From 2e5aa86609ec1cf37bcc204fd7ba6c24c2f49fec Mon Sep 17 00:00:00 2001
From: Paul Moore <pmoore@redhat.com>
Date: Tue, 23 Jul 2013 17:38:38 -0400
Subject: lsm: split the xfrm_state_alloc_security() hook implementation

The xfrm_state_alloc_security() LSM hook implementation is really a
multiplexed hook with two different behaviors depending on the
arguments passed to it by the caller.  This patch splits the LSM hook
implementation into two new hook implementations, which match the
LSM hooks in the rest of the kernel:

 * xfrm_state_alloc
 * xfrm_state_alloc_acquire

Also included in this patch are the necessary changes to the SELinux
code; no other LSMs are affected.

Signed-off-by: Paul Moore <pmoore@redhat.com>
Signed-off-by: Eric Paris <eparis@redhat.com>
---
 security/capability.c           |  15 ++-
 security/security.c             |  13 +--
 security/selinux/hooks.c        |   3 +-
 security/selinux/include/xfrm.h |   4 +-
 security/selinux/xfrm.c         | 199 ++++++++++++++++++----------------------
 5 files changed, 110 insertions(+), 124 deletions(-)

(limited to 'security')

diff --git a/security/capability.c b/security/capability.c
index 1728d4e375db..67afc679719a 100644
--- a/security/capability.c
+++ b/security/capability.c
@@ -767,9 +767,15 @@ static int cap_xfrm_policy_delete_security(struct xfrm_sec_ctx *ctx)
 	return 0;
 }
 
-static int cap_xfrm_state_alloc_security(struct xfrm_state *x,
-					 struct xfrm_user_sec_ctx *sec_ctx,
-					 u32 secid)
+static int cap_xfrm_state_alloc(struct xfrm_state *x,
+				struct xfrm_user_sec_ctx *sec_ctx)
+{
+	return 0;
+}
+
+static int cap_xfrm_state_alloc_acquire(struct xfrm_state *x,
+					struct xfrm_sec_ctx *polsec,
+					u32 secid)
 {
 	return 0;
 }
@@ -1084,7 +1090,8 @@ void __init security_fixup_ops(struct security_operations *ops)
 	set_to_cap_if_null(ops, xfrm_policy_clone_security);
 	set_to_cap_if_null(ops, xfrm_policy_free_security);
 	set_to_cap_if_null(ops, xfrm_policy_delete_security);
-	set_to_cap_if_null(ops, xfrm_state_alloc_security);
+	set_to_cap_if_null(ops, xfrm_state_alloc);
+	set_to_cap_if_null(ops, xfrm_state_alloc_acquire);
 	set_to_cap_if_null(ops, xfrm_state_free_security);
 	set_to_cap_if_null(ops, xfrm_state_delete_security);
 	set_to_cap_if_null(ops, xfrm_policy_lookup);
diff --git a/security/security.c b/security/security.c
index a3dce87d1aef..57e25c962968 100644
--- a/security/security.c
+++ b/security/security.c
@@ -1322,22 +1322,17 @@ int security_xfrm_policy_delete(struct xfrm_sec_ctx *ctx)
 	return security_ops->xfrm_policy_delete_security(ctx);
 }
 
-int security_xfrm_state_alloc(struct xfrm_state *x, struct xfrm_user_sec_ctx *sec_ctx)
+int security_xfrm_state_alloc(struct xfrm_state *x,
+			      struct xfrm_user_sec_ctx *sec_ctx)
 {
-	return security_ops->xfrm_state_alloc_security(x, sec_ctx, 0);
+	return security_ops->xfrm_state_alloc(x, sec_ctx);
 }
 EXPORT_SYMBOL(security_xfrm_state_alloc);
 
 int security_xfrm_state_alloc_acquire(struct xfrm_state *x,
 				      struct xfrm_sec_ctx *polsec, u32 secid)
 {
-	if (!polsec)
-		return 0;
-	/*
-	 * We want the context to be taken from secid which is usually
-	 * from the sock.
-	 */
-	return security_ops->xfrm_state_alloc_security(x, NULL, secid);
+	return security_ops->xfrm_state_alloc_acquire(x, polsec, secid);
 }
 
 int security_xfrm_state_delete(struct xfrm_state *x)
diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c
index 5c6f2cd2d095..d3555bdf66af 100644
--- a/security/selinux/hooks.c
+++ b/security/selinux/hooks.c
@@ -5708,7 +5708,8 @@ static struct security_operations selinux_ops = {
 	.xfrm_policy_clone_security =	selinux_xfrm_policy_clone,
 	.xfrm_policy_free_security =	selinux_xfrm_policy_free,
 	.xfrm_policy_delete_security =	selinux_xfrm_policy_delete,
-	.xfrm_state_alloc_security =	selinux_xfrm_state_alloc,
+	.xfrm_state_alloc =		selinux_xfrm_state_alloc,
+	.xfrm_state_alloc_acquire =	selinux_xfrm_state_alloc_acquire,
 	.xfrm_state_free_security =	selinux_xfrm_state_free,
 	.xfrm_state_delete_security =	selinux_xfrm_state_delete,
 	.xfrm_policy_lookup =		selinux_xfrm_policy_lookup,
diff --git a/security/selinux/include/xfrm.h b/security/selinux/include/xfrm.h
index 65f67cb0aefb..f2a2314aac1a 100644
--- a/security/selinux/include/xfrm.h
+++ b/security/selinux/include/xfrm.h
@@ -16,7 +16,9 @@ int selinux_xfrm_policy_clone(struct xfrm_sec_ctx *old_ctx,
 void selinux_xfrm_policy_free(struct xfrm_sec_ctx *ctx);
 int selinux_xfrm_policy_delete(struct xfrm_sec_ctx *ctx);
 int selinux_xfrm_state_alloc(struct xfrm_state *x,
-	struct xfrm_user_sec_ctx *sec_ctx, u32 secid);
+			     struct xfrm_user_sec_ctx *uctx);
+int selinux_xfrm_state_alloc_acquire(struct xfrm_state *x,
+				     struct xfrm_sec_ctx *polsec, u32 secid);
 void selinux_xfrm_state_free(struct xfrm_state *x);
 int selinux_xfrm_state_delete(struct xfrm_state *x);
 int selinux_xfrm_policy_lookup(struct xfrm_sec_ctx *ctx, u32 fl_secid, u8 dir);
diff --git a/security/selinux/xfrm.c b/security/selinux/xfrm.c
index d03081886214..07ae0c06dfc3 100644
--- a/security/selinux/xfrm.c
+++ b/security/selinux/xfrm.c
@@ -73,6 +73,54 @@ static inline int selinux_authorizable_xfrm(struct xfrm_state *x)
 	return selinux_authorizable_ctx(x->security);
 }
 
+/*
+ * Allocates a xfrm_sec_state and populates it using the supplied security
+ * xfrm_user_sec_ctx context.
+ */
+static int selinux_xfrm_alloc_user(struct xfrm_sec_ctx **ctxp,
+				   struct xfrm_user_sec_ctx *uctx)
+{
+	int rc;
+	const struct task_security_struct *tsec = current_security();
+	struct xfrm_sec_ctx *ctx = NULL;
+	u32 str_len;
+
+	if (ctxp == NULL || uctx == NULL ||
+	    uctx->ctx_doi != XFRM_SC_DOI_LSM ||
+	    uctx->ctx_alg != XFRM_SC_ALG_SELINUX)
+		return -EINVAL;
+
+	str_len = uctx->ctx_len;
+	if (str_len >= PAGE_SIZE)
+		return -ENOMEM;
+
+	ctx = kmalloc(sizeof(*ctx) + str_len + 1, GFP_KERNEL);
+	if (!ctx)
+		return -ENOMEM;
+
+	ctx->ctx_doi = XFRM_SC_DOI_LSM;
+	ctx->ctx_alg = XFRM_SC_ALG_SELINUX;
+	ctx->ctx_len = str_len;
+	memcpy(ctx->ctx_str, &uctx[1], str_len);
+	ctx->ctx_str[str_len] = '\0';
+	rc = security_context_to_sid(ctx->ctx_str, str_len, &ctx->ctx_sid);
+	if (rc)
+		goto err;
+
+	rc = avc_has_perm(tsec->sid, ctx->ctx_sid,
+			  SECCLASS_ASSOCIATION, ASSOCIATION__SETCONTEXT, NULL);
+	if (rc)
+		goto err;
+
+	*ctxp = ctx;
+	atomic_inc(&selinux_xfrm_refcount);
+	return 0;
+
+err:
+	kfree(ctx);
+	return rc;
+}
+
 /*
  * LSM hook implementation that authorizes that a flow can use
  * a xfrm policy rule.
@@ -190,96 +238,6 @@ int selinux_xfrm_decode_session(struct sk_buff *skb, u32 *sid, int ckall)
 	return 0;
 }
 
-/*
- * Security blob allocation for xfrm_policy and xfrm_state
- * CTX does not have a meaningful value on input
- */
-static int selinux_xfrm_sec_ctx_alloc(struct xfrm_sec_ctx **ctxp,
-	struct xfrm_user_sec_ctx *uctx, u32 sid)
-{
-	int rc = 0;
-	const struct task_security_struct *tsec = current_security();
-	struct xfrm_sec_ctx *ctx = NULL;
-	char *ctx_str = NULL;
-	u32 str_len;
-
-	BUG_ON(uctx && sid);
-
-	if (!uctx)
-		goto not_from_user;
-
-	if (uctx->ctx_alg != XFRM_SC_ALG_SELINUX)
-		return -EINVAL;
-
-	str_len = uctx->ctx_len;
-	if (str_len >= PAGE_SIZE)
-		return -ENOMEM;
-
-	*ctxp = ctx = kmalloc(sizeof(*ctx) +
-			      str_len + 1,
-			      GFP_KERNEL);
-
-	if (!ctx)
-		return -ENOMEM;
-
-	ctx->ctx_doi = uctx->ctx_doi;
-	ctx->ctx_len = str_len;
-	ctx->ctx_alg = uctx->ctx_alg;
-
-	memcpy(ctx->ctx_str,
-	       uctx+1,
-	       str_len);
-	ctx->ctx_str[str_len] = 0;
-	rc = security_context_to_sid(ctx->ctx_str,
-				     str_len,
-				     &ctx->ctx_sid);
-
-	if (rc)
-		goto out;
-
-	/*
-	 * Does the subject have permission to set security context?
-	 */
-	rc = avc_has_perm(tsec->sid, ctx->ctx_sid,
-			  SECCLASS_ASSOCIATION,
-			  ASSOCIATION__SETCONTEXT, NULL);
-	if (rc)
-		goto out;
-
-	return rc;
-
-not_from_user:
-	rc = security_sid_to_context(sid, &ctx_str, &str_len);
-	if (rc)
-		goto out;
-
-	*ctxp = ctx = kmalloc(sizeof(*ctx) +
-			      str_len,
-			      GFP_ATOMIC);
-
-	if (!ctx) {
-		rc = -ENOMEM;
-		goto out;
-	}
-
-	ctx->ctx_doi = XFRM_SC_DOI_LSM;
-	ctx->ctx_alg = XFRM_SC_ALG_SELINUX;
-	ctx->ctx_sid = sid;
-	ctx->ctx_len = str_len;
-	memcpy(ctx->ctx_str,
-	       ctx_str,
-	       str_len);
-
-	goto out2;
-
-out:
-	*ctxp = NULL;
-	kfree(ctx);
-out2:
-	kfree(ctx_str);
-	return rc;
-}
-
 /*
  * LSM hook implementation that allocs and transfers uctx spec to
  * xfrm_policy.
@@ -287,15 +245,7 @@ out2:
 int selinux_xfrm_policy_alloc(struct xfrm_sec_ctx **ctxp,
 			      struct xfrm_user_sec_ctx *uctx)
 {
-	int err;
-
-	BUG_ON(!uctx);
-
-	err = selinux_xfrm_sec_ctx_alloc(ctxp, uctx, 0);
-	if (err == 0)
-		atomic_inc(&selinux_xfrm_refcount);
-
-	return err;
+	return selinux_xfrm_alloc_user(ctxp, uctx);
 }
 
 
@@ -347,20 +297,51 @@ int selinux_xfrm_policy_delete(struct xfrm_sec_ctx *ctx)
 }
 
 /*
- * LSM hook implementation that allocs and transfers sec_ctx spec to
- * xfrm_state.
+ * LSM hook implementation that allocates a xfrm_sec_state, populates it using
+ * the supplied security context, and assigns it to the xfrm_state.
+ */
+int selinux_xfrm_state_alloc(struct xfrm_state *x,
+			     struct xfrm_user_sec_ctx *uctx)
+{
+	return selinux_xfrm_alloc_user(&x->security, uctx);
+}
+
+/*
+ * LSM hook implementation that allocates a xfrm_sec_state and populates based
+ * on a secid.
  */
-int selinux_xfrm_state_alloc(struct xfrm_state *x, struct xfrm_user_sec_ctx *uctx,
-		u32 secid)
+int selinux_xfrm_state_alloc_acquire(struct xfrm_state *x,
+				     struct xfrm_sec_ctx *polsec, u32 secid)
 {
-	int err;
+	int rc;
+	struct xfrm_sec_ctx *ctx;
+	char *ctx_str = NULL;
+	int str_len;
 
-	BUG_ON(!x);
+	if (!polsec)
+		return 0;
 
-	err = selinux_xfrm_sec_ctx_alloc(&x->security, uctx, secid);
-	if (err == 0)
-		atomic_inc(&selinux_xfrm_refcount);
-	return err;
+	if (secid == 0)
+		return -EINVAL;
+
+	rc = security_sid_to_context(secid, &ctx_str, &str_len);
+	if (rc)
+		return rc;
+
+	ctx = kmalloc(sizeof(*ctx) + str_len, GFP_ATOMIC);
+	if (!ctx)
+		return -ENOMEM;
+
+	ctx->ctx_doi = XFRM_SC_DOI_LSM;
+	ctx->ctx_alg = XFRM_SC_ALG_SELINUX;
+	ctx->ctx_sid = secid;
+	ctx->ctx_len = str_len;
+	memcpy(ctx->ctx_str, ctx_str, str_len);
+	kfree(ctx_str);
+
+	x->security = ctx;
+	atomic_inc(&selinux_xfrm_refcount);
+	return 0;
 }
 
 /*
-- 
cgit v1.2.3


From ccf17cc4b81537c29f0d5950b38b5548b6cb5858 Mon Sep 17 00:00:00 2001
From: Paul Moore <pmoore@redhat.com>
Date: Tue, 23 Jul 2013 17:38:39 -0400
Subject: selinux: cleanup and consolidate the XFRM alloc/clone/delete/free
 code

The SELinux labeled IPsec code state management functions have been
long neglected and could use some cleanup and consolidation.

Signed-off-by: Paul Moore <pmoore@redhat.com>
Signed-off-by: Eric Paris <eparis@redhat.com>
---
 security/selinux/xfrm.c | 71 ++++++++++++++++++++++++++++---------------------
 1 file changed, 40 insertions(+), 31 deletions(-)

(limited to 'security')

diff --git a/security/selinux/xfrm.c b/security/selinux/xfrm.c
index 07ae0c06dfc3..f8d71262b45d 100644
--- a/security/selinux/xfrm.c
+++ b/security/selinux/xfrm.c
@@ -121,6 +121,33 @@ err:
 	return rc;
 }
 
+/*
+ * Free the xfrm_sec_ctx structure.
+ */
+static void selinux_xfrm_free(struct xfrm_sec_ctx *ctx)
+{
+	if (!ctx)
+		return;
+
+	atomic_dec(&selinux_xfrm_refcount);
+	kfree(ctx);
+}
+
+/*
+ * Authorize the deletion of a labeled SA or policy rule.
+ */
+static int selinux_xfrm_delete(struct xfrm_sec_ctx *ctx)
+{
+	const struct task_security_struct *tsec = current_security();
+
+	if (!ctx)
+		return 0;
+
+	return avc_has_perm(tsec->sid, ctx->ctx_sid,
+			    SECCLASS_ASSOCIATION, ASSOCIATION__SETCONTEXT,
+			    NULL);
+}
+
 /*
  * LSM hook implementation that authorizes that a flow can use
  * a xfrm policy rule.
@@ -258,17 +285,16 @@ int selinux_xfrm_policy_clone(struct xfrm_sec_ctx *old_ctx,
 {
 	struct xfrm_sec_ctx *new_ctx;
 
-	if (old_ctx) {
-		new_ctx = kmalloc(sizeof(*old_ctx) + old_ctx->ctx_len,
-				  GFP_ATOMIC);
-		if (!new_ctx)
-			return -ENOMEM;
+	if (!old_ctx)
+		return 0;
+
+	new_ctx = kmalloc(sizeof(*old_ctx) + old_ctx->ctx_len, GFP_ATOMIC);
+	if (!new_ctx)
+		return -ENOMEM;
+	memcpy(new_ctx, old_ctx, sizeof(*old_ctx) + old_ctx->ctx_len);
+	atomic_inc(&selinux_xfrm_refcount);
+	*new_ctxp = new_ctx;
 
-		memcpy(new_ctx, old_ctx, sizeof(*new_ctx));
-		memcpy(new_ctx->ctx_str, old_ctx->ctx_str, new_ctx->ctx_len);
-		atomic_inc(&selinux_xfrm_refcount);
-		*new_ctxp = new_ctx;
-	}
 	return 0;
 }
 
@@ -277,8 +303,7 @@ int selinux_xfrm_policy_clone(struct xfrm_sec_ctx *old_ctx,
  */
 void selinux_xfrm_policy_free(struct xfrm_sec_ctx *ctx)
 {
-	atomic_dec(&selinux_xfrm_refcount);
-	kfree(ctx);
+	selinux_xfrm_free(ctx);
 }
 
 /*
@@ -286,14 +311,7 @@ void selinux_xfrm_policy_free(struct xfrm_sec_ctx *ctx)
  */
 int selinux_xfrm_policy_delete(struct xfrm_sec_ctx *ctx)
 {
-	const struct task_security_struct *tsec = current_security();
-
-	if (!ctx)
-		return 0;
-
-	return avc_has_perm(tsec->sid, ctx->ctx_sid,
-			    SECCLASS_ASSOCIATION, ASSOCIATION__SETCONTEXT,
-			    NULL);
+	return selinux_xfrm_delete(ctx);
 }
 
 /*
@@ -349,8 +367,7 @@ int selinux_xfrm_state_alloc_acquire(struct xfrm_state *x,
  */
 void selinux_xfrm_state_free(struct xfrm_state *x)
 {
-	atomic_dec(&selinux_xfrm_refcount);
-	kfree(x->security);
+	selinux_xfrm_free(x->security);
 }
 
  /*
@@ -358,15 +375,7 @@ void selinux_xfrm_state_free(struct xfrm_state *x)
   */
 int selinux_xfrm_state_delete(struct xfrm_state *x)
 {
-	const struct task_security_struct *tsec = current_security();
-	struct xfrm_sec_ctx *ctx = x->security;
-
-	if (!ctx)
-		return 0;
-
-	return avc_has_perm(tsec->sid, ctx->ctx_sid,
-			    SECCLASS_ASSOCIATION, ASSOCIATION__SETCONTEXT,
-			    NULL);
+	return selinux_xfrm_delete(x->security);
 }
 
 /*
-- 
cgit v1.2.3


From 96484348ad712aed2c6ad7229b848bc1bf6165a8 Mon Sep 17 00:00:00 2001
From: Paul Moore <pmoore@redhat.com>
Date: Tue, 23 Jul 2013 17:38:39 -0400
Subject: selinux: cleanup selinux_xfrm_policy_lookup() and
 selinux_xfrm_state_pol_flow_match()

Do some basic simplification and comment reformatting.

Signed-off-by: Paul Moore <pmoore@redhat.com>
Signed-off-by: Eric Paris <eparis@redhat.com>
---
 security/selinux/xfrm.c | 54 +++++++++++++++++--------------------------------
 1 file changed, 18 insertions(+), 36 deletions(-)

(limited to 'security')

diff --git a/security/selinux/xfrm.c b/security/selinux/xfrm.c
index f8d71262b45d..4a7ba4ac487e 100644
--- a/security/selinux/xfrm.c
+++ b/security/selinux/xfrm.c
@@ -155,42 +155,30 @@ static int selinux_xfrm_delete(struct xfrm_sec_ctx *ctx)
 int selinux_xfrm_policy_lookup(struct xfrm_sec_ctx *ctx, u32 fl_secid, u8 dir)
 {
 	int rc;
-	u32 sel_sid;
 
-	/* Context sid is either set to label or ANY_ASSOC */
-	if (ctx) {
-		if (!selinux_authorizable_ctx(ctx))
-			return -EINVAL;
-
-		sel_sid = ctx->ctx_sid;
-	} else
-		/*
-		 * All flows should be treated as polmatch'ing an
-		 * otherwise applicable "non-labeled" policy. This
-		 * would prevent inadvertent "leaks".
-		 */
+	/* All flows should be treated as polmatch'ing an otherwise applicable
+	 * "non-labeled" policy. This would prevent inadvertent "leaks". */
+	if (!ctx)
 		return 0;
 
-	rc = avc_has_perm(fl_secid, sel_sid, SECCLASS_ASSOCIATION,
-			  ASSOCIATION__POLMATCH,
-			  NULL);
-
-	if (rc == -EACCES)
-		return -ESRCH;
+	/* Context sid is either set to label or ANY_ASSOC */
+	if (!selinux_authorizable_ctx(ctx))
+		return -EINVAL;
 
-	return rc;
+	rc = avc_has_perm(fl_secid, ctx->ctx_sid,
+			  SECCLASS_ASSOCIATION, ASSOCIATION__POLMATCH, NULL);
+	return (rc == -EACCES ? -ESRCH : rc);
 }
 
 /*
  * LSM hook implementation that authorizes that a state matches
  * the given policy, flow combo.
  */
-
-int selinux_xfrm_state_pol_flow_match(struct xfrm_state *x, struct xfrm_policy *xp,
-			const struct flowi *fl)
+int selinux_xfrm_state_pol_flow_match(struct xfrm_state *x,
+				      struct xfrm_policy *xp,
+				      const struct flowi *fl)
 {
 	u32 state_sid;
-	int rc;
 
 	if (!xp->security)
 		if (x->security)
@@ -213,18 +201,12 @@ int selinux_xfrm_state_pol_flow_match(struct xfrm_state *x, struct xfrm_policy *
 	if (fl->flowi_secid != state_sid)
 		return 0;
 
-	rc = avc_has_perm(fl->flowi_secid, state_sid, SECCLASS_ASSOCIATION,
-			  ASSOCIATION__SENDTO,
-			  NULL)? 0:1;
-
-	/*
-	 * We don't need a separate SA Vs. policy polmatch check
-	 * since the SA is now of the same label as the flow and
-	 * a flow Vs. policy polmatch check had already happened
-	 * in selinux_xfrm_policy_lookup() above.
-	 */
-
-	return rc;
+	/* We don't need a separate SA Vs. policy polmatch check since the SA
+	 * is now of the same label as the flow and a flow Vs. policy polmatch
+	 * check had already happened in selinux_xfrm_policy_lookup() above. */
+	return (avc_has_perm(fl->flowi_secid, state_sid,
+			    SECCLASS_ASSOCIATION, ASSOCIATION__SENDTO,
+			    NULL) ? 0 : 1);
 }
 
 /*
-- 
cgit v1.2.3


From eef9b41622f2f09e824fb4e7356b42bddada6623 Mon Sep 17 00:00:00 2001
From: Paul Moore <pmoore@redhat.com>
Date: Tue, 23 Jul 2013 17:38:39 -0400
Subject: selinux: cleanup selinux_xfrm_sock_rcv_skb() and
 selinux_xfrm_postroute_last()

Some basic simplification and comment reformatting.

Signed-off-by: Paul Moore <pmoore@redhat.com>
Signed-off-by: Eric Paris <eparis@redhat.com>
---
 security/selinux/include/xfrm.h | 17 +++++----
 security/selinux/xfrm.c         | 85 ++++++++++++++++-------------------------
 2 files changed, 42 insertions(+), 60 deletions(-)

(limited to 'security')

diff --git a/security/selinux/include/xfrm.h b/security/selinux/include/xfrm.h
index f2a2314aac1a..b463f210f1af 100644
--- a/security/selinux/include/xfrm.h
+++ b/security/selinux/include/xfrm.h
@@ -44,10 +44,10 @@ static inline int selinux_xfrm_enabled(void)
 	return (atomic_read(&selinux_xfrm_refcount) > 0);
 }
 
-int selinux_xfrm_sock_rcv_skb(u32 sid, struct sk_buff *skb,
-			struct common_audit_data *ad);
-int selinux_xfrm_postroute_last(u32 isec_sid, struct sk_buff *skb,
-			struct common_audit_data *ad, u8 proto);
+int selinux_xfrm_sock_rcv_skb(u32 sk_sid, struct sk_buff *skb,
+			      struct common_audit_data *ad);
+int selinux_xfrm_postroute_last(u32 sk_sid, struct sk_buff *skb,
+				struct common_audit_data *ad, u8 proto);
 int selinux_xfrm_decode_session(struct sk_buff *skb, u32 *sid, int ckall);
 
 static inline void selinux_xfrm_notify_policyload(void)
@@ -61,14 +61,15 @@ static inline int selinux_xfrm_enabled(void)
 	return 0;
 }
 
-static inline int selinux_xfrm_sock_rcv_skb(u32 isec_sid, struct sk_buff *skb,
-			struct common_audit_data *ad)
+static inline int selinux_xfrm_sock_rcv_skb(u32 sk_sid, struct sk_buff *skb,
+					    struct common_audit_data *ad)
 {
 	return 0;
 }
 
-static inline int selinux_xfrm_postroute_last(u32 isec_sid, struct sk_buff *skb,
-			struct common_audit_data *ad, u8 proto)
+static inline int selinux_xfrm_postroute_last(u32 sk_sid, struct sk_buff *skb,
+					      struct common_audit_data *ad,
+					      u8 proto)
 {
 	return 0;
 }
diff --git a/security/selinux/xfrm.c b/security/selinux/xfrm.c
index 4a7ba4ac487e..1f6c6e619e98 100644
--- a/security/selinux/xfrm.c
+++ b/security/selinux/xfrm.c
@@ -367,14 +367,12 @@ int selinux_xfrm_state_delete(struct xfrm_state *x)
  * we need to check for unlabelled access since this may not have
  * gone thru the IPSec process.
  */
-int selinux_xfrm_sock_rcv_skb(u32 isec_sid, struct sk_buff *skb,
-				struct common_audit_data *ad)
+int selinux_xfrm_sock_rcv_skb(u32 sk_sid, struct sk_buff *skb,
+			      struct common_audit_data *ad)
 {
-	int i, rc = 0;
-	struct sec_path *sp;
-	u32 sel_sid = SECINITSID_UNLABELED;
-
-	sp = skb->sp;
+	int i;
+	struct sec_path *sp = skb->sp;
+	u32 peer_sid = SECINITSID_UNLABELED;
 
 	if (sp) {
 		for (i = 0; i < sp->len; i++) {
@@ -382,23 +380,17 @@ int selinux_xfrm_sock_rcv_skb(u32 isec_sid, struct sk_buff *skb,
 
 			if (x && selinux_authorizable_xfrm(x)) {
 				struct xfrm_sec_ctx *ctx = x->security;
-				sel_sid = ctx->ctx_sid;
+				peer_sid = ctx->ctx_sid;
 				break;
 			}
 		}
 	}
 
-	/*
-	 * This check even when there's no association involved is
-	 * intended, according to Trent Jaeger, to make sure a
-	 * process can't engage in non-ipsec communication unless
-	 * explicitly allowed by policy.
-	 */
-
-	rc = avc_has_perm(isec_sid, sel_sid, SECCLASS_ASSOCIATION,
-			  ASSOCIATION__RECVFROM, ad);
-
-	return rc;
+	/* This check even when there's no association involved is intended,
+	 * according to Trent Jaeger, to make sure a process can't engage in
+	 * non-IPsec communication unless explicitly allowed by policy. */
+	return avc_has_perm(sk_sid, peer_sid,
+			    SECCLASS_ASSOCIATION, ASSOCIATION__RECVFROM, ad);
 }
 
 /*
@@ -408,49 +400,38 @@ int selinux_xfrm_sock_rcv_skb(u32 isec_sid, struct sk_buff *skb,
  * If we do have a authorizable security association, then it has already been
  * checked in the selinux_xfrm_state_pol_flow_match hook above.
  */
-int selinux_xfrm_postroute_last(u32 isec_sid, struct sk_buff *skb,
-					struct common_audit_data *ad, u8 proto)
+int selinux_xfrm_postroute_last(u32 sk_sid, struct sk_buff *skb,
+				struct common_audit_data *ad, u8 proto)
 {
 	struct dst_entry *dst;
-	int rc = 0;
-
-	dst = skb_dst(skb);
-
-	if (dst) {
-		struct dst_entry *dst_test;
-
-		for (dst_test = dst; dst_test != NULL;
-		     dst_test = dst_test->child) {
-			struct xfrm_state *x = dst_test->xfrm;
-
-			if (x && selinux_authorizable_xfrm(x))
-				goto out;
-		}
-	}
 
 	switch (proto) {
 	case IPPROTO_AH:
 	case IPPROTO_ESP:
 	case IPPROTO_COMP:
-		/*
-		 * We should have already seen this packet once before
-		 * it underwent xfrm(s). No need to subject it to the
-		 * unlabeled check.
-		 */
-		goto out;
+		/* We should have already seen this packet once before it
+		 * underwent xfrm(s). No need to subject it to the unlabeled
+		 * check. */
+		return 0;
 	default:
 		break;
 	}
 
-	/*
-	 * This check even when there's no association involved is
-	 * intended, according to Trent Jaeger, to make sure a
-	 * process can't engage in non-ipsec communication unless
-	 * explicitly allowed by policy.
-	 */
+	dst = skb_dst(skb);
+	if (dst) {
+		struct dst_entry *iter;
 
-	rc = avc_has_perm(isec_sid, SECINITSID_UNLABELED, SECCLASS_ASSOCIATION,
-			  ASSOCIATION__SENDTO, ad);
-out:
-	return rc;
+		for (iter = dst; iter != NULL; iter = iter->child) {
+			struct xfrm_state *x = iter->xfrm;
+
+			if (x && selinux_authorizable_xfrm(x))
+				return 0;
+		}
+	}
+
+	/* This check even when there's no association involved is intended,
+	 * according to Trent Jaeger, to make sure a process can't engage in
+	 * non-IPsec communication unless explicitly allowed by policy. */
+	return avc_has_perm(sk_sid, SECINITSID_UNLABELED,
+			    SECCLASS_ASSOCIATION, ASSOCIATION__SENDTO, ad);
 }
-- 
cgit v1.2.3


From 4baabeec2a061fe771f9fcc01c61204a2ee2f608 Mon Sep 17 00:00:00 2001
From: Paul Moore <pmoore@redhat.com>
Date: Tue, 23 Jul 2013 17:38:39 -0400
Subject: selinux: cleanup some comment and whitespace issues in the XFRM code

Signed-off-by: Paul Moore <pmoore@redhat.com>
Signed-off-by: Eric Paris <eparis@redhat.com>
---
 security/selinux/xfrm.c | 23 ++++++++++-------------
 1 file changed, 10 insertions(+), 13 deletions(-)

(limited to 'security')

diff --git a/security/selinux/xfrm.c b/security/selinux/xfrm.c
index 1f6c6e619e98..00801cef1dd9 100644
--- a/security/selinux/xfrm.c
+++ b/security/selinux/xfrm.c
@@ -56,7 +56,7 @@
 atomic_t selinux_xfrm_refcount = ATOMIC_INIT(0);
 
 /*
- * Returns true if an LSM/SELinux context
+ * Returns true if the context is an LSM/SELinux context.
  */
 static inline int selinux_authorizable_ctx(struct xfrm_sec_ctx *ctx)
 {
@@ -66,7 +66,7 @@ static inline int selinux_authorizable_ctx(struct xfrm_sec_ctx *ctx)
 }
 
 /*
- * Returns true if the xfrm contains a security blob for SELinux
+ * Returns true if the xfrm contains a security blob for SELinux.
  */
 static inline int selinux_authorizable_xfrm(struct xfrm_state *x)
 {
@@ -149,8 +149,8 @@ static int selinux_xfrm_delete(struct xfrm_sec_ctx *ctx)
 }
 
 /*
- * LSM hook implementation that authorizes that a flow can use
- * a xfrm policy rule.
+ * LSM hook implementation that authorizes that a flow can use a xfrm policy
+ * rule.
  */
 int selinux_xfrm_policy_lookup(struct xfrm_sec_ctx *ctx, u32 fl_secid, u8 dir)
 {
@@ -213,7 +213,6 @@ int selinux_xfrm_state_pol_flow_match(struct xfrm_state *x,
  * LSM hook implementation that checks and/or returns the xfrm sid for the
  * incoming packet.
  */
-
 int selinux_xfrm_decode_session(struct sk_buff *skb, u32 *sid, int ckall)
 {
 	struct sec_path *sp;
@@ -248,8 +247,7 @@ int selinux_xfrm_decode_session(struct sk_buff *skb, u32 *sid, int ckall)
 }
 
 /*
- * LSM hook implementation that allocs and transfers uctx spec to
- * xfrm_policy.
+ * LSM hook implementation that allocs and transfers uctx spec to xfrm_policy.
  */
 int selinux_xfrm_policy_alloc(struct xfrm_sec_ctx **ctxp,
 			      struct xfrm_user_sec_ctx *uctx)
@@ -257,10 +255,9 @@ int selinux_xfrm_policy_alloc(struct xfrm_sec_ctx **ctxp,
 	return selinux_xfrm_alloc_user(ctxp, uctx);
 }
 
-
 /*
- * LSM hook implementation that copies security data structure from old to
- * new for policy cloning.
+ * LSM hook implementation that copies security data structure from old to new
+ * for policy cloning.
  */
 int selinux_xfrm_policy_clone(struct xfrm_sec_ctx *old_ctx,
 			      struct xfrm_sec_ctx **new_ctxp)
@@ -352,9 +349,9 @@ void selinux_xfrm_state_free(struct xfrm_state *x)
 	selinux_xfrm_free(x->security);
 }
 
- /*
-  * LSM hook implementation that authorizes deletion of labeled SAs.
-  */
+/*
+ * LSM hook implementation that authorizes deletion of labeled SAs.
+ */
 int selinux_xfrm_state_delete(struct xfrm_state *x)
 {
 	return selinux_xfrm_delete(x->security);
-- 
cgit v1.2.3


From e21936958000a4f2298193b3875b707fbcbc8f7b Mon Sep 17 00:00:00 2001
From: Paul Moore <pmoore@redhat.com>
Date: Tue, 23 Jul 2013 17:38:40 -0400
Subject: selinux: cleanup selinux_xfrm_decode_session()

Some basic simplification.

Signed-off-by: Paul Moore <pmoore@redhat.com>
Signed-off-by: Eric Paris <eparis@redhat.com>
---
 security/selinux/xfrm.c | 23 ++++++++++++-----------
 1 file changed, 12 insertions(+), 11 deletions(-)

(limited to 'security')

diff --git a/security/selinux/xfrm.c b/security/selinux/xfrm.c
index 00801cef1dd9..425b9f91d755 100644
--- a/security/selinux/xfrm.c
+++ b/security/selinux/xfrm.c
@@ -215,34 +215,35 @@ int selinux_xfrm_state_pol_flow_match(struct xfrm_state *x,
  */
 int selinux_xfrm_decode_session(struct sk_buff *skb, u32 *sid, int ckall)
 {
+	u32 sid_session = SECSID_NULL;
 	struct sec_path *sp;
 
-	*sid = SECSID_NULL;
-
 	if (skb == NULL)
-		return 0;
+		goto out;
 
 	sp = skb->sp;
 	if (sp) {
-		int i, sid_set = 0;
+		int i;
 
-		for (i = sp->len-1; i >= 0; i--) {
+		for (i = sp->len - 1; i >= 0; i--) {
 			struct xfrm_state *x = sp->xvec[i];
 			if (selinux_authorizable_xfrm(x)) {
 				struct xfrm_sec_ctx *ctx = x->security;
 
-				if (!sid_set) {
-					*sid = ctx->ctx_sid;
-					sid_set = 1;
-
+				if (sid_session == SECSID_NULL) {
+					sid_session = ctx->ctx_sid;
 					if (!ckall)
-						break;
-				} else if (*sid != ctx->ctx_sid)
+						goto out;
+				} else if (sid_session != ctx->ctx_sid) {
+					*sid = SECSID_NULL;
 					return -EINVAL;
+				}
 			}
 		}
 	}
 
+out:
+	*sid = sid_session;
 	return 0;
 }
 
-- 
cgit v1.2.3


From d1b17b09f390369271ecfbc7e4a4d0d0dcff1b1b Mon Sep 17 00:00:00 2001
From: Paul Moore <pmoore@redhat.com>
Date: Tue, 23 Jul 2013 17:38:40 -0400
Subject: selinux: cleanup the XFRM header

Remove the unused get_sock_isec() function and do some formatting
fixes.

Signed-off-by: Paul Moore <pmoore@redhat.com>
Signed-off-by: Eric Paris <eparis@redhat.com>
---
 security/selinux/include/xfrm.h | 19 +++++--------------
 1 file changed, 5 insertions(+), 14 deletions(-)

(limited to 'security')

diff --git a/security/selinux/include/xfrm.h b/security/selinux/include/xfrm.h
index b463f210f1af..60774bcf61b3 100644
--- a/security/selinux/include/xfrm.h
+++ b/security/selinux/include/xfrm.h
@@ -10,7 +10,7 @@
 #include <net/flow.h>
 
 int selinux_xfrm_policy_alloc(struct xfrm_sec_ctx **ctxp,
-			      struct xfrm_user_sec_ctx *sec_ctx);
+			      struct xfrm_user_sec_ctx *uctx);
 int selinux_xfrm_policy_clone(struct xfrm_sec_ctx *old_ctx,
 			      struct xfrm_sec_ctx **new_ctxp);
 void selinux_xfrm_policy_free(struct xfrm_sec_ctx *ctx);
@@ -23,18 +23,8 @@ void selinux_xfrm_state_free(struct xfrm_state *x);
 int selinux_xfrm_state_delete(struct xfrm_state *x);
 int selinux_xfrm_policy_lookup(struct xfrm_sec_ctx *ctx, u32 fl_secid, u8 dir);
 int selinux_xfrm_state_pol_flow_match(struct xfrm_state *x,
-			struct xfrm_policy *xp, const struct flowi *fl);
-
-/*
- * Extract the security blob from the sock (it's actually on the socket)
- */
-static inline struct inode_security_struct *get_sock_isec(struct sock *sk)
-{
-	if (!sk->sk_socket)
-		return NULL;
-
-	return SOCK_INODE(sk->sk_socket)->i_security;
-}
+				      struct xfrm_policy *xp,
+				      const struct flowi *fl);
 
 #ifdef CONFIG_SECURITY_NETWORK_XFRM
 extern atomic_t selinux_xfrm_refcount;
@@ -74,7 +64,8 @@ static inline int selinux_xfrm_postroute_last(u32 sk_sid, struct sk_buff *skb,
 	return 0;
 }
 
-static inline int selinux_xfrm_decode_session(struct sk_buff *skb, u32 *sid, int ckall)
+static inline int selinux_xfrm_decode_session(struct sk_buff *skb, u32 *sid,
+					      int ckall)
 {
 	*sid = SECSID_NULL;
 	return 0;
-- 
cgit v1.2.3


From bed4d7efb31fd81b3a3c83dc8540197cd0fe81c0 Mon Sep 17 00:00:00 2001
From: Paul Moore <pmoore@redhat.com>
Date: Tue, 23 Jul 2013 17:38:40 -0400
Subject: selinux: remove the BUG_ON() from selinux_skb_xfrm_sid()

Remove the BUG_ON() from selinux_skb_xfrm_sid() and propogate the
error code up to the caller.  Also check the return values in the
only caller function, selinux_skb_peerlbl_sid().

Signed-off-by: Paul Moore <pmoore@redhat.com>
Signed-off-by: Eric Paris <eparis@redhat.com>
---
 security/selinux/hooks.c        | 8 ++++++--
 security/selinux/include/xfrm.h | 5 ++---
 2 files changed, 8 insertions(+), 5 deletions(-)

(limited to 'security')

diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c
index d3555bdf66af..4bc068b3773d 100644
--- a/security/selinux/hooks.c
+++ b/security/selinux/hooks.c
@@ -3722,8 +3722,12 @@ static int selinux_skb_peerlbl_sid(struct sk_buff *skb, u16 family, u32 *sid)
 	u32 nlbl_sid;
 	u32 nlbl_type;
 
-	selinux_skb_xfrm_sid(skb, &xfrm_sid);
-	selinux_netlbl_skbuff_getsid(skb, family, &nlbl_type, &nlbl_sid);
+	err = selinux_skb_xfrm_sid(skb, &xfrm_sid);
+	if (unlikely(err))
+		return -EACCES;
+	err = selinux_netlbl_skbuff_getsid(skb, family, &nlbl_type, &nlbl_sid);
+	if (unlikely(err))
+		return -EACCES;
 
 	err = security_net_peersid_resolve(nlbl_sid, nlbl_type, xfrm_sid, sid);
 	if (unlikely(err)) {
diff --git a/security/selinux/include/xfrm.h b/security/selinux/include/xfrm.h
index 60774bcf61b3..7605251936f5 100644
--- a/security/selinux/include/xfrm.h
+++ b/security/selinux/include/xfrm.h
@@ -76,10 +76,9 @@ static inline void selinux_xfrm_notify_policyload(void)
 }
 #endif
 
-static inline void selinux_skb_xfrm_sid(struct sk_buff *skb, u32 *sid)
+static inline int selinux_skb_xfrm_sid(struct sk_buff *skb, u32 *sid)
 {
-	int err = selinux_xfrm_decode_session(skb, sid, 0);
-	BUG_ON(err);
+	return selinux_xfrm_decode_session(skb, sid, 0);
 }
 
 #endif /* _SELINUX_XFRM_H_ */
-- 
cgit v1.2.3


From fee7114298cf54bbd221cdb2ab49738be8b94f4c Mon Sep 17 00:00:00 2001
From: Waiman Long <Waiman.Long@hp.com>
Date: Tue, 23 Jul 2013 17:38:41 -0400
Subject: SELinux: Reduce overhead of mls_level_isvalid() function call

While running the high_systime workload of the AIM7 benchmark on
a 2-socket 12-core Westmere x86-64 machine running 3.10-rc4 kernel
(with HT on), it was found that a pretty sizable amount of time was
spent in the SELinux code. Below was the perf trace of the "perf
record -a -s" of a test run at 1500 users:

  5.04%            ls  [kernel.kallsyms]     [k] ebitmap_get_bit
  1.96%            ls  [kernel.kallsyms]     [k] mls_level_isvalid
  1.95%            ls  [kernel.kallsyms]     [k] find_next_bit

The ebitmap_get_bit() was the hottest function in the perf-report
output.  Both the ebitmap_get_bit() and find_next_bit() functions
were, in fact, called by mls_level_isvalid(). As a result, the
mls_level_isvalid() call consumed 8.95% of the total CPU time of
all the 24 virtual CPUs which is quite a lot. The majority of the
mls_level_isvalid() function invocations come from the socket creation
system call.

Looking at the mls_level_isvalid() function, it is checking to see
if all the bits set in one of the ebitmap structure are also set in
another one as well as the highest set bit is no bigger than the one
specified by the given policydb data structure. It is doing it in
a bit-by-bit manner. So if the ebitmap structure has many bits set,
the iteration loop will be done many times.

The current code can be rewritten to use a similar algorithm as the
ebitmap_contains() function with an additional check for the
highest set bit. The ebitmap_contains() function was extended to
cover an optional additional check for the highest set bit, and the
mls_level_isvalid() function was modified to call ebitmap_contains().

With that change, the perf trace showed that the used CPU time drop
down to just 0.08% (ebitmap_contains + mls_level_isvalid) of the
total which is about 100X less than before.

  0.07%            ls  [kernel.kallsyms]     [k] ebitmap_contains
  0.05%            ls  [kernel.kallsyms]     [k] ebitmap_get_bit
  0.01%            ls  [kernel.kallsyms]     [k] mls_level_isvalid
  0.01%            ls  [kernel.kallsyms]     [k] find_next_bit

The remaining ebitmap_get_bit() and find_next_bit() functions calls
are made by other kernel routines as the new mls_level_isvalid()
function will not call them anymore.

This patch also improves the high_systime AIM7 benchmark result,
though the improvement is not as impressive as is suggested by the
reduction in CPU time spent in the ebitmap functions. The table below
shows the performance change on the 2-socket x86-64 system (with HT
on) mentioned above.

+--------------+---------------+----------------+-----------------+
|   Workload   | mean % change | mean % change  | mean % change   |
|              | 10-100 users  | 200-1000 users | 1100-2000 users |
+--------------+---------------+----------------+-----------------+
| high_systime |     +0.1%     |     +0.9%      |     +2.6%       |
+--------------+---------------+----------------+-----------------+

Signed-off-by: Waiman Long <Waiman.Long@hp.com>
Acked-by:  Stephen Smalley <sds@tycho.nsa.gov>
Signed-off-by: Paul Moore <pmoore@redhat.com>
Signed-off-by: Eric Paris <eparis@redhat.com>
---
 security/selinux/ss/ebitmap.c   | 20 ++++++++++++++++++--
 security/selinux/ss/ebitmap.h   |  2 +-
 security/selinux/ss/mls.c       | 22 +++++++---------------
 security/selinux/ss/mls_types.h |  2 +-
 4 files changed, 27 insertions(+), 19 deletions(-)

(limited to 'security')

diff --git a/security/selinux/ss/ebitmap.c b/security/selinux/ss/ebitmap.c
index 30f119b1d1ec..820313a04d49 100644
--- a/security/selinux/ss/ebitmap.c
+++ b/security/selinux/ss/ebitmap.c
@@ -213,7 +213,12 @@ netlbl_import_failure:
 }
 #endif /* CONFIG_NETLABEL */
 
-int ebitmap_contains(struct ebitmap *e1, struct ebitmap *e2)
+/*
+ * Check to see if all the bits set in e2 are also set in e1. Optionally,
+ * if last_e2bit is non-zero, the highest set bit in e2 cannot exceed
+ * last_e2bit.
+ */
+int ebitmap_contains(struct ebitmap *e1, struct ebitmap *e2, u32 last_e2bit)
 {
 	struct ebitmap_node *n1, *n2;
 	int i;
@@ -223,14 +228,25 @@ int ebitmap_contains(struct ebitmap *e1, struct ebitmap *e2)
 
 	n1 = e1->node;
 	n2 = e2->node;
+
 	while (n1 && n2 && (n1->startbit <= n2->startbit)) {
 		if (n1->startbit < n2->startbit) {
 			n1 = n1->next;
 			continue;
 		}
-		for (i = 0; i < EBITMAP_UNIT_NUMS; i++) {
+		for (i = EBITMAP_UNIT_NUMS - 1; (i >= 0) && !n2->maps[i]; )
+			i--;	/* Skip trailing NULL map entries */
+		if (last_e2bit && (i >= 0)) {
+			u32 lastsetbit = n2->startbit + i * EBITMAP_UNIT_SIZE +
+					 __fls(n2->maps[i]);
+			if (lastsetbit > last_e2bit)
+				return 0;
+		}
+
+		while (i >= 0) {
 			if ((n1->maps[i] & n2->maps[i]) != n2->maps[i])
 				return 0;
+			i--;
 		}
 
 		n1 = n1->next;
diff --git a/security/selinux/ss/ebitmap.h b/security/selinux/ss/ebitmap.h
index 922f8afa89dd..e7eb3a9c5ab7 100644
--- a/security/selinux/ss/ebitmap.h
+++ b/security/selinux/ss/ebitmap.h
@@ -117,7 +117,7 @@ static inline void ebitmap_node_clr_bit(struct ebitmap_node *n,
 
 int ebitmap_cmp(struct ebitmap *e1, struct ebitmap *e2);
 int ebitmap_cpy(struct ebitmap *dst, struct ebitmap *src);
-int ebitmap_contains(struct ebitmap *e1, struct ebitmap *e2);
+int ebitmap_contains(struct ebitmap *e1, struct ebitmap *e2, u32 last_e2bit);
 int ebitmap_get_bit(struct ebitmap *e, unsigned long bit);
 int ebitmap_set_bit(struct ebitmap *e, unsigned long bit, int value);
 void ebitmap_destroy(struct ebitmap *e);
diff --git a/security/selinux/ss/mls.c b/security/selinux/ss/mls.c
index 40de8d3f208e..c85bc1ec040c 100644
--- a/security/selinux/ss/mls.c
+++ b/security/selinux/ss/mls.c
@@ -160,8 +160,6 @@ void mls_sid_to_context(struct context *context,
 int mls_level_isvalid(struct policydb *p, struct mls_level *l)
 {
 	struct level_datum *levdatum;
-	struct ebitmap_node *node;
-	int i;
 
 	if (!l->sens || l->sens > p->p_levels.nprim)
 		return 0;
@@ -170,19 +168,13 @@ int mls_level_isvalid(struct policydb *p, struct mls_level *l)
 	if (!levdatum)
 		return 0;
 
-	ebitmap_for_each_positive_bit(&l->cat, node, i) {
-		if (i > p->p_cats.nprim)
-			return 0;
-		if (!ebitmap_get_bit(&levdatum->level->cat, i)) {
-			/*
-			 * Category may not be associated with
-			 * sensitivity.
-			 */
-			return 0;
-		}
-	}
-
-	return 1;
+	/*
+	 * Return 1 iff all the bits set in l->cat are also be set in
+	 * levdatum->level->cat and no bit in l->cat is larger than
+	 * p->p_cats.nprim.
+	 */
+	return ebitmap_contains(&levdatum->level->cat, &l->cat,
+				p->p_cats.nprim);
 }
 
 int mls_range_isvalid(struct policydb *p, struct mls_range *r)
diff --git a/security/selinux/ss/mls_types.h b/security/selinux/ss/mls_types.h
index 03bed52a8052..e93648774137 100644
--- a/security/selinux/ss/mls_types.h
+++ b/security/selinux/ss/mls_types.h
@@ -35,7 +35,7 @@ static inline int mls_level_eq(struct mls_level *l1, struct mls_level *l2)
 static inline int mls_level_dom(struct mls_level *l1, struct mls_level *l2)
 {
 	return ((l1->sens >= l2->sens) &&
-		ebitmap_contains(&l1->cat, &l2->cat));
+		ebitmap_contains(&l1->cat, &l2->cat, 0));
 }
 
 #define mls_level_incomp(l1, l2) \
-- 
cgit v1.2.3


From a767f680e34bf14a36fefbbb6d85783eef99fd57 Mon Sep 17 00:00:00 2001
From: Waiman Long <Waiman.Long@hp.com>
Date: Tue, 23 Jul 2013 17:38:41 -0400
Subject: SELinux: Increase ebitmap_node size for 64-bit configuration

Currently, the ebitmap_node structure has a fixed size of 32 bytes. On
a 32-bit system, the overhead is 8 bytes, leaving 24 bytes for being
used as bitmaps. The overhead ratio is 1/4.

On a 64-bit system, the overhead is 16 bytes. Therefore, only 16 bytes
are left for bitmap purpose and the overhead ratio is 1/2. With a
3.8.2 kernel, a boot-up operation will cause the ebitmap_get_bit()
function to be called about 9 million times. The average number of
ebitmap_node traversal is about 3.7.

This patch increases the size of the ebitmap_node structure to 64
bytes for 64-bit system to keep the overhead ratio at 1/4. This may
also improve performance a little bit by making node to node traversal
less frequent (< 2) as more bits are available in each node.

Signed-off-by: Waiman Long <Waiman.Long@hp.com>
Acked-by:  Stephen Smalley <sds@tycho.nsa.gov>
Signed-off-by: Paul Moore <pmoore@redhat.com>
Signed-off-by: Eric Paris <eparis@redhat.com>
---
 security/selinux/ss/ebitmap.h | 8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)

(limited to 'security')

diff --git a/security/selinux/ss/ebitmap.h b/security/selinux/ss/ebitmap.h
index e7eb3a9c5ab7..712c8a7b8e8b 100644
--- a/security/selinux/ss/ebitmap.h
+++ b/security/selinux/ss/ebitmap.h
@@ -16,7 +16,13 @@
 
 #include <net/netlabel.h>
 
-#define EBITMAP_UNIT_NUMS	((32 - sizeof(void *) - sizeof(u32))	\
+#ifdef CONFIG_64BIT
+#define	EBITMAP_NODE_SIZE	64
+#else
+#define	EBITMAP_NODE_SIZE	32
+#endif
+
+#define EBITMAP_UNIT_NUMS	((EBITMAP_NODE_SIZE-sizeof(void *)-sizeof(u32))\
 					/ sizeof(unsigned long))
 #define EBITMAP_UNIT_SIZE	BITS_PER_LONG
 #define EBITMAP_SIZE		(EBITMAP_UNIT_NUMS * EBITMAP_UNIT_SIZE)
-- 
cgit v1.2.3


From 5c73fceb8c70466c5876ad94c356922ae75a0820 Mon Sep 17 00:00:00 2001
From: Stephen Smalley <sds@tycho.nsa.gov>
Date: Tue, 23 Jul 2013 17:38:41 -0400
Subject: SELinux: Enable setting security contexts on rootfs inodes.

rootfs (ramfs) can support setting of security contexts
by userspace due to the vfs fallback behavior of calling
the security module to set the in-core inode state
for security.* attributes when the filesystem does not
provide an xattr handler.  No xattr handler required
as the inodes are pinned in memory and have no backing
store.

This is useful in allowing early userspace to label individual
files within a rootfs while still providing a policy-defined
default via genfs.

Signed-off-by: Stephen Smalley <sds@tycho.nsa.gov>
Signed-off-by: Paul Moore <pmoore@redhat.com>
Signed-off-by: Eric Paris <eparis@redhat.com>
---
 security/selinux/hooks.c | 7 +++++++
 1 file changed, 7 insertions(+)

(limited to 'security')

diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c
index 4bc068b3773d..911b780fcf80 100644
--- a/security/selinux/hooks.c
+++ b/security/selinux/hooks.c
@@ -406,6 +406,13 @@ static int sb_finish_set_opts(struct super_block *sb)
 	if (strncmp(sb->s_type->name, "sysfs", sizeof("sysfs")) == 0)
 		sbsec->flags |= SE_SBLABELSUPP;
 
+	/*
+	 * Special handling for rootfs. Is genfs but supports
+	 * setting SELinux context on in-core inodes.
+	 */
+	if (strncmp(sb->s_type->name, "rootfs", sizeof("rootfs")) == 0)
+		sbsec->flags |= SE_SBLABELSUPP;
+
 	/* Initialize the root inode. */
 	rc = inode_doinit_with_dentry(root_inode, root);
 
-- 
cgit v1.2.3


From b138004ea0382bdc6d02599c39392651b4f63889 Mon Sep 17 00:00:00 2001
From: Eric Paris <eparis@redhat.com>
Date: Tue, 23 Jul 2013 17:38:42 -0400
Subject: SELinux: fix selinuxfs policy file on big endian systems

The /sys/fs/selinux/policy file is not valid on big endian systems like
ppc64 or s390.  Let's see why:

static int hashtab_cnt(void *key, void *data, void *ptr)
{
	int *cnt = ptr;
	*cnt = *cnt + 1;

	return 0;
}

static int range_write(struct policydb *p, void *fp)
{
	size_t nel;
[...]
	/* count the number of entries in the hashtab */
	nel = 0;
	rc = hashtab_map(p->range_tr, hashtab_cnt, &nel);
	if (rc)
		return rc;
	buf[0] = cpu_to_le32(nel);
	rc = put_entry(buf, sizeof(u32), 1, fp);

So size_t is 64 bits.  But then we pass a pointer to it as we do to
hashtab_cnt.  hashtab_cnt thinks it is a 32 bit int and only deals with
the first 4 bytes.  On x86_64 which is little endian, those first 4
bytes and the least significant, so this works out fine.  On ppc64/s390
those first 4 bytes of memory are the high order bits.  So at the end of
the call to hashtab_map nel has a HUGE number.  But the least
significant 32 bits are all 0's.

We then pass that 64 bit number to cpu_to_le32() which happily truncates
it to a 32 bit number and does endian swapping.  But the low 32 bits are
all 0's.  So no matter how many entries are in the hashtab, big endian
systems always say there are 0 entries because I screwed up the
counting.

The fix is easy.  Use a 32 bit int, as the hashtab_cnt expects, for nel.

Signed-off-by: Eric Paris <eparis@redhat.com>
Signed-off-by: Paul Moore <pmoore@redhat.com>
---
 security/selinux/ss/policydb.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

(limited to 'security')

diff --git a/security/selinux/ss/policydb.c b/security/selinux/ss/policydb.c
index 9cd9b7c661ec..3fc8969b499c 100644
--- a/security/selinux/ss/policydb.c
+++ b/security/selinux/ss/policydb.c
@@ -3200,9 +3200,8 @@ static int range_write_helper(void *key, void *data, void *ptr)
 
 static int range_write(struct policydb *p, void *fp)
 {
-	size_t nel;
 	__le32 buf[1];
-	int rc;
+	int rc, nel;
 	struct policy_data pd;
 
 	pd.p = p;
-- 
cgit v1.2.3


From 40d3d0b85fa22084fc3b7eeb943aca365097cea3 Mon Sep 17 00:00:00 2001
From: Eric Paris <eparis@redhat.com>
Date: Fri, 24 Aug 2012 15:58:45 -0400
Subject: SELinux: remove crazy contortions around proc

We check if the fsname is proc and if so set the proc superblock security
struct flag.  We then check if the flag is set and use the string 'proc'
for the fsname instead of just using the fsname.  What's the point?  It's
always proc...  Get rid of the useless conditional.

Signed-off-by: Eric Paris <eparis@redhat.com>
---
 security/selinux/hooks.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'security')

diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c
index 911b780fcf80..42b538ceb8b4 100644
--- a/security/selinux/hooks.c
+++ b/security/selinux/hooks.c
@@ -678,7 +678,7 @@ static int selinux_set_mnt_opts(struct super_block *sb,
 		sbsec->flags |= SE_SBPROC;
 
 	/* Determine the labeling behavior to use for this filesystem type. */
-	rc = security_fs_use((sbsec->flags & SE_SBPROC) ? "proc" : sb->s_type->name, &sbsec->behavior, &sbsec->sid);
+	rc = security_fs_use(sb->s_type->name, &sbsec->behavior, &sbsec->sid);
 	if (rc) {
 		printk(KERN_WARNING "%s: security_fs_use(%s) returned %d\n",
 		       __func__, sb->s_type->name, rc);
-- 
cgit v1.2.3


From d355987f47bbe24e7450b509a3f8aac0db88b65a Mon Sep 17 00:00:00 2001
From: Eric Paris <eparis@redhat.com>
Date: Fri, 24 Aug 2012 15:58:53 -0400
Subject: SELinux: make it harder to get the number of mnt opts wrong

Instead of just hard coding a value, use the enum to out benefit.

Signed-off-by: Eric Paris <eparis@redhat.com>
---
 security/selinux/hooks.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

(limited to 'security')

diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c
index 42b538ceb8b4..863f20590186 100644
--- a/security/selinux/hooks.c
+++ b/security/selinux/hooks.c
@@ -94,8 +94,6 @@
 #include "audit.h"
 #include "avc_ss.h"
 
-#define NUM_SEL_MNT_OPTS 5
-
 extern struct security_operations *security_ops;
 
 /* SECMARK reference count */
@@ -307,8 +305,11 @@ enum {
 	Opt_defcontext = 3,
 	Opt_rootcontext = 4,
 	Opt_labelsupport = 5,
+	Opt_nextmntopt = 6,
 };
 
+#define NUM_SEL_MNT_OPTS	(Opt_nextmntopt - 1)
+
 static const match_table_t tokens = {
 	{Opt_context, CONTEXT_STR "%s"},
 	{Opt_fscontext, FSCONTEXT_STR "%s"},
-- 
cgit v1.2.3


From af8e50cc7d546c508e9091bbbdf3cf8b243bd8cd Mon Sep 17 00:00:00 2001
From: Eric Paris <eparis@redhat.com>
Date: Fri, 24 Aug 2012 15:59:00 -0400
Subject: SELinux: use define for number of bits in the mnt flags mask

We had this random hard coded value of '8' in the code (I put it there)
for the number of bits to check for mount options.  This is stupid.  Instead
use the #define we already have which tells us the number of mount
options.

Signed-off-by: Eric Paris <eparis@redhat.com>
---
 security/selinux/hooks.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

(limited to 'security')

diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c
index 863f20590186..e13d65a62104 100644
--- a/security/selinux/hooks.c
+++ b/security/selinux/hooks.c
@@ -466,9 +466,12 @@ static int selinux_get_mnt_opts(const struct super_block *sb,
 	if (!ss_initialized)
 		return -EINVAL;
 
+	/* make sure we always check enough bits to cover the mask */
+	BUILD_BUG_ON(SE_MNTMASK >= (1 << NUM_SEL_MNT_OPTS));
+
 	tmp = sbsec->flags & SE_MNTMASK;
 	/* count the number of mount options for this sb */
-	for (i = 0; i < 8; i++) {
+	for (i = 0; i < NUM_SEL_MNT_OPTS; i++) {
 		if (tmp & 0x01)
 			opts->num_mnt_opts++;
 		tmp >>= 1;
-- 
cgit v1.2.3


From 12f348b9dcf6d9616c86a049c3c8700f9dc0af55 Mon Sep 17 00:00:00 2001
From: Eric Paris <eparis@redhat.com>
Date: Tue, 9 Oct 2012 10:56:25 -0400
Subject: SELinux: rename SE_SBLABELSUPP to SBLABEL_MNT

Just a flag rename as we prepare to make it not so special.

Signed-off-by: Eric Paris <eparis@redhat.com>
---
 security/selinux/hooks.c            | 28 ++++++++++++++--------------
 security/selinux/include/security.h |  2 +-
 2 files changed, 15 insertions(+), 15 deletions(-)

(limited to 'security')

diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c
index e13d65a62104..344f4f999681 100644
--- a/security/selinux/hooks.c
+++ b/security/selinux/hooks.c
@@ -387,7 +387,7 @@ static int sb_finish_set_opts(struct super_block *sb)
 		}
 	}
 
-	sbsec->flags |= (SE_SBINITIALIZED | SE_SBLABELSUPP);
+	sbsec->flags |= (SE_SBINITIALIZED | SBLABEL_MNT);
 
 	if (sbsec->behavior > ARRAY_SIZE(labeling_behaviors))
 		printk(KERN_ERR "SELinux: initialized (dev %s, type %s), unknown behavior\n",
@@ -401,18 +401,18 @@ static int sb_finish_set_opts(struct super_block *sb)
 	    sbsec->behavior == SECURITY_FS_USE_MNTPOINT ||
 	    sbsec->behavior == SECURITY_FS_USE_NONE ||
 	    sbsec->behavior > ARRAY_SIZE(labeling_behaviors))
-		sbsec->flags &= ~SE_SBLABELSUPP;
+		sbsec->flags &= ~SBLABEL_MNT;
 
 	/* Special handling for sysfs. Is genfs but also has setxattr handler*/
 	if (strncmp(sb->s_type->name, "sysfs", sizeof("sysfs")) == 0)
-		sbsec->flags |= SE_SBLABELSUPP;
+		sbsec->flags |= SBLABEL_MNT;
 
 	/*
 	 * Special handling for rootfs. Is genfs but supports
 	 * setting SELinux context on in-core inodes.
 	 */
 	if (strncmp(sb->s_type->name, "rootfs", sizeof("rootfs")) == 0)
-		sbsec->flags |= SE_SBLABELSUPP;
+		sbsec->flags |= SBLABEL_MNT;
 
 	/* Initialize the root inode. */
 	rc = inode_doinit_with_dentry(root_inode, root);
@@ -477,7 +477,7 @@ static int selinux_get_mnt_opts(const struct super_block *sb,
 		tmp >>= 1;
 	}
 	/* Check if the Label support flag is set */
-	if (sbsec->flags & SE_SBLABELSUPP)
+	if (sbsec->flags & SBLABEL_MNT)
 		opts->num_mnt_opts++;
 
 	opts->mnt_opts = kcalloc(opts->num_mnt_opts, sizeof(char *), GFP_ATOMIC);
@@ -524,9 +524,9 @@ static int selinux_get_mnt_opts(const struct super_block *sb,
 		opts->mnt_opts[i] = context;
 		opts->mnt_opts_flags[i++] = ROOTCONTEXT_MNT;
 	}
-	if (sbsec->flags & SE_SBLABELSUPP) {
+	if (sbsec->flags & SBLABEL_MNT) {
 		opts->mnt_opts[i] = NULL;
-		opts->mnt_opts_flags[i++] = SE_SBLABELSUPP;
+		opts->mnt_opts_flags[i++] = SBLABEL_MNT;
 	}
 
 	BUG_ON(i != opts->num_mnt_opts);
@@ -615,7 +615,7 @@ static int selinux_set_mnt_opts(struct super_block *sb,
 	for (i = 0; i < num_opts; i++) {
 		u32 sid;
 
-		if (flags[i] == SE_SBLABELSUPP)
+		if (flags[i] == SBLABEL_MNT)
 			continue;
 		rc = security_context_to_sid(mount_options[i],
 					     strlen(mount_options[i]), &sid);
@@ -1025,7 +1025,7 @@ static void selinux_write_opts(struct seq_file *m,
 		case DEFCONTEXT_MNT:
 			prefix = DEFCONTEXT_STR;
 			break;
-		case SE_SBLABELSUPP:
+		case SBLABEL_MNT:
 			seq_putc(m, ',');
 			seq_puts(m, LABELSUPP_STR);
 			continue;
@@ -1624,7 +1624,7 @@ static int may_create(struct inode *dir,
 	if (rc)
 		return rc;
 
-	if (!newsid || !(sbsec->flags & SE_SBLABELSUPP)) {
+	if (!newsid || !(sbsec->flags & SBLABEL_MNT)) {
 		rc = security_transition_sid(sid, dsec->sid, tclass,
 					     &dentry->d_name, &newsid);
 		if (rc)
@@ -2412,7 +2412,7 @@ static int selinux_sb_remount(struct super_block *sb, void *data)
 		u32 sid;
 		size_t len;
 
-		if (flags[i] == SE_SBLABELSUPP)
+		if (flags[i] == SBLABEL_MNT)
 			continue;
 		len = strlen(mount_options[i]);
 		rc = security_context_to_sid(mount_options[i], len, &sid);
@@ -2546,7 +2546,7 @@ static int selinux_inode_init_security(struct inode *inode, struct inode *dir,
 	if ((sbsec->flags & SE_SBINITIALIZED) &&
 	    (sbsec->behavior == SECURITY_FS_USE_MNTPOINT))
 		newsid = sbsec->mntpoint_sid;
-	else if (!newsid || !(sbsec->flags & SE_SBLABELSUPP)) {
+	else if (!newsid || !(sbsec->flags & SBLABEL_MNT)) {
 		rc = security_transition_sid(sid, dsec->sid,
 					     inode_mode_to_security_class(inode->i_mode),
 					     qstr, &newsid);
@@ -2568,7 +2568,7 @@ static int selinux_inode_init_security(struct inode *inode, struct inode *dir,
 		isec->initialized = 1;
 	}
 
-	if (!ss_initialized || !(sbsec->flags & SE_SBLABELSUPP))
+	if (!ss_initialized || !(sbsec->flags & SBLABEL_MNT))
 		return -EOPNOTSUPP;
 
 	if (name) {
@@ -2776,7 +2776,7 @@ static int selinux_inode_setxattr(struct dentry *dentry, const char *name,
 		return selinux_inode_setotherxattr(dentry, name);
 
 	sbsec = inode->i_sb->s_security;
-	if (!(sbsec->flags & SE_SBLABELSUPP))
+	if (!(sbsec->flags & SBLABEL_MNT))
 		return -EOPNOTSUPP;
 
 	if (!inode_owner_or_capable(inode))
diff --git a/security/selinux/include/security.h b/security/selinux/include/security.h
index 6d3885165d14..7ec750609cca 100644
--- a/security/selinux/include/security.h
+++ b/security/selinux/include/security.h
@@ -52,7 +52,7 @@
 /* Non-mount related flags */
 #define SE_SBINITIALIZED	0x10
 #define SE_SBPROC		0x20
-#define SE_SBLABELSUPP	0x40
+#define SBLABEL_MNT	0x40
 
 #define CONTEXT_STR	"context="
 #define FSCONTEXT_STR	"fscontext="
-- 
cgit v1.2.3


From eadcabc697e904e0d93d10070a324d8855740b91 Mon Sep 17 00:00:00 2001
From: Eric Paris <eparis@redhat.com>
Date: Fri, 24 Aug 2012 15:59:14 -0400
Subject: SELinux: do all flags twiddling in one place

Currently we set the initialize and seclabel flag in one place.  Do some
unrelated printk then we unset the seclabel flag.  Eww.  Instead do the flag
twiddling in one place in the code not seperated by unrelated printk.  Also
don't set and unset the seclabel flag.  Only set it if we need to.

Signed-off-by: Eric Paris <eparis@redhat.com>
---
 security/selinux/hooks.c | 12 +++++-------
 1 file changed, 5 insertions(+), 7 deletions(-)

(limited to 'security')

diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c
index 344f4f999681..ca0a1c671f0e 100644
--- a/security/selinux/hooks.c
+++ b/security/selinux/hooks.c
@@ -387,8 +387,6 @@ static int sb_finish_set_opts(struct super_block *sb)
 		}
 	}
 
-	sbsec->flags |= (SE_SBINITIALIZED | SBLABEL_MNT);
-
 	if (sbsec->behavior > ARRAY_SIZE(labeling_behaviors))
 		printk(KERN_ERR "SELinux: initialized (dev %s, type %s), unknown behavior\n",
 		       sb->s_id, sb->s_type->name);
@@ -397,11 +395,11 @@ static int sb_finish_set_opts(struct super_block *sb)
 		       sb->s_id, sb->s_type->name,
 		       labeling_behaviors[sbsec->behavior-1]);
 
-	if (sbsec->behavior == SECURITY_FS_USE_GENFS ||
-	    sbsec->behavior == SECURITY_FS_USE_MNTPOINT ||
-	    sbsec->behavior == SECURITY_FS_USE_NONE ||
-	    sbsec->behavior > ARRAY_SIZE(labeling_behaviors))
-		sbsec->flags &= ~SBLABEL_MNT;
+	sbsec->flags |= SE_SBINITIALIZED;
+	if (sbsec->behavior == SECURITY_FS_USE_XATTR ||
+	    sbsec->behavior == SECURITY_FS_USE_TRANS ||
+	    sbsec->behavior == SECURITY_FS_USE_TASK)
+		sbsec->flags |= SBLABEL_MNT;
 
 	/* Special handling for sysfs. Is genfs but also has setxattr handler*/
 	if (strncmp(sb->s_type->name, "sysfs", sizeof("sysfs")) == 0)
-- 
cgit v1.2.3


From cfca0303da0e2c3f570cb5cfc7c373828e6c13a2 Mon Sep 17 00:00:00 2001
From: Eric Paris <eparis@redhat.com>
Date: Tue, 9 Oct 2012 16:20:08 -0400
Subject: SELinux: renumber the superblock options

Just to make it clear that we have mount time options and flags,
separate them.  Since I decided to move the non-mount options above
above 0x10, we need a short instead of a char.  (x86 padding says
this takes up no additional space as we have a 3byte whole in the
structure)

Signed-off-by: Eric Paris <eparis@redhat.com>
---
 security/selinux/include/objsec.h   | 2 +-
 security/selinux/include/security.h | 7 ++++---
 2 files changed, 5 insertions(+), 4 deletions(-)

(limited to 'security')

diff --git a/security/selinux/include/objsec.h b/security/selinux/include/objsec.h
index aa47bcabb5f6..fe99f64a1d54 100644
--- a/security/selinux/include/objsec.h
+++ b/security/selinux/include/objsec.h
@@ -59,7 +59,7 @@ struct superblock_security_struct {
 	u32 def_sid;			/* default SID for labeling */
 	u32 mntpoint_sid;		/* SECURITY_FS_USE_MNTPOINT context for files */
 	unsigned int behavior;		/* labeling behavior */
-	unsigned char flags;		/* which mount options were specified */
+	unsigned short flags;		/* which mount options were specified */
 	struct mutex lock;
 	struct list_head isec_head;
 	spinlock_t isec_lock;
diff --git a/security/selinux/include/security.h b/security/selinux/include/security.h
index 7ec750609cca..9c424d8bd2e0 100644
--- a/security/selinux/include/security.h
+++ b/security/selinux/include/security.h
@@ -45,14 +45,15 @@
 /* Mask for just the mount related flags */
 #define SE_MNTMASK	0x0f
 /* Super block security struct flags for mount options */
+/* BE CAREFUL, these need to be the low order bits for selinux_get_mnt_opts */
 #define CONTEXT_MNT	0x01
 #define FSCONTEXT_MNT	0x02
 #define ROOTCONTEXT_MNT	0x04
 #define DEFCONTEXT_MNT	0x08
+#define SBLABEL_MNT	0x10
 /* Non-mount related flags */
-#define SE_SBINITIALIZED	0x10
-#define SE_SBPROC		0x20
-#define SBLABEL_MNT	0x40
+#define SE_SBINITIALIZED	0x0100
+#define SE_SBPROC		0x0200
 
 #define CONTEXT_STR	"context="
 #define FSCONTEXT_STR	"fscontext="
-- 
cgit v1.2.3


From f936c6e502d3bc21b87c9830b3a24d1e07e6b6e1 Mon Sep 17 00:00:00 2001
From: Eric Paris <eparis@redhat.com>
Date: Wed, 10 Oct 2012 10:38:47 -0400
Subject: SELinux: change sbsec->behavior to short

We only have 6 options, so char is good enough, but use a short as that
packs nicely.  This shrinks the superblock_security_struct just a little
bit.

Signed-off-by: Eric Paris <eparis@redhat.com>
---
 security/selinux/include/objsec.h   | 2 +-
 security/selinux/include/security.h | 2 +-
 security/selinux/ss/services.c      | 2 +-
 3 files changed, 3 insertions(+), 3 deletions(-)

(limited to 'security')

diff --git a/security/selinux/include/objsec.h b/security/selinux/include/objsec.h
index fe99f64a1d54..b1dfe1049450 100644
--- a/security/selinux/include/objsec.h
+++ b/security/selinux/include/objsec.h
@@ -58,7 +58,7 @@ struct superblock_security_struct {
 	u32 sid;			/* SID of file system superblock */
 	u32 def_sid;			/* default SID for labeling */
 	u32 mntpoint_sid;		/* SECURITY_FS_USE_MNTPOINT context for files */
-	unsigned int behavior;		/* labeling behavior */
+	unsigned short behavior;	/* labeling behavior */
 	unsigned short flags;		/* which mount options were specified */
 	struct mutex lock;
 	struct list_head isec_head;
diff --git a/security/selinux/include/security.h b/security/selinux/include/security.h
index 9c424d8bd2e0..20830be6b61f 100644
--- a/security/selinux/include/security.h
+++ b/security/selinux/include/security.h
@@ -171,7 +171,7 @@ int security_get_allow_unknown(void);
 #define SECURITY_FS_USE_NONE		5 /* no labeling support */
 #define SECURITY_FS_USE_MNTPOINT	6 /* use mountpoint labeling */
 
-int security_fs_use(const char *fstype, unsigned int *behavior,
+int security_fs_use(const char *fstype, short unsigned int *behavior,
 	u32 *sid);
 
 int security_genfs_sid(const char *fstype, char *name, u16 sclass,
diff --git a/security/selinux/ss/services.c b/security/selinux/ss/services.c
index b4feecc3fe01..603c638434bb 100644
--- a/security/selinux/ss/services.c
+++ b/security/selinux/ss/services.c
@@ -2329,7 +2329,7 @@ out:
  */
 int security_fs_use(
 	const char *fstype,
-	unsigned int *behavior,
+	short unsigned int *behavior,
 	u32 *sid)
 {
 	int rc = 0;
-- 
cgit v1.2.3


From 308ab70c465d97cf7e3168961dfd365535de21a6 Mon Sep 17 00:00:00 2001
From: Eric Paris <eparis@redhat.com>
Date: Fri, 24 Aug 2012 15:59:21 -0400
Subject: SELinux: do not handle seclabel as a special flag

Instead of having special code around the 'non-mount' seclabel mount option
just handle it like the mount options.

Signed-off-by: Eric Paris <eparis@redhat.com>
---
 security/selinux/hooks.c            | 3 ---
 security/selinux/include/security.h | 2 +-
 2 files changed, 1 insertion(+), 4 deletions(-)

(limited to 'security')

diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c
index ca0a1c671f0e..5596dc51e21b 100644
--- a/security/selinux/hooks.c
+++ b/security/selinux/hooks.c
@@ -474,9 +474,6 @@ static int selinux_get_mnt_opts(const struct super_block *sb,
 			opts->num_mnt_opts++;
 		tmp >>= 1;
 	}
-	/* Check if the Label support flag is set */
-	if (sbsec->flags & SBLABEL_MNT)
-		opts->num_mnt_opts++;
 
 	opts->mnt_opts = kcalloc(opts->num_mnt_opts, sizeof(char *), GFP_ATOMIC);
 	if (!opts->mnt_opts) {
diff --git a/security/selinux/include/security.h b/security/selinux/include/security.h
index 20830be6b61f..1a73fcd51d56 100644
--- a/security/selinux/include/security.h
+++ b/security/selinux/include/security.h
@@ -43,7 +43,7 @@
 #endif
 
 /* Mask for just the mount related flags */
-#define SE_MNTMASK	0x0f
+#define SE_MNTMASK	0x1f
 /* Super block security struct flags for mount options */
 /* BE CAREFUL, these need to be the low order bits for selinux_get_mnt_opts */
 #define CONTEXT_MNT	0x01
-- 
cgit v1.2.3


From a64c54cf0811b8032fdab8c9d52576f0370837fa Mon Sep 17 00:00:00 2001
From: Eric Paris <eparis@redhat.com>
Date: Fri, 24 Aug 2012 15:59:07 -0400
Subject: SELinux: pass a superblock to security_fs_use

Rather than passing pointers to memory locations, strings, and other
stuff just give up on the separation and give security_fs_use the
superblock.  It just makes the code easier to read (even if not easier to
reuse on some other OS)

Signed-off-by: Eric Paris <eparis@redhat.com>
---
 security/selinux/hooks.c            |  2 +-
 security/selinux/include/security.h |  3 +--
 security/selinux/ss/services.c      | 21 +++++++++------------
 3 files changed, 11 insertions(+), 15 deletions(-)

(limited to 'security')

diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c
index 5596dc51e21b..ec15a5694b9e 100644
--- a/security/selinux/hooks.c
+++ b/security/selinux/hooks.c
@@ -677,7 +677,7 @@ static int selinux_set_mnt_opts(struct super_block *sb,
 		sbsec->flags |= SE_SBPROC;
 
 	/* Determine the labeling behavior to use for this filesystem type. */
-	rc = security_fs_use(sb->s_type->name, &sbsec->behavior, &sbsec->sid);
+	rc = security_fs_use(sb);
 	if (rc) {
 		printk(KERN_WARNING "%s: security_fs_use(%s) returned %d\n",
 		       __func__, sb->s_type->name, rc);
diff --git a/security/selinux/include/security.h b/security/selinux/include/security.h
index 1a73fcd51d56..01a0382c43ca 100644
--- a/security/selinux/include/security.h
+++ b/security/selinux/include/security.h
@@ -171,8 +171,7 @@ int security_get_allow_unknown(void);
 #define SECURITY_FS_USE_NONE		5 /* no labeling support */
 #define SECURITY_FS_USE_MNTPOINT	6 /* use mountpoint labeling */
 
-int security_fs_use(const char *fstype, short unsigned int *behavior,
-	u32 *sid);
+int security_fs_use(struct super_block *sb);
 
 int security_genfs_sid(const char *fstype, char *name, u16 sclass,
 	u32 *sid);
diff --git a/security/selinux/ss/services.c b/security/selinux/ss/services.c
index 603c638434bb..a90721771615 100644
--- a/security/selinux/ss/services.c
+++ b/security/selinux/ss/services.c
@@ -2323,17 +2323,14 @@ out:
 
 /**
  * security_fs_use - Determine how to handle labeling for a filesystem.
- * @fstype: filesystem type
- * @behavior: labeling behavior
- * @sid: SID for filesystem (superblock)
+ * @sb: superblock in question
  */
-int security_fs_use(
-	const char *fstype,
-	short unsigned int *behavior,
-	u32 *sid)
+int security_fs_use(struct super_block *sb)
 {
 	int rc = 0;
 	struct ocontext *c;
+	struct superblock_security_struct *sbsec = sb->s_security;
+	const char *fstype = sb->s_type->name;
 
 	read_lock(&policy_rwlock);
 
@@ -2345,21 +2342,21 @@ int security_fs_use(
 	}
 
 	if (c) {
-		*behavior = c->v.behavior;
+		sbsec->behavior = c->v.behavior;
 		if (!c->sid[0]) {
 			rc = sidtab_context_to_sid(&sidtab, &c->context[0],
 						   &c->sid[0]);
 			if (rc)
 				goto out;
 		}
-		*sid = c->sid[0];
+		sbsec->sid = c->sid[0];
 	} else {
-		rc = security_genfs_sid(fstype, "/", SECCLASS_DIR, sid);
+		rc = security_genfs_sid(fstype, "/", SECCLASS_DIR, &sbsec->sid);
 		if (rc) {
-			*behavior = SECURITY_FS_USE_NONE;
+			sbsec->behavior = SECURITY_FS_USE_NONE;
 			rc = 0;
 		} else {
-			*behavior = SECURITY_FS_USE_GENFS;
+			sbsec->behavior = SECURITY_FS_USE_GENFS;
 		}
 	}
 
-- 
cgit v1.2.3


From b43e725d8d386bf2092473953b525aaae71b6c28 Mon Sep 17 00:00:00 2001
From: Eric Paris <eparis@redhat.com>
Date: Wed, 10 Oct 2012 14:27:35 -0400
Subject: SELinux: use a helper function to determine seclabel

Use a helper to determine if a superblock should have the seclabel flag
rather than doing it in the function.  I'm going to use this in the
security server as well.

Signed-off-by: Eric Paris <eparis@redhat.com>
---
 security/selinux/hooks.c | 38 ++++++++++++++++++++++++--------------
 1 file changed, 24 insertions(+), 14 deletions(-)

(limited to 'security')

diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c
index ec15a5694b9e..b222e966babe 100644
--- a/security/selinux/hooks.c
+++ b/security/selinux/hooks.c
@@ -354,6 +354,29 @@ static int may_context_mount_inode_relabel(u32 sid,
 	return rc;
 }
 
+static int selinux_is_sblabel_mnt(struct super_block *sb)
+{
+	struct superblock_security_struct *sbsec = sb->s_security;
+
+	if (sbsec->behavior == SECURITY_FS_USE_XATTR ||
+	    sbsec->behavior == SECURITY_FS_USE_TRANS ||
+	    sbsec->behavior == SECURITY_FS_USE_TASK)
+		return 1;
+
+	/* Special handling for sysfs. Is genfs but also has setxattr handler*/
+	if (strncmp(sb->s_type->name, "sysfs", sizeof("sysfs")) == 0)
+		return 1;
+
+	/*
+	 * Special handling for rootfs. Is genfs but supports
+	 * setting SELinux context on in-core inodes.
+	 */
+	if (strncmp(sb->s_type->name, "rootfs", sizeof("rootfs")) == 0)
+		return 1;
+
+	return 0;
+}
+
 static int sb_finish_set_opts(struct super_block *sb)
 {
 	struct superblock_security_struct *sbsec = sb->s_security;
@@ -396,20 +419,7 @@ static int sb_finish_set_opts(struct super_block *sb)
 		       labeling_behaviors[sbsec->behavior-1]);
 
 	sbsec->flags |= SE_SBINITIALIZED;
-	if (sbsec->behavior == SECURITY_FS_USE_XATTR ||
-	    sbsec->behavior == SECURITY_FS_USE_TRANS ||
-	    sbsec->behavior == SECURITY_FS_USE_TASK)
-		sbsec->flags |= SBLABEL_MNT;
-
-	/* Special handling for sysfs. Is genfs but also has setxattr handler*/
-	if (strncmp(sb->s_type->name, "sysfs", sizeof("sysfs")) == 0)
-		sbsec->flags |= SBLABEL_MNT;
-
-	/*
-	 * Special handling for rootfs. Is genfs but supports
-	 * setting SELinux context on in-core inodes.
-	 */
-	if (strncmp(sb->s_type->name, "rootfs", sizeof("rootfs")) == 0)
+	if (selinux_is_sblabel_mnt(sb))
 		sbsec->flags |= SBLABEL_MNT;
 
 	/* Initialize the root inode. */
-- 
cgit v1.2.3


From b04eea886409de7460b5727b5931fb0bd417275f Mon Sep 17 00:00:00 2001
From: Paul Moore <pmoore@redhat.com>
Date: Tue, 23 Jul 2013 17:38:38 -0400
Subject: selinux: fix problems in netnode when BUG() is compiled out

When the BUG() macro is disabled at compile time it can cause some
problems in the SELinux netnode code: invalid return codes and
uninitialized variables.  This patch fixes this by making sure we take
some corrective action after the BUG() macro.

Reported-by: Geert Uytterhoeven <geert@linux-m68k.org>
Signed-off-by: Paul Moore <pmoore@redhat.com>
Signed-off-by: Eric Paris <eparis@redhat.com>
---
 security/selinux/netnode.c | 2 ++
 1 file changed, 2 insertions(+)

(limited to 'security')

diff --git a/security/selinux/netnode.c b/security/selinux/netnode.c
index c5454c0477c3..03a72c32afd7 100644
--- a/security/selinux/netnode.c
+++ b/security/selinux/netnode.c
@@ -166,6 +166,7 @@ static void sel_netnode_insert(struct sel_netnode *node)
 		break;
 	default:
 		BUG();
+		return;
 	}
 
 	/* we need to impose a limit on the growth of the hash table so check
@@ -225,6 +226,7 @@ static int sel_netnode_sid_slow(void *addr, u16 family, u32 *sid)
 		break;
 	default:
 		BUG();
+		ret = -EINVAL;
 	}
 	if (ret != 0)
 		goto out;
-- 
cgit v1.2.3


From 2be4d74f2fd45460d70d4fe65cc1972ef45bf849 Mon Sep 17 00:00:00 2001
From: Chris PeBenito <cpebenito@tresys.com>
Date: Fri, 3 May 2013 09:05:39 -0400
Subject: Add SELinux policy capability for always checking packet and peer
 classes.

Currently the packet class in SELinux is not checked if there are no
SECMARK rules in the security or mangle netfilter tables.  Some systems
prefer that packets are always checked, for example, to protect the system
should the netfilter rules fail to load or if the nefilter rules
were maliciously flushed.

Add the always_check_network policy capability which, when enabled, treats
SECMARK as enabled, even if there are no netfilter SECMARK rules and
treats peer labeling as enabled, even if there is no Netlabel or
labeled IPSEC configuration.

Includes definition of "redhat1" SELinux policy capability, which
exists in the SELinux userpace library, to keep ordering correct.

The SELinux userpace portion of this was merged last year, but this kernel
change fell on the floor.

