */
}

static bool valid_mtrr_type(unsigned t)
{
	return t < 8 && (1 << t) & 0x73; /* 0, 1, 4, 5, 6 */
}

static bool mtrr_valid(struct kvm_vcpu *vcpu, u32 msr, u64 data)
{
	int i;

	if (!msr_mtrr_valid(msr))
		return false;

	if (msr == MSR_IA32_CR_PAT) {
		for (i = 0; i < 8; i++)
			if (!valid_pat_type((data >> (i * 8)) & 0xff))
				return false;
		return true;
	} else if (msr == MSR_MTRRdefType) {
		if (data & ~0xcff)
			return false;
		return valid_mtrr_type(data & 0xff);
	} else if (msr >= MSR_MTRRfix64K_00000 && msr <= MSR_MTRRfix4K_F8000) {
		for (i = 0; i < 8 ; i++)
			if (!valid_mtrr_type((data >> (i * 8)) & 0xff))
				return false;
		return true;
	}

	/* variable MTRRs */
	return valid_mtrr_type(data & 0xff);
}

static int set_msr_mtrr(struct kvm_vcpu *vcpu, u32 msr, u64 data)
{
	u64 *p = (u64 *)&vcpu->arch.mtrr_state.fixed_ranges;

	if (!mtrr_valid(vcpu, msr, data))
		return 1;

	if (msr == MSR_MTRRdefType) {
		vcpu->arch.mtrr_state.def_type = data;
		vcpu->arch.mtrr_state.enabled = (data & 0xc00) >> 10;
	} else if (msr == MSR_MTRRfix64K_00000)
		p[0] = data;
	else if (msr == MSR_MTRRfix16K_80000 || msr == MSR_MTRRfix16K_A0000)
		p[1 + msr - MSR_MTRRfix16K_80000] = data;
	else if (msr >= MSR_MTRRfix4K_C0000 && msr <= MSR_MTRRfix4K_F8000)
		p[3 + msr - MSR_MTRRfix4K_C0000] = data;
	else if (msr == MSR_IA32_CR_PAT)
		vcpu->arch.pat = data;
	else {	/* Variable MTRRs */
		int idx, is_mtrr_mask;
		u64 *pt;

		idx = (msr - 0x200) / 2;
		is_mtrr_mask = msr - 0x200 - 2 * idx;
		if (!is_mtrr_mask)
			pt =
			  (u64 *)&vcpu->arch.mtrr_state.var_ranges[idx].base_lo;
		else
			pt =
			  (u64 *)&vcpu->arch.mtrr_state.var_ranges[idx].mask_lo;
		*pt = data;
	}

	kvm_mmu_reset_context(vcpu);
	return 0;
}

static int set_msr_mce(struct kvm_vcpu *vcpu, u32 msr, u64 data)
{
	u64 mcg_cap = vcpu->arch.mcg_cap;
	unsigned bank_num = mcg_cap & 0xff;

	switch (msr) {
	case MSR_IA32_MCG_STATUS:
		vcpu->arch.mcg_status = data;
		break;
	case MSR_IA32_MCG_CTL:
		if (!(mcg_cap & MCG_CTL_P))
			return 1;
		if (data != 0 && data != ~(u64)0)
			return -1;
		vcpu->arch.mcg_ctl = data;
		break;
	default:
		if (msr >= MSR_IA32_MC0_CTL &&
		    msr < MSR_IA32_MC0_CTL + 4 * bank_num) {
			u32 offset = msr - MSR_IA32_MC0_CTL;
			/* only 0 or all 1s can be written to IA32_MCi_CTL
			 * some Linux kernels though clear bit 10 in bank 4 to
			 * workaround a BIOS/GART TBL issue on AMD K8s, ignore
			 * this to avoid an uncatched #GP in the guest
			 */
			if ((offset & 0x3) == 0 &&
			    data != 0 && (data | (1 << 10)) != ~(u64)0)
				return -1;
			vcpu->arch.mce_banks[offset] = data;
			break;
		}
		return 1;
	}
	return 0;
}

static int xen_hvm_config(struct kvm_vcpu *vcpu, u64 data)
{