Signed-off-by: Chris PeBenito <cpebenito@tresys.com>
Signed-off-by: Eric Paris <eparis@redhat.com>
---
 security/selinux/hooks.c            | 26 +++++++++++++++++++++-----
 security/selinux/include/security.h |  3 +++
 security/selinux/selinuxfs.c        |  4 +++-
 security/selinux/ss/services.c      |  3 +++
 4 files changed, 30 insertions(+), 6 deletions(-)

(limited to 'security')

diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c
index b222e966babe..4fbf2c5f26ce 100644
--- a/security/selinux/hooks.c
+++ b/security/selinux/hooks.c
@@ -136,12 +136,28 @@ static struct kmem_cache *sel_inode_cache;
  * This function checks the SECMARK reference counter to see if any SECMARK
  * targets are currently configured, if the reference counter is greater than
  * zero SECMARK is considered to be enabled.  Returns true (1) if SECMARK is
- * enabled, false (0) if SECMARK is disabled.
+ * enabled, false (0) if SECMARK is disabled.  If the always_check_network
+ * policy capability is enabled, SECMARK is always considered enabled.
  *
  */
 static int selinux_secmark_enabled(void)
 {
-	return (atomic_read(&selinux_secmark_refcount) > 0);
+	return (selinux_policycap_alwaysnetwork || atomic_read(&selinux_secmark_refcount));
+}
+
+/**
+ * selinux_peerlbl_enabled - Check to see if peer labeling is currently enabled
+ *
+ * Description:
+ * This function checks if NetLabel or labeled IPSEC is enabled.  Returns true
+ * (1) if any are enabled or false (0) if neither are enabled.  If the
+ * always_check_network policy capability is enabled, peer labeling
+ * is always considered enabled.
+ *
+ */
+static int selinux_peerlbl_enabled(void)
+{
+	return (selinux_policycap_alwaysnetwork || netlbl_enabled() || selinux_xfrm_enabled());
 }
 
 /*
@@ -4197,7 +4213,7 @@ static int selinux_socket_sock_rcv_skb(struct sock *sk, struct sk_buff *skb)
 		return selinux_sock_rcv_skb_compat(sk, skb, family);
 
 	secmark_active = selinux_secmark_enabled();
-	peerlbl_active = netlbl_enabled() || selinux_xfrm_enabled();
+	peerlbl_active = selinux_peerlbl_enabled();
 	if (!secmark_active && !peerlbl_active)
 		return 0;
 
@@ -4579,7 +4595,7 @@ static unsigned int selinux_ip_forward(struct sk_buff *skb, int ifindex,
 
 	secmark_active = selinux_secmark_enabled();
 	netlbl_active = netlbl_enabled();
-	peerlbl_active = netlbl_active || selinux_xfrm_enabled();
+	peerlbl_active = selinux_peerlbl_enabled();
 	if (!secmark_active && !peerlbl_active)
 		return NF_ACCEPT;
 
@@ -4731,7 +4747,7 @@ static unsigned int selinux_ip_postroute(struct sk_buff *skb, int ifindex,
 		return NF_ACCEPT;
 #endif
 	secmark_active = selinux_secmark_enabled();
-	peerlbl_active = netlbl_enabled() || selinux_xfrm_enabled();
+	peerlbl_active = selinux_peerlbl_enabled();
 	if (!secmark_active && !peerlbl_active)
 		return NF_ACCEPT;
 
diff --git a/security/selinux/include/security.h b/security/selinux/include/security.h
index 01a0382c43ca..004a2479880f 100644
--- a/security/selinux/include/security.h
+++ b/security/selinux/include/security.h
@@ -69,12 +69,15 @@ extern int selinux_enabled;
 enum {
 	POLICYDB_CAPABILITY_NETPEER,
 	POLICYDB_CAPABILITY_OPENPERM,
+	POLICYDB_CAPABILITY_REDHAT1,
+	POLICYDB_CAPABILITY_ALWAYSNETWORK,
 	__POLICYDB_CAPABILITY_MAX
 };
 #define POLICYDB_CAPABILITY_MAX (__POLICYDB_CAPABILITY_MAX - 1)
 
 extern int selinux_policycap_netpeer;
 extern int selinux_policycap_openperm;
+extern int selinux_policycap_alwaysnetwork;
 
 /*
  * type_datum properties
diff --git a/security/selinux/selinuxfs.c b/security/selinux/selinuxfs.c
index ff427733c290..5122affe06a8 100644
--- a/security/selinux/selinuxfs.c
+++ b/security/selinux/selinuxfs.c
@@ -44,7 +44,9 @@
 /* Policy capability filenames */
 static char *policycap_names[] = {
 	"network_peer_controls",
-	"open_perms"
+	"open_perms",
+	"redhat1",
+	"always_check_network"
 };
 
 unsigned int selinux_checkreqprot = CONFIG_SECURITY_SELINUX_CHECKREQPROT_VALUE;
diff --git a/security/selinux/ss/services.c b/security/selinux/ss/services.c
index a90721771615..d106733ad987 100644
--- a/security/selinux/ss/services.c
+++ b/security/selinux/ss/services.c
@@ -72,6 +72,7 @@
 
 int selinux_policycap_netpeer;
 int selinux_policycap_openperm;
+int selinux_policycap_alwaysnetwork;
 
 static DEFINE_RWLOCK(policy_rwlock);
 
@@ -1812,6 +1813,8 @@ static void security_load_policycaps(void)
 						  POLICYDB_CAPABILITY_NETPEER);
 	selinux_policycap_openperm = ebitmap_get_bit(&policydb.policycaps,
 						  POLICYDB_CAPABILITY_OPENPERM);
+	selinux_policycap_alwaysnetwork = ebitmap_get_bit(&policydb.policycaps,
+						  POLICYDB_CAPABILITY_ALWAYSNETWORK);
 }
 
 static int security_preserve_bools(struct policydb *p);
-- 
cgit v1.2.3


From 102aefdda4d8275ce7d7100bc16c88c74272b260 Mon Sep 17 00:00:00 2001
From: Anand Avati <avati@redhat.com>
Date: Tue, 16 Apr 2013 18:56:19 -0400
Subject: selinux: consider filesystem subtype in policies

Not considering sub filesystem has the following limitation. Support
for SELinux in FUSE is dependent on the particular userspace
filesystem, which is identified by the subtype. For e.g, GlusterFS,
a FUSE based filesystem supports SELinux (by mounting and processing
FUSE requests in different threads, avoiding the mount time
deadlock), whereas other FUSE based filesystems (identified by a
different subtype) have the mount time deadlock.

By considering the subtype of the filesytem in the SELinux policies,
allows us to specify a filesystem subtype, in the following way:

fs_use_xattr fuse.glusterfs gen_context(system_u:object_r:fs_t,s0);

This way not all FUSE filesystems are put in the same bucket and
subjected to the limitations of the other subtypes.

Signed-off-by: Anand Avati <avati@redhat.com>
Signed-off-by: Eric Paris <eparis@redhat.com>
---
 security/selinux/hooks.c       | 40 ++++++++++++++++++++++------------------
 security/selinux/ss/services.c | 42 ++++++++++++++++++++++++++++++++++++++----
 2 files changed, 60 insertions(+), 22 deletions(-)

(limited to 'security')

diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c
index 4fbf2c5f26ce..0d4408debb45 100644
--- a/security/selinux/hooks.c
+++ b/security/selinux/hooks.c
@@ -94,6 +94,10 @@
 #include "audit.h"
 #include "avc_ss.h"
 
+#define SB_TYPE_FMT "%s%s%s"
+#define SB_SUBTYPE(sb) (sb->s_subtype && sb->s_subtype[0])
+#define SB_TYPE_ARGS(sb) sb->s_type->name, SB_SUBTYPE(sb) ? "." : "", SB_SUBTYPE(sb) ? sb->s_subtype : ""
+
 extern struct security_operations *security_ops;
 
 /* SECMARK reference count */
@@ -407,8 +411,8 @@ static int sb_finish_set_opts(struct super_block *sb)
 		   the first boot of the SELinux kernel before we have
 		   assigned xattr values to the filesystem. */
 		if (!root_inode->i_op->getxattr) {
-			printk(KERN_WARNING "SELinux: (dev %s, type %s) has no "
-			       "xattr support\n", sb->s_id, sb->s_type->name);
+			printk(KERN_WARNING "SELinux: (dev %s, type "SB_TYPE_FMT") has no "
+			       "xattr support\n", sb->s_id, SB_TYPE_ARGS(sb));
 			rc = -EOPNOTSUPP;
 			goto out;
 		}
@@ -416,22 +420,22 @@ static int sb_finish_set_opts(struct super_block *sb)
 		if (rc < 0 && rc != -ENODATA) {
 			if (rc == -EOPNOTSUPP)
 				printk(KERN_WARNING "SELinux: (dev %s, type "
-				       "%s) has no security xattr handler\n",
-				       sb->s_id, sb->s_type->name);
+				       SB_TYPE_FMT") has no security xattr handler\n",
+				       sb->s_id, SB_TYPE_ARGS(sb));
 			else
 				printk(KERN_WARNING "SELinux: (dev %s, type "
-				       "%s) getxattr errno %d\n", sb->s_id,
-				       sb->s_type->name, -rc);
+				       SB_TYPE_FMT") getxattr errno %d\n", sb->s_id,
+				       SB_TYPE_ARGS(sb), -rc);
 			goto out;
 		}
 	}
 
 	if (sbsec->behavior > ARRAY_SIZE(labeling_behaviors))
-		printk(KERN_ERR "SELinux: initialized (dev %s, type %s), unknown behavior\n",
-		       sb->s_id, sb->s_type->name);
+		printk(KERN_ERR "SELinux: initialized (dev %s, type "SB_TYPE_FMT"), unknown behavior\n",
+		       sb->s_id, SB_TYPE_ARGS(sb));
 	else
-		printk(KERN_DEBUG "SELinux: initialized (dev %s, type %s), %s\n",
-		       sb->s_id, sb->s_type->name,
+		printk(KERN_DEBUG "SELinux: initialized (dev %s, type "SB_TYPE_FMT"), %s\n",
+		       sb->s_id, SB_TYPE_ARGS(sb),
 		       labeling_behaviors[sbsec->behavior-1]);
 
 	sbsec->flags |= SE_SBINITIALIZED;
@@ -589,7 +593,6 @@ static int selinux_set_mnt_opts(struct super_block *sb,
 	const struct cred *cred = current_cred();
 	int rc = 0, i;
 	struct superblock_security_struct *sbsec = sb->s_security;
-	const char *name = sb->s_type->name;
 	struct inode *inode = sbsec->sb->s_root->d_inode;
 	struct inode_security_struct *root_isec = inode->i_security;
 	u32 fscontext_sid = 0, context_sid = 0, rootcontext_sid = 0;
@@ -642,8 +645,8 @@ static int selinux_set_mnt_opts(struct super_block *sb,
 					     strlen(mount_options[i]), &sid);
 		if (rc) {
 			printk(KERN_WARNING "SELinux: security_context_to_sid"
-			       "(%s) failed for (dev %s, type %s) errno=%d\n",
-			       mount_options[i], sb->s_id, name, rc);
+			       "(%s) failed for (dev %s, type "SB_TYPE_FMT") errno=%d\n",
+			       mount_options[i], sb->s_id, SB_TYPE_ARGS(sb), rc);
 			goto out;
 		}
 		switch (flags[i]) {
@@ -779,7 +782,8 @@ out:
 out_double_mount:
 	rc = -EINVAL;
 	printk(KERN_WARNING "SELinux: mount invalid.  Same superblock, different "
-	       "security settings for (dev %s, type %s)\n", sb->s_id, name);
+	       "security settings for (dev %s, type "SB_TYPE_FMT")\n", sb->s_id,
+	       SB_TYPE_ARGS(sb));
 	goto out;
 }
 
@@ -2439,8 +2443,8 @@ static int selinux_sb_remount(struct super_block *sb, void *data)
 		rc = security_context_to_sid(mount_options[i], len, &sid);
 		if (rc) {
 			printk(KERN_WARNING "SELinux: security_context_to_sid"
-			       "(%s) failed for (dev %s, type %s) errno=%d\n",
-			       mount_options[i], sb->s_id, sb->s_type->name, rc);
+			       "(%s) failed for (dev %s, type "SB_TYPE_FMT") errno=%d\n",
+			       mount_options[i], sb->s_id, SB_TYPE_ARGS(sb), rc);
 			goto out_free_opts;
 		}
 		rc = -EINVAL;
@@ -2478,8 +2482,8 @@ out_free_secdata:
 	return rc;
 out_bad_option:
 	printk(KERN_WARNING "SELinux: unable to change security options "
-	       "during remount (dev %s, type=%s)\n", sb->s_id,
-	       sb->s_type->name);
+	       "during remount (dev %s, type "SB_TYPE_FMT")\n", sb->s_id,
+	       SB_TYPE_ARGS(sb));
 	goto out_free_opts;
 }
 
diff --git a/security/selinux/ss/services.c b/security/selinux/ss/services.c
index d106733ad987..ee470a0b5c27 100644
--- a/security/selinux/ss/services.c
+++ b/security/selinux/ss/services.c
@@ -2334,16 +2334,50 @@ int security_fs_use(struct super_block *sb)
 	struct ocontext *c;
 	struct superblock_security_struct *sbsec = sb->s_security;
 	const char *fstype = sb->s_type->name;
+	const char *subtype = (sb->s_subtype && sb->s_subtype[0]) ? sb->s_subtype : NULL;
+	struct ocontext *base = NULL;
 
 	read_lock(&policy_rwlock);
 
-	c = policydb.ocontexts[OCON_FSUSE];
-	while (c) {
-		if (strcmp(fstype, c->u.name) == 0)
+	for (c = policydb.ocontexts[OCON_FSUSE]; c; c = c->next) {
+		char *sub;
+		int baselen;
+
+		baselen = strlen(fstype);
+
+		/* if base does not match, this is not the one */
+		if (strncmp(fstype, c->u.name, baselen))
+			continue;
+
+		/* if there is no subtype, this is the one! */
+		if (!subtype)
+			break;
+
+		/* skip past the base in this entry */
+		sub = c->u.name + baselen;
+
+		/* entry is only a base. save it. keep looking for subtype */
+		if (sub[0] == '\0') {
+			base = c;
+			continue;
+		}
+
+		/* entry is not followed by a subtype, so it is not a match */
+		if (sub[0] != '.')
+			continue;
+
+		/* whew, we found a subtype of this fstype */
+		sub++; /* move past '.' */
+
+		/* exact match of fstype AND subtype */
+		if (!strcmp(subtype, sub))
 			break;
-		c = c->next;
 	}
 
+	/* in case we had found an fstype match but no subtype match */
+	if (!c)
+		c = base;
+
 	if (c) {
 		sbsec->behavior = c->v.behavior;
 		if (!c->sid[0]) {
-- 
cgit v1.2.3


From 0b4bdb3573a86a88c829b9e4ad702859eb923e7e Mon Sep 17 00:00:00 2001
From: Eric Paris <eparis@redhat.com>
Date: Wed, 28 Aug 2013 13:32:42 -0400
Subject: Revert "SELinux: do not handle seclabel as a special flag"

This reverts commit 308ab70c465d97cf7e3168961dfd365535de21a6.

It breaks my FC6 test box.  /dev/pts is not mounted.  dmesg says

SELinux: mount invalid.  Same superblock, different security settings
for (dev devpts, type devpts)

Cc: Peter Hurley <peter@hurleysoftware.com>
Cc: Greg KH <greg@kroah.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Eric Paris <eparis@redhat.com>
---
 security/selinux/hooks.c            | 3 +++
 security/selinux/include/security.h | 2 +-
 2 files changed, 4 insertions(+), 1 deletion(-)

(limited to 'security')

diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c
index 0d4408debb45..c156f5eb1aea 100644
--- a/security/selinux/hooks.c
+++ b/security/selinux/hooks.c
@@ -504,6 +504,9 @@ static int selinux_get_mnt_opts(const struct super_block *sb,
 			opts->num_mnt_opts++;
 		tmp >>= 1;
 	}
+	/* Check if the Label support flag is set */
+	if (sbsec->flags & SBLABEL_MNT)
+		opts->num_mnt_opts++;
 
 	opts->mnt_opts = kcalloc(opts->num_mnt_opts, sizeof(char *), GFP_ATOMIC);
 	if (!opts->mnt_opts) {
diff --git a/security/selinux/include/security.h b/security/selinux/include/security.h
index 004a2479880f..7aad3a1389d1 100644
--- a/security/selinux/include/security.h
+++ b/security/selinux/include/security.h
@@ -43,7 +43,7 @@
 #endif
 
 /* Mask for just the mount related flags */
-#define SE_MNTMASK	0x1f
+#define SE_MNTMASK	0x0f
 /* Super block security struct flags for mount options */
 /* BE CAREFUL, these need to be the low order bits for selinux_get_mnt_opts */
 #define CONTEXT_MNT	0x01
-- 
cgit v1.2.3


From a3c9e45d18ace44d02574518144742a00c7a94ec Mon Sep 17 00:00:00 2001
From: Eric Paris <eparis@redhat.com>
Date: Tue, 10 Sep 2013 09:51:50 -0400
Subject: security: remove erroneous comment about capabilities.o link ordering

Back when we had half ass LSM stacking we had to link capabilities.o
after bigger LSMs so that on initialization the bigger LSM would
register first and the capabilities module would be the one stacked as
the 'seconday'.  Somewhere around 6f0f0fd496333777d53 (back in 2008) we
finally removed the last of the kinda module stacking code but this
comment in the makefile still lives today.

Reported-by: Valdis Kletnieks <Valdis.Kletnieks@vt.edu>
Signed-off-by: Eric Paris <eparis@redhat.com>
Signed-off-by: James Morris <james.l.morris@oracle.com>
---
 security/Makefile | 1 -
 1 file changed, 1 deletion(-)

(limited to 'security')

diff --git a/security/Makefile b/security/Makefile
index c26c81e92571..a5918e01a4f7 100644
--- a/security/Makefile
+++ b/security/Makefile
@@ -16,7 +16,6 @@ obj-$(CONFIG_MMU)			+= min_addr.o
 # Object file lists
 obj-$(CONFIG_SECURITY)			+= security.o capability.o
 obj-$(CONFIG_SECURITYFS)		+= inode.o
-# Must precede capability.o in order to stack properly.
 obj-$(CONFIG_SECURITY_SELINUX)		+= selinux/built-in.o
 obj-$(CONFIG_SECURITY_SMACK)		+= smack/built-in.o
 obj-$(CONFIG_AUDIT)			+= lsm_audit.o
-- 
cgit v1.2.3


From 61ea0c0ba904a55f55317d850c1072ff7835ac92 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Tue, 24 Sep 2013 10:35:13 +0100
Subject: KEYS: Skip key state checks when checking for possession

Skip key state checks (invalidation, revocation and expiration) when checking
for possession.  Without this, keys that have been marked invalid, revoked
keys and expired keys are not given a possession attribute - which means the
possessor is not granted any possession permits and cannot do anything with
them unless they also have one a user, group or other permit.

This causes failures in the keyutils test suite's revocation and expiration
tests now that commit 96b5c8fea6c0861621051290d705ec2e971963f1 reduced the
initial permissions granted to a key.

The failures are due to accesses to revoked and expired keys being given
EACCES instead of EKEYREVOKED or EKEYEXPIRED.

Signed-off-by: David Howells <dhowells@redhat.com>
---
 security/keys/internal.h         | 1 +
 security/keys/process_keys.c     | 8 +++++---
 security/keys/request_key.c      | 6 ++++--
 security/keys/request_key_auth.c | 2 +-
 4 files changed, 11 insertions(+), 6 deletions(-)

(limited to 'security')

diff --git a/security/keys/internal.h b/security/keys/internal.h
index d4f1468b9b50..df971feceaf2 100644
--- a/security/keys/internal.h
+++ b/security/keys/internal.h
@@ -124,6 +124,7 @@ extern key_ref_t search_my_process_keyrings(struct key_type *type,
 extern key_ref_t search_process_keyrings(struct key_type *type,
 					 const void *description,
 					 key_match_func_t match,
+					 bool no_state_check,
 					 const struct cred *cred);
 
 extern struct key *find_keyring_by_name(const char *name, bool skip_perm_check);
diff --git a/security/keys/process_keys.c b/security/keys/process_keys.c
index 42defae1e161..a3410d605849 100644
--- a/security/keys/process_keys.c
+++ b/security/keys/process_keys.c
@@ -440,6 +440,7 @@ found:
 key_ref_t search_process_keyrings(struct key_type *type,
 				  const void *description,
 				  key_match_func_t match,
+				  bool no_state_check,
 				  const struct cred *cred)
 {
 	struct request_key_auth *rka;
@@ -448,7 +449,7 @@ key_ref_t search_process_keyrings(struct key_type *type,
 	might_sleep();
 
 	key_ref = search_my_process_keyrings(type, description, match,
-					     false, cred);
+					     no_state_check, cred);
 	if (!IS_ERR(key_ref))
 		goto found;
 	err = key_ref;
@@ -468,7 +469,8 @@ key_ref_t search_process_keyrings(struct key_type *type,
 			rka = cred->request_key_auth->payload.data;
 
 			key_ref = search_process_keyrings(type, description,
-							  match, rka->cred);
+							  match, no_state_check,
+							  rka->cred);
 
 			up_read(&cred->request_key_auth->sem);
 
@@ -675,7 +677,7 @@ try_again:
 		/* check to see if we possess the key */
 		skey_ref = search_process_keyrings(key->type, key,
 						   lookup_user_key_possessed,
-						   cred);
+						   true, cred);
 
 		if (!IS_ERR(skey_ref)) {
 			key_put(key);
diff --git a/security/keys/request_key.c b/security/keys/request_key.c
index c411f9bb156b..172115b38054 100644
--- a/security/keys/request_key.c
+++ b/security/keys/request_key.c
@@ -390,7 +390,8 @@ static int construct_alloc_key(struct key_type *type,
 	 * waited for locks */
 	mutex_lock(&key_construction_mutex);
 
-	key_ref = search_process_keyrings(type, description, type->match, cred);
+	key_ref = search_process_keyrings(type, description, type->match,
+					  false, cred);
 	if (!IS_ERR(key_ref))
 		goto key_already_present;
 
@@ -539,7 +540,8 @@ struct key *request_key_and_link(struct key_type *type,
 	       dest_keyring, flags);
 
 	/* search all the process keyrings for a key */
-	key_ref = search_process_keyrings(type, description, type->match, cred);
+	key_ref = search_process_keyrings(type, description, type->match,
+					  false, cred);
 
 	if (!IS_ERR(key_ref)) {
 		key = key_ref_to_ptr(key_ref);
diff --git a/security/keys/request_key_auth.c b/security/keys/request_key_auth.c
index 85730d5a5a59..92077de555df 100644
--- a/security/keys/request_key_auth.c
+++ b/security/keys/request_key_auth.c
@@ -247,7 +247,7 @@ struct key *key_get_instantiation_authkey(key_serial_t target_id)
 		&key_type_request_key_auth,
 		(void *) (unsigned long) target_id,
 		key_get_instantiation_authkey_match,
-		cred);
+		false, cred);
 
 	if (IS_ERR(authkey_ref)) {
 		authkey = ERR_CAST(authkey_ref);
-- 
cgit v1.2.3


From a5b4bd2874d9032b42db8cc4880058576c561b06 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Tue, 24 Sep 2013 10:35:14 +0100
Subject: KEYS: Use bool in make_key_ref() and is_key_possessed()

Make make_key_ref() take a bool possession parameter and make
is_key_possessed() return a bool.

Signed-off-by: David Howells <dhowells@redhat.com>
---
 Documentation/security/keys.txt | 7 +++----
 include/linux/key.h             | 4 ++--
 security/keys/keyring.c         | 5 +++--
 3 files changed, 8 insertions(+), 8 deletions(-)

(limited to 'security')

diff --git a/Documentation/security/keys.txt b/Documentation/security/keys.txt
index 7b4145d00452..9ede67084f0b 100644
--- a/Documentation/security/keys.txt
+++ b/Documentation/security/keys.txt
@@ -865,15 +865,14 @@ encountered:
      calling processes has a searchable link to the key from one of its
      keyrings. There are three functions for dealing with these:
 
-	key_ref_t make_key_ref(const struct key *key,
-			       unsigned long possession);
+	key_ref_t make_key_ref(const struct key *key, bool possession);
 
 	struct key *key_ref_to_ptr(const key_ref_t key_ref);
 
-	unsigned long is_key_possessed(const key_ref_t key_ref);
+	bool is_key_possessed(const key_ref_t key_ref);
 
      The first function constructs a key reference from a key pointer and
-     possession information (which must be 0 or 1 and not any other value).
+     possession information (which must be true or false).
 
      The second function retrieves the key pointer from a reference and the
      third retrieves the possession flag.
diff --git a/include/linux/key.h b/include/linux/key.h
index 4dfde1161c5e..51bce2950de4 100644
--- a/include/linux/key.h
+++ b/include/linux/key.h
@@ -99,7 +99,7 @@ struct keyring_name;
 typedef struct __key_reference_with_attributes *key_ref_t;
 
 static inline key_ref_t make_key_ref(const struct key *key,
-				     unsigned long possession)
+				     bool possession)
 {
 	return (key_ref_t) ((unsigned long) key | possession);
 }
@@ -109,7 +109,7 @@ static inline struct key *key_ref_to_ptr(const key_ref_t key_ref)
 	return (struct key *) ((unsigned long) key_ref & ~1UL);
 }
 
-static inline unsigned long is_key_possessed(const key_ref_t key_ref)
+static inline bool is_key_possessed(const key_ref_t key_ref)
 {
 	return (unsigned long) key_ref & 1UL;
 }
diff --git a/security/keys/keyring.c b/security/keys/keyring.c
index 6ece7f2e5707..f78406372ebe 100644
--- a/security/keys/keyring.c
+++ b/security/keys/keyring.c
@@ -329,9 +329,10 @@ key_ref_t keyring_search_aux(key_ref_t keyring_ref,
 
 	struct keyring_list *keylist;
 	struct timespec now;
-	unsigned long possessed, kflags;
+	unsigned long kflags;
 	struct key *keyring, *key;
 	key_ref_t key_ref;
+	bool possessed;
 	long err;
 	int sp, nkeys, kix;
 
@@ -542,8 +543,8 @@ key_ref_t __keyring_search_one(key_ref_t keyring_ref,
 			       key_perm_t perm)
 {
 	struct keyring_list *klist;
-	unsigned long possessed;
 	struct key *keyring, *key;
+	bool possessed;
 	int nkeys, loop;
 
 	keyring = key_ref_to_ptr(keyring_ref);
-- 
cgit v1.2.3


From 7e55ca6dcd07b45619035df343c9614a3ab35034 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Tue, 24 Sep 2013 10:35:14 +0100
Subject: KEYS: key_is_dead() should take a const key pointer argument

key_is_dead() should take a const key pointer argument as it doesn't modify
what it points to.

Signed-off-by: David Howells <dhowells@redhat.com>
---
 security/keys/internal.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'security')

diff --git a/security/keys/internal.h b/security/keys/internal.h
index df971feceaf2..490aef5ba34b 100644
--- a/security/keys/internal.h
+++ b/security/keys/internal.h
@@ -203,7 +203,7 @@ extern struct key *key_get_instantiation_authkey(key_serial_t target_id);
 /*
  * Determine whether a key is dead.
  */
-static inline bool key_is_dead(struct key *key, time_t limit)
+static inline bool key_is_dead(const struct key *key, time_t limit)
 {
 	return
 		key->flags & ((1 << KEY_FLAG_DEAD) |
-- 
cgit v1.2.3


From 16feef4340172b7dbb9cba60850e78fa6388adf1 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Tue, 24 Sep 2013 10:35:15 +0100
Subject: KEYS: Consolidate the concept of an 'index key' for key access

Consolidate the concept of an 'index key' for accessing keys.  The index key
is the search term needed to find a key directly - basically the key type and
the key description.  We can add to that the description length.

This will be useful when turning a keyring into an associative array rather
than just a pointer block.

Signed-off-by: David Howells <dhowells@redhat.com>
---
 include/linux/key.h         | 21 +++++++++----
 security/keys/internal.h    |  8 ++---
 security/keys/key.c         | 72 +++++++++++++++++++++++----------------------
 security/keys/keyring.c     | 37 +++++++++++------------
 security/keys/request_key.c | 12 +++++---
 5 files changed, 83 insertions(+), 67 deletions(-)

(limited to 'security')

diff --git a/include/linux/key.h b/include/linux/key.h
index 51bce2950de4..d573e820a23d 100644
--- a/include/linux/key.h
+++ b/include/linux/key.h
@@ -82,6 +82,12 @@ struct key_owner;
 struct keyring_list;
 struct keyring_name;
 
+struct keyring_index_key {
+	struct key_type		*type;
+	const char		*description;
+	size_t			desc_len;
+};
+
 /*****************************************************************************/
 /*
  * key reference with possession attribute handling
@@ -129,7 +135,6 @@ struct key {
 		struct list_head graveyard_link;
 		struct rb_node	serial_node;
 	};
-	struct key_type		*type;		/* type of key */
 	struct rw_semaphore	sem;		/* change vs change sem */
 	struct key_user		*user;		/* owner of this key */
 	void			*security;	/* security data for this key */
@@ -163,12 +168,18 @@ struct key {
 #define KEY_FLAG_ROOT_CAN_CLEAR	6	/* set if key can be cleared by root without permission */
 #define KEY_FLAG_INVALIDATED	7	/* set if key has been invalidated */
 
-	/* the description string
-	 * - this is used to match a key against search criteria
-	 * - this should be a printable string
+	/* the key type and key description string
+	 * - the desc is used to match a key against search criteria
+	 * - it should be a printable string
 	 * - eg: for krb5 AFS, this might be "afs@REDHAT.COM"
 	 */
-	char			*description;
+	union {
+		struct keyring_index_key index_key;
+		struct {
+			struct key_type	*type;		/* type of key */
+			char		*description;
+		};
+	};
 
 	/* type specific data
 	 * - this is used by the keyring type to index the name
diff --git a/security/keys/internal.h b/security/keys/internal.h
index 490aef5ba34b..77441dd1f9d4 100644
--- a/security/keys/internal.h
+++ b/security/keys/internal.h
@@ -89,19 +89,17 @@ extern struct key_type *key_type_lookup(const char *type);
 extern void key_type_put(struct key_type *ktype);
 
 extern int __key_link_begin(struct key *keyring,
-			    const struct key_type *type,
-			    const char *description,
+			    const struct keyring_index_key *index_key,
 			    unsigned long *_prealloc);
 extern int __key_link_check_live_key(struct key *keyring, struct key *key);
 extern void __key_link(struct key *keyring, struct key *key,
 		       unsigned long *_prealloc);
 extern void __key_link_end(struct key *keyring,
-			   struct key_type *type,
+			   const struct keyring_index_key *index_key,
 			   unsigned long prealloc);
 
 extern key_ref_t __keyring_search_one(key_ref_t keyring_ref,
-				      const struct key_type *type,
-				      const char *description,
+				      const struct keyring_index_key *index_key,
 				      key_perm_t perm);
 
 extern struct key *keyring_search_instkey(struct key *keyring,
diff --git a/security/keys/key.c b/security/keys/key.c
index 8fb7c7bd4657..7e6bc396bb23 100644
--- a/security/keys/key.c
+++ b/security/keys/key.c
@@ -242,8 +242,8 @@ struct key *key_alloc(struct key_type *type, const char *desc,
 		}
 	}
 
-	desclen = strlen(desc) + 1;
-	quotalen = desclen + type->def_datalen;
+	desclen = strlen(desc);
+	quotalen = desclen + 1 + type->def_datalen;
 
 	/* get hold of the key tracking for this user */
 	user = key_user_lookup(uid);
@@ -277,7 +277,8 @@ struct key *key_alloc(struct key_type *type, const char *desc,
 		goto no_memory_2;
 
 	if (desc) {
-		key->description = kmemdup(desc, desclen, GFP_KERNEL);
+		key->index_key.desc_len = desclen;
+		key->index_key.description = kmemdup(desc, desclen + 1, GFP_KERNEL);
 		if (!key->description)
 			goto no_memory_3;
 	}
@@ -285,7 +286,7 @@ struct key *key_alloc(struct key_type *type, const char *desc,
 	atomic_set(&key->usage, 1);
 	init_rwsem(&key->sem);
 	lockdep_set_class(&key->sem, &type->lock_class);
-	key->type = type;
+	key->index_key.type = type;
 	key->user = user;
 	key->quotalen = quotalen;
 	key->datalen = type->def_datalen;
@@ -489,8 +490,7 @@ int key_instantiate_and_link(struct key *key,
 	}
 
 	if (keyring) {
-		ret = __key_link_begin(keyring, key->type, key->description,
-				       &prealloc);
+		ret = __key_link_begin(keyring, &key->index_key, &prealloc);
 		if (ret < 0)
 			goto error_free_preparse;
 	}
@@ -499,7 +499,7 @@ int key_instantiate_and_link(struct key *key,
 					 &prealloc);
 
 	if (keyring)
-		__key_link_end(keyring, key->type, prealloc);
+		__key_link_end(keyring, &key->index_key, prealloc);
 
 error_free_preparse:
 	if (key->type->preparse)
@@ -548,8 +548,7 @@ int key_reject_and_link(struct key *key,
 	ret = -EBUSY;
 
 	if (keyring)
-		link_ret = __key_link_begin(keyring, key->type,
-					    key->description, &prealloc);
+		link_ret = __key_link_begin(keyring, &key->index_key, &prealloc);
 
 	mutex_lock(&key_construction_mutex);
 
@@ -581,7 +580,7 @@ int key_reject_and_link(struct key *key,
 	mutex_unlock(&key_construction_mutex);
 
 	if (keyring)
-		__key_link_end(keyring, key->type, prealloc);
+		__key_link_end(keyring, &key->index_key, prealloc);
 
 	/* wake up anyone waiting for a key to be constructed */
 	if (awaken)
@@ -780,25 +779,27 @@ key_ref_t key_create_or_update(key_ref_t keyring_ref,
 			       key_perm_t perm,
 			       unsigned long flags)
 {
-	unsigned long prealloc;
+	struct keyring_index_key index_key = {
+		.description	= description,
+	};
 	struct key_preparsed_payload prep;
 	const struct cred *cred = current_cred();
-	struct key_type *ktype;
+	unsigned long prealloc;
 	struct key *keyring, *key = NULL;
 	key_ref_t key_ref;
 	int ret;
 
 	/* look up the key type to see if it's one of the registered kernel
 	 * types */
-	ktype = key_type_lookup(type);
-	if (IS_ERR(ktype)) {
+	index_key.type = key_type_lookup(type);
+	if (IS_ERR(index_key.type)) {
 		key_ref = ERR_PTR(-ENODEV);
 		goto error;
 	}
 
 	key_ref = ERR_PTR(-EINVAL);
-	if (!ktype->match || !ktype->instantiate ||
-	    (!description && !ktype->preparse))
+	if (!index_key.type->match || !index_key.type->instantiate ||
+	    (!index_key.description && !index_key.type->preparse))
 		goto error_put_type;
 
 	keyring = key_ref_to_ptr(keyring_ref);
@@ -812,21 +813,22 @@ key_ref_t key_create_or_update(key_ref_t keyring_ref,
 	memset(&prep, 0, sizeof(prep));
 	prep.data = payload;
 	prep.datalen = plen;
-	prep.quotalen = ktype->def_datalen;
-	if (ktype->preparse) {
-		ret = ktype->preparse(&prep);
+	prep.quotalen = index_key.type->def_datalen;
+	if (index_key.type->preparse) {
+		ret = index_key.type->preparse(&prep);
 		if (ret < 0) {
 			key_ref = ERR_PTR(ret);
 			goto error_put_type;
 		}
-		if (!description)
-			description = prep.description;
+		if (!index_key.description)
+			index_key.description = prep.description;
 		key_ref = ERR_PTR(-EINVAL);
-		if (!description)
+		if (!index_key.description)
 			goto error_free_prep;
 	}
+	index_key.desc_len = strlen(index_key.description);
 
-	ret = __key_link_begin(keyring, ktype, description, &prealloc);
+	ret = __key_link_begin(keyring, &index_key, &prealloc);
 	if (ret < 0) {
 		key_ref = ERR_PTR(ret);
 		goto error_free_prep;
@@ -844,9 +846,8 @@ key_ref_t key_create_or_update(key_ref_t keyring_ref,
 	 * key of the same type and description in the destination keyring and
 	 * update that instead if possible
 	 */
-	if (ktype->update) {
-		key_ref = __keyring_search_one(keyring_ref, ktype, description,
-					       0);
+	if (index_key.type->update) {
+		key_ref = __keyring_search_one(keyring_ref, &index_key, 0);
 		if (!IS_ERR(key_ref))
 			goto found_matching_key;
 	}
@@ -856,16 +857,17 @@ key_ref_t key_create_or_update(key_ref_t keyring_ref,
 		perm = KEY_POS_VIEW | KEY_POS_SEARCH | KEY_POS_LINK | KEY_POS_SETATTR;
 		perm |= KEY_USR_VIEW;
 
-		if (ktype->read)
+		if (index_key.type->read)
 			perm |= KEY_POS_READ;
 
-		if (ktype == &key_type_keyring || ktype->update)
+		if (index_key.type == &key_type_keyring ||
+		    index_key.type->update)
 			perm |= KEY_POS_WRITE;
 	}
 
 	/* allocate a new key */
-	key = key_alloc(ktype, description, cred->fsuid, cred->fsgid, cred,
-			perm, flags);
+	key = key_alloc(index_key.type, index_key.description,
+			cred->fsuid, cred->fsgid, cred, perm, flags);
 	if (IS_ERR(key)) {
 		key_ref = ERR_CAST(key);
 		goto error_link_end;
@@ -882,12 +884,12 @@ key_ref_t key_create_or_update(key_ref_t keyring_ref,
 	key_ref = make_key_ref(key, is_key_possessed(keyring_ref));
 
 error_link_end:
-	__key_link_end(keyring, ktype, prealloc);
+	__key_link_end(keyring, &index_key, prealloc);
 error_free_prep:
-	if (ktype->preparse)
-		ktype->free_preparse(&prep);
+	if (index_key.type->preparse)
+		index_key.type->free_preparse(&prep);
 error_put_type:
-	key_type_put(ktype);
+	key_type_put(index_key.type);
 error:
 	return key_ref;
 
@@ -895,7 +897,7 @@ error:
 	/* we found a matching key, so we're going to try to update it
 	 * - we can drop the locks first as we have the key pinned
 	 */
-	__key_link_end(keyring, ktype, prealloc);
+	__key_link_end(keyring, &index_key, prealloc);
 
 	key_ref = __key_update(key_ref, &prep);
 	goto error_free_prep;
diff --git a/security/keys/keyring.c b/security/keys/keyring.c
index f78406372ebe..c7f59f9dd7b6 100644
--- a/security/keys/keyring.c
+++ b/security/keys/keyring.c
@@ -538,8 +538,7 @@ EXPORT_SYMBOL(keyring_search);
  * to the returned key reference.
  */
 key_ref_t __keyring_search_one(key_ref_t keyring_ref,
-			       const struct key_type *ktype,
-			       const char *description,
+			       const struct keyring_index_key *index_key,
 			       key_perm_t perm)
 {
 	struct keyring_list *klist;
@@ -558,9 +557,9 @@ key_ref_t __keyring_search_one(key_ref_t keyring_ref,
 		smp_rmb();
 		for (loop = 0; loop < nkeys ; loop++) {
 			key = rcu_dereference(klist->keys[loop]);
-			if (key->type == ktype &&
+			if (key->type == index_key->type &&
 			    (!key->type->match ||
-			     key->type->match(key, description)) &&
+			     key->type->match(key, index_key->description)) &&
 			    key_permission(make_key_ref(key, possessed),
 					   perm) == 0 &&
 			    !(key->flags & ((1 << KEY_FLAG_INVALIDATED) |
@@ -747,8 +746,8 @@ static void keyring_unlink_rcu_disposal(struct rcu_head *rcu)
 /*
  * Preallocate memory so that a key can be linked into to a keyring.
  */
-int __key_link_begin(struct key *keyring, const struct key_type *type,
-		     const char *description, unsigned long *_prealloc)
+int __key_link_begin(struct key *keyring, const struct keyring_index_key *index_key,
+		     unsigned long *_prealloc)
 	__acquires(&keyring->sem)
 	__acquires(&keyring_serialise_link_sem)
 {
@@ -759,7 +758,8 @@ int __key_link_begin(struct key *keyring, const struct key_type *type,
 	size_t size;
 	int loop, lru, ret;
 
-	kenter("%d,%s,%s,", key_serial(keyring), type->name, description);
+	kenter("%d,%s,%s,",
+	       key_serial(keyring), index_key->type->name, index_key->description);
 
 	if (keyring->type != &key_type_keyring)
 		return -ENOTDIR;
@@ -772,7 +772,7 @@ int __key_link_begin(struct key *keyring, const struct key_type *type,
 
 	/* serialise link/link calls to prevent parallel calls causing a cycle
 	 * when linking two keyring in opposite orders */
-	if (type == &key_type_keyring)
+	if (index_key->type == &key_type_keyring)
 		down_write(&keyring_serialise_link_sem);
 
 	klist = rcu_dereference_locked_keyring(keyring);
@@ -784,8 +784,8 @@ int __key_link_begin(struct key *keyring, const struct key_type *type,
 		for (loop = klist->nkeys - 1; loop >= 0; loop--) {
 			struct key *key = rcu_deref_link_locked(klist, loop,
 								keyring);
-			if (key->type == type &&
-			    strcmp(key->description, description) == 0) {
+			if (key->type == index_key->type &&
+			    strcmp(key->description, index_key->description) == 0) {
 				/* Found a match - we'll replace the link with
 				 * one to the new key.  We record the slot
 				 * position.
@@ -865,7 +865,7 @@ error_quota:
 	key_payload_reserve(keyring,
 			    keyring->datalen - KEYQUOTA_LINK_BYTES);
 error_sem:
-	if (type == &key_type_keyring)
+	if (index_key->type == &key_type_keyring)
 		up_write(&keyring_serialise_link_sem);
 error_krsem:
 	up_write(&keyring->sem);
@@ -957,16 +957,17 @@ void __key_link(struct key *keyring, struct key *key,
  *
  * Must be called with __key_link_begin() having being called.
  */
-void __key_link_end(struct key *keyring, struct key_type *type,
+void __key_link_end(struct key *keyring,
+		    const struct keyring_index_key *index_key,
 		    unsigned long prealloc)
 	__releases(&keyring->sem)
 	__releases(&keyring_serialise_link_sem)
 {
-	BUG_ON(type == NULL);
-	BUG_ON(type->name == NULL);
-	kenter("%d,%s,%lx", keyring->serial, type->name, prealloc);
+	BUG_ON(index_key->type == NULL);
+	BUG_ON(index_key->type->name == NULL);
+	kenter("%d,%s,%lx", keyring->serial, index_key->type->name, prealloc);
 
-	if (type == &key_type_keyring)
+	if (index_key->type == &key_type_keyring)
 		up_write(&keyring_serialise_link_sem);
 
 	if (prealloc) {
@@ -1007,12 +1008,12 @@ int key_link(struct key *keyring, struct key *key)
 	key_check(keyring);
 	key_check(key);
 
-	ret = __key_link_begin(keyring, key->type, key->description, &prealloc);
+	ret = __key_link_begin(keyring, &key->index_key, &prealloc);
 	if (ret == 0) {
 		ret = __key_link_check_live_key(keyring, key);
 		if (ret == 0)
 			__key_link(keyring, key, &prealloc);
-		__key_link_end(keyring, key->type, prealloc);
+		__key_link_end(keyring, &key->index_key, prealloc);
 	}
 
 	return ret;
diff --git a/security/keys/request_key.c b/security/keys/request_key.c
index 172115b38054..586cb79ee82d 100644
--- a/security/keys/request_key.c
+++ b/security/keys/request_key.c
@@ -352,6 +352,11 @@ static int construct_alloc_key(struct key_type *type,
 			       struct key_user *user,
 			       struct key **_key)
 {
+	const struct keyring_index_key index_key = {
+		.type		= type,
+		.description	= description,
+		.desc_len	= strlen(description),
+	};
 	const struct cred *cred = current_cred();
 	unsigned long prealloc;
 	struct key *key;
@@ -379,8 +384,7 @@ static int construct_alloc_key(struct key_type *type,
 	set_bit(KEY_FLAG_USER_CONSTRUCT, &key->flags);
 
 	if (dest_keyring) {
-		ret = __key_link_begin(dest_keyring, type, description,
-				       &prealloc);
+		ret = __key_link_begin(dest_keyring, &index_key, &prealloc);
 		if (ret < 0)
 			goto link_prealloc_failed;
 	}
@@ -400,7 +404,7 @@ static int construct_alloc_key(struct key_type *type,
 
 	mutex_unlock(&key_construction_mutex);
 	if (dest_keyring)
-		__key_link_end(dest_keyring, type, prealloc);
+		__key_link_end(dest_keyring, &index_key, prealloc);
 	mutex_unlock(&user->cons_lock);
 	*_key = key;
 	kleave(" = 0 [%d]", key_serial(key));
@@ -416,7 +420,7 @@ key_already_present:
 		ret = __key_link_check_live_key(dest_keyring, key);
 		if (ret == 0)
 			__key_link(dest_keyring, key, &prealloc);
-		__key_link_end(dest_keyring, type, prealloc);
+		__key_link_end(dest_keyring, &index_key, prealloc);
 		if (ret < 0)
 			goto link_check_failed;
 	}
-- 
cgit v1.2.3


From 4bdf0bc300314141e5475e145acb8b5ad846f00d Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Tue, 24 Sep 2013 10:35:15 +0100
Subject: KEYS: Introduce a search context structure

Search functions pass around a bunch of arguments, each of which gets copied
with each call.  Introduce a search context structure to hold these.

Whilst we're at it, create a search flag that indicates whether the search
should be directly to the description or whether it should iterate through all
keys looking for a non-description match.

This will be useful when keyrings use a generic data struct with generic
routines to manage their content as the search terms can just be passed
through to the iterator callback function.

Also, for future use, the data to be supplied to the match function is
separated from the description pointer in the search context.  This makes it
clear which is being supplied.

Signed-off-by: David Howells <dhowells@redhat.com>
---
 include/linux/key-type.h         |   5 ++
 security/keys/internal.h         |  40 +++++++------
 security/keys/keyring.c          |  70 +++++++++++------------
 security/keys/proc.c             |  17 ++++--
 security/keys/process_keys.c     | 117 +++++++++++++++++++--------------------
 security/keys/request_key.c      |  56 +++++++++----------
 security/keys/request_key_auth.c |  14 +++--
 security/keys/user_defined.c     |  18 +++---
 8 files changed, 179 insertions(+), 158 deletions(-)

(limited to 'security')

diff --git a/include/linux/key-type.h b/include/linux/key-type.h
index 518a53afb9ea..f58737bcb050 100644
--- a/include/linux/key-type.h
+++ b/include/linux/key-type.h
@@ -63,6 +63,11 @@ struct key_type {
 	 */
 	size_t def_datalen;
 
+	/* Default key search algorithm. */
+	unsigned def_lookup_type;
+#define KEYRING_SEARCH_LOOKUP_DIRECT	0x0000	/* Direct lookup by description. */
+#define KEYRING_SEARCH_LOOKUP_ITERATE	0x0001	/* Iterative search. */
+
 	/* vet a description */
 	int (*vet_description)(const char *description);
 
diff --git a/security/keys/internal.h b/security/keys/internal.h
index 77441dd1f9d4..f4bf938b68b4 100644
--- a/security/keys/internal.h
+++ b/security/keys/internal.h
@@ -107,23 +107,31 @@ extern struct key *keyring_search_instkey(struct key *keyring,
 
 typedef int (*key_match_func_t)(const struct key *, const void *);
 
+struct keyring_search_context {
+	struct keyring_index_key index_key;
+	const struct cred	*cred;
+	key_match_func_t	match;
+	const void		*match_data;
+	unsigned		flags;
+#define KEYRING_SEARCH_LOOKUP_TYPE	0x0001	/* [as type->def_lookup_type] */
+#define KEYRING_SEARCH_NO_STATE_CHECK	0x0002	/* Skip state checks */
+#define KEYRING_SEARCH_DO_STATE_CHECK	0x0004	/* Override NO_STATE_CHECK */
+#define KEYRING_SEARCH_NO_UPDATE_TIME	0x0008	/* Don't update times */
+#define KEYRING_SEARCH_NO_CHECK_PERM	0x0010	/* Don't check permissions */
+#define KEYRING_SEARCH_DETECT_TOO_DEEP	0x0020	/* Give an error on excessive depth */
+
+	/* Internal stuff */
+	int			skipped_ret;
+	bool			possessed;
+	key_ref_t		result;
+	struct timespec		now;
+};
+
 extern key_ref_t keyring_search_aux(key_ref_t keyring_ref,
-				    const struct cred *cred,
-				    struct key_type *type,
-				    const void *description,
-				    key_match_func_t match,
-				    bool no_state_check);
-
-extern key_ref_t search_my_process_keyrings(struct key_type *type,
-					    const void *description,
-					    key_match_func_t match,
-					    bool no_state_check,
-					    const struct cred *cred);
-extern key_ref_t search_process_keyrings(struct key_type *type,
-					 const void *description,
-					 key_match_func_t match,
-					 bool no_state_check,
-					 const struct cred *cred);
+				    struct keyring_search_context *ctx);
+
+extern key_ref_t search_my_process_keyrings(struct keyring_search_context *ctx);
+extern key_ref_t search_process_keyrings(struct keyring_search_context *ctx);
 
 extern struct key *find_keyring_by_name(const char *name, bool skip_perm_check);
 
diff --git a/security/keys/keyring.c b/security/keys/keyring.c
index c7f59f9dd7b6..b42f2d4f7f83 100644
--- a/security/keys/keyring.c
+++ b/security/keys/keyring.c
@@ -280,11 +280,7 @@ EXPORT_SYMBOL(keyring_alloc);
 /**
  * keyring_search_aux - Search a keyring tree for a key matching some criteria
  * @keyring_ref: A pointer to the keyring with possession indicator.
- * @cred: The credentials to use for permissions checks.
- * @type: The type of key to search for.
- * @description: Parameter for @match.
- * @match: Function to rule on whether or not a key is the one required.
- * @no_state_check: Don't check if a matching key is bad
+ * @ctx: The keyring search context.
  *
  * Search the supplied keyring tree for a key that matches the criteria given.
  * The root keyring and any linked keyrings must grant Search permission to the
@@ -314,11 +310,7 @@ EXPORT_SYMBOL(keyring_alloc);
  * @keyring_ref is propagated to the returned key reference.
  */
 key_ref_t keyring_search_aux(key_ref_t keyring_ref,
-			     const struct cred *cred,
-			     struct key_type *type,
-			     const void *description,
-			     key_match_func_t match,
-			     bool no_state_check)
+			     struct keyring_search_context *ctx)
 {
 	struct {
 		/* Need a separate keylist pointer for RCU purposes */
@@ -328,20 +320,18 @@ key_ref_t keyring_search_aux(key_ref_t keyring_ref,
 	} stack[KEYRING_SEARCH_MAX_DEPTH];
 
 	struct keyring_list *keylist;
-	struct timespec now;
 	unsigned long kflags;
 	struct key *keyring, *key;
 	key_ref_t key_ref;
-	bool possessed;
 	long err;
 	int sp, nkeys, kix;
 
 	keyring = key_ref_to_ptr(keyring_ref);
-	possessed = is_key_possessed(keyring_ref);
+	ctx->possessed = is_key_possessed(keyring_ref);
 	key_check(keyring);
 
 	/* top keyring must have search permission to begin the search */
-	err = key_task_permission(keyring_ref, cred, KEY_SEARCH);
+	err = key_task_permission(keyring_ref, ctx->cred, KEY_SEARCH);
 	if (err < 0) {
 		key_ref = ERR_PTR(err);
 		goto error;
@@ -353,7 +343,7 @@ key_ref_t keyring_search_aux(key_ref_t keyring_ref,
 
 	rcu_read_lock();
 
-	now = current_kernel_time();
+	ctx->now = current_kernel_time();
 	err = -EAGAIN;
 	sp = 0;
 
@@ -361,16 +351,17 @@ key_ref_t keyring_search_aux(key_ref_t keyring_ref,
 	 * are looking for */
 	key_ref = ERR_PTR(-EAGAIN);
 	kflags = keyring->flags;
-	if (keyring->type == type && match(keyring, description)) {
+	if (keyring->type == ctx->index_key.type &&
+	    ctx->match(keyring, ctx->match_data)) {
 		key = keyring;
-		if (no_state_check)
+		if (ctx->flags & KEYRING_SEARCH_NO_STATE_CHECK)
 			goto found;
 
 		/* check it isn't negative and hasn't expired or been
 		 * revoked */
 		if (kflags & (1 << KEY_FLAG_REVOKED))
 			goto error_2;
-		if (key->expiry && now.tv_sec >= key->expiry)
+		if (key->expiry && ctx->now.tv_sec >= key->expiry)
 			goto error_2;
 		key_ref = ERR_PTR(key->type_data.reject_error);
 		if (kflags & (1 << KEY_FLAG_NEGATIVE))
@@ -384,7 +375,7 @@ key_ref_t keyring_search_aux(key_ref_t keyring_ref,
 	if (kflags & ((1 << KEY_FLAG_INVALIDATED) |
 		      (1 << KEY_FLAG_REVOKED) |
 		      (1 << KEY_FLAG_NEGATIVE)) ||
-	    (keyring->expiry && now.tv_sec >= keyring->expiry))
+	    (keyring->expiry && ctx->now.tv_sec >= keyring->expiry))
 		goto error_2;
 
 	/* start processing a new keyring */
@@ -406,29 +397,29 @@ descend:
 		kflags = key->flags;
 
 		/* ignore keys not of this type */
-		if (key->type != type)
+		if (key->type != ctx->index_key.type)
 			continue;
 
 		/* skip invalidated, revoked and expired keys */
-		if (!no_state_check) {
+		if (!(ctx->flags & KEYRING_SEARCH_NO_STATE_CHECK)) {
 			if (kflags & ((1 << KEY_FLAG_INVALIDATED) |
 				      (1 << KEY_FLAG_REVOKED)))
 				continue;
 
-			if (key->expiry && now.tv_sec >= key->expiry)
+			if (key->expiry && ctx->now.tv_sec >= key->expiry)
 				continue;
 		}
 
 		/* keys that don't match */
-		if (!match(key, description))
+		if (!ctx->match(key, ctx->match_data))
 			continue;
 
 		/* key must have search permissions */
-		if (key_task_permission(make_key_ref(key, possessed),
-					cred, KEY_SEARCH) < 0)
+		if (key_task_permission(make_key_ref(key, ctx->possessed),
+					ctx->cred, KEY_SEARCH) < 0)
 			continue;
 
-		if (no_state_check)
+		if (ctx->flags & KEYRING_SEARCH_NO_STATE_CHECK)
 			goto found;
 
 		/* we set a different error code if we pass a negative key */
@@ -456,8 +447,8 @@ ascend:
 		if (sp >= KEYRING_SEARCH_MAX_DEPTH)
 			continue;
 
-		if (key_task_permission(make_key_ref(key, possessed),
-					cred, KEY_SEARCH) < 0)
+		if (key_task_permission(make_key_ref(key, ctx->possessed),
+					ctx->cred, KEY_SEARCH) < 0)
 			continue;
 
 		/* stack the current position */
@@ -489,12 +480,12 @@ not_this_keyring:
 	/* we found a viable match */
 found:
 	atomic_inc(&key->usage);
-	key->last_used_at = now.tv_sec;
-	keyring->last_used_at = now.tv_sec;
+	key->last_used_at = ctx->now.tv_sec;
+	keyring->last_used_at = ctx->now.tv_sec;
 	while (sp > 0)
-		stack[--sp].keyring->last_used_at = now.tv_sec;
+		stack[--sp].keyring->last_used_at = ctx->now.tv_sec;
 	key_check(key);
-	key_ref = make_key_ref(key, possessed);
+	key_ref = make_key_ref(key, ctx->possessed);
 error_2:
 	rcu_read_unlock();
 error:
@@ -514,11 +505,20 @@ key_ref_t keyring_search(key_ref_t keyring,
 			 struct key_type *type,
 			 const char *description)
 {
-	if (!type->match)
+	struct keyring_search_context ctx = {
+		.index_key.type		= type,
+		.index_key.description	= description,
+		.cred			= current_cred(),
+		.match			= type->match,
+		.match_data		= description,
+		.flags			= (type->def_lookup_type |
+					   KEYRING_SEARCH_DO_STATE_CHECK),
+	};
+
+	if (!ctx.match)
 		return ERR_PTR(-ENOKEY);
 
-	return keyring_search_aux(keyring, current->cred,
-				  type, description, type->match, false);
+	return keyring_search_aux(keyring, &ctx);
 }
 EXPORT_SYMBOL(keyring_search);
 
diff --git a/security/keys/proc.c b/security/keys/proc.c
index 217b6855e815..88e9a466940f 100644
--- a/security/keys/proc.c
+++ b/security/keys/proc.c
@@ -182,7 +182,6 @@ static void proc_keys_stop(struct seq_file *p, void *v)
 
 static int proc_keys_show(struct seq_file *m, void *v)
 {
-	const struct cred *cred = current_cred();
 	struct rb_node *_p = v;
 	struct key *key = rb_entry(_p, struct key, serial_node);
 	struct timespec now;
@@ -191,15 +190,23 @@ static int proc_keys_show(struct seq_file *m, void *v)
 	char xbuf[12];
 	int rc;
 
+	struct keyring_search_context ctx = {
+		.index_key.type		= key->type,
+		.index_key.description	= key->description,
+		.cred			= current_cred(),
+		.match			= lookup_user_key_possessed,
+		.match_data		= key,
+		.flags			= (KEYRING_SEARCH_NO_STATE_CHECK |
+					   KEYRING_SEARCH_LOOKUP_DIRECT),
+	};
+
 	key_ref = make_key_ref(key, 0);
 
 	/* determine if the key is possessed by this process (a test we can
 	 * skip if the key does not indicate the possessor can view it
 	 */
 	if (key->perm & KEY_POS_VIEW) {
-		skey_ref = search_my_process_keyrings(key->type, key,
-						      lookup_user_key_possessed,
-						      true, cred);
+		skey_ref = search_my_process_keyrings(&ctx);
 		if (!IS_ERR(skey_ref)) {
 			key_ref_put(skey_ref);
 			key_ref = make_key_ref(key, 1);
@@ -211,7 +218,7 @@ static int proc_keys_show(struct seq_file *m, void *v)
 	 * - the caller holds a spinlock, and thus the RCU read lock, making our
 	 *   access to __current_cred() safe
 	 */
-	rc = key_task_permission(key_ref, cred, KEY_VIEW);
+	rc = key_task_permission(key_ref, ctx.cred, KEY_VIEW);
 	if (rc < 0)
 		return 0;
 
diff --git a/security/keys/process_keys.c b/security/keys/process_keys.c
index a3410d605849..e68a3e0e7aa0 100644
--- a/security/keys/process_keys.c
+++ b/security/keys/process_keys.c
@@ -319,11 +319,7 @@ void key_fsgid_changed(struct task_struct *tsk)
  * In the case of a successful return, the possession attribute is set on the
  * returned key reference.
  */
-key_ref_t search_my_process_keyrings(struct key_type *type,
-				     const void *description,
-				     key_match_func_t match,
-				     bool no_state_check,
-				     const struct cred *cred)
+key_ref_t search_my_process_keyrings(struct keyring_search_context *ctx)
 {
 	key_ref_t key_ref, ret, err;
 
@@ -339,10 +335,9 @@ key_ref_t search_my_process_keyrings(struct key_type *type,
 	err = ERR_PTR(-EAGAIN);
 
 	/* search the thread keyring first */
-	if (cred->thread_keyring) {
+	if (ctx->cred->thread_keyring) {
 		key_ref = keyring_search_aux(
-			make_key_ref(cred->thread_keyring, 1),
-			cred, type, description, match, no_state_check);
+			make_key_ref(ctx->cred->thread_keyring, 1), ctx);
 		if (!IS_ERR(key_ref))
 			goto found;
 
@@ -358,10 +353,9 @@ key_ref_t search_my_process_keyrings(struct key_type *type,
 	}
 
 	/* search the process keyring second */
-	if (cred->process_keyring) {
+	if (ctx->cred->process_keyring) {
 		key_ref = keyring_search_aux(
-			make_key_ref(cred->process_keyring, 1),
-			cred, type, description, match, no_state_check);
+			make_key_ref(ctx->cred->process_keyring, 1), ctx);
 		if (!IS_ERR(key_ref))
 			goto found;
 
@@ -379,11 +373,11 @@ key_ref_t search_my_process_keyrings(struct key_type *type,
 	}
 
 	/* search the session keyring */
-	if (cred->session_keyring) {
+	if (ctx->cred->session_keyring) {
 		rcu_read_lock();
 		key_ref = keyring_search_aux(
-			make_key_ref(rcu_dereference(cred->session_keyring), 1),
-			cred, type, description, match, no_state_check);
+			make_key_ref(rcu_dereference(ctx->cred->session_keyring), 1),
+			ctx);
 		rcu_read_unlock();
 
 		if (!IS_ERR(key_ref))
@@ -402,10 +396,10 @@ key_ref_t search_my_process_keyrings(struct key_type *type,
 		}
 	}
 	/* or search the user-session keyring */
-	else if (cred->user->session_keyring) {
+	else if (ctx->cred->user->session_keyring) {
 		key_ref = keyring_search_aux(
-			make_key_ref(cred->user->session_keyring, 1),
-			cred, type, description, match, no_state_check);
+			make_key_ref(ctx->cred->user->session_keyring, 1),
+			ctx);
 		if (!IS_ERR(key_ref))
 			goto found;
 
@@ -437,19 +431,14 @@ found:
  *
  * Return same as search_my_process_keyrings().
  */
-key_ref_t search_process_keyrings(struct key_type *type,
-				  const void *description,
-				  key_match_func_t match,
-				  bool no_state_check,
-				  const struct cred *cred)
+key_ref_t search_process_keyrings(struct keyring_search_context *ctx)
 {
 	struct request_key_auth *rka;
 	key_ref_t key_ref, ret = ERR_PTR(-EACCES), err;
 
 	might_sleep();
 
-	key_ref = search_my_process_keyrings(type, description, match,
-					     no_state_check, cred);
+	key_ref = search_my_process_keyrings(ctx);
 	if (!IS_ERR(key_ref))
 		goto found;
 	err = key_ref;
@@ -458,19 +447,21 @@ key_ref_t search_process_keyrings(struct key_type *type,
 	 * search the keyrings of the process mentioned there
 	 * - we don't permit access to request_key auth keys via this method
 	 */
-	if (cred->request_key_auth &&
-	    cred == current_cred() &&
-	    type != &key_type_request_key_auth
+	if (ctx->cred->request_key_auth &&
+	    ctx->cred == current_cred() &&
+	    ctx->index_key.type != &key_type_request_key_auth
 	    ) {
+		const struct cred *cred = ctx->cred;
+
 		/* defend against the auth key being revoked */
 		down_read(&cred->request_key_auth->sem);
 
-		if (key_validate(cred->request_key_auth) == 0) {
-			rka = cred->request_key_auth->payload.data;
+		if (key_validate(ctx->cred->request_key_auth) == 0) {
+			rka = ctx->cred->request_key_auth->payload.data;
 
-			key_ref = search_process_keyrings(type, description,
-							  match, no_state_check,
-							  rka->cred);
+			ctx->cred = rka->cred;
+			key_ref = search_process_keyrings(ctx);
+			ctx->cred = cred;
 
 			up_read(&cred->request_key_auth->sem);
 
@@ -524,19 +515,23 @@ int lookup_user_key_possessed(const struct key *key, const void *target)
 key_ref_t lookup_user_key(key_serial_t id, unsigned long lflags,
 			  key_perm_t perm)
 {
+	struct keyring_search_context ctx = {
+		.match	= lookup_user_key_possessed,
+		.flags	= (KEYRING_SEARCH_NO_STATE_CHECK |
+			   KEYRING_SEARCH_LOOKUP_DIRECT),
+	};
 	struct request_key_auth *rka;
-	const struct cred *cred;
 	struct key *key;
 	key_ref_t key_ref, skey_ref;
 	int ret;
 
 try_again:
-	cred = get_current_cred();
+	ctx.cred = get_current_cred();
 	key_ref = ERR_PTR(-ENOKEY);
 
 	switch (id) {
 	case KEY_SPEC_THREAD_KEYRING:
-		if (!cred->thread_keyring) {
+		if (!ctx.cred->thread_keyring) {
 			if (!(lflags & KEY_LOOKUP_CREATE))
 				goto error;
 
@@ -548,13 +543,13 @@ try_again:
 			goto reget_creds;
 		}
 
-		key = cred->thread_keyring;
+		key = ctx.cred->thread_keyring;
 		atomic_inc(&key->usage);
 		key_ref = make_key_ref(key, 1);
 		break;
 
 	case KEY_SPEC_PROCESS_KEYRING:
-		if (!cred->process_keyring) {
+		if (!ctx.cred->process_keyring) {
 			if (!(lflags & KEY_LOOKUP_CREATE))
 				goto error;
 
@@ -566,13 +561,13 @@ try_again:
 			goto reget_creds;
 		}
 
-		key = cred->process_keyring;
+		key = ctx.cred->process_keyring;
 		atomic_inc(&key->usage);
 		key_ref = make_key_ref(key, 1);
 		break;
 
 	case KEY_SPEC_SESSION_KEYRING:
-		if (!cred->session_keyring) {
+		if (!ctx.cred->session_keyring) {
 			/* always install a session keyring upon access if one
 			 * doesn't exist yet */
 			ret = install_user_keyrings();
@@ -582,13 +577,13 @@ try_again:
 				ret = join_session_keyring(NULL);
 			else
 				ret = install_session_keyring(
-					cred->user->session_keyring);
+					ctx.cred->user->session_keyring);
 
 			if (ret < 0)
 				goto error;
 			goto reget_creds;
-		} else if (cred->session_keyring ==
-			   cred->user->session_keyring &&
+		} else if (ctx.cred->session_keyring ==
+			   ctx.cred->user->session_keyring &&
 			   lflags & KEY_LOOKUP_CREATE) {
 			ret = join_session_keyring(NULL);
 			if (ret < 0)
@@ -597,32 +592,32 @@ try_again:
 		}
 
 		rcu_read_lock();
-		key = rcu_dereference(cred->session_keyring);
+		key = rcu_dereference(ctx.cred->session_keyring);
 		atomic_inc(&key->usage);
 		rcu_read_unlock();
 		key_ref = make_key_ref(key, 1);
 		break;
 
 	case KEY_SPEC_USER_KEYRING:
-		if (!cred->user->uid_keyring) {
+		if (!ctx.cred->user->uid_keyring) {
 			ret = install_user_keyrings();
 			if (ret < 0)
 				goto error;
 		}
 
-		key = cred->user->uid_keyring;
+		key = ctx.cred->user->uid_keyring;
 		atomic_inc(&key->usage);
 		key_ref = make_key_ref(key, 1);
 		break;
 
 	case KEY_SPEC_USER_SESSION_KEYRING:
-		if (!cred->user->session_keyring) {
+		if (!ctx.cred->user->session_keyring) {
 			ret = install_user_keyrings();
 			if (ret < 0)
 				goto error;
 		}
 
-		key = cred->user->session_keyring;
+		key = ctx.cred->user->session_keyring;
 		atomic_inc(&key->usage);
 		key_ref = make_key_ref(key, 1);
 		break;
@@ -633,7 +628,7 @@ try_again:
 		goto error;
 
 	case KEY_SPEC_REQKEY_AUTH_KEY:
-		key = cred->request_key_auth;
+		key = ctx.cred->request_key_auth;
 		if (!key)
 			goto error;
 
@@ -642,20 +637,20 @@ try_again:
 		break;
 
 	case KEY_SPEC_REQUESTOR_KEYRING:
-		if (!cred->request_key_auth)
+		if (!ctx.cred->request_key_auth)
 			goto error;
 
-		down_read(&cred->request_key_auth->sem);
+		down_read(&ctx.cred->request_key_auth->sem);
 		if (test_bit(KEY_FLAG_REVOKED,
-			     &cred->request_key_auth->flags)) {
+			     &ctx.cred->request_key_auth->flags)) {
 			key_ref = ERR_PTR(-EKEYREVOKED);
 			key = NULL;
 		} else {
-			rka = cred->request_key_auth->payload.data;
+			rka = ctx.cred->request_key_auth->payload.data;
 			key = rka->dest_keyring;
 			atomic_inc(&key->usage);
 		}
-		up_read(&cred->request_key_auth->sem);
+		up_read(&ctx.cred->request_key_auth->sem);
 		if (!key)
 			goto error;
 		key_ref = make_key_ref(key, 1);
@@ -675,9 +670,13 @@ try_again:
 		key_ref = make_key_ref(key, 0);
 
 		/* check to see if we possess the key */
-		skey_ref = search_process_keyrings(key->type, key,
-						   lookup_user_key_possessed,
-						   true, cred);
+		ctx.index_key.type		= key->type;
+		ctx.index_key.description	= key->description;
+		ctx.index_key.desc_len		= strlen(key->description);
+		ctx.match_data			= key;
+		kdebug("check possessed");
+		skey_ref = search_process_keyrings(&ctx);
+		kdebug("possessed=%p", skey_ref);
 
 		if (!IS_ERR(skey_ref)) {
 			key_put(key);
@@ -717,14 +716,14 @@ try_again:
 		goto invalid_key;
 
 	/* check the permissions */
-	ret = key_task_permission(key_ref, cred, perm);
+	ret = key_task_permission(key_ref, ctx.cred, perm);
 	if (ret < 0)
 		goto invalid_key;
 
 	key->last_used_at = current_kernel_time().tv_sec;
 
 error:
-	put_cred(cred);
+	put_cred(ctx.cred);
 	return key_ref;
 
 invalid_key:
@@ -735,7 +734,7 @@ invalid_key:
 	/* if we attempted to install a keyring, then it may have caused new
 	 * creds to be installed */
 reget_creds:
-	put_cred(cred);
+	put_cred(ctx.cred);
 	goto try_again;
 }
 
diff --git a/security/keys/request_key.c b/security/keys/request_key.c
index 586cb79ee82d..ab75df4745af 100644
--- a/security/keys/request_key.c
+++ b/security/keys/request_key.c
@@ -345,38 +345,34 @@ static void construct_get_dest_keyring(struct key **_dest_keyring)
  * May return a key that's already under construction instead if there was a
  * race between two thread calling request_key().
  */
-static int construct_alloc_key(struct key_type *type,
-			       const char *description,
+static int construct_alloc_key(struct keyring_search_context *ctx,
 			       struct key *dest_keyring,
 			       unsigned long flags,
 			       struct key_user *user,
 			       struct key **_key)
 {
-	const struct keyring_index_key index_key = {
-		.type		= type,
-		.description	= description,
-		.desc_len	= strlen(description),
-	};
-	const struct cred *cred = current_cred();
 	unsigned long prealloc;
 	struct key *key;
 	key_perm_t perm;
 	key_ref_t key_ref;
 	int ret;
 
-	kenter("%s,%s,,,", type->name, description);
+	kenter("%s,%s,,,",
+	       ctx->index_key.type->name, ctx->index_key.description);
 
 	*_key = NULL;
 	mutex_lock(&user->cons_lock);
 
 	perm = KEY_POS_VIEW | KEY_POS_SEARCH | KEY_POS_LINK | KEY_POS_SETATTR;
 	perm |= KEY_USR_VIEW;
-	if (type->read)
+	if (ctx->index_key.type->read)
 		perm |= KEY_POS_READ;
-	if (type == &key_type_keyring || type->update)
+	if (ctx->index_key.type == &key_type_keyring ||
+	    ctx->index_key.type->update)
 		perm |= KEY_POS_WRITE;
 
-	key = key_alloc(type, description, cred->fsuid, cred->fsgid, cred,
+	key = key_alloc(ctx->index_key.type, ctx->index_key.description,
+			ctx->cred->fsuid, ctx->cred->fsgid, ctx->cred,
 			perm, flags);
 	if (IS_ERR(key))
 		goto alloc_failed;
@@ -384,7 +380,7 @@ static int construct_alloc_key(struct key_type *type,
 	set_bit(KEY_FLAG_USER_CONSTRUCT, &key->flags);
 
 	if (dest_keyring) {
-		ret = __key_link_begin(dest_keyring, &index_key, &prealloc);
+		ret = __key_link_begin(dest_keyring, &ctx->index_key, &prealloc);
 		if (ret < 0)
 			goto link_prealloc_failed;
 	}
@@ -394,8 +390,7 @@ static int construct_alloc_key(struct key_type *type,
 	 * waited for locks */
 	mutex_lock(&key_construction_mutex);
 
-	key_ref = search_process_keyrings(type, description, type->match,
-					  false, cred);
+	key_ref = search_process_keyrings(ctx);
 	if (!IS_ERR(key_ref))
 		goto key_already_present;
 
@@ -404,7 +399,7 @@ static int construct_alloc_key(struct key_type *type,
 
 	mutex_unlock(&key_construction_mutex);
 	if (dest_keyring)
-		__key_link_end(dest_keyring, &index_key, prealloc);
+		__key_link_end(dest_keyring, &ctx->index_key, prealloc);
 	mutex_unlock(&user->cons_lock);
 	*_key = key;
 	kleave(" = 0 [%d]", key_serial(key));
@@ -420,7 +415,7 @@ key_already_present:
 		ret = __key_link_check_live_key(dest_keyring, key);
 		if (ret == 0)
 			__key_link(dest_keyring, key, &prealloc);
-		__key_link_end(dest_keyring, &index_key, prealloc);
+		__key_link_end(dest_keyring, &ctx->index_key, prealloc);
 		if (ret < 0)
 			goto link_check_failed;
 	}
@@ -449,8 +444,7 @@ alloc_failed:
 /*
  * Commence key construction.
  */
-static struct key *construct_key_and_link(struct key_type *type,
-					  const char *description,
+static struct key *construct_key_and_link(struct keyring_search_context *ctx,
 					  const char *callout_info,
 					  size_t callout_len,
 					  void *aux,
@@ -469,8 +463,7 @@ static struct key *construct_key_and_link(struct key_type *type,
 
 	construct_get_dest_keyring(&dest_keyring);
 
-	ret = construct_alloc_key(type, description, dest_keyring, flags, user,
-				  &key);
+	ret = construct_alloc_key(ctx, dest_keyring, flags, user, &key);
 	key_user_put(user);
 
 	if (ret == 0) {
@@ -534,18 +527,24 @@ struct key *request_key_and_link(struct key_type *type,
 				 struct key *dest_keyring,
 				 unsigned long flags)
 {
-	const struct cred *cred = current_cred();
+	struct keyring_search_context ctx = {
+		.index_key.type		= type,
+		.index_key.description	= description,
+		.cred			= current_cred(),
+		.match			= type->match,
+		.match_data		= description,
+		.flags			= KEYRING_SEARCH_LOOKUP_DIRECT,
+	};
 	struct key *key;
 	key_ref_t key_ref;
 	int ret;
 
 	kenter("%s,%s,%p,%zu,%p,%p,%lx",
-	       type->name, description, callout_info, callout_len, aux,
-	       dest_keyring, flags);
+	       ctx.index_key.type->name, ctx.index_key.description,
+	       callout_info, callout_len, aux, dest_keyring, flags);
 
 	/* search all the process keyrings for a key */
-	key_ref = search_process_keyrings(type, description, type->match,
-					  false, cred);
+	key_ref = search_process_keyrings(&ctx);
 
 	if (!IS_ERR(key_ref)) {
 		key = key_ref_to_ptr(key_ref);
@@ -568,9 +567,8 @@ struct key *request_key_and_link(struct key_type *type,
 		if (!callout_info)
 			goto error;
 
-		key = construct_key_and_link(type, description, callout_info,
-					     callout_len, aux, dest_keyring,
-					     flags);
+		key = construct_key_and_link(&ctx, callout_info, callout_len,
+					     aux, dest_keyring, flags);
 	}
 
 error:
diff --git a/security/keys/request_key_auth.c b/security/keys/request_key_auth.c
index 92077de555df..8d09852854ca 100644
--- a/security/keys/request_key_auth.c
+++ b/security/keys/request_key_auth.c
@@ -239,15 +239,17 @@ static int key_get_instantiation_authkey_match(const struct key *key,
  */
 struct key *key_get_instantiation_authkey(key_serial_t target_id)
 {
-	const struct cred *cred = current_cred();
+	struct keyring_search_context ctx = {
+		.index_key.type		= &key_type_request_key_auth,
+		.cred			= current_cred(),
+		.match			= key_get_instantiation_authkey_match,
+		.match_data		= (void *)(unsigned long)target_id,
+		.flags			= KEYRING_SEARCH_LOOKUP_DIRECT,
+	};
 	struct key *authkey;
 	key_ref_t authkey_ref;
 
-	authkey_ref = search_process_keyrings(
-		&key_type_request_key_auth,
-		(void *) (unsigned long) target_id,
-		key_get_instantiation_authkey_match,
-		false, cred);
+	authkey_ref = search_process_keyrings(&ctx);
 
 	if (IS_ERR(authkey_ref)) {
 		authkey = ERR_CAST(authkey_ref);
diff --git a/security/keys/user_defined.c b/security/keys/user_defined.c
index 55dc88939185..faa2caeb593f 100644
--- a/security/keys/user_defined.c
+++ b/security/keys/user_defined.c
@@ -25,14 +25,15 @@ static int logon_vet_description(const char *desc);
  * arbitrary blob of data as the payload
  */
 struct key_type key_type_user = {
-	.name		= "user",
-	.instantiate	= user_instantiate,
-	.update		= user_update,
-	.match		= user_match,
-	.revoke		= user_revoke,
-	.destroy	= user_destroy,
-	.describe	= user_describe,
-	.read		= user_read,
+	.name			= "user",
+	.def_lookup_type	= KEYRING_SEARCH_LOOKUP_DIRECT,
+	.instantiate		= user_instantiate,
+	.update			= user_update,
+	.match			= user_match,
+	.revoke			= user_revoke,
+	.destroy		= user_destroy,
+	.describe		= user_describe,
+	.read			= user_read,
 };
 
 EXPORT_SYMBOL_GPL(key_type_user);
@@ -45,6 +46,7 @@ EXPORT_SYMBOL_GPL(key_type_user);
  */
 struct key_type key_type_logon = {
 	.name			= "logon",
+	.def_lookup_type	= KEYRING_SEARCH_LOOKUP_DIRECT,
 	.instantiate		= user_instantiate,
 	.update			= user_update,
 	.match			= user_match,
-- 
cgit v1.2.3


From d0a059cac6523b23ad7d743dec8783705aab1668 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Tue, 24 Sep 2013 10:35:16 +0100
Subject: KEYS: Search for auth-key by name rather than target key ID

Search for auth-key by name rather than by target key ID as, in a future
patch, we'll by searching directly by index key in preference to iteration
over all keys.

Signed-off-by: David Howells <dhowells@redhat.com>
---
 security/keys/request_key_auth.c | 21 +++++++--------------
 1 file changed, 7 insertions(+), 14 deletions(-)

(limited to 'security')

diff --git a/security/keys/request_key_auth.c b/security/keys/request_key_auth.c
index 8d09852854ca..7495a93b4b90 100644
--- a/security/keys/request_key_auth.c
+++ b/security/keys/request_key_auth.c
@@ -18,6 +18,7 @@
 #include <linux/slab.h>
 #include <asm/uaccess.h>
 #include "internal.h"
+#include <keys/user-type.h>
 
 static int request_key_auth_instantiate(struct key *,
 					struct key_preparsed_payload *);
@@ -221,34 +222,26 @@ error_alloc:
 	return ERR_PTR(ret);
 }
 
-/*
- * See if an authorisation key is associated with a particular key.
- */
-static int key_get_instantiation_authkey_match(const struct key *key,
-					       const void *_id)
-{
-	struct request_key_auth *rka = key->payload.data;
-	key_serial_t id = (key_serial_t)(unsigned long) _id;
-
-	return rka->target_key->serial == id;
-}
-
 /*
  * Search the current process's keyrings for the authorisation key for
  * instantiation of a key.
  */
 struct key *key_get_instantiation_authkey(key_serial_t target_id)
 {
+	char description[16];
 	struct keyring_search_context ctx = {
 		.index_key.type		= &key_type_request_key_auth,
+		.index_key.description	= description,
 		.cred			= current_cred(),
-		.match			= key_get_instantiation_authkey_match,
-		.match_data		= (void *)(unsigned long)target_id,
+		.match			= user_match,
+		.match_data		= description,
 		.flags			= KEYRING_SEARCH_LOOKUP_DIRECT,
 	};
 	struct key *authkey;
 	key_ref_t authkey_ref;
 
+	sprintf(description, "%x", target_id);
+
 	authkey_ref = search_process_keyrings(&ctx);
 
 	if (IS_ERR(authkey_ref)) {
-- 
cgit v1.2.3


From ccc3e6d9c9aea07a0b60b2b0bfc5b05a704b66d5 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Tue, 24 Sep 2013 10:35:16 +0100
Subject: KEYS: Define a __key_get() wrapper to use rather than atomic_inc()

Define a __key_get() wrapper to use rather than atomic_inc() on the key usage
count as this makes it easier to hook in refcount error debugging.

Signed-off-by: David Howells <dhowells@redhat.com>
---
 Documentation/security/keys.txt | 13 ++++++++-----
 include/linux/key.h             | 10 +++++++---
 security/keys/key.c             |  2 +-
 security/keys/keyring.c         |  6 +++---
 security/keys/process_keys.c    | 16 ++++++++--------
 5 files changed, 27 insertions(+), 20 deletions(-)

(limited to 'security')

diff --git a/Documentation/security/keys.txt b/Documentation/security/keys.txt
index 9ede67084f0b..a4c33f1a7c6d 100644
--- a/Documentation/security/keys.txt
+++ b/Documentation/security/keys.txt
@@ -960,14 +960,17 @@ payload contents" for more information.
     the argument will not be parsed.
 
 
-(*) Extra references can be made to a key by calling the following function:
+(*) Extra references can be made to a key by calling one of the following
+    functions:
 
+	struct key *__key_get(struct key *key);
 	struct key *key_get(struct key *key);
 
-    These need to be disposed of by calling key_put() when they've been
-    finished with. The key pointer passed in will be returned. If the pointer
-    is NULL or CONFIG_KEYS is not set then the key will not be dereferenced and
-    no increment will take place.
+    Keys so references will need to be disposed of by calling key_put() when
+    they've been finished with.  The key pointer passed in will be returned.
+
+    In the case of key_get(), if the pointer is NULL or CONFIG_KEYS is not set
+    then the key will not be dereferenced and no increment will take place.
 
 
 (*) A key's serial number can be obtained by calling:
diff --git a/include/linux/key.h b/include/linux/key.h
index d573e820a23d..ef596c7af585 100644
--- a/include/linux/key.h
+++ b/include/linux/key.h
@@ -219,13 +219,17 @@ extern void key_revoke(struct key *key);
 extern void key_invalidate(struct key *key);
 extern void key_put(struct key *key);
 
-static inline struct key *key_get(struct key *key)
+static inline struct key *__key_get(struct key *key)
 {
-	if (key)
-		atomic_inc(&key->usage);
+	atomic_inc(&key->usage);
 	return key;
 }
 
+static inline struct key *key_get(struct key *key)
+{
+	return key ? __key_get(key) : key;
+}
+
 static inline void key_ref_put(key_ref_t key_ref)
 {
 	key_put(key_ref_to_ptr(key_ref));
diff --git a/security/keys/key.c b/security/keys/key.c
index 7e6bc396bb23..1e23cc288106 100644
--- a/security/keys/key.c
+++ b/security/keys/key.c
@@ -644,7 +644,7 @@ found:
 	/* this races with key_put(), but that doesn't matter since key_put()
 	 * doesn't actually change the key
 	 */
-	atomic_inc(&key->usage);
+	__key_get(key);
 
 error:
 	spin_unlock(&key_serial_lock);
diff --git a/security/keys/keyring.c b/security/keys/keyring.c
index b42f2d4f7f83..87eff32b53f4 100644
--- a/security/keys/keyring.c
+++ b/security/keys/keyring.c
@@ -479,7 +479,7 @@ not_this_keyring:
 
 	/* we found a viable match */
 found:
-	atomic_inc(&key->usage);
+	__key_get(key);
 	key->last_used_at = ctx->now.tv_sec;
 	keyring->last_used_at = ctx->now.tv_sec;
 	while (sp > 0)
@@ -573,7 +573,7 @@ key_ref_t __keyring_search_one(key_ref_t keyring_ref,
 	return ERR_PTR(-ENOKEY);
 
 found:
-	atomic_inc(&key->usage);
+	__key_get(key);
 	keyring->last_used_at = key->last_used_at =
 		current_kernel_time().tv_sec;
 	rcu_read_unlock();
@@ -909,7 +909,7 @@ void __key_link(struct key *keyring, struct key *key,
 
 	klist = rcu_dereference_locked_keyring(keyring);
 
-	atomic_inc(&key->usage);
+	__key_get(key);
 	keyring->last_used_at = key->last_used_at =
 		current_kernel_time().tv_sec;
 
diff --git a/security/keys/process_keys.c b/security/keys/process_keys.c
index e68a3e0e7aa0..68548ea6fe01 100644
--- a/security/keys/process_keys.c
+++ b/security/keys/process_keys.c
@@ -235,7 +235,7 @@ int install_session_keyring_to_cred(struct cred *cred, struct key *keyring)
 		if (IS_ERR(keyring))
 			return PTR_ERR(keyring);
 	} else {
-		atomic_inc(&keyring->usage);
+		__key_get(keyring);
 	}
 
 	/* install the keyring */
@@ -544,7 +544,7 @@ try_again:
 		}
 
 		key = ctx.cred->thread_keyring;
-		atomic_inc(&key->usage);
+		__key_get(key);
 		key_ref = make_key_ref(key, 1);
 		break;
 
@@ -562,7 +562,7 @@ try_again:
 		}
 
 		key = ctx.cred->process_keyring;
-		atomic_inc(&key->usage);
+		__key_get(key);
 		key_ref = make_key_ref(key, 1);
 		break;
 
@@ -593,7 +593,7 @@ try_again:
 
 		rcu_read_lock();
 		key = rcu_dereference(ctx.cred->session_keyring);
-		atomic_inc(&key->usage);
+		__key_get(key);
 		rcu_read_unlock();
 		key_ref = make_key_ref(key, 1);
 		break;
@@ -606,7 +606,7 @@ try_again:
 		}
 
 		key = ctx.cred->user->uid_keyring;
-		atomic_inc(&key->usage);
+		__key_get(key);
 		key_ref = make_key_ref(key, 1);
 		break;
 
@@ -618,7 +618,7 @@ try_again:
 		}
 
 		key = ctx.cred->user->session_keyring;
-		atomic_inc(&key->usage);
+		__key_get(key);
 		key_ref = make_key_ref(key, 1);
 		break;
 
@@ -632,7 +632,7 @@ try_again:
 		if (!key)
 			goto error;
 
-		atomic_inc(&key->usage);
+		__key_get(key);
 		key_ref = make_key_ref(key, 1);
 		break;
 
@@ -648,7 +648,7 @@ try_again:
 		} else {
 			rka = ctx.cred->request_key_auth->payload.data;
 			key = rka->dest_keyring;
-			atomic_inc(&key->usage);
+			__key_get(key);
 		}
 		up_read(&ctx.cred->request_key_auth->sem);
 		if (!key)
-- 
cgit v1.2.3


From e57e8669f2ab8350d30f771dd2fdd5377f183db2 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Tue, 24 Sep 2013 10:35:17 +0100
Subject: KEYS: Drop the permissions argument from __keyring_search_one()

Drop the permissions argument from __keyring_search_one() as the only caller
passes 0 here - which causes all checks to be skipped.

Signed-off-by: David Howells <dhowells@redhat.com>
---
 security/keys/internal.h | 3 +--
 security/keys/key.c      | 2 +-
 security/keys/keyring.c  | 9 +++------
 3 files changed, 5 insertions(+), 9 deletions(-)

(limited to 'security')

diff --git a/security/keys/internal.h b/security/keys/internal.h
index f4bf938b68b4..73950bf8f875 100644
--- a/security/keys/internal.h
+++ b/security/keys/internal.h
@@ -99,8 +99,7 @@ extern void __key_link_end(struct key *keyring,
 			   unsigned long prealloc);
 
 extern key_ref_t __keyring_search_one(key_ref_t keyring_ref,
-				      const struct keyring_index_key *index_key,
-				      key_perm_t perm);
+				      const struct keyring_index_key *index_key);
 
 extern struct key *keyring_search_instkey(struct key *keyring,
 					  key_serial_t target_id);
diff --git a/security/keys/key.c b/security/keys/key.c
index 1e23cc288106..7d716b82a61e 100644
--- a/security/keys/key.c
+++ b/security/keys/key.c
@@ -847,7 +847,7 @@ key_ref_t key_create_or_update(key_ref_t keyring_ref,
 	 * update that instead if possible
 	 */
 	if (index_key.type->update) {
-		key_ref = __keyring_search_one(keyring_ref, &index_key, 0);
+		key_ref = __keyring_search_one(keyring_ref, &index_key);
 		if (!IS_ERR(key_ref))
 			goto found_matching_key;
 	}
diff --git a/security/keys/keyring.c b/security/keys/keyring.c
index 87eff32b53f4..eeef1a073db4 100644
--- a/security/keys/keyring.c
+++ b/security/keys/keyring.c
@@ -531,15 +531,14 @@ EXPORT_SYMBOL(keyring_search);
  * RCU is used to make it unnecessary to lock the keyring key list here.
  *
  * Returns a pointer to the found key with usage count incremented if
- * successful and returns -ENOKEY if not found.  Revoked keys and keys not
- * providing the requested permission are skipped over.
+ * successful and returns -ENOKEY if not found.  Revoked and invalidated keys
+ * are skipped over.
  *
  * If successful, the possession indicator is propagated from the keyring ref
  * to the returned key reference.
  */
 key_ref_t __keyring_search_one(key_ref_t keyring_ref,
-			       const struct keyring_index_key *index_key,
-			       key_perm_t perm)
+			       const struct keyring_index_key *index_key)
 {
 	struct keyring_list *klist;
 	struct key *keyring, *key;
@@ -560,8 +559,6 @@ key_ref_t __keyring_search_one(key_ref_t keyring_ref,
 			if (key->type == index_key->type &&
 			    (!key->type->match ||
 			     key->type->match(key, index_key->description)) &&
-			    key_permission(make_key_ref(key, possessed),
-					   perm) == 0 &&
 			    !(key->flags & ((1 << KEY_FLAG_INVALIDATED) |
 					    (1 << KEY_FLAG_REVOKED)))
 			    )
-- 
cgit v1.2.3


From b2a4df200d570b2c33a57e1ebfa5896e4bc81b69 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Tue, 24 Sep 2013 10:35:18 +0100
Subject: KEYS: Expand the capacity of a keyring

Expand the capacity of a keyring to be able to hold a lot more keys by using
the previously added associative array implementation.  Currently the maximum
capacity is:

	(PAGE_SIZE - sizeof(header)) / sizeof(struct key *)

which, on a 64-bit system, is a little more 500.  However, since this is being
used for the NFS uid mapper, we need more than that.  The new implementation
gives us effectively unlimited capacity.

With some alterations, the keyutils testsuite runs successfully to completion
after this patch is applied.  The alterations are because (a) keyrings that
are simply added to no longer appear ordered and (b) some of the errors have
changed a bit.

Signed-off-by: David Howells <dhowells@redhat.com>
---
 include/keys/keyring-type.h |   17 +-
 include/linux/key.h         |   13 +-
 lib/assoc_array.c           |    1 +
 security/keys/Kconfig       |    1 +
 security/keys/gc.c          |   33 +-
 security/keys/internal.h    |   17 +-
 security/keys/key.c         |   35 +-
 security/keys/keyring.c     | 1436 ++++++++++++++++++++++---------------------
 security/keys/request_key.c |   12 +-
 9 files changed, 803 insertions(+), 762 deletions(-)

(limited to 'security')

diff --git a/include/keys/keyring-type.h b/include/keys/keyring-type.h
index cf49159b0e3a..fca5c62340a4 100644
--- a/include/keys/keyring-type.h
+++ b/include/keys/keyring-type.h
@@ -1,6 +1,6 @@
 /* Keyring key type
  *
- * Copyright (C) 2008 Red Hat, Inc. All Rights Reserved.
+ * Copyright (C) 2008, 2013 Red Hat, Inc. All Rights Reserved.
  * Written by David Howells (dhowells@redhat.com)
  *
  * This program is free software; you can redistribute it and/or
@@ -13,19 +13,6 @@
 #define _KEYS_KEYRING_TYPE_H
 
 #include <linux/key.h>
-#include <linux/rcupdate.h>
-
-/*
- * the keyring payload contains a list of the keys to which the keyring is
- * subscribed
- */
-struct keyring_list {
-	struct rcu_head	rcu;		/* RCU deletion hook */
-	unsigned short	maxkeys;	/* max keys this list can hold */
-	unsigned short	nkeys;		/* number of keys currently held */
-	unsigned short	delkey;		/* key to be unlinked by RCU */
-	struct key __rcu *keys[0];
-};
-
+#include <linux/assoc_array.h>
 
 #endif /* _KEYS_KEYRING_TYPE_H */
diff --git a/include/linux/key.h b/include/linux/key.h
index ef596c7af585..2417f789d29b 100644
--- a/include/linux/key.h
+++ b/include/linux/key.h
@@ -22,6 +22,7 @@
 #include <linux/sysctl.h>
 #include <linux/rwsem.h>
 #include <linux/atomic.h>
+#include <linux/assoc_array.h>
 
 #ifdef __KERNEL__
 #include <linux/uidgid.h>
@@ -196,11 +197,13 @@ struct key {
 	 *   whatever
 	 */
 	union {
-		unsigned long		value;
-		void __rcu		*rcudata;
-		void			*data;
-		struct keyring_list __rcu *subscriptions;
-	} payload;
+		union {
+			unsigned long		value;
+			void __rcu		*rcudata;
+			void			*data;
+		} payload;
+		struct assoc_array keys;
+	};
 };
 
 extern struct key *key_alloc(struct key_type *type,
diff --git a/lib/assoc_array.c b/lib/assoc_array.c
index a0952818f938..17edeaf19180 100644
--- a/lib/assoc_array.c
+++ b/lib/assoc_array.c
@@ -12,6 +12,7 @@
  */
 //#define DEBUG
 #include <linux/slab.h>
+#include <linux/err.h>
 #include <linux/assoc_array_priv.h>
 
 /*
diff --git a/security/keys/Kconfig b/security/keys/Kconfig
index a90d6d300dbd..15e0dfe8c80f 100644
--- a/security/keys/Kconfig
+++ b/security/keys/Kconfig
@@ -4,6 +4,7 @@
 
 config KEYS
 	bool "Enable access key retention support"
+	select ASSOCIATIVE_ARRAY
 	help
 	  This option provides support for retaining authentication tokens and
 	  access keys in the kernel.
diff --git a/security/keys/gc.c b/security/keys/gc.c
index d67c97bb1025..cce621c33dce 100644
--- a/security/keys/gc.c
+++ b/security/keys/gc.c
@@ -130,6 +130,13 @@ void key_gc_keytype(struct key_type *ktype)
 	kleave("");
 }
 
+static int key_gc_keyring_func(const void *object, void *iterator_data)
+{
+	const struct key *key = object;
+	time_t *limit = iterator_data;
+	return key_is_dead(key, *limit);
+}
+
 /*
  * Garbage collect pointers from a keyring.
  *
@@ -138,10 +145,9 @@ void key_gc_keytype(struct key_type *ktype)
  */
 static void key_gc_keyring(struct key *keyring, time_t limit)
 {
-	struct keyring_list *klist;
-	int loop;
+	int result;
 
-	kenter("%x", key_serial(keyring));
+	kenter("%x{%s}", keyring->serial, keyring->description ?: "");
 
 	if (keyring->flags & ((1 << KEY_FLAG_INVALIDATED) |
 			      (1 << KEY_FLAG_REVOKED)))
@@ -149,27 +155,17 @@ static void key_gc_keyring(struct key *keyring, time_t limit)
 
 	/* scan the keyring looking for dead keys */
 	rcu_read_lock();
-	klist = rcu_dereference(keyring->payload.subscriptions);
-	if (!klist)
-		goto unlock_dont_gc;
-
-	loop = klist->nkeys;
-	smp_rmb();
-	for (loop--; loop >= 0; loop--) {
-		struct key *key = rcu_dereference(klist->keys[loop]);
-		if (key_is_dead(key, limit))
-			goto do_gc;
-	}
-
-unlock_dont_gc:
+	result = assoc_array_iterate(&keyring->keys,
+				     key_gc_keyring_func, &limit);
 	rcu_read_unlock();
+	if (result == true)
+		goto do_gc;
+
 dont_gc:
 	kleave(" [no gc]");
 	return;
 
 do_gc:
-	rcu_read_unlock();
-
 	keyring_gc(keyring, limit);
 	kleave(" [gc]");
 }
@@ -392,7 +388,6 @@ found_unreferenced_key:
 	 */
 found_keyring:
 	spin_unlock(&key_serial_lock);
-	kdebug("scan keyring %d", key->serial);
 	key_gc_keyring(key, limit);
 	goto maybe_resched;
 
diff --git a/security/keys/internal.h b/security/keys/internal.h
index 73950bf8f875..581c6f688352 100644
--- a/security/keys/internal.h
+++ b/security/keys/internal.h
@@ -90,20 +90,23 @@ extern void key_type_put(struct key_type *ktype);
 
 extern int __key_link_begin(struct key *keyring,
 			    const struct keyring_index_key *index_key,
-			    unsigned long *_prealloc);
+			    struct assoc_array_edit **_edit);
 extern int __key_link_check_live_key(struct key *keyring, struct key *key);
-extern void __key_link(struct key *keyring, struct key *key,
-		       unsigned long *_prealloc);
+extern void __key_link(struct key *key, struct assoc_array_edit **_edit);
 extern void __key_link_end(struct key *keyring,
 			   const struct keyring_index_key *index_key,
-			   unsigned long prealloc);
+			   struct assoc_array_edit *edit);
 
-extern key_ref_t __keyring_search_one(key_ref_t keyring_ref,
-				      const struct keyring_index_key *index_key);
+extern key_ref_t find_key_to_update(key_ref_t keyring_ref,
+				    const struct keyring_index_key *index_key);
 
 extern struct key *keyring_search_instkey(struct key *keyring,
 					  key_serial_t target_id);
 
+extern int iterate_over_keyring(const struct key *keyring,
+				int (*func)(const struct key *key, void *data),
+				void *data);
+
 typedef int (*key_match_func_t)(const struct key *, const void *);
 
 struct keyring_search_context {
@@ -119,6 +122,8 @@ struct keyring_search_context {
 #define KEYRING_SEARCH_NO_CHECK_PERM	0x0010	/* Don't check permissions */
 #define KEYRING_SEARCH_DETECT_TOO_DEEP	0x0020	/* Give an error on excessive depth */
 
+	int (*iterator)(const void *object, void *iterator_data);
+
 	/* Internal stuff */
 	int			skipped_ret;
 	bool			possessed;
diff --git a/security/keys/key.c b/security/keys/key.c
index 7d716b82a61e..a819b5c7d4ec 100644
--- a/security/keys/key.c
+++ b/security/keys/key.c
@@ -409,7 +409,7 @@ static int __key_instantiate_and_link(struct key *key,
 				      struct key_preparsed_payload *prep,
 				      struct key *keyring,
 				      struct key *authkey,
-				      unsigned long *_prealloc)
+				      struct assoc_array_edit **_edit)
 {
 	int ret, awaken;
 
@@ -436,7 +436,7 @@ static int __key_instantiate_and_link(struct key *key,
 
 			/* and link it into the destination keyring */
 			if (keyring)
-				__key_link(keyring, key, _prealloc);
+				__key_link(key, _edit);
 
 			/* disable the authorisation key */
 			if (authkey)
@@ -476,7 +476,7 @@ int key_instantiate_and_link(struct key *key,
 			     struct key *authkey)
 {
 	struct key_preparsed_payload prep;
-	unsigned long prealloc;
+	struct assoc_array_edit *edit;
 	int ret;
 
 	memset(&prep, 0, sizeof(prep));
@@ -490,16 +490,15 @@ int key_instantiate_and_link(struct key *key,
 	}
 
 	if (keyring) {
-		ret = __key_link_begin(keyring, &key->index_key, &prealloc);
+		ret = __key_link_begin(keyring, &key->index_key, &edit);
 		if (ret < 0)
 			goto error_free_preparse;
 	}
 
-	ret = __key_instantiate_and_link(key, &prep, keyring, authkey,
-					 &prealloc);
+	ret = __key_instantiate_and_link(key, &prep, keyring, authkey, &edit);
 
 	if (keyring)
-		__key_link_end(keyring, &key->index_key, prealloc);
+		__key_link_end(keyring, &key->index_key, edit);
 
 error_free_preparse:
 	if (key->type->preparse)
@@ -537,7 +536,7 @@ int key_reject_and_link(struct key *key,
 			struct key *keyring,
 			struct key *authkey)
 {
-	unsigned long prealloc;
+	struct assoc_array_edit *edit;
 	struct timespec now;
 	int ret, awaken, link_ret = 0;
 
@@ -548,7 +547,7 @@ int key_reject_and_link(struct key *key,
 	ret = -EBUSY;
 
 	if (keyring)
-		link_ret = __key_link_begin(keyring, &key->index_key, &prealloc);
+		link_ret = __key_link_begin(keyring, &key->index_key, &edit);
 
 	mutex_lock(&key_construction_mutex);
 
@@ -570,7 +569,7 @@ int key_reject_and_link(struct key *key,
 
 		/* and link it into the destination keyring */
 		if (keyring && link_ret == 0)
-			__key_link(keyring, key, &prealloc);
+			__key_link(key, &edit);
 
 		/* disable the authorisation key */
 		if (authkey)
@@ -580,7 +579,7 @@ int key_reject_and_link(struct key *key,
 	mutex_unlock(&key_construction_mutex);
 
 	if (keyring)
-		__key_link_end(keyring, &key->index_key, prealloc);
+		__key_link_end(keyring, &key->index_key, edit);
 
 	/* wake up anyone waiting for a key to be constructed */
 	if (awaken)
@@ -783,8 +782,8 @@ key_ref_t key_create_or_update(key_ref_t keyring_ref,
 		.description	= description,
 	};
 	struct key_preparsed_payload prep;
+	struct assoc_array_edit *edit;
 	const struct cred *cred = current_cred();
-	unsigned long prealloc;
 	struct key *keyring, *key = NULL;
 	key_ref_t key_ref;
 	int ret;
@@ -828,7 +827,7 @@ key_ref_t key_create_or_update(key_ref_t keyring_ref,
 	}
 	index_key.desc_len = strlen(index_key.description);
 
-	ret = __key_link_begin(keyring, &index_key, &prealloc);
+	ret = __key_link_begin(keyring, &index_key, &edit);
 	if (ret < 0) {
 		key_ref = ERR_PTR(ret);
 		goto error_free_prep;
@@ -847,8 +846,8 @@ key_ref_t key_create_or_update(key_ref_t keyring_ref,
 	 * update that instead if possible
 	 */
 	if (index_key.type->update) {
-		key_ref = __keyring_search_one(keyring_ref, &index_key);
-		if (!IS_ERR(key_ref))
+		key_ref = find_key_to_update(keyring_ref, &index_key);
+		if (key_ref)
 			goto found_matching_key;
 	}
 
@@ -874,7 +873,7 @@ key_ref_t key_create_or_update(key_ref_t keyring_ref,
 	}
 
 	/* instantiate it and link it into the target keyring */
-	ret = __key_instantiate_and_link(key, &prep, keyring, NULL, &prealloc);
+	ret = __key_instantiate_and_link(key, &prep, keyring, NULL, &edit);
 	if (ret < 0) {
 		key_put(key);
 		key_ref = ERR_PTR(ret);
@@ -884,7 +883,7 @@ key_ref_t key_create_or_update(key_ref_t keyring_ref,
 	key_ref = make_key_ref(key, is_key_possessed(keyring_ref));
 
 error_link_end:
-	__key_link_end(keyring, &index_key, prealloc);
+	__key_link_end(keyring, &index_key, edit);
 error_free_prep:
 	if (index_key.type->preparse)
 		index_key.type->free_preparse(&prep);
@@ -897,7 +896,7 @@ error:
 	/* we found a matching key, so we're going to try to update it
 	 * - we can drop the locks first as we have the key pinned
 	 */
-	__key_link_end(keyring, &index_key, prealloc);
+	__key_link_end(keyring, &index_key, edit);
 
 	key_ref = __key_update(key_ref, &prep);
 	goto error_free_prep;
diff --git a/security/keys/keyring.c b/security/keys/keyring.c
index eeef1a073db4..f7cdea22214f 100644
--- a/security/keys/keyring.c
+++ b/security/keys/keyring.c
@@ -1,6 +1,6 @@
 /* Keyring handling
  *
- * Copyright (C) 2004-2005, 2008 Red Hat, Inc. All Rights Reserved.
+ * Copyright (C) 2004-2005, 2008, 2013 Red Hat, Inc. All Rights Reserved.
  * Written by David Howells (dhowells@redhat.com)
  *
  * This program is free software; you can redistribute it and/or
@@ -17,25 +17,11 @@
 #include <linux/seq_file.h>
 #include <linux/err.h>
 #include <keys/keyring-type.h>
+#include <keys/user-type.h>
+#include <linux/assoc_array_priv.h>
 #include <linux/uaccess.h>
 #include "internal.h"
 
-#define rcu_dereference_locked_keyring(keyring)				\
-	(rcu_dereference_protected(					\
-		(keyring)->payload.subscriptions,			\
-		rwsem_is_locked((struct rw_semaphore *)&(keyring)->sem)))
-
-#define rcu_deref_link_locked(klist, index, keyring)			\
-	(rcu_dereference_protected(					\
-		(klist)->keys[index],					\
-		rwsem_is_locked((struct rw_semaphore *)&(keyring)->sem)))
-
-#define MAX_KEYRING_LINKS						\
-	min_t(size_t, USHRT_MAX - 1,					\
-	      ((PAGE_SIZE - sizeof(struct keyring_list)) / sizeof(struct key *)))
-
-#define KEY_LINK_FIXQUOTA 1UL
-
 /*
  * When plumbing the depths of the key tree, this sets a hard limit
  * set on how deep we're willing to go.
@@ -47,6 +33,28 @@
  */
 #define KEYRING_NAME_HASH_SIZE	(1 << 5)
 
+/*
+ * We mark pointers we pass to the associative array with bit 1 set if
+ * they're keyrings and clear otherwise.
+ */
+#define KEYRING_PTR_SUBTYPE	0x2UL
+
+static inline bool keyring_ptr_is_keyring(const struct assoc_array_ptr *x)
+{
+	return (unsigned long)x & KEYRING_PTR_SUBTYPE;
+}
+static inline struct key *keyring_ptr_to_key(const struct assoc_array_ptr *x)
+{
+	void *object = assoc_array_ptr_to_leaf(x);
+	return (struct key *)((unsigned long)object & ~KEYRING_PTR_SUBTYPE);
+}
+static inline void *keyring_key_to_ptr(struct key *key)
+{
+	if (key->type == &key_type_keyring)
+		return (void *)((unsigned long)key | KEYRING_PTR_SUBTYPE);
+	return key;
+}
+
 static struct list_head	keyring_name_hash[KEYRING_NAME_HASH_SIZE];
 static DEFINE_RWLOCK(keyring_name_lock);
 
@@ -67,7 +75,6 @@ static inline unsigned keyring_hash(const char *desc)
  */
 static int keyring_instantiate(struct key *keyring,
 			       struct key_preparsed_payload *prep);
-static int keyring_match(const struct key *keyring, const void *criterion);
 static void keyring_revoke(struct key *keyring);
 static void keyring_destroy(struct key *keyring);
 static void keyring_describe(const struct key *keyring, struct seq_file *m);
@@ -76,9 +83,9 @@ static long keyring_read(const struct key *keyring,
 
 struct key_type key_type_keyring = {
 	.name		= "keyring",
-	.def_datalen	= sizeof(struct keyring_list),
+	.def_datalen	= 0,
 	.instantiate	= keyring_instantiate,
-	.match		= keyring_match,
+	.match		= user_match,
 	.revoke		= keyring_revoke,
 	.destroy	= keyring_destroy,
 	.describe	= keyring_describe,
@@ -127,6 +134,7 @@ static int keyring_instantiate(struct key *keyring,
 
 	ret = -EINVAL;
 	if (prep->datalen == 0) {
+		assoc_array_init(&keyring->keys);
 		/* make the keyring available by name if it has one */
 		keyring_publish_name(keyring);
 		ret = 0;
@@ -136,14 +144,225 @@ static int keyring_instantiate(struct key *keyring,
 }
 
 /*
- * Match keyrings on their name
+ * Multiply 64-bits by 32-bits to 96-bits and fold back to 64-bit.  Ideally we'd
+ * fold the carry back too, but that requires inline asm.
+ */
+static u64 mult_64x32_and_fold(u64 x, u32 y)
+{
+	u64 hi = (u64)(u32)(x >> 32) * y;
+	u64 lo = (u64)(u32)(x) * y;
+	return lo + ((u64)(u32)hi << 32) + (u32)(hi >> 32);
+}
+
+/*
+ * Hash a key type and description.
+ */
+static unsigned long hash_key_type_and_desc(const struct keyring_index_key *index_key)
+{
+	const unsigned level_shift = ASSOC_ARRAY_LEVEL_STEP;
+	const unsigned long level_mask = ASSOC_ARRAY_LEVEL_STEP_MASK;
+	const char *description = index_key->description;
+	unsigned long hash, type;
+	u32 piece;
+	u64 acc;
+	int n, desc_len = index_key->desc_len;
+
+	type = (unsigned long)index_key->type;
+
+	acc = mult_64x32_and_fold(type, desc_len + 13);
+	acc = mult_64x32_and_fold(acc, 9207);
+	for (;;) {
+		n = desc_len;
+		if (n <= 0)
+			break;
+		if (n > 4)
+			n = 4;
+		piece = 0;
+		memcpy(&piece, description, n);
+		description += n;
+		desc_len -= n;
+		acc = mult_64x32_and_fold(acc, piece);
+		acc = mult_64x32_and_fold(acc, 9207);
+	}
+
+	/* Fold the hash down to 32 bits if need be. */
+	hash = acc;
+	if (ASSOC_ARRAY_KEY_CHUNK_SIZE == 32)
+		hash ^= acc >> 32;
+
+	/* Squidge all the keyrings into a separate part of the tree to
+	 * ordinary keys by making sure the lowest level segment in the hash is
+	 * zero for keyrings and non-zero otherwise.
+	 */
+	if (index_key->type != &key_type_keyring && (hash & level_mask) == 0)
+		return hash | (hash >> (ASSOC_ARRAY_KEY_CHUNK_SIZE - level_shift)) | 1;
+	if (index_key->type == &key_type_keyring && (hash & level_mask) != 0)
+		return (hash + (hash << level_shift)) & ~level_mask;
+	return hash;
+}
+
+/*
+ * Build the next index key chunk.
+ *
+ * On 32-bit systems the index key is laid out as:
+ *
+ *	0	4	5	9...
+ *	hash	desclen	typeptr	desc[]
+ *
+ * On 64-bit systems:
+ *
+ *	0	8	9	17...
+ *	hash	desclen	typeptr	desc[]
+ *
+ * We return it one word-sized chunk at a time.
  */
-static int keyring_match(const struct key *keyring, const void *description)
+static unsigned long keyring_get_key_chunk(const void *data, int level)
+{
+	const struct keyring_index_key *index_key = data;
+	unsigned long chunk = 0;
+	long offset = 0;
+	int desc_len = index_key->desc_len, n = sizeof(chunk);
+
+	level /= ASSOC_ARRAY_KEY_CHUNK_SIZE;
+	switch (level) {
+	case 0:
+		return hash_key_type_and_desc(index_key);
+	case 1:
+		return ((unsigned long)index_key->type << 8) | desc_len;
+	case 2:
+		if (desc_len == 0)
+			return (u8)((unsigned long)index_key->type >>
+				    (ASSOC_ARRAY_KEY_CHUNK_SIZE - 8));
+		n--;
+		offset = 1;
+	default:
+		offset += sizeof(chunk) - 1;
+		offset += (level - 3) * sizeof(chunk);
+		if (offset >= desc_len)
+			return 0;
+		desc_len -= offset;
+		if (desc_len > n)
+			desc_len = n;
+		offset += desc_len;
+		do {
+			chunk <<= 8;
+			chunk |= ((u8*)index_key->description)[--offset];
+		} while (--desc_len > 0);
+
+		if (level == 2) {
+			chunk <<= 8;
+			chunk |= (u8)((unsigned long)index_key->type >>
+				      (ASSOC_ARRAY_KEY_CHUNK_SIZE - 8));
+		}
+		return chunk;
+	}
+}
+
+static unsigned long keyring_get_object_key_chunk(const void *object, int level)
+{
+	const struct key *key = keyring_ptr_to_key(object);
+	return keyring_get_key_chunk(&key->index_key, level);
+}
+
+static bool keyring_compare_object(const void *object, const void *data)
 {
-	return keyring->description &&
-		strcmp(keyring->description, description) == 0;
+	const struct keyring_index_key *index_key = data;
+	const struct key *key = keyring_ptr_to_key(object);
+
+	return key->index_key.type == index_key->type &&
+		key->index_key.desc_len == index_key->desc_len &&
+		memcmp(key->index_key.description, index_key->description,
+		       index_key->desc_len) == 0;
 }
 
+/*
+ * Compare the index keys of a pair of objects and determine the bit position
+ * at which they differ - if they differ.
+ */
+static int keyring_diff_objects(const void *_a, const void *_b)
+{
+	const struct key *key_a = keyring_ptr_to_key(_a);
+	const struct key *key_b = keyring_ptr_to_key(_b);
+	const struct keyring_index_key *a = &key_a->index_key;
+	const struct keyring_index_key *b = &key_b->index_key;
+	unsigned long seg_a, seg_b;
+	int level, i;
+
+	level = 0;
+	seg_a = hash_key_type_and_desc(a);
+	seg_b = hash_key_type_and_desc(b);
+	if ((seg_a ^ seg_b) != 0)
+		goto differ;
+
+	/* The number of bits contributed by the hash is controlled by a
+	 * constant in the assoc_array headers.  Everything else thereafter we
+	 * can deal with as being machine word-size dependent.
+	 */
+	level += ASSOC_ARRAY_KEY_CHUNK_SIZE / 8;
+	seg_a = a->desc_len;
+	seg_b = b->desc_len;
+	if ((seg_a ^ seg_b) != 0)
+		goto differ;
+
+	/* The next bit may not work on big endian */
+	level++;
+	seg_a = (unsigned long)a->type;
+	seg_b = (unsigned long)b->type;
+	if ((seg_a ^ seg_b) != 0)
+		goto differ;
+
+	level += sizeof(unsigned long);
+	if (a->desc_len == 0)
+		goto same;
+
+	i = 0;
+	if (((unsigned long)a->description | (unsigned long)b->description) &
+	    (sizeof(unsigned long) - 1)) {
+		do {
+			seg_a = *(unsigned long *)(a->description + i);
+			seg_b = *(unsigned long *)(b->description + i);
+			if ((seg_a ^ seg_b) != 0)
+				goto differ_plus_i;
+			i += sizeof(unsigned long);
+		} while (i < (a->desc_len & (sizeof(unsigned long) - 1)));
+	}
+
+	for (; i < a->desc_len; i++) {
+		seg_a = *(unsigned char *)(a->description + i);
+		seg_b = *(unsigned char *)(b->description + i);
+		if ((seg_a ^ seg_b) != 0)
+			goto differ_plus_i;
+	}
+
+same:
+	return -1;
+
+differ_plus_i:
+	level += i;
+differ:
+	i = level * 8 + __ffs(seg_a ^ seg_b);
+	return i;
+}
+
+/*
+ * Free an object after stripping the keyring flag off of the pointer.
+ */
+static void keyring_free_object(void *object)
+{
+	key_put(keyring_ptr_to_key(object));
+}
+
+/*
+ * Operations for keyring management by the index-tree routines.
+ */
+static const struct assoc_array_ops keyring_assoc_array_ops = {
+	.get_key_chunk		= keyring_get_key_chunk,
+	.get_object_key_chunk	= keyring_get_object_key_chunk,
+	.compare_object		= keyring_compare_object,
+	.diff_objects		= keyring_diff_objects,
+	.free_object		= keyring_free_object,
+};
+
 /*
  * Clean up a keyring when it is destroyed.  Unpublish its name if it had one
  * and dispose of its data.
@@ -155,9 +374,6 @@ static int keyring_match(const struct key *keyring, const void *description)
  */
 static void keyring_destroy(struct key *keyring)
 {
-	struct keyring_list *klist;
-	int loop;
-
 	if (keyring->description) {
 		write_lock(&keyring_name_lock);
 
@@ -168,12 +384,7 @@ static void keyring_destroy(struct key *keyring)
 		write_unlock(&keyring_name_lock);
 	}
 
-	klist = rcu_access_pointer(keyring->payload.subscriptions);
-	if (klist) {
-		for (loop = klist->nkeys - 1; loop >= 0; loop--)
-			key_put(rcu_access_pointer(klist->keys[loop]));
-		kfree(klist);
-	}
+	assoc_array_destroy(&keyring->keys, &keyring_assoc_array_ops);
 }
 
 /*
@@ -181,76 +392,88 @@ static void keyring_destroy(struct key *keyring)
  */
 static void keyring_describe(const struct key *keyring, struct seq_file *m)
 {
-	struct keyring_list *klist;
-
 	if (keyring->description)
 		seq_puts(m, keyring->description);
 	else
 		seq_puts(m, "[anon]");
 
 	if (key_is_instantiated(keyring)) {
-		rcu_read_lock();
-		klist = rcu_dereference(keyring->payload.subscriptions);
-		if (klist)
-			seq_printf(m, ": %u/%u", klist->nkeys, klist->maxkeys);
+		if (keyring->keys.nr_leaves_on_tree != 0)
+			seq_printf(m, ": %lu", keyring->keys.nr_leaves_on_tree);
 		else
 			seq_puts(m, ": empty");
-		rcu_read_unlock();
 	}
 }
 
+struct keyring_read_iterator_context {
+	size_t			qty;
+	size_t			count;
+	key_serial_t __user	*buffer;
+};
+
+static int keyring_read_iterator(const void *object, void *data)
+{
+	struct keyring_read_iterator_context *ctx = data;
+	const struct key *key = keyring_ptr_to_key(object);
+	int ret;
+
+	kenter("{%s,%d},,{%zu/%zu}",
+	       key->type->name, key->serial, ctx->count, ctx->qty);
+
+	if (ctx->count >= ctx->qty)
+		return 1;
+
+	ret = put_user(key->serial, ctx->buffer);
+	if (ret < 0)
+		return ret;
+	ctx->buffer++;
+	ctx->count += sizeof(key->serial);
+	return 0;
+}
+
 /*
  * Read a list of key IDs from the keyring's contents in binary form
  *
- * The keyring's semaphore is read-locked by the caller.
+ * The keyring's semaphore is read-locked by the caller.  This prevents someone
+ * from modifying it under us - which could cause us to read key IDs multiple
+ * times.
  */
 static long keyring_read(const struct key *keyring,
 			 char __user *buffer, size_t buflen)
 {
-	struct keyring_list *klist;
-	struct key *key;
-	size_t qty, tmp;
-	int loop, ret;
+	struct keyring_read_iterator_context ctx;
+	unsigned long nr_keys;
+	int ret;
 
-	ret = 0;
-	klist = rcu_dereference_locked_keyring(keyring);
-	if (klist) {
-		/* calculate how much data we could return */
-		qty = klist->nkeys * sizeof(key_serial_t);
-
-		if (buffer && buflen > 0) {
-			if (buflen > qty)
-				buflen = qty;
-
-			/* copy the IDs of the subscribed keys into the
-			 * buffer */
-			ret = -EFAULT;
-
-			for (loop = 0; loop < klist->nkeys; loop++) {
-				key = rcu_deref_link_locked(klist, loop,
-							    keyring);
-
-				tmp = sizeof(key_serial_t);
-				if (tmp > buflen)
-					tmp = buflen;
-
-				if (copy_to_user(buffer,
-						 &key->serial,
-						 tmp) != 0)
-					goto error;
-
-				buflen -= tmp;
-				if (buflen == 0)
-					break;
-				buffer += tmp;
-			}
-		}
+	kenter("{%d},,%zu", key_serial(keyring), buflen);
+
+	if (buflen & (sizeof(key_serial_t) - 1))
+		return -EINVAL;
+
+	nr_keys = keyring->keys.nr_leaves_on_tree;
+	if (nr_keys == 0)
+		return 0;
 
-		ret = qty;
+	/* Calculate how much data we could return */
+	ctx.qty = nr_keys * sizeof(key_serial_t);
+
+	if (!buffer || !buflen)
+		return ctx.qty;
+
+	if (buflen > ctx.qty)
+		ctx.qty = buflen;
+
+	/* Copy the IDs of the subscribed keys into the buffer */
+	ctx.buffer = (key_serial_t __user *)buffer;
+	ctx.count = 0;
+	ret = assoc_array_iterate(&keyring->keys, keyring_read_iterator, &ctx);
+	if (ret < 0) {
+		kleave(" = %d [iterate]", ret);
+		return ret;
 	}
 
-error:
-	return ret;
+	kleave(" = %zu [ok]", ctx.count);
+	return ctx.count;
 }
 
 /*
@@ -277,219 +500,360 @@ struct key *keyring_alloc(const char *description, kuid_t uid, kgid_t gid,
 }
 EXPORT_SYMBOL(keyring_alloc);
 
-/**
- * keyring_search_aux - Search a keyring tree for a key matching some criteria
- * @keyring_ref: A pointer to the keyring with possession indicator.
- * @ctx: The keyring search context.
- *
- * Search the supplied keyring tree for a key that matches the criteria given.
- * The root keyring and any linked keyrings must grant Search permission to the
- * caller to be searchable and keys can only be found if they too grant Search
- * to the caller. The possession flag on the root keyring pointer controls use
- * of the possessor bits in permissions checking of the entire tree.  In
- * addition, the LSM gets to forbid keyring searches and key matches.
- *
- * The search is performed as a breadth-then-depth search up to the prescribed
- * limit (KEYRING_SEARCH_MAX_DEPTH).
- *
- * Keys are matched to the type provided and are then filtered by the match
- * function, which is given the description to use in any way it sees fit.  The
- * match function may use any attributes of a key that it wishes to to
- * determine the match.  Normally the match function from the key type would be
- * used.
- *
- * RCU is used to prevent the keyring key lists from disappearing without the
- * need to take lots of locks.
- *
- * Returns a pointer to the found key and increments the key usage count if
- * successful; -EAGAIN if no matching keys were found, or if expired or revoked
- * keys were found; -ENOKEY if only negative keys were found; -ENOTDIR if the
- * specified keyring wasn't a keyring.
- *
- * In the case of a successful return, the possession attribute from
- * @keyring_ref is propagated to the returned key reference.
+/*
+ * Iteration function to consider each key found.
  */
-key_ref_t keyring_search_aux(key_ref_t keyring_ref,
-			     struct keyring_search_context *ctx)
+static int keyring_search_iterator(const void *object, void *iterator_data)
 {
-	struct {
-		/* Need a separate keylist pointer for RCU purposes */
-		struct key *keyring;
-		struct keyring_list *keylist;
-		int kix;
-	} stack[KEYRING_SEARCH_MAX_DEPTH];
-
-	struct keyring_list *keylist;
-	unsigned long kflags;
-	struct key *keyring, *key;
-	key_ref_t key_ref;
-	long err;
-	int sp, nkeys, kix;
+	struct keyring_search_context *ctx = iterator_data;
+	const struct key *key = keyring_ptr_to_key(object);
+	unsigned long kflags = key->flags;
 
-	keyring = key_ref_to_ptr(keyring_ref);
-	ctx->possessed = is_key_possessed(keyring_ref);
-	key_check(keyring);
+	kenter("{%d}", key->serial);
 
-	/* top keyring must have search permission to begin the search */
-	err = key_task_permission(keyring_ref, ctx->cred, KEY_SEARCH);
-	if (err < 0) {
-		key_ref = ERR_PTR(err);
-		goto error;
+	/* ignore keys not of this type */
+	if (key->type != ctx->index_key.type) {
+		kleave(" = 0 [!type]");
+		return 0;
 	}
 
-	key_ref = ERR_PTR(-ENOTDIR);
-	if (keyring->type != &key_type_keyring)
-		goto error;
+	/* skip invalidated, revoked and expired keys */
+	if (ctx->flags & KEYRING_SEARCH_DO_STATE_CHECK) {
+		if (kflags & ((1 << KEY_FLAG_INVALIDATED) |
+			      (1 << KEY_FLAG_REVOKED))) {
+			ctx->result = ERR_PTR(-EKEYREVOKED);
+			kleave(" = %d [invrev]", ctx->skipped_ret);
+			goto skipped;
+		}
 
-	rcu_read_lock();
+		if (key->expiry && ctx->now.tv_sec >= key->expiry) {
+			ctx->result = ERR_PTR(-EKEYEXPIRED);
+			kleave(" = %d [expire]", ctx->skipped_ret);
+			goto skipped;
+		}
+	}
 
-	ctx->now = current_kernel_time();
-	err = -EAGAIN;
-	sp = 0;
-
-	/* firstly we should check to see if this top-level keyring is what we
-	 * are looking for */
-	key_ref = ERR_PTR(-EAGAIN);
-	kflags = keyring->flags;
-	if (keyring->type == ctx->index_key.type &&
-	    ctx->match(keyring, ctx->match_data)) {
-		key = keyring;
-		if (ctx->flags & KEYRING_SEARCH_NO_STATE_CHECK)
-			goto found;
+	/* keys that don't match */
+	if (!ctx->match(key, ctx->match_data)) {
+		kleave(" = 0 [!match]");
+		return 0;
+	}
 
-		/* check it isn't negative and hasn't expired or been
-		 * revoked */
-		if (kflags & (1 << KEY_FLAG_REVOKED))
-			goto error_2;
-		if (key->expiry && ctx->now.tv_sec >= key->expiry)
-			goto error_2;
-		key_ref = ERR_PTR(key->type_data.reject_error);
-		if (kflags & (1 << KEY_FLAG_NEGATIVE))
-			goto error_2;
-		goto found;
+	/* key must have search permissions */
+	if (!(ctx->flags & KEYRING_SEARCH_NO_CHECK_PERM) &&
+	    key_task_permission(make_key_ref(key, ctx->possessed),
+				ctx->cred, KEY_SEARCH) < 0) {
+		ctx->result = ERR_PTR(-EACCES);
+		kleave(" = %d [!perm]", ctx->skipped_ret);
+		goto skipped;
 	}
 
-	/* otherwise, the top keyring must not be revoked, expired, or
-	 * negatively instantiated if we are to search it */
-	key_ref = ERR_PTR(-EAGAIN);
-	if (kflags & ((1 << KEY_FLAG_INVALIDATED) |
-		      (1 << KEY_FLAG_REVOKED) |
-		      (1 << KEY_FLAG_NEGATIVE)) ||
-	    (keyring->expiry && ctx->now.tv_sec >= keyring->expiry))
-		goto error_2;
-
-	/* start processing a new keyring */
-descend:
-	kflags = keyring->flags;
-	if (kflags & ((1 << KEY_FLAG_INVALIDATED) |
-		      (1 << KEY_FLAG_REVOKED)))
-		goto not_this_keyring;
+	if (ctx->flags & KEYRING_SEARCH_DO_STATE_CHECK) {
+		/* we set a different error code if we pass a negative key */
+		if (kflags & (1 << KEY_FLAG_NEGATIVE)) {
+			ctx->result = ERR_PTR(key->type_data.reject_error);
+			kleave(" = %d [neg]", ctx->skipped_ret);
+			goto skipped;
+		}
+	}
 
-	keylist = rcu_dereference(keyring->payload.subscriptions);
-	if (!keylist)
-		goto not_this_keyring;
+	/* Found */
+	ctx->result = make_key_ref(key, ctx->possessed);
+	kleave(" = 1 [found]");
+	return 1;
 
-	/* iterate through the keys in this keyring first */
-	nkeys = keylist->nkeys;
-	smp_rmb();
-	for (kix = 0; kix < nkeys; kix++) {
-		key = rcu_dereference(keylist->keys[kix]);
-		kflags = key->flags;
+skipped:
+	return ctx->skipped_ret;
+}
 
-		/* ignore keys not of this type */
-		if (key->type != ctx->index_key.type)
-			continue;
+/*
+ * Search inside a keyring for a key.  We can search by walking to it
+ * directly based on its index-key or we can iterate over the entire
+ * tree looking for it, based on the match function.
+ */
+static int search_keyring(struct key *keyring, struct keyring_search_context *ctx)
+{
+	if ((ctx->flags & KEYRING_SEARCH_LOOKUP_TYPE) ==
+	    KEYRING_SEARCH_LOOKUP_DIRECT) {
+		const void *object;
+
+		object = assoc_array_find(&keyring->keys,
+					  &keyring_assoc_array_ops,
+					  &ctx->index_key);
+		return object ? ctx->iterator(object, ctx) : 0;
+	}
+	return assoc_array_iterate(&keyring->keys, ctx->iterator, ctx);
+}
 
-		/* skip invalidated, revoked and expired keys */
-		if (!(ctx->flags & KEYRING_SEARCH_NO_STATE_CHECK)) {
-			if (kflags & ((1 << KEY_FLAG_INVALIDATED) |
-				      (1 << KEY_FLAG_REVOKED)))
-				continue;
+/*
+ * Search a tree of keyrings that point to other keyrings up to the maximum
+ * depth.
+ */
+static bool search_nested_keyrings(struct key *keyring,
+				   struct keyring_search_context *ctx)
+{
+	struct {
+		struct key *keyring;
+		struct assoc_array_node *node;
+		int slot;
+	} stack[KEYRING_SEARCH_MAX_DEPTH];
 
-			if (key->expiry && ctx->now.tv_sec >= key->expiry)
-				continue;
-		}
+	struct assoc_array_shortcut *shortcut;
+	struct assoc_array_node *node;
+	struct assoc_array_ptr *ptr;
+	struct key *key;
+	int sp = 0, slot;
 
-		/* keys that don't match */
-		if (!ctx->match(key, ctx->match_data))
-			continue;
+	kenter("{%d},{%s,%s}",
+	       keyring->serial,
+	       ctx->index_key.type->name,
+	       ctx->index_key.description);
 
-		/* key must have search permissions */
-		if (key_task_permission(make_key_ref(key, ctx->possessed),
-					ctx->cred, KEY_SEARCH) < 0)
-			continue;
+	if (ctx->index_key.description)
+		ctx->index_key.desc_len = strlen(ctx->index_key.description);
 
-		if (ctx->flags & KEYRING_SEARCH_NO_STATE_CHECK)
+	/* Check to see if this top-level keyring is what we are looking for
+	 * and whether it is valid or not.
+	 */
+	if (ctx->flags & KEYRING_SEARCH_LOOKUP_ITERATE ||
+	    keyring_compare_object(keyring, &ctx->index_key)) {
+		ctx->skipped_ret = 2;
+		ctx->flags |= KEYRING_SEARCH_DO_STATE_CHECK;
+		switch (ctx->iterator(keyring_key_to_ptr(keyring), ctx)) {
+		case 1:
 			goto found;
-
-		/* we set a different error code if we pass a negative key */
-		if (kflags & (1 << KEY_FLAG_NEGATIVE)) {
-			err = key->type_data.reject_error;
-			continue;
+		case 2:
+			return false;
+		default:
+			break;
 		}
+	}
 
+	ctx->skipped_ret = 0;
+	if (ctx->flags & KEYRING_SEARCH_NO_STATE_CHECK)
+		ctx->flags &= ~KEYRING_SEARCH_DO_STATE_CHECK;
+
+	/* Start processing a new keyring */
+descend_to_keyring:
+	kdebug("descend to %d", keyring->serial);
+	if (keyring->flags & ((1 << KEY_FLAG_INVALIDATED) |
+			      (1 << KEY_FLAG_REVOKED)))
+		goto not_this_keyring;
+
+	/* Search through the keys in this keyring before its searching its
+	 * subtrees.
+	 */
+	if (search_keyring(keyring, ctx))
 		goto found;
-	}
 
-	/* search through the keyrings nested in this one */
-	kix = 0;
-ascend:
-	nkeys = keylist->nkeys;
-	smp_rmb();
-	for (; kix < nkeys; kix++) {
-		key = rcu_dereference(keylist->keys[kix]);
-		if (key->type != &key_type_keyring)
-			continue;
+	/* Then manually iterate through the keyrings nested in this one.
+	 *
+	 * Start from the root node of the index tree.  Because of the way the
+	 * hash function has been set up, keyrings cluster on the leftmost
+	 * branch of the root node (root slot 0) or in the root node itself.
+	 * Non-keyrings avoid the leftmost branch of the root entirely (root
+	 * slots 1-15).
+	 */
+	ptr = ACCESS_ONCE(keyring->keys.root);
+	if (!ptr)
+		goto not_this_keyring;
 
-		/* recursively search nested keyrings
-		 * - only search keyrings for which we have search permission
+	if (assoc_array_ptr_is_shortcut(ptr)) {
+		/* If the root is a shortcut, either the keyring only contains
+		 * keyring pointers (everything clusters behind root slot 0) or
+		 * doesn't contain any keyring pointers.
 		 */
-		if (sp >= KEYRING_SEARCH_MAX_DEPTH)
+		shortcut = assoc_array_ptr_to_shortcut(ptr);
+		smp_read_barrier_depends();
+		if ((shortcut->index_key[0] & ASSOC_ARRAY_FAN_MASK) != 0)
+			goto not_this_keyring;
+
+		ptr = ACCESS_ONCE(shortcut->next_node);
+		node = assoc_array_ptr_to_node(ptr);
+		goto begin_node;
+	}
+
+	node = assoc_array_ptr_to_node(ptr);
+	smp_read_barrier_depends();
+
+	ptr = node->slots[0];
+	if (!assoc_array_ptr_is_meta(ptr))
+		goto begin_node;
+
+descend_to_node:
+	/* Descend to a more distal node in this keyring's content tree and go
+	 * through that.
+	 */
+	kdebug("descend");
+	if (assoc_array_ptr_is_shortcut(ptr)) {
+		shortcut = assoc_array_ptr_to_shortcut(ptr);
+		smp_read_barrier_depends();
+		ptr = ACCESS_ONCE(shortcut->next_node);
+		BUG_ON(!assoc_array_ptr_is_node(ptr));
+		node = assoc_array_ptr_to_node(ptr);
+	}
+
+begin_node:
+	kdebug("begin_node");
+	smp_read_barrier_depends();
+	slot = 0;
+ascend_to_node:
+	/* Go through the slots in a node */
+	for (; slot < ASSOC_ARRAY_FAN_OUT; slot++) {
+		ptr = ACCESS_ONCE(node->slots[slot]);
+
+		if (assoc_array_ptr_is_meta(ptr) && node->back_pointer)
+			goto descend_to_node;
+
+		if (!keyring_ptr_is_keyring(ptr))
 			continue;
 
-		if (key_task_permission(make_key_ref(key, ctx->possessed),
+		key = keyring_ptr_to_key(ptr);
+
+		if (sp >= KEYRING_SEARCH_MAX_DEPTH) {
+			if (ctx->flags & KEYRING_SEARCH_DETECT_TOO_DEEP) {
+				ctx->result = ERR_PTR(-ELOOP);
+				return false;
+			}
+			goto not_this_keyring;
+		}
+
+		/* Search a nested keyring */
+		if (!(ctx->flags & KEYRING_SEARCH_NO_CHECK_PERM) &&
+		    key_task_permission(make_key_ref(key, ctx->possessed),
 					ctx->cred, KEY_SEARCH) < 0)
 			continue;
 
 		/* stack the current position */
 		stack[sp].keyring = keyring;
-		stack[sp].keylist = keylist;
-		stack[sp].kix = kix;
+		stack[sp].node = node;
+		stack[sp].slot = slot;
 		sp++;
 
 		/* begin again with the new keyring */
 		keyring = key;
-		goto descend;
+		goto descend_to_keyring;
+	}
+
+	/* We've dealt with all the slots in the current node, so now we need
+	 * to ascend to the parent and continue processing there.
+	 */
+	ptr = ACCESS_ONCE(node->back_pointer);
+	slot = node->parent_slot;
+
+	if (ptr && assoc_array_ptr_is_shortcut(ptr)) {
+		shortcut = assoc_array_ptr_to_shortcut(ptr);
+		smp_read_barrier_depends();
+		ptr = ACCESS_ONCE(shortcut->back_pointer);
+		slot = shortcut->parent_slot;
+	}
+	if (!ptr)
+		goto not_this_keyring;
+	node = assoc_array_ptr_to_node(ptr);
+	smp_read_barrier_depends();
+	slot++;
+
+	/* If we've ascended to the root (zero backpointer), we must have just
+	 * finished processing the leftmost branch rather than the root slots -
+	 * so there can't be any more keyrings for us to find.
+	 */
+	if (node->back_pointer) {
+		kdebug("ascend %d", slot);
+		goto ascend_to_node;
 	}
 
-	/* the keyring we're looking at was disqualified or didn't contain a
-	 * matching key */
+	/* The keyring we're looking at was disqualified or didn't contain a
+	 * matching key.
+	 */
 not_this_keyring:
-	if (sp > 0) {
-		/* resume the processing of a keyring higher up in the tree */
-		sp--;
-		keyring = stack[sp].keyring;
-		keylist = stack[sp].keylist;
-		kix = stack[sp].kix + 1;
-		goto ascend;
+	kdebug("not_this_keyring %d", sp);
+	if (sp <= 0) {
+		kleave(" = false");
+		return false;
 	}
 
-	key_ref = ERR_PTR(err);
-	goto error_2;
+	/* Resume the processing of a keyring higher up in the tree */
+	sp--;
+	keyring = stack[sp].keyring;
+	node = stack[sp].node;
+	slot = stack[sp].slot + 1;
+	kdebug("ascend to %d [%d]", keyring->serial, slot);
+	goto ascend_to_node;
 
-	/* we found a viable match */
+	/* We found a viable match */
 found:
-	__key_get(key);
-	key->last_used_at = ctx->now.tv_sec;
-	keyring->last_used_at = ctx->now.tv_sec;
-	while (sp > 0)
-		stack[--sp].keyring->last_used_at = ctx->now.tv_sec;
+	key = key_ref_to_ptr(ctx->result);
 	key_check(key);
-	key_ref = make_key_ref(key, ctx->possessed);
-error_2:
+	if (!(ctx->flags & KEYRING_SEARCH_NO_UPDATE_TIME)) {
+		key->last_used_at = ctx->now.tv_sec;
+		keyring->last_used_at = ctx->now.tv_sec;
+		while (sp > 0)
+			stack[--sp].keyring->last_used_at = ctx->now.tv_sec;
+	}
+	kleave(" = true");
+	return true;
+}
+
+/**
+ * keyring_search_aux - Search a keyring tree for a key matching some criteria
+ * @keyring_ref: A pointer to the keyring with possession indicator.
+ * @ctx: The keyring search context.
+ *
+ * Search the supplied keyring tree for a key that matches the criteria given.
+ * The root keyring and any linked keyrings must grant Search permission to the
+ * caller to be searchable and keys can only be found if they too grant Search
+ * to the caller. The possession flag on the root keyring pointer controls use
+ * of the possessor bits in permissions checking of the entire tree.  In
+ * addition, the LSM gets to forbid keyring searches and key matches.
+ *
+ * The search is performed as a breadth-then-depth search up to the prescribed
+ * limit (KEYRING_SEARCH_MAX_DEPTH).
+ *
+ * Keys are matched to the type provided and are then filtered by the match
+ * function, which is given the description to use in any way it sees fit.  The
+ * match function may use any attributes of a key that it wishes to to
+ * determine the match.  Normally the match function from the key type would be
+ * used.
+ *
+ * RCU can be used to prevent the keyring key lists from disappearing without
+ * the need to take lots of locks.
+ *
+ * Returns a pointer to the found key and increments the key usage count if
+ * successful; -EAGAIN if no matching keys were found, or if expired or revoked
+ * keys were found; -ENOKEY if only negative keys were found; -ENOTDIR if the
+ * specified keyring wasn't a keyring.
+ *
+ * In the case of a successful return, the possession attribute from
+ * @keyring_ref is propagated to the returned key reference.
+ */
+key_ref_t keyring_search_aux(key_ref_t keyring_ref,
+			     struct keyring_search_context *ctx)
+{
+	struct key *keyring;
+	long err;
+
+	ctx->iterator = keyring_search_iterator;
+	ctx->possessed = is_key_possessed(keyring_ref);
+	ctx->result = ERR_PTR(-EAGAIN);
+
+	keyring = key_ref_to_ptr(keyring_ref);
+	key_check(keyring);
+
+	if (keyring->type != &key_type_keyring)
+		return ERR_PTR(-ENOTDIR);
+
+	if (!(ctx->flags & KEYRING_SEARCH_NO_CHECK_PERM)) {
+		err = key_task_permission(keyring_ref, ctx->cred, KEY_SEARCH);
+		if (err < 0)
+			return ERR_PTR(err);
+	}
+
+	rcu_read_lock();
+	ctx->now = current_kernel_time();
+	if (search_nested_keyrings(keyring, ctx))
+		__key_get(key_ref_to_ptr(ctx->result));
 	rcu_read_unlock();
-error:
-	return key_ref;
+	return ctx->result;
 }
 
 /**
@@ -499,7 +863,7 @@ error:
  * @description: The name of the keyring we want to find.
  *
  * As keyring_search_aux() above, but using the current task's credentials and
- * type's default matching function.
+ * type's default matching function and preferred search method.
  */
 key_ref_t keyring_search(key_ref_t keyring,
 			 struct key_type *type,
@@ -523,58 +887,49 @@ key_ref_t keyring_search(key_ref_t keyring,
 EXPORT_SYMBOL(keyring_search);
 
 /*
- * Search the given keyring only (no recursion).
+ * Search the given keyring for a key that might be updated.
  *
  * The caller must guarantee that the keyring is a keyring and that the
- * permission is granted to search the keyring as no check is made here.
- *
- * RCU is used to make it unnecessary to lock the keyring key list here.
+ * permission is granted to modify the keyring as no check is made here.  The
+ * caller must also hold a lock on the keyring semaphore.
  *
  * Returns a pointer to the found key with usage count incremented if
- * successful and returns -ENOKEY if not found.  Revoked and invalidated keys
- * are skipped over.
+ * successful and returns NULL if not found.  Revoked and invalidated keys are
+ * skipped over.
  *
  * If successful, the possession indicator is propagated from the keyring ref
  * to the returned key reference.
  */
-key_ref_t __keyring_search_one(key_ref_t keyring_ref,
-			       const struct keyring_index_key *index_key)
+key_ref_t find_key_to_update(key_ref_t keyring_ref,
+			     const struct keyring_index_key *index_key)
 {
-	struct keyring_list *klist;
 	struct key *keyring, *key;
-	bool possessed;
-	int nkeys, loop;
+	const void *object;
 
 	keyring = key_ref_to_ptr(keyring_ref);
-	possessed = is_key_possessed(keyring_ref);
 
-	rcu_read_lock();
+	kenter("{%d},{%s,%s}",
+	       keyring->serial, index_key->type->name, index_key->description);
 
-	klist = rcu_dereference(keyring->payload.subscriptions);
-	if (klist) {
-		nkeys = klist->nkeys;
-		smp_rmb();
-		for (loop = 0; loop < nkeys ; loop++) {
-			key = rcu_dereference(klist->keys[loop]);
-			if (key->type == index_key->type &&
-			    (!key->type->match ||
-			     key->type->match(key, index_key->description)) &&
-			    !(key->flags & ((1 << KEY_FLAG_INVALIDATED) |
-					    (1 << KEY_FLAG_REVOKED)))
-			    )
-				goto found;
-		}
-	}
+	object = assoc_array_find(&keyring->keys, &keyring_assoc_array_ops,
+				  index_key);
 
-	rcu_read_unlock();
-	return ERR_PTR(-ENOKEY);
+	if (object)
+		goto found;
+
+	kleave(" = NULL");
+	return NULL;
 
 found:
+	key = keyring_ptr_to_key(object);
+	if (key->flags & ((1 << KEY_FLAG_INVALIDATED) |
+			  (1 << KEY_FLAG_REVOKED))) {
+		kleave(" = NULL [x]");
+		return NULL;
+	}
 	__key_get(key);
-	keyring->last_used_at = key->last_used_at =
-		current_kernel_time().tv_sec;
-	rcu_read_unlock();
-	return make_key_ref(key, possessed);
+	kleave(" = {%d}", key->serial);
+	return make_key_ref(key, is_key_possessed(keyring_ref));
 }
 
 /*
@@ -637,6 +992,19 @@ out:
 	return keyring;
 }
 
+static int keyring_detect_cycle_iterator(const void *object,
+					 void *iterator_data)
+{
+	struct keyring_search_context *ctx = iterator_data;
+	const struct key *key = keyring_ptr_to_key(object);
+
+	kenter("{%d}", key->serial);
+
+	BUG_ON(key != ctx->match_data);
+	ctx->result = ERR_PTR(-EDEADLK);
+	return 1;
+}
+
 /*
  * See if a cycle will will be created by inserting acyclic tree B in acyclic
  * tree A at the topmost level (ie: as a direct child of A).
@@ -646,117 +1014,39 @@ out:
  */
 static int keyring_detect_cycle(struct key *A, struct key *B)
 {
-	struct {
-		struct keyring_list *keylist;
-		int kix;
-	} stack[KEYRING_SEARCH_MAX_DEPTH];
-
-	struct keyring_list *keylist;
-	struct key *subtree, *key;
-	int sp, nkeys, kix, ret;
+	struct keyring_search_context ctx = {
+		.index_key	= A->index_key,
+		.match_data	= A,
+		.iterator	= keyring_detect_cycle_iterator,
+		.flags		= (KEYRING_SEARCH_LOOKUP_DIRECT |
+				   KEYRING_SEARCH_NO_STATE_CHECK |
+				   KEYRING_SEARCH_NO_UPDATE_TIME |
+				   KEYRING_SEARCH_NO_CHECK_PERM |
+				   KEYRING_SEARCH_DETECT_TOO_DEEP),
+	};
 
 	rcu_read_lock();
-
-	ret = -EDEADLK;
-	if (A == B)
-		goto cycle_detected;
-
-	subtree = B;
-	sp = 0;
-
-	/* start processing a new keyring */
-descend:
-	if (test_bit(KEY_FLAG_REVOKED, &subtree->flags))
-		goto not_this_keyring;
-
-	keylist = rcu_dereference(subtree->payload.subscriptions);
-	if (!keylist)
-		goto not_this_keyring;
-	kix = 0;
-
-ascend:
-	/* iterate through the remaining keys in this keyring */
-	nkeys = keylist->nkeys;
-	smp_rmb();
-	for (; kix < nkeys; kix++) {
-		key = rcu_dereference(keylist->keys[kix]);
-
-		if (key == A)
-			goto cycle_detected;
-
-		/* recursively check nested keyrings */
-		if (key->type == &key_type_keyring) {
-			if (sp >= KEYRING_SEARCH_MAX_DEPTH)
-				goto too_deep;
-
-			/* stack the current position */
-			stack[sp].keylist = keylist;
-			stack[sp].kix = kix;
-			sp++;
-
-			/* begin again with the new keyring */
-			subtree = key;
-			goto descend;
-		}
-	}
-
-	/* the keyring we're looking at was disqualified or didn't contain a
-	 * matching key */
-not_this_keyring:
-	if (sp > 0) {
-		/* resume the checking of a keyring higher up in the tree */
-		sp--;
-		keylist = stack[sp].keylist;
-		kix = stack[sp].kix + 1;
-		goto ascend;
-	}
-
-	ret = 0; /* no cycles detected */
-
-error:
+	search_nested_keyrings(B, &ctx);
 	rcu_read_unlock();
-	return ret;
-
-too_deep:
-	ret = -ELOOP;
-	goto error;
-
-cycle_detected:
-	ret = -EDEADLK;
-	goto error;
-}
-
-/*
- * Dispose of a keyring list after the RCU grace period, freeing the unlinked
- * key
- */
-static void keyring_unlink_rcu_disposal(struct rcu_head *rcu)
-{
-	struct keyring_list *klist =
-		container_of(rcu, struct keyring_list, rcu);
-
-	if (klist->delkey != USHRT_MAX)
-		key_put(rcu_access_pointer(klist->keys[klist->delkey]));
-	kfree(klist);
+	return PTR_ERR(ctx.result) == -EAGAIN ? 0 : PTR_ERR(ctx.result);
 }
 
 /*
  * Preallocate memory so that a key can be linked into to a keyring.
  */
-int __key_link_begin(struct key *keyring, const struct keyring_index_key *index_key,
-		     unsigned long *_prealloc)
+int __key_link_begin(struct key *keyring,
+		     const struct keyring_index_key *index_key,
+		     struct assoc_array_edit **_edit)
 	__acquires(&keyring->sem)
 	__acquires(&keyring_serialise_link_sem)
 {
-	struct keyring_list *klist, *nklist;
-	unsigned long prealloc;
-	unsigned max;
-	time_t lowest_lru;
-	size_t size;
-	int loop, lru, ret;
+	struct assoc_array_edit *edit;
+	int ret;
 
 	kenter("%d,%s,%s,",
-	       key_serial(keyring), index_key->type->name, index_key->description);
+	       keyring->serial, index_key->type->name, index_key->description);
+
+	BUG_ON(index_key->desc_len == 0);
 
 	if (keyring->type != &key_type_keyring)
 		return -ENOTDIR;
@@ -772,88 +1062,25 @@ int __key_link_begin(struct key *keyring, const struct keyring_index_key *index_
 	if (index_key->type == &key_type_keyring)
 		down_write(&keyring_serialise_link_sem);
 
-	klist = rcu_dereference_locked_keyring(keyring);
-
-	/* see if there's a matching key we can displace */
-	lru = -1;
-	if (klist && klist->nkeys > 0) {
-		lowest_lru = TIME_T_MAX;
-		for (loop = klist->nkeys - 1; loop >= 0; loop--) {
-			struct key *key = rcu_deref_link_locked(klist, loop,
-								keyring);
-			if (key->type == index_key->type &&
-			    strcmp(key->description, index_key->description) == 0) {
-				/* Found a match - we'll replace the link with
-				 * one to the new key.  We record the slot
-				 * position.
-				 */
-				klist->delkey = loop;
-				prealloc = 0;
-				goto done;
-			}
-			if (key->last_used_at < lowest_lru) {
-				lowest_lru = key->last_used_at;
-				lru = loop;
-			}
-		}
-	}
-
-	/* If the keyring is full then do an LRU discard */
-	if (klist &&
-	    klist->nkeys == klist->maxkeys &&
-	    klist->maxkeys >= MAX_KEYRING_LINKS) {
-		kdebug("LRU discard %d\n", lru);
-		klist->delkey = lru;
-		prealloc = 0;
-		goto done;
-	}
-
 	/* check that we aren't going to overrun the user's quota */
 	ret = key_payload_reserve(keyring,
 				  keyring->datalen + KEYQUOTA_LINK_BYTES);
 	if (ret < 0)
 		goto error_sem;
 
-	if (klist && klist->nkeys < klist->maxkeys) {
-		/* there's sufficient slack space to append directly */
-		klist->delkey = klist->nkeys;
-		prealloc = KEY_LINK_FIXQUOTA;
-	} else {
-		/* grow the key list */
-		max = 4;
-		if (klist) {
-			max += klist->maxkeys;
-			if (max > MAX_KEYRING_LINKS)
-				max = MAX_KEYRING_LINKS;
-			BUG_ON(max <= klist->maxkeys);
-		}
-
-		size = sizeof(*klist) + sizeof(struct key *) * max;
-
-		ret = -ENOMEM;
-		nklist = kmalloc(size, GFP_KERNEL);
-		if (!nklist)
-			goto error_quota;
-
-		nklist->maxkeys = max;
-		if (klist) {
-			memcpy(nklist->keys, klist->keys,
-			       sizeof(struct key *) * klist->nkeys);
-			nklist->delkey = klist->nkeys;
-			nklist->nkeys = klist->nkeys + 1;
-			klist->delkey = USHRT_MAX;
-		} else {
-			nklist->nkeys = 1;
-			nklist->delkey = 0;
-		}
-
-		/* add the key into the new space */
-		RCU_INIT_POINTER(nklist->keys[nklist->delkey], NULL);
-		prealloc = (unsigned long)nklist | KEY_LINK_FIXQUOTA;
+	/* Create an edit script that will insert/replace the key in the
+	 * keyring tree.
+	 */
+	edit = assoc_array_insert(&keyring->keys,
+				  &keyring_assoc_array_ops,
+				  index_key,
+				  NULL);
+	if (IS_ERR(edit)) {
+		ret = PTR_ERR(edit);
+		goto error_quota;
 	}
 
-done:
-	*_prealloc = prealloc;
+	*_edit = edit;
 	kleave(" = 0");
 	return 0;
 
@@ -893,60 +1120,12 @@ int __key_link_check_live_key(struct key *keyring, struct key *key)
  * holds at most one link to any given key of a particular type+description
  * combination.
  */
-void __key_link(struct key *keyring, struct key *key,
-		unsigned long *_prealloc)
+void __key_link(struct key *key, struct assoc_array_edit **_edit)
 {
-	struct keyring_list *klist, *nklist;
-	struct key *discard;
-
-	nklist = (struct keyring_list *)(*_prealloc & ~KEY_LINK_FIXQUOTA);
-	*_prealloc = 0;
-
-	kenter("%d,%d,%p", keyring->serial, key->serial, nklist);
-
-	klist = rcu_dereference_locked_keyring(keyring);
-
 	__key_get(key);
-	keyring->last_used_at = key->last_used_at =
-		current_kernel_time().tv_sec;
-
-	/* there's a matching key we can displace or an empty slot in a newly
-	 * allocated list we can fill */
-	if (nklist) {
-		kdebug("reissue %hu/%hu/%hu",
-		       nklist->delkey, nklist->nkeys, nklist->maxkeys);
-
-		RCU_INIT_POINTER(nklist->keys[nklist->delkey], key);
-
-		rcu_assign_pointer(keyring->payload.subscriptions, nklist);
-
-		/* dispose of the old keyring list and, if there was one, the
-		 * displaced key */
-		if (klist) {
-			kdebug("dispose %hu/%hu/%hu",
-			       klist->delkey, klist->nkeys, klist->maxkeys);
-			call_rcu(&klist->rcu, keyring_unlink_rcu_disposal);
-		}
-	} else if (klist->delkey < klist->nkeys) {
-		kdebug("replace %hu/%hu/%hu",
-		       klist->delkey, klist->nkeys, klist->maxkeys);
-
-		discard = rcu_dereference_protected(
-			klist->keys[klist->delkey],
-			rwsem_is_locked(&keyring->sem));
-		rcu_assign_pointer(klist->keys[klist->delkey], key);
-		/* The garbage collector will take care of RCU
-		 * synchronisation */
-		key_put(discard);
-	} else {
-		/* there's sufficient slack space to append directly */
-		kdebug("append %hu/%hu/%hu",
-		       klist->delkey, klist->nkeys, klist->maxkeys);
-
-		RCU_INIT_POINTER(klist->keys[klist->delkey], key);
-		smp_wmb();
-		klist->nkeys++;
-	}
+	assoc_array_insert_set_object(*_edit, keyring_key_to_ptr(key));
+	assoc_array_apply_edit(*_edit);
+	*_edit = NULL;
 }
 
 /*
@@ -956,23 +1135,20 @@ void __key_link(struct key *keyring, struct key *key,
  */
 void __key_link_end(struct key *keyring,
 		    const struct keyring_index_key *index_key,
-		    unsigned long prealloc)
+		    struct assoc_array_edit *edit)
 	__releases(&keyring->sem)
 	__releases(&keyring_serialise_link_sem)
 {
 	BUG_ON(index_key->type == NULL);
-	BUG_ON(index_key->type->name == NULL);
-	kenter("%d,%s,%lx", keyring->serial, index_key->type->name, prealloc);
+	kenter("%d,%s,", keyring->serial, index_key->type->name);
 
 	if (index_key->type == &key_type_keyring)
 		up_write(&keyring_serialise_link_sem);
 
-	if (prealloc) {
-		if (prealloc & KEY_LINK_FIXQUOTA)
-			key_payload_reserve(keyring,
-					    keyring->datalen -
-					    KEYQUOTA_LINK_BYTES);
-		kfree((struct keyring_list *)(prealloc & ~KEY_LINK_FIXQUOTA));
+	if (edit) {
+		key_payload_reserve(keyring,
+				    keyring->datalen - KEYQUOTA_LINK_BYTES);
+		assoc_array_cancel_edit(edit);
 	}
 	up_write(&keyring->sem);
 }
@@ -999,20 +1175,24 @@ void __key_link_end(struct key *keyring,
  */
 int key_link(struct key *keyring, struct key *key)
 {
-	unsigned long prealloc;
+	struct assoc_array_edit *edit;
 	int ret;
 
+	kenter("{%d,%d}", keyring->serial, atomic_read(&keyring->usage));
+
 	key_check(keyring);
 	key_check(key);
 
-	ret = __key_link_begin(keyring, &key->index_key, &prealloc);
+	ret = __key_link_begin(keyring, &key->index_key, &edit);
 	if (ret == 0) {
+		kdebug("begun {%d,%d}", keyring->serial, atomic_read(&keyring->usage));
 		ret = __key_link_check_live_key(keyring, key);
 		if (ret == 0)
-			__key_link(keyring, key, &prealloc);
-		__key_link_end(keyring, &key->index_key, prealloc);
+			__key_link(key, &edit);
+		__key_link_end(keyring, &key->index_key, edit);
 	}
 
+	kleave(" = %d {%d,%d}", ret, keyring->serial, atomic_read(&keyring->usage));
 	return ret;
 }
 EXPORT_SYMBOL(key_link);
@@ -1036,90 +1216,36 @@ EXPORT_SYMBOL(key_link);
  */
 int key_unlink(struct key *keyring, struct key *key)
 {
-	struct keyring_list *klist, *nklist;
-	int loop, ret;
+	struct assoc_array_edit *edit;
+	int ret;
 
 	key_check(keyring);
 	key_check(key);
 
-	ret = -ENOTDIR;
 	if (keyring->type != &key_type_keyring)
-		goto error;
+		return -ENOTDIR;
 
 	down_write(&keyring->sem);
 
-	klist = rcu_dereference_locked_keyring(keyring);
-	if (klist) {
-		/* search the keyring for the key */
-		for (loop = 0; loop < klist->nkeys; loop++)
-			if (rcu_access_pointer(klist->keys[loop]) == key)
-				goto key_is_present;
+	edit = assoc_array_delete(&keyring->keys, &keyring_assoc_array_ops,
+				  &key->index_key);
+	if (IS_ERR(edit)) {
+		ret = PTR_ERR(edit);
+		goto error;
 	}
-
-	up_write(&keyring->sem);
 	ret = -ENOENT;
-	goto error;
-
-key_is_present:
-	/* we need to copy the key list for RCU purposes */
-	nklist = kmalloc(sizeof(*klist) +
-			 sizeof(struct key *) * klist->maxkeys,
-			 GFP_KERNEL);
-	if (!nklist)
-		goto nomem;
-	nklist->maxkeys = klist->maxkeys;
-	nklist->nkeys = klist->nkeys - 1;
-
-	if (loop > 0)
-		memcpy(&nklist->keys[0],
-		       &klist->keys[0],
-		       loop * sizeof(struct key *));
-
-	if (loop < nklist->nkeys)
-		memcpy(&nklist->keys[loop],
-		       &klist->keys[loop + 1],
-		       (nklist->nkeys - loop) * sizeof(struct key *));
-
-	/* adjust the user's quota */
-	key_payload_reserve(keyring,
-			    keyring->datalen - KEYQUOTA_LINK_BYTES);
-
-	rcu_assign_pointer(keyring->payload.subscriptions, nklist);
-
-	up_write(&keyring->sem);
-
-	/* schedule for later cleanup */
-	klist->delkey = loop;
-	call_rcu(&klist->rcu, keyring_unlink_rcu_disposal);
+	if (edit == NULL)
+		goto error;
 
+	assoc_array_apply_edit(edit);
 	ret = 0;
 
 error:
-	return ret;
-nomem:
-	ret = -ENOMEM;
 	up_write(&keyring->sem);
-	goto error;
+	return ret;
 }
 EXPORT_SYMBOL(key_unlink);
 
-/*
- * Dispose of a keyring list after the RCU grace period, releasing the keys it
- * links to.
- */
-static void keyring_clear_rcu_disposal(struct rcu_head *rcu)
-{
-	struct keyring_list *klist;
-	int loop;
-
-	klist = container_of(rcu, struct keyring_list, rcu);
-
-	for (loop = klist->nkeys - 1; loop >= 0; loop--)
-		key_put(rcu_access_pointer(klist->keys[loop]));
-
-	kfree(klist);
-}
-
 /**
  * keyring_clear - Clear a keyring
  * @keyring: The keyring to clear.
@@ -1130,33 +1256,25 @@ static void keyring_clear_rcu_disposal(struct rcu_head *rcu)
  */
 int keyring_clear(struct key *keyring)
 {
-	struct keyring_list *klist;
+	struct assoc_array_edit *edit;
 	int ret;
 
-	ret = -ENOTDIR;
-	if (keyring->type == &key_type_keyring) {
-		/* detach the pointer block with the locks held */
-		down_write(&keyring->sem);
-
-		klist = rcu_dereference_locked_keyring(keyring);
-		if (klist) {
-			/* adjust the quota */
-			key_payload_reserve(keyring,
-					    sizeof(struct keyring_list));
-
-			rcu_assign_pointer(keyring->payload.subscriptions,
-					   NULL);
-		}
-
-		up_write(&keyring->sem);
+	if (keyring->type != &key_type_keyring)
+		return -ENOTDIR;
 
-		/* free the keys after the locks have been dropped */
-		if (klist)
-			call_rcu(&klist->rcu, keyring_clear_rcu_disposal);
+	down_write(&keyring->sem);
 
+	edit = assoc_array_clear(&keyring->keys, &keyring_assoc_array_ops);
+	if (IS_ERR(edit)) {
+		ret = PTR_ERR(edit);
+	} else {
+		if (edit)
+			assoc_array_apply_edit(edit);
+		key_payload_reserve(keyring, 0);
 		ret = 0;
 	}
 
+	up_write(&keyring->sem);
 	return ret;
 }
 EXPORT_SYMBOL(keyring_clear);
@@ -1168,17 +1286,25 @@ EXPORT_SYMBOL(keyring_clear);
  */
 static void keyring_revoke(struct key *keyring)
 {
-	struct keyring_list *klist;
+	struct assoc_array_edit *edit;
 
-	klist = rcu_dereference_locked_keyring(keyring);
+	edit = assoc_array_clear(&keyring->keys, &keyring_assoc_array_ops);
+	if (!IS_ERR(edit)) {
+		if (edit)
+			assoc_array_apply_edit(edit);
+		key_payload_reserve(keyring, 0);
+	}
+}
 
-	/* adjust the quota */
-	key_payload_reserve(keyring, 0);
+static bool gc_iterator(void *object, void *iterator_data)
+{
+	struct key *key = keyring_ptr_to_key(object);
+	time_t *limit = iterator_data;
 
-	if (klist) {
-		rcu_assign_pointer(keyring->payload.subscriptions, NULL);
-		call_rcu(&klist->rcu, keyring_clear_rcu_disposal);
-	}
+	if (key_is_dead(key, *limit))
+		return false;
+	key_get(key);
+	return true;
 }
 
 /*
@@ -1191,88 +1317,12 @@ static void keyring_revoke(struct key *keyring)
  */
 void keyring_gc(struct key *keyring, time_t limit)
 {
-	struct keyring_list *klist, *new;
-	struct key *key;
-	int loop, keep, max;
-
 	kenter("{%x,%s}", key_serial(keyring), keyring->description);
 
 	down_write(&keyring->sem);
-
-	klist = rcu_dereference_locked_keyring(keyring);
-	if (!klist)
-		goto no_klist;
-
-	/* work out how many subscriptions we're keeping */
-	keep = 0;
-	for (loop = klist->nkeys - 1; loop >= 0; loop--)
-		if (!key_is_dead(rcu_deref_link_locked(klist, loop, keyring),
-				 limit))
-			keep++;
-
-	if (keep == klist->nkeys)
-		goto just_return;
-
-	/* allocate a new keyring payload */
-	max = roundup(keep, 4);
-	new = kmalloc(sizeof(struct keyring_list) + max * sizeof(struct key *),
-		      GFP_KERNEL);
-	if (!new)
-		goto nomem;
-	new->maxkeys = max;
-	new->nkeys = 0;
-	new->delkey = 0;
-
-	/* install the live keys
-	 * - must take care as expired keys may be updated back to life
-	 */
-	keep = 0;
-	for (loop = klist->nkeys - 1; loop >= 0; loop--) {
-		key = rcu_deref_link_locked(klist, loop, keyring);
-		if (!key_is_dead(key, limit)) {
-			if (keep >= max)
-				goto discard_new;
-			RCU_INIT_POINTER(new->keys[keep++], key_get(key));
-		}
-	}
-	new->nkeys = keep;
-
-	/* adjust the quota */
-	key_payload_reserve(keyring,
-			    sizeof(struct keyring_list) +
-			    KEYQUOTA_LINK_BYTES * keep);
-
-	if (keep == 0) {
-		rcu_assign_pointer(keyring->payload.subscriptions, NULL);
-		kfree(new);
-	} else {
-		rcu_assign_pointer(keyring->payload.subscriptions, new);
-	}
-
-	up_write(&keyring->sem);
-
-	call_rcu(&klist->rcu, keyring_clear_rcu_disposal);
-	kleave(" [yes]");
-	return;
-
-discard_new:
-	new->nkeys = keep;
-	keyring_clear_rcu_disposal(&new->rcu);
+	assoc_array_gc(&keyring->keys, &keyring_assoc_array_ops,
+		       gc_iterator, &limit);
 	up_write(&keyring->sem);
-	kleave(" [discard]");
-	return;
 
-just_return:
-	up_write(&keyring->sem);
-	kleave(" [no dead]");
-	return;
-
-no_klist:
-	up_write(&keyring->sem);
-	kleave(" [no_klist]");
-	return;
-
-nomem:
-	up_write(&keyring->sem);
-	kleave(" [oom]");
+	kleave("");
 }
diff --git a/security/keys/request_key.c b/security/keys/request_key.c
index ab75df4745af..df94827103d0 100644
--- a/security/keys/request_key.c
+++ b/security/keys/request_key.c
@@ -351,7 +351,7 @@ static int construct_alloc_key(struct keyring_search_context *ctx,
 			       struct key_user *user,
 			       struct key **_key)
 {
-	unsigned long prealloc;
+	struct assoc_array_edit *edit;
 	struct key *key;
 	key_perm_t perm;
 	key_ref_t key_ref;
@@ -380,7 +380,7 @@ static int construct_alloc_key(struct keyring_search_context *ctx,
 	set_bit(KEY_FLAG_USER_CONSTRUCT, &key->flags);
 
 	if (dest_keyring) {
-		ret = __key_link_begin(dest_keyring, &ctx->index_key, &prealloc);
+		ret = __key_link_begin(dest_keyring, &ctx->index_key, &edit);
 		if (ret < 0)
 			goto link_prealloc_failed;
 	}
@@ -395,11 +395,11 @@ static int construct_alloc_key(struct keyring_search_context *ctx,
 		goto key_already_present;
 
 	if (dest_keyring)
-		__key_link(dest_keyring, key, &prealloc);
+		__key_link(key, &edit);
 
 	mutex_unlock(&key_construction_mutex);
 	if (dest_keyring)
-		__key_link_end(dest_keyring, &ctx->index_key, prealloc);
+		__key_link_end(dest_keyring, &ctx->index_key, edit);
 	mutex_unlock(&user->cons_lock);
 	*_key = key;
 	kleave(" = 0 [%d]", key_serial(key));
@@ -414,8 +414,8 @@ key_already_present:
 	if (dest_keyring) {
 		ret = __key_link_check_live_key(dest_keyring, key);
 		if (ret == 0)
-			__key_link(dest_keyring, key, &prealloc);
-		__key_link_end(dest_keyring, &ctx->index_key, prealloc);
+			__key_link(key, &edit);
+		__key_link_end(dest_keyring, &ctx->index_key, edit);
 		if (ret < 0)
 			goto link_check_failed;
 	}
-- 
cgit v1.2.3


From ab3c3587f8cda9083209a61dbe3a4407d3cada10 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Tue, 24 Sep 2013 10:35:18 +0100
Subject: KEYS: Implement a big key type that can save to tmpfs

Implement a big key type that can save its contents to tmpfs and thus
swapspace when memory is tight.  This is useful for Kerberos ticket caches.

Signed-off-by: David Howells <dhowells@redhat.com>
Tested-by: Simo Sorce <simo@redhat.com>
---
 include/keys/big_key-type.h |  25 ++++++
 include/linux/key.h         |   1 +
 security/keys/Kconfig       |  11 +++
 security/keys/Makefile      |   1 +
 security/keys/big_key.c     | 204 ++++++++++++++++++++++++++++++++++++++++++++
 5 files changed, 242 insertions(+)
 create mode 100644 include/keys/big_key-type.h
 create mode 100644 security/keys/big_key.c

(limited to 'security')

diff --git a/include/keys/big_key-type.h b/include/keys/big_key-type.h
new file mode 100644
index 000000000000..d69bc8af3292
--- /dev/null
+++ b/include/keys/big_key-type.h
@@ -0,0 +1,25 @@
+/* Big capacity key type.
+ *
+ * Copyright (C) 2013 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#ifndef _KEYS_BIG_KEY_TYPE_H
+#define _KEYS_BIG_KEY_TYPE_H
+
+#include <linux/key-type.h>
+
+extern struct key_type key_type_big_key;
+
+extern int big_key_instantiate(struct key *key, struct key_preparsed_payload *prep);
+extern void big_key_revoke(struct key *key);
+extern void big_key_destroy(struct key *key);
+extern void big_key_describe(const struct key *big_key, struct seq_file *m);
+extern long big_key_read(const struct key *key, char __user *buffer, size_t buflen);
+
+#endif /* _KEYS_BIG_KEY_TYPE_H */
diff --git a/include/linux/key.h b/include/linux/key.h
index 2417f789d29b..010dbb618aca 100644
--- a/include/linux/key.h
+++ b/include/linux/key.h
@@ -201,6 +201,7 @@ struct key {
 			unsigned long		value;
 			void __rcu		*rcudata;
 			void			*data;
+			void			*data2[2];
 		} payload;
 		struct assoc_array keys;
 	};
diff --git a/security/keys/Kconfig b/security/keys/Kconfig
index 15e0dfe8c80f..b56362275ec8 100644
--- a/security/keys/Kconfig
+++ b/security/keys/Kconfig
@@ -20,6 +20,17 @@ config KEYS
 
 	  If you are unsure as to whether this is required, answer N.
 
+config BIG_KEYS
+	tristate "Large payload keys"
+	depends on KEYS
+	depends on TMPFS
+	help
+	  This option provides support for holding large keys within the kernel
+	  (for example Kerberos ticket caches).  The data may be stored out to
+	  swapspace by tmpfs.
+
+	  If you are unsure as to whether this is required, answer N.
+
 config TRUSTED_KEYS
 	tristate "TRUSTED KEYS"
 	depends on KEYS && TCG_TPM
diff --git a/security/keys/Makefile b/security/keys/Makefile
index 504aaa008388..c487c77a00be 100644
--- a/security/keys/Makefile
+++ b/security/keys/Makefile
@@ -22,5 +22,6 @@ obj-$(CONFIG_SYSCTL) += sysctl.o
 #
 # Key types
 #
+obj-$(CONFIG_BIG_KEYS) += big_key.o
 obj-$(CONFIG_TRUSTED_KEYS) += trusted.o
 obj-$(CONFIG_ENCRYPTED_KEYS) += encrypted-keys/
diff --git a/security/keys/big_key.c b/security/keys/big_key.c
new file mode 100644
index 000000000000..5f9defc4a807
--- /dev/null
+++ b/security/keys/big_key.c
@@ -0,0 +1,204 @@
+/* Large capacity key type
+ *
+ * Copyright (C) 2013 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public Licence
+ * as published by the Free Software Foundation; either version
+ * 2 of the Licence, or (at your option) any later version.
+ */
+
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/seq_file.h>
+#include <linux/file.h>
+#include <linux/shmem_fs.h>
+#include <linux/err.h>
+#include <keys/user-type.h>
+#include <keys/big_key-type.h>
+
+MODULE_LICENSE("GPL");
+
+/*
+ * If the data is under this limit, there's no point creating a shm file to
+ * hold it as the permanently resident metadata for the shmem fs will be at
+ * least as large as the data.
+ */
+#define BIG_KEY_FILE_THRESHOLD (sizeof(struct inode) + sizeof(struct dentry))
+
+/*
+ * big_key defined keys take an arbitrary string as the description and an
+ * arbitrary blob of data as the payload
+ */
+struct key_type key_type_big_key = {
+	.name			= "big_key",
+	.def_lookup_type	= KEYRING_SEARCH_LOOKUP_DIRECT,
+	.instantiate		= big_key_instantiate,
+	.match			= user_match,
+	.revoke			= big_key_revoke,
+	.destroy		= big_key_destroy,
+	.describe		= big_key_describe,
+	.read			= big_key_read,
+};
+
+/*
+ * Instantiate a big key
+ */
+int big_key_instantiate(struct key *key, struct key_preparsed_payload *prep)
+{
+	struct path *path = (struct path *)&key->payload.data2;
+	struct file *file;
+	ssize_t written;
+	size_t datalen = prep->datalen;
+	int ret;
+
+	ret = -EINVAL;
+	if (datalen <= 0 || datalen > 1024 * 1024 || !prep->data)
+		goto error;
+
+	/* Set an arbitrary quota */
+	ret = key_payload_reserve(key, 16);
+	if (ret < 0)
+		goto error;
+
+	key->type_data.x[1] = datalen;
+
+	if (datalen > BIG_KEY_FILE_THRESHOLD) {
+		/* Create a shmem file to store the data in.  This will permit the data
+		 * to be swapped out if needed.
+		 *
+		 * TODO: Encrypt the stored data with a temporary key.
+		 */
+		file = shmem_file_setup("", datalen, 0);
+		if (IS_ERR(file))
+			goto err_quota;
+
+		written = kernel_write(file, prep->data, prep->datalen, 0);
+		if (written != datalen) {
+			if (written >= 0)
+				ret = -ENOMEM;
+			goto err_fput;
+		}
+
+		/* Pin the mount and dentry to the key so that we can open it again
+		 * later
+		 */
+		*path = file->f_path;
+		path_get(path);
+		fput(file);
+	} else {
+		/* Just store the data in a buffer */
+		void *data = kmalloc(datalen, GFP_KERNEL);
+		if (!data) {
+			ret = -ENOMEM;
+			goto err_quota;
+		}
+
+		key->payload.data = memcpy(data, prep->data, prep->datalen);
+	}
+	return 0;
+
+err_fput:
+	fput(file);
+err_quota:
+	key_payload_reserve(key, 0);
+error:
+	return ret;
+}
+
+/*
+ * dispose of the links from a revoked keyring
+ * - called with the key sem write-locked
+ */
+void big_key_revoke(struct key *key)
+{
+	struct path *path = (struct path *)&key->payload.data2;
+
+	/* clear the quota */
+	key_payload_reserve(key, 0);
+	if (key_is_instantiated(key) && key->type_data.x[1] > BIG_KEY_FILE_THRESHOLD)
+		vfs_truncate(path, 0);
+}
+
+/*
+ * dispose of the data dangling from the corpse of a big_key key
+ */
+void big_key_destroy(struct key *key)
+{
+	if (key->type_data.x[1] > BIG_KEY_FILE_THRESHOLD) {
+		struct path *path = (struct path *)&key->payload.data2;
+		path_put(path);
+		path->mnt = NULL;
+		path->dentry = NULL;
+	} else {
+		kfree(key->payload.data);
+		key->payload.data = NULL;
+	}
+}
+
+/*
+ * describe the big_key key
+ */
+void big_key_describe(const struct key *key, struct seq_file *m)
+{
+	unsigned long datalen = key->type_data.x[1];
+
+	seq_puts(m, key->description);
+
+	if (key_is_instantiated(key))
+		seq_printf(m, ": %lu [%s]",
+			   datalen,
+			   datalen > BIG_KEY_FILE_THRESHOLD ? "file" : "buff");
+}
+
+/*
+ * read the key data
+ * - the key's semaphore is read-locked
+ */
+long big_key_read(const struct key *key, char __user *buffer, size_t buflen)
+{
+	unsigned long datalen = key->type_data.x[1];
+	long ret;
+
+	if (!buffer || buflen < datalen)
+		return datalen;
+
+	if (datalen > BIG_KEY_FILE_THRESHOLD) {
+		struct path *path = (struct path *)&key->payload.data2;
+		struct file *file;
+		loff_t pos;
+
+		file = dentry_open(path, O_RDONLY, current_cred());
+		if (IS_ERR(file))
+			return PTR_ERR(file);
+
+		pos = 0;
+		ret = vfs_read(file, buffer, datalen, &pos);
+		fput(file);
+		if (ret >= 0 && ret != datalen)
+			ret = -EIO;
+	} else {
+		ret = datalen;
+		if (copy_to_user(buffer, key->payload.data, datalen) != 0)
+			ret = -EFAULT;
+	}
+
+	return ret;
+}
+
+/*
+ * Module stuff
+ */
+static int __init big_key_init(void)
+{
+	return register_key_type(&key_type_big_key);
+}
+
+static void __exit big_key_cleanup(void)
+{
+	unregister_key_type(&key_type_big_key);
+}
+
+module_init(big_key_init);
+module_exit(big_key_cleanup);
-- 
cgit v1.2.3


From f36f8c75ae2e7d4da34f4c908cebdb4aa42c977e Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Tue, 24 Sep 2013 10:35:19 +0100
Subject: KEYS: Add per-user_namespace registers for persistent per-UID
 kerberos caches

Add support for per-user_namespace registers of persistent per-UID kerberos
caches held within the kernel.

This allows the kerberos cache to be retained beyond the life of all a user's
processes so that the user's cron jobs can work.

The kerberos cache is envisioned as a keyring/key tree looking something like:

	struct user_namespace
	  \___ .krb_cache keyring		- The register
		\___ _krb.0 keyring		- Root's Kerberos cache
		\___ _krb.5000 keyring		- User 5000's Kerberos cache
		\___ _krb.5001 keyring		- User 5001's Kerberos cache
			\___ tkt785 big_key	- A ccache blob
			\___ tkt12345 big_key	- Another ccache blob

Or possibly:

	struct user_namespace
	  \___ .krb_cache keyring		- The register
		\___ _krb.0 keyring		- Root's Kerberos cache
		\___ _krb.5000 keyring		- User 5000's Kerberos cache
		\___ _krb.5001 keyring		- User 5001's Kerberos cache
			\___ tkt785 keyring	- A ccache
				\___ krbtgt/REDHAT.COM@REDHAT.COM big_key
				\___ http/REDHAT.COM@REDHAT.COM user
				\___ afs/REDHAT.COM@REDHAT.COM user
				\___ nfs/REDHAT.COM@REDHAT.COM user
				\___ krbtgt/KERNEL.ORG@KERNEL.ORG big_key
				\___ http/KERNEL.ORG@KERNEL.ORG big_key

What goes into a particular Kerberos cache is entirely up to userspace.  Kernel
support is limited to giving you the Kerberos cache keyring that you want.

The user asks for their Kerberos cache by:

	krb_cache = keyctl_get_krbcache(uid, dest_keyring);

The uid is -1 or the user's own UID for the user's own cache or the uid of some
other user's cache (requires CAP_SETUID).  This permits rpc.gssd or whatever to
mess with the cache.

The cache returned is a keyring named "_krb.<uid>" that the possessor can read,
search, clear, invalidate, unlink from and add links to.  Active LSMs get a
chance to rule on whether the caller is permitted to make a link.

Each uid's cache keyring is created when it first accessed and is given a
timeout that is extended each time this function is called so that the keyring
goes away after a while.  The timeout is configurable by sysctl but defaults to
three days.

Each user_namespace struct gets a lazily-created keyring that serves as the
register.  The cache keyrings are added to it.  This means that standard key
search and garbage collection facilities are available.

The user_namespace struct's register goes away when it does and anything left
in it is then automatically gc'd.

Signed-off-by: David Howells <dhowells@redhat.com>
Tested-by: Simo Sorce <simo@redhat.com>
cc: Serge E. Hallyn <serge.hallyn@ubuntu.com>
cc: Eric W. Biederman <ebiederm@xmission.com>
---
 include/linux/user_namespace.h |   6 ++
 include/uapi/linux/keyctl.h    |   1 +
 kernel/user.c                  |   4 +
 kernel/user_namespace.c        |   6 ++
 security/keys/Kconfig          |  17 +++++
 security/keys/Makefile         |   1 +
 security/keys/compat.c         |   3 +
 security/keys/internal.h       |   9 +++
 security/keys/keyctl.c         |   3 +
 security/keys/persistent.c     | 169 +++++++++++++++++++++++++++++++++++++++++
 security/keys/sysctl.c         |  11 +++
 11 files changed, 230 insertions(+)
 create mode 100644 security/keys/persistent.c

(limited to 'security')

diff --git a/include/linux/user_namespace.h b/include/linux/user_namespace.h
index 4db29859464f..4836ba3c1cd8 100644
--- a/include/linux/user_namespace.h
+++ b/include/linux/user_namespace.h
@@ -27,6 +27,12 @@ struct user_namespace {
 	kuid_t			owner;
 	kgid_t			group;
 	unsigned int		proc_inum;
+
+	/* Register of per-UID persistent keyrings for this namespace */
+#ifdef CONFIG_PERSISTENT_KEYRINGS
+	struct key		*persistent_keyring_register;
+	struct rw_semaphore	persistent_keyring_register_sem;
+#endif
 };
 
 extern struct user_namespace init_user_ns;
diff --git a/include/uapi/linux/keyctl.h b/include/uapi/linux/keyctl.h
index c9b7f4faf97a..840cb990abe2 100644
--- a/include/uapi/linux/keyctl.h
+++ b/include/uapi/linux/keyctl.h
@@ -56,5 +56,6 @@
 #define KEYCTL_REJECT			19	/* reject a partially constructed key */
 #define KEYCTL_INSTANTIATE_IOV		20	/* instantiate a partially constructed key */
 #define KEYCTL_INVALIDATE		21	/* invalidate a key */
+#define KEYCTL_GET_PERSISTENT		22	/* get a user's persistent keyring */
 
 #endif /*  _LINUX_KEYCTL_H */
diff --git a/kernel/user.c b/kernel/user.c
index 5bbb91988e69..a3a0dbfda329 100644
--- a/kernel/user.c
+++ b/kernel/user.c
@@ -51,6 +51,10 @@ struct user_namespace init_user_ns = {
 	.owner = GLOBAL_ROOT_UID,
 	.group = GLOBAL_ROOT_GID,
 	.proc_inum = PROC_USER_INIT_INO,
+#ifdef CONFIG_KEYS_KERBEROS_CACHE
+	.krb_cache_register_sem =
+	__RWSEM_INITIALIZER(init_user_ns.krb_cache_register_sem),
+#endif
 };
 EXPORT_SYMBOL_GPL(init_user_ns);
 
diff --git a/kernel/user_namespace.c b/kernel/user_namespace.c
index 13fb1134ba58..240fb62cf394 100644
--- a/kernel/user_namespace.c
+++ b/kernel/user_namespace.c
@@ -101,6 +101,9 @@ int create_user_ns(struct cred *new)
 
 	set_cred_user_ns(new, ns);
 
+#ifdef CONFIG_PERSISTENT_KEYRINGS
+	init_rwsem(&ns->persistent_keyring_register_sem);
+#endif
 	return 0;
 }
 
@@ -130,6 +133,9 @@ void free_user_ns(struct user_namespace *ns)
 
 	do {
 		parent = ns->parent;
+#ifdef CONFIG_PERSISTENT_KEYRINGS
+		key_put(ns->persistent_keyring_register);
+#endif
 		proc_free_inum(ns->proc_inum);
 		kmem_cache_free(user_ns_cachep, ns);
 		ns = parent;
diff --git a/security/keys/Kconfig b/security/keys/Kconfig
index b56362275ec8..53d8748c9564 100644
--- a/security/keys/Kconfig
+++ b/security/keys/Kconfig
@@ -20,6 +20,23 @@ config KEYS
 
 	  If you are unsure as to whether this is required, answer N.
 
+config PERSISTENT_KEYRINGS
+	bool "Enable register of persistent per-UID keyrings"
+	depends on KEYS
+	help
+	  This option provides a register of persistent per-UID keyrings,
+	  primarily aimed at Kerberos key storage.  The keyrings are persistent
+	  in the sense that they stay around after all processes of that UID
+	  have exited, not that they survive the machine being rebooted.
+
+	  A particular keyring may be accessed by either the user whose keyring
+	  it is or by a process with administrative privileges.  The active
+	  LSMs gets to rule on which admin-level processes get to access the
+	  cache.
+
+	  Keyrings are created and added into the register upon demand and get
+	  removed if they expire (a default timeout is set upon creation).
+
 config BIG_KEYS
 	tristate "Large payload keys"
 	depends on KEYS
diff --git a/security/keys/Makefile b/security/keys/Makefile
index c487c77a00be..dfb3a7bededf 100644
--- a/security/keys/Makefile
+++ b/security/keys/Makefile
@@ -18,6 +18,7 @@ obj-y := \
 obj-$(CONFIG_KEYS_COMPAT) += compat.o
 obj-$(CONFIG_PROC_FS) += proc.o
 obj-$(CONFIG_SYSCTL) += sysctl.o
+obj-$(CONFIG_PERSISTENT_KEYRINGS) += persistent.o
 
 #
 # Key types
diff --git a/security/keys/compat.c b/security/keys/compat.c
index d65fa7fa29ba..bbd32c729dbb 100644
--- a/security/keys/compat.c
+++ b/security/keys/compat.c
@@ -138,6 +138,9 @@ asmlinkage long compat_sys_keyctl(u32 option,
 	case KEYCTL_INVALIDATE:
 		return keyctl_invalidate_key(arg2);
 
+	case KEYCTL_GET_PERSISTENT:
+		return keyctl_get_persistent(arg2, arg3);
+
 	default:
 		return -EOPNOTSUPP;
 	}
diff --git a/security/keys/internal.h b/security/keys/internal.h
index 581c6f688352..80b2aac4f50c 100644
--- a/security/keys/internal.h
+++ b/security/keys/internal.h
@@ -255,6 +255,15 @@ extern long keyctl_invalidate_key(key_serial_t);
 extern long keyctl_instantiate_key_common(key_serial_t,
 					  const struct iovec *,
 					  unsigned, size_t, key_serial_t);
+#ifdef CONFIG_PERSISTENT_KEYRINGS
+extern long keyctl_get_persistent(uid_t, key_serial_t);
+extern unsigned persistent_keyring_expiry;
+#else
+static inline long keyctl_get_persistent(uid_t uid, key_serial_t destring)
+{
+	return -EOPNOTSUPP;
+}
+#endif
 
 /*
  * Debugging key validation
diff --git a/security/keys/keyctl.c b/security/keys/keyctl.c
index 33cfd27b4de2..cee72ce64222 100644
--- a/security/keys/keyctl.c
+++ b/security/keys/keyctl.c
@@ -1667,6 +1667,9 @@ SYSCALL_DEFINE5(keyctl, int, option, unsigned long, arg2, unsigned long, arg3,
 	case KEYCTL_INVALIDATE:
 		return keyctl_invalidate_key((key_serial_t) arg2);
 
+	case KEYCTL_GET_PERSISTENT:
+		return keyctl_get_persistent((uid_t)arg2, (key_serial_t)arg3);
+
 	default:
 		return -EOPNOTSUPP;
 	}
diff --git a/security/keys/persistent.c b/security/keys/persistent.c
new file mode 100644
index 000000000000..82f4957a7acf
--- /dev/null
+++ b/security/keys/persistent.c
@@ -0,0 +1,169 @@
+/* General persistent per-UID keyrings register
+ *
+ * Copyright (C) 2013 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public Licence
+ * as published by the Free Software Foundation; either version
+ * 2 of the Licence, or (at your option) any later version.
+ */
+
+#include <linux/user_namespace.h>
+#include "internal.h"
+
+unsigned persistent_keyring_expiry = 3 * 24 * 3600; /* Expire after 3 days of non-use */
+
+/*
+ * Create the persistent keyring register for the current user namespace.
+ *
+ * Called with the namespace's sem locked for writing.
+ */
+static int key_create_persistent_register(struct user_namespace *ns)
+{
+	struct key *reg = keyring_alloc(".persistent_register",
+					KUIDT_INIT(0), KGIDT_INIT(0),
+					current_cred(),
+					((KEY_POS_ALL & ~KEY_POS_SETATTR) |
+					 KEY_USR_VIEW | KEY_USR_READ),
+					KEY_ALLOC_NOT_IN_QUOTA, NULL);
+	if (IS_ERR(reg))
+		return PTR_ERR(reg);
+
+	ns->persistent_keyring_register = reg;
+	return 0;
+}
+
+/*
+ * Create the persistent keyring for the specified user.
+ *
+ * Called with the namespace's sem locked for writing.
+ */
+static key_ref_t key_create_persistent(struct user_namespace *ns, kuid_t uid,
+				       struct keyring_index_key *index_key)
+{
+	struct key *persistent;
+	key_ref_t reg_ref, persistent_ref;
+
+	if (!ns->persistent_keyring_register) {
+		long err = key_create_persistent_register(ns);
+		if (err < 0)
+			return ERR_PTR(err);
+	} else {
+		reg_ref = make_key_ref(ns->persistent_keyring_register, true);
+		persistent_ref = find_key_to_update(reg_ref, index_key);
+		if (persistent_ref)
+			return persistent_ref;
+	}
+
+	persistent = keyring_alloc(index_key->description,
+				   uid, INVALID_GID, current_cred(),
+				   ((KEY_POS_ALL & ~KEY_POS_SETATTR) |
+				    KEY_USR_VIEW | KEY_USR_READ),
+				   KEY_ALLOC_NOT_IN_QUOTA,
+				   ns->persistent_keyring_register);
+	if (IS_ERR(persistent))
+		return ERR_CAST(persistent);
+
+	return make_key_ref(persistent, true);
+}
+
+/*
+ * Get the persistent keyring for a specific UID and link it to the nominated
+ * keyring.
+ */
+static long key_get_persistent(struct user_namespace *ns, kuid_t uid,
+			       key_ref_t dest_ref)
+{
+	struct keyring_index_key index_key;
+	struct key *persistent;
+	key_ref_t reg_ref, persistent_ref;
+	char buf[32];
+	long ret;
+
+	/* Look in the register if it exists */
+	index_key.type = &key_type_keyring;
+	index_key.description = buf;
+	index_key.desc_len = sprintf(buf, "_persistent.%u", from_kuid(ns, uid));
+
+	if (ns->persistent_keyring_register) {
+		reg_ref = make_key_ref(ns->persistent_keyring_register, true);
+		down_read(&ns->persistent_keyring_register_sem);
+		persistent_ref = find_key_to_update(reg_ref, &index_key);
+		up_read(&ns->persistent_keyring_register_sem);
+
+		if (persistent_ref)
+			goto found;
+	}
+
+	/* It wasn't in the register, so we'll need to create it.  We might
+	 * also need to create the register.
+	 */
+	down_write(&ns->persistent_keyring_register_sem);
+	persistent_ref = key_create_persistent(ns, uid, &index_key);
+	up_write(&ns->persistent_keyring_register_sem);
+	if (!IS_ERR(persistent_ref))
+		goto found;
+
+	return PTR_ERR(persistent_ref);
+
+found:
+	ret = key_task_permission(persistent_ref, current_cred(), KEY_LINK);
+	if (ret == 0) {
+		persistent = key_ref_to_ptr(persistent_ref);
+		ret = key_link(key_ref_to_ptr(dest_ref), persistent);
+		if (ret == 0) {
+			key_set_timeout(persistent, persistent_keyring_expiry);
+			ret = persistent->serial;		
+		}
+	}
+
+	key_ref_put(persistent_ref);
+	return ret;
+}
+
+/*
+ * Get the persistent keyring for a specific UID and link it to the nominated
+ * keyring.
+ */
+long keyctl_get_persistent(uid_t _uid, key_serial_t destid)
+{
+	struct user_namespace *ns = current_user_ns();
+	key_ref_t dest_ref;
+	kuid_t uid;
+	long ret;
+
+	/* -1 indicates the current user */
+	if (_uid == (uid_t)-1) {
+		uid = current_uid();
+	} else {
+		uid = make_kuid(ns, _uid);
+		if (!uid_valid(uid))
+			return -EINVAL;
+
+		/* You can only see your own persistent cache if you're not
+		 * sufficiently privileged.
+		 */
+		if (uid_eq(uid, current_uid()) &&
+		    uid_eq(uid, current_suid()) &&
+		    uid_eq(uid, current_euid()) &&
+		    uid_eq(uid, current_fsuid()) &&
+		    !ns_capable(ns, CAP_SETUID))
+			return -EPERM;
+	}
+
+	/* There must be a destination keyring */
+	dest_ref = lookup_user_key(destid, KEY_LOOKUP_CREATE, KEY_WRITE);
+	if (IS_ERR(dest_ref))
+		return PTR_ERR(dest_ref);
+	if (key_ref_to_ptr(dest_ref)->type != &key_type_keyring) {
+		ret = -ENOTDIR;
+		goto out_put_dest;
+	}
+
+	ret = key_get_persistent(ns, uid, dest_ref);
+
+out_put_dest:
+	key_ref_put(dest_ref);
+	return ret;
+}
diff --git a/security/keys/sysctl.c b/security/keys/sysctl.c
index ee32d181764a..8c0af08760c8 100644
--- a/security/keys/sysctl.c
+++ b/security/keys/sysctl.c
@@ -61,5 +61,16 @@ ctl_table key_sysctls[] = {
 		.extra1 = (void *) &zero,
 		.extra2 = (void *) &max,
 	},
+#ifdef CONFIG_PERSISTENT_KEYRINGS
+	{
+		.procname = "persistent_keyring_expiry",
+		.data = &persistent_keyring_expiry,
+		.maxlen = sizeof(unsigned),
+		.mode = 0644,
+		.proc_handler = proc_dointvec_minmax,
+		.extra1 = (void *) &zero,
+		.extra2 = (void *) &max,
+	},
+#endif
 	{ }
 };
-- 
cgit v1.2.3


From 008643b86c5f33c115c84ccdda1725cac3ad50ad Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Fri, 30 Aug 2013 16:07:37 +0100
Subject: KEYS: Add a 'trusted' flag and a 'trusted only' flag

Add KEY_FLAG_TRUSTED to indicate that a key either comes from a trusted source
or had a cryptographic signature chain that led back to a trusted key the
kernel already possessed.

Add KEY_FLAGS_TRUSTED_ONLY to indicate that a keyring will only accept links to
keys marked with KEY_FLAGS_TRUSTED.

Signed-off-by: David Howells <dhowells@redhat.com>
Reviewed-by: Kees Cook <keescook@chromium.org>
---
 include/linux/key-type.h | 1 +
 include/linux/key.h      | 3 +++
 kernel/system_keyring.c  | 4 +++-
 security/keys/key.c      | 8 ++++++++
 security/keys/keyring.c  | 4 ++++
 5 files changed, 19 insertions(+), 1 deletion(-)

(limited to 'security')

diff --git a/include/linux/key-type.h b/include/linux/key-type.h
index f58737bcb050..a74c3a84dfdd 100644
--- a/include/linux/key-type.h
+++ b/include/linux/key-type.h
@@ -45,6 +45,7 @@ struct key_preparsed_payload {
 	const void	*data;		/* Raw data */
 	size_t		datalen;	/* Raw datalen */
 	size_t		quotalen;	/* Quota length for proposed payload */
+	bool		trusted;	/* True if key is trusted */
 };
 
 typedef int (*request_key_actor_t)(struct key_construction *key,
diff --git a/include/linux/key.h b/include/linux/key.h
index 010dbb618aca..80d677483e31 100644
--- a/include/linux/key.h
+++ b/include/linux/key.h
@@ -168,6 +168,8 @@ struct key {
 #define KEY_FLAG_NEGATIVE	5	/* set if key is negative */
 #define KEY_FLAG_ROOT_CAN_CLEAR	6	/* set if key can be cleared by root without permission */
 #define KEY_FLAG_INVALIDATED	7	/* set if key has been invalidated */
+#define KEY_FLAG_TRUSTED	8	/* set if key is trusted */
+#define KEY_FLAG_TRUSTED_ONLY	9	/* set if keyring only accepts links to trusted keys */
 
 	/* the key type and key description string
 	 * - the desc is used to match a key against search criteria
@@ -218,6 +220,7 @@ extern struct key *key_alloc(struct key_type *type,
 #define KEY_ALLOC_IN_QUOTA	0x0000	/* add to quota, reject if would overrun */
 #define KEY_ALLOC_QUOTA_OVERRUN	0x0001	/* add to quota, permit even if overrun */
 #define KEY_ALLOC_NOT_IN_QUOTA	0x0002	/* not in quota */
+#define KEY_ALLOC_TRUSTED	0x0004	/* Key should be flagged as trusted */
 
 extern void key_revoke(struct key *key);
 extern void key_invalidate(struct key *key);
diff --git a/kernel/system_keyring.c b/kernel/system_keyring.c
index 51c35141a13a..5296721eca5b 100644
--- a/kernel/system_keyring.c
+++ b/kernel/system_keyring.c
@@ -40,6 +40,7 @@ static __init int system_trusted_keyring_init(void)
 	if (IS_ERR(system_trusted_keyring))
 		panic("Can't allocate system trusted keyring\n");
 
+	set_bit(KEY_FLAG_TRUSTED_ONLY, &system_trusted_keyring->flags);
 	return 0;
 }
 
@@ -82,7 +83,8 @@ static __init int load_system_certificate_list(void)
 					   plen,
 					   (KEY_POS_ALL & ~KEY_POS_SETATTR) |
 					   KEY_USR_VIEW,
-					   KEY_ALLOC_NOT_IN_QUOTA);
+					   KEY_ALLOC_NOT_IN_QUOTA |
+					   KEY_ALLOC_TRUSTED);
 		if (IS_ERR(key)) {
 			pr_err("Problem loading in-kernel X.509 certificate (%ld)\n",
 			       PTR_ERR(key));
diff --git a/security/keys/key.c b/security/keys/key.c
index a819b5c7d4ec..d331ea9ef380 100644
--- a/security/keys/key.c
+++ b/security/keys/key.c
@@ -300,6 +300,8 @@ struct key *key_alloc(struct key_type *type, const char *desc,
 
 	if (!(flags & KEY_ALLOC_NOT_IN_QUOTA))
 		key->flags |= 1 << KEY_FLAG_IN_QUOTA;
+	if (flags & KEY_ALLOC_TRUSTED)
+		key->flags |= 1 << KEY_FLAG_TRUSTED;
 
 	memset(&key->type_data, 0, sizeof(key->type_data));
 
@@ -813,6 +815,7 @@ key_ref_t key_create_or_update(key_ref_t keyring_ref,
 	prep.data = payload;
 	prep.datalen = plen;
 	prep.quotalen = index_key.type->def_datalen;
+	prep.trusted = flags & KEY_ALLOC_TRUSTED;
 	if (index_key.type->preparse) {
 		ret = index_key.type->preparse(&prep);
 		if (ret < 0) {
@@ -827,6 +830,11 @@ key_ref_t key_create_or_update(key_ref_t keyring_ref,
 	}
 	index_key.desc_len = strlen(index_key.description);
 
+	key_ref = ERR_PTR(-EPERM);
+	if (!prep.trusted && test_bit(KEY_FLAG_TRUSTED_ONLY, &keyring->flags))
+		goto error_free_prep;
+	flags |= prep.trusted ? KEY_ALLOC_TRUSTED : 0;
+
 	ret = __key_link_begin(keyring, &index_key, &edit);
 	if (ret < 0) {
 		key_ref = ERR_PTR(ret);
diff --git a/security/keys/keyring.c b/security/keys/keyring.c
index f7cdea22214f..9b6f6e09b50c 100644
--- a/security/keys/keyring.c
+++ b/security/keys/keyring.c
@@ -1183,6 +1183,10 @@ int key_link(struct key *keyring, struct key *key)
 	key_check(keyring);
 	key_check(key);
 
+	if (test_bit(KEY_FLAG_TRUSTED_ONLY, &keyring->flags) &&
+	    !test_bit(KEY_FLAG_TRUSTED, &key->flags))
+		return -EPERM;
+
 	ret = __key_link_begin(keyring, &key->index_key, &edit);
 	if (ret == 0) {
 		kdebug("begun {%d,%d}", keyring->serial, atomic_read(&keyring->usage));
-- 
cgit v1.2.3


From c124bde28bce41f9e46e32d03d134a81e116d38c Mon Sep 17 00:00:00 2001
From: Mimi Zohar <zohar@linux.vnet.ibm.com>
Date: Wed, 4 Sep 2013 13:26:22 +0100
Subject: KEYS: initialize root uid and session keyrings early

In order to create the integrity keyrings (eg. _evm, _ima), root's
uid and session keyrings need to be initialized early.

Signed-off-by: Mimi Zohar <zohar@us.ibm.com>
Signed-off-by: David Howells <dhowells@redhat.com>
---
 security/keys/process_keys.c | 10 ++++++++++
 1 file changed, 10 insertions(+)

(limited to 'security')

diff --git a/security/keys/process_keys.c b/security/keys/process_keys.c
index 68548ea6fe01..0cf8a130a267 100644
--- a/security/keys/process_keys.c
+++ b/security/keys/process_keys.c
@@ -857,3 +857,13 @@ void key_change_session_keyring(struct callback_head *twork)
 
 	commit_creds(new);
 }
+
+/*
+ * Make sure that root's user and user-session keyrings exist.
+ */
+static int __init init_root_keyring(void)
+{
+	return install_user_keyrings();
+}
+
+late_initcall(init_root_keyring);
-- 
cgit v1.2.3


From 7d1db4b242134bb4c7170f4c15491980ac064ac3 Mon Sep 17 00:00:00 2001
From: Duan Jiong <duanj.fnst@cn.fujitsu.com>
Date: Thu, 26 Sep 2013 15:52:13 -0400
Subject: selinux: Use kmemdup instead of kmalloc + memcpy

Signed-off-by: Duan Jiong <duanj.fnst@cn.fujitsu.com>
Signed-off-by: Paul Moore <paul@paul-moore.com>
---
 security/selinux/xfrm.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'security')

diff --git a/security/selinux/xfrm.c b/security/selinux/xfrm.c
index 425b9f91d755..a91d205ec0c6 100644
--- a/security/selinux/xfrm.c
+++ b/security/selinux/xfrm.c
@@ -268,10 +268,10 @@ int selinux_xfrm_policy_clone(struct xfrm_sec_ctx *old_ctx,
 	if (!old_ctx)
 		return 0;
 
-	new_ctx = kmalloc(sizeof(*old_ctx) + old_ctx->ctx_len, GFP_ATOMIC);
+	new_ctx = kmemdup(old_ctx, sizeof(*old_ctx) + old_ctx->ctx_len,
+			  GFP_ATOMIC);
 	if (!new_ctx)
 		return -ENOMEM;
-	memcpy(new_ctx, old_ctx, sizeof(*old_ctx) + old_ctx->ctx_len);
 	atomic_inc(&selinux_xfrm_refcount);
 	*new_ctxp = new_ctx;
 
-- 
cgit v1.2.3


From 42d64e1add3a1ce8a787116036163b8724362145 Mon Sep 17 00:00:00 2001
From: Paul Moore <pmoore@redhat.com>
Date: Thu, 26 Sep 2013 17:00:46 -0400
Subject: selinux: correct locking in selinux_netlbl_socket_connect)

The SELinux/NetLabel glue code has a locking bug that affects systems
with NetLabel enabled, see the kernel error message below.  This patch
corrects this problem by converting the bottom half socket lock to a
more conventional, and correct for this call-path, lock_sock() call.

 ===============================
 [ INFO: suspicious RCU usage. ]
 3.11.0-rc3+ #19 Not tainted
 -------------------------------
 net/ipv4/cipso_ipv4.c:1928 suspicious rcu_dereference_protected() usage!

 other info that might help us debug this:

 rcu_scheduler_active = 1, debug_locks = 0
 2 locks held by ping/731:
  #0:  (slock-AF_INET/1){+.-...}, at: [...] selinux_netlbl_socket_connect
  #1:  (rcu_read_lock){.+.+..}, at: [<...>] netlbl_conn_setattr

 stack backtrace:
 CPU: 1 PID: 731 Comm: ping Not tainted 3.11.0-rc3+ #19
 Hardware name: Bochs Bochs, BIOS Bochs 01/01/2011
  0000000000000001 ffff88006f659d28 ffffffff81726b6a ffff88003732c500
  ffff88006f659d58 ffffffff810e4457 ffff88006b845a00 0000000000000000
  000000000000000c ffff880075aa2f50 ffff88006f659d90 ffffffff8169bec7
 Call Trace:
  [<ffffffff81726b6a>] dump_stack+0x54/0x74
  [<ffffffff810e4457>] lockdep_rcu_suspicious+0xe7/0x120
  [<ffffffff8169bec7>] cipso_v4_sock_setattr+0x187/0x1a0
  [<ffffffff8170f317>] netlbl_conn_setattr+0x187/0x190
  [<ffffffff8170f195>] ? netlbl_conn_setattr+0x5/0x190
  [<ffffffff8131ac9e>] selinux_netlbl_socket_connect+0xae/0xc0
  [<ffffffff81303025>] selinux_socket_connect+0x135/0x170
  [<ffffffff8119d127>] ? might_fault+0x57/0xb0
  [<ffffffff812fb146>] security_socket_connect+0x16/0x20
  [<ffffffff815d3ad3>] SYSC_connect+0x73/0x130
  [<ffffffff81739a85>] ? sysret_check+0x22/0x5d
  [<ffffffff810e5e2d>] ? trace_hardirqs_on_caller+0xfd/0x1c0
  [<ffffffff81373d4e>] ? trace_hardirqs_on_thunk+0x3a/0x3f
  [<ffffffff815d52be>] SyS_connect+0xe/0x10
  [<ffffffff81739a59>] system_call_fastpath+0x16/0x1b

Cc: stable@vger.kernel.org
Signed-off-by: Paul Moore <pmoore@redhat.com>
---
 security/selinux/netlabel.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

(limited to 'security')

diff --git a/security/selinux/netlabel.c b/security/selinux/netlabel.c
index da4b8b233280..6235d052338b 100644
--- a/security/selinux/netlabel.c
+++ b/security/selinux/netlabel.c
@@ -442,8 +442,7 @@ int selinux_netlbl_socket_connect(struct sock *sk, struct sockaddr *addr)
 	    sksec->nlbl_state != NLBL_CONNLABELED)
 		return 0;
 
-	local_bh_disable();
-	bh_lock_sock_nested(sk);
+	lock_sock(sk);
 
 	/* connected sockets are allowed to disconnect when the address family
 	 * is set to AF_UNSPEC, if that is what is happening we want to reset
@@ -464,7 +463,6 @@ int selinux_netlbl_socket_connect(struct sock *sk, struct sockaddr *addr)
 		sksec->nlbl_state = NLBL_CONNLABELED;
 
 socket_connect_return:
-	bh_unlock_sock(sk);
-	local_bh_enable();
+	release_sock(sk);
 	return rc;
 }
-- 
cgit v1.2.3


From 0bbf87d852d243680ed7074110ccc1dea003b61a Mon Sep 17 00:00:00 2001
From: "Eric W. Biederman" <ebiederm@xmission.com>
Date: Sat, 28 Sep 2013 14:10:59 -0700
Subject: net ipv4: Convert ipv4.ip_local_port_range to be per netns v3

- Move sysctl_local_ports from a global variable into struct netns_ipv4.
- Modify inet_get_local_port_range to take a struct net, and update all
  of the callers.
- Move the initialization of sysctl_local_ports into
   sysctl_net_ipv4.c:ipv4_sysctl_init_net from inet_connection_sock.c

v2:
- Ensure indentation used tabs
- Fixed ip.h so it applies cleanly to todays net-next

v3:
- Compile fixes of strange callers of inet_get_local_port_range.
  This patch now successfully passes an allmodconfig build.
  Removed manual inlining of inet_get_local_port_range in ipv4_local_port_range

Originally-by: Samya <samya@twitter.com>
Acked-by: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/infiniband/core/cma.c   |  2 +-
 drivers/net/vxlan.c             |  2 +-
 include/net/ip.h                |  6 +----
 include/net/netns/ipv4.h        |  6 +++++
 net/ipv4/inet_connection_sock.c | 20 +++++-----------
 net/ipv4/inet_hashtables.c      |  2 +-
 net/ipv4/ping.c                 |  4 ++--
 net/ipv4/sysctl_net_ipv4.c      | 52 +++++++++++++++++++++++++++--------------
 net/ipv4/udp.c                  |  2 +-
 net/openvswitch/vport-vxlan.c   |  2 +-
 net/sctp/socket.c               |  2 +-
 security/selinux/hooks.c        |  2 +-
 12 files changed, 56 insertions(+), 46 deletions(-)

(limited to 'security')

diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c
index dab4b41f1715..a082fd9e7ebe 100644
--- a/drivers/infiniband/core/cma.c
+++ b/drivers/infiniband/core/cma.c
@@ -2294,7 +2294,7 @@ static int cma_alloc_any_port(struct idr *ps, struct rdma_id_private *id_priv)
 	int low, high, remaining;
 	unsigned int rover;
 
-	inet_get_local_port_range(&low, &high);
+	inet_get_local_port_range(&init_net, &low, &high);
 	remaining = (high - low) + 1;
 	rover = net_random() % remaining + low;
 retry:
diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index d1292fe746bc..c376be7b528a 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -2089,7 +2089,7 @@ static void vxlan_setup(struct net_device *dev)
 	vxlan->age_timer.function = vxlan_cleanup;
 	vxlan->age_timer.data = (unsigned long) vxlan;
 
-	inet_get_local_port_range(&low, &high);
+	inet_get_local_port_range(dev_net(dev), &low, &high);
 	vxlan->port_min = low;
 	vxlan->port_max = high;
 	vxlan->dst_port = htons(vxlan_port);
diff --git a/include/net/ip.h b/include/net/ip.h
index 77b4f9b57c28..16078f422397 100644
--- a/include/net/ip.h
+++ b/include/net/ip.h
@@ -217,11 +217,7 @@ static inline void snmp_mib_free(void __percpu *ptr[SNMP_ARRAY_SZ])
 	}
 }
 
-extern struct local_ports {
-	seqlock_t	lock;
-	int		range[2];
-} sysctl_local_ports;
-void inet_get_local_port_range(int *low, int *high);
+void inet_get_local_port_range(struct net *net, int *low, int *high);
 
 extern unsigned long *sysctl_local_reserved_ports;
 static inline int inet_is_reserved_local_port(int port)
diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h
index bf2ec2202c56..5dbd232e12ff 100644
--- a/include/net/netns/ipv4.h
+++ b/include/net/netns/ipv4.h
@@ -15,6 +15,10 @@ struct fib_rules_ops;
 struct hlist_head;
 struct fib_table;
 struct sock;
+struct local_ports {
+	seqlock_t	lock;
+	int		range[2];
+};
 
 struct netns_ipv4 {
 #ifdef CONFIG_SYSCTL
@@ -62,6 +66,8 @@ struct netns_ipv4 {
 	int sysctl_icmp_ratemask;
 	int sysctl_icmp_errors_use_inbound_ifaddr;
 
+	struct local_ports sysctl_local_ports;
+
 	int sysctl_tcp_ecn;
 
 	kgid_t sysctl_ping_group_range[2];
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index 6acb541c9091..7ac7aa11130e 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -29,27 +29,19 @@ const char inet_csk_timer_bug_msg[] = "inet_csk BUG: unknown timer value\n";
 EXPORT_SYMBOL(inet_csk_timer_bug_msg);
 #endif
 
-/*
- * This struct holds the first and last local port number.
- */
-struct local_ports sysctl_local_ports __read_mostly = {
-	.lock = __SEQLOCK_UNLOCKED(sysctl_local_ports.lock),
-	.range = { 32768, 61000 },
-};
-
 unsigned long *sysctl_local_reserved_ports;
 EXPORT_SYMBOL(sysctl_local_reserved_ports);
 
-void inet_get_local_port_range(int *low, int *high)
+void inet_get_local_port_range(struct net *net, int *low, int *high)
 {
 	unsigned int seq;
 
 	do {
-		seq = read_seqbegin(&sysctl_local_ports.lock);
+		seq = read_seqbegin(&net->ipv4.sysctl_local_ports.lock);
 
-		*low = sysctl_local_ports.range[0];
-		*high = sysctl_local_ports.range[1];
-	} while (read_seqretry(&sysctl_local_ports.lock, seq));
+		*low = net->ipv4.sysctl_local_ports.range[0];
+		*high = net->ipv4.sysctl_local_ports.range[1];
+	} while (read_seqretry(&net->ipv4.sysctl_local_ports.lock, seq));
 }
 EXPORT_SYMBOL(inet_get_local_port_range);
 
@@ -116,7 +108,7 @@ int inet_csk_get_port(struct sock *sk, unsigned short snum)
 		int remaining, rover, low, high;
 
 again:
-		inet_get_local_port_range(&low, &high);
+		inet_get_local_port_range(net, &low, &high);
 		remaining = (high - low) + 1;
 		smallest_rover = rover = net_random() % remaining + low;
 
diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c
index 7bd8983dbfcf..2779037bd113 100644
--- a/net/ipv4/inet_hashtables.c
+++ b/net/ipv4/inet_hashtables.c
@@ -494,7 +494,7 @@ int __inet_hash_connect(struct inet_timewait_death_row *death_row,
 		u32 offset = hint + port_offset;
 		struct inet_timewait_sock *tw = NULL;
 
-		inet_get_local_port_range(&low, &high);
+		inet_get_local_port_range(net, &low, &high);
 		remaining = (high - low) + 1;
 
 		local_bh_disable();
diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c
index 706d108e128c..a62610443152 100644
--- a/net/ipv4/ping.c
+++ b/net/ipv4/ping.c
@@ -237,11 +237,11 @@ static void inet_get_ping_group_range_net(struct net *net, kgid_t *low,
 	unsigned int seq;
 
 	do {
-		seq = read_seqbegin(&sysctl_local_ports.lock);
+		seq = read_seqbegin(&net->ipv4.sysctl_local_ports.lock);
 
 		*low = data[0];
 		*high = data[1];
-	} while (read_seqretry(&sysctl_local_ports.lock, seq));
+	} while (read_seqretry(&net->ipv4.sysctl_local_ports.lock, seq));
 }
 
 
diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index 540279f4c531..c08f096d46b5 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -43,12 +43,12 @@ static int ip_ping_group_range_min[] = { 0, 0 };
 static int ip_ping_group_range_max[] = { GID_T_MAX, GID_T_MAX };
 
 /* Update system visible IP port range */
-static void set_local_port_range(int range[2])
+static void set_local_port_range(struct net *net, int range[2])
 {
-	write_seqlock(&sysctl_local_ports.lock);
-	sysctl_local_ports.range[0] = range[0];
-	sysctl_local_ports.range[1] = range[1];
-	write_sequnlock(&sysctl_local_ports.lock);
+	write_seqlock(&net->ipv4.sysctl_local_ports.lock);
+	net->ipv4.sysctl_local_ports.range[0] = range[0];
+	net->ipv4.sysctl_local_ports.range[1] = range[1];
+	write_sequnlock(&net->ipv4.sysctl_local_ports.lock);
 }
 
 /* Validate changes from /proc interface. */
@@ -56,6 +56,8 @@ static int ipv4_local_port_range(struct ctl_table *table, int write,
 				 void __user *buffer,
 				 size_t *lenp, loff_t *ppos)
 {
+	struct net *net =
+		container_of(table->data, struct net, ipv4.sysctl_local_ports.range);
 	int ret;
 	int range[2];
 	struct ctl_table tmp = {
@@ -66,14 +68,15 @@ static int ipv4_local_port_range(struct ctl_table *table, int write,
 		.extra2 = &ip_local_port_range_max,
 	};
 
-	inet_get_local_port_range(range, range + 1);
+	inet_get_local_port_range(net, &range[0], &range[1]);
+
 	ret = proc_dointvec_minmax(&tmp, write, buffer, lenp, ppos);
 
 	if (write && ret == 0) {
 		if (range[1] < range[0])
 			ret = -EINVAL;
 		else
-			set_local_port_range(range);
+			set_local_port_range(net, range);
 	}
 
 	return ret;
@@ -83,23 +86,27 @@ static int ipv4_local_port_range(struct ctl_table *table, int write,
 static void inet_get_ping_group_range_table(struct ctl_table *table, kgid_t *low, kgid_t *high)
 {
 	kgid_t *data = table->data;
+	struct net *net =
+		container_of(table->data, struct net, ipv4.sysctl_ping_group_range);
 	unsigned int seq;
 	do {
-		seq = read_seqbegin(&sysctl_local_ports.lock);
+		seq = read_seqbegin(&net->ipv4.sysctl_local_ports.lock);
 
 		*low = data[0];
 		*high = data[1];
-	} while (read_seqretry(&sysctl_local_ports.lock, seq));
+	} while (read_seqretry(&net->ipv4.sysctl_local_ports.lock, seq));
 }
 
 /* Update system visible IP port range */
 static void set_ping_group_range(struct ctl_table *table, kgid_t low, kgid_t high)
 {
 	kgid_t *data = table->data;
-	write_seqlock(&sysctl_local_ports.lock);
+	struct net *net =
+		container_of(table->data, struct net, ipv4.sysctl_ping_group_range);
+	write_seqlock(&net->ipv4.sysctl_local_ports.lock);
 	data[0] = low;
 	data[1] = high;
-	write_sequnlock(&sysctl_local_ports.lock);
+	write_sequnlock(&net->ipv4.sysctl_local_ports.lock);
 }
 
 /* Validate changes from /proc interface. */
@@ -474,13 +481,6 @@ static struct ctl_table ipv4_table[] = {
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec
 	},
-	{
-		.procname	= "ip_local_port_range",
-		.data		= &sysctl_local_ports.range,
-		.maxlen		= sizeof(sysctl_local_ports.range),
-		.mode		= 0644,
-		.proc_handler	= ipv4_local_port_range,
-	},
 	{
 		.procname	= "ip_local_reserved_ports",
 		.data		= NULL, /* initialized in sysctl_ipv4_init */
@@ -853,6 +853,13 @@ static struct ctl_table ipv4_net_table[] = {
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec
 	},
+	{
+		.procname	= "ip_local_port_range",
+		.maxlen		= sizeof(init_net.ipv4.sysctl_local_ports.range),
+		.data		= &init_net.ipv4.sysctl_local_ports.range,
+		.mode		= 0644,
+		.proc_handler	= ipv4_local_port_range,
+	},
 	{
 		.procname	= "tcp_mem",
 		.maxlen		= sizeof(init_net.ipv4.sysctl_tcp_mem),
@@ -888,6 +895,8 @@ static __net_init int ipv4_sysctl_init_net(struct net *net)
 			&net->ipv4.sysctl_ping_group_range;
 		table[7].data =
 			&net->ipv4.sysctl_tcp_ecn;
+		table[8].data =
+			&net->ipv4.sysctl_local_ports.range;
 
 		/* Don't export sysctls to unprivileged users */
 		if (net->user_ns != &init_user_ns)
@@ -901,6 +910,13 @@ static __net_init int ipv4_sysctl_init_net(struct net *net)
 	net->ipv4.sysctl_ping_group_range[0] = make_kgid(&init_user_ns, 1);
 	net->ipv4.sysctl_ping_group_range[1] = make_kgid(&init_user_ns, 0);
 
+	/*
+	 * Set defaults for local port range
+	 */
+	seqlock_init(&net->ipv4.sysctl_local_ports.lock);
+	net->ipv4.sysctl_local_ports.range[0] =  32768;
+	net->ipv4.sysctl_local_ports.range[1] =  61000;
+
 	tcp_init_mem(net);
 
 	net->ipv4.ipv4_hdr = register_net_sysctl(net, "net/ipv4", table);
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 22462d947750..728ce9503a27 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -219,7 +219,7 @@ int udp_lib_get_port(struct sock *sk, unsigned short snum,
 		unsigned short first, last;
 		DECLARE_BITMAP(bitmap, PORTS_PER_CHAIN);
 
-		inet_get_local_port_range(&low, &high);
+		inet_get_local_port_range(net, &low, &high);
 		remaining = (high - low) + 1;
 
 		rand = net_random();
diff --git a/net/openvswitch/vport-vxlan.c b/net/openvswitch/vport-vxlan.c
index a481c03e2861..56e22b74cf96 100644
--- a/net/openvswitch/vport-vxlan.c
+++ b/net/openvswitch/vport-vxlan.c
@@ -173,7 +173,7 @@ static int vxlan_tnl_send(struct vport *vport, struct sk_buff *skb)
 
 	skb->local_df = 1;
 
-	inet_get_local_port_range(&port_min, &port_max);
+	inet_get_local_port_range(net, &port_min, &port_max);
 	src_port = vxlan_src_port(port_min, port_max, skb);
 
 	err = vxlan_xmit_skb(vxlan_port->vs, rt, skb,
diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index 911b71b26b0e..72046b9729a8 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -5890,7 +5890,7 @@ static long sctp_get_port_local(struct sock *sk, union sctp_addr *addr)
 		int low, high, remaining, index;
 		unsigned int rover;
 
-		inet_get_local_port_range(&low, &high);
+		inet_get_local_port_range(sock_net(sk), &low, &high);
 		remaining = (high - low) + 1;
 		rover = net_random() % remaining + low;
 
diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c
index a5091ec06aa6..568c7699abf1 100644
--- a/security/selinux/hooks.c
+++ b/security/selinux/hooks.c
@@ -3929,7 +3929,7 @@ static int selinux_socket_bind(struct socket *sock, struct sockaddr *address, in
 		if (snum) {
 			int low, high;
 
-			inet_get_local_port_range(&low, &high);
+			inet_get_local_port_range(sock_net(sk), &low, &high);
 
 			if (snum < max(PROT_SOCK, low) || snum > high) {
 				err = sel_netport_sid(sk->sk_protocol,
-- 
cgit v1.2.3


From efe4208f47f907b86f528788da711e8ab9dea44d Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 3 Oct 2013 15:42:29 -0700
Subject: ipv6: make lookups simpler and faster

TCP listener refactoring, part 4 :

To speed up inet lookups, we moved IPv4 addresses from inet to struct
sock_common

Now is time to do the same for IPv6, because it permits us to have fast
lookups for all kind of sockets, including upcoming SYN_RECV.

Getting IPv6 addresses in TCP lookups currently requires two extra cache
lines, plus a dereference (and memory stall).

inet6_sk(sk) does the dereference of inet_sk(__sk)->pinet6

This patch is way bigger than its IPv4 counter part, because for IPv4,
we could add aliases (inet_daddr, inet_rcv_saddr), while on IPv6,
it's not doable easily.

inet6_sk(sk)->daddr becomes sk->sk_v6_daddr
inet6_sk(sk)->rcv_saddr becomes sk->sk_v6_rcv_saddr

And timewait socket also have tw->tw_v6_daddr & tw->tw_v6_rcv_saddr
at the same offset.

We get rid of INET6_TW_MATCH() as INET6_MATCH() is now the generic
macro.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/ipv6.h                           | 46 +++-----------------
 include/net/inet6_hashtables.h                 |  5 +--
 include/net/inet_timewait_sock.h               |  4 +-
 include/net/ip.h                               |  2 +-
 include/net/ip6_checksum.h                     |  2 +-
 include/net/sock.h                             |  9 ++++
 net/dccp/ipv6.c                                | 24 +++++------
 net/dccp/ipv6.h                                |  1 -
 net/dccp/minisocks.c                           |  7 +---
 net/ipv4/inet_diag.c                           | 35 +++++++---------
 net/ipv4/ping.c                                | 15 ++++---
 net/ipv4/tcp_metrics.c                         | 10 ++---
 net/ipv4/tcp_minisocks.c                       |  7 +---
 net/ipv4/tcp_probe.c                           | 29 +++++--------
 net/ipv4/tcp_timer.c                           |  3 +-
 net/ipv6/af_inet6.c                            | 10 ++---
 net/ipv6/datagram.c                            | 25 ++++++-----
 net/ipv6/inet6_connection_sock.c               |  7 ++--
 net/ipv6/inet6_hashtables.c                    | 58 +++++++++-----------------
 net/ipv6/ipv6_sockglue.c                       |  7 ++--
 net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c |  4 +-
 net/ipv6/ping.c                                |  2 +-
 net/ipv6/raw.c                                 | 17 ++++----
 net/ipv6/tcp_ipv6.c                            | 44 ++++++++++---------
 net/ipv6/udp.c                                 | 48 ++++++++++-----------
 net/l2tp/l2tp_core.c                           | 10 ++---
 net/l2tp/l2tp_debugfs.c                        |  5 ++-
 net/l2tp/l2tp_ip6.c                            | 16 +++----
 net/l2tp/l2tp_netlink.c                        |  4 +-
 net/l2tp/l2tp_ppp.c                            | 12 +++---
 net/netfilter/xt_TPROXY.c                      |  2 +-
 net/netfilter/xt_socket.c                      |  2 +-
 net/sctp/ipv6.c                                | 22 +++++-----
 net/sunrpc/svcsock.c                           |  2 +-
 security/lsm_audit.c                           |  5 +--
 35 files changed, 213 insertions(+), 288 deletions(-)

(limited to 'security')

diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h
index b7f1f3bb346d..35f6c1b562c4 100644
--- a/include/linux/ipv6.h
+++ b/include/linux/ipv6.h
@@ -141,8 +141,6 @@ struct ipv6_fl_socklist;
  */
 struct ipv6_pinfo {
 	struct in6_addr 	saddr;
-	struct in6_addr 	rcv_saddr;
-	struct in6_addr		daddr;
 	struct in6_pktinfo	sticky_pktinfo;
 	const struct in6_addr		*daddr_cache;
 #ifdef CONFIG_IPV6_SUBTREES
@@ -256,22 +254,10 @@ struct tcp6_sock {
 
 extern int inet6_sk_rebuild_header(struct sock *sk);
 
-struct inet6_timewait_sock {
-	struct in6_addr tw_v6_daddr;
-	struct in6_addr	tw_v6_rcv_saddr;
-};
-
 struct tcp6_timewait_sock {
 	struct tcp_timewait_sock   tcp6tw_tcp;
-	struct inet6_timewait_sock tcp6tw_inet6;
 };
 
-static inline struct inet6_timewait_sock *inet6_twsk(const struct sock *sk)
-{
-	return (struct inet6_timewait_sock *)(((u8 *)sk) +
-					      inet_twsk(sk)->tw_ipv6_offset);
-}
-
 #if IS_ENABLED(CONFIG_IPV6)
 static inline struct ipv6_pinfo * inet6_sk(const struct sock *__sk)
 {
@@ -321,21 +307,11 @@ static inline void inet_sk_copy_descendant(struct sock *sk_to,
 #define __ipv6_only_sock(sk)	(inet6_sk(sk)->ipv6only)
 #define ipv6_only_sock(sk)	((sk)->sk_family == PF_INET6 && __ipv6_only_sock(sk))
 
-static inline u16 inet6_tw_offset(const struct proto *prot)
-{
-	return prot->twsk_prot->twsk_obj_size -
-			sizeof(struct inet6_timewait_sock);
-}
-
-static inline struct in6_addr *__inet6_rcv_saddr(const struct sock *sk)
+static inline const struct in6_addr *inet6_rcv_saddr(const struct sock *sk)
 {
-	return likely(sk->sk_state != TCP_TIME_WAIT) ?
-		&inet6_sk(sk)->rcv_saddr : &inet6_twsk(sk)->tw_v6_rcv_saddr;
-}
-
-static inline struct in6_addr *inet6_rcv_saddr(const struct sock *sk)
-{
-	return sk->sk_family == AF_INET6 ? __inet6_rcv_saddr(sk) : NULL;
+	if (sk->sk_family == AF_INET6)
+		return &sk->sk_v6_rcv_saddr;
+	return NULL;
 }
 
 static inline int inet_v6_ipv6only(const struct sock *sk)
@@ -363,7 +339,6 @@ static inline struct raw6_sock *raw6_sk(const struct sock *sk)
 	return NULL;
 }
 
-#define __inet6_rcv_saddr(__sk)	NULL
 #define inet6_rcv_saddr(__sk)	NULL
 #define tcp_twsk_ipv6only(__sk)		0
 #define inet_v6_ipv6only(__sk)		0
@@ -372,19 +347,10 @@ static inline struct raw6_sock *raw6_sk(const struct sock *sk)
 #define INET6_MATCH(__sk, __net, __saddr, __daddr, __ports, __dif)	\
 	(((__sk)->sk_portpair == (__ports))			&&	\
 	 ((__sk)->sk_family == AF_INET6)			&&	\
-	 ipv6_addr_equal(&inet6_sk(__sk)->daddr, (__saddr))	&&	\
-	 ipv6_addr_equal(&inet6_sk(__sk)->rcv_saddr, (__daddr))	&&	\
+	 ipv6_addr_equal(&(__sk)->sk_v6_daddr, (__saddr))		&&	\
+	 ipv6_addr_equal(&(__sk)->sk_v6_rcv_saddr, (__daddr))	&&	\
 	 (!(__sk)->sk_bound_dev_if	||				\
 	   ((__sk)->sk_bound_dev_if == (__dif))) 		&&	\
 	 net_eq(sock_net(__sk), (__net)))
 
-#define INET6_TW_MATCH(__sk, __net, __saddr, __daddr, __ports, __dif)	   \
-	(((__sk)->sk_portpair == (__ports))				&& \
-	 ((__sk)->sk_family == AF_INET6)				&& \
-	 ipv6_addr_equal(&inet6_twsk(__sk)->tw_v6_daddr, (__saddr))	&& \
-	 ipv6_addr_equal(&inet6_twsk(__sk)->tw_v6_rcv_saddr, (__daddr)) && \
-	 (!(__sk)->sk_bound_dev_if	||				   \
-	  ((__sk)->sk_bound_dev_if == (__dif)))				&& \
-	 net_eq(sock_net(__sk), (__net)))
-
 #endif /* _IPV6_H */
diff --git a/include/net/inet6_hashtables.h b/include/net/inet6_hashtables.h
index f52fa88feb64..a105d1a2fc00 100644
--- a/include/net/inet6_hashtables.h
+++ b/include/net/inet6_hashtables.h
@@ -43,9 +43,8 @@ static inline unsigned int inet6_ehashfn(struct net *net,
 static inline int inet6_sk_ehashfn(const struct sock *sk)
 {
 	const struct inet_sock *inet = inet_sk(sk);
-	const struct ipv6_pinfo *np = inet6_sk(sk);
-	const struct in6_addr *laddr = &np->rcv_saddr;
-	const struct in6_addr *faddr = &np->daddr;
+	const struct in6_addr *laddr = &sk->sk_v6_rcv_saddr;
+	const struct in6_addr *faddr = &sk->sk_v6_daddr;
 	const __u16 lport = inet->inet_num;
 	const __be16 fport = inet->inet_dport;
 	struct net *net = sock_net(sk);
diff --git a/include/net/inet_timewait_sock.h b/include/net/inet_timewait_sock.h
index de9e3ab7d43d..b647c6270eb7 100644
--- a/include/net/inet_timewait_sock.h
+++ b/include/net/inet_timewait_sock.h
@@ -116,7 +116,9 @@ struct inet_timewait_sock {
 #define tw_prot			__tw_common.skc_prot
 #define tw_net			__tw_common.skc_net
 #define tw_daddr        	__tw_common.skc_daddr
+#define tw_v6_daddr		__tw_common.skc_v6_daddr
 #define tw_rcv_saddr    	__tw_common.skc_rcv_saddr
+#define tw_v6_rcv_saddr    	__tw_common.skc_v6_rcv_saddr
 #define tw_dport		__tw_common.skc_dport
 #define tw_num			__tw_common.skc_num
 
@@ -133,7 +135,7 @@ struct inet_timewait_sock {
 				tw_transparent  : 1,
 				tw_pad		: 6,	/* 6 bits hole */
 				tw_tos		: 8,
-				tw_ipv6_offset  : 16;
+				tw_pad2		: 16 /* 16 bits hole */
 	kmemcheck_bitfield_end(flags);
 	u32			tw_ttd;
 	struct inet_bind_bucket	*tw_tb;
diff --git a/include/net/ip.h b/include/net/ip.h
index b39ebe5339ac..217bc5bfc6c6 100644
--- a/include/net/ip.h
+++ b/include/net/ip.h
@@ -374,7 +374,7 @@ static __inline__ void inet_reset_saddr(struct sock *sk)
 		struct ipv6_pinfo *np = inet6_sk(sk);
 
 		memset(&np->saddr, 0, sizeof(np->saddr));
-		memset(&np->rcv_saddr, 0, sizeof(np->rcv_saddr));
+		memset(&sk->sk_v6_rcv_saddr, 0, sizeof(sk->sk_v6_rcv_saddr));
 	}
 #endif
 }
diff --git a/include/net/ip6_checksum.h b/include/net/ip6_checksum.h
index 7686e3f5033d..1944406949ba 100644
--- a/include/net/ip6_checksum.h
+++ b/include/net/ip6_checksum.h
@@ -70,7 +70,7 @@ static inline void tcp_v6_send_check(struct sock *sk, struct sk_buff *skb)
 {
 	struct ipv6_pinfo *np = inet6_sk(sk);
 
-	__tcp_v6_send_check(skb, &np->saddr, &np->daddr);
+	__tcp_v6_send_check(skb, &np->saddr, &sk->sk_v6_daddr);
 }
 
 int udp6_csum_init(struct sk_buff *skb, struct udphdr *uh, int proto);
diff --git a/include/net/sock.h b/include/net/sock.h
index 3f3e48c4704d..7e50df5c71d4 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -191,6 +191,12 @@ struct sock_common {
 #ifdef CONFIG_NET_NS
 	struct net	 	*skc_net;
 #endif
+
+#if IS_ENABLED(CONFIG_IPV6)
+	struct in6_addr		skc_v6_daddr;
+	struct in6_addr		skc_v6_rcv_saddr;
+#endif
+
 	/*
 	 * fields between dontcopy_begin/dontcopy_end
 	 * are not copied in sock_copy()
@@ -314,6 +320,9 @@ struct sock {
 #define sk_bind_node		__sk_common.skc_bind_node
 #define sk_prot			__sk_common.skc_prot
 #define sk_net			__sk_common.skc_net
+#define sk_v6_daddr		__sk_common.skc_v6_daddr
+#define sk_v6_rcv_saddr	__sk_common.skc_v6_rcv_saddr
+
 	socket_lock_t		sk_lock;
 	struct sk_buff_head	sk_receive_queue;
 	/*
diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c
index 6cf9f7782ad4..7f075b83128a 100644
--- a/net/dccp/ipv6.c
+++ b/net/dccp/ipv6.c
@@ -67,7 +67,7 @@ static inline void dccp_v6_send_check(struct sock *sk, struct sk_buff *skb)
 	struct dccp_hdr *dh = dccp_hdr(skb);
 
 	dccp_csum_outgoing(skb);
-	dh->dccph_checksum = dccp_v6_csum_finish(skb, &np->saddr, &np->daddr);
+	dh->dccph_checksum = dccp_v6_csum_finish(skb, &np->saddr, &sk->sk_v6_daddr);
 }
 
 static inline __u64 dccp_v6_init_sequence(struct sk_buff *skb)
@@ -467,11 +467,11 @@ static struct sock *dccp_v6_request_recv_sock(struct sock *sk,
 
 		memcpy(newnp, np, sizeof(struct ipv6_pinfo));
 
-		ipv6_addr_set_v4mapped(newinet->inet_daddr, &newnp->daddr);
+		ipv6_addr_set_v4mapped(newinet->inet_daddr, &newsk->sk_v6_daddr);
 
 		ipv6_addr_set_v4mapped(newinet->inet_saddr, &newnp->saddr);
 
-		newnp->rcv_saddr = newnp->saddr;
+		newsk->sk_v6_rcv_saddr = newnp->saddr;
 
 		inet_csk(newsk)->icsk_af_ops = &dccp_ipv6_mapped;
 		newsk->sk_backlog_rcv = dccp_v4_do_rcv;
@@ -538,9 +538,9 @@ static struct sock *dccp_v6_request_recv_sock(struct sock *sk,
 
 	memcpy(newnp, np, sizeof(struct ipv6_pinfo));
 
-	newnp->daddr = ireq6->rmt_addr;
+	newsk->sk_v6_daddr = ireq6->rmt_addr;
 	newnp->saddr = ireq6->loc_addr;
-	newnp->rcv_saddr = ireq6->loc_addr;
+	newsk->sk_v6_rcv_saddr = ireq6->loc_addr;
 	newsk->sk_bound_dev_if = ireq6->iif;
 
 	/* Now IPv6 options...
@@ -885,7 +885,7 @@ static int dccp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
 			return -EINVAL;
 	}
 
-	np->daddr = usin->sin6_addr;
+	sk->sk_v6_daddr = usin->sin6_addr;
 	np->flow_label = fl6.flowlabel;
 
 	/*
@@ -915,16 +915,16 @@ static int dccp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
 			goto failure;
 		}
 		ipv6_addr_set_v4mapped(inet->inet_saddr, &np->saddr);
-		ipv6_addr_set_v4mapped(inet->inet_rcv_saddr, &np->rcv_saddr);
+		ipv6_addr_set_v4mapped(inet->inet_rcv_saddr, &sk->sk_v6_rcv_saddr);
 
 		return err;
 	}
 
-	if (!ipv6_addr_any(&np->rcv_saddr))
-		saddr = &np->rcv_saddr;
+	if (!ipv6_addr_any(&sk->sk_v6_rcv_saddr))
+		saddr = &sk->sk_v6_rcv_saddr;
 
 	fl6.flowi6_proto = IPPROTO_DCCP;
-	fl6.daddr = np->daddr;
+	fl6.daddr = sk->sk_v6_daddr;
 	fl6.saddr = saddr ? *saddr : np->saddr;
 	fl6.flowi6_oif = sk->sk_bound_dev_if;
 	fl6.fl6_dport = usin->sin6_port;
@@ -941,7 +941,7 @@ static int dccp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
 
 	if (saddr == NULL) {
 		saddr = &fl6.saddr;
-		np->rcv_saddr = *saddr;
+		sk->sk_v6_rcv_saddr = *saddr;
 	}
 
 	/* set the source address */
@@ -963,7 +963,7 @@ static int dccp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
 		goto late_failure;
 
 	dp->dccps_iss = secure_dccpv6_sequence_number(np->saddr.s6_addr32,
-						      np->daddr.s6_addr32,
+						      sk->sk_v6_daddr.s6_addr32,
 						      inet->inet_sport,
 						      inet->inet_dport);
 	err = dccp_connect(sk);
diff --git a/net/dccp/ipv6.h b/net/dccp/ipv6.h
index 6eef81fdbe56..6604fc3fe953 100644
--- a/net/dccp/ipv6.h
+++ b/net/dccp/ipv6.h
@@ -30,7 +30,6 @@ struct dccp6_request_sock {
 
 struct dccp6_timewait_sock {
 	struct inet_timewait_sock   inet;
-	struct inet6_timewait_sock  tw6;
 };
 
 #endif /* _DCCP_IPV6_H */
diff --git a/net/dccp/minisocks.c b/net/dccp/minisocks.c
index 662071b249cc..32e80d96d4c0 100644
--- a/net/dccp/minisocks.c
+++ b/net/dccp/minisocks.c
@@ -56,12 +56,9 @@ void dccp_time_wait(struct sock *sk, int state, int timeo)
 #if IS_ENABLED(CONFIG_IPV6)
 		if (tw->tw_family == PF_INET6) {
 			const struct ipv6_pinfo *np = inet6_sk(sk);
-			struct inet6_timewait_sock *tw6;
 
-			tw->tw_ipv6_offset = inet6_tw_offset(sk->sk_prot);
-			tw6 = inet6_twsk((struct sock *)tw);
-			tw6->tw_v6_daddr = np->daddr;
-			tw6->tw_v6_rcv_saddr = np->rcv_saddr;
+			tw->tw_v6_daddr = sk->sk_v6_daddr;
+			tw->tw_v6_rcv_saddr = sk->sk_v6_rcv_saddr;
 			tw->tw_ipv6only = np->ipv6only;
 		}
 #endif
diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c
index 8e1e40653357..ecc179d676e4 100644
--- a/net/ipv4/inet_diag.c
+++ b/net/ipv4/inet_diag.c
@@ -121,13 +121,13 @@ int inet_sk_diag_fill(struct sock *sk, struct inet_connection_sock *icsk,
 
 #if IS_ENABLED(CONFIG_IPV6)
 	if (r->idiag_family == AF_INET6) {
-		const struct ipv6_pinfo *np = inet6_sk(sk);
 
-		*(struct in6_addr *)r->id.idiag_src = np->rcv_saddr;
-		*(struct in6_addr *)r->id.idiag_dst = np->daddr;
+		*(struct in6_addr *)r->id.idiag_src = sk->sk_v6_rcv_saddr;
+		*(struct in6_addr *)r->id.idiag_dst = sk->sk_v6_daddr;
 
 		if (ext & (1 << (INET_DIAG_TCLASS - 1)))
-			if (nla_put_u8(skb, INET_DIAG_TCLASS, np->tclass) < 0)
+			if (nla_put_u8(skb, INET_DIAG_TCLASS,
+				       inet6_sk(sk)->tclass) < 0)
 				goto errout;
 	}
 #endif
@@ -255,11 +255,8 @@ static int inet_twsk_diag_fill(struct inet_timewait_sock *tw,
 	r->idiag_inode	      = 0;
 #if IS_ENABLED(CONFIG_IPV6)
 	if (tw->tw_family == AF_INET6) {
-		const struct inet6_timewait_sock *tw6 =
-						inet6_twsk((struct sock *)tw);
-
-		*(struct in6_addr *)r->id.idiag_src = tw6->tw_v6_rcv_saddr;
-		*(struct in6_addr *)r->id.idiag_dst = tw6->tw_v6_daddr;
+		*(struct in6_addr *)r->id.idiag_src = tw->tw_v6_rcv_saddr;
+		*(struct in6_addr *)r->id.idiag_dst = tw->tw_v6_daddr;
 	}
 #endif
 
@@ -273,10 +270,11 @@ static int sk_diag_fill(struct sock *sk, struct sk_buff *skb,
 			const struct nlmsghdr *unlh)
 {
 	if (sk->sk_state == TCP_TIME_WAIT)
-		return inet_twsk_diag_fill((struct inet_timewait_sock *)sk,
-					   skb, r, portid, seq, nlmsg_flags,
-					   unlh);
-	return inet_csk_diag_fill(sk, skb, r, user_ns, portid, seq, nlmsg_flags, unlh);
+		return inet_twsk_diag_fill(inet_twsk(sk), skb, r, portid, seq,
+					   nlmsg_flags, unlh);
+
+	return inet_csk_diag_fill(sk, skb, r, user_ns, portid, seq,
+				  nlmsg_flags, unlh);
 }
 
 int inet_diag_dump_one_icsk(struct inet_hashinfo *hashinfo, struct sk_buff *in_skb,
@@ -489,10 +487,9 @@ int inet_diag_bc_sk(const struct nlattr *bc, struct sock *sk)
 	entry.family = sk->sk_family;
 #if IS_ENABLED(CONFIG_IPV6)
 	if (entry.family == AF_INET6) {
-		struct ipv6_pinfo *np = inet6_sk(sk);
 
-		entry.saddr = np->rcv_saddr.s6_addr32;
-		entry.daddr = np->daddr.s6_addr32;
+		entry.saddr = sk->sk_v6_rcv_saddr.s6_addr32;
+		entry.daddr = sk->sk_v6_daddr.s6_addr32;
 	} else
 #endif
 	{
@@ -649,10 +646,8 @@ static int inet_twsk_diag_dump(struct sock *sk,
 		entry.family = tw->tw_family;
 #if IS_ENABLED(CONFIG_IPV6)
 		if (tw->tw_family == AF_INET6) {
-			struct inet6_timewait_sock *tw6 =
-						inet6_twsk((struct sock *)tw);
-			entry.saddr = tw6->tw_v6_rcv_saddr.s6_addr32;
-			entry.daddr = tw6->tw_v6_daddr.s6_addr32;
+			entry.saddr = tw->tw_v6_rcv_saddr.s6_addr32;
+			entry.daddr = tw->tw_v6_daddr.s6_addr32;
 		} else
 #endif
 		{
diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c
index a62610443152..ccefc07beacd 100644
--- a/net/ipv4/ping.c
+++ b/net/ipv4/ping.c
@@ -202,15 +202,14 @@ static struct sock *ping_lookup(struct net *net, struct sk_buff *skb, u16 ident)
 #if IS_ENABLED(CONFIG_IPV6)
 		} else if (skb->protocol == htons(ETH_P_IPV6) &&
 			   sk->sk_family == AF_INET6) {
-			struct ipv6_pinfo *np = inet6_sk(sk);
 
 			pr_debug("found: %p: num=%d, daddr=%pI6c, dif=%d\n", sk,
 				 (int) isk->inet_num,
-				 &inet6_sk(sk)->rcv_saddr,
+				 &sk->sk_v6_rcv_saddr,
 				 sk->sk_bound_dev_if);
 
-			if (!ipv6_addr_any(&np->rcv_saddr) &&
-			    !ipv6_addr_equal(&np->rcv_saddr,
+			if (!ipv6_addr_any(&sk->sk_v6_rcv_saddr) &&
+			    !ipv6_addr_equal(&sk->sk_v6_rcv_saddr,
 					     &ipv6_hdr(skb)->daddr))
 				continue;
 #endif
@@ -362,7 +361,7 @@ static void ping_set_saddr(struct sock *sk, struct sockaddr *saddr)
 	} else if (saddr->sa_family == AF_INET6) {
 		struct sockaddr_in6 *addr = (struct sockaddr_in6 *) saddr;
 		struct ipv6_pinfo *np = inet6_sk(sk);
-		np->rcv_saddr = np->saddr = addr->sin6_addr;
+		sk->sk_v6_rcv_saddr = np->saddr = addr->sin6_addr;
 #endif
 	}
 }
@@ -376,7 +375,7 @@ static void ping_clear_saddr(struct sock *sk, int dif)
 #if IS_ENABLED(CONFIG_IPV6)
 	} else if (sk->sk_family == AF_INET6) {
 		struct ipv6_pinfo *np = inet6_sk(sk);
-		memset(&np->rcv_saddr, 0, sizeof(np->rcv_saddr));
+		memset(&sk->sk_v6_rcv_saddr, 0, sizeof(sk->sk_v6_rcv_saddr));
 		memset(&np->saddr, 0, sizeof(np->saddr));
 #endif
 	}
@@ -418,7 +417,7 @@ int ping_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 	err = 0;
 	if ((sk->sk_family == AF_INET && isk->inet_rcv_saddr) ||
 	    (sk->sk_family == AF_INET6 &&
-	     !ipv6_addr_any(&inet6_sk(sk)->rcv_saddr)))
+	     !ipv6_addr_any(&sk->sk_v6_rcv_saddr)))
 		sk->sk_userlocks |= SOCK_BINDADDR_LOCK;
 
 	if (snum)
@@ -429,7 +428,7 @@ int ping_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 
 #if IS_ENABLED(CONFIG_IPV6)
 	if (sk->sk_family == AF_INET6)
-		memset(&inet6_sk(sk)->daddr, 0, sizeof(inet6_sk(sk)->daddr));
+		memset(&sk->sk_v6_daddr, 0, sizeof(sk->sk_v6_daddr));
 #endif
 
 	sk_dst_reset(sk);
diff --git a/net/ipv4/tcp_metrics.c b/net/ipv4/tcp_metrics.c
index 52f3c6b971d2..27535fd5ea10 100644
--- a/net/ipv4/tcp_metrics.c
+++ b/net/ipv4/tcp_metrics.c
@@ -240,7 +240,6 @@ static struct tcp_metrics_block *__tcp_get_metrics_req(struct request_sock *req,
 
 static struct tcp_metrics_block *__tcp_get_metrics_tw(struct inet_timewait_sock *tw)
 {
-	struct inet6_timewait_sock *tw6;
 	struct tcp_metrics_block *tm;
 	struct inetpeer_addr addr;
 	unsigned int hash;
@@ -253,9 +252,8 @@ static struct tcp_metrics_block *__tcp_get_metrics_tw(struct inet_timewait_sock
 		hash = (__force unsigned int) addr.addr.a4;
 		break;
 	case AF_INET6:
-		tw6 = inet6_twsk((struct sock *)tw);
-		*(struct in6_addr *)addr.addr.a6 = tw6->tw_v6_daddr;
-		hash = ipv6_addr_hash(&tw6->tw_v6_daddr);
+		*(struct in6_addr *)addr.addr.a6 = tw->tw_v6_daddr;
+		hash = ipv6_addr_hash(&tw->tw_v6_daddr);
 		break;
 	default:
 		return NULL;
@@ -289,8 +287,8 @@ static struct tcp_metrics_block *tcp_get_metrics(struct sock *sk,
 		hash = (__force unsigned int) addr.addr.a4;
 		break;
 	case AF_INET6:
-		*(struct in6_addr *)addr.addr.a6 = inet6_sk(sk)->daddr;
-		hash = ipv6_addr_hash(&inet6_sk(sk)->daddr);
+		*(struct in6_addr *)addr.addr.a6 = sk->sk_v6_daddr;
+		hash = ipv6_addr_hash(&sk->sk_v6_daddr);
 		break;
 	default:
 		return NULL;
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index 58a3e69aef64..97b684159861 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -293,12 +293,9 @@ void tcp_time_wait(struct sock *sk, int state, int timeo)
 #if IS_ENABLED(CONFIG_IPV6)
 		if (tw->tw_family == PF_INET6) {
 			struct ipv6_pinfo *np = inet6_sk(sk);
-			struct inet6_timewait_sock *tw6;
 
-			tw->tw_ipv6_offset = inet6_tw_offset(sk->sk_prot);
-			tw6 = inet6_twsk((struct sock *)tw);
-			tw6->tw_v6_daddr = np->daddr;
-			tw6->tw_v6_rcv_saddr = np->rcv_saddr;
+			tw->tw_v6_daddr = sk->sk_v6_daddr;
+			tw->tw_v6_rcv_saddr = sk->sk_v6_rcv_saddr;
 			tw->tw_tclass = np->tclass;
 			tw->tw_ipv6only = np->ipv6only;
 		}
diff --git a/net/ipv4/tcp_probe.c b/net/ipv4/tcp_probe.c
index 611beab38a00..8b97d71e193b 100644
--- a/net/ipv4/tcp_probe.c
+++ b/net/ipv4/tcp_probe.c
@@ -101,22 +101,6 @@ static inline int tcp_probe_avail(void)
 		si4.sin_addr.s_addr = inet->inet_##mem##addr;	\
 	} while (0)						\
 
-#if IS_ENABLED(CONFIG_IPV6)
-#define tcp_probe_copy_fl_to_si6(inet, si6, mem)		\
-	do {							\
-		struct ipv6_pinfo *pi6 = inet->pinet6;		\
-		si6.sin6_family = AF_INET6;			\
-		si6.sin6_port = inet->inet_##mem##port;		\
-		si6.sin6_addr = pi6->mem##addr;			\
-		si6.sin6_flowinfo = 0; /* No need here. */	\
-		si6.sin6_scope_id = 0;	/* No need here. */	\
-	} while (0)
-#else
-#define tcp_probe_copy_fl_to_si6(fl, si6, mem)			\
-	do {							\
-		memset(&si6, 0, sizeof(si6));			\
-	} while (0)
-#endif
 
 /*
  * Hook inserted to be called before each receive packet.
@@ -147,8 +131,17 @@ static void jtcp_rcv_established(struct sock *sk, struct sk_buff *skb,
 				tcp_probe_copy_fl_to_si4(inet, p->dst.v4, d);
 				break;
 			case AF_INET6:
-				tcp_probe_copy_fl_to_si6(inet, p->src.v6, s);
-				tcp_probe_copy_fl_to_si6(inet, p->dst.v6, d);
+				memset(&p->src.v6, 0, sizeof(p->src.v6));
+				memset(&p->dst.v6, 0, sizeof(p->dst.v6));
+#if IS_ENABLED(CONFIG_IPV6)
+				p->src.v6.sin6_family = AF_INET6;
+				p->src.v6.sin6_port = inet->inet_sport;
+				p->src.v6.sin6_addr = inet6_sk(sk)->saddr;
+
+				p->dst.v6.sin6_family = AF_INET6;
+				p->dst.v6.sin6_port = inet->inet_dport;
+				p->dst.v6.sin6_addr = sk->sk_v6_daddr;
+#endif
 				break;
 			default:
 				BUG();
diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c
index 4b85e6f636c9..af07b5b23ebf 100644
--- a/net/ipv4/tcp_timer.c
+++ b/net/ipv4/tcp_timer.c
@@ -374,9 +374,8 @@ void tcp_retransmit_timer(struct sock *sk)
 		}
 #if IS_ENABLED(CONFIG_IPV6)
 		else if (sk->sk_family == AF_INET6) {
-			struct ipv6_pinfo *np = inet6_sk(sk);
 			LIMIT_NETDEBUG(KERN_DEBUG pr_fmt("Peer %pI6:%u/%u unexpectedly shrunk window %u:%u (repaired)\n"),
-				       &np->daddr,
+				       &sk->sk_v6_daddr,
 				       ntohs(inet->inet_dport), inet->inet_num,
 				       tp->snd_una, tp->snd_nxt);
 		}
diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index 4966b124dc2e..a2cb07cd3850 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -364,7 +364,7 @@ int inet6_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
 	inet->inet_rcv_saddr = v4addr;
 	inet->inet_saddr = v4addr;
 
-	np->rcv_saddr = addr->sin6_addr;
+	sk->sk_v6_rcv_saddr = addr->sin6_addr;
 
 	if (!(addr_type & IPV6_ADDR_MULTICAST))
 		np->saddr = addr->sin6_addr;
@@ -461,14 +461,14 @@ int inet6_getname(struct socket *sock, struct sockaddr *uaddr,
 		    peer == 1)
 			return -ENOTCONN;
 		sin->sin6_port = inet->inet_dport;
-		sin->sin6_addr = np->daddr;
+		sin->sin6_addr = sk->sk_v6_daddr;
 		if (np->sndflow)
 			sin->sin6_flowinfo = np->flow_label;
 	} else {
-		if (ipv6_addr_any(&np->rcv_saddr))
+		if (ipv6_addr_any(&sk->sk_v6_rcv_saddr))
 			sin->sin6_addr = np->saddr;
 		else
-			sin->sin6_addr = np->rcv_saddr;
+			sin->sin6_addr = sk->sk_v6_rcv_saddr;
 
 		sin->sin6_port = inet->inet_sport;
 	}
@@ -655,7 +655,7 @@ int inet6_sk_rebuild_header(struct sock *sk)
 
 		memset(&fl6, 0, sizeof(fl6));
 		fl6.flowi6_proto = sk->sk_protocol;
-		fl6.daddr = np->daddr;
+		fl6.daddr = sk->sk_v6_daddr;
 		fl6.saddr = np->saddr;
 		fl6.flowlabel = np->flow_label;
 		fl6.flowi6_oif = sk->sk_bound_dev_if;
diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c
index 48b6bd2a9a14..a454b0ff57c7 100644
--- a/net/ipv6/datagram.c
+++ b/net/ipv6/datagram.c
@@ -107,16 +107,16 @@ ipv4_connected:
 		if (err)
 			goto out;
 
-		ipv6_addr_set_v4mapped(inet->inet_daddr, &np->daddr);
+		ipv6_addr_set_v4mapped(inet->inet_daddr, &sk->sk_v6_daddr);
 
 		if (ipv6_addr_any(&np->saddr) ||
 		    ipv6_mapped_addr_any(&np->saddr))
 			ipv6_addr_set_v4mapped(inet->inet_saddr, &np->saddr);
 
-		if (ipv6_addr_any(&np->rcv_saddr) ||
-		    ipv6_mapped_addr_any(&np->rcv_saddr)) {
+		if (ipv6_addr_any(&sk->sk_v6_rcv_saddr) ||
+		    ipv6_mapped_addr_any(&sk->sk_v6_rcv_saddr)) {
 			ipv6_addr_set_v4mapped(inet->inet_rcv_saddr,
-					       &np->rcv_saddr);
+					       &sk->sk_v6_rcv_saddr);
 			if (sk->sk_prot->rehash)
 				sk->sk_prot->rehash(sk);
 		}
@@ -145,7 +145,7 @@ ipv4_connected:
 		}
 	}
 
-	np->daddr = *daddr;
+	sk->sk_v6_daddr = *daddr;
 	np->flow_label = fl6.flowlabel;
 
 	inet->inet_dport = usin->sin6_port;
@@ -156,7 +156,7 @@ ipv4_connected:
 	 */
 
 	fl6.flowi6_proto = sk->sk_protocol;
-	fl6.daddr = np->daddr;
+	fl6.daddr = sk->sk_v6_daddr;
 	fl6.saddr = np->saddr;
 	fl6.flowi6_oif = sk->sk_bound_dev_if;
 	fl6.flowi6_mark = sk->sk_mark;
@@ -183,16 +183,16 @@ ipv4_connected:
 	if (ipv6_addr_any(&np->saddr))
 		np->saddr = fl6.saddr;
 
-	if (ipv6_addr_any(&np->rcv_saddr)) {
-		np->rcv_saddr = fl6.saddr;
+	if (ipv6_addr_any(&sk->sk_v6_rcv_saddr)) {
+		sk->sk_v6_rcv_saddr = fl6.saddr;
 		inet->inet_rcv_saddr = LOOPBACK4_IPV6;
 		if (sk->sk_prot->rehash)
 			sk->sk_prot->rehash(sk);
 	}
 
 	ip6_dst_store(sk, dst,
-		      ipv6_addr_equal(&fl6.daddr, &np->daddr) ?
-		      &np->daddr : NULL,
+		      ipv6_addr_equal(&fl6.daddr, &sk->sk_v6_daddr) ?
+		      &sk->sk_v6_daddr : NULL,
 #ifdef CONFIG_IPV6_SUBTREES
 		      ipv6_addr_equal(&fl6.saddr, &np->saddr) ?
 		      &np->saddr :
@@ -883,11 +883,10 @@ EXPORT_SYMBOL_GPL(ip6_datagram_send_ctl);
 void ip6_dgram_sock_seq_show(struct seq_file *seq, struct sock *sp,
 			     __u16 srcp, __u16 destp, int bucket)
 {
-	struct ipv6_pinfo *np = inet6_sk(sp);
 	const struct in6_addr *dest, *src;
 
-	dest  = &np->daddr;
-	src   = &np->rcv_saddr;
+	dest  = &sp->sk_v6_daddr;
+	src   = &sp->sk_v6_rcv_saddr;
 	seq_printf(seq,
 		   "%5d: %08X%08X%08X%08X:%04X %08X%08X%08X%08X:%04X "
 		   "%02X %08X:%08X %02X:%08lX %08X %5u %8d %lu %d %pK %d\n",
diff --git a/net/ipv6/inet6_connection_sock.c b/net/ipv6/inet6_connection_sock.c
index e4311cbc8b4e..b7400b480e74 100644
--- a/net/ipv6/inet6_connection_sock.c
+++ b/net/ipv6/inet6_connection_sock.c
@@ -165,11 +165,10 @@ EXPORT_SYMBOL_GPL(inet6_csk_reqsk_queue_hash_add);
 
 void inet6_csk_addr2sockaddr(struct sock *sk, struct sockaddr * uaddr)
 {
-	struct ipv6_pinfo *np = inet6_sk(sk);
 	struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *) uaddr;
 
 	sin6->sin6_family = AF_INET6;
-	sin6->sin6_addr = np->daddr;
+	sin6->sin6_addr = sk->sk_v6_daddr;
 	sin6->sin6_port	= inet_sk(sk)->inet_dport;
 	/* We do not store received flowlabel for TCP */
 	sin6->sin6_flowinfo = 0;
@@ -203,7 +202,7 @@ static struct dst_entry *inet6_csk_route_socket(struct sock *sk,
 
 	memset(fl6, 0, sizeof(*fl6));
 	fl6->flowi6_proto = sk->sk_protocol;
-	fl6->daddr = np->daddr;
+	fl6->daddr = sk->sk_v6_daddr;
 	fl6->saddr = np->saddr;
 	fl6->flowlabel = np->flow_label;
 	IP6_ECN_flow_xmit(sk, fl6->flowlabel);
@@ -245,7 +244,7 @@ int inet6_csk_xmit(struct sk_buff *skb, struct flowi *fl_unused)
 	skb_dst_set_noref(skb, dst);
 
 	/* Restore final destination back after routing done */
-	fl6.daddr = np->daddr;
+	fl6.daddr = sk->sk_v6_daddr;
 
 	res = ip6_xmit(sk, skb, &fl6, np->opt, np->tclass);
 	rcu_read_unlock();
diff --git a/net/ipv6/inet6_hashtables.c b/net/ipv6/inet6_hashtables.c
index 46440777e1c5..842d833dfc18 100644
--- a/net/ipv6/inet6_hashtables.c
+++ b/net/ipv6/inet6_hashtables.c
@@ -89,30 +89,16 @@ begin:
 	sk_nulls_for_each_rcu(sk, node, &head->chain) {
 		if (sk->sk_hash != hash)
 			continue;
-		if (sk->sk_state == TCP_TIME_WAIT) {
-			if (!INET6_TW_MATCH(sk, net, saddr, daddr, ports, dif))
-				continue;
-		} else {
-			if (!INET6_MATCH(sk, net, saddr, daddr, ports, dif))
-				continue;
-		}
+		if (!INET6_MATCH(sk, net, saddr, daddr, ports, dif))
+			continue;
 		if (unlikely(!atomic_inc_not_zero(&sk->sk_refcnt)))
 			goto out;
 
-		if (sk->sk_state == TCP_TIME_WAIT) {
-			if (unlikely(!INET6_TW_MATCH(sk, net, saddr, daddr,
-						     ports, dif))) {
-				sock_gen_put(sk);
-				goto begin;
-			}
-		} else {
-			if (unlikely(!INET6_MATCH(sk, net, saddr, daddr,
-						  ports, dif))) {
-				sock_put(sk);
-				goto begin;
-			}
-		goto found;
+		if (unlikely(!INET6_MATCH(sk, net, saddr, daddr, ports, dif))) {
+			sock_gen_put(sk);
+			goto begin;
 		}
+		goto found;
 	}
 	if (get_nulls_value(node) != slot)
 		goto begin;
@@ -133,11 +119,10 @@ static inline int compute_score(struct sock *sk, struct net *net,
 
 	if (net_eq(sock_net(sk), net) && inet_sk(sk)->inet_num == hnum &&
 	    sk->sk_family == PF_INET6) {
-		const struct ipv6_pinfo *np = inet6_sk(sk);
 
 		score = 1;
-		if (!ipv6_addr_any(&np->rcv_saddr)) {
-			if (!ipv6_addr_equal(&np->rcv_saddr, daddr))
+		if (!ipv6_addr_any(&sk->sk_v6_rcv_saddr)) {
+			if (!ipv6_addr_equal(&sk->sk_v6_rcv_saddr, daddr))
 				return -1;
 			score++;
 		}
@@ -229,9 +214,8 @@ static int __inet6_check_established(struct inet_timewait_death_row *death_row,
 {
 	struct inet_hashinfo *hinfo = death_row->hashinfo;
 	struct inet_sock *inet = inet_sk(sk);
-	const struct ipv6_pinfo *np = inet6_sk(sk);
-	const struct in6_addr *daddr = &np->rcv_saddr;
-	const struct in6_addr *saddr = &np->daddr;
+	const struct in6_addr *daddr = &sk->sk_v6_rcv_saddr;
+	const struct in6_addr *saddr = &sk->sk_v6_daddr;
 	const int dif = sk->sk_bound_dev_if;
 	const __portpair ports = INET_COMBINED_PORTS(inet->inet_dport, lport);
 	struct net *net = sock_net(sk);
@@ -250,23 +234,19 @@ static int __inet6_check_established(struct inet_timewait_death_row *death_row,
 		if (sk2->sk_hash != hash)
 			continue;
 
-		if (sk2->sk_state == TCP_TIME_WAIT) {
-			if (likely(INET6_TW_MATCH(sk2, net, saddr, daddr,
-						  ports, dif))) {
+		if (likely(INET6_MATCH(sk2, net, saddr, daddr, ports, dif))) {
+			if (sk2->sk_state == TCP_TIME_WAIT) {
 				tw = inet_twsk(sk2);
 				if (twsk_unique(sk, sk2, twp))
-					goto unique;
-				else
-					goto not_unique;
+					break;
 			}
-		}
-		if (likely(INET6_MATCH(sk2, net, saddr, daddr, ports, dif)))
 			goto not_unique;
+		}
 	}
 
-unique:
 	/* Must record num and sport now. Otherwise we will see
-	 * in hash table socket with a funny identity. */
+	 * in hash table socket with a funny identity.
+	 */
 	inet->inet_num = lport;
 	inet->inet_sport = htons(lport);
 	sk->sk_hash = hash;
@@ -299,9 +279,9 @@ not_unique:
 static inline u32 inet6_sk_port_offset(const struct sock *sk)
 {
 	const struct inet_sock *inet = inet_sk(sk);
-	const struct ipv6_pinfo *np = inet6_sk(sk);
-	return secure_ipv6_port_ephemeral(np->rcv_saddr.s6_addr32,
-					  np->daddr.s6_addr32,
+
+	return secure_ipv6_port_ephemeral(sk->sk_v6_rcv_saddr.s6_addr32,
+					  sk->sk_v6_daddr.s6_addr32,
 					  inet->inet_dport);
 }
 
diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c
index d1e2e8ef29c5..4919a8e6063e 100644
--- a/net/ipv6/ipv6_sockglue.c
+++ b/net/ipv6/ipv6_sockglue.c
@@ -174,7 +174,7 @@ static int do_ipv6_setsockopt(struct sock *sk, int level, int optname,
 			}
 
 			if (ipv6_only_sock(sk) ||
-			    !ipv6_addr_v4mapped(&np->daddr)) {
+			    !ipv6_addr_v4mapped(&sk->sk_v6_daddr)) {
 				retv = -EADDRNOTAVAIL;
 				break;
 			}
@@ -1011,7 +1011,7 @@ static int do_ipv6_getsockopt(struct sock *sk, int level, int optname,
 				struct in6_pktinfo src_info;
 				src_info.ipi6_ifindex = np->mcast_oif ? np->mcast_oif :
 					np->sticky_pktinfo.ipi6_ifindex;
-				src_info.ipi6_addr = np->mcast_oif ? np->daddr : np->sticky_pktinfo.ipi6_addr;
+				src_info.ipi6_addr = np->mcast_oif ? sk->sk_v6_daddr : np->sticky_pktinfo.ipi6_addr;
 				put_cmsg(&msg, SOL_IPV6, IPV6_PKTINFO, sizeof(src_info), &src_info);
 			}
 			if (np->rxopt.bits.rxhlim) {
@@ -1026,7 +1026,8 @@ static int do_ipv6_getsockopt(struct sock *sk, int level, int optname,
 				struct in6_pktinfo src_info;
 				src_info.ipi6_ifindex = np->mcast_oif ? np->mcast_oif :
 					np->sticky_pktinfo.ipi6_ifindex;
-				src_info.ipi6_addr = np->mcast_oif ? np->daddr : np->sticky_pktinfo.ipi6_addr;
+				src_info.ipi6_addr = np->mcast_oif ? sk->sk_v6_daddr :
+								     np->sticky_pktinfo.ipi6_addr;
 				put_cmsg(&msg, SOL_IPV6, IPV6_2292PKTINFO, sizeof(src_info), &src_info);
 			}
 			if (np->rxopt.bits.rxohlim) {
diff --git a/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c b/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c
index d6e4dd8b58df..54b75ead5a69 100644
--- a/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c
+++ b/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c
@@ -297,9 +297,9 @@ ipv6_getorigdst(struct sock *sk, int optval, void __user *user, int *len)
 	struct nf_conntrack_tuple tuple = { .src.l3num = NFPROTO_IPV6 };
 	struct nf_conn *ct;
 
-	tuple.src.u3.in6 = inet6->rcv_saddr;
+	tuple.src.u3.in6 = sk->sk_v6_rcv_saddr;
 	tuple.src.u.tcp.port = inet->inet_sport;
-	tuple.dst.u3.in6 = inet6->daddr;
+	tuple.dst.u3.in6 = sk->sk_v6_daddr;
 	tuple.dst.u.tcp.port = inet->inet_dport;
 	tuple.dst.protonum = sk->sk_protocol;
 
diff --git a/net/ipv6/ping.c b/net/ipv6/ping.c
index 18f19df4189f..8815e31a87fe 100644
--- a/net/ipv6/ping.c
+++ b/net/ipv6/ping.c
@@ -116,7 +116,7 @@ int ping_v6_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 	} else {
 		if (sk->sk_state != TCP_ESTABLISHED)
 			return -EDESTADDRREQ;
-		daddr = &np->daddr;
+		daddr = &sk->sk_v6_daddr;
 	}
 
 	if (!iif)
diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c
index a4ed2416399e..3c00842b0079 100644
--- a/net/ipv6/raw.c
+++ b/net/ipv6/raw.c
@@ -77,20 +77,19 @@ static struct sock *__raw_v6_lookup(struct net *net, struct sock *sk,
 
 	sk_for_each_from(sk)
 		if (inet_sk(sk)->inet_num == num) {
-			struct ipv6_pinfo *np = inet6_sk(sk);
 
 			if (!net_eq(sock_net(sk), net))
 				continue;
 
-			if (!ipv6_addr_any(&np->daddr) &&
-			    !ipv6_addr_equal(&np->daddr, rmt_addr))
+			if (!ipv6_addr_any(&sk->sk_v6_daddr) &&
+			    !ipv6_addr_equal(&sk->sk_v6_daddr, rmt_addr))
 				continue;
 
 			if (sk->sk_bound_dev_if && sk->sk_bound_dev_if != dif)
 				continue;
 
-			if (!ipv6_addr_any(&np->rcv_saddr)) {
-				if (ipv6_addr_equal(&np->rcv_saddr, loc_addr))
+			if (!ipv6_addr_any(&sk->sk_v6_rcv_saddr)) {
+				if (ipv6_addr_equal(&sk->sk_v6_rcv_saddr, loc_addr))
 					goto found;
 				if (is_multicast &&
 				    inet6_mc_check(sk, loc_addr, rmt_addr))
@@ -302,7 +301,7 @@ static int rawv6_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 	}
 
 	inet->inet_rcv_saddr = inet->inet_saddr = v4addr;
-	np->rcv_saddr = addr->sin6_addr;
+	sk->sk_v6_rcv_saddr = addr->sin6_addr;
 	if (!(addr_type & IPV6_ADDR_MULTICAST))
 		np->saddr = addr->sin6_addr;
 	err = 0;
@@ -804,8 +803,8 @@ static int rawv6_sendmsg(struct kiocb *iocb, struct sock *sk,
 		 * sk->sk_dst_cache.
 		 */
 		if (sk->sk_state == TCP_ESTABLISHED &&
-		    ipv6_addr_equal(daddr, &np->daddr))
-			daddr = &np->daddr;
+		    ipv6_addr_equal(daddr, &sk->sk_v6_daddr))
+			daddr = &sk->sk_v6_daddr;
 
 		if (addr_len >= sizeof(struct sockaddr_in6) &&
 		    sin6->sin6_scope_id &&
@@ -816,7 +815,7 @@ static int rawv6_sendmsg(struct kiocb *iocb, struct sock *sk,
 			return -EDESTADDRREQ;
 
 		proto = inet->inet_num;
-		daddr = &np->daddr;
+		daddr = &sk->sk_v6_daddr;
 		fl6.flowlabel = np->flow_label;
 	}
 
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 528e61afaf5e..541dfc40c7b3 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -192,13 +192,13 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
 	}
 
 	if (tp->rx_opt.ts_recent_stamp &&
-	    !ipv6_addr_equal(&np->daddr, &usin->sin6_addr)) {
+	    !ipv6_addr_equal(&sk->sk_v6_daddr, &usin->sin6_addr)) {
 		tp->rx_opt.ts_recent = 0;
 		tp->rx_opt.ts_recent_stamp = 0;
 		tp->write_seq = 0;
 	}
 
-	np->daddr = usin->sin6_addr;
+	sk->sk_v6_daddr = usin->sin6_addr;
 	np->flow_label = fl6.flowlabel;
 
 	/*
@@ -237,17 +237,17 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
 		} else {
 			ipv6_addr_set_v4mapped(inet->inet_saddr, &np->saddr);
 			ipv6_addr_set_v4mapped(inet->inet_rcv_saddr,
-					       &np->rcv_saddr);
+					       &sk->sk_v6_rcv_saddr);
 		}
 
 		return err;
 	}
 
-	if (!ipv6_addr_any(&np->rcv_saddr))
-		saddr = &np->rcv_saddr;
+	if (!ipv6_addr_any(&sk->sk_v6_rcv_saddr))
+		saddr = &sk->sk_v6_rcv_saddr;
 
 	fl6.flowi6_proto = IPPROTO_TCP;
-	fl6.daddr = np->daddr;
+	fl6.daddr = sk->sk_v6_daddr;
 	fl6.saddr = saddr ? *saddr : np->saddr;
 	fl6.flowi6_oif = sk->sk_bound_dev_if;
 	fl6.flowi6_mark = sk->sk_mark;
@@ -266,7 +266,7 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
 
 	if (saddr == NULL) {
 		saddr = &fl6.saddr;
-		np->rcv_saddr = *saddr;
+		sk->sk_v6_rcv_saddr = *saddr;
 	}
 
 	/* set the source address */
@@ -279,7 +279,7 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
 	rt = (struct rt6_info *) dst;
 	if (tcp_death_row.sysctl_tw_recycle &&
 	    !tp->rx_opt.ts_recent_stamp &&
-	    ipv6_addr_equal(&rt->rt6i_dst.addr, &np->daddr))
+	    ipv6_addr_equal(&rt->rt6i_dst.addr, &sk->sk_v6_daddr))
 		tcp_fetch_timewait_stamp(sk, dst);
 
 	icsk->icsk_ext_hdr_len = 0;
@@ -298,7 +298,7 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
 
 	if (!tp->write_seq && likely(!tp->repair))
 		tp->write_seq = secure_tcpv6_sequence_number(np->saddr.s6_addr32,
-							     np->daddr.s6_addr32,
+							     sk->sk_v6_daddr.s6_addr32,
 							     inet->inet_sport,
 							     inet->inet_dport);
 
@@ -515,7 +515,7 @@ static struct tcp_md5sig_key *tcp_v6_md5_do_lookup(struct sock *sk,
 static struct tcp_md5sig_key *tcp_v6_md5_lookup(struct sock *sk,
 						struct sock *addr_sk)
 {
-	return tcp_v6_md5_do_lookup(sk, &inet6_sk(addr_sk)->daddr);
+	return tcp_v6_md5_do_lookup(sk, &addr_sk->sk_v6_daddr);
 }
 
 static struct tcp_md5sig_key *tcp_v6_reqsk_md5_lookup(struct sock *sk,
@@ -621,7 +621,7 @@ static int tcp_v6_md5_hash_skb(char *md5_hash, struct tcp_md5sig_key *key,
 
 	if (sk) {
 		saddr = &inet6_sk(sk)->saddr;
-		daddr = &inet6_sk(sk)->daddr;
+		daddr = &sk->sk_v6_daddr;
 	} else if (req) {
 		saddr = &inet6_rsk(req)->loc_addr;
 		daddr = &inet6_rsk(req)->rmt_addr;
@@ -1116,11 +1116,11 @@ static struct sock * tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb,
 
 		memcpy(newnp, np, sizeof(struct ipv6_pinfo));
 
-		ipv6_addr_set_v4mapped(newinet->inet_daddr, &newnp->daddr);
+		ipv6_addr_set_v4mapped(newinet->inet_daddr, &newsk->sk_v6_daddr);
 
 		ipv6_addr_set_v4mapped(newinet->inet_saddr, &newnp->saddr);
 
-		newnp->rcv_saddr = newnp->saddr;
+		newsk->sk_v6_rcv_saddr = newnp->saddr;
 
 		inet_csk(newsk)->icsk_af_ops = &ipv6_mapped;
 		newsk->sk_backlog_rcv = tcp_v4_do_rcv;
@@ -1185,9 +1185,9 @@ static struct sock * tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb,
 
 	memcpy(newnp, np, sizeof(struct ipv6_pinfo));
 
-	newnp->daddr = treq->rmt_addr;
+	newsk->sk_v6_daddr = treq->rmt_addr;
 	newnp->saddr = treq->loc_addr;
-	newnp->rcv_saddr = treq->loc_addr;
+	newsk->sk_v6_rcv_saddr = treq->loc_addr;
 	newsk->sk_bound_dev_if = treq->iif;
 
 	/* Now IPv6 options...
@@ -1244,13 +1244,13 @@ static struct sock * tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb,
 
 #ifdef CONFIG_TCP_MD5SIG
 	/* Copy over the MD5 key from the original socket */
-	if ((key = tcp_v6_md5_do_lookup(sk, &newnp->daddr)) != NULL) {
+	if ((key = tcp_v6_md5_do_lookup(sk, &newsk->sk_v6_daddr)) != NULL) {
 		/* We're using one, so create a matching key
 		 * on the newsk structure. If we fail to get
 		 * memory, then we end up not copying the key
 		 * across. Shucks.
 		 */
-		tcp_md5_do_add(newsk, (union tcp_md5_addr *)&newnp->daddr,
+		tcp_md5_do_add(newsk, (union tcp_md5_addr *)&newsk->sk_v6_daddr,
 			       AF_INET6, key->key, key->keylen,
 			       sk_gfp_atomic(sk, GFP_ATOMIC));
 	}
@@ -1758,10 +1758,9 @@ static void get_tcp6_sock(struct seq_file *seq, struct sock *sp, int i)
 	const struct inet_sock *inet = inet_sk(sp);
 	const struct tcp_sock *tp = tcp_sk(sp);
 	const struct inet_connection_sock *icsk = inet_csk(sp);
-	const struct ipv6_pinfo *np = inet6_sk(sp);
 
-	dest  = &np->daddr;
-	src   = &np->rcv_saddr;
+	dest  = &sp->sk_v6_daddr;
+	src   = &sp->sk_v6_rcv_saddr;
 	destp = ntohs(inet->inet_dport);
 	srcp  = ntohs(inet->inet_sport);
 
@@ -1810,11 +1809,10 @@ static void get_timewait6_sock(struct seq_file *seq,
 {
 	const struct in6_addr *dest, *src;
 	__u16 destp, srcp;
-	const struct inet6_timewait_sock *tw6 = inet6_twsk((struct sock *)tw);
 	s32 delta = tw->tw_ttd - inet_tw_time_stamp();
 
-	dest = &tw6->tw_v6_daddr;
-	src  = &tw6->tw_v6_rcv_saddr;
+	dest = &tw->tw_v6_daddr;
+	src  = &tw->tw_v6_rcv_saddr;
 	destp = ntohs(tw->tw_dport);
 	srcp  = ntohs(tw->tw_sport);
 
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 37532478e3ba..b496de19a341 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -55,11 +55,10 @@
 
 int ipv6_rcv_saddr_equal(const struct sock *sk, const struct sock *sk2)
 {
-	const struct in6_addr *sk_rcv_saddr6 = &inet6_sk(sk)->rcv_saddr;
 	const struct in6_addr *sk2_rcv_saddr6 = inet6_rcv_saddr(sk2);
 	int sk_ipv6only = ipv6_only_sock(sk);
 	int sk2_ipv6only = inet_v6_ipv6only(sk2);
-	int addr_type = ipv6_addr_type(sk_rcv_saddr6);
+	int addr_type = ipv6_addr_type(&sk->sk_v6_rcv_saddr);
 	int addr_type2 = sk2_rcv_saddr6 ? ipv6_addr_type(sk2_rcv_saddr6) : IPV6_ADDR_MAPPED;
 
 	/* if both are mapped, treat as IPv4 */
@@ -77,7 +76,7 @@ int ipv6_rcv_saddr_equal(const struct sock *sk, const struct sock *sk2)
 		return 1;
 
 	if (sk2_rcv_saddr6 &&
-	    ipv6_addr_equal(sk_rcv_saddr6, sk2_rcv_saddr6))
+	    ipv6_addr_equal(&sk->sk_v6_rcv_saddr, sk2_rcv_saddr6))
 		return 1;
 
 	return 0;
@@ -105,7 +104,7 @@ int udp_v6_get_port(struct sock *sk, unsigned short snum)
 	unsigned int hash2_nulladdr =
 		udp6_portaddr_hash(sock_net(sk), &in6addr_any, snum);
 	unsigned int hash2_partial =
-		udp6_portaddr_hash(sock_net(sk), &inet6_sk(sk)->rcv_saddr, 0);
+		udp6_portaddr_hash(sock_net(sk), &sk->sk_v6_rcv_saddr, 0);
 
 	/* precompute partial secondary hash */
 	udp_sk(sk)->udp_portaddr_hash = hash2_partial;
@@ -115,7 +114,7 @@ int udp_v6_get_port(struct sock *sk, unsigned short snum)
 static void udp_v6_rehash(struct sock *sk)
 {
 	u16 new_hash = udp6_portaddr_hash(sock_net(sk),
-					  &inet6_sk(sk)->rcv_saddr,
+					  &sk->sk_v6_rcv_saddr,
 					  inet_sk(sk)->inet_num);
 
 	udp_lib_rehash(sk, new_hash);
@@ -131,7 +130,6 @@ static inline int compute_score(struct sock *sk, struct net *net,
 
 	if (net_eq(sock_net(sk), net) && udp_sk(sk)->udp_port_hash == hnum &&
 			sk->sk_family == PF_INET6) {
-		struct ipv6_pinfo *np = inet6_sk(sk);
 		struct inet_sock *inet = inet_sk(sk);
 
 		score = 0;
@@ -140,13 +138,13 @@ static inline int compute_score(struct sock *sk, struct net *net,
 				return -1;
 			score++;
 		}
-		if (!ipv6_addr_any(&np->rcv_saddr)) {
-			if (!ipv6_addr_equal(&np->rcv_saddr, daddr))
+		if (!ipv6_addr_any(&sk->sk_v6_rcv_saddr)) {
+			if (!ipv6_addr_equal(&sk->sk_v6_rcv_saddr, daddr))
 				return -1;
 			score++;
 		}
-		if (!ipv6_addr_any(&np->daddr)) {
-			if (!ipv6_addr_equal(&np->daddr, saddr))
+		if (!ipv6_addr_any(&sk->sk_v6_daddr)) {
+			if (!ipv6_addr_equal(&sk->sk_v6_daddr, saddr))
 				return -1;
 			score++;
 		}
@@ -169,10 +167,9 @@ static inline int compute_score2(struct sock *sk, struct net *net,
 
 	if (net_eq(sock_net(sk), net) && udp_sk(sk)->udp_port_hash == hnum &&
 			sk->sk_family == PF_INET6) {
-		struct ipv6_pinfo *np = inet6_sk(sk);
 		struct inet_sock *inet = inet_sk(sk);
 
-		if (!ipv6_addr_equal(&np->rcv_saddr, daddr))
+		if (!ipv6_addr_equal(&sk->sk_v6_rcv_saddr, daddr))
 			return -1;
 		score = 0;
 		if (inet->inet_dport) {
@@ -180,8 +177,8 @@ static inline int compute_score2(struct sock *sk, struct net *net,
 				return -1;
 			score++;
 		}
-		if (!ipv6_addr_any(&np->daddr)) {
-			if (!ipv6_addr_equal(&np->daddr, saddr))
+		if (!ipv6_addr_any(&sk->sk_v6_daddr)) {
+			if (!ipv6_addr_equal(&sk->sk_v6_daddr, saddr))
 				return -1;
 			score++;
 		}
@@ -549,7 +546,7 @@ static int __udpv6_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
 {
 	int rc;
 
-	if (!ipv6_addr_any(&inet6_sk(sk)->daddr)) {
+	if (!ipv6_addr_any(&sk->sk_v6_daddr)) {
 		sock_rps_save_rxhash(sk, skb);
 		sk_mark_napi_id(sk, skb);
 	}
@@ -690,20 +687,19 @@ static struct sock *udp_v6_mcast_next(struct net *net, struct sock *sk,
 
 		if (udp_sk(s)->udp_port_hash == num &&
 		    s->sk_family == PF_INET6) {
-			struct ipv6_pinfo *np = inet6_sk(s);
 			if (inet->inet_dport) {
 				if (inet->inet_dport != rmt_port)
 					continue;
 			}
-			if (!ipv6_addr_any(&np->daddr) &&
-			    !ipv6_addr_equal(&np->daddr, rmt_addr))
+			if (!ipv6_addr_any(&sk->sk_v6_daddr) &&
+			    !ipv6_addr_equal(&sk->sk_v6_daddr, rmt_addr))
 				continue;
 
 			if (s->sk_bound_dev_if && s->sk_bound_dev_if != dif)
 				continue;
 
-			if (!ipv6_addr_any(&np->rcv_saddr)) {
-				if (!ipv6_addr_equal(&np->rcv_saddr, loc_addr))
+			if (!ipv6_addr_any(&sk->sk_v6_rcv_saddr)) {
+				if (!ipv6_addr_equal(&sk->sk_v6_rcv_saddr, loc_addr))
 					continue;
 			}
 			if (!inet6_mc_check(s, loc_addr, rmt_addr))
@@ -1063,7 +1059,7 @@ int udpv6_sendmsg(struct kiocb *iocb, struct sock *sk,
 	} else if (!up->pending) {
 		if (sk->sk_state != TCP_ESTABLISHED)
 			return -EDESTADDRREQ;
-		daddr = &np->daddr;
+		daddr = &sk->sk_v6_daddr;
 	} else
 		daddr = NULL;
 
@@ -1133,8 +1129,8 @@ do_udp_sendmsg:
 		 * sk->sk_dst_cache.
 		 */
 		if (sk->sk_state == TCP_ESTABLISHED &&
-		    ipv6_addr_equal(daddr, &np->daddr))
-			daddr = &np->daddr;
+		    ipv6_addr_equal(daddr, &sk->sk_v6_daddr))
+			daddr = &sk->sk_v6_daddr;
 
 		if (addr_len >= sizeof(struct sockaddr_in6) &&
 		    sin6->sin6_scope_id &&
@@ -1145,7 +1141,7 @@ do_udp_sendmsg:
 			return -EDESTADDRREQ;
 
 		fl6.fl6_dport = inet->inet_dport;
-		daddr = &np->daddr;
+		daddr = &sk->sk_v6_daddr;
 		fl6.flowlabel = np->flow_label;
 		connected = 1;
 	}
@@ -1261,8 +1257,8 @@ do_append_data:
 	if (dst) {
 		if (connected) {
 			ip6_dst_store(sk, dst,
-				      ipv6_addr_equal(&fl6.daddr, &np->daddr) ?
-				      &np->daddr : NULL,
+				      ipv6_addr_equal(&fl6.daddr, &sk->sk_v6_daddr) ?
+				      &sk->sk_v6_daddr : NULL,
 #ifdef CONFIG_IPV6_SUBTREES
 				      ipv6_addr_equal(&fl6.saddr, &np->saddr) ?
 				      &np->saddr :
diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c
index b076e8309bc2..9af77d9c0ec9 100644
--- a/net/l2tp/l2tp_core.c
+++ b/net/l2tp/l2tp_core.c
@@ -1181,7 +1181,7 @@ static void l2tp_xmit_ipv6_csum(struct sock *sk, struct sk_buff *skb,
 	    !(skb_dst(skb)->dev->features & NETIF_F_IPV6_CSUM)) {
 		__wsum csum = skb_checksum(skb, 0, udp_len, 0);
 		skb->ip_summed = CHECKSUM_UNNECESSARY;
-		uh->check = csum_ipv6_magic(&np->saddr, &np->daddr, udp_len,
+		uh->check = csum_ipv6_magic(&np->saddr, &sk->sk_v6_daddr, udp_len,
 					    IPPROTO_UDP, csum);
 		if (uh->check == 0)
 			uh->check = CSUM_MANGLED_0;
@@ -1189,7 +1189,7 @@ static void l2tp_xmit_ipv6_csum(struct sock *sk, struct sk_buff *skb,
 		skb->ip_summed = CHECKSUM_PARTIAL;
 		skb->csum_start = skb_transport_header(skb) - skb->head;
 		skb->csum_offset = offsetof(struct udphdr, check);
-		uh->check = ~csum_ipv6_magic(&np->saddr, &np->daddr,
+		uh->check = ~csum_ipv6_magic(&np->saddr, &sk->sk_v6_daddr,
 					     udp_len, IPPROTO_UDP, 0);
 	}
 }
@@ -1713,13 +1713,13 @@ int l2tp_tunnel_create(struct net *net, int fd, int version, u32 tunnel_id, u32
 		struct ipv6_pinfo *np = inet6_sk(sk);
 
 		if (ipv6_addr_v4mapped(&np->saddr) &&
-		    ipv6_addr_v4mapped(&np->daddr)) {
+		    ipv6_addr_v4mapped(&sk->sk_v6_daddr)) {
 			struct inet_sock *inet = inet_sk(sk);
 
 			tunnel->v4mapped = true;
 			inet->inet_saddr = np->saddr.s6_addr32[3];
-			inet->inet_rcv_saddr = np->rcv_saddr.s6_addr32[3];
-			inet->inet_daddr = np->daddr.s6_addr32[3];
+			inet->inet_rcv_saddr = sk->sk_v6_rcv_saddr.s6_addr32[3];
+			inet->inet_daddr = sk->sk_v6_daddr.s6_addr32[3];
 		} else {
 			tunnel->v4mapped = false;
 		}
diff --git a/net/l2tp/l2tp_debugfs.c b/net/l2tp/l2tp_debugfs.c
index 072d7202e182..2d6760a2ae34 100644
--- a/net/l2tp/l2tp_debugfs.c
+++ b/net/l2tp/l2tp_debugfs.c
@@ -127,9 +127,10 @@ static void l2tp_dfs_seq_tunnel_show(struct seq_file *m, void *v)
 
 #if IS_ENABLED(CONFIG_IPV6)
 		if (tunnel->sock->sk_family == AF_INET6) {
-			struct ipv6_pinfo *np = inet6_sk(tunnel->sock);
+			const struct ipv6_pinfo *np = inet6_sk(tunnel->sock);
+
 			seq_printf(m, " from %pI6c to %pI6c\n",
-				&np->saddr, &np->daddr);
+				&np->saddr, &tunnel->sock->sk_v6_daddr);
 		} else
 #endif
 		seq_printf(m, " from %pI4 to %pI4\n",
diff --git a/net/l2tp/l2tp_ip6.c b/net/l2tp/l2tp_ip6.c
index b8a6039314e8..cfd65304be60 100644
--- a/net/l2tp/l2tp_ip6.c
+++ b/net/l2tp/l2tp_ip6.c
@@ -63,7 +63,7 @@ static struct sock *__l2tp_ip6_bind_lookup(struct net *net,
 	struct sock *sk;
 
 	sk_for_each_bound(sk, &l2tp_ip6_bind_table) {
-		struct in6_addr *addr = inet6_rcv_saddr(sk);
+		const struct in6_addr *addr = inet6_rcv_saddr(sk);
 		struct l2tp_ip6_sock *l2tp = l2tp_ip6_sk(sk);
 
 		if (l2tp == NULL)
@@ -331,7 +331,7 @@ static int l2tp_ip6_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 	rcu_read_unlock();
 
 	inet->inet_rcv_saddr = inet->inet_saddr = v4addr;
-	np->rcv_saddr = addr->l2tp_addr;
+	sk->sk_v6_rcv_saddr = addr->l2tp_addr;
 	np->saddr = addr->l2tp_addr;
 
 	l2tp_ip6_sk(sk)->conn_id = addr->l2tp_conn_id;
@@ -421,14 +421,14 @@ static int l2tp_ip6_getname(struct socket *sock, struct sockaddr *uaddr,
 		if (!lsk->peer_conn_id)
 			return -ENOTCONN;
 		lsa->l2tp_conn_id = lsk->peer_conn_id;
-		lsa->l2tp_addr = np->daddr;
+		lsa->l2tp_addr = sk->sk_v6_daddr;
 		if (np->sndflow)
 			lsa->l2tp_flowinfo = np->flow_label;
 	} else {
-		if (ipv6_addr_any(&np->rcv_saddr))
+		if (ipv6_addr_any(&sk->sk_v6_rcv_saddr))
 			lsa->l2tp_addr = np->saddr;
 		else
-			lsa->l2tp_addr = np->rcv_saddr;
+			lsa->l2tp_addr = sk->sk_v6_rcv_saddr;
 
 		lsa->l2tp_conn_id = lsk->conn_id;
 	}
@@ -537,8 +537,8 @@ static int l2tp_ip6_sendmsg(struct kiocb *iocb, struct sock *sk,
 		 * sk->sk_dst_cache.
 		 */
 		if (sk->sk_state == TCP_ESTABLISHED &&
-		    ipv6_addr_equal(daddr, &np->daddr))
-			daddr = &np->daddr;
+		    ipv6_addr_equal(daddr, &sk->sk_v6_daddr))
+			daddr = &sk->sk_v6_daddr;
 
 		if (addr_len >= sizeof(struct sockaddr_in6) &&
 		    lsa->l2tp_scope_id &&
@@ -548,7 +548,7 @@ static int l2tp_ip6_sendmsg(struct kiocb *iocb, struct sock *sk,
 		if (sk->sk_state != TCP_ESTABLISHED)
 			return -EDESTADDRREQ;
 
-		daddr = &np->daddr;
+		daddr = &sk->sk_v6_daddr;
 		fl6.flowlabel = np->flow_label;
 	}
 
diff --git a/net/l2tp/l2tp_netlink.c b/net/l2tp/l2tp_netlink.c
index 0825ff26e113..be446d517bc9 100644
--- a/net/l2tp/l2tp_netlink.c
+++ b/net/l2tp/l2tp_netlink.c
@@ -306,8 +306,8 @@ static int l2tp_nl_tunnel_send(struct sk_buff *skb, u32 portid, u32 seq, int fla
 		if (np) {
 			if (nla_put(skb, L2TP_ATTR_IP6_SADDR, sizeof(np->saddr),
 				    &np->saddr) ||
-			    nla_put(skb, L2TP_ATTR_IP6_DADDR, sizeof(np->daddr),
-				    &np->daddr))
+			    nla_put(skb, L2TP_ATTR_IP6_DADDR, sizeof(sk->sk_v6_daddr),
+				    &sk->sk_v6_daddr))
 				goto nla_put_failure;
 		} else
 #endif
diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c
index 5ebee2ded9e9..f0a7adaef2ea 100644
--- a/net/l2tp/l2tp_ppp.c
+++ b/net/l2tp/l2tp_ppp.c
@@ -906,8 +906,8 @@ static int pppol2tp_getname(struct socket *sock, struct sockaddr *uaddr,
 #if IS_ENABLED(CONFIG_IPV6)
 	} else if ((tunnel->version == 2) &&
 		   (tunnel->sock->sk_family == AF_INET6)) {
-		struct ipv6_pinfo *np = inet6_sk(tunnel->sock);
 		struct sockaddr_pppol2tpin6 sp;
+
 		len = sizeof(sp);
 		memset(&sp, 0, len);
 		sp.sa_family	= AF_PPPOX;
@@ -920,13 +920,13 @@ static int pppol2tp_getname(struct socket *sock, struct sockaddr *uaddr,
 		sp.pppol2tp.d_session = session->peer_session_id;
 		sp.pppol2tp.addr.sin6_family = AF_INET6;
 		sp.pppol2tp.addr.sin6_port = inet->inet_dport;
-		memcpy(&sp.pppol2tp.addr.sin6_addr, &np->daddr,
-		       sizeof(np->daddr));
+		memcpy(&sp.pppol2tp.addr.sin6_addr, &tunnel->sock->sk_v6_daddr,
+		       sizeof(tunnel->sock->sk_v6_daddr));
 		memcpy(uaddr, &sp, len);
 	} else if ((tunnel->version == 3) &&
 		   (tunnel->sock->sk_family == AF_INET6)) {
-		struct ipv6_pinfo *np = inet6_sk(tunnel->sock);
 		struct sockaddr_pppol2tpv3in6 sp;
+
 		len = sizeof(sp);
 		memset(&sp, 0, len);
 		sp.sa_family	= AF_PPPOX;
@@ -939,8 +939,8 @@ static int pppol2tp_getname(struct socket *sock, struct sockaddr *uaddr,
 		sp.pppol2tp.d_session = session->peer_session_id;
 		sp.pppol2tp.addr.sin6_family = AF_INET6;
 		sp.pppol2tp.addr.sin6_port = inet->inet_dport;
-		memcpy(&sp.pppol2tp.addr.sin6_addr, &np->daddr,
-		       sizeof(np->daddr));
+		memcpy(&sp.pppol2tp.addr.sin6_addr, &tunnel->sock->sk_v6_daddr,
+		       sizeof(tunnel->sock->sk_v6_daddr));
 		memcpy(uaddr, &sp, len);
 #endif
 	} else if (tunnel->version == 3) {
diff --git a/net/netfilter/xt_TPROXY.c b/net/netfilter/xt_TPROXY.c
index 5d8a3a3cd5a7..ef8a926752a9 100644
--- a/net/netfilter/xt_TPROXY.c
+++ b/net/netfilter/xt_TPROXY.c
@@ -200,7 +200,7 @@ nf_tproxy_get_sock_v6(struct net *net, const u8 protocol,
 				     in->ifindex);
 		if (sk) {
 			int connected = (sk->sk_state == TCP_ESTABLISHED);
-			int wildcard = ipv6_addr_any(&inet6_sk(sk)->rcv_saddr);
+			int wildcard = ipv6_addr_any(&sk->sk_v6_rcv_saddr);
 
 			/* NOTE: we return listeners even if bound to
 			 * 0.0.0.0, those are filtered out in
diff --git a/net/netfilter/xt_socket.c b/net/netfilter/xt_socket.c
index 06df2b9110f5..3dd0e374bc2b 100644
--- a/net/netfilter/xt_socket.c
+++ b/net/netfilter/xt_socket.c
@@ -370,7 +370,7 @@ socket_mt6_v1_v2(const struct sk_buff *skb, struct xt_action_param *par)
 		 */
 		wildcard = (!(info->flags & XT_SOCKET_NOWILDCARD) &&
 			    sk->sk_state != TCP_TIME_WAIT &&
-			    ipv6_addr_any(&inet6_sk(sk)->rcv_saddr));
+			    ipv6_addr_any(&sk->sk_v6_rcv_saddr));
 
 		/* Ignore non-transparent sockets,
 		   if XT_SOCKET_TRANSPARENT is used */
diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c
index e7b2d4fe2b6a..f6334aa19151 100644
--- a/net/sctp/ipv6.c
+++ b/net/sctp/ipv6.c
@@ -426,20 +426,20 @@ static void sctp_v6_from_sk(union sctp_addr *addr, struct sock *sk)
 {
 	addr->v6.sin6_family = AF_INET6;
 	addr->v6.sin6_port = 0;
-	addr->v6.sin6_addr = inet6_sk(sk)->rcv_saddr;
+	addr->v6.sin6_addr = sk->sk_v6_rcv_saddr;
 }
 
 /* Initialize sk->sk_rcv_saddr from sctp_addr. */
 static void sctp_v6_to_sk_saddr(union sctp_addr *addr, struct sock *sk)
 {
 	if (addr->sa.sa_family == AF_INET && sctp_sk(sk)->v4mapped) {
-		inet6_sk(sk)->rcv_saddr.s6_addr32[0] = 0;
-		inet6_sk(sk)->rcv_saddr.s6_addr32[1] = 0;
-		inet6_sk(sk)->rcv_saddr.s6_addr32[2] = htonl(0x0000ffff);
-		inet6_sk(sk)->rcv_saddr.s6_addr32[3] =
+		sk->sk_v6_rcv_saddr.s6_addr32[0] = 0;
+		sk->sk_v6_rcv_saddr.s6_addr32[1] = 0;
+		sk->sk_v6_rcv_saddr.s6_addr32[2] = htonl(0x0000ffff);
+		sk->sk_v6_rcv_saddr.s6_addr32[3] =
 			addr->v4.sin_addr.s_addr;
 	} else {
-		inet6_sk(sk)->rcv_saddr = addr->v6.sin6_addr;
+		sk->sk_v6_rcv_saddr = addr->v6.sin6_addr;
 	}
 }
 
@@ -447,12 +447,12 @@ static void sctp_v6_to_sk_saddr(union sctp_addr *addr, struct sock *sk)
 static void sctp_v6_to_sk_daddr(union sctp_addr *addr, struct sock *sk)
 {
 	if (addr->sa.sa_family == AF_INET && sctp_sk(sk)->v4mapped) {
-		inet6_sk(sk)->daddr.s6_addr32[0] = 0;
-		inet6_sk(sk)->daddr.s6_addr32[1] = 0;
-		inet6_sk(sk)->daddr.s6_addr32[2] = htonl(0x0000ffff);
-		inet6_sk(sk)->daddr.s6_addr32[3] = addr->v4.sin_addr.s_addr;
+		sk->sk_v6_daddr.s6_addr32[0] = 0;
+		sk->sk_v6_daddr.s6_addr32[1] = 0;
+		sk->sk_v6_daddr.s6_addr32[2] = htonl(0x0000ffff);
+		sk->sk_v6_daddr.s6_addr32[3] = addr->v4.sin_addr.s_addr;
 	} else {
-		inet6_sk(sk)->daddr = addr->v6.sin6_addr;
+		sk->sk_v6_daddr = addr->v6.sin6_addr;
 	}
 }
 
diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c
index 9c9caaa5e0d3..0045c7cf1e9e 100644
--- a/net/sunrpc/svcsock.c
+++ b/net/sunrpc/svcsock.c
@@ -294,7 +294,7 @@ static int svc_one_sock_name(struct svc_sock *svsk, char *buf, int remaining)
 	case PF_INET6:
 		len = snprintf(buf, remaining, "ipv6 %s %pI6 %d\n",
 				proto_name,
-				&inet6_sk(sk)->rcv_saddr,
+				&sk->sk_v6_rcv_saddr,
 				inet_sk(sk)->inet_num);
 		break;
 	default:
diff --git a/security/lsm_audit.c b/security/lsm_audit.c
index 8d8d97dbb389..80554fcf9fcc 100644
--- a/security/lsm_audit.c
+++ b/security/lsm_audit.c
@@ -304,12 +304,11 @@ static void dump_common_audit_data(struct audit_buffer *ab,
 			}
 			case AF_INET6: {
 				struct inet_sock *inet = inet_sk(sk);
-				struct ipv6_pinfo *inet6 = inet6_sk(sk);
 
-				print_ipv6_addr(ab, &inet6->rcv_saddr,
+				print_ipv6_addr(ab, &sk->sk_v6_rcv_saddr,
 						inet->inet_sport,
 						"laddr", "lport");
-				print_ipv6_addr(ab, &inet6->daddr,
+				print_ipv6_addr(ab, &sk->sk_v6_daddr,
 						inet->inet_dport,
 						"faddr", "fport");
 				break;
-- 
cgit v1.2.3


From c2bb06db59eaf92eb5ca9c6faed590597c6ceccb Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 9 Oct 2013 03:05:48 -0700
Subject: net: fix build errors if ipv6 is disabled

CONFIG_IPV6=n is still a valid choice ;)

It appears we can remove dead code.

Reported-by: Wu Fengguang <fengguang.wu@intel.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/ip6_checksum.h | 2 ++
 net/ipv4/ping.c            | 8 +++++---
 net/ipv4/tcp_metrics.c     | 4 ++++
 net/sunrpc/svcsock.c       | 2 ++
 security/lsm_audit.c       | 2 ++
 5 files changed, 15 insertions(+), 3 deletions(-)

(limited to 'security')

diff --git a/include/net/ip6_checksum.h b/include/net/ip6_checksum.h
index 1944406949ba..9e3c540c1b11 100644
--- a/include/net/ip6_checksum.h
+++ b/include/net/ip6_checksum.h
@@ -66,12 +66,14 @@ static inline void __tcp_v6_send_check(struct sk_buff *skb,
 	}
 }
 
+#if IS_ENABLED(CONFIG_IPV6)
 static inline void tcp_v6_send_check(struct sock *sk, struct sk_buff *skb)
 {
 	struct ipv6_pinfo *np = inet6_sk(sk);
 
 	__tcp_v6_send_check(skb, &np->saddr, &sk->sk_v6_daddr);
 }
+#endif
 
 int udp6_csum_init(struct sk_buff *skb, struct udphdr *uh, int proto);
 #endif
diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c
index ccefc07beacd..9afbdb19f4a2 100644
--- a/net/ipv4/ping.c
+++ b/net/ipv4/ping.c
@@ -415,10 +415,12 @@ int ping_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 		 (int)sk->sk_bound_dev_if);
 
 	err = 0;
-	if ((sk->sk_family == AF_INET && isk->inet_rcv_saddr) ||
-	    (sk->sk_family == AF_INET6 &&
-	     !ipv6_addr_any(&sk->sk_v6_rcv_saddr)))
+	if (sk->sk_family == AF_INET && isk->inet_rcv_saddr)
 		sk->sk_userlocks |= SOCK_BINDADDR_LOCK;
+#if IS_ENABLED(CONFIG_IPV6)
+	if (sk->sk_family == AF_INET6 && !ipv6_addr_any(&sk->sk_v6_rcv_saddr))
+		sk->sk_userlocks |= SOCK_BINDADDR_LOCK;
+#endif
 
 	if (snum)
 		sk->sk_userlocks |= SOCK_BINDPORT_LOCK;
diff --git a/net/ipv4/tcp_metrics.c b/net/ipv4/tcp_metrics.c
index 27535fd5ea10..8fcc2cb9dba4 100644
--- a/net/ipv4/tcp_metrics.c
+++ b/net/ipv4/tcp_metrics.c
@@ -251,10 +251,12 @@ static struct tcp_metrics_block *__tcp_get_metrics_tw(struct inet_timewait_sock
 		addr.addr.a4 = tw->tw_daddr;
 		hash = (__force unsigned int) addr.addr.a4;
 		break;
+#if IS_ENABLED(CONFIG_IPV6)
 	case AF_INET6:
 		*(struct in6_addr *)addr.addr.a6 = tw->tw_v6_daddr;
 		hash = ipv6_addr_hash(&tw->tw_v6_daddr);
 		break;
+#endif
 	default:
 		return NULL;
 	}
@@ -286,10 +288,12 @@ static struct tcp_metrics_block *tcp_get_metrics(struct sock *sk,
 		addr.addr.a4 = inet_sk(sk)->inet_daddr;
 		hash = (__force unsigned int) addr.addr.a4;
 		break;
+#if IS_ENABLED(CONFIG_IPV6)
 	case AF_INET6:
 		*(struct in6_addr *)addr.addr.a6 = sk->sk_v6_daddr;
 		hash = ipv6_addr_hash(&sk->sk_v6_daddr);
 		break;
+#endif
 	default:
 		return NULL;
 	}
diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c
index 0045c7cf1e9e..b6e59f0a9475 100644
--- a/net/sunrpc/svcsock.c
+++ b/net/sunrpc/svcsock.c
@@ -291,12 +291,14 @@ static int svc_one_sock_name(struct svc_sock *svsk, char *buf, int remaining)
 				&inet_sk(sk)->inet_rcv_saddr,
 				inet_sk(sk)->inet_num);
 		break;
+#if IS_ENABLED(CONFIG_IPV6)
 	case PF_INET6:
 		len = snprintf(buf, remaining, "ipv6 %s %pI6 %d\n",
 				proto_name,
 				&sk->sk_v6_rcv_saddr,
 				inet_sk(sk)->inet_num);
 		break;
+#endif
 	default:
 		len = snprintf(buf, remaining, "*unknown-%d*\n",
 				sk->sk_family);
diff --git a/security/lsm_audit.c b/security/lsm_audit.c
index 80554fcf9fcc..234bc2ab450c 100644
--- a/security/lsm_audit.c
+++ b/security/lsm_audit.c
@@ -302,6 +302,7 @@ static void dump_common_audit_data(struct audit_buffer *ab,
 						"faddr", "fport");
 				break;
 			}
+#if IS_ENABLED(CONFIG_IPV6)
 			case AF_INET6: {
 				struct inet_sock *inet = inet_sk(sk);
 
@@ -313,6 +314,7 @@ static void dump_common_audit_data(struct audit_buffer *ab,
 						"faddr", "fport");
 				break;
 			}
+#endif
 			case AF_UNIX:
 				u = unix_sk(sk);
 				if (u->path.dentry) {
-- 
cgit v1.2.3


From 795aa6ef6a1aba99050735eadd0c2341b789b53b Mon Sep 17 00:00:00 2001
From: Patrick McHardy <kaber@trash.net>
Date: Thu, 10 Oct 2013 09:21:55 +0200
Subject: netfilter: pass hook ops to hookfn

Pass the hook ops to the hookfn to allow for generic hook
functions. This change is required by nf_tables.

Signed-off-by: Patrick McHardy <kaber@trash.net>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/linux/netfilter.h                      |  3 +-
 net/bridge/br_netfilter.c                      | 22 +++++++++-----
 net/bridge/netfilter/ebtable_filter.c          | 16 ++++++----
 net/bridge/netfilter/ebtable_nat.c             | 16 ++++++----
 net/decnet/netfilter/dn_rtmsg.c                |  2 +-
 net/ipv4/netfilter/arptable_filter.c           |  5 +--
 net/ipv4/netfilter/ipt_CLUSTERIP.c             |  2 +-
 net/ipv4/netfilter/ipt_SYNPROXY.c              |  2 +-
 net/ipv4/netfilter/iptable_filter.c            |  7 +++--
 net/ipv4/netfilter/iptable_mangle.c            | 10 +++---
 net/ipv4/netfilter/iptable_nat.c               | 26 ++++++++--------
 net/ipv4/netfilter/iptable_raw.c               |  6 ++--
 net/ipv4/netfilter/iptable_security.c          |  7 +++--
 net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c | 12 ++++----
 net/ipv4/netfilter/nf_defrag_ipv4.c            |  6 ++--
 net/ipv6/netfilter/ip6t_SYNPROXY.c             |  2 +-
 net/ipv6/netfilter/ip6table_filter.c           |  5 +--
 net/ipv6/netfilter/ip6table_mangle.c           | 10 +++---
 net/ipv6/netfilter/ip6table_nat.c              | 27 +++++++++--------
 net/ipv6/netfilter/ip6table_raw.c              |  5 +--
 net/ipv6/netfilter/ip6table_security.c         |  5 +--
 net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c | 14 +++++----
 net/ipv6/netfilter/nf_defrag_ipv6_hooks.c      |  6 ++--
 net/netfilter/core.c                           |  2 +-
 net/netfilter/ipvs/ip_vs_core.c                | 42 +++++++++++++-------------
 security/selinux/hooks.c                       | 10 +++---
 26 files changed, 148 insertions(+), 122 deletions(-)

(limited to 'security')

diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h
index 61223c52414f..fef7e67f7101 100644
--- a/include/linux/netfilter.h
+++ b/include/linux/netfilter.h
@@ -42,7 +42,8 @@ int netfilter_init(void);
 
 struct sk_buff;
 
-typedef unsigned int nf_hookfn(unsigned int hooknum,
+struct nf_hook_ops;
+typedef unsigned int nf_hookfn(const struct nf_hook_ops *ops,
 			       struct sk_buff *skb,
 			       const struct net_device *in,
 			       const struct net_device *out,
diff --git a/net/bridge/br_netfilter.c b/net/bridge/br_netfilter.c
index f87736270eaa..878f008afefa 100644
--- a/net/bridge/br_netfilter.c
+++ b/net/bridge/br_netfilter.c
@@ -619,7 +619,7 @@ bad:
 
 /* Replicate the checks that IPv6 does on packet reception and pass the packet
  * to ip6tables, which doesn't support NAT, so things are fairly simple. */
-static unsigned int br_nf_pre_routing_ipv6(unsigned int hook,
+static unsigned int br_nf_pre_routing_ipv6(const struct nf_hook_ops *ops,
 					   struct sk_buff *skb,
 					   const struct net_device *in,
 					   const struct net_device *out,
@@ -669,7 +669,8 @@ static unsigned int br_nf_pre_routing_ipv6(unsigned int hook,
  * receiving device) to make netfilter happy, the REDIRECT
  * target in particular.  Save the original destination IP
  * address to be able to detect DNAT afterwards. */
-static unsigned int br_nf_pre_routing(unsigned int hook, struct sk_buff *skb,
+static unsigned int br_nf_pre_routing(const struct nf_hook_ops *ops,
+				      struct sk_buff *skb,
 				      const struct net_device *in,
 				      const struct net_device *out,
 				      int (*okfn)(struct sk_buff *))
@@ -691,7 +692,7 @@ static unsigned int br_nf_pre_routing(unsigned int hook, struct sk_buff *skb,
 			return NF_ACCEPT;
 
 		nf_bridge_pull_encap_header_rcsum(skb);
-		return br_nf_pre_routing_ipv6(hook, skb, in, out, okfn);
+		return br_nf_pre_routing_ipv6(ops, skb, in, out, okfn);
 	}
 
 	if (!brnf_call_iptables && !br->nf_call_iptables)
@@ -727,7 +728,8 @@ static unsigned int br_nf_pre_routing(unsigned int hook, struct sk_buff *skb,
  * took place when the packet entered the bridge), but we
  * register an IPv4 PRE_ROUTING 'sabotage' hook that will
  * prevent this from happening. */
-static unsigned int br_nf_local_in(unsigned int hook, struct sk_buff *skb,
+static unsigned int br_nf_local_in(const struct nf_hook_ops *ops,
+				   struct sk_buff *skb,
 				   const struct net_device *in,
 				   const struct net_device *out,
 				   int (*okfn)(struct sk_buff *))
@@ -765,7 +767,8 @@ static int br_nf_forward_finish(struct sk_buff *skb)
  * but we are still able to filter on the 'real' indev/outdev
  * because of the physdev module. For ARP, indev and outdev are the
  * bridge ports. */
-static unsigned int br_nf_forward_ip(unsigned int hook, struct sk_buff *skb,
+static unsigned int br_nf_forward_ip(const struct nf_hook_ops *ops,
+				     struct sk_buff *skb,
 				     const struct net_device *in,
 				     const struct net_device *out,
 				     int (*okfn)(struct sk_buff *))
@@ -818,7 +821,8 @@ static unsigned int br_nf_forward_ip(unsigned int hook, struct sk_buff *skb,
 	return NF_STOLEN;
 }
 
-static unsigned int br_nf_forward_arp(unsigned int hook, struct sk_buff *skb,
+static unsigned int br_nf_forward_arp(const struct nf_hook_ops *ops,
+				      struct sk_buff *skb,
 				      const struct net_device *in,
 				      const struct net_device *out,
 				      int (*okfn)(struct sk_buff *))
@@ -878,7 +882,8 @@ static int br_nf_dev_queue_xmit(struct sk_buff *skb)
 #endif
 
 /* PF_BRIDGE/POST_ROUTING ********************************************/
-static unsigned int br_nf_post_routing(unsigned int hook, struct sk_buff *skb,
+static unsigned int br_nf_post_routing(const struct nf_hook_ops *ops,
+				       struct sk_buff *skb,
 				       const struct net_device *in,
 				       const struct net_device *out,
 				       int (*okfn)(struct sk_buff *))
@@ -923,7 +928,8 @@ static unsigned int br_nf_post_routing(unsigned int hook, struct sk_buff *skb,
 /* IP/SABOTAGE *****************************************************/
 /* Don't hand locally destined packets to PF_INET(6)/PRE_ROUTING
  * for the second time. */
-static unsigned int ip_sabotage_in(unsigned int hook, struct sk_buff *skb,
+static unsigned int ip_sabotage_in(const struct nf_hook_ops *ops,
+				   struct sk_buff *skb,
 				   const struct net_device *in,
 				   const struct net_device *out,
 				   int (*okfn)(struct sk_buff *))
diff --git a/net/bridge/netfilter/ebtable_filter.c b/net/bridge/netfilter/ebtable_filter.c
index 94b2b700cff8..bb2da7b706e7 100644
--- a/net/bridge/netfilter/ebtable_filter.c
+++ b/net/bridge/netfilter/ebtable_filter.c
@@ -60,17 +60,21 @@ static const struct ebt_table frame_filter =
 };
 
 static unsigned int
-ebt_in_hook(unsigned int hook, struct sk_buff *skb, const struct net_device *in,
-   const struct net_device *out, int (*okfn)(struct sk_buff *))
+ebt_in_hook(const struct nf_hook_ops *ops, struct sk_buff *skb,
+	    const struct net_device *in, const struct net_device *out,
+	    int (*okfn)(struct sk_buff *))
 {
-	return ebt_do_table(hook, skb, in, out, dev_net(in)->xt.frame_filter);
+	return ebt_do_table(ops->hooknum, skb, in, out,
+			    dev_net(in)->xt.frame_filter);
 }
 
 static unsigned int
-ebt_out_hook(unsigned int hook, struct sk_buff *skb, const struct net_device *in,
-   const struct net_device *out, int (*okfn)(struct sk_buff *))
+ebt_out_hook(const struct nf_hook_ops *ops, struct sk_buff *skb,
+	     const struct net_device *in, const struct net_device *out,
+	     int (*okfn)(struct sk_buff *))
 {
-	return ebt_do_table(hook, skb, in, out, dev_net(out)->xt.frame_filter);
+	return ebt_do_table(ops->hooknum, skb, in, out,
+			    dev_net(out)->xt.frame_filter);
 }
 
 static struct nf_hook_ops ebt_ops_filter[] __read_mostly = {
diff --git a/net/bridge/netfilter/ebtable_nat.c b/net/bridge/netfilter/ebtable_nat.c
index 322555acdd40..bd238f1f105b 100644
--- a/net/bridge/netfilter/ebtable_nat.c
+++ b/net/bridge/netfilter/ebtable_nat.c
@@ -60,17 +60,21 @@ static struct ebt_table frame_nat =
 };
 
 static unsigned int
-ebt_nat_in(unsigned int hook, struct sk_buff *skb, const struct net_device *in
-   , const struct net_device *out, int (*okfn)(struct sk_buff *))
+ebt_nat_in(const struct nf_hook_ops *ops, struct sk_buff *skb,
+	   const struct net_device *in, const struct net_device *out,
+	   int (*okfn)(struct sk_buff *))
 {
-	return ebt_do_table(hook, skb, in, out, dev_net(in)->xt.frame_nat);
+	return ebt_do_table(ops->hooknum, skb, in, out,
+			    dev_net(in)->xt.frame_nat);
 }
 
 static unsigned int
-ebt_nat_out(unsigned int hook, struct sk_buff *skb, const struct net_device *in
-   , const struct net_device *out, int (*okfn)(struct sk_buff *))
+ebt_nat_out(const struct nf_hook_ops *ops, struct sk_buff *skb,
+	    const struct net_device *in, const struct net_device *out,
+	    int (*okfn)(struct sk_buff *))
 {
-	return ebt_do_table(hook, skb, in, out, dev_net(out)->xt.frame_nat);
+	return ebt_do_table(ops->hooknum, skb, in, out,
+			    dev_net(out)->xt.frame_nat);
 }
 
 static struct nf_hook_ops ebt_ops_nat[] __read_mostly = {
diff --git a/net/decnet/netfilter/dn_rtmsg.c b/net/decnet/netfilter/dn_rtmsg.c
index 2a7efe388344..e83015cecfa7 100644
--- a/net/decnet/netfilter/dn_rtmsg.c
+++ b/net/decnet/netfilter/dn_rtmsg.c
@@ -87,7 +87,7 @@ static void dnrmg_send_peer(struct sk_buff *skb)
 }
 
 
-static unsigned int dnrmg_hook(unsigned int hook,
+static unsigned int dnrmg_hook(const struct nf_hook_ops *ops,
 			struct sk_buff *skb,
 			const struct net_device *in,
 			const struct net_device *out,
diff --git a/net/ipv4/netfilter/arptable_filter.c b/net/ipv4/netfilter/arptable_filter.c
index a865f6f94013..802ddecb30b8 100644
--- a/net/ipv4/netfilter/arptable_filter.c
+++ b/net/ipv4/netfilter/arptable_filter.c
@@ -27,13 +27,14 @@ static const struct xt_table packet_filter = {
 
 /* The work comes in here from netfilter.c */
 static unsigned int
-arptable_filter_hook(unsigned int hook, struct sk_buff *skb,
+arptable_filter_hook(const struct nf_hook_ops *ops, struct sk_buff *skb,
 		     const struct net_device *in, const struct net_device *out,
 		     int (*okfn)(struct sk_buff *))
 {
 	const struct net *net = dev_net((in != NULL) ? in : out);
 
-	return arpt_do_table(skb, hook, in, out, net->ipv4.arptable_filter);
+	return arpt_do_table(skb, ops->hooknum, in, out,
+			     net->ipv4.arptable_filter);
 }
 
 static struct nf_hook_ops *arpfilter_ops __read_mostly;
diff --git a/net/ipv4/netfilter/ipt_CLUSTERIP.c b/net/ipv4/netfilter/ipt_CLUSTERIP.c
index 0b732efd32e2..a2e2b61cd7da 100644
--- a/net/ipv4/netfilter/ipt_CLUSTERIP.c
+++ b/net/ipv4/netfilter/ipt_CLUSTERIP.c
@@ -483,7 +483,7 @@ static void arp_print(struct arp_payload *payload)
 #endif
 
 static unsigned int
-arp_mangle(unsigned int hook,
+arp_mangle(const struct nf_hook_ops *ops,
 	   struct sk_buff *skb,
 	   const struct net_device *in,
 	   const struct net_device *out,
diff --git a/net/ipv4/netfilter/ipt_SYNPROXY.c b/net/ipv4/netfilter/ipt_SYNPROXY.c
index b6346bf2fde3..01cffeaa0085 100644
--- a/net/ipv4/netfilter/ipt_SYNPROXY.c
+++ b/net/ipv4/netfilter/ipt_SYNPROXY.c
@@ -297,7 +297,7 @@ synproxy_tg4(struct sk_buff *skb, const struct xt_action_param *par)
 	return XT_CONTINUE;
 }
 
-static unsigned int ipv4_synproxy_hook(unsigned int hooknum,
+static unsigned int ipv4_synproxy_hook(const struct nf_hook_ops *ops,
 				       struct sk_buff *skb,
 				       const struct net_device *in,
 				       const struct net_device *out,
diff --git a/net/ipv4/netfilter/iptable_filter.c b/net/ipv4/netfilter/iptable_filter.c
index 50af5b45c050..e08a74a243a8 100644
--- a/net/ipv4/netfilter/iptable_filter.c
+++ b/net/ipv4/netfilter/iptable_filter.c
@@ -33,20 +33,21 @@ static const struct xt_table packet_filter = {
 };
 
 static unsigned int
-iptable_filter_hook(unsigned int hook, struct sk_buff *skb,
+iptable_filter_hook(const struct nf_hook_ops *ops, struct sk_buff *skb,
 		    const struct net_device *in, const struct net_device *out,
 		    int (*okfn)(struct sk_buff *))
 {
 	const struct net *net;
 
-	if (hook == NF_INET_LOCAL_OUT &&
+	if (ops->hooknum == NF_INET_LOCAL_OUT &&
 	    (skb->len < sizeof(struct iphdr) ||
 	     ip_hdrlen(skb) < sizeof(struct iphdr)))
 		/* root is playing with raw sockets. */
 		return NF_ACCEPT;
 
 	net = dev_net((in != NULL) ? in : out);
-	return ipt_do_table(skb, hook, in, out, net->ipv4.iptable_filter);
+	return ipt_do_table(skb, ops->hooknum, in, out,
+			    net->ipv4.iptable_filter);
 }
 
 static struct nf_hook_ops *filter_ops __read_mostly;
diff --git a/net/ipv4/netfilter/iptable_mangle.c b/net/ipv4/netfilter/iptable_mangle.c
index 0d8cd82e0fad..6a5079c34bb3 100644
--- a/net/ipv4/netfilter/iptable_mangle.c
+++ b/net/ipv4/netfilter/iptable_mangle.c
@@ -79,19 +79,19 @@ ipt_mangle_out(struct sk_buff *skb, const struct net_device *out)
 
 /* The work comes in here from netfilter.c. */
 static unsigned int
-iptable_mangle_hook(unsigned int hook,
+iptable_mangle_hook(const struct nf_hook_ops *ops,
 		     struct sk_buff *skb,
 		     const struct net_device *in,
 		     const struct net_device *out,
 		     int (*okfn)(struct sk_buff *))
 {
-	if (hook == NF_INET_LOCAL_OUT)
+	if (ops->hooknum == NF_INET_LOCAL_OUT)
 		return ipt_mangle_out(skb, out);
-	if (hook == NF_INET_POST_ROUTING)
-		return ipt_do_table(skb, hook, in, out,
+	if (ops->hooknum == NF_INET_POST_ROUTING)
+		return ipt_do_table(skb, ops->hooknum, in, out,
 				    dev_net(out)->ipv4.iptable_mangle);
 	/* PREROUTING/INPUT/FORWARD: */
-	return ipt_do_table(skb, hook, in, out,
+	return ipt_do_table(skb, ops->hooknum, in, out,
 			    dev_net(in)->ipv4.iptable_mangle);
 }
 
diff --git a/net/ipv4/netfilter/iptable_nat.c b/net/ipv4/netfilter/iptable_nat.c
index 683bfaffed65..ee2886126e3d 100644
--- a/net/ipv4/netfilter/iptable_nat.c
+++ b/net/ipv4/netfilter/iptable_nat.c
@@ -61,7 +61,7 @@ static unsigned int nf_nat_rule_find(struct sk_buff *skb, unsigned int hooknum,
 }
 
 static unsigned int
-nf_nat_ipv4_fn(unsigned int hooknum,
+nf_nat_ipv4_fn(const struct nf_hook_ops *ops,
 	       struct sk_buff *skb,
 	       const struct net_device *in,
 	       const struct net_device *out,
@@ -71,7 +71,7 @@ nf_nat_ipv4_fn(unsigned int hooknum,
 	enum ip_conntrack_info ctinfo;
 	struct nf_conn_nat *nat;
 	/* maniptype == SRC for postrouting. */
-	enum nf_nat_manip_type maniptype = HOOK2MANIP(hooknum);
+	enum nf_nat_manip_type maniptype = HOOK2MANIP(ops->hooknum);
 
 	/* We never see fragments: conntrack defrags on pre-routing
 	 * and local-out, and nf_nat_out protects post-routing.
@@ -108,7 +108,7 @@ nf_nat_ipv4_fn(unsigned int hooknum,
 	case IP_CT_RELATED_REPLY:
 		if (ip_hdr(skb)->protocol == IPPROTO_ICMP) {
 			if (!nf_nat_icmp_reply_translation(skb, ct, ctinfo,
-							   hooknum))
+							   ops->hooknum))
 				return NF_DROP;
 			else
 				return NF_ACCEPT;
@@ -121,14 +121,14 @@ nf_nat_ipv4_fn(unsigned int hooknum,
 		if (!nf_nat_initialized(ct, maniptype)) {
 			unsigned int ret;
 
-			ret = nf_nat_rule_find(skb, hooknum, in, out, ct);
+			ret = nf_nat_rule_find(skb, ops->hooknum, in, out, ct);
 			if (ret != NF_ACCEPT)
 				return ret;
 		} else {
 			pr_debug("Already setup manip %s for ct %p\n",
 				 maniptype == NF_NAT_MANIP_SRC ? "SRC" : "DST",
 				 ct);
-			if (nf_nat_oif_changed(hooknum, ctinfo, nat, out))
+			if (nf_nat_oif_changed(ops->hooknum, ctinfo, nat, out))
 				goto oif_changed;
 		}
 		break;
@@ -137,11 +137,11 @@ nf_nat_ipv4_fn(unsigned int hooknum,
 		/* ESTABLISHED */
 		NF_CT_ASSERT(ctinfo == IP_CT_ESTABLISHED ||
 			     ctinfo == IP_CT_ESTABLISHED_REPLY);
-		if (nf_nat_oif_changed(hooknum, ctinfo, nat, out))
+		if (nf_nat_oif_changed(ops->hooknum, ctinfo, nat, out))
 			goto oif_changed;
 	}
 
-	return nf_nat_packet(ct, ctinfo, hooknum, skb);
+	return nf_nat_packet(ct, ctinfo, ops->hooknum, skb);
 
 oif_changed:
 	nf_ct_kill_acct(ct, ctinfo, skb);
@@ -149,7 +149,7 @@ oif_changed:
 }
 
 static unsigned int
-nf_nat_ipv4_in(unsigned int hooknum,
+nf_nat_ipv4_in(const struct nf_hook_ops *ops,
 	       struct sk_buff *skb,
 	       const struct net_device *in,
 	       const struct net_device *out,
@@ -158,7 +158,7 @@ nf_nat_ipv4_in(unsigned int hooknum,
 	unsigned int ret;
 	__be32 daddr = ip_hdr(skb)->daddr;
 
-	ret = nf_nat_ipv4_fn(hooknum, skb, in, out, okfn);
+	ret = nf_nat_ipv4_fn(ops, skb, in, out, okfn);
 	if (ret != NF_DROP && ret != NF_STOLEN &&
 	    daddr != ip_hdr(skb)->daddr)
 		skb_dst_drop(skb);
@@ -167,7 +167,7 @@ nf_nat_ipv4_in(unsigned int hooknum,
 }
 
 static unsigned int
-nf_nat_ipv4_out(unsigned int hooknum,
+nf_nat_ipv4_out(const struct nf_hook_ops *ops,
 		struct sk_buff *skb,
 		const struct net_device *in,
 		const struct net_device *out,
@@ -185,7 +185,7 @@ nf_nat_ipv4_out(unsigned int hooknum,
 	    ip_hdrlen(skb) < sizeof(struct iphdr))
 		return NF_ACCEPT;
 
-	ret = nf_nat_ipv4_fn(hooknum, skb, in, out, okfn);
+	ret = nf_nat_ipv4_fn(ops, skb, in, out, okfn);
 #ifdef CONFIG_XFRM
 	if (ret != NF_DROP && ret != NF_STOLEN &&
 	    !(IPCB(skb)->flags & IPSKB_XFRM_TRANSFORMED) &&
@@ -207,7 +207,7 @@ nf_nat_ipv4_out(unsigned int hooknum,
 }
 
 static unsigned int
-nf_nat_ipv4_local_fn(unsigned int hooknum,
+nf_nat_ipv4_local_fn(const struct nf_hook_ops *ops,
 		     struct sk_buff *skb,
 		     const struct net_device *in,
 		     const struct net_device *out,
@@ -223,7 +223,7 @@ nf_nat_ipv4_local_fn(unsigned int hooknum,
 	    ip_hdrlen(skb) < sizeof(struct iphdr))
 		return NF_ACCEPT;
 
-	ret = nf_nat_ipv4_fn(hooknum, skb, in, out, okfn);
+	ret = nf_nat_ipv4_fn(ops, skb, in, out, okfn);
 	if (ret != NF_DROP && ret != NF_STOLEN &&
 	    (ct = nf_ct_get(skb, &ctinfo)) != NULL) {
 		enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo);
diff --git a/net/ipv4/netfilter/iptable_raw.c b/net/ipv4/netfilter/iptable_raw.c
index 1f82aea11df6..b2f7e8f98316 100644
--- a/net/ipv4/netfilter/iptable_raw.c
+++ b/net/ipv4/netfilter/iptable_raw.c
@@ -20,20 +20,20 @@ static const struct xt_table packet_raw = {
 
 /* The work comes in here from netfilter.c. */
 static unsigned int
-iptable_raw_hook(unsigned int hook, struct sk_buff *skb,
+iptable_raw_hook(const struct nf_hook_ops *ops, struct sk_buff *skb,
 		 const struct net_device *in, const struct net_device *out,
 		 int (*okfn)(struct sk_buff *))
 {
 	const struct net *net;
 
-	if (hook == NF_INET_LOCAL_OUT && 
+	if (ops->hooknum == NF_INET_LOCAL_OUT &&
 	    (skb->len < sizeof(struct iphdr) ||
 	     ip_hdrlen(skb) < sizeof(struct iphdr)))
 		/* root is playing with raw sockets. */
 		return NF_ACCEPT;
 
 	net = dev_net((in != NULL) ? in : out);
-	return ipt_do_table(skb, hook, in, out, net->ipv4.iptable_raw);
+	return ipt_do_table(skb, ops->hooknum, in, out, net->ipv4.iptable_raw);
 }
 
 static struct nf_hook_ops *rawtable_ops __read_mostly;
diff --git a/net/ipv4/netfilter/iptable_security.c b/net/ipv4/netfilter/iptable_security.c
index f867a8d38bf7..c86647ed2078 100644
--- a/net/ipv4/netfilter/iptable_security.c
+++ b/net/ipv4/netfilter/iptable_security.c
@@ -37,21 +37,22 @@ static const struct xt_table security_table = {
 };
 
 static unsigned int
-iptable_security_hook(unsigned int hook, struct sk_buff *skb,
+iptable_security_hook(const struct nf_hook_ops *ops, struct sk_buff *skb,
 		      const struct net_device *in,
 		      const struct net_device *out,
 		      int (*okfn)(struct sk_buff *))
 {
 	const struct net *net;
 
-	if (hook == NF_INET_LOCAL_OUT &&
+	if (ops->hooknum == NF_INET_LOCAL_OUT &&
 	    (skb->len < sizeof(struct iphdr) ||
 	     ip_hdrlen(skb) < sizeof(struct iphdr)))
 		/* Somebody is playing with raw sockets. */
 		return NF_ACCEPT;
 
 	net = dev_net((in != NULL) ? in : out);
-	return ipt_do_table(skb, hook, in, out, net->ipv4.iptable_security);
+	return ipt_do_table(skb, ops->hooknum, in, out,
+			    net->ipv4.iptable_security);
 }
 
 static struct nf_hook_ops *sectbl_ops __read_mostly;
diff --git a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c
index 86f5b34a4ed1..ecd8bec411c9 100644
--- a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c
+++ b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c
@@ -92,7 +92,7 @@ static int ipv4_get_l4proto(const struct sk_buff *skb, unsigned int nhoff,
 	return NF_ACCEPT;
 }
 
-static unsigned int ipv4_helper(unsigned int hooknum,
+static unsigned int ipv4_helper(const struct nf_hook_ops *ops,
 				struct sk_buff *skb,
 				const struct net_device *in,
 				const struct net_device *out,
@@ -121,7 +121,7 @@ static unsigned int ipv4_helper(unsigned int hooknum,
 			    ct, ctinfo);
 }
 
-static unsigned int ipv4_confirm(unsigned int hooknum,
+static unsigned int ipv4_confirm(const struct nf_hook_ops *ops,
 				 struct sk_buff *skb,
 				 const struct net_device *in,
 				 const struct net_device *out,
@@ -147,16 +147,16 @@ out:
 	return nf_conntrack_confirm(skb);
 }
 
-static unsigned int ipv4_conntrack_in(unsigned int hooknum,
+static unsigned int ipv4_conntrack_in(const struct nf_hook_ops *ops,
 				      struct sk_buff *skb,
 				      const struct net_device *in,
 				      const struct net_device *out,
 				      int (*okfn)(struct sk_buff *))
 {
-	return nf_conntrack_in(dev_net(in), PF_INET, hooknum, skb);
+	return nf_conntrack_in(dev_net(in), PF_INET, ops->hooknum, skb);
 }
 
-static unsigned int ipv4_conntrack_local(unsigned int hooknum,
+static unsigned int ipv4_conntrack_local(const struct nf_hook_ops *ops,
 					 struct sk_buff *skb,
 					 const struct net_device *in,
 					 const struct net_device *out,
@@ -166,7 +166,7 @@ static unsigned int ipv4_conntrack_local(unsigned int hooknum,
 	if (skb->len < sizeof(struct iphdr) ||
 	    ip_hdrlen(skb) < sizeof(struct iphdr))
 		return NF_ACCEPT;
-	return nf_conntrack_in(dev_net(out), PF_INET, hooknum, skb);
+	return nf_conntrack_in(dev_net(out), PF_INET, ops->hooknum, skb);
 }
 
 /* Connection tracking may drop packets, but never alters them, so
diff --git a/net/ipv4/netfilter/nf_defrag_ipv4.c b/net/ipv4/netfilter/nf_defrag_ipv4.c
index 742815518b0f..12e13bd82b5b 100644
--- a/net/ipv4/netfilter/nf_defrag_ipv4.c
+++ b/net/ipv4/netfilter/nf_defrag_ipv4.c
@@ -60,7 +60,7 @@ static enum ip_defrag_users nf_ct_defrag_user(unsigned int hooknum,
 		return IP_DEFRAG_CONNTRACK_OUT + zone;
 }
 
-static unsigned int ipv4_conntrack_defrag(unsigned int hooknum,
+static unsigned int ipv4_conntrack_defrag(const struct nf_hook_ops *ops,
 					  struct sk_buff *skb,
 					  const struct net_device *in,
 					  const struct net_device *out,
@@ -83,7 +83,9 @@ static unsigned int ipv4_conntrack_defrag(unsigned int hooknum,
 #endif
 	/* Gather fragments. */
 	if (ip_is_fragment(ip_hdr(skb))) {
-		enum ip_defrag_users user = nf_ct_defrag_user(hooknum, skb);
+		enum ip_defrag_users user =
+			nf_ct_defrag_user(ops->hooknum, skb);
+
 		if (nf_ct_ipv4_gather_frags(skb, user))
 			return NF_STOLEN;
 	}
diff --git a/net/ipv6/netfilter/ip6t_SYNPROXY.c b/net/ipv6/netfilter/ip6t_SYNPROXY.c
index 2748b042da72..bf9f612c1bc2 100644
--- a/net/ipv6/netfilter/ip6t_SYNPROXY.c
+++ b/net/ipv6/netfilter/ip6t_SYNPROXY.c
@@ -312,7 +312,7 @@ synproxy_tg6(struct sk_buff *skb, const struct xt_action_param *par)
 	return XT_CONTINUE;
 }
 
-static unsigned int ipv6_synproxy_hook(unsigned int hooknum,
+static unsigned int ipv6_synproxy_hook(const struct nf_hook_ops *ops,
 				       struct sk_buff *skb,
 				       const struct net_device *in,
 				       const struct net_device *out,
diff --git a/net/ipv6/netfilter/ip6table_filter.c b/net/ipv6/netfilter/ip6table_filter.c
index 29b44b14c5ea..ca7f6c128086 100644
--- a/net/ipv6/netfilter/ip6table_filter.c
+++ b/net/ipv6/netfilter/ip6table_filter.c
@@ -32,13 +32,14 @@ static const struct xt_table packet_filter = {
 
 /* The work comes in here from netfilter.c. */
 static unsigned int
-ip6table_filter_hook(unsigned int hook, struct sk_buff *skb,
+ip6table_filter_hook(const struct nf_hook_ops *ops, struct sk_buff *skb,
 		     const struct net_device *in, const struct net_device *out,
 		     int (*okfn)(struct sk_buff *))
 {
 	const struct net *net = dev_net((in != NULL) ? in : out);
 
-	return ip6t_do_table(skb, hook, in, out, net->ipv6.ip6table_filter);
+	return ip6t_do_table(skb, ops->hooknum, in, out,
+			     net->ipv6.ip6table_filter);
 }
 
 static struct nf_hook_ops *filter_ops __read_mostly;
diff --git a/net/ipv6/netfilter/ip6table_mangle.c b/net/ipv6/netfilter/ip6table_mangle.c
index c705907ae6ab..307bbb782d14 100644
--- a/net/ipv6/netfilter/ip6table_mangle.c
+++ b/net/ipv6/netfilter/ip6table_mangle.c
@@ -76,17 +76,17 @@ ip6t_mangle_out(struct sk_buff *skb, const struct net_device *out)
 
 /* The work comes in here from netfilter.c. */
 static unsigned int
-ip6table_mangle_hook(unsigned int hook, struct sk_buff *skb,
+ip6table_mangle_hook(const struct nf_hook_ops *ops, struct sk_buff *skb,
 		     const struct net_device *in, const struct net_device *out,
 		     int (*okfn)(struct sk_buff *))
 {
-	if (hook == NF_INET_LOCAL_OUT)
+	if (ops->hooknum == NF_INET_LOCAL_OUT)
 		return ip6t_mangle_out(skb, out);
-	if (hook == NF_INET_POST_ROUTING)
-		return ip6t_do_table(skb, hook, in, out,
+	if (ops->hooknum == NF_INET_POST_ROUTING)
+		return ip6t_do_table(skb, ops->hooknum, in, out,
 				     dev_net(out)->ipv6.ip6table_mangle);
 	/* INPUT/FORWARD */
-	return ip6t_do_table(skb, hook, in, out,
+	return ip6t_do_table(skb, ops->hooknum, in, out,
 			     dev_net(in)->ipv6.ip6table_mangle);
 }
 
diff --git a/net/ipv6/netfilter/ip6table_nat.c b/net/ipv6/netfilter/ip6table_nat.c
index 9b076d2d3a7b..84c7f33d0cf8 100644
--- a/net/ipv6/netfilter/ip6table_nat.c
+++ b/net/ipv6/netfilter/ip6table_nat.c
@@ -63,7 +63,7 @@ static unsigned int nf_nat_rule_find(struct sk_buff *skb, unsigned int hooknum,
 }
 
 static unsigned int
-nf_nat_ipv6_fn(unsigned int hooknum,
+nf_nat_ipv6_fn(const struct nf_hook_ops *ops,
 	       struct sk_buff *skb,
 	       const struct net_device *in,
 	       const struct net_device *out,
@@ -72,7 +72,7 @@ nf_nat_ipv6_fn(unsigned int hooknum,
 	struct nf_conn *ct;
 	enum ip_conntrack_info ctinfo;
 	struct nf_conn_nat *nat;
-	enum nf_nat_manip_type maniptype = HOOK2MANIP(hooknum);
+	enum nf_nat_manip_type maniptype = HOOK2MANIP(ops->hooknum);
 	__be16 frag_off;
 	int hdrlen;
 	u8 nexthdr;
@@ -111,7 +111,8 @@ nf_nat_ipv6_fn(unsigned int hooknum,
 
 		if (hdrlen >= 0 && nexthdr == IPPROTO_ICMPV6) {
 			if (!nf_nat_icmpv6_reply_translation(skb, ct, ctinfo,
-							     hooknum, hdrlen))
+							     ops->hooknum,
+							     hdrlen))
 				return NF_DROP;
 			else
 				return NF_ACCEPT;
@@ -124,14 +125,14 @@ nf_nat_ipv6_fn(unsigned int hooknum,
 		if (!nf_nat_initialized(ct, maniptype)) {
 			unsigned int ret;
 
-			ret = nf_nat_rule_find(skb, hooknum, in, out, ct);
+			ret = nf_nat_rule_find(skb, ops->hooknum, in, out, ct);
 			if (ret != NF_ACCEPT)
 				return ret;
 		} else {
 			pr_debug("Already setup manip %s for ct %p\n",
 				 maniptype == NF_NAT_MANIP_SRC ? "SRC" : "DST",
 				 ct);
-			if (nf_nat_oif_changed(hooknum, ctinfo, nat, out))
+			if (nf_nat_oif_changed(ops->hooknum, ctinfo, nat, out))
 				goto oif_changed;
 		}
 		break;
@@ -140,11 +141,11 @@ nf_nat_ipv6_fn(unsigned int hooknum,
 		/* ESTABLISHED */
 		NF_CT_ASSERT(ctinfo == IP_CT_ESTABLISHED ||
 			     ctinfo == IP_CT_ESTABLISHED_REPLY);
-		if (nf_nat_oif_changed(hooknum, ctinfo, nat, out))
+		if (nf_nat_oif_changed(ops->hooknum, ctinfo, nat, out))
 			goto oif_changed;
 	}
 
-	return nf_nat_packet(ct, ctinfo, hooknum, skb);
+	return nf_nat_packet(ct, ctinfo, ops->hooknum, skb);
 
 oif_changed:
 	nf_ct_kill_acct(ct, ctinfo, skb);
@@ -152,7 +153,7 @@ oif_changed:
 }
 
 static unsigned int
-nf_nat_ipv6_in(unsigned int hooknum,
+nf_nat_ipv6_in(const struct nf_hook_ops *ops,
 	       struct sk_buff *skb,
 	       const struct net_device *in,
 	       const struct net_device *out,
@@ -161,7 +162,7 @@ nf_nat_ipv6_in(unsigned int hooknum,
 	unsigned int ret;
 	struct in6_addr daddr = ipv6_hdr(skb)->daddr;
 
-	ret = nf_nat_ipv6_fn(hooknum, skb, in, out, okfn);
+	ret = nf_nat_ipv6_fn(ops, skb, in, out, okfn);
 	if (ret != NF_DROP && ret != NF_STOLEN &&
 	    ipv6_addr_cmp(&daddr, &ipv6_hdr(skb)->daddr))
 		skb_dst_drop(skb);
@@ -170,7 +171,7 @@ nf_nat_ipv6_in(unsigned int hooknum,
 }
 
 static unsigned int
-nf_nat_ipv6_out(unsigned int hooknum,
+nf_nat_ipv6_out(const struct nf_hook_ops *ops,
 		struct sk_buff *skb,
 		const struct net_device *in,
 		const struct net_device *out,
@@ -187,7 +188,7 @@ nf_nat_ipv6_out(unsigned int hooknum,
 	if (skb->len < sizeof(struct ipv6hdr))
 		return NF_ACCEPT;
 
-	ret = nf_nat_ipv6_fn(hooknum, skb, in, out, okfn);
+	ret = nf_nat_ipv6_fn(ops, skb, in, out, okfn);
 #ifdef CONFIG_XFRM
 	if (ret != NF_DROP && ret != NF_STOLEN &&
 	    !(IP6CB(skb)->flags & IP6SKB_XFRM_TRANSFORMED) &&
@@ -209,7 +210,7 @@ nf_nat_ipv6_out(unsigned int hooknum,
 }
 
 static unsigned int
-nf_nat_ipv6_local_fn(unsigned int hooknum,
+nf_nat_ipv6_local_fn(const struct nf_hook_ops *ops,
 		     struct sk_buff *skb,
 		     const struct net_device *in,
 		     const struct net_device *out,
@@ -224,7 +225,7 @@ nf_nat_ipv6_local_fn(unsigned int hooknum,
 	if (skb->len < sizeof(struct ipv6hdr))
 		return NF_ACCEPT;
 
-	ret = nf_nat_ipv6_fn(hooknum, skb, in, out, okfn);
+	ret = nf_nat_ipv6_fn(ops, skb, in, out, okfn);
 	if (ret != NF_DROP && ret != NF_STOLEN &&
 	    (ct = nf_ct_get(skb, &ctinfo)) != NULL) {
 		enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo);
diff --git a/net/ipv6/netfilter/ip6table_raw.c b/net/ipv6/netfilter/ip6table_raw.c
index 9a626d86720f..5274740acecc 100644
--- a/net/ipv6/netfilter/ip6table_raw.c
+++ b/net/ipv6/netfilter/ip6table_raw.c
@@ -19,13 +19,14 @@ static const struct xt_table packet_raw = {
 
 /* The work comes in here from netfilter.c. */
 static unsigned int
-ip6table_raw_hook(unsigned int hook, struct sk_buff *skb,
+ip6table_raw_hook(const struct nf_hook_ops *ops, struct sk_buff *skb,
 		  const struct net_device *in, const struct net_device *out,
 		  int (*okfn)(struct sk_buff *))
 {
 	const struct net *net = dev_net((in != NULL) ? in : out);
 
-	return ip6t_do_table(skb, hook, in, out, net->ipv6.ip6table_raw);
+	return ip6t_do_table(skb, ops->hooknum, in, out,
+			     net->ipv6.ip6table_raw);
 }
 
 static struct nf_hook_ops *rawtable_ops __read_mostly;
diff --git a/net/ipv6/netfilter/ip6table_security.c b/net/ipv6/netfilter/ip6table_security.c
index ce88d1d7e525..ab3b0219ecfa 100644
--- a/net/ipv6/netfilter/ip6table_security.c
+++ b/net/ipv6/netfilter/ip6table_security.c
@@ -36,14 +36,15 @@ static const struct xt_table security_table = {
 };
 
 static unsigned int
-ip6table_security_hook(unsigned int hook, struct sk_buff *skb,
+ip6table_security_hook(const struct nf_hook_ops *ops, struct sk_buff *skb,
 		       const struct net_device *in,
 		       const struct net_device *out,
 		       int (*okfn)(struct sk_buff *))
 {
 	const struct net *net = dev_net((in != NULL) ? in : out);
 
-	return ip6t_do_table(skb, hook, in, out, net->ipv6.ip6table_security);
+	return ip6t_do_table(skb, ops->hooknum, in, out,
+			     net->ipv6.ip6table_security);
 }
 
 static struct nf_hook_ops *sectbl_ops __read_mostly;
diff --git a/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c b/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c
index 54b75ead5a69..486545eb42ce 100644
--- a/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c
+++ b/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c
@@ -95,7 +95,7 @@ static int ipv6_get_l4proto(const struct sk_buff *skb, unsigned int nhoff,
 	return NF_ACCEPT;
 }
 
-static unsigned int ipv6_helper(unsigned int hooknum,
+static unsigned int ipv6_helper(const struct nf_hook_ops *ops,
 				struct sk_buff *skb,
 				const struct net_device *in,
 				const struct net_device *out,
@@ -133,7 +133,7 @@ static unsigned int ipv6_helper(unsigned int hooknum,
 	return helper->help(skb, protoff, ct, ctinfo);
 }
 
-static unsigned int ipv6_confirm(unsigned int hooknum,
+static unsigned int ipv6_confirm(const struct nf_hook_ops *ops,
 				 struct sk_buff *skb,
 				 const struct net_device *in,
 				 const struct net_device *out,
@@ -219,16 +219,17 @@ static unsigned int __ipv6_conntrack_in(struct net *net,
 	return nf_conntrack_in(net, PF_INET6, hooknum, skb);
 }
 
-static unsigned int ipv6_conntrack_in(unsigned int hooknum,
+static unsigned int ipv6_conntrack_in(const struct nf_hook_ops *ops,
 				      struct sk_buff *skb,
 				      const struct net_device *in,
 				      const struct net_device *out,
 				      int (*okfn)(struct sk_buff *))
 {
-	return __ipv6_conntrack_in(dev_net(in), hooknum, skb, in, out, okfn);
+	return __ipv6_conntrack_in(dev_net(in), ops->hooknum, skb, in, out,
+				   okfn);
 }
 
-static unsigned int ipv6_conntrack_local(unsigned int hooknum,
+static unsigned int ipv6_conntrack_local(const struct nf_hook_ops *ops,
 					 struct sk_buff *skb,
 					 const struct net_device *in,
 					 const struct net_device *out,
@@ -239,7 +240,8 @@ static unsigned int ipv6_conntrack_local(unsigned int hooknum,
 		net_notice_ratelimited("ipv6_conntrack_local: packet too short\n");
 		return NF_ACCEPT;
 	}
-	return __ipv6_conntrack_in(dev_net(out), hooknum, skb, in, out, okfn);
+	return __ipv6_conntrack_in(dev_net(out), ops->hooknum, skb, in, out,
+				   okfn);
 }
 
 static struct nf_hook_ops ipv6_conntrack_ops[] __read_mostly = {
diff --git a/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c b/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c
index aacd121fe8c5..ec483aa3f60f 100644
--- a/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c
+++ b/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c
@@ -52,7 +52,7 @@ static enum ip6_defrag_users nf_ct6_defrag_user(unsigned int hooknum,
 
 }
 
-static unsigned int ipv6_defrag(unsigned int hooknum,
+static unsigned int ipv6_defrag(const struct nf_hook_ops *ops,
 				struct sk_buff *skb,
 				const struct net_device *in,
 				const struct net_device *out,
@@ -66,7 +66,7 @@ static unsigned int ipv6_defrag(unsigned int hooknum,
 		return NF_ACCEPT;
 #endif
 
-	reasm = nf_ct_frag6_gather(skb, nf_ct6_defrag_user(hooknum, skb));
+	reasm = nf_ct_frag6_gather(skb, nf_ct6_defrag_user(ops->hooknum, skb));
 	/* queued */
 	if (reasm == NULL)
 		return NF_STOLEN;
@@ -75,7 +75,7 @@ static unsigned int ipv6_defrag(unsigned int hooknum,
 	if (reasm == skb)
 		return NF_ACCEPT;
 
-	nf_ct_frag6_output(hooknum, reasm, (struct net_device *)in,
+	nf_ct_frag6_output(ops->hooknum, reasm, (struct net_device *)in,
 			   (struct net_device *)out, okfn);
 
 	return NF_STOLEN;
diff --git a/net/netfilter/core.c b/net/netfilter/core.c
index 593b16ea45e0..1fbab0cdd302 100644
--- a/net/netfilter/core.c
+++ b/net/netfilter/core.c
@@ -146,7 +146,7 @@ unsigned int nf_iterate(struct list_head *head,
 		/* Optimization: we don't need to hold module
 		   reference here, since function can't sleep. --RR */
 repeat:
-		verdict = (*elemp)->hook(hook, skb, indev, outdev, okfn);
+		verdict = (*elemp)->hook(*elemp, skb, indev, outdev, okfn);
 		if (verdict != NF_ACCEPT) {
 #ifdef CONFIG_NETFILTER_DEBUG
 			if (unlikely((verdict & NF_VERDICT_MASK)
diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c
index 74fd00c27210..34fda62f40f6 100644
--- a/net/netfilter/ipvs/ip_vs_core.c
+++ b/net/netfilter/ipvs/ip_vs_core.c
@@ -1239,11 +1239,11 @@ ip_vs_out(unsigned int hooknum, struct sk_buff *skb, int af)
  *	Check if packet is reply for established ip_vs_conn.
  */
 static unsigned int
-ip_vs_reply4(unsigned int hooknum, struct sk_buff *skb,
+ip_vs_reply4(const struct nf_hook_ops *ops, struct sk_buff *skb,
 	     const struct net_device *in, const struct net_device *out,
 	     int (*okfn)(struct sk_buff *))
 {
-	return ip_vs_out(hooknum, skb, AF_INET);
+	return ip_vs_out(ops->hooknum, skb, AF_INET);
 }
 
 /*
@@ -1251,11 +1251,11 @@ ip_vs_reply4(unsigned int hooknum, struct sk_buff *skb,
  *	Check if packet is reply for established ip_vs_conn.
  */
 static unsigned int
-ip_vs_local_reply4(unsigned int hooknum, struct sk_buff *skb,
+ip_vs_local_reply4(const struct nf_hook_ops *ops, struct sk_buff *skb,
 		   const struct net_device *in, const struct net_device *out,
 		   int (*okfn)(struct sk_buff *))
 {
-	return ip_vs_out(hooknum, skb, AF_INET);
+	return ip_vs_out(ops->hooknum, skb, AF_INET);
 }
 
 #ifdef CONFIG_IP_VS_IPV6
@@ -1266,11 +1266,11 @@ ip_vs_local_reply4(unsigned int hooknum, struct sk_buff *skb,
  *	Check if packet is reply for established ip_vs_conn.
  */
 static unsigned int
-ip_vs_reply6(unsigned int hooknum, struct sk_buff *skb,
+ip_vs_reply6(const struct nf_hook_ops *ops, struct sk_buff *skb,
 	     const struct net_device *in, const struct net_device *out,
 	     int (*okfn)(struct sk_buff *))
 {
-	return ip_vs_out(hooknum, skb, AF_INET6);
+	return ip_vs_out(ops->hooknum, skb, AF_INET6);
 }
 
 /*
@@ -1278,11 +1278,11 @@ ip_vs_reply6(unsigned int hooknum, struct sk_buff *skb,
  *	Check if packet is reply for established ip_vs_conn.
  */
 static unsigned int
-ip_vs_local_reply6(unsigned int hooknum, struct sk_buff *skb,
+ip_vs_local_reply6(const struct nf_hook_ops *ops, struct sk_buff *skb,
 		   const struct net_device *in, const struct net_device *out,
 		   int (*okfn)(struct sk_buff *))
 {
-	return ip_vs_out(hooknum, skb, AF_INET6);
+	return ip_vs_out(ops->hooknum, skb, AF_INET6);
 }
 
 #endif
@@ -1733,12 +1733,12 @@ ip_vs_in(unsigned int hooknum, struct sk_buff *skb, int af)
  *	Schedule and forward packets from remote clients
  */
 static unsigned int
-ip_vs_remote_request4(unsigned int hooknum, struct sk_buff *skb,
+ip_vs_remote_request4(const struct nf_hook_ops *ops, struct sk_buff *skb,
 		      const struct net_device *in,
 		      const struct net_device *out,
 		      int (*okfn)(struct sk_buff *))
 {
-	return ip_vs_in(hooknum, skb, AF_INET);
+	return ip_vs_in(ops->hooknum, skb, AF_INET);
 }
 
 /*
@@ -1746,11 +1746,11 @@ ip_vs_remote_request4(unsigned int hooknum, struct sk_buff *skb,
  *	Schedule and forward packets from local clients
  */
 static unsigned int
-ip_vs_local_request4(unsigned int hooknum, struct sk_buff *skb,
+ip_vs_local_request4(const struct nf_hook_ops *ops, struct sk_buff *skb,
 		     const struct net_device *in, const struct net_device *out,
 		     int (*okfn)(struct sk_buff *))
 {
-	return ip_vs_in(hooknum, skb, AF_INET);
+	return ip_vs_in(ops->hooknum, skb, AF_INET);
 }
 
 #ifdef CONFIG_IP_VS_IPV6
@@ -1760,7 +1760,7 @@ ip_vs_local_request4(unsigned int hooknum, struct sk_buff *skb,
  * Copy info from first fragment, to the rest of them.
  */
 static unsigned int
-ip_vs_preroute_frag6(unsigned int hooknum, struct sk_buff *skb,
+ip_vs_preroute_frag6(const struct nf_hook_ops *ops, struct sk_buff *skb,
 		     const struct net_device *in,
 		     const struct net_device *out,
 		     int (*okfn)(struct sk_buff *))
@@ -1792,12 +1792,12 @@ ip_vs_preroute_frag6(unsigned int hooknum, struct sk_buff *skb,
  *	Schedule and forward packets from remote clients
  */
 static unsigned int
-ip_vs_remote_request6(unsigned int hooknum, struct sk_buff *skb,
+ip_vs_remote_request6(const struct nf_hook_ops *ops, struct sk_buff *skb,
 		      const struct net_device *in,
 		      const struct net_device *out,
 		      int (*okfn)(struct sk_buff *))
 {
-	return ip_vs_in(hooknum, skb, AF_INET6);
+	return ip_vs_in(ops->hooknum, skb, AF_INET6);
 }
 
 /*
@@ -1805,11 +1805,11 @@ ip_vs_remote_request6(unsigned int hooknum, struct sk_buff *skb,
  *	Schedule and forward packets from local clients
  */
 static unsigned int
-ip_vs_local_request6(unsigned int hooknum, struct sk_buff *skb,
+ip_vs_local_request6(const struct nf_hook_ops *ops, struct sk_buff *skb,
 		     const struct net_device *in, const struct net_device *out,
 		     int (*okfn)(struct sk_buff *))
 {
-	return ip_vs_in(hooknum, skb, AF_INET6);
+	return ip_vs_in(ops->hooknum, skb, AF_INET6);
 }
 
 #endif
@@ -1825,7 +1825,7 @@ ip_vs_local_request6(unsigned int hooknum, struct sk_buff *skb,
  *      and send them to ip_vs_in_icmp.
  */
 static unsigned int
-ip_vs_forward_icmp(unsigned int hooknum, struct sk_buff *skb,
+ip_vs_forward_icmp(const struct nf_hook_ops *ops, struct sk_buff *skb,
 		   const struct net_device *in, const struct net_device *out,
 		   int (*okfn)(struct sk_buff *))
 {
@@ -1842,12 +1842,12 @@ ip_vs_forward_icmp(unsigned int hooknum, struct sk_buff *skb,
 	if (unlikely(sysctl_backup_only(ipvs) || !ipvs->enable))
 		return NF_ACCEPT;
 
-	return ip_vs_in_icmp(skb, &r, hooknum);
+	return ip_vs_in_icmp(skb, &r, ops->hooknum);
 }
 
 #ifdef CONFIG_IP_VS_IPV6
 static unsigned int
-ip_vs_forward_icmp_v6(unsigned int hooknum, struct sk_buff *skb,
+ip_vs_forward_icmp_v6(const struct nf_hook_ops *ops, struct sk_buff *skb,
 		      const struct net_device *in, const struct net_device *out,
 		      int (*okfn)(struct sk_buff *))
 {
@@ -1866,7 +1866,7 @@ ip_vs_forward_icmp_v6(unsigned int hooknum, struct sk_buff *skb,
 	if (unlikely(sysctl_backup_only(ipvs) || !ipvs->enable))
 		return NF_ACCEPT;
 
-	return ip_vs_in_icmp_v6(skb, &r, hooknum, &iphdr);
+	return ip_vs_in_icmp_v6(skb, &r, ops->hooknum, &iphdr);
 }
 #endif
 
diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c
index 568c7699abf1..3f224d7795f5 100644
--- a/security/selinux/hooks.c
+++ b/security/selinux/hooks.c
@@ -4668,7 +4668,7 @@ static unsigned int selinux_ip_forward(struct sk_buff *skb, int ifindex,
 	return NF_ACCEPT;
 }
 
-static unsigned int selinux_ipv4_forward(unsigned int hooknum,
+static unsigned int selinux_ipv4_forward(const struct nf_hook_ops *ops,
 					 struct sk_buff *skb,
 					 const struct net_device *in,
 					 const struct net_device *out,
@@ -4678,7 +4678,7 @@ static unsigned int selinux_ipv4_forward(unsigned int hooknum,
 }
 
 #if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
-static unsigned int selinux_ipv6_forward(unsigned int hooknum,
+static unsigned int selinux_ipv6_forward(const struct nf_hook_ops *ops,
 					 struct sk_buff *skb,
 					 const struct net_device *in,
 					 const struct net_device *out,
@@ -4710,7 +4710,7 @@ static unsigned int selinux_ip_output(struct sk_buff *skb,
 	return NF_ACCEPT;
 }
 
-static unsigned int selinux_ipv4_output(unsigned int hooknum,
+static unsigned int selinux_ipv4_output(const struct nf_hook_ops *ops,
 					struct sk_buff *skb,
 					const struct net_device *in,
 					const struct net_device *out,
@@ -4837,7 +4837,7 @@ static unsigned int selinux_ip_postroute(struct sk_buff *skb, int ifindex,
 	return NF_ACCEPT;
 }
 
-static unsigned int selinux_ipv4_postroute(unsigned int hooknum,
+static unsigned int selinux_ipv4_postroute(const struct nf_hook_ops *ops,
 					   struct sk_buff *skb,
 					   const struct net_device *in,
 					   const struct net_device *out,
@@ -4847,7 +4847,7 @@ static unsigned int selinux_ipv4_postroute(unsigned int hooknum,
 }
 
 #if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
-static unsigned int selinux_ipv6_postroute(unsigned int hooknum,
+static unsigned int selinux_ipv6_postroute(const struct nf_hook_ops *ops,
 					   struct sk_buff *skb,
 					   const struct net_device *in,
 					   const struct net_device *out,
-- 
cgit v1.2.3


From c0ab6e56dcb7ca9903d460247cb464e769ae6e77 Mon Sep 17 00:00:00 2001
From: Casey Schaufler <casey@schaufler-ca.com>
Date: Fri, 11 Oct 2013 18:06:39 -0700
Subject: Smack: Implement lock security mode

Linux file locking does not follow the same rules
as other mechanisms. Even though it is a write operation
a process can set a read lock on files which it has open
only for read access. Two programs with read access to
a file can use read locks to communicate.

This is not acceptable in a Mandatory Access Control
environment. Smack treats setting a read lock as the
write operation that it is. Unfortunately, many programs
assume that setting a read lock is a read operation.
These programs are unhappy in the Smack environment.

This patch introduces a new access mode (lock) to address
this problem. A process with lock access to a file can
set a read lock. A process with write access to a file can
set a read lock or a write lock. This prevents a situation
where processes are granted write access just so they can
set read locks.

Targeted for git://git.gitorious.org/smack-next/kernel.git

Signed-off-by: Casey Schaufler <casey@schaufler-ca.com>
---
 security/smack/smack.h        | 12 ++++++++----
 security/smack/smack_access.c | 10 ++++++++++
 security/smack/smack_lsm.c    |  9 +++++++--
 security/smack/smackfs.c      | 10 ++++++++--
 4 files changed, 33 insertions(+), 8 deletions(-)

(limited to 'security')

diff --git a/security/smack/smack.h b/security/smack/smack.h
index 076b8e8a51ab..364cc64fce71 100644
--- a/security/smack/smack.h
+++ b/security/smack/smack.h
@@ -177,9 +177,13 @@ struct smk_port_label {
 #define SMACK_CIPSO_MAXCATNUM           184     /* 23 * 8 */
 
 /*
- * Flag for transmute access
+ * Flags for untraditional access modes.
+ * It shouldn't be necessary to avoid conflicts with definitions
+ * in fs.h, but do so anyway.
  */
-#define MAY_TRANSMUTE	64
+#define MAY_TRANSMUTE	0x00001000	/* Controls directory labeling */
+#define MAY_LOCK	0x00002000	/* Locks should be writes, but ... */
+
 /*
  * Just to make the common cases easier to deal with
  */
@@ -188,9 +192,9 @@ struct smk_port_label {
 #define MAY_NOT		0
 
 /*
- * Number of access types used by Smack (rwxat)
+ * Number of access types used by Smack (rwxatl)
  */
-#define SMK_NUM_ACCESS_TYPE 5
+#define SMK_NUM_ACCESS_TYPE 6
 
 /* SMACK data */
 struct smack_audit_data {
diff --git a/security/smack/smack_access.c b/security/smack/smack_access.c
index b3b59b1e93d6..14293cd9b1e5 100644
--- a/security/smack/smack_access.c
+++ b/security/smack/smack_access.c
@@ -84,6 +84,8 @@ int log_policy = SMACK_AUDIT_DENIED;
  *
  * Do the object check first because that is more
  * likely to differ.
+ *
+ * Allowing write access implies allowing locking.
  */
 int smk_access_entry(char *subject_label, char *object_label,
 			struct list_head *rule_list)
@@ -99,6 +101,11 @@ int smk_access_entry(char *subject_label, char *object_label,
 		}
 	}
 
+	/*
+	 * MAY_WRITE implies MAY_LOCK.
+	 */
+	if ((may & MAY_WRITE) == MAY_WRITE)
+		may |= MAY_LOCK;
 	return may;
 }
 
@@ -245,6 +252,7 @@ out_audit:
 static inline void smack_str_from_perm(char *string, int access)
 {
 	int i = 0;
+
 	if (access & MAY_READ)
 		string[i++] = 'r';
 	if (access & MAY_WRITE)
@@ -255,6 +263,8 @@ static inline void smack_str_from_perm(char *string, int access)
 		string[i++] = 'a';
 	if (access & MAY_TRANSMUTE)
 		string[i++] = 't';
+	if (access & MAY_LOCK)
+		string[i++] = 'l';
 	string[i] = '\0';
 }
 /**
diff --git a/security/smack/smack_lsm.c b/security/smack/smack_lsm.c
index 8825375cc031..88d366e55793 100644
--- a/security/smack/smack_lsm.c
+++ b/security/smack/smack_lsm.c
@@ -1146,7 +1146,7 @@ static int smack_file_ioctl(struct file *file, unsigned int cmd,
  * @file: the object
  * @cmd: unused
  *
- * Returns 0 if current has write access, error code otherwise
+ * Returns 0 if current has lock access, error code otherwise
  */
 static int smack_file_lock(struct file *file, unsigned int cmd)
 {
@@ -1154,7 +1154,7 @@ static int smack_file_lock(struct file *file, unsigned int cmd)
 
 	smk_ad_init(&ad, __func__, LSM_AUDIT_DATA_PATH);
 	smk_ad_setfield_u_fs_path(&ad, file->f_path);
-	return smk_curacc(file->f_security, MAY_WRITE, &ad);
+	return smk_curacc(file->f_security, MAY_LOCK, &ad);
 }
 
 /**
@@ -1178,8 +1178,13 @@ static int smack_file_fcntl(struct file *file, unsigned int cmd,
 
 	switch (cmd) {
 	case F_GETLK:
+		break;
 	case F_SETLK:
 	case F_SETLKW:
+		smk_ad_init(&ad, __func__, LSM_AUDIT_DATA_PATH);
+		smk_ad_setfield_u_fs_path(&ad, file->f_path);
+		rc = smk_curacc(file->f_security, MAY_LOCK, &ad);
+		break;
 	case F_SETOWN:
 	case F_SETSIG:
 		smk_ad_init(&ad, __func__, LSM_AUDIT_DATA_PATH);
diff --git a/security/smack/smackfs.c b/security/smack/smackfs.c
index 80f4b4a45725..160aa08e3cd5 100644
--- a/security/smack/smackfs.c
+++ b/security/smack/smackfs.c
@@ -139,7 +139,7 @@ const char *smack_cipso_option = SMACK_CIPSO_OPTION;
  * SMK_LOADLEN: Smack rule length
  */
 #define SMK_OACCESS	"rwxa"
-#define SMK_ACCESS	"rwxat"
+#define SMK_ACCESS	"rwxatl"
 #define SMK_OACCESSLEN	(sizeof(SMK_OACCESS) - 1)
 #define SMK_ACCESSLEN	(sizeof(SMK_ACCESS) - 1)
 #define SMK_OLOADLEN	(SMK_LABELLEN + SMK_LABELLEN + SMK_OACCESSLEN)
@@ -282,6 +282,10 @@ static int smk_perm_from_str(const char *string)
 		case 'T':
 			perm |= MAY_TRANSMUTE;
 			break;
+		case 'l':
+		case 'L':
+			perm |= MAY_LOCK;
+			break;
 		default:
 			return perm;
 		}
@@ -452,7 +456,7 @@ static ssize_t smk_write_rules_list(struct file *file, const char __user *buf,
 		/*
 		 * Minor hack for backward compatibility
 		 */
-		if (count != SMK_OLOADLEN && count != SMK_LOADLEN)
+		if (count < SMK_OLOADLEN || count > SMK_LOADLEN)
 			return -EINVAL;
 	} else {
 		if (count >= PAGE_SIZE) {
@@ -592,6 +596,8 @@ static void smk_rule_show(struct seq_file *s, struct smack_rule *srp, int max)
 		seq_putc(s, 'a');
 	if (srp->smk_access & MAY_TRANSMUTE)
 		seq_putc(s, 't');
+	if (srp->smk_access & MAY_LOCK)
+		seq_putc(s, 'l');
 
 	seq_putc(s, '\n');
 }
-- 
cgit v1.2.3


From 73ba353471e0b692f398f3d63018b7f46ccf1d3e Mon Sep 17 00:00:00 2001
From: Serge Hallyn <serge.hallyn@ubuntu.com>
Date: Wed, 23 Oct 2013 01:34:00 +0200
Subject: device_cgroup: remove can_attach

It is really only wanting to duplicate a check which is already done by the
cgroup subsystem.

With this patch, user jdoe still cannot move pid 1 into a devices cgroup
he owns, but now he can move his own other tasks into devices cgroups.

Signed-off-by: Serge Hallyn <serge.hallyn@ubuntu.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
Cc: Aristeu Rozanski <aris@redhat.com>
---
 security/device_cgroup.c | 11 -----------
 1 file changed, 11 deletions(-)

(limited to 'security')

diff --git a/security/device_cgroup.c b/security/device_cgroup.c
index c123628d3f84..7c2a0a71049e 100644
--- a/security/device_cgroup.c
+++ b/security/device_cgroup.c
@@ -63,16 +63,6 @@ static inline struct dev_cgroup *task_devcgroup(struct task_struct *task)
 
 struct cgroup_subsys devices_subsys;
 
-static int devcgroup_can_attach(struct cgroup_subsys_state *new_css,
-				struct cgroup_taskset *set)
-{
-	struct task_struct *task = cgroup_taskset_first(set);
-
-	if (current != task && !capable(CAP_SYS_ADMIN))
-		return -EPERM;
-	return 0;
-}
-
 /*
  * called under devcgroup_mutex
  */
@@ -697,7 +687,6 @@ static struct cftype dev_cgroup_files[] = {
 
 struct cgroup_subsys devices_subsys = {
 	.name = "devices",
-	.can_attach = devcgroup_can_attach,
 	.css_alloc = devcgroup_css_alloc,
 	.css_free = devcgroup_css_free,
 	.css_online = devcgroup_online,
-- 
cgit v1.2.3


From 089bc8e95ae07b1ada14069935c30fd88204c21c Mon Sep 17 00:00:00 2001
From: Dmitry Kasatkin <d.kasatkin@samsung.com>
Date: Thu, 10 Oct 2013 15:56:13 +0900
Subject: ima: fix script messages

Fix checkpatch, lindent, etc, warnings/errors

Signed-off-by: Dmitry Kasatkin <d.kasatkin@samsung.com>
Signed-off-by: Mimi Zohar <zohar@linux.vnet.ibm.com>
---
 security/integrity/digsig.c            |  2 +-
 security/integrity/evm/evm_posix_acl.c |  3 ++-
 security/integrity/ima/ima_appraise.c  |  6 +++---
 security/integrity/ima/ima_fs.c        |  3 +--
 security/integrity/ima/ima_main.c      | 10 +++++-----
 security/integrity/integrity.h         |  2 +-
 6 files changed, 13 insertions(+), 13 deletions(-)

(limited to 'security')

diff --git a/security/integrity/digsig.c b/security/integrity/digsig.c
index 0b759e17a131..198e60903685 100644
--- a/security/integrity/digsig.c
+++ b/security/integrity/digsig.c
@@ -28,7 +28,7 @@ static const char *keyring_name[INTEGRITY_KEYRING_MAX] = {
 };
 
 int integrity_digsig_verify(const unsigned int id, const char *sig, int siglen,
-					const char *digest, int digestlen)
+			    const char *digest, int digestlen)
 {
 	if (id >= INTEGRITY_KEYRING_MAX)
 		return -EINVAL;
diff --git a/security/integrity/evm/evm_posix_acl.c b/security/integrity/evm/evm_posix_acl.c
index b1753e98bf9a..46408b9e62e8 100644
--- a/security/integrity/evm/evm_posix_acl.c
+++ b/security/integrity/evm/evm_posix_acl.c
@@ -11,8 +11,9 @@
 
 #include <linux/module.h>
 #include <linux/xattr.h>
+#include <linux/evm.h>
 
-int posix_xattr_acl(char *xattr)
+int posix_xattr_acl(const char *xattr)
 {
 	int xattr_len = strlen(xattr);
 
diff --git a/security/integrity/ima/ima_appraise.c b/security/integrity/ima/ima_appraise.c
index 2d4becab8918..e3230d6a8d96 100644
--- a/security/integrity/ima/ima_appraise.c
+++ b/security/integrity/ima/ima_appraise.c
@@ -55,7 +55,7 @@ static int ima_fix_xattr(struct dentry *dentry,
 enum integrity_status ima_get_cache_status(struct integrity_iint_cache *iint,
 					   int func)
 {
-	switch(func) {
+	switch (func) {
 	case MMAP_CHECK:
 		return iint->ima_mmap_status;
 	case BPRM_CHECK:
@@ -71,7 +71,7 @@ enum integrity_status ima_get_cache_status(struct integrity_iint_cache *iint,
 static void ima_set_cache_status(struct integrity_iint_cache *iint,
 				 int func, enum integrity_status status)
 {
-	switch(func) {
+	switch (func) {
 	case MMAP_CHECK:
 		iint->ima_mmap_status = status;
 		break;
@@ -90,7 +90,7 @@ static void ima_set_cache_status(struct integrity_iint_cache *iint,
 
 static void ima_cache_flags(struct integrity_iint_cache *iint, int func)
 {
-	switch(func) {
+	switch (func) {
 	case MMAP_CHECK:
 		iint->flags |= (IMA_MMAP_APPRAISED | IMA_APPRAISED);
 		break;
diff --git a/security/integrity/ima/ima_fs.c b/security/integrity/ima/ima_fs.c
index 38477c9c3415..5f0fd113433a 100644
--- a/security/integrity/ima/ima_fs.c
+++ b/security/integrity/ima/ima_fs.c
@@ -88,8 +88,7 @@ static void *ima_measurements_next(struct seq_file *m, void *v, loff_t *pos)
 	 * against concurrent list-extension
 	 */
 	rcu_read_lock();
-	qe = list_entry_rcu(qe->later.next,
-			    struct ima_queue_entry, later);
+	qe = list_entry_rcu(qe->later.next, struct ima_queue_entry, later);
 	rcu_read_unlock();
 	(*pos)++;
 
diff --git a/security/integrity/ima/ima_main.c b/security/integrity/ima/ima_main.c
index e9508d5bbfcf..0f359df6344c 100644
--- a/security/integrity/ima/ima_main.c
+++ b/security/integrity/ima/ima_main.c
@@ -244,9 +244,9 @@ int ima_file_mmap(struct file *file, unsigned long prot)
 int ima_bprm_check(struct linux_binprm *bprm)
 {
 	return process_measurement(bprm->file,
-				 (strcmp(bprm->filename, bprm->interp) == 0) ?
-				 bprm->filename : bprm->interp,
-				 MAY_EXEC, BPRM_CHECK);
+				   (strcmp(bprm->filename, bprm->interp) == 0) ?
+				   bprm->filename : bprm->interp,
+				   MAY_EXEC, BPRM_CHECK);
 }
 
 /**
@@ -263,8 +263,8 @@ int ima_file_check(struct file *file, int mask)
 {
 	ima_rdwr_violation_check(file);
 	return process_measurement(file, NULL,
-				 mask & (MAY_READ | MAY_WRITE | MAY_EXEC),
-				 FILE_CHECK);
+				   mask & (MAY_READ | MAY_WRITE | MAY_EXEC),
+				   FILE_CHECK);
 }
 EXPORT_SYMBOL_GPL(ima_file_check);
 
diff --git a/security/integrity/integrity.h b/security/integrity/integrity.h
index c42fb7a70dee..f86731649f54 100644
--- a/security/integrity/integrity.h
+++ b/security/integrity/integrity.h
@@ -89,7 +89,7 @@ struct integrity_iint_cache *integrity_iint_find(struct inode *inode);
 #ifdef CONFIG_INTEGRITY_SIGNATURE
 
 int integrity_digsig_verify(const unsigned int id, const char *sig, int siglen,
-					const char *digest, int digestlen);
+			    const char *digest, int digestlen);
 
 #else
 
-- 
cgit v1.2.3


From 08de59eb144d7c41351a467442f898d720f0f15f Mon Sep 17 00:00:00 2001
From: Mimi Zohar <zohar@linux.vnet.ibm.com>
Date: Thu, 17 Oct 2013 07:34:02 -0400
Subject: Revert "ima: policy for RAMFS"

This reverts commit 4c2c392763a682354fac65b6a569adec4e4b5387.

Everything in the initramfs should be measured and appraised,
but until the initramfs has extended attribute support, at
least measured.

Signed-off-by: Mimi Zohar <zohar@us.ibm.com>
Cc: Stable Kernel <stable@kernel.org>
---
 security/integrity/ima/ima_policy.c | 1 -
 1 file changed, 1 deletion(-)

(limited to 'security')

diff --git a/security/integrity/ima/ima_policy.c b/security/integrity/ima/ima_policy.c
index 399433ad614e..a9c3d3cd1990 100644
--- a/security/integrity/ima/ima_policy.c
+++ b/security/integrity/ima/ima_policy.c
@@ -73,7 +73,6 @@ static struct ima_rule_entry default_rules[] = {
 	{.action = DONT_MEASURE,.fsmagic = SYSFS_MAGIC,.flags = IMA_FSMAGIC},
 	{.action = DONT_MEASURE,.fsmagic = DEBUGFS_MAGIC,.flags = IMA_FSMAGIC},
 	{.action = DONT_MEASURE,.fsmagic = TMPFS_MAGIC,.flags = IMA_FSMAGIC},
-	{.action = DONT_MEASURE,.fsmagic = RAMFS_MAGIC,.flags = IMA_FSMAGIC},
 	{.action = DONT_MEASURE,.fsmagic = DEVPTS_SUPER_MAGIC,.flags = IMA_FSMAGIC},
 	{.action = DONT_MEASURE,.fsmagic = BINFMTFS_MAGIC,.flags = IMA_FSMAGIC},
 	{.action = DONT_MEASURE,.fsmagic = SECURITYFS_MAGIC,.flags = IMA_FSMAGIC},
-- 
cgit v1.2.3


From c7c8bb237fdbff932b5e431aebee5ce862ea07d1 Mon Sep 17 00:00:00 2001
From: Dmitry Kasatkin <d.kasatkin@samsung.com>
Date: Thu, 25 Apr 2013 10:43:56 +0300
Subject: ima: provide support for arbitrary hash algorithms

In preparation of supporting more hash algorithms with larger hash sizes
needed for signature verification, this patch replaces the 20 byte sized
digest, with a more flexible structure.  The new structure includes the
hash algorithm, digest size, and digest.

Changelog:
- recalculate filedata hash for the measurement list, if the signature
  hash digest size is greater than 20 bytes.
- use generic HASH_ALGO_
- make ima_calc_file_hash static
- scripts lindent and checkpatch fixes

Signed-off-by: Dmitry Kasatkin <d.kasatkin@samsung.com>
Signed-off-by: Mimi Zohar <zohar@linux.vnet.ibm.com>
---
 crypto/asymmetric_keys/x509_parser.h     |  2 --
 crypto/asymmetric_keys/x509_public_key.c |  3 +-
 security/integrity/ima/Kconfig           |  1 +
 security/integrity/ima/ima.h             |  7 +++--
 security/integrity/ima/ima_api.c         | 32 +++++++++++++++------
 security/integrity/ima/ima_appraise.c    | 20 +++++++------
 security/integrity/ima/ima_crypto.c      | 49 ++++++++++++++++++++++++++------
 security/integrity/ima/ima_main.c        |  6 ++--
 security/integrity/integrity.h           | 15 ++++++++--
 9 files changed, 100 insertions(+), 35 deletions(-)

(limited to 'security')

diff --git a/crypto/asymmetric_keys/x509_parser.h b/crypto/asymmetric_keys/x509_parser.h
index 04c81bd0f3f2..87d9cc26f630 100644
--- a/crypto/asymmetric_keys/x509_parser.h
+++ b/crypto/asymmetric_keys/x509_parser.h
@@ -21,8 +21,6 @@ struct x509_certificate {
 	char		*authority;		/* Authority key fingerprint as hex */
 	struct tm	valid_from;
 	struct tm	valid_to;
-	enum pkey_algo	pkey_algo : 8;		/* Public key algorithm */
-	enum hash_algo sig_hash_algo : 8;	/* Signature hash algorithm */
 	const void	*tbs;			/* Signed data */
 	unsigned	tbs_size;		/* Size of signed data */
 	unsigned	raw_sig_size;		/* Size of sigature */
diff --git a/crypto/asymmetric_keys/x509_public_key.c b/crypto/asymmetric_keys/x509_public_key.c
index 0a6bfad54916..f83300b6e8c1 100644
--- a/crypto/asymmetric_keys/x509_public_key.c
+++ b/crypto/asymmetric_keys/x509_public_key.c
@@ -213,7 +213,8 @@ static int x509_key_preparse(struct key_preparsed_payload *prep)
 		 cert->valid_to.tm_year + 1900, cert->valid_to.tm_mon + 1,
 		 cert->valid_to.tm_mday, cert->valid_to.tm_hour,
 		 cert->valid_to.tm_min,  cert->valid_to.tm_sec);
-	pr_devel("Cert Signature: %s\n",
+	pr_devel("Cert Signature: %s + %s\n",
+		 pkey_algo_name[cert->sig.pkey_algo],
 		 hash_algo_name[cert->sig.pkey_hash_algo]);
 
 	if (!cert->fingerprint) {
diff --git a/security/integrity/ima/Kconfig b/security/integrity/ima/Kconfig
index 39196abaff0d..e6628e783df1 100644
--- a/security/integrity/ima/Kconfig
+++ b/security/integrity/ima/Kconfig
@@ -9,6 +9,7 @@ config IMA
 	select CRYPTO_HMAC
 	select CRYPTO_MD5
 	select CRYPTO_SHA1
+	select CRYPTO_HASH_INFO
 	select TCG_TPM if HAS_IOMEM && !UML
 	select TCG_TIS if TCG_TPM && X86
 	select TCG_IBMVTPM if TCG_TPM && PPC64
diff --git a/security/integrity/ima/ima.h b/security/integrity/ima/ima.h
index b3dd616560f7..eb86032f4f1e 100644
--- a/security/integrity/ima/ima.h
+++ b/security/integrity/ima/ima.h
@@ -39,7 +39,7 @@ enum tpm_pcrs { TPM_PCR0 = 0, TPM_PCR8 = 8 };
 /* set during initialization */
 extern int ima_initialized;
 extern int ima_used_chip;
-extern char *ima_hash;
+extern int ima_hash_algo;
 extern int ima_appraise;
 
 /* IMA inode template definition */
@@ -70,8 +70,9 @@ void ima_fs_cleanup(void);
 int ima_inode_alloc(struct inode *inode);
 int ima_add_template_entry(struct ima_template_entry *entry, int violation,
 			   const char *op, struct inode *inode);
-int ima_calc_file_hash(struct file *file, char *digest);
-int ima_calc_buffer_hash(const void *data, int len, char *digest);
+int ima_calc_file_hash(struct file *file, struct ima_digest_data *hash);
+int ima_calc_buffer_hash(const void *data, int len,
+			 struct ima_digest_data *hash);
 int ima_calc_boot_aggregate(char *digest);
 void ima_add_violation(struct inode *inode, const unsigned char *filename,
 		       const char *op, const char *cause);
diff --git a/security/integrity/ima/ima_api.c b/security/integrity/ima/ima_api.c
index 1c03e8f1e0e1..e531fe22e582 100644
--- a/security/integrity/ima/ima_api.c
+++ b/security/integrity/ima/ima_api.c
@@ -44,6 +44,7 @@ int ima_store_template(struct ima_template_entry *entry,
 	const char *op = "add_template_measure";
 	const char *audit_cause = "hashing_error";
 	int result;
+	struct ima_digest_data hash;
 
 	memset(entry->digest, 0, sizeof(entry->digest));
 	entry->template_name = IMA_TEMPLATE_NAME;
@@ -51,14 +52,14 @@ int ima_store_template(struct ima_template_entry *entry,
 
 	if (!violation) {
 		result = ima_calc_buffer_hash(&entry->template,
-						entry->template_len,
-						entry->digest);
+					      entry->template_len, &hash);
 		if (result < 0) {
 			integrity_audit_msg(AUDIT_INTEGRITY_PCR, inode,
 					    entry->template_name, op,
 					    audit_cause, result, 0);
 			return result;
 		}
+		memcpy(entry->digest, hash.digest, hash.length);
 	}
 	result = ima_add_template_entry(entry, violation, op, inode);
 	return result;
@@ -147,8 +148,9 @@ int ima_collect_measurement(struct integrity_iint_cache *iint,
 	if (!(iint->flags & IMA_COLLECTED)) {
 		u64 i_version = file_inode(file)->i_version;
 
-		iint->ima_xattr.type = IMA_XATTR_DIGEST;
-		result = ima_calc_file_hash(file, iint->ima_xattr.digest);
+		/* use default hash algorithm */
+		iint->ima_hash.algo = ima_hash_algo;
+		result = ima_calc_file_hash(file, &iint->ima_hash);
 		if (!result) {
 			iint->version = i_version;
 			iint->flags |= IMA_COLLECTED;
@@ -196,7 +198,21 @@ void ima_store_measurement(struct integrity_iint_cache *iint,
 		return;
 	}
 	memset(&entry->template, 0, sizeof(entry->template));
-	memcpy(entry->template.digest, iint->ima_xattr.digest, IMA_DIGEST_SIZE);
+	if (iint->ima_hash.algo != ima_hash_algo) {
+		struct ima_digest_data hash;
+
+		hash.algo = ima_hash_algo;
+		result = ima_calc_file_hash(file, &hash);
+		if (result)
+			integrity_audit_msg(AUDIT_INTEGRITY_DATA, inode,
+					    filename, "collect_data", "failed",
+					    result, 0);
+		else
+			memcpy(entry->template.digest, hash.digest,
+			       hash.length);
+	} else
+		memcpy(entry->template.digest, iint->ima_hash.digest,
+		       iint->ima_hash.length);
 	strcpy(entry->template.file_name,
 	       (strlen(filename) > IMA_EVENT_NAME_LEN_MAX) ?
 	       file->f_dentry->d_name.name : filename);
@@ -212,14 +228,14 @@ void ima_audit_measurement(struct integrity_iint_cache *iint,
 			   const unsigned char *filename)
 {
 	struct audit_buffer *ab;
-	char hash[(IMA_DIGEST_SIZE * 2) + 1];
+	char hash[(iint->ima_hash.length * 2) + 1];
 	int i;
 
 	if (iint->flags & IMA_AUDITED)
 		return;
 
-	for (i = 0; i < IMA_DIGEST_SIZE; i++)
-		hex_byte_pack(hash + (i * 2), iint->ima_xattr.digest[i]);
+	for (i = 0; i < iint->ima_hash.length; i++)
+		hex_byte_pack(hash + (i * 2), iint->ima_hash.digest[i]);
 	hash[i * 2] = '\0';
 
 	ab = audit_log_start(current->audit_context, GFP_KERNEL,
diff --git a/security/integrity/ima/ima_appraise.c b/security/integrity/ima/ima_appraise.c
index e3230d6a8d96..3833b0fa7108 100644
--- a/security/integrity/ima/ima_appraise.c
+++ b/security/integrity/ima/ima_appraise.c
@@ -43,12 +43,12 @@ int ima_must_appraise(struct inode *inode, int mask, enum ima_hooks func)
 }
 
 static int ima_fix_xattr(struct dentry *dentry,
-			  struct integrity_iint_cache *iint)
+			 struct integrity_iint_cache *iint)
 {
-	iint->ima_xattr.type = IMA_XATTR_DIGEST;
+	iint->ima_hash.type = IMA_XATTR_DIGEST;
 	return __vfs_setxattr_noperm(dentry, XATTR_NAME_IMA,
-				     (u8 *)&iint->ima_xattr,
-				      sizeof(iint->ima_xattr), 0);
+				     &iint->ima_hash.type,
+				     1 + iint->ima_hash.length, 0);
 }
 
 /* Return specific func appraised cached result */
@@ -159,8 +159,12 @@ int ima_appraise_measurement(int func, struct integrity_iint_cache *iint,
 			status = INTEGRITY_FAIL;
 			break;
 		}
-		rc = memcmp(xattr_value->digest, iint->ima_xattr.digest,
-			    IMA_DIGEST_SIZE);
+		if (rc - 1 == iint->ima_hash.length)
+			rc = memcmp(xattr_value->digest,
+				    iint->ima_hash.digest,
+				    iint->ima_hash.length);
+		else
+			rc = -EINVAL;
 		if (rc) {
 			cause = "invalid-hash";
 			status = INTEGRITY_FAIL;
@@ -172,8 +176,8 @@ int ima_appraise_measurement(int func, struct integrity_iint_cache *iint,
 		iint->flags |= IMA_DIGSIG;
 		rc = integrity_digsig_verify(INTEGRITY_KEYRING_IMA,
 					     xattr_value->digest, rc - 1,
-					     iint->ima_xattr.digest,
-					     IMA_DIGEST_SIZE);
+					     iint->ima_hash.digest,
+					     iint->ima_hash.length);
 		if (rc == -EOPNOTSUPP) {
 			status = INTEGRITY_UNKNOWN;
 		} else if (rc) {
diff --git a/security/integrity/ima/ima_crypto.c b/security/integrity/ima/ima_crypto.c
index a02e0791cf15..2fd178651467 100644
--- a/security/integrity/ima/ima_crypto.c
+++ b/security/integrity/ima/ima_crypto.c
@@ -20,6 +20,7 @@
 #include <linux/err.h>
 #include <linux/slab.h>
 #include <crypto/hash.h>
+#include <crypto/hash_info.h>
 #include "ima.h"
 
 static struct crypto_shash *ima_shash_tfm;
@@ -28,10 +29,11 @@ int ima_init_crypto(void)
 {
 	long rc;
 
-	ima_shash_tfm = crypto_alloc_shash(ima_hash, 0, 0);
+	ima_shash_tfm = crypto_alloc_shash(hash_algo_name[ima_hash_algo], 0, 0);
 	if (IS_ERR(ima_shash_tfm)) {
 		rc = PTR_ERR(ima_shash_tfm);
-		pr_err("Can not allocate %s (reason: %ld)\n", ima_hash, rc);
+		pr_err("Can not allocate %s (reason: %ld)\n",
+		       hash_algo_name[ima_hash_algo], rc);
 		return rc;
 	}
 	return 0;
@@ -40,17 +42,19 @@ int ima_init_crypto(void)
 /*
  * Calculate the MD5/SHA1 file digest
  */
-int ima_calc_file_hash(struct file *file, char *digest)
+static int ima_calc_file_hash_tfm(struct file *file,
+				  struct ima_digest_data *hash,
+				  struct crypto_shash *tfm)
 {
 	loff_t i_size, offset = 0;
 	char *rbuf;
 	int rc, read = 0;
 	struct {
 		struct shash_desc shash;
-		char ctx[crypto_shash_descsize(ima_shash_tfm)];
+		char ctx[crypto_shash_descsize(tfm)];
 	} desc;
 
-	desc.shash.tfm = ima_shash_tfm;
+	desc.shash.tfm = tfm;
 	desc.shash.flags = 0;
 
 	rc = crypto_shash_init(&desc.shash);
@@ -85,17 +89,42 @@ int ima_calc_file_hash(struct file *file, char *digest)
 	}
 	kfree(rbuf);
 	if (!rc)
-		rc = crypto_shash_final(&desc.shash, digest);
+		rc = crypto_shash_final(&desc.shash, hash->digest);
 	if (read)
 		file->f_mode &= ~FMODE_READ;
 out:
 	return rc;
 }
 
+int ima_calc_file_hash(struct file *file, struct ima_digest_data *hash)
+{
+	struct crypto_shash *tfm = ima_shash_tfm;
+	int rc;
+
+	if (hash->algo != ima_hash_algo && hash->algo < HASH_ALGO__LAST) {
+		tfm = crypto_alloc_shash(hash_algo_name[hash->algo], 0, 0);
+		if (IS_ERR(tfm)) {
+			rc = PTR_ERR(tfm);
+			pr_err("Can not allocate %s (reason: %d)\n",
+			       hash_algo_name[hash->algo], rc);
+			return rc;
+		}
+	}
+
+	hash->length = crypto_shash_digestsize(tfm);
+
+	rc = ima_calc_file_hash_tfm(file, hash, tfm);
+
+	if (tfm != ima_shash_tfm)
+		crypto_free_shash(tfm);
+
+	return rc;
+}
+
 /*
  * Calculate the hash of a given buffer
  */
-int ima_calc_buffer_hash(const void *data, int len, char *digest)
+int ima_calc_buffer_hash(const void *buf, int len, struct ima_digest_data *hash)
 {
 	struct {
 		struct shash_desc shash;
@@ -105,7 +134,11 @@ int ima_calc_buffer_hash(const void *data, int len, char *digest)
 	desc.shash.tfm = ima_shash_tfm;
 	desc.shash.flags = 0;
 
-	return crypto_shash_digest(&desc.shash, data, len, digest);
+	/* this function uses default algo */
+	hash->algo = ima_hash_algo;
+	hash->length = crypto_shash_digestsize(ima_shash_tfm);
+
+	return crypto_shash_digest(&desc.shash, buf, len, hash->digest);
 }
 
 static void __init ima_pcrread(int idx, u8 *pcr)
diff --git a/security/integrity/ima/ima_main.c b/security/integrity/ima/ima_main.c
index 0f359df6344c..7708c2120d9c 100644
--- a/security/integrity/ima/ima_main.c
+++ b/security/integrity/ima/ima_main.c
@@ -24,6 +24,7 @@
 #include <linux/slab.h>
 #include <linux/xattr.h>
 #include <linux/ima.h>
+#include <crypto/hash_info.h>
 
 #include "ima.h"
 
@@ -35,11 +36,12 @@ int ima_appraise = IMA_APPRAISE_ENFORCE;
 int ima_appraise;
 #endif
 
-char *ima_hash = "sha1";
+int ima_hash_algo = HASH_ALGO_SHA1;
+
 static int __init hash_setup(char *str)
 {
 	if (strncmp(str, "md5", 3) == 0)
-		ima_hash = "md5";
+		ima_hash_algo = HASH_ALGO_MD5;
 	return 1;
 }
 __setup("ima_hash=", hash_setup);
diff --git a/security/integrity/integrity.h b/security/integrity/integrity.h
index f86731649f54..0b02ea868e30 100644
--- a/security/integrity/integrity.h
+++ b/security/integrity/integrity.h
@@ -59,20 +59,29 @@ enum evm_ima_xattr_type {
 struct evm_ima_xattr_data {
 	u8 type;
 	u8 digest[SHA1_DIGEST_SIZE];
-}  __attribute__((packed));
+} __packed;
+
+#define IMA_MAX_DIGEST_SIZE	64
+
+struct ima_digest_data {
+	u8 algo;
+	u8 length;
+	u8 type;
+	u8 digest[IMA_MAX_DIGEST_SIZE];
+} __packed;
 
 /* integrity data associated with an inode */
 struct integrity_iint_cache {
-	struct rb_node rb_node; /* rooted in integrity_iint_tree */
+	struct rb_node rb_node;	/* rooted in integrity_iint_tree */
 	struct inode *inode;	/* back pointer to inode in question */
 	u64 version;		/* track inode changes */
 	unsigned long flags;
-	struct evm_ima_xattr_data ima_xattr;
 	enum integrity_status ima_file_status:4;
 	enum integrity_status ima_mmap_status:4;
 	enum integrity_status ima_bprm_status:4;
 	enum integrity_status ima_module_status:4;
 	enum integrity_status evm_status:4;
+	struct ima_digest_data ima_hash;
 };
 
 /* rbtree tree calls to lookup, insert, delete
-- 
cgit v1.2.3


From d3634d0f426bdeb433cb288bdbb0a5e16cf3dbbf Mon Sep 17 00:00:00 2001
From: Dmitry Kasatkin <d.kasatkin@samsung.com>
Date: Thu, 25 Apr 2013 10:44:04 +0300
Subject: ima: read and use signature hash algorithm

All files on the filesystem, currently, are hashed using the same hash
algorithm.  In preparation for files from different packages being
signed using different hash algorithms, this patch adds support for
reading the signature hash algorithm from the 'security.ima' extended
attribute and calculates the appropriate file data hash based on it.

Changelog:
- fix scripts Lindent and checkpatch msgs - Mimi
- fix md5 support for older version, which occupied 20 bytes in the
  xattr, not the expected 16 bytes.  Fix the comparison to compare
  only the first 16 bytes.

Signed-off-by: Dmitry Kasatkin <d.kasatkin@samsung.com>
Signed-off-by: Mimi Zohar <zohar@linux.vnet.ibm.com>
---
 security/integrity/digsig_asymmetric.c | 11 ---------
 security/integrity/ima/ima.h           | 29 +++++++++++++++++++---
 security/integrity/ima/ima_api.c       | 12 ++++++++-
 security/integrity/ima/ima_appraise.c  | 45 ++++++++++++++++++++++++++++------
 security/integrity/ima/ima_main.c      | 11 +++++++--
 security/integrity/integrity.h         | 11 +++++++++
 6 files changed, 94 insertions(+), 25 deletions(-)

(limited to 'security')

diff --git a/security/integrity/digsig_asymmetric.c b/security/integrity/digsig_asymmetric.c
index b4754667659d..9eae4809006b 100644
--- a/security/integrity/digsig_asymmetric.c
+++ b/security/integrity/digsig_asymmetric.c
@@ -19,17 +19,6 @@
 
 #include "integrity.h"
 
-/*
- * signature format v2 - for using with asymmetric keys
- */
-struct signature_v2_hdr {
-	uint8_t version;	/* signature format version */
-	uint8_t	hash_algo;	/* Digest algorithm [enum pkey_hash_algo] */
-	uint32_t keyid;		/* IMA key identifier - not X509/PGP specific*/
-	uint16_t sig_size;	/* signature size */
-	uint8_t sig[0];		/* signature payload */
-} __packed;
-
 /*
  * Request an asymmetric key.
  */
diff --git a/security/integrity/ima/ima.h b/security/integrity/ima/ima.h
index eb86032f4f1e..efcdef2bf1bc 100644
--- a/security/integrity/ima/ima.h
+++ b/security/integrity/ima/ima.h
@@ -99,7 +99,9 @@ static inline unsigned long ima_hash_key(u8 *digest)
 int ima_get_action(struct inode *inode, int mask, int function);
 int ima_must_measure(struct inode *inode, int mask, int function);
 int ima_collect_measurement(struct integrity_iint_cache *iint,
-			    struct file *file);
+			    struct file *file,
+			    struct evm_ima_xattr_data **xattr_value,
+			    int *xattr_len);
 void ima_store_measurement(struct integrity_iint_cache *iint, struct file *file,
 			   const unsigned char *filename);
 void ima_audit_measurement(struct integrity_iint_cache *iint,
@@ -132,17 +134,25 @@ void ima_delete_rules(void);
 
 #ifdef CONFIG_IMA_APPRAISE
 int ima_appraise_measurement(int func, struct integrity_iint_cache *iint,
-			     struct file *file, const unsigned char *filename);
+			     struct file *file, const unsigned char *filename,
+			     struct evm_ima_xattr_data *xattr_value,
+			     int xattr_len);
 int ima_must_appraise(struct inode *inode, int mask, enum ima_hooks func);
 void ima_update_xattr(struct integrity_iint_cache *iint, struct file *file);
 enum integrity_status ima_get_cache_status(struct integrity_iint_cache *iint,
 					   int func);
+void ima_get_hash_algo(struct evm_ima_xattr_data *xattr_value, int xattr_len,
+		       struct ima_digest_data *hash);
+int ima_read_xattr(struct dentry *dentry,
+		   struct evm_ima_xattr_data **xattr_value);
 
 #else
 static inline int ima_appraise_measurement(int func,
 					   struct integrity_iint_cache *iint,
 					   struct file *file,
-					   const unsigned char *filename)
+					   const unsigned char *filename,
+					   struct evm_ima_xattr_data *xattr_value,
+					   int xattr_len)
 {
 	return INTEGRITY_UNKNOWN;
 }
@@ -163,6 +173,19 @@ static inline enum integrity_status ima_get_cache_status(struct integrity_iint_c
 {
 	return INTEGRITY_UNKNOWN;
 }
+
+static inline void ima_get_hash_algo(struct evm_ima_xattr_data *xattr_value,
+				     int xattr_len,
+				     struct ima_digest_data *hash)
+{
+}
+
+static inline int ima_read_xattr(struct dentry *dentry,
+				 struct evm_ima_xattr_data **xattr_value)
+{
+	return 0;
+}
+
 #endif
 
 /* LSM based policy rules require audit */
diff --git a/security/integrity/ima/ima_api.c b/security/integrity/ima/ima_api.c
index e531fe22e582..1dba98e2d7e9 100644
--- a/security/integrity/ima/ima_api.c
+++ b/security/integrity/ima/ima_api.c
@@ -139,17 +139,27 @@ int ima_must_measure(struct inode *inode, int mask, int function)
  * Return 0 on success, error code otherwise
  */
 int ima_collect_measurement(struct integrity_iint_cache *iint,
-			    struct file *file)
+			    struct file *file,
+			    struct evm_ima_xattr_data **xattr_value,
+			    int *xattr_len)
 {
 	struct inode *inode = file_inode(file);
 	const char *filename = file->f_dentry->d_name.name;
 	int result = 0;
 
+	if (xattr_value)
+		*xattr_len = ima_read_xattr(file->f_dentry, xattr_value);
+
 	if (!(iint->flags & IMA_COLLECTED)) {
 		u64 i_version = file_inode(file)->i_version;
 
 		/* use default hash algorithm */
 		iint->ima_hash.algo = ima_hash_algo;
+
+		if (xattr_value)
+			ima_get_hash_algo(*xattr_value, *xattr_len,
+					  &iint->ima_hash);
+
 		result = ima_calc_file_hash(file, &iint->ima_hash);
 		if (!result) {
 			iint->version = i_version;
diff --git a/security/integrity/ima/ima_appraise.c b/security/integrity/ima/ima_appraise.c
index 3833b0fa7108..00708a3052cc 100644
--- a/security/integrity/ima/ima_appraise.c
+++ b/security/integrity/ima/ima_appraise.c
@@ -107,6 +107,34 @@ static void ima_cache_flags(struct integrity_iint_cache *iint, int func)
 	}
 }
 
+void ima_get_hash_algo(struct evm_ima_xattr_data *xattr_value, int xattr_len,
+		       struct ima_digest_data *hash)
+{
+	struct signature_v2_hdr *sig;
+
+	if (!xattr_value || xattr_len < 0 || xattr_len <= 1 + sizeof(*sig))
+		return;
+
+	sig = (typeof(sig)) xattr_value->digest;
+
+	if (xattr_value->type != EVM_IMA_XATTR_DIGSIG || sig->version != 2)
+		return;
+
+	hash->algo = sig->hash_algo;
+}
+
+int ima_read_xattr(struct dentry *dentry,
+		   struct evm_ima_xattr_data **xattr_value)
+{
+	struct inode *inode = dentry->d_inode;
+
+	if (!inode->i_op->getxattr)
+		return 0;
+
+	return vfs_getxattr_alloc(dentry, XATTR_NAME_IMA, (char **)xattr_value,
+				  0, GFP_NOFS);
+}
+
 /*
  * ima_appraise_measurement - appraise file measurement
  *
@@ -116,23 +144,22 @@ static void ima_cache_flags(struct integrity_iint_cache *iint, int func)
  * Return 0 on success, error code otherwise
  */
 int ima_appraise_measurement(int func, struct integrity_iint_cache *iint,
-			     struct file *file, const unsigned char *filename)
+			     struct file *file, const unsigned char *filename,
+			     struct evm_ima_xattr_data *xattr_value,
+			     int xattr_len)
 {
 	struct dentry *dentry = file->f_dentry;
 	struct inode *inode = dentry->d_inode;
-	struct evm_ima_xattr_data *xattr_value = NULL;
 	enum integrity_status status = INTEGRITY_UNKNOWN;
 	const char *op = "appraise_data";
 	char *cause = "unknown";
-	int rc;
+	int rc = xattr_len;
 
 	if (!ima_appraise)
 		return 0;
 	if (!inode->i_op->getxattr)
 		return INTEGRITY_UNKNOWN;
 
-	rc = vfs_getxattr_alloc(dentry, XATTR_NAME_IMA, (char **)&xattr_value,
-				0, GFP_NOFS);
 	if (rc <= 0) {
 		if (rc && rc != -ENODATA)
 			goto out;
@@ -159,7 +186,10 @@ int ima_appraise_measurement(int func, struct integrity_iint_cache *iint,
 			status = INTEGRITY_FAIL;
 			break;
 		}
-		if (rc - 1 == iint->ima_hash.length)
+		if (xattr_len - 1 >= iint->ima_hash.length)
+			/* xattr length may be longer. md5 hash in previous
+			   version occupied 20 bytes in xattr, instead of 16
+			 */
 			rc = memcmp(xattr_value->digest,
 				    iint->ima_hash.digest,
 				    iint->ima_hash.length);
@@ -207,7 +237,6 @@ out:
 		ima_cache_flags(iint, func);
 	}
 	ima_set_cache_status(iint, func, status);
-	kfree(xattr_value);
 	return status;
 }
 
@@ -223,7 +252,7 @@ void ima_update_xattr(struct integrity_iint_cache *iint, struct file *file)
 	if (iint->flags & IMA_DIGSIG)
 		return;
 
-	rc = ima_collect_measurement(iint, file);
+	rc = ima_collect_measurement(iint, file, NULL, NULL);
 	if (rc < 0)
 		return;
 
diff --git a/security/integrity/ima/ima_main.c b/security/integrity/ima/ima_main.c
index 7708c2120d9c..95b5df2c6501 100644
--- a/security/integrity/ima/ima_main.c
+++ b/security/integrity/ima/ima_main.c
@@ -149,6 +149,8 @@ static int process_measurement(struct file *file, const char *filename,
 	char *pathbuf = NULL;
 	const char *pathname = NULL;
 	int rc = -ENOMEM, action, must_appraise, _func;
+	struct evm_ima_xattr_data *xattr_value = NULL, **xattr_ptr = NULL;
+	int xattr_len = 0;
 
 	if (!ima_initialized || !S_ISREG(inode->i_mode))
 		return 0;
@@ -187,7 +189,10 @@ static int process_measurement(struct file *file, const char *filename,
 		goto out_digsig;
 	}
 
-	rc = ima_collect_measurement(iint, file);
+	if (action & IMA_APPRAISE_SUBMASK)
+		xattr_ptr = &xattr_value;
+
+	rc = ima_collect_measurement(iint, file, xattr_ptr, &xattr_len);
 	if (rc != 0)
 		goto out_digsig;
 
@@ -198,7 +203,8 @@ static int process_measurement(struct file *file, const char *filename,
 	if (action & IMA_MEASURE)
 		ima_store_measurement(iint, file, pathname);
 	if (action & IMA_APPRAISE_SUBMASK)
-		rc = ima_appraise_measurement(_func, iint, file, pathname);
+		rc = ima_appraise_measurement(_func, iint, file, pathname,
+					      xattr_value, xattr_len);
 	if (action & IMA_AUDIT)
 		ima_audit_measurement(iint, pathname);
 	kfree(pathbuf);
@@ -207,6 +213,7 @@ out_digsig:
 		rc = -EACCES;
 out:
 	mutex_unlock(&inode->i_mutex);
+	kfree(xattr_value);
 	if ((rc && must_appraise) && (ima_appraise & IMA_APPRAISE_ENFORCE))
 		return -EACCES;
 	return 0;
diff --git a/security/integrity/integrity.h b/security/integrity/integrity.h
index 0b02ea868e30..ea2318983d97 100644
--- a/security/integrity/integrity.h
+++ b/security/integrity/integrity.h
@@ -70,6 +70,17 @@ struct ima_digest_data {
 	u8 digest[IMA_MAX_DIGEST_SIZE];
 } __packed;
 
+/*
+ * signature format v2 - for using with asymmetric keys
+ */
+struct signature_v2_hdr {
+	uint8_t version;	/* signature format version */
+	uint8_t	hash_algo;	/* Digest algorithm [enum pkey_hash_algo] */
+	uint32_t keyid;		/* IMA key identifier - not X509/PGP specific */
+	uint16_t sig_size;	/* signature size */
+	uint8_t sig[0];		/* signature payload */
+} __packed;
+
 /* integrity data associated with an inode */
 struct integrity_iint_cache {
 	struct rb_node rb_node;	/* rooted in integrity_iint_tree */
-- 
cgit v1.2.3


From b1aaab22e263d0cca1effe319b7d2bf895444219 Mon Sep 17 00:00:00 2001
From: Dmitry Kasatkin <d.kasatkin@samsung.com>
Date: Thu, 10 Oct 2013 16:12:03 +0900
Subject: ima: pass full xattr with the signature

For possibility to use xattr type for new signature formats,
pass full xattr to the signature verification function.

Signed-off-by: Dmitry Kasatkin <d.kasatkin@samsung.com>
Signed-off-by: Mimi Zohar <zohar@linux.vnet.ibm.com>
---
 security/integrity/digsig.c           | 5 +++--
 security/integrity/evm/evm_main.c     | 4 ++--
 security/integrity/ima/ima_appraise.c | 2 +-
 security/integrity/integrity.h        | 1 +
 4 files changed, 7 insertions(+), 5 deletions(-)

(limited to 'security')

diff --git a/security/integrity/digsig.c b/security/integrity/digsig.c
index 198e60903685..b4af4ebc5be2 100644
--- a/security/integrity/digsig.c
+++ b/security/integrity/digsig.c
@@ -44,9 +44,10 @@ int integrity_digsig_verify(const unsigned int id, const char *sig, int siglen,
 		}
 	}
 
-	switch (sig[0]) {
+	switch (sig[1]) {
 	case 1:
-		return digsig_verify(keyring[id], sig, siglen,
+		/* v1 API expect signature without xattr type */
+		return digsig_verify(keyring[id], sig + 1, siglen - 1,
 				     digest, digestlen);
 	case 2:
 		return asymmetric_verify(keyring[id], sig, siglen,
diff --git a/security/integrity/evm/evm_main.c b/security/integrity/evm/evm_main.c
index af9b6852f4e1..336b3ddfe63f 100644
--- a/security/integrity/evm/evm_main.c
+++ b/security/integrity/evm/evm_main.c
@@ -123,7 +123,7 @@ static enum integrity_status evm_verify_hmac(struct dentry *dentry,
 		goto out;
 	}
 
-	xattr_len = rc - 1;
+	xattr_len = rc;
 
 	/* check value type */
 	switch (xattr_data->type) {
@@ -143,7 +143,7 @@ static enum integrity_status evm_verify_hmac(struct dentry *dentry,
 		if (rc)
 			break;
 		rc = integrity_digsig_verify(INTEGRITY_KEYRING_EVM,
-					xattr_data->digest, xattr_len,
+					(const char *)xattr_data, xattr_len,
 					calc.digest, sizeof(calc.digest));
 		if (!rc) {
 			/* we probably want to replace rsa with hmac here */
diff --git a/security/integrity/ima/ima_appraise.c b/security/integrity/ima/ima_appraise.c
index 00708a3052cc..e1865a6e80ec 100644
--- a/security/integrity/ima/ima_appraise.c
+++ b/security/integrity/ima/ima_appraise.c
@@ -205,7 +205,7 @@ int ima_appraise_measurement(int func, struct integrity_iint_cache *iint,
 	case EVM_IMA_XATTR_DIGSIG:
 		iint->flags |= IMA_DIGSIG;
 		rc = integrity_digsig_verify(INTEGRITY_KEYRING_IMA,
-					     xattr_value->digest, rc - 1,
+					     (const char *)xattr_value, rc,
 					     iint->ima_hash.digest,
 					     iint->ima_hash.length);
 		if (rc == -EOPNOTSUPP) {
diff --git a/security/integrity/integrity.h b/security/integrity/integrity.h
index ea2318983d97..aead6b2b5488 100644
--- a/security/integrity/integrity.h
+++ b/security/integrity/integrity.h
@@ -74,6 +74,7 @@ struct ima_digest_data {
  * signature format v2 - for using with asymmetric keys
  */
 struct signature_v2_hdr {
+	uint8_t type;		/* xattr type */
 	uint8_t version;	/* signature format version */
 	uint8_t	hash_algo;	/* Digest algorithm [enum pkey_hash_algo] */
 	uint32_t keyid;		/* IMA key identifier - not X509/PGP specific */
-- 
cgit v1.2.3


From a35c3fb6490cc1d3446e4781693408100113c4fb Mon Sep 17 00:00:00 2001
From: Dmitry Kasatkin <d.kasatkin@samsung.com>
Date: Thu, 25 Apr 2013 10:44:04 +0300
Subject: ima: use dynamically allocated hash storage

For each inode in the IMA policy, an iint is allocated.  To support
larger hash digests, the iint digest size changed from 20 bytes to
the maximum supported hash digest size.  Instead of allocating the
maximum size, which most likely is not needed, this patch dynamically
allocates the needed hash storage.

Changelog:
- fix krealloc bug

Signed-off-by: Dmitry Kasatkin <d.kasatkin@samsung.com>
Signed-off-by: Mimi Zohar <zohar@linux.vnet.ibm.com>
---
 security/integrity/iint.c             |  2 ++
 security/integrity/ima/ima_api.c      | 57 +++++++++++++++++++++++------------
 security/integrity/ima/ima_appraise.c | 16 +++++-----
 security/integrity/integrity.h        |  4 +--
 4 files changed, 49 insertions(+), 30 deletions(-)

(limited to 'security')

diff --git a/security/integrity/iint.c b/security/integrity/iint.c
index 74522dbd10a6..c49d3f14cbec 100644
--- a/security/integrity/iint.c
+++ b/security/integrity/iint.c
@@ -70,6 +70,8 @@ struct integrity_iint_cache *integrity_iint_find(struct inode *inode)
 
 static void iint_free(struct integrity_iint_cache *iint)
 {
+	kfree(iint->ima_hash);
+	iint->ima_hash = NULL;
 	iint->version = 0;
 	iint->flags = 0UL;
 	iint->ima_file_status = INTEGRITY_UNKNOWN;
diff --git a/security/integrity/ima/ima_api.c b/security/integrity/ima/ima_api.c
index 1dba98e2d7e9..5a7942e20814 100644
--- a/security/integrity/ima/ima_api.c
+++ b/security/integrity/ima/ima_api.c
@@ -44,7 +44,10 @@ int ima_store_template(struct ima_template_entry *entry,
 	const char *op = "add_template_measure";
 	const char *audit_cause = "hashing_error";
 	int result;
-	struct ima_digest_data hash;
+	struct {
+		struct ima_digest_data hdr;
+		char digest[IMA_MAX_DIGEST_SIZE];
+	} hash;
 
 	memset(entry->digest, 0, sizeof(entry->digest));
 	entry->template_name = IMA_TEMPLATE_NAME;
@@ -52,14 +55,14 @@ int ima_store_template(struct ima_template_entry *entry,
 
 	if (!violation) {
 		result = ima_calc_buffer_hash(&entry->template,
-					      entry->template_len, &hash);
+					      entry->template_len, &hash.hdr);
 		if (result < 0) {
 			integrity_audit_msg(AUDIT_INTEGRITY_PCR, inode,
 					    entry->template_name, op,
 					    audit_cause, result, 0);
 			return result;
 		}
-		memcpy(entry->digest, hash.digest, hash.length);
+		memcpy(entry->digest, hash.hdr.digest, hash.hdr.length);
 	}
 	result = ima_add_template_entry(entry, violation, op, inode);
 	return result;
@@ -146,6 +149,10 @@ int ima_collect_measurement(struct integrity_iint_cache *iint,
 	struct inode *inode = file_inode(file);
 	const char *filename = file->f_dentry->d_name.name;
 	int result = 0;
+	struct {
+		struct ima_digest_data hdr;
+		char digest[IMA_MAX_DIGEST_SIZE];
+	} hash;
 
 	if (xattr_value)
 		*xattr_len = ima_read_xattr(file->f_dentry, xattr_value);
@@ -154,16 +161,23 @@ int ima_collect_measurement(struct integrity_iint_cache *iint,
 		u64 i_version = file_inode(file)->i_version;
 
 		/* use default hash algorithm */
-		iint->ima_hash.algo = ima_hash_algo;
+		hash.hdr.algo = ima_hash_algo;
 
 		if (xattr_value)
-			ima_get_hash_algo(*xattr_value, *xattr_len,
-					  &iint->ima_hash);
+			ima_get_hash_algo(*xattr_value, *xattr_len, &hash.hdr);
 
-		result = ima_calc_file_hash(file, &iint->ima_hash);
+		result = ima_calc_file_hash(file, &hash.hdr);
 		if (!result) {
-			iint->version = i_version;
-			iint->flags |= IMA_COLLECTED;
+			int length = sizeof(hash.hdr) + hash.hdr.length;
+			void *tmpbuf = krealloc(iint->ima_hash, length,
+						GFP_NOFS);
+			if (tmpbuf) {
+				iint->ima_hash = tmpbuf;
+				memcpy(iint->ima_hash, &hash, length);
+				iint->version = i_version;
+				iint->flags |= IMA_COLLECTED;
+			} else
+				result = -ENOMEM;
 		}
 	}
 	if (result)
@@ -208,21 +222,24 @@ void ima_store_measurement(struct integrity_iint_cache *iint,
 		return;
 	}
 	memset(&entry->template, 0, sizeof(entry->template));
-	if (iint->ima_hash.algo != ima_hash_algo) {
-		struct ima_digest_data hash;
+	if (iint->ima_hash->algo != ima_hash_algo) {
+		struct {
+			struct ima_digest_data hdr;
+			char digest[IMA_MAX_DIGEST_SIZE];
+		} hash;
 
-		hash.algo = ima_hash_algo;
-		result = ima_calc_file_hash(file, &hash);
+		hash.hdr.algo = ima_hash_algo;
+		result = ima_calc_file_hash(file, &hash.hdr);
 		if (result)
 			integrity_audit_msg(AUDIT_INTEGRITY_DATA, inode,
 					    filename, "collect_data", "failed",
 					    result, 0);
 		else
-			memcpy(entry->template.digest, hash.digest,
-			       hash.length);
+			memcpy(entry->template.digest, hash.hdr.digest,
+			       hash.hdr.length);
 	} else
-		memcpy(entry->template.digest, iint->ima_hash.digest,
-		       iint->ima_hash.length);
+		memcpy(entry->template.digest, iint->ima_hash->digest,
+		       iint->ima_hash->length);
 	strcpy(entry->template.file_name,
 	       (strlen(filename) > IMA_EVENT_NAME_LEN_MAX) ?
 	       file->f_dentry->d_name.name : filename);
@@ -238,14 +255,14 @@ void ima_audit_measurement(struct integrity_iint_cache *iint,
 			   const unsigned char *filename)
 {
 	struct audit_buffer *ab;
-	char hash[(iint->ima_hash.length * 2) + 1];
+	char hash[(iint->ima_hash->length * 2) + 1];
 	int i;
 
 	if (iint->flags & IMA_AUDITED)
 		return;
 
-	for (i = 0; i < iint->ima_hash.length; i++)
-		hex_byte_pack(hash + (i * 2), iint->ima_hash.digest[i]);
+	for (i = 0; i < iint->ima_hash->length; i++)
+		hex_byte_pack(hash + (i * 2), iint->ima_hash->digest[i]);
 	hash[i * 2] = '\0';
 
 	ab = audit_log_start(current->audit_context, GFP_KERNEL,
diff --git a/security/integrity/ima/ima_appraise.c b/security/integrity/ima/ima_appraise.c
index e1865a6e80ec..116630ca5ff3 100644
--- a/security/integrity/ima/ima_appraise.c
+++ b/security/integrity/ima/ima_appraise.c
@@ -45,10 +45,10 @@ int ima_must_appraise(struct inode *inode, int mask, enum ima_hooks func)
 static int ima_fix_xattr(struct dentry *dentry,
 			 struct integrity_iint_cache *iint)
 {
-	iint->ima_hash.type = IMA_XATTR_DIGEST;
+	iint->ima_hash->type = IMA_XATTR_DIGEST;
 	return __vfs_setxattr_noperm(dentry, XATTR_NAME_IMA,
-				     &iint->ima_hash.type,
-				     1 + iint->ima_hash.length, 0);
+				     &iint->ima_hash->type,
+				     1 + iint->ima_hash->length, 0);
 }
 
 /* Return specific func appraised cached result */
@@ -186,13 +186,13 @@ int ima_appraise_measurement(int func, struct integrity_iint_cache *iint,
 			status = INTEGRITY_FAIL;
 			break;
 		}
-		if (xattr_len - 1 >= iint->ima_hash.length)
+		if (xattr_len - 1 >= iint->ima_hash->length)
 			/* xattr length may be longer. md5 hash in previous
 			   version occupied 20 bytes in xattr, instead of 16
 			 */
 			rc = memcmp(xattr_value->digest,
-				    iint->ima_hash.digest,
-				    iint->ima_hash.length);
+				    iint->ima_hash->digest,
+				    iint->ima_hash->length);
 		else
 			rc = -EINVAL;
 		if (rc) {
@@ -206,8 +206,8 @@ int ima_appraise_measurement(int func, struct integrity_iint_cache *iint,
 		iint->flags |= IMA_DIGSIG;
 		rc = integrity_digsig_verify(INTEGRITY_KEYRING_IMA,
 					     (const char *)xattr_value, rc,
-					     iint->ima_hash.digest,
-					     iint->ima_hash.length);
+					     iint->ima_hash->digest,
+					     iint->ima_hash->length);
 		if (rc == -EOPNOTSUPP) {
 			status = INTEGRITY_UNKNOWN;
 		} else if (rc) {
diff --git a/security/integrity/integrity.h b/security/integrity/integrity.h
index aead6b2b5488..5429ca59125b 100644
--- a/security/integrity/integrity.h
+++ b/security/integrity/integrity.h
@@ -67,7 +67,7 @@ struct ima_digest_data {
 	u8 algo;
 	u8 length;
 	u8 type;
-	u8 digest[IMA_MAX_DIGEST_SIZE];
+	u8 digest[0];
 } __packed;
 
 /*
@@ -93,7 +93,7 @@ struct integrity_iint_cache {
 	enum integrity_status ima_bprm_status:4;
 	enum integrity_status ima_module_status:4;
 	enum integrity_status evm_status:4;
-	struct ima_digest_data ima_hash;
+	struct ima_digest_data *ima_hash;
 };
 
 /* rbtree tree calls to lookup, insert, delete
-- 
cgit v1.2.3


From 140d802240a4ba3351494b4ab199964b96f87493 Mon Sep 17 00:00:00 2001
From: Mimi Zohar <zohar@linux.vnet.ibm.com>
Date: Mon, 11 Mar 2013 20:29:47 -0400
Subject: ima: differentiate between template hash and file data hash sizes

The TPM v1.2 limits the template hash size to 20 bytes.  This
patch differentiates between the template hash size, as defined
in the ima_template_entry, and the file data hash size, as
defined in the ima_template_data.  Subsequent patches add support
for different file data hash algorithms.

Change log:
- hash digest definition in ima_store_template() should be TPM_DIGEST_SIZE

Signed-off-by: Mimi Zohar <zohar@us.ibm.com>
---
 security/integrity/ima/ima.h        |  2 +-
 security/integrity/ima/ima_api.c    |  2 +-
 security/integrity/ima/ima_crypto.c |  4 ++--
 security/integrity/ima/ima_fs.c     | 10 +++++-----
 security/integrity/ima/ima_init.c   |  2 +-
 security/integrity/ima/ima_queue.c  |  4 ++--
 6 files changed, 12 insertions(+), 12 deletions(-)

(limited to 'security')

diff --git a/security/integrity/ima/ima.h b/security/integrity/ima/ima.h
index efcdef2bf1bc..52393edfbfd9 100644
--- a/security/integrity/ima/ima.h
+++ b/security/integrity/ima/ima.h
@@ -49,7 +49,7 @@ struct ima_template_data {
 };
 
 struct ima_template_entry {
-	u8 digest[IMA_DIGEST_SIZE];	/* sha1 or md5 measurement hash */
+	u8 digest[TPM_DIGEST_SIZE];	/* sha1 or md5 measurement hash */
 	const char *template_name;
 	int template_len;
 	struct ima_template_data template;
diff --git a/security/integrity/ima/ima_api.c b/security/integrity/ima/ima_api.c
index 5a7942e20814..2cc5dcc6bdeb 100644
--- a/security/integrity/ima/ima_api.c
+++ b/security/integrity/ima/ima_api.c
@@ -46,7 +46,7 @@ int ima_store_template(struct ima_template_entry *entry,
 	int result;
 	struct {
 		struct ima_digest_data hdr;
-		char digest[IMA_MAX_DIGEST_SIZE];
+		char digest[TPM_DIGEST_SIZE];
 	} hash;
 
 	memset(entry->digest, 0, sizeof(entry->digest));
diff --git a/security/integrity/ima/ima_crypto.c b/security/integrity/ima/ima_crypto.c
index 2fd178651467..872c6698067c 100644
--- a/security/integrity/ima/ima_crypto.c
+++ b/security/integrity/ima/ima_crypto.c
@@ -155,7 +155,7 @@ static void __init ima_pcrread(int idx, u8 *pcr)
  */
 int __init ima_calc_boot_aggregate(char *digest)
 {
-	u8 pcr_i[IMA_DIGEST_SIZE];
+	u8 pcr_i[TPM_DIGEST_SIZE];
 	int rc, i;
 	struct {
 		struct shash_desc shash;
@@ -173,7 +173,7 @@ int __init ima_calc_boot_aggregate(char *digest)
 	for (i = TPM_PCR0; i < TPM_PCR8; i++) {
 		ima_pcrread(i, pcr_i);
 		/* now accumulate with current aggregate */
-		rc = crypto_shash_update(&desc.shash, pcr_i, IMA_DIGEST_SIZE);
+		rc = crypto_shash_update(&desc.shash, pcr_i, TPM_DIGEST_SIZE);
 	}
 	if (!rc)
 		crypto_shash_final(&desc.shash, digest);
diff --git a/security/integrity/ima/ima_fs.c b/security/integrity/ima/ima_fs.c
index 5f0fd113433a..c35cfb5b3c5e 100644
--- a/security/integrity/ima/ima_fs.c
+++ b/security/integrity/ima/ima_fs.c
@@ -133,7 +133,7 @@ static int ima_measurements_show(struct seq_file *m, void *v)
 	ima_putc(m, &pcr, sizeof pcr);
 
 	/* 2nd: template digest */
-	ima_putc(m, e->digest, IMA_DIGEST_SIZE);
+	ima_putc(m, e->digest, TPM_DIGEST_SIZE);
 
 	/* 3rd: template name size */
 	namelen = strlen(e->template_name);
@@ -167,11 +167,11 @@ static const struct file_operations ima_measurements_ops = {
 	.release = seq_release,
 };
 
-static void ima_print_digest(struct seq_file *m, u8 *digest)
+static void ima_print_digest(struct seq_file *m, u8 *digest, int size)
 {
 	int i;
 
-	for (i = 0; i < IMA_DIGEST_SIZE; i++)
+	for (i = 0; i < size; i++)
 		seq_printf(m, "%02x", *(digest + i));
 }
 
@@ -182,7 +182,7 @@ void ima_template_show(struct seq_file *m, void *e, enum ima_show_type show)
 
 	switch (show) {
 	case IMA_SHOW_ASCII:
-		ima_print_digest(m, entry->digest);
+		ima_print_digest(m, entry->digest, IMA_DIGEST_SIZE);
 		seq_printf(m, " %s\n", entry->file_name);
 		break;
 	case IMA_SHOW_BINARY:
@@ -212,7 +212,7 @@ static int ima_ascii_measurements_show(struct seq_file *m, void *v)
 	seq_printf(m, "%2d ", CONFIG_IMA_MEASURE_PCR_IDX);
 
 	/* 2nd: SHA1 template hash */
-	ima_print_digest(m, e->digest);
+	ima_print_digest(m, e->digest, TPM_DIGEST_SIZE);
 
 	/* 3th:  template name */
 	seq_printf(m, " %s ", e->template_name);
diff --git a/security/integrity/ima/ima_init.c b/security/integrity/ima/ima_init.c
index 162ea723db3d..9d0243c10558 100644
--- a/security/integrity/ima/ima_init.c
+++ b/security/integrity/ima/ima_init.c
@@ -74,7 +74,7 @@ err_out:
 
 int __init ima_init(void)
 {
-	u8 pcr_i[IMA_DIGEST_SIZE];
+	u8 pcr_i[TPM_DIGEST_SIZE];
 	int rc;
 
 	ima_used_chip = 0;
diff --git a/security/integrity/ima/ima_queue.c b/security/integrity/ima/ima_queue.c
index ff63fe00c195..e63ff3369f10 100644
--- a/security/integrity/ima/ima_queue.c
+++ b/security/integrity/ima/ima_queue.c
@@ -50,7 +50,7 @@ static struct ima_queue_entry *ima_lookup_digest_entry(u8 *digest_value)
 	key = ima_hash_key(digest_value);
 	rcu_read_lock();
 	hlist_for_each_entry_rcu(qe, &ima_htable.queue[key], hnext) {
-		rc = memcmp(qe->entry->digest, digest_value, IMA_DIGEST_SIZE);
+		rc = memcmp(qe->entry->digest, digest_value, TPM_DIGEST_SIZE);
 		if (rc == 0) {
 			ret = qe;
 			break;
@@ -106,7 +106,7 @@ static int ima_pcr_extend(const u8 *hash)
 int ima_add_template_entry(struct ima_template_entry *entry, int violation,
 			   const char *op, struct inode *inode)
 {
-	u8 digest[IMA_DIGEST_SIZE];
+	u8 digest[TPM_DIGEST_SIZE];
 	const char *audit_cause = "hash_added";
 	char tpm_audit_cause[AUDIT_CAUSE_LEN_MAX];
 	int audit_info = 1;
-- 
cgit v1.2.3


From 723326b927b675daf4223fe31d7428eca68f194b Mon Sep 17 00:00:00 2001
From: Dmitry Kasatkin <d.kasatkin@samsung.com>
Date: Thu, 4 Jul 2013 17:40:01 +0300
Subject: ima: provide dedicated hash algo allocation function

This patch provides dedicated hash algo allocation and
deallocation function which can be used by different clients.

Signed-off-by: Dmitry Kasatkin <d.kasatkin@samsung.com>
Signed-off-by: Mimi Zohar <zohar@linux.vnet.ibm.com>
---
 security/integrity/ima/ima_crypto.c | 43 +++++++++++++++++++++++++------------
 1 file changed, 29 insertions(+), 14 deletions(-)

(limited to 'security')

diff --git a/security/integrity/ima/ima_crypto.c b/security/integrity/ima/ima_crypto.c
index 872c6698067c..e5d3ebf18436 100644
--- a/security/integrity/ima/ima_crypto.c
+++ b/security/integrity/ima/ima_crypto.c
@@ -39,6 +39,28 @@ int ima_init_crypto(void)
 	return 0;
 }
 
+static struct crypto_shash *ima_alloc_tfm(enum hash_algo algo)
+{
+	struct crypto_shash *tfm = ima_shash_tfm;
+	int rc;
+
+	if (algo != ima_hash_algo && algo < HASH_ALGO__LAST) {
+		tfm = crypto_alloc_shash(hash_algo_name[algo], 0, 0);
+		if (IS_ERR(tfm)) {
+			rc = PTR_ERR(tfm);
+			pr_err("Can not allocate %s (reason: %d)\n",
+			       hash_algo_name[algo], rc);
+		}
+	}
+	return tfm;
+}
+
+static void ima_free_tfm(struct crypto_shash *tfm)
+{
+	if (tfm != ima_shash_tfm)
+		crypto_free_shash(tfm);
+}
+
 /*
  * Calculate the MD5/SHA1 file digest
  */
@@ -57,6 +79,8 @@ static int ima_calc_file_hash_tfm(struct file *file,
 	desc.shash.tfm = tfm;
 	desc.shash.flags = 0;
 
+	hash->length = crypto_shash_digestsize(tfm);
+
 	rc = crypto_shash_init(&desc.shash);
 	if (rc != 0)
 		return rc;
@@ -98,25 +122,16 @@ out:
 
 int ima_calc_file_hash(struct file *file, struct ima_digest_data *hash)
 {
-	struct crypto_shash *tfm = ima_shash_tfm;
+	struct crypto_shash *tfm;
 	int rc;
 
-	if (hash->algo != ima_hash_algo && hash->algo < HASH_ALGO__LAST) {
-		tfm = crypto_alloc_shash(hash_algo_name[hash->algo], 0, 0);
-		if (IS_ERR(tfm)) {
-			rc = PTR_ERR(tfm);
-			pr_err("Can not allocate %s (reason: %d)\n",
-			       hash_algo_name[hash->algo], rc);
-			return rc;
-		}
-	}
-
-	hash->length = crypto_shash_digestsize(tfm);
+	tfm = ima_alloc_tfm(hash->algo);
+	if (IS_ERR(tfm))
+		return PTR_ERR(tfm);
 
 	rc = ima_calc_file_hash_tfm(file, hash, tfm);
 
-	if (tfm != ima_shash_tfm)
-		crypto_free_shash(tfm);
+	ima_free_tfm(tfm);
 
 	return rc;
 }
-- 
cgit v1.2.3


From ea593993d361748e795f5eb783a5fb5144fb2df9 Mon Sep 17 00:00:00 2001
From: Dmitry Kasatkin <d.kasatkin@samsung.com>
Date: Fri, 7 Jun 2013 12:16:24 +0200
Subject: ima: support arbitrary hash algorithms in ima_calc_buffer_hash

ima_calc_buffer_hash will be used with different hash algorithms.
This patch provides support for arbitrary hash algorithms in
ima_calc_buffer_hash.

Signed-off-by: Dmitry Kasatkin <d.kasatkin@samsung.com>
Signed-off-by: Mimi Zohar <zohar@linux.vnet.ibm.com>
---
 security/integrity/ima/ima_api.c    |  3 +++
 security/integrity/ima/ima_crypto.c | 28 ++++++++++++++++++++++------
 2 files changed, 25 insertions(+), 6 deletions(-)

(limited to 'security')

diff --git a/security/integrity/ima/ima_api.c b/security/integrity/ima/ima_api.c
index 2cc5dcc6bdeb..bc1d1282a06f 100644
--- a/security/integrity/ima/ima_api.c
+++ b/security/integrity/ima/ima_api.c
@@ -18,6 +18,7 @@
 #include <linux/fs.h>
 #include <linux/xattr.h>
 #include <linux/evm.h>
+#include <crypto/hash_info.h>
 #include "ima.h"
 
 static const char *IMA_TEMPLATE_NAME = "ima";
@@ -54,6 +55,8 @@ int ima_store_template(struct ima_template_entry *entry,
 	entry->template_len = sizeof(entry->template);
 
 	if (!violation) {
+		/* this function uses default algo */
+		hash.hdr.algo = HASH_ALGO_SHA1;
 		result = ima_calc_buffer_hash(&entry->template,
 					      entry->template_len, &hash.hdr);
 		if (result < 0) {
diff --git a/security/integrity/ima/ima_crypto.c b/security/integrity/ima/ima_crypto.c
index e5d3ebf18436..e2be2524a372 100644
--- a/security/integrity/ima/ima_crypto.c
+++ b/security/integrity/ima/ima_crypto.c
@@ -139,23 +139,39 @@ int ima_calc_file_hash(struct file *file, struct ima_digest_data *hash)
 /*
  * Calculate the hash of a given buffer
  */
-int ima_calc_buffer_hash(const void *buf, int len, struct ima_digest_data *hash)
+static int ima_calc_buffer_hash_tfm(const void *buf, int len,
+				    struct ima_digest_data *hash,
+				    struct crypto_shash *tfm)
 {
 	struct {
 		struct shash_desc shash;
-		char ctx[crypto_shash_descsize(ima_shash_tfm)];
+		char ctx[crypto_shash_descsize(tfm)];
 	} desc;
 
-	desc.shash.tfm = ima_shash_tfm;
+	desc.shash.tfm = tfm;
 	desc.shash.flags = 0;
 
-	/* this function uses default algo */
-	hash->algo = ima_hash_algo;
-	hash->length = crypto_shash_digestsize(ima_shash_tfm);
+	hash->length = crypto_shash_digestsize(tfm);
 
 	return crypto_shash_digest(&desc.shash, buf, len, hash->digest);
 }
 
+int ima_calc_buffer_hash(const void *buf, int len, struct ima_digest_data *hash)
+{
+	struct crypto_shash *tfm;
+	int rc;
+
+	tfm = ima_alloc_tfm(hash->algo);
+	if (IS_ERR(tfm))
+		return PTR_ERR(tfm);
+
+	rc = ima_calc_buffer_hash_tfm(buf, len, hash, tfm);
+
+	ima_free_tfm(tfm);
+
+	return rc;
+}
+
 static void __init ima_pcrread(int idx, u8 *pcr)
 {
 	if (!ima_used_chip)
-- 
cgit v1.2.3


From 09ef54359c4ad49c01a12503b2c510b424ecf059 Mon Sep 17 00:00:00 2001
From: Dmitry Kasatkin <d.kasatkin@samsung.com>
Date: Fri, 7 Jun 2013 12:16:25 +0200
Subject: ima: ima_calc_boot_agregate must use SHA1

With multiple hash algorithms, ima_hash_tfm is no longer guaranteed to be sha1.
Need to force to use sha1.

Changelog:
- pass ima_digest_data to ima_calc_boot_aggregate() instead of char *
  (Roberto Sassu);
- create an ima_digest_data structure in ima_add_boot_aggregate()
  (Roberto Sassu);
- pass hash->algo to ima_alloc_tfm() (Roberto Sassu, reported by Dmitry).
- "move hash definition in ima_add_boot_aggregate()" commit hunk to here.
- sparse warning fix - Fengguang Wu

Signed-off-by: Dmitry Kasatkin <d.kasatkin@samsung.com>
Signed-off-by: Roberto Sassu <roberto.sassu@polito.it>
Signed-off-by: Mimi Zohar <zohar@linux.vnet.ibm.com>
---
 security/integrity/ima/ima.h        |  2 +-
 security/integrity/ima/ima_crypto.c | 24 +++++++++++++++++++++---
 security/integrity/ima/ima_init.c   | 10 +++++++++-
 3 files changed, 31 insertions(+), 5 deletions(-)

(limited to 'security')

diff --git a/security/integrity/ima/ima.h b/security/integrity/ima/ima.h
index 52393edfbfd9..e0e1cde6e674 100644
--- a/security/integrity/ima/ima.h
+++ b/security/integrity/ima/ima.h
@@ -73,7 +73,7 @@ int ima_add_template_entry(struct ima_template_entry *entry, int violation,
 int ima_calc_file_hash(struct file *file, struct ima_digest_data *hash);
 int ima_calc_buffer_hash(const void *data, int len,
 			 struct ima_digest_data *hash);
-int ima_calc_boot_aggregate(char *digest);
+int __init ima_calc_boot_aggregate(struct ima_digest_data *hash);
 void ima_add_violation(struct inode *inode, const unsigned char *filename,
 		       const char *op, const char *cause);
 int ima_init_crypto(void);
diff --git a/security/integrity/ima/ima_crypto.c b/security/integrity/ima/ima_crypto.c
index e2be2524a372..22be23f13b3d 100644
--- a/security/integrity/ima/ima_crypto.c
+++ b/security/integrity/ima/ima_crypto.c
@@ -184,16 +184,17 @@ static void __init ima_pcrread(int idx, u8 *pcr)
 /*
  * Calculate the boot aggregate hash
  */
-int __init ima_calc_boot_aggregate(char *digest)
+static int __init ima_calc_boot_aggregate_tfm(char *digest,
+					      struct crypto_shash *tfm)
 {
 	u8 pcr_i[TPM_DIGEST_SIZE];
 	int rc, i;
 	struct {
 		struct shash_desc shash;
-		char ctx[crypto_shash_descsize(ima_shash_tfm)];
+		char ctx[crypto_shash_descsize(tfm)];
 	} desc;
 
-	desc.shash.tfm = ima_shash_tfm;
+	desc.shash.tfm = tfm;
 	desc.shash.flags = 0;
 
 	rc = crypto_shash_init(&desc.shash);
@@ -210,3 +211,20 @@ int __init ima_calc_boot_aggregate(char *digest)
 		crypto_shash_final(&desc.shash, digest);
 	return rc;
 }
+
+int __init ima_calc_boot_aggregate(struct ima_digest_data *hash)
+{
+	struct crypto_shash *tfm;
+	int rc;
+
+	tfm = ima_alloc_tfm(hash->algo);
+	if (IS_ERR(tfm))
+		return PTR_ERR(tfm);
+
+	hash->length = crypto_shash_digestsize(tfm);
+	rc = ima_calc_boot_aggregate_tfm(hash->digest, tfm);
+
+	ima_free_tfm(tfm);
+
+	return rc;
+}
diff --git a/security/integrity/ima/ima_init.c b/security/integrity/ima/ima_init.c
index 9d0243c10558..77cd5005f2db 100644
--- a/security/integrity/ima/ima_init.c
+++ b/security/integrity/ima/ima_init.c
@@ -18,6 +18,7 @@
 #include <linux/scatterlist.h>
 #include <linux/slab.h>
 #include <linux/err.h>
+#include <crypto/hash_info.h>
 #include "ima.h"
 
 /* name for boot aggregate entry */
@@ -46,6 +47,10 @@ static void __init ima_add_boot_aggregate(void)
 	const char *audit_cause = "ENOMEM";
 	int result = -ENOMEM;
 	int violation = 1;
+	struct {
+		struct ima_digest_data hdr;
+		char digest[TPM_DIGEST_SIZE];
+	} hash;
 
 	entry = kmalloc(sizeof(*entry), GFP_KERNEL);
 	if (!entry)
@@ -56,12 +61,15 @@ static void __init ima_add_boot_aggregate(void)
 		IMA_EVENT_NAME_LEN_MAX);
 	if (ima_used_chip) {
 		violation = 0;
-		result = ima_calc_boot_aggregate(entry->template.digest);
+		hash.hdr.algo = HASH_ALGO_SHA1;
+		result = ima_calc_boot_aggregate(&hash.hdr);
 		if (result < 0) {
 			audit_cause = "hashing_error";
 			kfree(entry);
 			goto err_out;
 		}
+		memcpy(entry->template.digest, hash.hdr.digest,
+		       hash.hdr.length);
 	}
 	result = ima_store_template(entry, violation, NULL);
 	if (result < 0)
-- 
cgit v1.2.3


From 7d802a227b7f26c89f13dab09767e6b0aebd9c9f Mon Sep 17 00:00:00 2001
From: Roberto Sassu <roberto.sassu@polito.it>
Date: Fri, 7 Jun 2013 12:16:26 +0200
Subject: ima: pass the file descriptor to ima_add_violation()

Pass the file descriptor instead of the inode to ima_add_violation(),
to make the latter consistent with ima_store_measurement() in
preparation for the new template architecture.

Signed-off-by: Roberto Sassu <roberto.sassu@polito.it>
Signed-off-by: Mimi Zohar <zohar@linux.vnet.ibm.com>
---
 security/integrity/ima/ima.h      | 2 +-
 security/integrity/ima/ima_api.c  | 3 ++-
 security/integrity/ima/ima_main.c | 5 ++---
 3 files changed, 5 insertions(+), 5 deletions(-)

(limited to 'security')

diff --git a/security/integrity/ima/ima.h b/security/integrity/ima/ima.h
index e0e1cde6e674..d7bec6f37b61 100644
--- a/security/integrity/ima/ima.h
+++ b/security/integrity/ima/ima.h
@@ -74,7 +74,7 @@ int ima_calc_file_hash(struct file *file, struct ima_digest_data *hash);
 int ima_calc_buffer_hash(const void *data, int len,
 			 struct ima_digest_data *hash);
 int __init ima_calc_boot_aggregate(struct ima_digest_data *hash);
-void ima_add_violation(struct inode *inode, const unsigned char *filename,
+void ima_add_violation(struct file *file, const unsigned char *filename,
 		       const char *op, const char *cause);
 int ima_init_crypto(void);
 
diff --git a/security/integrity/ima/ima_api.c b/security/integrity/ima/ima_api.c
index bc1d1282a06f..98160a3259fe 100644
--- a/security/integrity/ima/ima_api.c
+++ b/security/integrity/ima/ima_api.c
@@ -78,10 +78,11 @@ int ima_store_template(struct ima_template_entry *entry,
  * By extending the PCR with 0xFF's instead of with zeroes, the PCR
  * value is invalidated.
  */
-void ima_add_violation(struct inode *inode, const unsigned char *filename,
+void ima_add_violation(struct file *file, const unsigned char *filename,
 		       const char *op, const char *cause)
 {
 	struct ima_template_entry *entry;
+	struct inode *inode = file->f_dentry->d_inode;
 	int violation = 1;
 	int result;
 
diff --git a/security/integrity/ima/ima_main.c b/security/integrity/ima/ima_main.c
index 95b5df2c6501..5e8b1f7becd2 100644
--- a/security/integrity/ima/ima_main.c
+++ b/security/integrity/ima/ima_main.c
@@ -94,10 +94,9 @@ out:
 		pathname = dentry->d_name.name;
 
 	if (send_tomtou)
-		ima_add_violation(inode, pathname,
-				  "invalid_pcr", "ToMToU");
+		ima_add_violation(file, pathname, "invalid_pcr", "ToMToU");
 	if (send_writers)
-		ima_add_violation(inode, pathname,
+		ima_add_violation(file, pathname,
 				  "invalid_pcr", "open_writers");
 	kfree(pathbuf);
 }
-- 
cgit v1.2.3


From 9803d413f41db86fdf0097f1af781fe2e68f474c Mon Sep 17 00:00:00 2001
From: Roberto Sassu <roberto.sassu@polito.it>
Date: Fri, 7 Jun 2013 12:16:27 +0200
Subject: ima: pass the filename argument up to ima_add_template_entry()

Pass the filename argument to ima_add_template_entry() in order to
eliminate a dependency on template specific data (third argument of
integrity_audit_msg).

This change is required because, with the new template management
mechanism, the generation of a new measurement entry will be performed
by new specific functions (introduced in next patches) and the current IMA
code will not be aware anymore of how data is stored in the entry payload.

Signed-off-by: Roberto Sassu <roberto.sassu@polito.it>
Signed-off-by: Mimi Zohar <zohar@linux.vnet.ibm.com>
---
 security/integrity/ima/ima.h       | 5 +++--
 security/integrity/ima/ima_api.c   | 9 +++++----
 security/integrity/ima/ima_init.c  | 3 ++-
 security/integrity/ima/ima_queue.c | 6 +++---
 4 files changed, 13 insertions(+), 10 deletions(-)

(limited to 'security')

diff --git a/security/integrity/ima/ima.h b/security/integrity/ima/ima.h
index d7bec6f37b61..27d2ffbd0763 100644
--- a/security/integrity/ima/ima.h
+++ b/security/integrity/ima/ima.h
@@ -69,7 +69,8 @@ int ima_fs_init(void);
 void ima_fs_cleanup(void);
 int ima_inode_alloc(struct inode *inode);
 int ima_add_template_entry(struct ima_template_entry *entry, int violation,
-			   const char *op, struct inode *inode);
+			   const char *op, struct inode *inode,
+			   const unsigned char *filename);
 int ima_calc_file_hash(struct file *file, struct ima_digest_data *hash);
 int ima_calc_buffer_hash(const void *data, int len,
 			 struct ima_digest_data *hash);
@@ -107,7 +108,7 @@ void ima_store_measurement(struct integrity_iint_cache *iint, struct file *file,
 void ima_audit_measurement(struct integrity_iint_cache *iint,
 			   const unsigned char *filename);
 int ima_store_template(struct ima_template_entry *entry, int violation,
-		       struct inode *inode);
+		       struct inode *inode, const unsigned char *filename);
 void ima_template_show(struct seq_file *m, void *e, enum ima_show_type show);
 const char *ima_d_path(struct path *path, char **pathbuf);
 
diff --git a/security/integrity/ima/ima_api.c b/security/integrity/ima/ima_api.c
index 98160a3259fe..a0fe5041310a 100644
--- a/security/integrity/ima/ima_api.c
+++ b/security/integrity/ima/ima_api.c
@@ -40,7 +40,8 @@ static const char *IMA_TEMPLATE_NAME = "ima";
  * Returns 0 on success, error code otherwise
  */
 int ima_store_template(struct ima_template_entry *entry,
-		       int violation, struct inode *inode)
+		       int violation, struct inode *inode,
+		       const unsigned char *filename)
 {
 	const char *op = "add_template_measure";
 	const char *audit_cause = "hashing_error";
@@ -67,7 +68,7 @@ int ima_store_template(struct ima_template_entry *entry,
 		}
 		memcpy(entry->digest, hash.hdr.digest, hash.hdr.length);
 	}
-	result = ima_add_template_entry(entry, violation, op, inode);
+	result = ima_add_template_entry(entry, violation, op, inode, filename);
 	return result;
 }
 
@@ -96,7 +97,7 @@ void ima_add_violation(struct file *file, const unsigned char *filename,
 	}
 	memset(&entry->template, 0, sizeof(entry->template));
 	strncpy(entry->template.file_name, filename, IMA_EVENT_NAME_LEN_MAX);
-	result = ima_store_template(entry, violation, inode);
+	result = ima_store_template(entry, violation, inode, filename);
 	if (result < 0)
 		kfree(entry);
 err_out:
@@ -248,7 +249,7 @@ void ima_store_measurement(struct integrity_iint_cache *iint,
 	       (strlen(filename) > IMA_EVENT_NAME_LEN_MAX) ?
 	       file->f_dentry->d_name.name : filename);
 
-	result = ima_store_template(entry, violation, inode);
+	result = ima_store_template(entry, violation, inode, filename);
 	if (!result || result == -EEXIST)
 		iint->flags |= IMA_MEASURED;
 	if (result < 0)
diff --git a/security/integrity/ima/ima_init.c b/security/integrity/ima/ima_init.c
index 77cd5005f2db..d42fac308aaa 100644
--- a/security/integrity/ima/ima_init.c
+++ b/security/integrity/ima/ima_init.c
@@ -71,7 +71,8 @@ static void __init ima_add_boot_aggregate(void)
 		memcpy(entry->template.digest, hash.hdr.digest,
 		       hash.hdr.length);
 	}
-	result = ima_store_template(entry, violation, NULL);
+	result = ima_store_template(entry, violation, NULL,
+				    boot_aggregate_name);
 	if (result < 0)
 		kfree(entry);
 	return;
diff --git a/security/integrity/ima/ima_queue.c b/security/integrity/ima/ima_queue.c
index e63ff3369f10..d85e99761f4f 100644
--- a/security/integrity/ima/ima_queue.c
+++ b/security/integrity/ima/ima_queue.c
@@ -104,7 +104,8 @@ static int ima_pcr_extend(const u8 *hash)
  * and extend the pcr.
  */
 int ima_add_template_entry(struct ima_template_entry *entry, int violation,
-			   const char *op, struct inode *inode)
+			   const char *op, struct inode *inode,
+			   const unsigned char *filename)
 {
 	u8 digest[TPM_DIGEST_SIZE];
 	const char *audit_cause = "hash_added";
@@ -141,8 +142,7 @@ int ima_add_template_entry(struct ima_template_entry *entry, int violation,
 	}
 out:
 	mutex_unlock(&ima_extend_list_mutex);
-	integrity_audit_msg(AUDIT_INTEGRITY_PCR, inode,
-			    entry->template.file_name,
+	integrity_audit_msg(AUDIT_INTEGRITY_PCR, inode, filename,
 			    op, audit_cause, result, audit_info);
 	return result;
 }
-- 
cgit v1.2.3


From 7bc5f447ce9d01e19394b5399bf1a4fcebf0f8dd Mon Sep 17 00:00:00 2001
From: Roberto Sassu <roberto.sassu@polito.it>
Date: Fri, 7 Jun 2013 12:16:28 +0200
Subject: ima: define new function ima_alloc_init_template() to API

Instead of allocating and initializing the template entry from multiple
places (eg. boot aggregate, violation, and regular measurements), this
patch defines a new function called ima_alloc_init_template().  The new
function allocates and initializes the measurement entry with the inode
digest and the filename.

In respect to the current behavior, it truncates the file name passed
in the 'filename' argument if the latter's size is greater than 255 bytes
and the passed file descriptor is NULL.

Changelog:
- initialize 'hash' variable for non TPM case - Mimi
- conform to expectation for 'iint' to be defined as a pointer. - Mimi
- add missing 'file' dependency for recalculating file hash. - Mimi

Signed-off-by: Roberto Sassu <roberto.sassu@polito.it>
Signed-off-by: Mimi Zohar <zohar@linux.vnet.ibm.com>
---
 security/integrity/ima/ima.h      |  3 ++
 security/integrity/ima/ima_api.c  | 88 ++++++++++++++++++++++++++-------------
 security/integrity/ima/ima_init.c | 24 ++++++-----
 3 files changed, 76 insertions(+), 39 deletions(-)

(limited to 'security')

diff --git a/security/integrity/ima/ima.h b/security/integrity/ima/ima.h
index 27d2ffbd0763..da03d3389619 100644
--- a/security/integrity/ima/ima.h
+++ b/security/integrity/ima/ima.h
@@ -107,6 +107,9 @@ void ima_store_measurement(struct integrity_iint_cache *iint, struct file *file,
 			   const unsigned char *filename);
 void ima_audit_measurement(struct integrity_iint_cache *iint,
 			   const unsigned char *filename);
+int ima_alloc_init_template(struct integrity_iint_cache *iint,
+			    struct file *file, const unsigned char *filename,
+			    struct ima_template_entry **entry);
 int ima_store_template(struct ima_template_entry *entry, int violation,
 		       struct inode *inode, const unsigned char *filename);
 void ima_template_show(struct seq_file *m, void *e, enum ima_show_type show);
diff --git a/security/integrity/ima/ima_api.c b/security/integrity/ima/ima_api.c
index a0fe5041310a..29dd43de823a 100644
--- a/security/integrity/ima/ima_api.c
+++ b/security/integrity/ima/ima_api.c
@@ -23,6 +23,62 @@
 
 static const char *IMA_TEMPLATE_NAME = "ima";
 
+/*
+ * ima_alloc_init_template - create and initialize a new template entry
+ */
+int ima_alloc_init_template(struct integrity_iint_cache *iint,
+			    struct file *file, const unsigned char *filename,
+			    struct ima_template_entry **entry)
+{
+	struct ima_template_entry *e;
+	int result = 0;
+
+	e = kzalloc(sizeof(**entry), GFP_NOFS);
+	if (!e)
+		return -ENOMEM;
+
+	memset(&(e)->template, 0, sizeof(e->template));
+	if (!iint)		/* IMA measurement violation entry */
+		goto out;
+
+	if (iint->ima_hash->algo != ima_hash_algo) {
+		struct inode *inode;
+		struct {
+			struct ima_digest_data hdr;
+			char digest[IMA_MAX_DIGEST_SIZE];
+		} hash;
+
+		if (!file) {
+			result = -EINVAL;
+			goto out_free;
+		}
+
+		inode = file_inode(file);
+		hash.hdr.algo = ima_hash_algo;
+		hash.hdr.length = SHA1_DIGEST_SIZE;
+		result = ima_calc_file_hash(file, &hash.hdr);
+		if (result) {
+			integrity_audit_msg(AUDIT_INTEGRITY_DATA, inode,
+					    filename, "collect_data",
+					    "failed", result, 0);
+			goto out_free;
+		} else
+			memcpy(e->template.digest, hash.hdr.digest,
+			       hash.hdr.length);
+	} else
+		memcpy(e->template.digest, iint->ima_hash->digest,
+		       iint->ima_hash->length);
+out:
+	strcpy(e->template.file_name,
+	       (strlen(filename) > IMA_EVENT_NAME_LEN_MAX && file != NULL) ?
+	       file->f_dentry->d_name.name : filename);
+	*entry = e;
+	return 0;
+out_free:
+	kfree(e);
+	return result;
+}
+
 /*
  * ima_store_template - store ima template measurements
  *
@@ -90,13 +146,11 @@ void ima_add_violation(struct file *file, const unsigned char *filename,
 	/* can overflow, only indicator */
 	atomic_long_inc(&ima_htable.violations);
 
-	entry = kmalloc(sizeof(*entry), GFP_KERNEL);
-	if (!entry) {
+	result = ima_alloc_init_template(NULL, file, filename, &entry);
+	if (result < 0) {
 		result = -ENOMEM;
 		goto err_out;
 	}
-	memset(&entry->template, 0, sizeof(entry->template));
-	strncpy(entry->template.file_name, filename, IMA_EVENT_NAME_LEN_MAX);
 	result = ima_store_template(entry, violation, inode, filename);
 	if (result < 0)
 		kfree(entry);
@@ -220,34 +274,12 @@ void ima_store_measurement(struct integrity_iint_cache *iint,
 	if (iint->flags & IMA_MEASURED)
 		return;
 
-	entry = kmalloc(sizeof(*entry), GFP_KERNEL);
-	if (!entry) {
+	result = ima_alloc_init_template(iint, file, filename, &entry);
+	if (result < 0) {
 		integrity_audit_msg(AUDIT_INTEGRITY_PCR, inode, filename,
 				    op, audit_cause, result, 0);
 		return;
 	}
-	memset(&entry->template, 0, sizeof(entry->template));
-	if (iint->ima_hash->algo != ima_hash_algo) {
-		struct {
-			struct ima_digest_data hdr;
-			char digest[IMA_MAX_DIGEST_SIZE];
-		} hash;
-
-		hash.hdr.algo = ima_hash_algo;
-		result = ima_calc_file_hash(file, &hash.hdr);
-		if (result)
-			integrity_audit_msg(AUDIT_INTEGRITY_DATA, inode,
-					    filename, "collect_data", "failed",
-					    result, 0);
-		else
-			memcpy(entry->template.digest, hash.hdr.digest,
-			       hash.hdr.length);
-	} else
-		memcpy(entry->template.digest, iint->ima_hash->digest,
-		       iint->ima_hash->length);
-	strcpy(entry->template.file_name,
-	       (strlen(filename) > IMA_EVENT_NAME_LEN_MAX) ?
-	       file->f_dentry->d_name.name : filename);
 
 	result = ima_store_template(entry, violation, inode, filename);
 	if (!result || result == -EEXIST)
diff --git a/security/integrity/ima/ima_init.c b/security/integrity/ima/ima_init.c
index d42fac308aaa..50e15e6336c4 100644
--- a/security/integrity/ima/ima_init.c
+++ b/security/integrity/ima/ima_init.c
@@ -43,34 +43,36 @@ int ima_used_chip;
 static void __init ima_add_boot_aggregate(void)
 {
 	struct ima_template_entry *entry;
+	struct integrity_iint_cache tmp_iint, *iint = &tmp_iint;
 	const char *op = "add_boot_aggregate";
 	const char *audit_cause = "ENOMEM";
 	int result = -ENOMEM;
-	int violation = 1;
+	int violation = 0;
 	struct {
 		struct ima_digest_data hdr;
 		char digest[TPM_DIGEST_SIZE];
 	} hash;
 
-	entry = kmalloc(sizeof(*entry), GFP_KERNEL);
-	if (!entry)
-		goto err_out;
+	memset(iint, 0, sizeof(*iint));
+	memset(&hash, 0, sizeof(hash));
+	iint->ima_hash = &hash.hdr;
+	iint->ima_hash->algo = HASH_ALGO_SHA1;
+	iint->ima_hash->length = SHA1_DIGEST_SIZE;
 
-	memset(&entry->template, 0, sizeof(entry->template));
-	strncpy(entry->template.file_name, boot_aggregate_name,
-		IMA_EVENT_NAME_LEN_MAX);
 	if (ima_used_chip) {
-		violation = 0;
-		hash.hdr.algo = HASH_ALGO_SHA1;
 		result = ima_calc_boot_aggregate(&hash.hdr);
 		if (result < 0) {
 			audit_cause = "hashing_error";
 			kfree(entry);
 			goto err_out;
 		}
-		memcpy(entry->template.digest, hash.hdr.digest,
-		       hash.hdr.length);
 	}
+
+	result = ima_alloc_init_template(iint, NULL, boot_aggregate_name,
+					 &entry);
+	if (result < 0)
+		return;
+
 	result = ima_store_template(entry, violation, NULL,
 				    boot_aggregate_name);
 	if (result < 0)
-- 
cgit v1.2.3


From adf53a778a0a5a5dc9103509da4a9719046e5310 Mon Sep 17 00:00:00 2001
From: Roberto Sassu <roberto.sassu@polito.it>
Date: Fri, 7 Jun 2013 12:16:29 +0200
Subject: ima: new templates management mechanism
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The original 'ima' template is fixed length, containing the filedata hash
and pathname.  The filedata hash is limited to 20 bytes (md5/sha1).  The
pathname is a null terminated string, limited to 255 characters.  To
overcome these limitations and to add additional file metadata, it is
necessary to extend the current version of IMA by defining additional
templates.

The main reason to introduce this feature is that, each time a new
template is defined, the functions that generate and display the
measurement list would include the code for handling a new format and,
thus, would significantly grow over time.

This patch set solves this problem by separating the template management
from the remaining IMA code. The core of this solution is the definition
of two new data structures: a template descriptor, to determine which
information should be included in the measurement list, and a template
field, to generate and display data of a given type.

To define a new template field, developers define the field identifier
and implement two functions, init() and show(), respectively to generate
and display measurement entries.  Initially, this patch set defines the
following template fields (support for additional data types will be
added later):
 - 'd': the digest of the event (i.e. the digest of a measured file),
        calculated with the SHA1 or MD5 hash algorithm;
 - 'n': the name of the event (i.e. the file name), with size up to
        255 bytes;
 - 'd-ng': the digest of the event, calculated with an arbitrary hash
           algorithm (field format: [<hash algo>:]digest, where the digest
           prefix is shown only if the hash algorithm is not SHA1 or MD5);
 - 'n-ng': the name of the event, without size limitations.

Defining a new template descriptor requires specifying the template format,
a string of field identifiers separated by the '|' character.  This patch
set defines the following template descriptors:
 - "ima": its format is 'd|n';
 - "ima-ng" (default): its format is 'd-ng|n-ng'

Further details about the new template architecture can be found in
Documentation/security/IMA-templates.txt.

Changelog:
- don't defer calling ima_init_template() - Mimi
- don't define ima_lookup_template_desc() until used - Mimi
- squashed with documentation patch - Mimi

Signed-off-by: Roberto Sassu <roberto.sassu@polito.it>
Signed-off-by: Mimi Zohar <zohar@linux.vnet.ibm.com>
---
 Documentation/security/00-INDEX          |   2 +
 Documentation/security/IMA-templates.txt |  87 ++++++++++++++++++++++++
 security/integrity/ima/Makefile          |   2 +-
 security/integrity/ima/ima.h             |  29 ++++++++
 security/integrity/ima/ima_init.c        |   4 ++
 security/integrity/ima/ima_template.c    | 112 +++++++++++++++++++++++++++++++
 6 files changed, 235 insertions(+), 1 deletion(-)
 create mode 100644 Documentation/security/IMA-templates.txt
 create mode 100644 security/integrity/ima/ima_template.c

(limited to 'security')

diff --git a/Documentation/security/00-INDEX b/Documentation/security/00-INDEX
index 414235c1fcfc..45c82fd3e9d3 100644
--- a/Documentation/security/00-INDEX
+++ b/Documentation/security/00-INDEX
@@ -22,3 +22,5 @@ keys.txt
 	- description of the kernel key retention service.
 tomoyo.txt
 	- documentation on the TOMOYO Linux Security Module.
+IMA-templates.txt
+	- documentation on the template management mechanism for IMA.
diff --git a/Documentation/security/IMA-templates.txt b/Documentation/security/IMA-templates.txt
new file mode 100644
index 000000000000..a777e5f1df5b
--- /dev/null
+++ b/Documentation/security/IMA-templates.txt
@@ -0,0 +1,87 @@
+                       IMA Template Management Mechanism
+
+
+==== INTRODUCTION ====
+
+The original 'ima' template is fixed length, containing the filedata hash
+and pathname. The filedata hash is limited to 20 bytes (md5/sha1).
+The pathname is a null terminated string, limited to 255 characters.
+To overcome these limitations and to add additional file metadata, it is
+necessary to extend the current version of IMA by defining additional
+templates. For example, information that could be possibly reported are
+the inode UID/GID or the LSM labels either of the inode and of the process
+that is accessing it.
+
+However, the main problem to introduce this feature is that, each time
+a new template is defined, the functions that generate and display
+the measurements list would include the code for handling a new format
+and, thus, would significantly grow over the time.
+
+The proposed solution solves this problem by separating the template
+management from the remaining IMA code. The core of this solution is the
+definition of two new data structures: a template descriptor, to determine
+which information should be included in the measurement list; a template
+field, to generate and display data of a given type.
+
+Managing templates with these structures is very simple. To support
+a new data type, developers define the field identifier and implement
+two functions, init() and show(), respectively to generate and display
+measurement entries. Defining a new template descriptor requires
+specifying the template format, a string of field identifiers separated
+by the '|' character. While in the current implementation it is possible
+to define new template descriptors only by adding their definition in the
+template specific code (ima_template.c), in a future version it will be
+possible to register a new template on a running kernel by supplying to IMA
+the desired format string. In this version, IMA initializes at boot time
+all defined template descriptors by translating the format into an array
+of template fields structures taken from the set of the supported ones.
+
+After the initialization step, IMA will call ima_alloc_init_template()
+(new function defined within the patches for the new template management
+mechanism) to generate a new measurement entry by using the template
+descriptor chosen through the kernel configuration or through the newly
+introduced 'ima_template=' kernel command line parameter. It is during this
+phase that the advantages of the new architecture are clearly shown:
+the latter function will not contain specific code to handle a given template
+but, instead, it simply calls the init() method of the template fields
+associated to the chosen template descriptor and store the result (pointer
+to allocated data and data length) in the measurement entry structure.
+
+The same mechanism is employed to display measurements entries.
+The functions ima[_ascii]_measurements_show() retrieve, for each entry,
+the template descriptor used to produce that entry and call the show()
+method for each item of the array of template fields structures.
+
+
+
+==== SUPPORTED TEMPLATE FIELDS AND DESCRIPTORS ====
+
+In the following, there is the list of supported template fields
+('<identifier>': description), that can be used to define new template
+descriptors by adding their identifier to the format string
+(support for more data types will be added later):
+
+ - 'd': the digest of the event (i.e. the digest of a measured file),
+        calculated with the SHA1 or MD5 hash algorithm;
+ - 'n': the name of the event (i.e. the file name), with size up to 255 bytes;
+ - 'd-ng': the digest of the event, calculated with an arbitrary hash
+           algorithm (field format: [<hash algo>:]digest, where the digest
+           prefix is shown only if the hash algorithm is not SHA1 or MD5);
+ - 'n-ng': the name of the event, without size limitations.
+
+
+Below, there is the list of defined template descriptors:
+ - "ima": its format is 'd|n';
+ - "ima-ng" (default): its format is 'd-ng|n-ng'.
+
+
+
+==== USE ====
+
+To specify the template descriptor to be used to generate measurement entries,
+currently the following methods are supported:
+
+ - select a template descriptor among those supported in the kernel
+   configuration ('ima-ng' is the default choice);
+ - specify a template descriptor name from the kernel command line through
+   the 'ima_template=' parameter.
diff --git a/security/integrity/ima/Makefile b/security/integrity/ima/Makefile
index 56dfee7cbf61..7fe4ae37dbea 100644
--- a/security/integrity/ima/Makefile
+++ b/security/integrity/ima/Makefile
@@ -6,5 +6,5 @@
 obj-$(CONFIG_IMA) += ima.o
 
 ima-y := ima_fs.o ima_queue.o ima_init.o ima_main.o ima_crypto.o ima_api.o \
-	 ima_policy.o
+	 ima_policy.o ima_template.o
 ima-$(CONFIG_IMA_APPRAISE) += ima_appraise.o
diff --git a/security/integrity/ima/ima.h b/security/integrity/ima/ima.h
index da03d3389619..c85718f1f623 100644
--- a/security/integrity/ima/ima.h
+++ b/security/integrity/ima/ima.h
@@ -36,12 +36,39 @@ enum tpm_pcrs { TPM_PCR0 = 0, TPM_PCR8 = 8 };
 #define IMA_HASH_BITS 9
 #define IMA_MEASURE_HTABLE_SIZE (1 << IMA_HASH_BITS)
 
+#define IMA_TEMPLATE_FIELD_ID_MAX_LEN	16
+#define IMA_TEMPLATE_NUM_FIELDS_MAX	15
+
 /* set during initialization */
 extern int ima_initialized;
 extern int ima_used_chip;
 extern int ima_hash_algo;
 extern int ima_appraise;
 
+/* IMA template field data definition */
+struct ima_field_data {
+	u8 *data;
+	u32 len;
+};
+
+/* IMA template field definition */
+struct ima_template_field {
+	const char field_id[IMA_TEMPLATE_FIELD_ID_MAX_LEN];
+	int (*field_init) (struct integrity_iint_cache *iint, struct file *file,
+			   const unsigned char *filename,
+			   struct ima_field_data *field_data);
+	void (*field_show) (struct seq_file *m, enum ima_show_type show,
+			    struct ima_field_data *field_data);
+};
+
+/* IMA template descriptor definition */
+struct ima_template_desc {
+	char *name;
+	char *fmt;
+	int num_fields;
+	struct ima_template_field **fields;
+};
+
 /* IMA inode template definition */
 struct ima_template_data {
 	u8 digest[IMA_DIGEST_SIZE];	/* sha1/md5 measurement hash */
@@ -79,6 +106,8 @@ void ima_add_violation(struct file *file, const unsigned char *filename,
 		       const char *op, const char *cause);
 int ima_init_crypto(void);
 
+int ima_init_template(void);
+
 /*
  * used to protect h_table and sha_table
  */
diff --git a/security/integrity/ima/ima_init.c b/security/integrity/ima/ima_init.c
index 50e15e6336c4..f84aec5412f3 100644
--- a/security/integrity/ima/ima_init.c
+++ b/security/integrity/ima/ima_init.c
@@ -99,6 +99,10 @@ int __init ima_init(void)
 	rc = ima_init_crypto();
 	if (rc)
 		return rc;
+	rc = ima_init_template();
+	if (rc != 0)
+		return rc;
+
 	ima_add_boot_aggregate();	/* boot aggregate must be first entry */
 	ima_init_policy();
 
diff --git a/security/integrity/ima/ima_template.c b/security/integrity/ima/ima_template.c
new file mode 100644
index 000000000000..7e86783ccf51
--- /dev/null
+++ b/security/integrity/ima/ima_template.c
@@ -0,0 +1,112 @@
+/*
+ * Copyright (C) 2013 Politecnico di Torino, Italy
+ *                    TORSEC group -- http://security.polito.it
+ *
+ * Author: Roberto Sassu <roberto.sassu@polito.it>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License as
+ * published by the Free Software Foundation, version 2 of the
+ * License.
+ *
+ * File: ima_template.c
+ *      Helpers to manage template descriptors.
+ */
+#include "ima.h"
+
+static struct ima_template_desc defined_templates[] = {
+};
+
+static struct ima_template_field supported_fields[] = {
+};
+
+static struct ima_template_field *ima_lookup_template_field(
+							const char *field_id)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(supported_fields); i++)
+		if (strncmp(supported_fields[i].field_id, field_id,
+			    IMA_TEMPLATE_FIELD_ID_MAX_LEN) == 0)
+			return &supported_fields[i];
+	return NULL;
+}
+
+static int ima_template_fmt_size(char *template_fmt)
+{
+	char c;
+	int template_fmt_len = strlen(template_fmt);
+	int i = 0, j = 0;
+
+	while (i < template_fmt_len) {
+		c = template_fmt[i];
+		if (c == '|')
+			j++;
+		i++;
+	}
+
+	return j + 1;
+}
+
+static int template_desc_init_fields(char *template_fmt,
+				     struct ima_template_field ***fields,
+				     int *num_fields)
+{
+	char *c, *template_fmt_ptr = template_fmt;
+	int template_num_fields = ima_template_fmt_size(template_fmt);
+	int i, result = 0;
+
+	if (template_num_fields > IMA_TEMPLATE_NUM_FIELDS_MAX)
+		return -EINVAL;
+
+	*fields = kzalloc(template_num_fields * sizeof(*fields), GFP_KERNEL);
+	if (*fields == NULL) {
+		result = -ENOMEM;
+		goto out;
+	}
+	for (i = 0; (c = strsep(&template_fmt_ptr, "|")) != NULL &&
+	     i < template_num_fields; i++) {
+		struct ima_template_field *f = ima_lookup_template_field(c);
+
+		if (!f) {
+			result = -ENOENT;
+			goto out;
+		}
+		(*fields)[i] = f;
+	}
+	*num_fields = i;
+	return 0;
+out:
+	kfree(*fields);
+	*fields = NULL;
+	return result;
+}
+
+static int init_defined_templates(void)
+{
+	int i = 0;
+	int result = 0;
+
+	/* Init defined templates. */
+	for (i = 0; i < ARRAY_SIZE(defined_templates); i++) {
+		struct ima_template_desc *template = &defined_templates[i];
+
+		result = template_desc_init_fields(template->fmt,
+						   &(template->fields),
+						   &(template->num_fields));
+		if (result < 0)
+			return result;
+	}
+	return result;
+}
+
+int ima_init_template(void)
+{
+	int result;
+
+	result = init_defined_templates();
+	if (result < 0)
+		return result;
+
+	return 0;
+}
-- 
cgit v1.2.3


From 3ce1217d6cd5dfa82a9db5c2a999cc1bb01490d9 Mon Sep 17 00:00:00 2001
From: Roberto Sassu <roberto.sassu@polito.it>
Date: Fri, 7 Jun 2013 12:16:30 +0200
Subject: ima: define template fields library and new helpers

This patch defines a library containing two initial template fields,
inode digest (d) and file name (n), the 'ima' template descriptor,
whose format is 'd|n', and two helper functions,
ima_write_template_field_data() and ima_show_template_field_data().

Changelog:
- replace ima_eventname_init() parameter NULL checking with BUG_ON.
  (suggested by Mimi)
- include "new template fields for inode digest (d) and file name (n)"
  definitions to fix a compiler warning.  - Mimi
- unnecessary to prefix static function names with 'ima_'. remove
  prefix to resolve Lindent formatting changes. - Mimi
- abbreviated/removed inline comments - Mimi
- always send the template field length - Mimi

Signed-off-by: Roberto Sassu <roberto.sassu@polito.it>
Signed-off-by: Mimi Zohar <zohar@linux.vnet.ibm.com>
---
 security/integrity/ima/Makefile           |   2 +-
 security/integrity/ima/ima.h              |   5 +
 security/integrity/ima/ima_fs.c           |   4 +-
 security/integrity/ima/ima_template.c     |  15 ++-
 security/integrity/ima/ima_template_lib.c | 193 ++++++++++++++++++++++++++++++
 security/integrity/ima/ima_template_lib.h |  31 +++++
 6 files changed, 242 insertions(+), 8 deletions(-)
 create mode 100644 security/integrity/ima/ima_template_lib.c
 create mode 100644 security/integrity/ima/ima_template_lib.h

(limited to 'security')

diff --git a/security/integrity/ima/Makefile b/security/integrity/ima/Makefile
index 7fe4ae37dbea..d79263d2fdbf 100644
--- a/security/integrity/ima/Makefile
+++ b/security/integrity/ima/Makefile
@@ -6,5 +6,5 @@
 obj-$(CONFIG_IMA) += ima.o
 
 ima-y := ima_fs.o ima_queue.o ima_init.o ima_main.o ima_crypto.o ima_api.o \
-	 ima_policy.o ima_template.o
+	 ima_policy.o ima_template.o ima_template_lib.o
 ima-$(CONFIG_IMA_APPRAISE) += ima_appraise.o
diff --git a/security/integrity/ima/ima.h b/security/integrity/ima/ima.h
index c85718f1f623..e1f081d65dbf 100644
--- a/security/integrity/ima/ima.h
+++ b/security/integrity/ima/ima.h
@@ -39,6 +39,9 @@ enum tpm_pcrs { TPM_PCR0 = 0, TPM_PCR8 = 8 };
 #define IMA_TEMPLATE_FIELD_ID_MAX_LEN	16
 #define IMA_TEMPLATE_NUM_FIELDS_MAX	15
 
+#define IMA_TEMPLATE_IMA_NAME "ima"
+#define IMA_TEMPLATE_IMA_FMT "d|n"
+
 /* set during initialization */
 extern int ima_initialized;
 extern int ima_used_chip;
@@ -105,6 +108,8 @@ int __init ima_calc_boot_aggregate(struct ima_digest_data *hash);
 void ima_add_violation(struct file *file, const unsigned char *filename,
 		       const char *op, const char *cause);
 int ima_init_crypto(void);
+void ima_putc(struct seq_file *m, void *data, int datalen);
+void ima_print_digest(struct seq_file *m, u8 *digest, int size);
 
 int ima_init_template(void);
 
diff --git a/security/integrity/ima/ima_fs.c b/security/integrity/ima/ima_fs.c
index c35cfb5b3c5e..414862e1904b 100644
--- a/security/integrity/ima/ima_fs.c
+++ b/security/integrity/ima/ima_fs.c
@@ -99,7 +99,7 @@ static void ima_measurements_stop(struct seq_file *m, void *v)
 {
 }
 
-static void ima_putc(struct seq_file *m, void *data, int datalen)
+void ima_putc(struct seq_file *m, void *data, int datalen)
 {
 	while (datalen--)
 		seq_putc(m, *(char *)data++);
@@ -167,7 +167,7 @@ static const struct file_operations ima_measurements_ops = {
 	.release = seq_release,
 };
 
-static void ima_print_digest(struct seq_file *m, u8 *digest, int size)
+void ima_print_digest(struct seq_file *m, u8 *digest, int size)
 {
 	int i;
 
diff --git a/security/integrity/ima/ima_template.c b/security/integrity/ima/ima_template.c
index 7e86783ccf51..810042264396 100644
--- a/security/integrity/ima/ima_template.c
+++ b/security/integrity/ima/ima_template.c
@@ -13,15 +13,20 @@
  *      Helpers to manage template descriptors.
  */
 #include "ima.h"
+#include "ima_template_lib.h"
 
 static struct ima_template_desc defined_templates[] = {
+	{.name = IMA_TEMPLATE_IMA_NAME,.fmt = IMA_TEMPLATE_IMA_FMT},
 };
 
 static struct ima_template_field supported_fields[] = {
+	{.field_id = "d",.field_init = ima_eventdigest_init,
+	 .field_show = ima_show_template_digest},
+	{.field_id = "n",.field_init = ima_eventname_init,
+	 .field_show = ima_show_template_string},
 };
 
-static struct ima_template_field *ima_lookup_template_field(
-							const char *field_id)
+static struct ima_template_field *lookup_template_field(const char *field_id)
 {
 	int i;
 
@@ -32,7 +37,7 @@ static struct ima_template_field *ima_lookup_template_field(
 	return NULL;
 }
 
-static int ima_template_fmt_size(char *template_fmt)
+static int template_fmt_size(char *template_fmt)
 {
 	char c;
 	int template_fmt_len = strlen(template_fmt);
@@ -53,7 +58,7 @@ static int template_desc_init_fields(char *template_fmt,
 				     int *num_fields)
 {
 	char *c, *template_fmt_ptr = template_fmt;
-	int template_num_fields = ima_template_fmt_size(template_fmt);
+	int template_num_fields = template_fmt_size(template_fmt);
 	int i, result = 0;
 
 	if (template_num_fields > IMA_TEMPLATE_NUM_FIELDS_MAX)
@@ -66,7 +71,7 @@ static int template_desc_init_fields(char *template_fmt,
 	}
 	for (i = 0; (c = strsep(&template_fmt_ptr, "|")) != NULL &&
 	     i < template_num_fields; i++) {
-		struct ima_template_field *f = ima_lookup_template_field(c);
+		struct ima_template_field *f = lookup_template_field(c);
 
 		if (!f) {
 			result = -ENOENT;
diff --git a/security/integrity/ima/ima_template_lib.c b/security/integrity/ima/ima_template_lib.c
new file mode 100644
index 000000000000..e13fc7c04ebc
--- /dev/null
+++ b/security/integrity/ima/ima_template_lib.c
@@ -0,0 +1,193 @@
+/*
+ * Copyright (C) 2013 Politecnico di Torino, Italy
+ *                    TORSEC group -- http://security.polito.it
+ *
+ * Author: Roberto Sassu <roberto.sassu@polito.it>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License as
+ * published by the Free Software Foundation, version 2 of the
+ * License.
+ *
+ * File: ima_template_lib.c
+ *      Library of supported template fields.
+ */
+#include "ima_template_lib.h"
+
+enum data_formats { DATA_FMT_DIGEST = 0, DATA_FMT_EVENT_NAME, DATA_FMT_STRING };
+static int ima_write_template_field_data(const void *data, const u32 datalen,
+					 enum data_formats datafmt,
+					 struct ima_field_data *field_data)
+{
+	u8 *buf, *buf_ptr;
+	u32 buflen;
+
+	switch (datafmt) {
+	case DATA_FMT_EVENT_NAME:
+		buflen = IMA_EVENT_NAME_LEN_MAX + 1;
+		break;
+	case DATA_FMT_STRING:
+		buflen = datalen + 1;
+		break;
+	default:
+		buflen = datalen;
+	}
+
+	buf = kzalloc(buflen, GFP_KERNEL);
+	if (!buf)
+		return -ENOMEM;
+
+	memcpy(buf, data, datalen);
+
+	/*
+	 * Replace all space characters with underscore for event names and
+	 * strings. This avoid that, during the parsing of a measurements list,
+	 * filenames with spaces or that end with the suffix ' (deleted)' are
+	 * split into multiple template fields (the space is the delimitator
+	 * character for measurements lists in ASCII format).
+	 */
+	if (datafmt == DATA_FMT_EVENT_NAME || datafmt == DATA_FMT_STRING) {
+		for (buf_ptr = buf; buf_ptr - buf < datalen; buf_ptr++)
+			if (*buf_ptr == ' ')
+				*buf_ptr = '_';
+	}
+
+	field_data->data = buf;
+	field_data->len = buflen;
+	return 0;
+}
+
+static void ima_show_template_data_ascii(struct seq_file *m,
+					 enum ima_show_type show,
+					 enum data_formats datafmt,
+					 struct ima_field_data *field_data)
+{
+	switch (datafmt) {
+	case DATA_FMT_DIGEST:
+		ima_print_digest(m, field_data->data, field_data->len);
+		break;
+	case DATA_FMT_STRING:
+		seq_printf(m, "%s", field_data->data);
+		break;
+	default:
+		break;
+	}
+}
+
+static void ima_show_template_data_binary(struct seq_file *m,
+					  enum ima_show_type show,
+					  enum data_formats datafmt,
+					  struct ima_field_data *field_data)
+{
+	ima_putc(m, &field_data->len, sizeof(u32));
+	if (!field_data->len)
+		return;
+	ima_putc(m, field_data->data, field_data->len);
+}
+
+static void ima_show_template_field_data(struct seq_file *m,
+					 enum ima_show_type show,
+					 enum data_formats datafmt,
+					 struct ima_field_data *field_data)
+{
+	switch (show) {
+	case IMA_SHOW_ASCII:
+		ima_show_template_data_ascii(m, show, datafmt, field_data);
+		break;
+	case IMA_SHOW_BINARY:
+		ima_show_template_data_binary(m, show, datafmt, field_data);
+		break;
+	default:
+		break;
+	}
+}
+
+void ima_show_template_digest(struct seq_file *m, enum ima_show_type show,
+			      struct ima_field_data *field_data)
+{
+	ima_show_template_field_data(m, show, DATA_FMT_DIGEST, field_data);
+}
+
+void ima_show_template_string(struct seq_file *m, enum ima_show_type show,
+			      struct ima_field_data *field_data)
+{
+	ima_show_template_field_data(m, show, DATA_FMT_STRING, field_data);
+}
+
+/*
+ * This function writes the digest of an event.
+ */
+int ima_eventdigest_init(struct integrity_iint_cache *iint, struct file *file,
+			 const unsigned char *filename,
+			 struct ima_field_data *field_data)
+{
+	struct {
+		struct ima_digest_data hdr;
+		char digest[IMA_MAX_DIGEST_SIZE];
+	} hash;
+	u8 *cur_digest = hash.hdr.digest;
+	u32 cur_digestsize = IMA_DIGEST_SIZE;
+	struct inode *inode;
+	int result;
+
+	memset(&hash, 0, sizeof(hash));
+
+	if (!iint)		/* recording a violation. */
+		goto out;
+
+	if (iint->ima_hash->algo == ima_hash_algo) {
+		cur_digest = iint->ima_hash->digest;
+		cur_digestsize = iint->ima_hash->length;
+		goto out;
+	}
+
+	if (!file)		/* missing info to re-calculate the digest */
+		return -EINVAL;
+
+	inode = file_inode(file);
+	hash.hdr.algo = ima_hash_algo;
+	result = ima_calc_file_hash(file, &hash.hdr);
+	if (result) {
+		integrity_audit_msg(AUDIT_INTEGRITY_DATA, inode,
+				    filename, "collect_data",
+				    "failed", result, 0);
+		return result;
+	}
+out:
+	return ima_write_template_field_data(cur_digest, cur_digestsize,
+					     DATA_FMT_DIGEST, field_data);
+}
+
+/*
+ * This function writes the name of an event.
+ */
+int ima_eventname_init(struct integrity_iint_cache *iint, struct file *file,
+		       const unsigned char *filename,
+		       struct ima_field_data *field_data)
+{
+	const char *cur_filename = NULL;
+	u32 cur_filename_len = 0;
+
+	BUG_ON(filename == NULL && file == NULL);
+
+	if (filename) {
+		cur_filename = filename;
+		cur_filename_len = strlen(filename);
+
+		if (cur_filename_len <= IMA_EVENT_NAME_LEN_MAX)
+			goto out;
+	}
+
+	if (file) {
+		cur_filename = file->f_dentry->d_name.name;
+		cur_filename_len = strlen(cur_filename);
+	} else
+		/*
+		 * Truncate filename if the latter is too long and
+		 * the file descriptor is not available.
+		 */
+		cur_filename_len = IMA_EVENT_NAME_LEN_MAX;
+out:
+	return ima_write_template_field_data(cur_filename, cur_filename_len,
+					     DATA_FMT_EVENT_NAME, field_data);
+}
diff --git a/security/integrity/ima/ima_template_lib.h b/security/integrity/ima/ima_template_lib.h
new file mode 100644
index 000000000000..2cecc83a928d
--- /dev/null
+++ b/security/integrity/ima/ima_template_lib.h
@@ -0,0 +1,31 @@
+/*
+ * Copyright (C) 2013 Politecnico di Torino, Italy
+ *                    TORSEC group -- http://security.polito.it
+ *
+ * Author: Roberto Sassu <roberto.sassu@polito.it>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License as
+ * published by the Free Software Foundation, version 2 of the
+ * License.
+ *
+ * File: ima_template_lib.h
+ *      Header for the library of supported template fields.
+ */
+#ifndef __LINUX_IMA_TEMPLATE_LIB_H
+#define __LINUX_IMA_TEMPLATE_LIB_H
+
+#include <linux/seq_file.h>
+#include "ima.h"
+
+void ima_show_template_digest(struct seq_file *m, enum ima_show_type show,
+			      struct ima_field_data *field_data);
+void ima_show_template_string(struct seq_file *m, enum ima_show_type show,
+			      struct ima_field_data *field_data);
+int ima_eventdigest_init(struct integrity_iint_cache *iint, struct file *file,
+			 const unsigned char *filename,
+			 struct ima_field_data *field_data);
+int ima_eventname_init(struct integrity_iint_cache *iint, struct file *file,
+		       const unsigned char *filename,
+		       struct ima_field_data *field_data);
+#endif /* __LINUX_IMA_TEMPLATE_LIB_H */
-- 
cgit v1.2.3


From 4d7aeee73f5304bf195aa2904f8eb1d7b2e8fe52 Mon Sep 17 00:00:00 2001
From: Roberto Sassu <roberto.sassu@polito.it>
Date: Fri, 7 Jun 2013 12:16:32 +0200
Subject: ima: define new template ima-ng and template fields d-ng and n-ng

This patch adds support for the new template 'ima-ng', whose format
is defined as 'd-ng|n-ng'.  These new field definitions remove the
size limitations of the original 'ima' template.  Further, the 'd-ng'
field prefixes the inode digest with the hash algorithim, when
displaying the new larger digest sizes.

Change log:
- scripts/Lindent fixes  - Mimi
- "always true comparison" - reported by Fengguang Wu, resolved Dmitry
- initialize hash_algo variable to HASH_ALGO__LAST
- always prefix digest with hash algorithm - Mimi

Signed-off-by: Roberto Sassu <roberto.sassu@polito.it>
Signed-off-by: Mimi Zohar <zohar@linux.vnet.ibm.com>
---
 security/integrity/ima/ima_template.c     |   7 +-
 security/integrity/ima/ima_template_lib.c | 152 ++++++++++++++++++++++++++----
 security/integrity/ima/ima_template_lib.h |   8 ++
 3 files changed, 150 insertions(+), 17 deletions(-)

(limited to 'security')

diff --git a/security/integrity/ima/ima_template.c b/security/integrity/ima/ima_template.c
index 810042264396..bf38d1af3cfd 100644
--- a/security/integrity/ima/ima_template.c
+++ b/security/integrity/ima/ima_template.c
@@ -16,7 +16,8 @@
 #include "ima_template_lib.h"
 
 static struct ima_template_desc defined_templates[] = {
-	{.name = IMA_TEMPLATE_IMA_NAME,.fmt = IMA_TEMPLATE_IMA_FMT},
+	{.name = IMA_TEMPLATE_IMA_NAME, .fmt = IMA_TEMPLATE_IMA_FMT},
+	{.name = "ima-ng",.fmt = "d-ng|n-ng"},
 };
 
 static struct ima_template_field supported_fields[] = {
@@ -24,6 +25,10 @@ static struct ima_template_field supported_fields[] = {
 	 .field_show = ima_show_template_digest},
 	{.field_id = "n",.field_init = ima_eventname_init,
 	 .field_show = ima_show_template_string},
+	{.field_id = "d-ng",.field_init = ima_eventdigest_ng_init,
+	 .field_show = ima_show_template_digest_ng},
+	{.field_id = "n-ng",.field_init = ima_eventname_ng_init,
+	 .field_show = ima_show_template_string},
 };
 
 static struct ima_template_field *lookup_template_field(const char *field_id)
diff --git a/security/integrity/ima/ima_template_lib.c b/security/integrity/ima/ima_template_lib.c
index e13fc7c04ebc..7d841448f246 100644
--- a/security/integrity/ima/ima_template_lib.c
+++ b/security/integrity/ima/ima_template_lib.c
@@ -12,9 +12,25 @@
  * File: ima_template_lib.c
  *      Library of supported template fields.
  */
+#include <crypto/hash_info.h>
+
 #include "ima_template_lib.h"
 
-enum data_formats { DATA_FMT_DIGEST = 0, DATA_FMT_EVENT_NAME, DATA_FMT_STRING };
+static bool ima_template_hash_algo_allowed(u8 algo)
+{
+	if (algo == HASH_ALGO_SHA1 || algo == HASH_ALGO_MD5)
+		return true;
+
+	return false;
+}
+
+enum data_formats {
+	DATA_FMT_DIGEST = 0,
+	DATA_FMT_DIGEST_WITH_ALGO,
+	DATA_FMT_EVENT_NAME,
+	DATA_FMT_STRING
+};
+
 static int ima_write_template_field_data(const void *data, const u32 datalen,
 					 enum data_formats datafmt,
 					 struct ima_field_data *field_data)
@@ -62,12 +78,22 @@ static void ima_show_template_data_ascii(struct seq_file *m,
 					 enum data_formats datafmt,
 					 struct ima_field_data *field_data)
 {
+	u8 *buf_ptr = field_data->data, buflen = field_data->len;
+
 	switch (datafmt) {
+	case DATA_FMT_DIGEST_WITH_ALGO:
+		buf_ptr = strnchr(field_data->data, buflen, ':');
+		if (buf_ptr != field_data->data)
+			seq_printf(m, "%s", field_data->data);
+
+		/* skip ':' and '\0' */
+		buf_ptr += 2;
+		buflen -= buf_ptr - field_data->data;
 	case DATA_FMT_DIGEST:
-		ima_print_digest(m, field_data->data, field_data->len);
+		ima_print_digest(m, buf_ptr, buflen);
 		break;
 	case DATA_FMT_STRING:
-		seq_printf(m, "%s", field_data->data);
+		seq_printf(m, "%s", buf_ptr);
 		break;
 	default:
 		break;
@@ -108,14 +134,59 @@ void ima_show_template_digest(struct seq_file *m, enum ima_show_type show,
 	ima_show_template_field_data(m, show, DATA_FMT_DIGEST, field_data);
 }
 
+void ima_show_template_digest_ng(struct seq_file *m, enum ima_show_type show,
+				 struct ima_field_data *field_data)
+{
+	ima_show_template_field_data(m, show, DATA_FMT_DIGEST_WITH_ALGO,
+				     field_data);
+}
+
 void ima_show_template_string(struct seq_file *m, enum ima_show_type show,
 			      struct ima_field_data *field_data)
 {
 	ima_show_template_field_data(m, show, DATA_FMT_STRING, field_data);
 }
 
+static int ima_eventdigest_init_common(u8 *digest, u32 digestsize, u8 hash_algo,
+				       struct ima_field_data *field_data,
+				       bool size_limit)
+{
+	/*
+	 * digest formats:
+	 *  - DATA_FMT_DIGEST: digest
+	 *  - DATA_FMT_DIGEST_WITH_ALGO: [<hash algo>] + ':' + '\0' + digest,
+	 *    where <hash algo> is provided if the hash algoritm is not
+	 *    SHA1 or MD5
+	 */
+	u8 buffer[CRYPTO_MAX_ALG_NAME + 2 + IMA_MAX_DIGEST_SIZE] = { 0 };
+	enum data_formats fmt = DATA_FMT_DIGEST;
+	u32 offset = 0;
+
+	if (!size_limit) {
+		fmt = DATA_FMT_DIGEST_WITH_ALGO;
+		if (hash_algo < HASH_ALGO__LAST)
+			offset += snprintf(buffer, CRYPTO_MAX_ALG_NAME + 1,
+					   "%s", hash_algo_name[hash_algo]);
+		buffer[offset] = ':';
+		offset += 2;
+	}
+
+	if (digest)
+		memcpy(buffer + offset, digest, digestsize);
+	else
+		/*
+		 * If digest is NULL, the event being recorded is a violation.
+		 * Make room for the digest by increasing the offset of
+		 * IMA_DIGEST_SIZE.
+		 */
+		offset += IMA_DIGEST_SIZE;
+
+	return ima_write_template_field_data(buffer, offset + digestsize,
+					     fmt, field_data);
+}
+
 /*
- * This function writes the digest of an event.
+ * This function writes the digest of an event (with size limit).
  */
 int ima_eventdigest_init(struct integrity_iint_cache *iint, struct file *file,
 			 const unsigned char *filename,
@@ -125,8 +196,8 @@ int ima_eventdigest_init(struct integrity_iint_cache *iint, struct file *file,
 		struct ima_digest_data hdr;
 		char digest[IMA_MAX_DIGEST_SIZE];
 	} hash;
-	u8 *cur_digest = hash.hdr.digest;
-	u32 cur_digestsize = IMA_DIGEST_SIZE;
+	u8 *cur_digest = NULL;
+	u32 cur_digestsize = 0;
 	struct inode *inode;
 	int result;
 
@@ -135,7 +206,7 @@ int ima_eventdigest_init(struct integrity_iint_cache *iint, struct file *file,
 	if (!iint)		/* recording a violation. */
 		goto out;
 
-	if (iint->ima_hash->algo == ima_hash_algo) {
+	if (ima_template_hash_algo_allowed(iint->ima_hash->algo)) {
 		cur_digest = iint->ima_hash->digest;
 		cur_digestsize = iint->ima_hash->length;
 		goto out;
@@ -145,7 +216,8 @@ int ima_eventdigest_init(struct integrity_iint_cache *iint, struct file *file,
 		return -EINVAL;
 
 	inode = file_inode(file);
-	hash.hdr.algo = ima_hash_algo;
+	hash.hdr.algo = ima_template_hash_algo_allowed(ima_hash_algo) ?
+	    ima_hash_algo : HASH_ALGO_SHA1;
 	result = ima_calc_file_hash(file, &hash.hdr);
 	if (result) {
 		integrity_audit_msg(AUDIT_INTEGRITY_DATA, inode,
@@ -153,20 +225,46 @@ int ima_eventdigest_init(struct integrity_iint_cache *iint, struct file *file,
 				    "failed", result, 0);
 		return result;
 	}
+	cur_digest = hash.hdr.digest;
+	cur_digestsize = hash.hdr.length;
 out:
-	return ima_write_template_field_data(cur_digest, cur_digestsize,
-					     DATA_FMT_DIGEST, field_data);
+	return ima_eventdigest_init_common(cur_digest, cur_digestsize, -1,
+					   field_data, true);
 }
 
 /*
- * This function writes the name of an event.
+ * This function writes the digest of an event (without size limit).
  */
-int ima_eventname_init(struct integrity_iint_cache *iint, struct file *file,
-		       const unsigned char *filename,
-		       struct ima_field_data *field_data)
+int ima_eventdigest_ng_init(struct integrity_iint_cache *iint,
+			    struct file *file, const unsigned char *filename,
+			    struct ima_field_data *field_data)
+{
+	u8 *cur_digest = NULL, hash_algo = HASH_ALGO__LAST;
+	u32 cur_digestsize = 0;
+
+	/* If iint is NULL, we are recording a violation. */
+	if (!iint)
+		goto out;
+
+	cur_digest = iint->ima_hash->digest;
+	cur_digestsize = iint->ima_hash->length;
+
+	hash_algo = iint->ima_hash->algo;
+out:
+	return ima_eventdigest_init_common(cur_digest, cur_digestsize,
+					   hash_algo, field_data, false);
+}
+
+static int ima_eventname_init_common(struct integrity_iint_cache *iint,
+				     struct file *file,
+				     const unsigned char *filename,
+				     struct ima_field_data *field_data,
+				     bool size_limit)
 {
 	const char *cur_filename = NULL;
 	u32 cur_filename_len = 0;
+	enum data_formats fmt = size_limit ?
+	    DATA_FMT_EVENT_NAME : DATA_FMT_STRING;
 
 	BUG_ON(filename == NULL && file == NULL);
 
@@ -174,7 +272,7 @@ int ima_eventname_init(struct integrity_iint_cache *iint, struct file *file,
 		cur_filename = filename;
 		cur_filename_len = strlen(filename);
 
-		if (cur_filename_len <= IMA_EVENT_NAME_LEN_MAX)
+		if (!size_limit || cur_filename_len <= IMA_EVENT_NAME_LEN_MAX)
 			goto out;
 	}
 
@@ -189,5 +287,27 @@ int ima_eventname_init(struct integrity_iint_cache *iint, struct file *file,
 		cur_filename_len = IMA_EVENT_NAME_LEN_MAX;
 out:
 	return ima_write_template_field_data(cur_filename, cur_filename_len,
-					     DATA_FMT_EVENT_NAME, field_data);
+					     fmt, field_data);
+}
+
+/*
+ * This function writes the name of an event (with size limit).
+ */
+int ima_eventname_init(struct integrity_iint_cache *iint, struct file *file,
+		       const unsigned char *filename,
+		       struct ima_field_data *field_data)
+{
+	return ima_eventname_init_common(iint, file, filename,
+					 field_data, true);
+}
+
+/*
+ * This function writes the name of an event (without size limit).
+ */
+int ima_eventname_ng_init(struct integrity_iint_cache *iint, struct file *file,
+			  const unsigned char *filename,
+			  struct ima_field_data *field_data)
+{
+	return ima_eventname_init_common(iint, file, filename,
+					 field_data, false);
 }
diff --git a/security/integrity/ima/ima_template_lib.h b/security/integrity/ima/ima_template_lib.h
index 2cecc83a928d..16c5e7810234 100644
--- a/security/integrity/ima/ima_template_lib.h
+++ b/security/integrity/ima/ima_template_lib.h
@@ -20,6 +20,8 @@
 
 void ima_show_template_digest(struct seq_file *m, enum ima_show_type show,
 			      struct ima_field_data *field_data);
+void ima_show_template_digest_ng(struct seq_file *m, enum ima_show_type show,
+				 struct ima_field_data *field_data);
 void ima_show_template_string(struct seq_file *m, enum ima_show_type show,
 			      struct ima_field_data *field_data);
 int ima_eventdigest_init(struct integrity_iint_cache *iint, struct file *file,
@@ -28,4 +30,10 @@ int ima_eventdigest_init(struct integrity_iint_cache *iint, struct file *file,
 int ima_eventname_init(struct integrity_iint_cache *iint, struct file *file,
 		       const unsigned char *filename,
 		       struct ima_field_data *field_data);
+int ima_eventdigest_ng_init(struct integrity_iint_cache *iint,
+			    struct file *file, const unsigned char *filename,
+			    struct ima_field_data *field_data);
+int ima_eventname_ng_init(struct integrity_iint_cache *iint, struct file *file,
+			  const unsigned char *filename,
+			  struct ima_field_data *field_data);
 #endif /* __LINUX_IMA_TEMPLATE_LIB_H */
-- 
cgit v1.2.3


From a71dc65d30a472409f05d247f4eab91b14acf2f5 Mon Sep 17 00:00:00 2001
From: Roberto Sassu <roberto.sassu@polito.it>
Date: Fri, 7 Jun 2013 12:16:33 +0200
Subject: ima: switch to new template management mechanism

This patch performs the switch to the new template mechanism by modifying
the functions ima_alloc_init_template(), ima_measurements_show() and
ima_ascii_measurements_show(). The old function ima_template_show() was
removed as it is no longer needed. Also, if the template descriptor used
to generate a measurement entry is not 'ima', the whole length of field
data stored for an entry is provided before the data itself through the
binary_runtime_measurement interface.

Changelog:
- unnecessary to use strncmp() (Mimi Zohar)
- create new variable 'field' in ima_alloc_init_template() (Roberto Sassu)
- use GFP_NOFS flag in ima_alloc_init_template() (Roberto Sassu)
- new variable 'num_fields' in ima_store_template() (Roberto Sassu,
  proposed by Mimi Zohar)
- rename ima_calc_buffer_hash/template_hash() to ima_calc_field_array_hash(),
  something more generic (Mimi, requested by Dmitry)
- sparse error fix - Fengguang Wu
- fix lindent warnings
- always include the field length in the template data length
- include the template field length variable size in the template data length
- include both the template field data and field length in the template digest
  calculation. Simplifies verifying the template digest. (Mimi)

Signed-off-by: Roberto Sassu <roberto.sassu@polito.it>
Signed-off-by: Mimi Zohar <zohar@linux.vnet.ibm.com>
---
 security/integrity/ima/ima.h          | 19 ++++-----
 security/integrity/ima/ima_api.c      | 75 ++++++++++++-----------------------
 security/integrity/ima/ima_crypto.c   | 34 ++++++++++++----
 security/integrity/ima/ima_fs.c       | 54 ++++++++++++-------------
 security/integrity/ima/ima_template.c | 22 ++++++++++
 5 files changed, 107 insertions(+), 97 deletions(-)

(limited to 'security')

diff --git a/security/integrity/ima/ima.h b/security/integrity/ima/ima.h
index e1f081d65dbf..72d013e190b1 100644
--- a/security/integrity/ima/ima.h
+++ b/security/integrity/ima/ima.h
@@ -72,17 +72,11 @@ struct ima_template_desc {
 	struct ima_template_field **fields;
 };
 
-/* IMA inode template definition */
-struct ima_template_data {
-	u8 digest[IMA_DIGEST_SIZE];	/* sha1/md5 measurement hash */
-	char file_name[IMA_EVENT_NAME_LEN_MAX + 1];	/* name + \0 */
-};
-
 struct ima_template_entry {
 	u8 digest[TPM_DIGEST_SIZE];	/* sha1 or md5 measurement hash */
-	const char *template_name;
-	int template_len;
-	struct ima_template_data template;
+	struct ima_template_desc *template_desc; /* template descriptor */
+	u32 template_data_len;
+	struct ima_field_data template_data[0];	/* template related data */
 };
 
 struct ima_queue_entry {
@@ -102,14 +96,16 @@ int ima_add_template_entry(struct ima_template_entry *entry, int violation,
 			   const char *op, struct inode *inode,
 			   const unsigned char *filename);
 int ima_calc_file_hash(struct file *file, struct ima_digest_data *hash);
-int ima_calc_buffer_hash(const void *data, int len,
-			 struct ima_digest_data *hash);
+int ima_calc_field_array_hash(struct ima_field_data *field_data, int num_fields,
+			      struct ima_digest_data *hash);
 int __init ima_calc_boot_aggregate(struct ima_digest_data *hash);
 void ima_add_violation(struct file *file, const unsigned char *filename,
 		       const char *op, const char *cause);
 int ima_init_crypto(void);
 void ima_putc(struct seq_file *m, void *data, int datalen);
 void ima_print_digest(struct seq_file *m, u8 *digest, int size);
+struct ima_template_desc *ima_template_desc_current(void);
+int ima_init_template(void);
 
 int ima_init_template(void);
 
@@ -146,7 +142,6 @@ int ima_alloc_init_template(struct integrity_iint_cache *iint,
 			    struct ima_template_entry **entry);
 int ima_store_template(struct ima_template_entry *entry, int violation,
 		       struct inode *inode, const unsigned char *filename);
-void ima_template_show(struct seq_file *m, void *e, enum ima_show_type show);
 const char *ima_d_path(struct path *path, char **pathbuf);
 
 /* rbtree tree calls to lookup, insert, delete
diff --git a/security/integrity/ima/ima_api.c b/security/integrity/ima/ima_api.c
index 29dd43de823a..baa348179527 100644
--- a/security/integrity/ima/ima_api.c
+++ b/security/integrity/ima/ima_api.c
@@ -21,8 +21,6 @@
 #include <crypto/hash_info.h>
 #include "ima.h"
 
-static const char *IMA_TEMPLATE_NAME = "ima";
-
 /*
  * ima_alloc_init_template - create and initialize a new template entry
  */
@@ -30,52 +28,32 @@ int ima_alloc_init_template(struct integrity_iint_cache *iint,
 			    struct file *file, const unsigned char *filename,
 			    struct ima_template_entry **entry)
 {
-	struct ima_template_entry *e;
-	int result = 0;
+	struct ima_template_desc *template_desc = ima_template_desc_current();
+	int i, result = 0;
 
-	e = kzalloc(sizeof(**entry), GFP_NOFS);
-	if (!e)
+	*entry = kzalloc(sizeof(**entry) + template_desc->num_fields *
+			 sizeof(struct ima_field_data), GFP_NOFS);
+	if (!*entry)
 		return -ENOMEM;
 
-	memset(&(e)->template, 0, sizeof(e->template));
-	if (!iint)		/* IMA measurement violation entry */
-		goto out;
-
-	if (iint->ima_hash->algo != ima_hash_algo) {
-		struct inode *inode;
-		struct {
-			struct ima_digest_data hdr;
-			char digest[IMA_MAX_DIGEST_SIZE];
-		} hash;
+	for (i = 0; i < template_desc->num_fields; i++) {
+		struct ima_template_field *field = template_desc->fields[i];
+		u32 len;
 
-		if (!file) {
-			result = -EINVAL;
-			goto out_free;
-		}
+		result = field->field_init(iint, file, filename,
+					   &((*entry)->template_data[i]));
+		if (result != 0)
+			goto out;
 
-		inode = file_inode(file);
-		hash.hdr.algo = ima_hash_algo;
-		hash.hdr.length = SHA1_DIGEST_SIZE;
-		result = ima_calc_file_hash(file, &hash.hdr);
-		if (result) {
-			integrity_audit_msg(AUDIT_INTEGRITY_DATA, inode,
-					    filename, "collect_data",
-					    "failed", result, 0);
-			goto out_free;
-		} else
-			memcpy(e->template.digest, hash.hdr.digest,
-			       hash.hdr.length);
-	} else
-		memcpy(e->template.digest, iint->ima_hash->digest,
-		       iint->ima_hash->length);
-out:
-	strcpy(e->template.file_name,
-	       (strlen(filename) > IMA_EVENT_NAME_LEN_MAX && file != NULL) ?
-	       file->f_dentry->d_name.name : filename);
-	*entry = e;
+		len = (*entry)->template_data[i].len;
+		(*entry)->template_data_len += sizeof(len);
+		(*entry)->template_data_len += len;
+	}
+	(*entry)->template_desc = template_desc;
 	return 0;
-out_free:
-	kfree(e);
+out:
+	kfree(*entry);
+	*entry = NULL;
 	return result;
 }
 
@@ -101,24 +79,23 @@ int ima_store_template(struct ima_template_entry *entry,
 {
 	const char *op = "add_template_measure";
 	const char *audit_cause = "hashing_error";
+	char *template_name = entry->template_desc->name;
 	int result;
 	struct {
 		struct ima_digest_data hdr;
 		char digest[TPM_DIGEST_SIZE];
 	} hash;
 
-	memset(entry->digest, 0, sizeof(entry->digest));
-	entry->template_name = IMA_TEMPLATE_NAME;
-	entry->template_len = sizeof(entry->template);
-
 	if (!violation) {
+		int num_fields = entry->template_desc->num_fields;
+
 		/* this function uses default algo */
 		hash.hdr.algo = HASH_ALGO_SHA1;
-		result = ima_calc_buffer_hash(&entry->template,
-					      entry->template_len, &hash.hdr);
+		result = ima_calc_field_array_hash(&entry->template_data[0],
+						   num_fields, &hash.hdr);
 		if (result < 0) {
 			integrity_audit_msg(AUDIT_INTEGRITY_PCR, inode,
-					    entry->template_name, op,
+					    template_name, op,
 					    audit_cause, result, 0);
 			return result;
 		}
diff --git a/security/integrity/ima/ima_crypto.c b/security/integrity/ima/ima_crypto.c
index 22be23f13b3d..676e0292dfec 100644
--- a/security/integrity/ima/ima_crypto.c
+++ b/security/integrity/ima/ima_crypto.c
@@ -137,26 +137,46 @@ int ima_calc_file_hash(struct file *file, struct ima_digest_data *hash)
 }
 
 /*
- * Calculate the hash of a given buffer
+ * Calculate the hash of template data
  */
-static int ima_calc_buffer_hash_tfm(const void *buf, int len,
-				    struct ima_digest_data *hash,
-				    struct crypto_shash *tfm)
+static int ima_calc_field_array_hash_tfm(struct ima_field_data *field_data,
+					 int num_fields,
+					 struct ima_digest_data *hash,
+					 struct crypto_shash *tfm)
 {
 	struct {
 		struct shash_desc shash;
 		char ctx[crypto_shash_descsize(tfm)];
 	} desc;
+	int rc, i;
 
 	desc.shash.tfm = tfm;
 	desc.shash.flags = 0;
 
 	hash->length = crypto_shash_digestsize(tfm);
 
-	return crypto_shash_digest(&desc.shash, buf, len, hash->digest);
+	rc = crypto_shash_init(&desc.shash);
+	if (rc != 0)
+		return rc;
+
+	for (i = 0; i < num_fields; i++) {
+		rc = crypto_shash_update(&desc.shash,
+					 (const u8 *) &field_data[i].len,
+					 sizeof(field_data[i].len));
+		rc = crypto_shash_update(&desc.shash, field_data[i].data,
+					 field_data[i].len);
+		if (rc)
+			break;
+	}
+
+	if (!rc)
+		rc = crypto_shash_final(&desc.shash, hash->digest);
+
+	return rc;
 }
 
-int ima_calc_buffer_hash(const void *buf, int len, struct ima_digest_data *hash)
+int ima_calc_field_array_hash(struct ima_field_data *field_data, int num_fields,
+			      struct ima_digest_data *hash)
 {
 	struct crypto_shash *tfm;
 	int rc;
@@ -165,7 +185,7 @@ int ima_calc_buffer_hash(const void *buf, int len, struct ima_digest_data *hash)
 	if (IS_ERR(tfm))
 		return PTR_ERR(tfm);
 
-	rc = ima_calc_buffer_hash_tfm(buf, len, hash, tfm);
+	rc = ima_calc_field_array_hash_tfm(field_data, num_fields, hash, tfm);
 
 	ima_free_tfm(tfm);
 
diff --git a/security/integrity/ima/ima_fs.c b/security/integrity/ima/ima_fs.c
index 414862e1904b..d47a7c86a21d 100644
--- a/security/integrity/ima/ima_fs.c
+++ b/security/integrity/ima/ima_fs.c
@@ -110,6 +110,7 @@ void ima_putc(struct seq_file *m, void *data, int datalen)
  *       char[20]=template digest
  *       32bit-le=template name size
  *       char[n]=template name
+ *       [eventdata length]
  *       eventdata[n]=template specific data
  */
 static int ima_measurements_show(struct seq_file *m, void *v)
@@ -119,6 +120,7 @@ static int ima_measurements_show(struct seq_file *m, void *v)
 	struct ima_template_entry *e;
 	int namelen;
 	u32 pcr = CONFIG_IMA_MEASURE_PCR_IDX;
+	int i;
 
 	/* get entry */
 	e = qe->entry;
@@ -136,15 +138,22 @@ static int ima_measurements_show(struct seq_file *m, void *v)
 	ima_putc(m, e->digest, TPM_DIGEST_SIZE);
 
 	/* 3rd: template name size */
-	namelen = strlen(e->template_name);
+	namelen = strlen(e->template_desc->name);
 	ima_putc(m, &namelen, sizeof namelen);
 
 	/* 4th:  template name */
-	ima_putc(m, (void *)e->template_name, namelen);
+	ima_putc(m, e->template_desc->name, namelen);
+
+	/* 5th:  template length (except for 'ima' template) */
+	if (strcmp(e->template_desc->name, IMA_TEMPLATE_IMA_NAME) != 0)
+		ima_putc(m, &e->template_data_len,
+			 sizeof(e->template_data_len));
 
-	/* 5th:  template specific data */
-	ima_template_show(m, (struct ima_template_data *)&e->template,
-			  IMA_SHOW_BINARY);
+	/* 6th:  template specific data */
+	for (i = 0; i < e->template_desc->num_fields; i++) {
+		e->template_desc->fields[i]->field_show(m, IMA_SHOW_BINARY,
+							&e->template_data[i]);
+	}
 	return 0;
 }
 
@@ -175,33 +184,13 @@ void ima_print_digest(struct seq_file *m, u8 *digest, int size)
 		seq_printf(m, "%02x", *(digest + i));
 }
 
-void ima_template_show(struct seq_file *m, void *e, enum ima_show_type show)
-{
-	struct ima_template_data *entry = e;
-	int namelen;
-
-	switch (show) {
-	case IMA_SHOW_ASCII:
-		ima_print_digest(m, entry->digest, IMA_DIGEST_SIZE);
-		seq_printf(m, " %s\n", entry->file_name);
-		break;
-	case IMA_SHOW_BINARY:
-		ima_putc(m, entry->digest, IMA_DIGEST_SIZE);
-
-		namelen = strlen(entry->file_name);
-		ima_putc(m, &namelen, sizeof namelen);
-		ima_putc(m, entry->file_name, namelen);
-	default:
-		break;
-	}
-}
-
 /* print in ascii */
 static int ima_ascii_measurements_show(struct seq_file *m, void *v)
 {
 	/* the list never shrinks, so we don't need a lock here */
 	struct ima_queue_entry *qe = v;
 	struct ima_template_entry *e;
+	int i;
 
 	/* get entry */
 	e = qe->entry;
@@ -215,11 +204,18 @@ static int ima_ascii_measurements_show(struct seq_file *m, void *v)
 	ima_print_digest(m, e->digest, TPM_DIGEST_SIZE);
 
 	/* 3th:  template name */
-	seq_printf(m, " %s ", e->template_name);
+	seq_printf(m, " %s", e->template_desc->name);
 
 	/* 4th:  template specific data */
-	ima_template_show(m, (struct ima_template_data *)&e->template,
-			  IMA_SHOW_ASCII);
+	for (i = 0; i < e->template_desc->num_fields; i++) {
+		seq_puts(m, " ");
+		if (e->template_data[i].len == 0)
+			continue;
+
+		e->template_desc->fields[i]->field_show(m, IMA_SHOW_ASCII,
+							&e->template_data[i]);
+	}
+	seq_puts(m, "\n");
 	return 0;
 }
 
diff --git a/security/integrity/ima/ima_template.c b/security/integrity/ima/ima_template.c
index bf38d1af3cfd..1c4cf194592c 100644
--- a/security/integrity/ima/ima_template.c
+++ b/security/integrity/ima/ima_template.c
@@ -31,6 +31,20 @@ static struct ima_template_field supported_fields[] = {
 	 .field_show = ima_show_template_string},
 };
 
+static struct ima_template_desc *ima_template;
+
+static struct ima_template_desc *lookup_template_desc(const char *name)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(defined_templates); i++) {
+		if (strcmp(defined_templates[i].name, name) == 0)
+			return defined_templates + i;
+	}
+
+	return NULL;
+}
+
 static struct ima_template_field *lookup_template_field(const char *field_id)
 {
 	int i;
@@ -110,6 +124,14 @@ static int init_defined_templates(void)
 	return result;
 }
 
+struct ima_template_desc *ima_template_desc_current(void)
+{
+	if (!ima_template)
+		ima_template = lookup_template_desc(IMA_TEMPLATE_IMA_NAME);
+
+	return ima_template;
+}
+
 int ima_init_template(void)
 {
 	int result;
-- 
cgit v1.2.3


From 5278aa52f35003ddafda80b0243b3693f935b134 Mon Sep 17 00:00:00 2001
From: Mimi Zohar <zohar@linux.vnet.ibm.com>
Date: Fri, 7 Jun 2013 12:16:38 +0200
Subject: ima: add audit log support for larger hashes

Different files might be signed based on different hash algorithms.
This patch prefixes the audit log measurement hash with the hash
algorithm.

Changelog:
- use generic HASH_ALGO defintions
- use ':' as delimiter between the hash algorithm and the digest
  (Roberto Sassu)
- always include the hash algorithm used when audit-logging a measurement

Signed-off-by: Mimi Zohar <zohar@linux.vnet.ibm.com>
Signed-off-by: Roberto Sassu <roberto.sassu@polito.it>
Signed-off-by: Peter Moody <pmoody@google.com>
---
 security/integrity/ima/ima_api.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

(limited to 'security')

diff --git a/security/integrity/ima/ima_api.c b/security/integrity/ima/ima_api.c
index baa348179527..5fcc80695d87 100644
--- a/security/integrity/ima/ima_api.c
+++ b/security/integrity/ima/ima_api.c
@@ -270,6 +270,8 @@ void ima_audit_measurement(struct integrity_iint_cache *iint,
 {
 	struct audit_buffer *ab;
 	char hash[(iint->ima_hash->length * 2) + 1];
+	const char *algo_name = hash_algo_name[iint->ima_hash->algo];
+	char algo_hash[sizeof(hash) + strlen(algo_name) + 2];
 	int i;
 
 	if (iint->flags & IMA_AUDITED)
@@ -287,7 +289,8 @@ void ima_audit_measurement(struct integrity_iint_cache *iint,
 	audit_log_format(ab, "file=");
 	audit_log_untrustedstring(ab, filename);
 	audit_log_format(ab, " hash=");
-	audit_log_untrustedstring(ab, hash);
+	snprintf(algo_hash, sizeof(algo_hash), "%s:%s", algo_name, hash);
+	audit_log_untrustedstring(ab, algo_hash);
 
 	audit_log_task_info(ab, current);
 	audit_log_end(ab);
-- 
cgit v1.2.3


From add1c05dceb495a45036d66cdcbb3b2306de26c1 Mon Sep 17 00:00:00 2001
From: Roberto Sassu <roberto.sassu@polito.it>
Date: Fri, 7 Jun 2013 12:16:39 +0200
Subject: ima: defer determining the appraisal hash algorithm for 'ima'
 template

The same hash algorithm should be used for calculating the file
data hash for the IMA measurement list, as for appraising the file
data integrity.  (The appraise hash algorithm is stored in the
'security.ima' extended attribute.)  The exception is when the
reference file data hash digest, stored in the extended attribute,
is larger than the one supported by the template.  In this case,
the file data hash needs to be calculated twice, once for the
measurement list and, again, for appraisal.

Signed-off-by: Roberto Sassu <roberto.sassu@polito.it>
Signed-off-by: Mimi Zohar <zohar@linux.vnet.ibm.com>
---
 security/integrity/ima/ima_main.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

(limited to 'security')

diff --git a/security/integrity/ima/ima_main.c b/security/integrity/ima/ima_main.c
index 5e8b1f7becd2..0b11bb49ac4f 100644
--- a/security/integrity/ima/ima_main.c
+++ b/security/integrity/ima/ima_main.c
@@ -145,6 +145,7 @@ static int process_measurement(struct file *file, const char *filename,
 {
 	struct inode *inode = file_inode(file);
 	struct integrity_iint_cache *iint;
+	struct ima_template_desc *template_desc = ima_template_desc_current();
 	char *pathbuf = NULL;
 	const char *pathname = NULL;
 	int rc = -ENOMEM, action, must_appraise, _func;
@@ -188,7 +189,10 @@ static int process_measurement(struct file *file, const char *filename,
 		goto out_digsig;
 	}
 
-	if (action & IMA_APPRAISE_SUBMASK)
+	if (strcmp(template_desc->name, IMA_TEMPLATE_IMA_NAME) == 0) {
+		if (action & IMA_APPRAISE_SUBMASK)
+			xattr_ptr = &xattr_value;
+	} else
 		xattr_ptr = &xattr_value;
 
 	rc = ima_collect_measurement(iint, file, xattr_ptr, &xattr_len);
-- 
cgit v1.2.3


From 4286587dccd43d4f81fa227e413ed7e909895342 Mon Sep 17 00:00:00 2001
From: Mimi Zohar <zohar@linux.vnet.ibm.com>
Date: Fri, 7 Jun 2013 12:16:34 +0200
Subject: ima: add Kconfig default measurement list template

This patch adds a Kconfig option to select the default IMA
measurement list template.  The 'ima' template limited the
filedata hash to 20 bytes and the pathname to 255 charaters.
The 'ima-ng' measurement list template permits larger hash
digests and longer pathnames.

Changelog:
- keep 'select CRYPTO_HASH_INFO' in 'config IMA' section (Kconfig)
  (Roberto Sassu);
- removed trailing whitespaces (Roberto Sassu).
- Lindent fixes

Signed-off-by: Mimi Zohar <zohar@us.ibm.com>
Signed-off-by: Roberto Sassu <roberto.sassu@polito.it>
---
 security/integrity/ima/Kconfig        | 25 +++++++++++++++++++++++++
 security/integrity/ima/ima_template.c |  4 ++--
 2 files changed, 27 insertions(+), 2 deletions(-)

(limited to 'security')

diff --git a/security/integrity/ima/Kconfig b/security/integrity/ima/Kconfig
index e6628e783df1..de26cc873ae6 100644
--- a/security/integrity/ima/Kconfig
+++ b/security/integrity/ima/Kconfig
@@ -46,6 +46,31 @@ config IMA_LSM_RULES
 	help
 	  Disabling this option will disregard LSM based policy rules.
 
+choice
+	prompt "Default template"
+	default IMA_NG_TEMPLATE
+	depends on IMA
+	help
+	  Select the default IMA measurement template.
+
+	  The original 'ima' measurement list template contains a
+	  hash, defined as 20 bytes, and a null terminated pathname,
+	  limited to 255 characters.  The 'ima-ng' measurement list
+	  template permits both larger hash digests and longer
+	  pathnames.
+
+	config IMA_TEMPLATE
+		bool "ima"
+	config IMA_NG_TEMPLATE
+		bool "ima-ng (default)"
+endchoice
+
+config IMA_DEFAULT_TEMPLATE
+	string
+	depends on IMA
+	default "ima" if IMA_TEMPLATE
+	default "ima-ng" if IMA_NG_TEMPLATE
+
 config IMA_APPRAISE
 	bool "Appraise integrity measurements"
 	depends on IMA
diff --git a/security/integrity/ima/ima_template.c b/security/integrity/ima/ima_template.c
index 1c4cf194592c..c28ff9bf8f32 100644
--- a/security/integrity/ima/ima_template.c
+++ b/security/integrity/ima/ima_template.c
@@ -127,8 +127,8 @@ static int init_defined_templates(void)
 struct ima_template_desc *ima_template_desc_current(void)
 {
 	if (!ima_template)
-		ima_template = lookup_template_desc(IMA_TEMPLATE_IMA_NAME);
-
+		ima_template =
+		    lookup_template_desc(CONFIG_IMA_DEFAULT_TEMPLATE);
 	return ima_template;
 }
 
-- 
cgit v1.2.3


From 9b9d4ce592d283fc4c01da746c02a840c499bb7e Mon Sep 17 00:00:00 2001
From: Roberto Sassu <roberto.sassu@polito.it>
Date: Fri, 7 Jun 2013 12:16:35 +0200
Subject: ima: define kernel parameter 'ima_template=' to change configured
 default

This patch allows users to specify from the kernel command line the
template descriptor, among those defined, that will be used to generate
and display measurement entries. If an user specifies a wrong template,
IMA reverts to the template descriptor set in the kernel configuration.

Signed-off-by: Roberto Sassu <roberto.sassu@polito.it>
Signed-off-by: Mimi Zohar <zohar@linux.vnet.ibm.com>
---
 Documentation/kernel-parameters.txt   |  5 +++++
 security/integrity/ima/ima_template.c | 31 +++++++++++++++++++++++++++++++
 2 files changed, 36 insertions(+)

(limited to 'security')

diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt
index 1a036cd972fb..2b78cb55ac34 100644
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@@ -1190,6 +1190,11 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 			programs exec'd, files mmap'd for exec, and all files
 			opened for read by uid=0.
 
+	ima_template=   [IMA]
+			Select one of defined IMA measurements template formats.
+			Formats: { "ima" | "ima-ng" }
+			Default: "ima-ng"
+
 	init=		[KNL]
 			Format: <full_path>
 			Run specified binary instead of /sbin/init as init
diff --git a/security/integrity/ima/ima_template.c b/security/integrity/ima/ima_template.c
index c28ff9bf8f32..000221419f6c 100644
--- a/security/integrity/ima/ima_template.c
+++ b/security/integrity/ima/ima_template.c
@@ -12,6 +12,8 @@
  * File: ima_template.c
  *      Helpers to manage template descriptors.
  */
+#include <crypto/hash_info.h>
+
 #include "ima.h"
 #include "ima_template_lib.h"
 
@@ -32,6 +34,35 @@ static struct ima_template_field supported_fields[] = {
 };
 
 static struct ima_template_desc *ima_template;
+static struct ima_template_desc *lookup_template_desc(const char *name);
+
+static int __init ima_template_setup(char *str)
+{
+	struct ima_template_desc *template_desc;
+	int template_len = strlen(str);
+
+	/*
+	 * Verify that a template with the supplied name exists.
+	 * If not, use CONFIG_IMA_DEFAULT_TEMPLATE.
+	 */
+	template_desc = lookup_template_desc(str);
+	if (!template_desc)
+		return 1;
+
+	/*
+	 * Verify whether the current hash algorithm is supported
+	 * by the 'ima' template.
+	 */
+	if (template_len == 3 && strcmp(str, IMA_TEMPLATE_IMA_NAME) == 0 &&
+	    ima_hash_algo != HASH_ALGO_SHA1 && ima_hash_algo != HASH_ALGO_MD5) {
+		pr_err("IMA: template does not support hash alg\n");
+		return 1;
+	}
+
+	ima_template = template_desc;
+	return 1;
+}
+__setup("ima_template=", ima_template_setup);
 
 static struct ima_template_desc *lookup_template_desc(const char *name)
 {
-- 
cgit v1.2.3


From e7a2ad7eb6f48ad80c70a22dd8167fb34b409466 Mon Sep 17 00:00:00 2001
From: Mimi Zohar <zohar@linux.vnet.ibm.com>
Date: Fri, 7 Jun 2013 12:16:37 +0200
Subject: ima: enable support for larger default filedata hash algorithms

The IMA measurement list contains two hashes - a template data hash
and a filedata hash.  The template data hash is committed to the TPM,
which is limited, by the TPM v1.2 specification, to 20 bytes.  The
filedata hash is defined as 20 bytes as well.

Now that support for variable length measurement list templates was
added, the filedata hash is not limited to 20 bytes.  This patch adds
Kconfig support for defining larger default filedata hash algorithms
and replacing the builtin default with one specified on the kernel
command line.

<uapi/linux/hash_info.h> contains a list of hash algorithms.  The
Kconfig default hash algorithm is a subset of this list, but any hash
algorithm included in the list can be specified at boot, using the
'ima_hash=' kernel command line option.

Changelog v2:
- update Kconfig

Changelog:
- support hashes that are configured
- use generic HASH_ALGO_ definitions
- add Kconfig support
- hash_setup must be called only once (Dmitry)
- removed trailing whitespaces (Roberto Sassu)

Signed-off-by: Mimi Zohar <zohar@us.ibm.com>
Signed-off-by: Roberto Sassu <roberto.sassu@polito.it>
---
 Documentation/kernel-parameters.txt |  6 +++++-
 security/integrity/ima/Kconfig      | 35 +++++++++++++++++++++++++++++++++++
 security/integrity/ima/ima_main.c   | 26 ++++++++++++++++++++++++--
 3 files changed, 64 insertions(+), 3 deletions(-)

(limited to 'security')

diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt
index 2b78cb55ac34..1e8761c89a2c 100644
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@@ -1181,9 +1181,13 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 			owned by uid=0.
 
 	ima_hash=	[IMA]
-			Format: { "sha1" | "md5" }
+			Format: { md5 | sha1 | rmd160 | sha256 | sha384
+				   | sha512 | ... }
 			default: "sha1"
 
+			The list of supported hash algorithms is defined
+			in crypto/hash_info.h.
+
 	ima_tcb		[IMA]
 			Load a policy which meets the needs of the Trusted
 			Computing Base.  This means IMA will measure all
diff --git a/security/integrity/ima/Kconfig b/security/integrity/ima/Kconfig
index de26cc873ae6..351a58ed56ab 100644
--- a/security/integrity/ima/Kconfig
+++ b/security/integrity/ima/Kconfig
@@ -71,6 +71,41 @@ config IMA_DEFAULT_TEMPLATE
 	default "ima" if IMA_TEMPLATE
 	default "ima-ng" if IMA_NG_TEMPLATE
 
+choice
+	prompt "Default integrity hash algorithm"
+	default IMA_DEFAULT_HASH_SHA1
+	depends on IMA
+	help
+	   Select the default hash algorithm used for the measurement
+	   list, integrity appraisal and audit log.  The compiled default
+	   hash algorithm can be overwritten using the kernel command
+	   line 'ima_hash=' option.
+
+	config IMA_DEFAULT_HASH_SHA1
+		bool "SHA1 (default)"
+		depends on CRYPTO_SHA1
+
+	config IMA_DEFAULT_HASH_SHA256
+		bool "SHA256"
+		depends on CRYPTO_SHA256 && !IMA_TEMPLATE
+
+	config IMA_DEFAULT_HASH_SHA512
+		bool "SHA512"
+		depends on CRYPTO_SHA512 && !IMA_TEMPLATE
+
+	config IMA_DEFAULT_HASH_WP512
+		bool "WP512"
+		depends on CRYPTO_WP512 && !IMA_TEMPLATE
+endchoice
+
+config IMA_DEFAULT_HASH
+	string
+	depends on IMA
+	default "sha1" if IMA_DEFAULT_HASH_SHA1
+	default "sha256" if IMA_DEFAULT_HASH_SHA256
+	default "sha512" if IMA_DEFAULT_HASH_SHA512
+	default "wp512" if IMA_DEFAULT_HASH_WP512
+
 config IMA_APPRAISE
 	bool "Appraise integrity measurements"
 	depends on IMA
diff --git a/security/integrity/ima/ima_main.c b/security/integrity/ima/ima_main.c
index 0b11bb49ac4f..14d4cb557894 100644
--- a/security/integrity/ima/ima_main.c
+++ b/security/integrity/ima/ima_main.c
@@ -37,11 +37,32 @@ int ima_appraise;
 #endif
 
 int ima_hash_algo = HASH_ALGO_SHA1;
+static int hash_setup_done;
 
 static int __init hash_setup(char *str)
 {
-	if (strncmp(str, "md5", 3) == 0)
-		ima_hash_algo = HASH_ALGO_MD5;
+	struct ima_template_desc *template_desc = ima_template_desc_current();
+	int i;
+
+	if (hash_setup_done)
+		return 1;
+
+	if (strcmp(template_desc->name, IMA_TEMPLATE_IMA_NAME) == 0) {
+		if (strncmp(str, "sha1", 4) == 0)
+			ima_hash_algo = HASH_ALGO_SHA1;
+		else if (strncmp(str, "md5", 3) == 0)
+			ima_hash_algo = HASH_ALGO_MD5;
+		goto out;
+	}
+
+	for (i = 0; i < HASH_ALGO__LAST; i++) {
+		if (strcmp(str, hash_algo_name[i]) == 0) {
+			ima_hash_algo = i;
+			break;
+		}
+	}
+out:
+	hash_setup_done = 1;
 	return 1;
 }
 __setup("ima_hash=", hash_setup);
@@ -306,6 +327,7 @@ static int __init init_ima(void)
 {
 	int error;
 
+	hash_setup(CONFIG_IMA_DEFAULT_HASH);
 	error = ima_init();
 	if (!error)
 		ima_initialized = 1;
-- 
cgit v1.2.3


From 3ea7a56067e663278470c04fd655adf809e72d4d Mon Sep 17 00:00:00 2001
From: Dmitry Kasatkin <d.kasatkin@samsung.com>
Date: Mon, 12 Aug 2013 11:22:51 +0300
Subject: ima: provide hash algo info in the xattr

All files labeled with 'security.ima' hashes, are hashed using the
same hash algorithm.  Changing from one hash algorithm to another,
requires relabeling the filesystem.  This patch defines a new xattr
type, which includes the hash algorithm, permitting different files
to be hashed with different algorithms.

Signed-off-by: Dmitry Kasatkin <d.kasatkin@samsung.com>
Signed-off-by: Mimi Zohar <zohar@linux.vnet.ibm.com>
---
 security/integrity/ima/ima_appraise.c | 61 +++++++++++++++++++++++++++--------
 security/integrity/integrity.h        | 13 +++++++-
 2 files changed, 59 insertions(+), 15 deletions(-)

(limited to 'security')

diff --git a/security/integrity/ima/ima_appraise.c b/security/integrity/ima/ima_appraise.c
index 116630ca5ff3..734e9468aca0 100644
--- a/security/integrity/ima/ima_appraise.c
+++ b/security/integrity/ima/ima_appraise.c
@@ -15,6 +15,7 @@
 #include <linux/magic.h>
 #include <linux/ima.h>
 #include <linux/evm.h>
+#include <crypto/hash_info.h>
 
 #include "ima.h"
 
@@ -45,10 +46,22 @@ int ima_must_appraise(struct inode *inode, int mask, enum ima_hooks func)
 static int ima_fix_xattr(struct dentry *dentry,
 			 struct integrity_iint_cache *iint)
 {
-	iint->ima_hash->type = IMA_XATTR_DIGEST;
-	return __vfs_setxattr_noperm(dentry, XATTR_NAME_IMA,
-				     &iint->ima_hash->type,
-				     1 + iint->ima_hash->length, 0);
+	int rc, offset;
+	u8 algo = iint->ima_hash->algo;
+
+	if (algo <= HASH_ALGO_SHA1) {
+		offset = 1;
+		iint->ima_hash->xattr.sha1.type = IMA_XATTR_DIGEST;
+	} else {
+		offset = 0;
+		iint->ima_hash->xattr.ng.type = IMA_XATTR_DIGEST_NG;
+		iint->ima_hash->xattr.ng.algo = algo;
+	}
+	rc = __vfs_setxattr_noperm(dentry, XATTR_NAME_IMA,
+				   &iint->ima_hash->xattr.data[offset],
+				   (sizeof(iint->ima_hash->xattr) - offset) +
+				   iint->ima_hash->length, 0);
+	return rc;
 }
 
 /* Return specific func appraised cached result */
@@ -112,15 +125,31 @@ void ima_get_hash_algo(struct evm_ima_xattr_data *xattr_value, int xattr_len,
 {
 	struct signature_v2_hdr *sig;
 
-	if (!xattr_value || xattr_len < 0 || xattr_len <= 1 + sizeof(*sig))
+	if (!xattr_value || xattr_len < 2)
 		return;
 
-	sig = (typeof(sig)) xattr_value->digest;
-
-	if (xattr_value->type != EVM_IMA_XATTR_DIGSIG || sig->version != 2)
-		return;
-
-	hash->algo = sig->hash_algo;
+	switch (xattr_value->type) {
+	case EVM_IMA_XATTR_DIGSIG:
+		sig = (typeof(sig))xattr_value;
+		if (sig->version != 2 || xattr_len <= sizeof(*sig))
+			return;
+		hash->algo = sig->hash_algo;
+		break;
+	case IMA_XATTR_DIGEST_NG:
+		hash->algo = xattr_value->digest[0];
+		break;
+	case IMA_XATTR_DIGEST:
+		/* this is for backward compatibility */
+		if (xattr_len == 21) {
+			unsigned int zero = 0;
+			if (!memcmp(&xattr_value->digest[16], &zero, 4))
+				hash->algo = HASH_ALGO_MD5;
+			else
+				hash->algo = HASH_ALGO_SHA1;
+		} else if (xattr_len == 17)
+			hash->algo = HASH_ALGO_MD5;
+		break;
+	}
 }
 
 int ima_read_xattr(struct dentry *dentry,
@@ -153,7 +182,7 @@ int ima_appraise_measurement(int func, struct integrity_iint_cache *iint,
 	enum integrity_status status = INTEGRITY_UNKNOWN;
 	const char *op = "appraise_data";
 	char *cause = "unknown";
-	int rc = xattr_len;
+	int rc = xattr_len, hash_start = 0;
 
 	if (!ima_appraise)
 		return 0;
@@ -180,17 +209,21 @@ int ima_appraise_measurement(int func, struct integrity_iint_cache *iint,
 		goto out;
 	}
 	switch (xattr_value->type) {
+	case IMA_XATTR_DIGEST_NG:
+		/* first byte contains algorithm id */
+		hash_start = 1;
 	case IMA_XATTR_DIGEST:
 		if (iint->flags & IMA_DIGSIG_REQUIRED) {
 			cause = "IMA signature required";
 			status = INTEGRITY_FAIL;
 			break;
 		}
-		if (xattr_len - 1 >= iint->ima_hash->length)
+		if (xattr_len - sizeof(xattr_value->type) - hash_start >=
+				iint->ima_hash->length)
 			/* xattr length may be longer. md5 hash in previous
 			   version occupied 20 bytes in xattr, instead of 16
 			 */
-			rc = memcmp(xattr_value->digest,
+			rc = memcmp(&xattr_value->digest[hash_start],
 				    iint->ima_hash->digest,
 				    iint->ima_hash->length);
 		else
diff --git a/security/integrity/integrity.h b/security/integrity/integrity.h
index 5429ca59125b..2fb5e53e927f 100644
--- a/security/integrity/integrity.h
+++ b/security/integrity/integrity.h
@@ -54,6 +54,7 @@ enum evm_ima_xattr_type {
 	IMA_XATTR_DIGEST = 0x01,
 	EVM_XATTR_HMAC,
 	EVM_IMA_XATTR_DIGSIG,
+	IMA_XATTR_DIGEST_NG,
 };
 
 struct evm_ima_xattr_data {
@@ -66,7 +67,17 @@ struct evm_ima_xattr_data {
 struct ima_digest_data {
 	u8 algo;
 	u8 length;
-	u8 type;
+	union {
+		struct {
+			u8 unused;
+			u8 type;
+		} sha1;
+		struct {
+			u8 type;
+			u8 algo;
+		} ng;
+		u8 data[2];
+	} xattr;
 	u8 digest[0];
 } __packed;
 
-- 
cgit v1.2.3


From b5dfd8075bc26636d11c3d8888940198afbf5112 Mon Sep 17 00:00:00 2001
From: Casey Schaufler <casey@schaufler-ca.com>
Date: Tue, 22 Oct 2013 11:47:45 -0700
Subject: Smack: Ptrace access check mode

When the ptrace security hooks were split the addition of
a mode parameter was not taken advantage of in the Smack
ptrace access check. This changes the access check from
always looking for read and write access to using the
passed mode. This will make use of /proc much happier.

Targeted for git://git.gitorious.org/smack-next/kernel.git

Signed-off-by: Casey Schaufler <casey@schaufler-ca.com>
---
 security/smack/smack_lsm.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'security')

diff --git a/security/smack/smack_lsm.c b/security/smack/smack_lsm.c
index 88d366e55793..b0be893ad44d 100644
--- a/security/smack/smack_lsm.c
+++ b/security/smack/smack_lsm.c
@@ -185,7 +185,7 @@ static int smack_ptrace_access_check(struct task_struct *ctp, unsigned int mode)
 	smk_ad_init(&ad, __func__, LSM_AUDIT_DATA_TASK);
 	smk_ad_setfield_u_tsk(&ad, ctp);
 
-	rc = smk_curacc(skp->smk_known, MAY_READWRITE, &ad);
+	rc = smk_curacc(skp->smk_known, mode, &ad);
 	return rc;
 }
 
-- 
cgit v1.2.3


From dd0c6e86f66080869ca0a48c78fb9bfbe4cf156f Mon Sep 17 00:00:00 2001
From: John Johansen <john.johansen@canonical.com>
Date: Tue, 8 Oct 2013 05:37:18 -0700
Subject: apparmor: fix capability to not use the current task, during
 reporting

Mediation is based off of the cred but auditing includes the current
task which may not be related to the actual request.

Signed-off-by: John Johansen <john.johansen@canonical.com>
---
 security/apparmor/capability.c         | 15 +++++----------
 security/apparmor/domain.c             |  2 +-
 security/apparmor/include/capability.h |  5 ++---
 security/apparmor/include/ipc.h        |  4 ++--
 security/apparmor/ipc.c                |  9 ++++-----
 security/apparmor/lsm.c                |  2 +-
 6 files changed, 15 insertions(+), 22 deletions(-)

(limited to 'security')

diff --git a/security/apparmor/capability.c b/security/apparmor/capability.c
index 84d1f5f53877..1101c6f64bb7 100644
--- a/security/apparmor/capability.c
+++ b/security/apparmor/capability.c
@@ -53,8 +53,7 @@ static void audit_cb(struct audit_buffer *ab, void *va)
 
 /**
  * audit_caps - audit a capability
- * @profile: profile confining task (NOT NULL)
- * @task: task capability test was performed against (NOT NULL)
+ * @profile: profile being tested for confinement (NOT NULL)
  * @cap: capability tested
  * @error: error code returned by test
  *
@@ -63,8 +62,7 @@ static void audit_cb(struct audit_buffer *ab, void *va)
  *
  * Returns: 0 or sa->error on success,  error code on failure
  */
-static int audit_caps(struct aa_profile *profile, struct task_struct *task,
-		      int cap, int error)
+static int audit_caps(struct aa_profile *profile, int cap, int error)
 {
 	struct audit_cache *ent;
 	int type = AUDIT_APPARMOR_AUTO;
@@ -73,7 +71,6 @@ static int audit_caps(struct aa_profile *profile, struct task_struct *task,
 	sa.type = LSM_AUDIT_DATA_CAP;
 	sa.aad = &aad;
 	sa.u.cap = cap;
-	sa.aad->tsk = task;
 	sa.aad->op = OP_CAPABLE;
 	sa.aad->error = error;
 
@@ -124,8 +121,7 @@ static int profile_capable(struct aa_profile *profile, int cap)
 
 /**
  * aa_capable - test permission to use capability
- * @task: task doing capability test against (NOT NULL)
- * @profile: profile confining @task (NOT NULL)
+ * @profile: profile being tested against (NOT NULL)
  * @cap: capability to be tested
  * @audit: whether an audit record should be generated
  *
@@ -133,8 +129,7 @@ static int profile_capable(struct aa_profile *profile, int cap)
  *
  * Returns: 0 on success, or else an error code.
  */
-int aa_capable(struct task_struct *task, struct aa_profile *profile, int cap,
-	       int audit)
+int aa_capable(struct aa_profile *profile, int cap, int audit)
 {
 	int error = profile_capable(profile, cap);
 
@@ -144,5 +139,5 @@ int aa_capable(struct task_struct *task, struct aa_profile *profile, int cap,
 		return error;
 	}
 
-	return audit_caps(profile, task, cap, error);
+	return audit_caps(profile, cap, error);
 }
diff --git a/security/apparmor/domain.c b/security/apparmor/domain.c
index 26c607c971f5..e5538a12d162 100644
--- a/security/apparmor/domain.c
+++ b/security/apparmor/domain.c
@@ -75,7 +75,7 @@ static int may_change_ptraced_domain(struct task_struct *task,
 	if (!tracer || unconfined(tracerp))
 		goto out;
 
-	error = aa_may_ptrace(tracer, tracerp, to_profile, PTRACE_MODE_ATTACH);
+	error = aa_may_ptrace(tracerp, to_profile, PTRACE_MODE_ATTACH);
 
 out:
 	rcu_read_unlock();
diff --git a/security/apparmor/include/capability.h b/security/apparmor/include/capability.h
index 2e7c9d6a2f3b..fc3fa381d850 100644
--- a/security/apparmor/include/capability.h
+++ b/security/apparmor/include/capability.h
@@ -4,7 +4,7 @@
  * This file contains AppArmor capability mediation definitions.
  *
  * Copyright (C) 1998-2008 Novell/SUSE
- * Copyright 2009-2010 Canonical Ltd.
+ * Copyright 2009-2013 Canonical Ltd.
  *
  * This program is free software; you can redistribute it and/or
  * modify it under the terms of the GNU General Public License as
@@ -38,8 +38,7 @@ struct aa_caps {
 
 extern struct aa_fs_entry aa_fs_entry_caps[];
 
-int aa_capable(struct task_struct *task, struct aa_profile *profile, int cap,
-	       int audit);
+int aa_capable(struct aa_profile *profile, int cap, int audit);
 
 static inline void aa_free_cap_rules(struct aa_caps *caps)
 {
diff --git a/security/apparmor/include/ipc.h b/security/apparmor/include/ipc.h
index aeda0fbc8b2f..288ca76e2fb1 100644
--- a/security/apparmor/include/ipc.h
+++ b/security/apparmor/include/ipc.h
@@ -19,8 +19,8 @@
 
 struct aa_profile;
 
-int aa_may_ptrace(struct task_struct *tracer_task, struct aa_profile *tracer,
-		  struct aa_profile *tracee, unsigned int mode);
+int aa_may_ptrace(struct aa_profile *tracer, struct aa_profile *tracee,
+		  unsigned int mode);
 
 int aa_ptrace(struct task_struct *tracer, struct task_struct *tracee,
 	      unsigned int mode);
diff --git a/security/apparmor/ipc.c b/security/apparmor/ipc.c
index c51d2266587e..777ac1c47253 100644
--- a/security/apparmor/ipc.c
+++ b/security/apparmor/ipc.c
@@ -54,15 +54,14 @@ static int aa_audit_ptrace(struct aa_profile *profile,
 
 /**
  * aa_may_ptrace - test if tracer task can trace the tracee
- * @tracer_task: task who will do the tracing  (NOT NULL)
  * @tracer: profile of the task doing the tracing  (NOT NULL)
  * @tracee: task to be traced
  * @mode: whether PTRACE_MODE_READ || PTRACE_MODE_ATTACH
  *
  * Returns: %0 else error code if permission denied or error
  */
-int aa_may_ptrace(struct task_struct *tracer_task, struct aa_profile *tracer,
-		  struct aa_profile *tracee, unsigned int mode)
+int aa_may_ptrace(struct aa_profile *tracer, struct aa_profile *tracee,
+		  unsigned int mode)
 {
 	/* TODO: currently only based on capability, not extended ptrace
 	 *       rules,
@@ -72,7 +71,7 @@ int aa_may_ptrace(struct task_struct *tracer_task, struct aa_profile *tracer,
 	if (unconfined(tracer) || tracer == tracee)
 		return 0;
 	/* log this capability request */
-	return aa_capable(tracer_task, tracer, CAP_SYS_PTRACE, 1);
+	return aa_capable(tracer, CAP_SYS_PTRACE, 1);
 }
 
 /**
@@ -101,7 +100,7 @@ int aa_ptrace(struct task_struct *tracer, struct task_struct *tracee,
 	if (!unconfined(tracer_p)) {
 		struct aa_profile *tracee_p = aa_get_task_profile(tracee);
 
-		error = aa_may_ptrace(tracer, tracer_p, tracee_p, mode);
+		error = aa_may_ptrace(tracer_p, tracee_p, mode);
 		error = aa_audit_ptrace(tracer_p, tracee_p, error);
 
 		aa_put_profile(tracee_p);
diff --git a/security/apparmor/lsm.c b/security/apparmor/lsm.c
index fb99e18123b4..4257b7e2796b 100644
--- a/security/apparmor/lsm.c
+++ b/security/apparmor/lsm.c
@@ -145,7 +145,7 @@ static int apparmor_capable(const struct cred *cred, struct user_namespace *ns,
 	if (!error) {
 		profile = aa_cred_profile(cred);
 		if (!unconfined(profile))
-			error = aa_capable(current, profile, cap, audit);
+			error = aa_capable(profile, cap, audit);
 	}
 	return error;
 }
-- 
cgit v1.2.3


From 61e3fb8acaea0ca4303ef123bae7edf8435dc2b7 Mon Sep 17 00:00:00 2001
From: John Johansen <john.johansen@canonical.com>
Date: Tue, 8 Oct 2013 05:37:26 -0700
Subject: apparmor: remove tsk field from the apparmor_audit_struct

Now that aa_capabile no longer sets the task field it can be removed
and the lsm_audit version of the field can be used.

Signed-off-by: John Johansen <john.johansen@canonical.com>
---
 security/apparmor/audit.c | 10 ++--------
 1 file changed, 2 insertions(+), 8 deletions(-)

(limited to 'security')

diff --git a/security/apparmor/audit.c b/security/apparmor/audit.c
index 031d2d9dd695..e32c4483fba1 100644
--- a/security/apparmor/audit.c
+++ b/security/apparmor/audit.c
@@ -111,7 +111,7 @@ static const char *const aa_audit_type[] = {
 static void audit_pre(struct audit_buffer *ab, void *ca)
 {
 	struct common_audit_data *sa = ca;
-	struct task_struct *tsk = sa->aad->tsk ? sa->aad->tsk : current;
+	struct task_struct *tsk = sa->u.tsk ? sa->u.tsk : current;
 
 	if (aa_g_audit_header) {
 		audit_log_format(ab, "apparmor=");
@@ -149,12 +149,6 @@ static void audit_pre(struct audit_buffer *ab, void *ca)
 		audit_log_format(ab, " name=");
 		audit_log_untrustedstring(ab, sa->aad->name);
 	}
-
-	if (sa->aad->tsk) {
-		audit_log_format(ab, " pid=%d comm=", tsk->pid);
-		audit_log_untrustedstring(ab, tsk->comm);
-	}
-
 }
 
 /**
@@ -212,7 +206,7 @@ int aa_audit(int type, struct aa_profile *profile, gfp_t gfp,
 
 	if (sa->aad->type == AUDIT_APPARMOR_KILL)
 		(void)send_sig_info(SIGKILL, NULL,
-				    sa->aad->tsk ?  sa->aad->tsk : current);
+				    sa->u.tsk ?  sa->u.tsk : current);
 
 	if (sa->aad->type == AUDIT_APPARMOR_ALLOWED)
 		return complain_error(sa->aad->error);
-- 
cgit v1.2.3


From 4a7fc3018f05f4305723b508b12f3be13b7c4875 Mon Sep 17 00:00:00 2001
From: John Johansen <john.johansen@canonical.com>
Date: Tue, 8 Oct 2013 05:39:02 -0700
Subject: apparmor: remove parent task info from audit logging

The reporting of the parent task info is a vestage from old versions of
apparmor. The need for this information was removed by unique null-
profiles before apparmor was upstreamed so remove this info from logging.

Signed-off-by: John Johansen <john.johansen@canonical.com>
---
 security/apparmor/audit.c         | 6 ------
 security/apparmor/include/audit.h | 1 -
 2 files changed, 7 deletions(-)

(limited to 'security')

diff --git a/security/apparmor/audit.c b/security/apparmor/audit.c
index e32c4483fba1..89c78658031f 100644
--- a/security/apparmor/audit.c
+++ b/security/apparmor/audit.c
@@ -111,7 +111,6 @@ static const char *const aa_audit_type[] = {
 static void audit_pre(struct audit_buffer *ab, void *ca)
 {
 	struct common_audit_data *sa = ca;
-	struct task_struct *tsk = sa->u.tsk ? sa->u.tsk : current;
 
 	if (aa_g_audit_header) {
 		audit_log_format(ab, "apparmor=");
@@ -132,11 +131,6 @@ static void audit_pre(struct audit_buffer *ab, void *ca)
 
 	if (sa->aad->profile) {
 		struct aa_profile *profile = sa->aad->profile;
-		pid_t pid;
-		rcu_read_lock();
-		pid = rcu_dereference(tsk->real_parent)->pid;
-		rcu_read_unlock();
-		audit_log_format(ab, " parent=%d", pid);
 		if (profile->ns != root_ns) {
 			audit_log_format(ab, " namespace=");
 			audit_log_untrustedstring(ab, profile->ns->base.hname);
diff --git a/security/apparmor/include/audit.h b/security/apparmor/include/audit.h
index 30e8d7687259..ba3dfd17f23f 100644
--- a/security/apparmor/include/audit.h
+++ b/security/apparmor/include/audit.h
@@ -109,7 +109,6 @@ struct apparmor_audit_data {
 	void *profile;
 	const char *name;
 	const char *info;
-	struct task_struct *tsk;
 	union {
 		void *target;
 		struct {
-- 
cgit v1.2.3


From 51775fe736f053329faf0f5de7c679ee4cb0023d Mon Sep 17 00:00:00 2001
From: Oleg Nesterov <oleg@redhat.com>
Date: Tue, 8 Oct 2013 05:46:03 -0700
Subject: apparmor: remove the "task" arg from may_change_ptraced_domain()

Unless task == current ptrace_parent(task) is not safe even under
rcu_read_lock() and most of the current users are not right.

So may_change_ptraced_domain(task) looks wrong as well. However it
is always called with task == current so the code is actually fine.
Remove this argument to make this fact clear.

Note: perhaps we should simply kill ptrace_parent(), it buys almost
nothing. And it is obviously racy, perhaps this should be fixed.

Signed-off-by: Oleg Nesterov <oleg@redhat.com>
Signed-off-by: John Johansen <john.johansen@canonical.com>
---
 security/apparmor/domain.c | 14 ++++++--------
 1 file changed, 6 insertions(+), 8 deletions(-)

(limited to 'security')

diff --git a/security/apparmor/domain.c b/security/apparmor/domain.c
index e5538a12d162..452567d3a08e 100644
--- a/security/apparmor/domain.c
+++ b/security/apparmor/domain.c
@@ -50,23 +50,21 @@ void aa_free_domain_entries(struct aa_domain *domain)
 
 /**
  * may_change_ptraced_domain - check if can change profile on ptraced task
- * @task: task we want to change profile of   (NOT NULL)
  * @to_profile: profile to change to  (NOT NULL)
  *
- * Check if the task is ptraced and if so if the tracing task is allowed
+ * Check if current is ptraced and if so if the tracing task is allowed
  * to trace the new domain
  *
  * Returns: %0 or error if change not allowed
  */
-static int may_change_ptraced_domain(struct task_struct *task,
-				     struct aa_profile *to_profile)
+static int may_change_ptraced_domain(struct aa_profile *to_profile)
 {
 	struct task_struct *tracer;
 	struct aa_profile *tracerp = NULL;
 	int error = 0;
 
 	rcu_read_lock();
-	tracer = ptrace_parent(task);
+	tracer = ptrace_parent(current);
 	if (tracer)
 		/* released below */
 		tracerp = aa_get_task_profile(tracer);
@@ -477,7 +475,7 @@ int apparmor_bprm_set_creds(struct linux_binprm *bprm)
 	}
 
 	if (bprm->unsafe & (LSM_UNSAFE_PTRACE | LSM_UNSAFE_PTRACE_CAP)) {
-		error = may_change_ptraced_domain(current, new_profile);
+		error = may_change_ptraced_domain(new_profile);
 		if (error) {
 			aa_put_profile(new_profile);
 			goto audit;
@@ -690,7 +688,7 @@ int aa_change_hat(const char *hats[], int count, u64 token, bool permtest)
 			}
 		}
 
-		error = may_change_ptraced_domain(current, hat);
+		error = may_change_ptraced_domain(hat);
 		if (error) {
 			info = "ptraced";
 			error = -EPERM;
@@ -829,7 +827,7 @@ int aa_change_profile(const char *ns_name, const char *hname, bool onexec,
 	}
 
 	/* check if tracing task is allowed to trace target domain */
-	error = may_change_ptraced_domain(current, target);
+	error = may_change_ptraced_domain(target);
 	if (error) {
 		info = "ptrace prevents transition";
 		goto audit;
-- 
cgit v1.2.3


From 2eaf6b5dcafda2b8c22930eff7f48a364fce1741 Mon Sep 17 00:00:00 2001
From: Josh Boyer <jwboyer@redhat.com>
Date: Wed, 30 Oct 2013 11:15:23 +0000
Subject: KEYS: Make BIG_KEYS boolean

Having the big_keys functionality as a module is very marginally useful.
The userspace code that would use this functionality will get odd error
messages from the keys layer if the module isn't loaded.  The code itself
is fairly small, so just have this as a boolean option and not a tristate.

Signed-off-by: Josh Boyer <jwboyer@fedoraproject.org>
Signed-off-by: David Howells <dhowells@redhat.com>
---
 security/keys/Kconfig | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'security')

diff --git a/security/keys/Kconfig b/security/keys/Kconfig
index 53d8748c9564..a4f3f8c48d6e 100644
--- a/security/keys/Kconfig
+++ b/security/keys/Kconfig
@@ -38,7 +38,7 @@ config PERSISTENT_KEYRINGS
 	  removed if they expire (a default timeout is set upon creation).
 
 config BIG_KEYS
-	tristate "Large payload keys"
+	bool "Large payload keys"
 	depends on KEYS
 	depends on TMPFS
 	help
-- 
cgit v1.2.3


From 74792b0001ee85b845dc82c1a716c6052c2db9de Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Wed, 30 Oct 2013 11:15:24 +0000
Subject: KEYS: Fix a race between negating a key and reading the error set

key_reject_and_link() marking a key as negative and setting the error with
which it was negated races with keyring searches and other things that read
that error.

The fix is to switch the order in which the assignments are done in
key_reject_and_link() and to use memory barriers.

Kudos to Dave Wysochanski <dwysocha@redhat.com> and Scott Mayhew
<smayhew@redhat.com> for tracking this down.

This may be the cause of:

BUG: unable to handle kernel NULL pointer dereference at 0000000000000070
IP: [<ffffffff81219011>] wait_for_key_construction+0x31/0x80
PGD c6b2c3067 PUD c59879067 PMD 0
Oops: 0000 [#1] SMP
last sysfs file: /sys/devices/system/cpu/cpu3/cache/index2/shared_cpu_map
CPU 0
Modules linked in: ...

Pid: 13359, comm: amqzxma0 Not tainted 2.6.32-358.20.1.el6.x86_64 #1 IBM System x3650 M3 -[7945PSJ]-/00J6159
RIP: 0010:[<ffffffff81219011>] wait_for_key_construction+0x31/0x80
RSP: 0018:ffff880c6ab33758  EFLAGS: 00010246
RAX: ffffffff81219080 RBX: 0000000000000000 RCX: 0000000000000002
RDX: ffffffff81219060 RSI: 0000000000000000 RDI: 0000000000000000
RBP: ffff880c6ab33768 R08: 0000000000000000 R09: 0000000000000000
R10: 0000000000000001 R11: 0000000000000000 R12: ffff880adfcbce40
R13: ffffffffa03afb84 R14: ffff880adfcbce40 R15: ffff880adfcbce43
FS:  00007f29b8042700(0000) GS:ffff880028200000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 0000000000000070 CR3: 0000000c613dc000 CR4: 00000000000007f0
DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400
Process amqzxma0 (pid: 13359, threadinfo ffff880c6ab32000, task ffff880c610deae0)
Stack:
 ffff880adfcbce40 0000000000000000 ffff880c6ab337b8 ffffffff81219695
<d> 0000000000000000 ffff880a000000d0 ffff880c6ab337a8 000000000000000f
<d> ffffffffa03afb93 000000000000000f ffff88186c7882c0 0000000000000014
Call Trace:
 [<ffffffff81219695>] request_key+0x65/0xa0
 [<ffffffffa03a0885>] nfs_idmap_request_key+0xc5/0x170 [nfs]
 [<ffffffffa03a0eb4>] nfs_idmap_lookup_id+0x34/0x80 [nfs]
 [<ffffffffa03a1255>] nfs_map_group_to_gid+0x75/0xa0 [nfs]
 [<ffffffffa039a9ad>] decode_getfattr_attrs+0xbdd/0xfb0 [nfs]
 [<ffffffff81057310>] ? __dequeue_entity+0x30/0x50
 [<ffffffff8100988e>] ? __switch_to+0x26e/0x320
 [<ffffffffa039ae03>] decode_getfattr+0x83/0xe0 [nfs]
 [<ffffffffa039b610>] ? nfs4_xdr_dec_getattr+0x0/0xa0 [nfs]
 [<ffffffffa039b69f>] nfs4_xdr_dec_getattr+0x8f/0xa0 [nfs]
 [<ffffffffa02dada4>] rpcauth_unwrap_resp+0x84/0xb0 [sunrpc]
 [<ffffffffa039b610>] ? nfs4_xdr_dec_getattr+0x0/0xa0 [nfs]
 [<ffffffffa02cf923>] call_decode+0x1b3/0x800 [sunrpc]
 [<ffffffff81096de0>] ? wake_bit_function+0x0/0x50
 [<ffffffffa02cf770>] ? call_decode+0x0/0x800 [sunrpc]
 [<ffffffffa02d99a7>] __rpc_execute+0x77/0x350 [sunrpc]
 [<ffffffff81096c67>] ? bit_waitqueue+0x17/0xd0
 [<ffffffffa02d9ce1>] rpc_execute+0x61/0xa0 [sunrpc]
 [<ffffffffa02d03a5>] rpc_run_task+0x75/0x90 [sunrpc]
 [<ffffffffa02d04c2>] rpc_call_sync+0x42/0x70 [sunrpc]
 [<ffffffffa038ff80>] _nfs4_call_sync+0x30/0x40 [nfs]
 [<ffffffffa038836c>] _nfs4_proc_getattr+0xac/0xc0 [nfs]
 [<ffffffff810aac87>] ? futex_wait+0x227/0x380
 [<ffffffffa038b856>] nfs4_proc_getattr+0x56/0x80 [nfs]
 [<ffffffffa0371403>] __nfs_revalidate_inode+0xe3/0x220 [nfs]
 [<ffffffffa037158e>] nfs_revalidate_mapping+0x4e/0x170 [nfs]
 [<ffffffffa036f147>] nfs_file_read+0x77/0x130 [nfs]
 [<ffffffff811811aa>] do_sync_read+0xfa/0x140
 [<ffffffff81096da0>] ? autoremove_wake_function+0x0/0x40
 [<ffffffff8100bb8e>] ? apic_timer_interrupt+0xe/0x20
 [<ffffffff8100b9ce>] ? common_interrupt+0xe/0x13
 [<ffffffff81228ffb>] ? selinux_file_permission+0xfb/0x150
 [<ffffffff8121bed6>] ? security_file_permission+0x16/0x20
 [<ffffffff81181a95>] vfs_read+0xb5/0x1a0
 [<ffffffff81181bd1>] sys_read+0x51/0x90
 [<ffffffff810dc685>] ? __audit_syscall_exit+0x265/0x290
 [<ffffffff8100b072>] system_call_fastpath+0x16/0x1b

Signed-off-by: David Howells <dhowells@redhat.com>
cc: Dave Wysochanski <dwysocha@redhat.com>
cc: Scott Mayhew <smayhew@redhat.com>
---
 security/keys/key.c         | 3 ++-
 security/keys/keyring.c     | 1 +
 security/keys/request_key.c | 4 +++-
 3 files changed, 6 insertions(+), 2 deletions(-)

(limited to 'security')

diff --git a/security/keys/key.c b/security/keys/key.c
index d331ea9ef380..55d110f0aced 100644
--- a/security/keys/key.c
+++ b/security/keys/key.c
@@ -557,9 +557,10 @@ int key_reject_and_link(struct key *key,
 	if (!test_bit(KEY_FLAG_INSTANTIATED, &key->flags)) {
 		/* mark the key as being negatively instantiated */
 		atomic_inc(&key->user->nikeys);
+		key->type_data.reject_error = -error;
+		smp_wmb();
 		set_bit(KEY_FLAG_NEGATIVE, &key->flags);
 		set_bit(KEY_FLAG_INSTANTIATED, &key->flags);
-		key->type_data.reject_error = -error;
 		now = current_kernel_time();
 		key->expiry = now.tv_sec + timeout;
 		key_schedule_gc(key->expiry + key_gc_delay);
diff --git a/security/keys/keyring.c b/security/keys/keyring.c
index 9b6f6e09b50c..8c05ebd7203d 100644
--- a/security/keys/keyring.c
+++ b/security/keys/keyring.c
@@ -551,6 +551,7 @@ static int keyring_search_iterator(const void *object, void *iterator_data)
 	if (ctx->flags & KEYRING_SEARCH_DO_STATE_CHECK) {
 		/* we set a different error code if we pass a negative key */
 		if (kflags & (1 << KEY_FLAG_NEGATIVE)) {
+			smp_rmb();
 			ctx->result = ERR_PTR(key->type_data.reject_error);
 			kleave(" = %d [neg]", ctx->skipped_ret);
 			goto skipped;
diff --git a/security/keys/request_key.c b/security/keys/request_key.c
index df94827103d0..381411941cc1 100644
--- a/security/keys/request_key.c
+++ b/security/keys/request_key.c
@@ -596,8 +596,10 @@ int wait_for_key_construction(struct key *key, bool intr)
 			  intr ? TASK_INTERRUPTIBLE : TASK_UNINTERRUPTIBLE);
 	if (ret < 0)
 		return ret;
-	if (test_bit(KEY_FLAG_NEGATIVE, &key->flags))
+	if (test_bit(KEY_FLAG_NEGATIVE, &key->flags)) {
+		smp_rmb();
 		return key->type_data.reject_error;
+	}
 	return key_validate(key);
 }
 EXPORT_SYMBOL(wait_for_key_construction);
-- 
cgit v1.2.3


From 034faeb9ef390d58239e1dce748143f6b35a0d9b Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Wed, 30 Oct 2013 11:15:24 +0000
Subject: KEYS: Fix keyring quota misaccounting on key replacement and unlink

If a key is displaced from a keyring by a matching one, then four more bytes
of quota are allocated to the keyring - despite the fact that the keyring does
not change in size.

Further, when a key is unlinked from a keyring, the four bytes of quota
allocated the link isn't recovered and returned to the user's pool.

The first can be tested by repeating:

	keyctl add big_key a fred @s
	cat /proc/key-users

(Don't put it in a shell loop otherwise the garbage collector won't have time
to clear the displaced keys, thus affecting the result).

This was causing the kerberos keyring to run out of room fairly quickly.

The second can be tested by:

	cat /proc/key-users
	a=`keyctl add user a a @s`
	cat /proc/key-users
	keyctl unlink $a
	sleep 1 # Give RCU a chance to delete the key
	cat /proc/key-users

assuming no system activity that otherwise adds/removes keys, the amount of
key data allocated should go up (say 40/20000 -> 47/20000) and then return to
the original value at the end.

Reported-by: Stephen Gallagher <sgallagh@redhat.com>
Signed-off-by: David Howells <dhowells@redhat.com>
---
 security/keys/keyring.c | 27 +++++++++++++++------------
 1 file changed, 15 insertions(+), 12 deletions(-)

(limited to 'security')

diff --git a/security/keys/keyring.c b/security/keys/keyring.c
index 8c05ebd7203d..d80311e571c3 100644
--- a/security/keys/keyring.c
+++ b/security/keys/keyring.c
@@ -1063,12 +1063,6 @@ int __key_link_begin(struct key *keyring,
 	if (index_key->type == &key_type_keyring)
 		down_write(&keyring_serialise_link_sem);
 
-	/* check that we aren't going to overrun the user's quota */
-	ret = key_payload_reserve(keyring,
-				  keyring->datalen + KEYQUOTA_LINK_BYTES);
-	if (ret < 0)
-		goto error_sem;
-
 	/* Create an edit script that will insert/replace the key in the
 	 * keyring tree.
 	 */
@@ -1078,17 +1072,25 @@ int __key_link_begin(struct key *keyring,
 				  NULL);
 	if (IS_ERR(edit)) {
 		ret = PTR_ERR(edit);
-		goto error_quota;
+		goto error_sem;
+	}
+
+	/* If we're not replacing a link in-place then we're going to need some
+	 * extra quota.
+	 */
+	if (!edit->dead_leaf) {
+		ret = key_payload_reserve(keyring,
+					  keyring->datalen + KEYQUOTA_LINK_BYTES);
+		if (ret < 0)
+			goto error_cancel;
 	}
 
 	*_edit = edit;
 	kleave(" = 0");
 	return 0;
 
-error_quota:
-	/* undo the quota changes */
-	key_payload_reserve(keyring,
-			    keyring->datalen - KEYQUOTA_LINK_BYTES);
+error_cancel:
+	assoc_array_cancel_edit(edit);
 error_sem:
 	if (index_key->type == &key_type_keyring)
 		up_write(&keyring_serialise_link_sem);
@@ -1146,7 +1148,7 @@ void __key_link_end(struct key *keyring,
 	if (index_key->type == &key_type_keyring)
 		up_write(&keyring_serialise_link_sem);
 
-	if (edit) {
+	if (edit && !edit->dead_leaf) {
 		key_payload_reserve(keyring,
 				    keyring->datalen - KEYQUOTA_LINK_BYTES);
 		assoc_array_cancel_edit(edit);
@@ -1243,6 +1245,7 @@ int key_unlink(struct key *keyring, struct key *key)
 		goto error;
 
 	assoc_array_apply_edit(edit);
+	key_payload_reserve(keyring, keyring->datalen - KEYQUOTA_LINK_BYTES);
 	ret = 0;
 
 error:
-- 
cgit v1.2.3


From d2b86970245b64652c4d7799e707dd8bd1533b64 Mon Sep 17 00:00:00 2001
From: Wei Yongjun <yongjun_wei@trendmicro.com.cn>
Date: Wed, 30 Oct 2013 11:23:02 +0800
Subject: KEYS: fix error return code in big_key_instantiate()

Fix to return a negative error code from the error handling
case instead of 0, as done elsewhere in this function.

Signed-off-by: Wei Yongjun <yongjun_wei@trendmicro.com.cn>
Signed-off-by: David Howells <dhowells@redhat.com>
---
 security/keys/big_key.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

(limited to 'security')

diff --git a/security/keys/big_key.c b/security/keys/big_key.c
index 5f9defc4a807..2cf5e62d67af 100644
--- a/security/keys/big_key.c
+++ b/security/keys/big_key.c
@@ -71,8 +71,10 @@ int big_key_instantiate(struct key *key, struct key_preparsed_payload *prep)
 		 * TODO: Encrypt the stored data with a temporary key.
 		 */
 		file = shmem_file_setup("", datalen, 0);
-		if (IS_ERR(file))
+		if (IS_ERR(file)) {
+			ret = PTR_ERR(file);
 			goto err_quota;
+		}
 
 		written = kernel_write(file, prep->data, prep->datalen, 0);
 		if (written != datalen) {
-- 
cgit v1.2.3


From bcbc9b0cf6d8f340a1d166e414f4612b353f7a9b Mon Sep 17 00:00:00 2001
From: Mimi Zohar <zohar@linux.vnet.ibm.com>
Date: Tue, 23 Jul 2013 11:15:00 -0400
Subject: ima: extend the measurement list to include the file signature

This patch defines a new template called 'ima-sig', which includes
the file signature in the template data, in addition to the file's
digest and pathname.

A template is composed of a set of fields.  Associated with each
field is an initialization and display function.  This patch defines
a new template field called 'sig', the initialization function
ima_eventsig_init(), and the display function ima_show_template_sig().

This patch modifies the .field_init() function definition to include
the 'security.ima' extended attribute and length.

Changelog:
- remove unused code (Dmitry Kasatkin)
- avoid calling ima_write_template_field_data() unnecesarily (Roberto Sassu)
- rename DATA_FMT_SIG to DATA_FMT_HEX
- cleanup ima_eventsig_init() based on Roberto's comments

Signed-off-by: Mimi Zohar <zohar@linux.vnet.ibm.com>
Signed-off-by: Dmitry Kasatkin <d.kasatkin@samsung.com>
Signed-off-by: Roberto Sassu <roberto.sassu@polito.it>
---
 security/integrity/ima/Kconfig            |  3 +++
 security/integrity/ima/ima.h              | 10 +++++---
 security/integrity/ima/ima_api.c          | 14 ++++++++----
 security/integrity/ima/ima_init.c         |  2 +-
 security/integrity/ima/ima_main.c         |  3 ++-
 security/integrity/ima/ima_template.c     |  3 +++
 security/integrity/ima/ima_template_lib.c | 38 +++++++++++++++++++++++++++++--
 security/integrity/ima/ima_template_lib.h | 12 +++++++++-
 8 files changed, 73 insertions(+), 12 deletions(-)

(limited to 'security')

diff --git a/security/integrity/ima/Kconfig b/security/integrity/ima/Kconfig
index 351a58ed56ab..81a27971d884 100644
--- a/security/integrity/ima/Kconfig
+++ b/security/integrity/ima/Kconfig
@@ -63,6 +63,8 @@ choice
 		bool "ima"
 	config IMA_NG_TEMPLATE
 		bool "ima-ng (default)"
+	config IMA_SIG_TEMPLATE
+		bool "ima-sig"
 endchoice
 
 config IMA_DEFAULT_TEMPLATE
@@ -70,6 +72,7 @@ config IMA_DEFAULT_TEMPLATE
 	depends on IMA
 	default "ima" if IMA_TEMPLATE
 	default "ima-ng" if IMA_NG_TEMPLATE
+	default "ima-sig" if IMA_SIG_TEMPLATE
 
 choice
 	prompt "Default integrity hash algorithm"
diff --git a/security/integrity/ima/ima.h b/security/integrity/ima/ima.h
index 72d013e190b1..bf03c6a16cc8 100644
--- a/security/integrity/ima/ima.h
+++ b/security/integrity/ima/ima.h
@@ -59,7 +59,8 @@ struct ima_template_field {
 	const char field_id[IMA_TEMPLATE_FIELD_ID_MAX_LEN];
 	int (*field_init) (struct integrity_iint_cache *iint, struct file *file,
 			   const unsigned char *filename,
-			   struct ima_field_data *field_data);
+			   struct evm_ima_xattr_data *xattr_value,
+			   int xattr_len, struct ima_field_data *field_data);
 	void (*field_show) (struct seq_file *m, enum ima_show_type show,
 			    struct ima_field_data *field_data);
 };
@@ -134,12 +135,15 @@ int ima_collect_measurement(struct integrity_iint_cache *iint,
 			    struct evm_ima_xattr_data **xattr_value,
 			    int *xattr_len);
 void ima_store_measurement(struct integrity_iint_cache *iint, struct file *file,
-			   const unsigned char *filename);
+			   const unsigned char *filename,
+			   struct evm_ima_xattr_data *xattr_value,
+			   int xattr_len);
 void ima_audit_measurement(struct integrity_iint_cache *iint,
 			   const unsigned char *filename);
 int ima_alloc_init_template(struct integrity_iint_cache *iint,
 			    struct file *file, const unsigned char *filename,
-			    struct ima_template_entry **entry);
+			    struct evm_ima_xattr_data *xattr_value,
+			    int xattr_len, struct ima_template_entry **entry);
 int ima_store_template(struct ima_template_entry *entry, int violation,
 		       struct inode *inode, const unsigned char *filename);
 const char *ima_d_path(struct path *path, char **pathbuf);
diff --git a/security/integrity/ima/ima_api.c b/security/integrity/ima/ima_api.c
index 5fcc80695d87..0e7540863fc2 100644
--- a/security/integrity/ima/ima_api.c
+++ b/security/integrity/ima/ima_api.c
@@ -26,7 +26,8 @@
  */
 int ima_alloc_init_template(struct integrity_iint_cache *iint,
 			    struct file *file, const unsigned char *filename,
-			    struct ima_template_entry **entry)
+			    struct evm_ima_xattr_data *xattr_value,
+			    int xattr_len, struct ima_template_entry **entry)
 {
 	struct ima_template_desc *template_desc = ima_template_desc_current();
 	int i, result = 0;
@@ -41,6 +42,7 @@ int ima_alloc_init_template(struct integrity_iint_cache *iint,
 		u32 len;
 
 		result = field->field_init(iint, file, filename,
+					   xattr_value, xattr_len,
 					   &((*entry)->template_data[i]));
 		if (result != 0)
 			goto out;
@@ -123,7 +125,8 @@ void ima_add_violation(struct file *file, const unsigned char *filename,
 	/* can overflow, only indicator */
 	atomic_long_inc(&ima_htable.violations);
 
-	result = ima_alloc_init_template(NULL, file, filename, &entry);
+	result = ima_alloc_init_template(NULL, file, filename,
+					 NULL, 0, &entry);
 	if (result < 0) {
 		result = -ENOMEM;
 		goto err_out;
@@ -239,7 +242,9 @@ int ima_collect_measurement(struct integrity_iint_cache *iint,
  * Must be called with iint->mutex held.
  */
 void ima_store_measurement(struct integrity_iint_cache *iint,
-			   struct file *file, const unsigned char *filename)
+			   struct file *file, const unsigned char *filename,
+			   struct evm_ima_xattr_data *xattr_value,
+			   int xattr_len)
 {
 	const char *op = "add_template_measure";
 	const char *audit_cause = "ENOMEM";
@@ -251,7 +256,8 @@ void ima_store_measurement(struct integrity_iint_cache *iint,
 	if (iint->flags & IMA_MEASURED)
 		return;
 
-	result = ima_alloc_init_template(iint, file, filename, &entry);
+	result = ima_alloc_init_template(iint, file, filename,
+					 xattr_value, xattr_len, &entry);
 	if (result < 0) {
 		integrity_audit_msg(AUDIT_INTEGRITY_PCR, inode, filename,
 				    op, audit_cause, result, 0);
diff --git a/security/integrity/ima/ima_init.c b/security/integrity/ima/ima_init.c
index f84aec5412f3..15f34bd40abe 100644
--- a/security/integrity/ima/ima_init.c
+++ b/security/integrity/ima/ima_init.c
@@ -69,7 +69,7 @@ static void __init ima_add_boot_aggregate(void)
 	}
 
 	result = ima_alloc_init_template(iint, NULL, boot_aggregate_name,
-					 &entry);
+					 NULL, 0, &entry);
 	if (result < 0)
 		return;
 
diff --git a/security/integrity/ima/ima_main.c b/security/integrity/ima/ima_main.c
index 14d4cb557894..149ee1119f87 100644
--- a/security/integrity/ima/ima_main.c
+++ b/security/integrity/ima/ima_main.c
@@ -225,7 +225,8 @@ static int process_measurement(struct file *file, const char *filename,
 		pathname = (const char *)file->f_dentry->d_name.name;
 
 	if (action & IMA_MEASURE)
-		ima_store_measurement(iint, file, pathname);
+		ima_store_measurement(iint, file, pathname,
+				      xattr_value, xattr_len);
 	if (action & IMA_APPRAISE_SUBMASK)
 		rc = ima_appraise_measurement(_func, iint, file, pathname,
 					      xattr_value, xattr_len);
diff --git a/security/integrity/ima/ima_template.c b/security/integrity/ima/ima_template.c
index 000221419f6c..4e5da990630b 100644
--- a/security/integrity/ima/ima_template.c
+++ b/security/integrity/ima/ima_template.c
@@ -20,6 +20,7 @@
 static struct ima_template_desc defined_templates[] = {
 	{.name = IMA_TEMPLATE_IMA_NAME, .fmt = IMA_TEMPLATE_IMA_FMT},
 	{.name = "ima-ng",.fmt = "d-ng|n-ng"},
+	{.name = "ima-sig",.fmt = "d-ng|n-ng|sig"},
 };
 
 static struct ima_template_field supported_fields[] = {
@@ -31,6 +32,8 @@ static struct ima_template_field supported_fields[] = {
 	 .field_show = ima_show_template_digest_ng},
 	{.field_id = "n-ng",.field_init = ima_eventname_ng_init,
 	 .field_show = ima_show_template_string},
+	{.field_id = "sig",.field_init = ima_eventsig_init,
+	 .field_show = ima_show_template_sig},
 };
 
 static struct ima_template_desc *ima_template;
diff --git a/security/integrity/ima/ima_template_lib.c b/security/integrity/ima/ima_template_lib.c
index 7d841448f246..6d66ad6ed265 100644
--- a/security/integrity/ima/ima_template_lib.c
+++ b/security/integrity/ima/ima_template_lib.c
@@ -28,7 +28,8 @@ enum data_formats {
 	DATA_FMT_DIGEST = 0,
 	DATA_FMT_DIGEST_WITH_ALGO,
 	DATA_FMT_EVENT_NAME,
-	DATA_FMT_STRING
+	DATA_FMT_STRING,
+	DATA_FMT_HEX
 };
 
 static int ima_write_template_field_data(const void *data, const u32 datalen,
@@ -90,6 +91,9 @@ static void ima_show_template_data_ascii(struct seq_file *m,
 		buf_ptr += 2;
 		buflen -= buf_ptr - field_data->data;
 	case DATA_FMT_DIGEST:
+	case DATA_FMT_HEX:
+		if (!buflen)
+			break;
 		ima_print_digest(m, buf_ptr, buflen);
 		break;
 	case DATA_FMT_STRING:
@@ -147,6 +151,12 @@ void ima_show_template_string(struct seq_file *m, enum ima_show_type show,
 	ima_show_template_field_data(m, show, DATA_FMT_STRING, field_data);
 }
 
+void ima_show_template_sig(struct seq_file *m, enum ima_show_type show,
+			   struct ima_field_data *field_data)
+{
+	ima_show_template_field_data(m, show, DATA_FMT_HEX, field_data);
+}
+
 static int ima_eventdigest_init_common(u8 *digest, u32 digestsize, u8 hash_algo,
 				       struct ima_field_data *field_data,
 				       bool size_limit)
@@ -190,6 +200,7 @@ static int ima_eventdigest_init_common(u8 *digest, u32 digestsize, u8 hash_algo,
  */
 int ima_eventdigest_init(struct integrity_iint_cache *iint, struct file *file,
 			 const unsigned char *filename,
+			 struct evm_ima_xattr_data *xattr_value, int xattr_len,
 			 struct ima_field_data *field_data)
 {
 	struct {
@@ -237,7 +248,8 @@ out:
  */
 int ima_eventdigest_ng_init(struct integrity_iint_cache *iint,
 			    struct file *file, const unsigned char *filename,
-			    struct ima_field_data *field_data)
+			    struct evm_ima_xattr_data *xattr_value,
+			    int xattr_len, struct ima_field_data *field_data)
 {
 	u8 *cur_digest = NULL, hash_algo = HASH_ALGO__LAST;
 	u32 cur_digestsize = 0;
@@ -295,6 +307,7 @@ out:
  */
 int ima_eventname_init(struct integrity_iint_cache *iint, struct file *file,
 		       const unsigned char *filename,
+		       struct evm_ima_xattr_data *xattr_value, int xattr_len,
 		       struct ima_field_data *field_data)
 {
 	return ima_eventname_init_common(iint, file, filename,
@@ -306,8 +319,29 @@ int ima_eventname_init(struct integrity_iint_cache *iint, struct file *file,
  */
 int ima_eventname_ng_init(struct integrity_iint_cache *iint, struct file *file,
 			  const unsigned char *filename,
+			  struct evm_ima_xattr_data *xattr_value, int xattr_len,
 			  struct ima_field_data *field_data)
 {
 	return ima_eventname_init_common(iint, file, filename,
 					 field_data, false);
 }
+
+/*
+ *  ima_eventsig_init - include the file signature as part of the template data
+ */
+int ima_eventsig_init(struct integrity_iint_cache *iint, struct file *file,
+		      const unsigned char *filename,
+		      struct evm_ima_xattr_data *xattr_value, int xattr_len,
+		      struct ima_field_data *field_data)
+{
+	enum data_formats fmt = DATA_FMT_HEX;
+	int rc = 0;
+
+	if ((!xattr_value) || (xattr_value->type != EVM_IMA_XATTR_DIGSIG))
+		goto out;
+
+	rc = ima_write_template_field_data(xattr_value, xattr_len, fmt,
+					   field_data);
+out:
+	return rc;
+}
diff --git a/security/integrity/ima/ima_template_lib.h b/security/integrity/ima/ima_template_lib.h
index 16c5e7810234..63f6b52cb1c2 100644
--- a/security/integrity/ima/ima_template_lib.h
+++ b/security/integrity/ima/ima_template_lib.h
@@ -24,16 +24,26 @@ void ima_show_template_digest_ng(struct seq_file *m, enum ima_show_type show,
 				 struct ima_field_data *field_data);
 void ima_show_template_string(struct seq_file *m, enum ima_show_type show,
 			      struct ima_field_data *field_data);
+void ima_show_template_sig(struct seq_file *m, enum ima_show_type show,
+			   struct ima_field_data *field_data);
 int ima_eventdigest_init(struct integrity_iint_cache *iint, struct file *file,
 			 const unsigned char *filename,
+			 struct evm_ima_xattr_data *xattr_value, int xattr_len,
 			 struct ima_field_data *field_data);
 int ima_eventname_init(struct integrity_iint_cache *iint, struct file *file,
 		       const unsigned char *filename,
+		       struct evm_ima_xattr_data *xattr_value, int xattr_len,
 		       struct ima_field_data *field_data);
 int ima_eventdigest_ng_init(struct integrity_iint_cache *iint,
 			    struct file *file, const unsigned char *filename,
-			    struct ima_field_data *field_data);
+			    struct evm_ima_xattr_data *xattr_value,
+			    int xattr_len, struct ima_field_data *field_data);
 int ima_eventname_ng_init(struct integrity_iint_cache *iint, struct file *file,
 			  const unsigned char *filename,
+			  struct evm_ima_xattr_data *xattr_value, int xattr_len,
 			  struct ima_field_data *field_data);
+int ima_eventsig_init(struct integrity_iint_cache *iint, struct file *file,
+		      const unsigned char *filename,
+		      struct evm_ima_xattr_data *xattr_value, int xattr_len,
+		      struct ima_field_data *field_data);
 #endif /* __LINUX_IMA_TEMPLATE_LIB_H */
-- 
cgit v1.2.3


From 217091dd7a7a1bdac027ddb7c5a25f6ac0b8e241 Mon Sep 17 00:00:00 2001
From: Mimi Zohar <zohar@linux.vnet.ibm.com>
Date: Tue, 13 Aug 2013 08:47:43 -0400
Subject: ima: define '_ima' as a builtin 'trusted' keyring

Require all keys added to the IMA keyring be signed by an
existing trusted key on the system trusted keyring.

Changelog:
- define stub integrity_init_keyring() function (reported-by Fengguang Wu)
- differentiate between regular and trusted keyring names.
- replace printk with pr_info (D. Kasatkin)

Signed-off-by: Mimi Zohar <zohar@us.ibm.com>
---
 security/integrity/digsig.c           | 30 +++++++++++++++++++++++++++++-
 security/integrity/ima/Kconfig        |  8 ++++++++
 security/integrity/ima/ima_appraise.c | 11 +++++++++++
 security/integrity/integrity.h        |  7 +++++++
 4 files changed, 55 insertions(+), 1 deletion(-)

(limited to 'security')

diff --git a/security/integrity/digsig.c b/security/integrity/digsig.c
index b4af4ebc5be2..77ca965ab684 100644
--- a/security/integrity/digsig.c
+++ b/security/integrity/digsig.c
@@ -13,7 +13,9 @@
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 
 #include <linux/err.h>
+#include <linux/sched.h>
 #include <linux/rbtree.h>
+#include <linux/cred.h>
 #include <linux/key-type.h>
 #include <linux/digsig.h>
 
@@ -21,11 +23,19 @@
 
 static struct key *keyring[INTEGRITY_KEYRING_MAX];
 
+#ifdef CONFIG_IMA_TRUSTED_KEYRING
+static const char *keyring_name[INTEGRITY_KEYRING_MAX] = {
+	".evm",
+	".module",
+	".ima",
+};
+#else
 static const char *keyring_name[INTEGRITY_KEYRING_MAX] = {
 	"_evm",
 	"_module",
 	"_ima",
 };
+#endif
 
 int integrity_digsig_verify(const unsigned int id, const char *sig, int siglen,
 			    const char *digest, int digestlen)
@@ -35,7 +45,7 @@ int integrity_digsig_verify(const unsigned int id, const char *sig, int siglen,
 
 	if (!keyring[id]) {
 		keyring[id] =
-			request_key(&key_type_keyring, keyring_name[id], NULL);
+		    request_key(&key_type_keyring, keyring_name[id], NULL);
 		if (IS_ERR(keyring[id])) {
 			int err = PTR_ERR(keyring[id]);
 			pr_err("no %s keyring: %d\n", keyring_name[id], err);
@@ -56,3 +66,21 @@ int integrity_digsig_verify(const unsigned int id, const char *sig, int siglen,
 
 	return -EOPNOTSUPP;
 }
+
+int integrity_init_keyring(const unsigned int id)
+{
+	const struct cred *cred = current_cred();
+	const struct user_struct *user = cred->user;
+
+	keyring[id] = keyring_alloc(keyring_name[id], KUIDT_INIT(0),
+				    KGIDT_INIT(0), cred,
+				    ((KEY_POS_ALL & ~KEY_POS_SETATTR) |
+				     KEY_USR_VIEW | KEY_USR_READ),
+				    KEY_ALLOC_NOT_IN_QUOTA, user->uid_keyring);
+	if (!IS_ERR(keyring[id]))
+		set_bit(KEY_FLAG_TRUSTED_ONLY, &keyring[id]->flags);
+	else
+		pr_info("Can't allocate %s keyring (%ld)\n",
+			keyring_name[id], PTR_ERR(keyring[id]));
+	return 0;
+}
diff --git a/security/integrity/ima/Kconfig b/security/integrity/ima/Kconfig
index 81a27971d884..dad8d4ca2437 100644
--- a/security/integrity/ima/Kconfig
+++ b/security/integrity/ima/Kconfig
@@ -123,3 +123,11 @@ config IMA_APPRAISE
 	  For more information on integrity appraisal refer to:
 	  <http://linux-ima.sourceforge.net>
 	  If unsure, say N.
+
+config IMA_TRUSTED_KEYRING
+	bool "Require all keys on the _ima keyring be signed"
+	depends on IMA_APPRAISE && SYSTEM_TRUSTED_KEYRING
+	default y
+	help
+	   This option requires that all keys added to the _ima
+	   keyring be signed by a key on the system trusted keyring.
diff --git a/security/integrity/ima/ima_appraise.c b/security/integrity/ima/ima_appraise.c
index 734e9468aca0..46353ee517f6 100644
--- a/security/integrity/ima/ima_appraise.c
+++ b/security/integrity/ima/ima_appraise.c
@@ -381,3 +381,14 @@ int ima_inode_removexattr(struct dentry *dentry, const char *xattr_name)
 	}
 	return result;
 }
+
+#ifdef CONFIG_IMA_TRUSTED_KEYRING
+static int __init init_ima_keyring(void)
+{
+	int ret;
+
+	ret = integrity_init_keyring(INTEGRITY_KEYRING_IMA);
+	return 0;
+}
+late_initcall(init_ima_keyring);
+#endif
diff --git a/security/integrity/integrity.h b/security/integrity/integrity.h
index 2fb5e53e927f..b9e7c133734a 100644
--- a/security/integrity/integrity.h
+++ b/security/integrity/integrity.h
@@ -137,12 +137,19 @@ static inline int integrity_digsig_verify(const unsigned int id,
 #ifdef CONFIG_INTEGRITY_ASYMMETRIC_KEYS
 int asymmetric_verify(struct key *keyring, const char *sig,
 		      int siglen, const char *data, int datalen);
+
+int integrity_init_keyring(const unsigned int id);
 #else
 static inline int asymmetric_verify(struct key *keyring, const char *sig,
 				    int siglen, const char *data, int datalen)
 {
 	return -EOPNOTSUPP;
 }
+
+static int integrity_init_keyring(const unsigned int id)
+{
+	return 0;
+}
 #endif
 
 #ifdef CONFIG_INTEGRITY_AUDIT
-- 
cgit v1.2.3


From fbf8c53f1a2ac7610ed124043600dc074992e71b Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Wed, 6 Nov 2013 14:01:51 +0000
Subject: KEYS: Fix UID check in keyctl_get_persistent()

If the UID is specified by userspace when calling the KEYCTL_GET_PERSISTENT
function and the process does not have the CAP_SETUID capability, then the
function will return -EPERM if the current process's uid, suid, euid and fsuid
all match the requested UID.  This is incorrect.

Fix it such that when a non-privileged caller requests a persistent keyring by
a specific UID they can only request their own (ie. the specified UID matches
either then process's UID or the process's EUID).

This can be tested by logging in as the user and doing:

	keyctl get_persistent @p
	keyctl get_persistent @p `id -u`
	keyctl get_persistent @p 0

The first two should successfully print the same key ID.  The third should do
the same if called by UID 0 or indicate Operation Not Permitted otherwise.

Signed-off-by: David Howells <dhowells@redhat.com>
Acked-by: Stephen Gallagher <sgallagh@redhat.com>
---
 security/keys/persistent.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

(limited to 'security')

diff --git a/security/keys/persistent.c b/security/keys/persistent.c
index 82f4957a7acf..0ad3ee283781 100644
--- a/security/keys/persistent.c
+++ b/security/keys/persistent.c
@@ -144,10 +144,8 @@ long keyctl_get_persistent(uid_t _uid, key_serial_t destid)
 		/* You can only see your own persistent cache if you're not
 		 * sufficiently privileged.
 		 */
-		if (uid_eq(uid, current_uid()) &&
-		    uid_eq(uid, current_suid()) &&
-		    uid_eq(uid, current_euid()) &&
-		    uid_eq(uid, current_fsuid()) &&
+		if (!uid_eq(uid, current_uid()) &&
+		    !uid_eq(uid, current_euid()) &&
 		    !ns_capable(ns, CAP_SETUID))
 			return -EPERM;
 	}
-- 
cgit v1.2.3


From 97826c821ec6724fc359d9b7840dc10af914c641 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Wed, 13 Nov 2013 16:51:06 +0000
Subject: KEYS: Fix error handling in big_key instantiation

In the big_key_instantiate() function we return 0 if kernel_write() returns us
an error rather than returning an error.  This can potentially lead to
dentry_open() giving a BUG when called from big_key_read() with an unset
tmpfile path.

	------------[ cut here ]------------
	kernel BUG at fs/open.c:798!
	...
	RIP: 0010:[<ffffffff8119bbd1>] dentry_open+0xd1/0xe0
	...
	Call Trace:
	 [<ffffffff812350c5>] big_key_read+0x55/0x100
	 [<ffffffff81231084>] keyctl_read_key+0xb4/0xe0
	 [<ffffffff81231e58>] SyS_keyctl+0xf8/0x1d0
	 [<ffffffff815bb799>] system_call_fastpath+0x16/0x1b


Signed-off-by: David Howells <dhowells@redhat.com>
Reviewed-by: Stephen Gallagher <sgallagh@redhat.com>
---
 security/keys/big_key.c | 1 +
 1 file changed, 1 insertion(+)

(limited to 'security')

diff --git a/security/keys/big_key.c b/security/keys/big_key.c
index 2cf5e62d67af..7f44c3207a9b 100644
--- a/security/keys/big_key.c
+++ b/security/keys/big_key.c
@@ -78,6 +78,7 @@ int big_key_instantiate(struct key *key, struct key_preparsed_payload *prep)
 
 		written = kernel_write(file, prep->data, prep->datalen, 0);
 		if (written != datalen) {
+			ret = written;
 			if (written >= 0)
 				ret = -ENOMEM;
 			goto err_fput;
-- 
cgit v1.2.3


From 62fe318256befbd1b4a6765e71d9c997f768fe79 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Thu, 14 Nov 2013 13:02:31 +0000
Subject: KEYS: Fix keyring content gc scanner

Key pointers stored in the keyring are marked in bit 1 to indicate if they
point to a keyring.  We need to strip off this bit before using the pointer
when iterating over the keyring for the purpose of looking for links to garbage
collect.

This means that expirable keyrings aren't correctly expiring because the
checker is seeing their key pointer with 2 added to it.

Since the fix for this involves knowing about the internals of the keyring,
key_gc_keyring() is moved to keyring.c and merged into keyring_gc().

This can be tested by:

	echo 2 >/proc/sys/kernel/keys/gc_delay
	keyctl timeout `keyctl add keyring qwerty "" @s` 2
	cat /proc/keys
	sleep 5; cat /proc/keys

which should see a keyring called "qwerty" appear in the session keyring and
then disappear after it expires, and:

	echo 2 >/proc/sys/kernel/keys/gc_delay
	a=`keyctl get_persistent @s`
	b=`keyctl add keyring 0 "" $a`
	keyctl add user a a $b
	keyctl timeout $b 2
	cat /proc/keys
	sleep 5; cat /proc/keys

which should see a keyring called "0" with a key called "a" in it appear in the
user's persistent keyring (which will be attached to the session keyring) and
then both the "0" keyring and the "a" key should disappear when the "0" keyring
expires.

Signed-off-by: David Howells <dhowells@redhat.com>
Acked-by: Simo Sorce <simo@redhat.com>
---
 security/keys/gc.c      | 42 +-----------------------------------------
 security/keys/keyring.c | 45 +++++++++++++++++++++++++++++++++++----------
 2 files changed, 36 insertions(+), 51 deletions(-)

(limited to 'security')

diff --git a/security/keys/gc.c b/security/keys/gc.c
index cce621c33dce..d3222b6d7d59 100644
--- a/security/keys/gc.c
+++ b/security/keys/gc.c
@@ -130,46 +130,6 @@ void key_gc_keytype(struct key_type *ktype)
 	kleave("");
 }
 
-static int key_gc_keyring_func(const void *object, void *iterator_data)
-{
-	const struct key *key = object;
-	time_t *limit = iterator_data;
-	return key_is_dead(key, *limit);
-}
-
-/*
- * Garbage collect pointers from a keyring.
- *
- * Not called with any locks held.  The keyring's key struct will not be
- * deallocated under us as only our caller may deallocate it.
- */
-static void key_gc_keyring(struct key *keyring, time_t limit)
-{
-	int result;
-
-	kenter("%x{%s}", keyring->serial, keyring->description ?: "");
-
-	if (keyring->flags & ((1 << KEY_FLAG_INVALIDATED) |
-			      (1 << KEY_FLAG_REVOKED)))
-		goto dont_gc;
-
-	/* scan the keyring looking for dead keys */
-	rcu_read_lock();
-	result = assoc_array_iterate(&keyring->keys,
-				     key_gc_keyring_func, &limit);
-	rcu_read_unlock();
-	if (result == true)
-		goto do_gc;
-
-dont_gc:
-	kleave(" [no gc]");
-	return;
-
-do_gc:
-	keyring_gc(keyring, limit);
-	kleave(" [gc]");
-}
-
 /*
  * Garbage collect a list of unreferenced, detached keys
  */
@@ -388,7 +348,7 @@ found_unreferenced_key:
 	 */
 found_keyring:
 	spin_unlock(&key_serial_lock);
-	key_gc_keyring(key, limit);
+	keyring_gc(key, limit);
 	goto maybe_resched;
 
 	/* We found a dead key that is still referenced.  Reset its type and
diff --git a/security/keys/keyring.c b/security/keys/keyring.c
index d80311e571c3..69f0cb7bab7e 100644
--- a/security/keys/keyring.c
+++ b/security/keys/keyring.c
@@ -1304,7 +1304,7 @@ static void keyring_revoke(struct key *keyring)
 	}
 }
 
-static bool gc_iterator(void *object, void *iterator_data)
+static bool keyring_gc_select_iterator(void *object, void *iterator_data)
 {
 	struct key *key = keyring_ptr_to_key(object);
 	time_t *limit = iterator_data;
@@ -1315,22 +1315,47 @@ static bool gc_iterator(void *object, void *iterator_data)
 	return true;
 }
 
+static int keyring_gc_check_iterator(const void *object, void *iterator_data)
+{
+	const struct key *key = keyring_ptr_to_key(object);
+	time_t *limit = iterator_data;
+
+	key_check(key);
+	return key_is_dead(key, *limit);
+}
+
 /*
- * Collect garbage from the contents of a keyring, replacing the old list with
- * a new one with the pointers all shuffled down.
+ * Garbage collect pointers from a keyring.
  *
- * Dead keys are classed as oned that are flagged as being dead or are revoked,
- * expired or negative keys that were revoked or expired before the specified
- * limit.
+ * Not called with any locks held.  The keyring's key struct will not be
+ * deallocated under us as only our caller may deallocate it.
  */
 void keyring_gc(struct key *keyring, time_t limit)
 {
-	kenter("{%x,%s}", key_serial(keyring), keyring->description);
+	int result;
+
+	kenter("%x{%s}", keyring->serial, keyring->description ?: "");
 
+	if (keyring->flags & ((1 << KEY_FLAG_INVALIDATED) |
+			      (1 << KEY_FLAG_REVOKED)))
+		goto dont_gc;
+
+	/* scan the keyring looking for dead keys */
+	rcu_read_lock();
+	result = assoc_array_iterate(&keyring->keys,
+				     keyring_gc_check_iterator, &limit);
+	rcu_read_unlock();
+	if (result == true)
+		goto do_gc;
+
+dont_gc:
+	kleave(" [no gc]");
+	return;
+
+do_gc:
 	down_write(&keyring->sem);
 	assoc_array_gc(&keyring->keys, &keyring_assoc_array_ops,
-		       gc_iterator, &limit);
+		       keyring_gc_select_iterator, &limit);
 	up_write(&keyring->sem);
-
-	kleave("");
+	kleave(" [gc]");
 }
-- 
cgit v1.2.3


From 34ef7bd3823bf4401bf8f1f855e1bc77b82b1a43 Mon Sep 17 00:00:00 2001
From: Linus Torvalds <torvalds@linux-foundation.org>
Date: Sat, 23 Nov 2013 16:36:35 -0800
Subject: Revert "ima: define '_ima' as a builtin 'trusted' keyring"
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This reverts commit 217091dd7a7a1bdac027ddb7c5a25f6ac0b8e241, which
caused the following build error:

  security/integrity/digsig.c:70:5: error: redefinition of ‘integrity_init_keyring’
  security/integrity/integrity.h:149:12: note: previous definition of ‘integrity_init_keyring’ w
  security/integrity/integrity.h:149:12: warning: ‘integrity_init_keyring’ defined but not used

reported by Krzysztof Kolasa. Mimi says:

 "I made the classic mistake of requesting this patch to be upstreamed
  at the last second, rather than waiting until the next open window.

  At this point, the best course would probably be to revert the two
  commits and fix them for the next open window"

Reported-by: Krzysztof Kolasa <kkolasa@winsoft.pl>
Acked-by: Mimi Zohar <zohar@linux.vnet.ibm.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 security/integrity/digsig.c           | 30 +-----------------------------
 security/integrity/ima/Kconfig        |  8 --------
 security/integrity/ima/ima_appraise.c | 11 -----------
 security/integrity/integrity.h        |  7 -------
 4 files changed, 1 insertion(+), 55 deletions(-)

(limited to 'security')

diff --git a/security/integrity/digsig.c b/security/integrity/digsig.c
index 77ca965ab684..b4af4ebc5be2 100644
--- a/security/integrity/digsig.c
+++ b/security/integrity/digsig.c
@@ -13,9 +13,7 @@
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 
 #include <linux/err.h>
-#include <linux/sched.h>
 #include <linux/rbtree.h>
-#include <linux/cred.h>
 #include <linux/key-type.h>
 #include <linux/digsig.h>
 
@@ -23,19 +21,11 @@
 
 static struct key *keyring[INTEGRITY_KEYRING_MAX];
 
-#ifdef CONFIG_IMA_TRUSTED_KEYRING
-static const char *keyring_name[INTEGRITY_KEYRING_MAX] = {
-	".evm",
-	".module",
-	".ima",
-};
-#else
 static const char *keyring_name[INTEGRITY_KEYRING_MAX] = {
 	"_evm",
 	"_module",
 	"_ima",
 };
-#endif
 
 int integrity_digsig_verify(const unsigned int id, const char *sig, int siglen,
 			    const char *digest, int digestlen)
@@ -45,7 +35,7 @@ int integrity_digsig_verify(const unsigned int id, const char *sig, int siglen,
 
 	if (!keyring[id]) {
 		keyring[id] =
-		    request_key(&key_type_keyring, keyring_name[id], NULL);
+			request_key(&key_type_keyring, keyring_name[id], NULL);
 		if (IS_ERR(keyring[id])) {
 			int err = PTR_ERR(keyring[id]);
 			pr_err("no %s keyring: %d\n", keyring_name[id], err);
@@ -66,21 +56,3 @@ int integrity_digsig_verify(const unsigned int id, const char *sig, int siglen,
 
 	return -EOPNOTSUPP;
 }
-
-int integrity_init_keyring(const unsigned int id)
-{
-	const struct cred *cred = current_cred();
-	const struct user_struct *user = cred->user;
-
-	keyring[id] = keyring_alloc(keyring_name[id], KUIDT_INIT(0),
-				    KGIDT_INIT(0), cred,
-				    ((KEY_POS_ALL & ~KEY_POS_SETATTR) |
-				     KEY_USR_VIEW | KEY_USR_READ),
-				    KEY_ALLOC_NOT_IN_QUOTA, user->uid_keyring);
-	if (!IS_ERR(keyring[id]))
-		set_bit(KEY_FLAG_TRUSTED_ONLY, &keyring[id]->flags);
-	else
-		pr_info("Can't allocate %s keyring (%ld)\n",
-			keyring_name[id], PTR_ERR(keyring[id]));
-	return 0;
-}
diff --git a/security/integrity/ima/Kconfig b/security/integrity/ima/Kconfig
index dad8d4ca2437..81a27971d884 100644
--- a/security/integrity/ima/Kconfig
+++ b/security/integrity/ima/Kconfig
@@ -123,11 +123,3 @@ config IMA_APPRAISE
 	  For more information on integrity appraisal refer to:
 	  <http://linux-ima.sourceforge.net>
 	  If unsure, say N.
-
-config IMA_TRUSTED_KEYRING
-	bool "Require all keys on the _ima keyring be signed"
-	depends on IMA_APPRAISE && SYSTEM_TRUSTED_KEYRING
-	default y
-	help
-	   This option requires that all keys added to the _ima
-	   keyring be signed by a key on the system trusted keyring.
diff --git a/security/integrity/ima/ima_appraise.c b/security/integrity/ima/ima_appraise.c
index 46353ee517f6..734e9468aca0 100644
--- a/security/integrity/ima/ima_appraise.c
+++ b/security/integrity/ima/ima_appraise.c
@@ -381,14 +381,3 @@ int ima_inode_removexattr(struct dentry *dentry, const char *xattr_name)
 	}
 	return result;
 }
-
-#ifdef CONFIG_IMA_TRUSTED_KEYRING
-static int __init init_ima_keyring(void)
-{
-	int ret;
-
-	ret = integrity_init_keyring(INTEGRITY_KEYRING_IMA);
-	return 0;
-}
-late_initcall(init_ima_keyring);
-#endif
diff --git a/security/integrity/integrity.h b/security/integrity/integrity.h
index b9e7c133734a..2fb5e53e927f 100644
--- a/security/integrity/integrity.h
+++ b/security/integrity/integrity.h
@@ -137,19 +137,12 @@ static inline int integrity_digsig_verify(const unsigned int id,
 #ifdef CONFIG_INTEGRITY_ASYMMETRIC_KEYS
 int asymmetric_verify(struct key *keyring, const char *sig,
 		      int siglen, const char *data, int datalen);
-
-int integrity_init_keyring(const unsigned int id);
 #else
 static inline int asymmetric_verify(struct key *keyring, const char *sig,
 				    int siglen, const char *data, int datalen)
 {
 	return -EOPNOTSUPP;
 }
-
-static int integrity_init_keyring(const unsigned int id)
-{
-	return 0;
-}
 #endif
 
 #ifdef CONFIG_INTEGRITY_AUDIT
-- 
cgit v1.2.3


From b6f8f16f41d92861621b043389ef49de1c52d613 Mon Sep 17 00:00:00 2001
From: Roberto Sassu <roberto.sassu@polito.it>
Date: Fri, 8 Nov 2013 19:21:39 +0100
Subject: ima: do not include field length in template digest calc for ima
 template

To maintain compatibility with userspace tools, the field length must not
be included in the template digest calculation for the 'ima' template.

Fixes commit: a71dc65 ima: switch to new template management mechanism

Signed-off-by: Roberto Sassu <roberto.sassu@polito.it>
Signed-off-by: Mimi Zohar <zohar@linux.vnet.ibm.com>
---
 security/integrity/ima/ima.h        |  3 ++-
 security/integrity/ima/ima_api.c    |  1 +
 security/integrity/ima/ima_crypto.c | 17 ++++++++++++-----
 3 files changed, 15 insertions(+), 6 deletions(-)

(limited to 'security')

diff --git a/security/integrity/ima/ima.h b/security/integrity/ima/ima.h
index bf03c6a16cc8..a21cf706d213 100644
--- a/security/integrity/ima/ima.h
+++ b/security/integrity/ima/ima.h
@@ -97,7 +97,8 @@ int ima_add_template_entry(struct ima_template_entry *entry, int violation,
 			   const char *op, struct inode *inode,
 			   const unsigned char *filename);
 int ima_calc_file_hash(struct file *file, struct ima_digest_data *hash);
-int ima_calc_field_array_hash(struct ima_field_data *field_data, int num_fields,
+int ima_calc_field_array_hash(struct ima_field_data *field_data,
+			      struct ima_template_desc *desc, int num_fields,
 			      struct ima_digest_data *hash);
 int __init ima_calc_boot_aggregate(struct ima_digest_data *hash);
 void ima_add_violation(struct file *file, const unsigned char *filename,
diff --git a/security/integrity/ima/ima_api.c b/security/integrity/ima/ima_api.c
index 0e7540863fc2..80374842fe0b 100644
--- a/security/integrity/ima/ima_api.c
+++ b/security/integrity/ima/ima_api.c
@@ -94,6 +94,7 @@ int ima_store_template(struct ima_template_entry *entry,
 		/* this function uses default algo */
 		hash.hdr.algo = HASH_ALGO_SHA1;
 		result = ima_calc_field_array_hash(&entry->template_data[0],
+						   entry->template_desc,
 						   num_fields, &hash.hdr);
 		if (result < 0) {
 			integrity_audit_msg(AUDIT_INTEGRITY_PCR, inode,
diff --git a/security/integrity/ima/ima_crypto.c b/security/integrity/ima/ima_crypto.c
index 676e0292dfec..fdf60def52e9 100644
--- a/security/integrity/ima/ima_crypto.c
+++ b/security/integrity/ima/ima_crypto.c
@@ -140,6 +140,7 @@ int ima_calc_file_hash(struct file *file, struct ima_digest_data *hash)
  * Calculate the hash of template data
  */
 static int ima_calc_field_array_hash_tfm(struct ima_field_data *field_data,
+					 struct ima_template_desc *td,
 					 int num_fields,
 					 struct ima_digest_data *hash,
 					 struct crypto_shash *tfm)
@@ -160,9 +161,13 @@ static int ima_calc_field_array_hash_tfm(struct ima_field_data *field_data,
 		return rc;
 
 	for (i = 0; i < num_fields; i++) {
-		rc = crypto_shash_update(&desc.shash,
-					 (const u8 *) &field_data[i].len,
-					 sizeof(field_data[i].len));
+		if (strcmp(td->name, IMA_TEMPLATE_IMA_NAME) != 0) {
+			rc = crypto_shash_update(&desc.shash,
+						(const u8 *) &field_data[i].len,
+						sizeof(field_data[i].len));
+			if (rc)
+				break;
+		}
 		rc = crypto_shash_update(&desc.shash, field_data[i].data,
 					 field_data[i].len);
 		if (rc)
@@ -175,7 +180,8 @@ static int ima_calc_field_array_hash_tfm(struct ima_field_data *field_data,
 	return rc;
 }
 
-int ima_calc_field_array_hash(struct ima_field_data *field_data, int num_fields,
+int ima_calc_field_array_hash(struct ima_field_data *field_data,
+			      struct ima_template_desc *desc, int num_fields,
 			      struct ima_digest_data *hash)
 {
 	struct crypto_shash *tfm;
@@ -185,7 +191,8 @@ int ima_calc_field_array_hash(struct ima_field_data *field_data, int num_fields,
 	if (IS_ERR(tfm))
 		return PTR_ERR(tfm);
 
-	rc = ima_calc_field_array_hash_tfm(field_data, num_fields, hash, tfm);
+	rc = ima_calc_field_array_hash_tfm(field_data, desc, num_fields,
+					   hash, tfm);
 
 	ima_free_tfm(tfm);
 
-- 
cgit v1.2.3


From 3e8e5503a33577d89bdb7469b851b11f507bbed6 Mon Sep 17 00:00:00 2001
From: Roberto Sassu <roberto.sassu@polito.it>
Date: Fri, 8 Nov 2013 19:21:40 +0100
Subject: ima: do not send field length to userspace for digest of ima template

This patch defines a new value for the 'ima_show_type' enumerator
(IMA_SHOW_BINARY_NO_FIELD_LEN) to prevent that the field length
is transmitted through the 'binary_runtime_measurements' interface
for the digest field of the 'ima' template.

Fixes commit: 3ce1217 ima: define template fields library and new helpers

Signed-off-by: Roberto Sassu <roberto.sassu@polito.it>
Signed-off-by: Mimi Zohar <zohar@linux.vnet.ibm.com>
---
 security/integrity/ima/ima.h              |  3 ++-
 security/integrity/ima/ima_fs.c           | 14 +++++++++++---
 security/integrity/ima/ima_template_lib.c |  6 +++++-
 3 files changed, 18 insertions(+), 5 deletions(-)

(limited to 'security')

diff --git a/security/integrity/ima/ima.h b/security/integrity/ima/ima.h
index a21cf706d213..9636e17c9f5d 100644
--- a/security/integrity/ima/ima.h
+++ b/security/integrity/ima/ima.h
@@ -26,7 +26,8 @@
 
 #include "../integrity.h"
 
-enum ima_show_type { IMA_SHOW_BINARY, IMA_SHOW_ASCII };
+enum ima_show_type { IMA_SHOW_BINARY, IMA_SHOW_BINARY_NO_FIELD_LEN,
+		     IMA_SHOW_ASCII };
 enum tpm_pcrs { TPM_PCR0 = 0, TPM_PCR8 = 8 };
 
 /* digest size for IMA, fits SHA1 or MD5 */
diff --git a/security/integrity/ima/ima_fs.c b/security/integrity/ima/ima_fs.c
index d47a7c86a21d..db01125926bd 100644
--- a/security/integrity/ima/ima_fs.c
+++ b/security/integrity/ima/ima_fs.c
@@ -120,6 +120,7 @@ static int ima_measurements_show(struct seq_file *m, void *v)
 	struct ima_template_entry *e;
 	int namelen;
 	u32 pcr = CONFIG_IMA_MEASURE_PCR_IDX;
+	bool is_ima_template = false;
 	int i;
 
 	/* get entry */
@@ -145,14 +146,21 @@ static int ima_measurements_show(struct seq_file *m, void *v)
 	ima_putc(m, e->template_desc->name, namelen);
 
 	/* 5th:  template length (except for 'ima' template) */
-	if (strcmp(e->template_desc->name, IMA_TEMPLATE_IMA_NAME) != 0)
+	if (strcmp(e->template_desc->name, IMA_TEMPLATE_IMA_NAME) == 0)
+		is_ima_template = true;
+
+	if (!is_ima_template)
 		ima_putc(m, &e->template_data_len,
 			 sizeof(e->template_data_len));
 
 	/* 6th:  template specific data */
 	for (i = 0; i < e->template_desc->num_fields; i++) {
-		e->template_desc->fields[i]->field_show(m, IMA_SHOW_BINARY,
-							&e->template_data[i]);
+		enum ima_show_type show = IMA_SHOW_BINARY;
+		struct ima_template_field *field = e->template_desc->fields[i];
+
+		if (is_ima_template && strcmp(field->field_id, "d") == 0)
+			show = IMA_SHOW_BINARY_NO_FIELD_LEN;
+		field->field_show(m, show, &e->template_data[i]);
 	}
 	return 0;
 }
diff --git a/security/integrity/ima/ima_template_lib.c b/security/integrity/ima/ima_template_lib.c
index 6d66ad6ed265..c38adcc910fb 100644
--- a/security/integrity/ima/ima_template_lib.c
+++ b/security/integrity/ima/ima_template_lib.c
@@ -109,9 +109,12 @@ static void ima_show_template_data_binary(struct seq_file *m,
 					  enum data_formats datafmt,
 					  struct ima_field_data *field_data)
 {
-	ima_putc(m, &field_data->len, sizeof(u32));
+	if (show != IMA_SHOW_BINARY_NO_FIELD_LEN)
+		ima_putc(m, &field_data->len, sizeof(u32));
+
 	if (!field_data->len)
 		return;
+
 	ima_putc(m, field_data->data, field_data->len);
 }
 
@@ -125,6 +128,7 @@ static void ima_show_template_field_data(struct seq_file *m,
 		ima_show_template_data_ascii(m, show, datafmt, field_data);
 		break;
 	case IMA_SHOW_BINARY:
+	case IMA_SHOW_BINARY_NO_FIELD_LEN:
 		ima_show_template_data_binary(m, show, datafmt, field_data);
 		break;
 	default:
-- 
cgit v1.2.3


From dbc335d2dc3c437649eb6b39f4e9aee2a13eb0af Mon Sep 17 00:00:00 2001
From: Roberto Sassu <roberto.sassu@polito.it>
Date: Mon, 25 Nov 2013 20:18:52 +0100
Subject: ima: make a copy of template_fmt in template_desc_init_fields()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This patch makes a copy of the 'template_fmt' function argument so that
the latter will not be modified by strsep(), which does the splitting by
replacing the given separator with '\0'.

 IMA: No TPM chip found, activating TPM-bypass!
 Unable to handle kernel pointer dereference at virtual kernel address 0000000000842000
 Oops: 0004 [#1] SMP
 Modules linked in:
 CPU: 3 PID: 1 Comm: swapper/0 Not tainted 3.12.0-rc2-00098-g3ce1217d6cd5 #17
 task: 000000003ffa0000 ti: 000000003ff84000 task.ti: 000000003ff84000
 Krnl PSW : 0704e00180000000 000000000044bf88 (strsep+0x7c/0xa0)
            R:0 T:1 IO:1 EX:1 Key:0 M:1 W:0 P:0 AS:3 CC:2 PM:0 EA:3
 Krnl GPRS: 000000000000007c 000000000000007c 000000003ff87d90 0000000000821fd8
            0000000000000000 000000000000007c 0000000000aa37e0 0000000000aa9008
            0000000000000051 0000000000a114d8 0000000100000002 0000000000842bde
            0000000000842bdf 00000000006f97f0 000000000040062c 000000003ff87cf0
 Krnl Code: 000000000044bf7c: a7f4000a           brc     15,44bf90
            000000000044bf80: b90200cc           ltgr    %r12,%r12
           #000000000044bf84: a7840006           brc     8,44bf90
           >000000000044bf88: 9200c000           mvi     0(%r12),0
            000000000044bf8c: 41c0c001           la      %r12,1(%r12)
            000000000044bf90: e3c020000024       stg     %r12,0(%r2)
            000000000044bf96: b904002b           lgr     %r2,%r11
            000000000044bf9a: ebbcf0700004       lmg     %r11,%r12,112(%r15)
 Call Trace:
 ([<00000000004005fe>] ima_init_template+0xa2/0x1bc)
  [<0000000000a7c896>] ima_init+0x7a/0xa8
  [<0000000000a7c938>] init_ima+0x24/0x40
  [<00000000001000e8>] do_one_initcall+0x68/0x128
  [<0000000000a4eb56>] kernel_init_freeable+0x20a/0x2b4
  [<00000000006a1ff4>] kernel_init+0x30/0x178
  [<00000000006b69fe>] kernel_thread_starter+0x6/0xc
  [<00000000006b69f8>] kernel_thread_starter+0x0/0xc
 Last Breaking-Event-Address:
  [<000000000044bf42>] strsep+0x36/0xa0

Fixes commit: adf53a7 ima: new templates management mechanism

Changelog v1:
- make template_fmt 'const char *' (reported-by James Morris)
- fix kstrdup memory leak (reported-by James Morris)

Reported-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Roberto Sassu <roberto.sassu@polito.it>
Signed-off-by: Mimi Zohar <zohar@linux.vnet.ibm.com>
Tested-by: Heiko Carstens <heiko.carstens@de.ibm.com>
---
 security/integrity/ima/ima_template.c | 21 ++++++++++++++-------
 1 file changed, 14 insertions(+), 7 deletions(-)

(limited to 'security')

diff --git a/security/integrity/ima/ima_template.c b/security/integrity/ima/ima_template.c
index 4e5da990630b..913e1927f916 100644
--- a/security/integrity/ima/ima_template.c
+++ b/security/integrity/ima/ima_template.c
@@ -90,7 +90,7 @@ static struct ima_template_field *lookup_template_field(const char *field_id)
 	return NULL;
 }
 
-static int template_fmt_size(char *template_fmt)
+static int template_fmt_size(const char *template_fmt)
 {
 	char c;
 	int template_fmt_len = strlen(template_fmt);
@@ -106,23 +106,28 @@ static int template_fmt_size(char *template_fmt)
 	return j + 1;
 }
 
-static int template_desc_init_fields(char *template_fmt,
+static int template_desc_init_fields(const char *template_fmt,
 				     struct ima_template_field ***fields,
 				     int *num_fields)
 {
-	char *c, *template_fmt_ptr = template_fmt;
+	char *c, *template_fmt_copy;
 	int template_num_fields = template_fmt_size(template_fmt);
 	int i, result = 0;
 
 	if (template_num_fields > IMA_TEMPLATE_NUM_FIELDS_MAX)
 		return -EINVAL;
 
+	/* copying is needed as strsep() modifies the original buffer */
+	template_fmt_copy = kstrdup(template_fmt, GFP_KERNEL);
+	if (template_fmt_copy == NULL)
+		return -ENOMEM;
+
 	*fields = kzalloc(template_num_fields * sizeof(*fields), GFP_KERNEL);
 	if (*fields == NULL) {
 		result = -ENOMEM;
 		goto out;
 	}
-	for (i = 0; (c = strsep(&template_fmt_ptr, "|")) != NULL &&
+	for (i = 0; (c = strsep(&template_fmt_copy, "|")) != NULL &&
 	     i < template_num_fields; i++) {
 		struct ima_template_field *f = lookup_template_field(c);
 
@@ -133,10 +138,12 @@ static int template_desc_init_fields(char *template_fmt,
 		(*fields)[i] = f;
 	}
 	*num_fields = i;
-	return 0;
 out:
-	kfree(*fields);
-	*fields = NULL;
+	if (result < 0) {
+		kfree(*fields);
+		*fields = NULL;
+	}
+	kfree(template_fmt_copy);
 	return result;
 }
 
-- 
cgit v1.2.3


From af91706d5ddecb4a9858cca9e90d463037cfd498 Mon Sep 17 00:00:00 2001
From: Roberto Sassu <roberto.sassu@polito.it>
Date: Wed, 27 Nov 2013 14:40:41 +0100
Subject: ima: store address of template_fmt_copy in a pointer before calling
 strsep

This patch stores the address of the 'template_fmt_copy' variable in a new
variable, called 'template_fmt_ptr', so that the latter is passed as an
argument of strsep() instead of the former. This modification is needed
in order to correctly free the memory area referenced by
'template_fmt_copy' (strsep() modifies the pointer of the passed string).

Signed-off-by: Roberto Sassu <roberto.sassu@polito.it>
Reported-by: Sebastian Ott <sebott@linux.vnet.ibm.com>
Signed-off-by: Mimi Zohar <zohar@us.ibm.com>
Signed-off-by: James Morris <james.l.morris@oracle.com>
---
 security/integrity/ima/ima_template.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

(limited to 'security')

diff --git a/security/integrity/ima/ima_template.c b/security/integrity/ima/ima_template.c
index 913e1927f916..635695f6a185 100644
--- a/security/integrity/ima/ima_template.c
+++ b/security/integrity/ima/ima_template.c
@@ -110,7 +110,7 @@ static int template_desc_init_fields(const char *template_fmt,
 				     struct ima_template_field ***fields,
 				     int *num_fields)
 {
-	char *c, *template_fmt_copy;
+	char *c, *template_fmt_copy, *template_fmt_ptr;
 	int template_num_fields = template_fmt_size(template_fmt);
 	int i, result = 0;
 
@@ -127,7 +127,9 @@ static int template_desc_init_fields(const char *template_fmt,
 		result = -ENOMEM;
 		goto out;
 	}
-	for (i = 0; (c = strsep(&template_fmt_copy, "|")) != NULL &&
+
+	template_fmt_ptr = template_fmt_copy;
+	for (i = 0; (c = strsep(&template_fmt_ptr, "|")) != NULL &&
 	     i < template_num_fields; i++) {
 		struct ima_template_field *f = lookup_template_field(c);
 
-- 
cgit v1.2.3


From 2480f57fb3023eb047c5f2d6dfefef41ab9b893c Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Mon, 2 Dec 2013 11:24:18 +0000
Subject: KEYS: Pre-clear struct key on allocation

The second word of key->payload does not get initialised in key_alloc(), but
the big_key type is relying on it having been cleared.  The problem comes when
big_key fails to instantiate a large key and doesn't then set the payload.  The
big_key_destroy() op is called from the garbage collector and this assumes that
the dentry pointer stored in the second word will be NULL if instantiation did
not complete.

Therefore just pre-clear the entire struct key on allocation rather than trying
to be clever and only initialising to 0 only those bits that aren't otherwise
initialised.

The lack of initialisation can lead to a bug report like the following if
big_key failed to initialise its file:

	general protection fault: 0000 [#1] SMP
	Modules linked in: ...
	CPU: 0 PID: 51 Comm: kworker/0:1 Not tainted 3.10.0-53.el7.x86_64 #1
	Hardware name: Dell Inc. PowerEdge 1955/0HC513, BIOS 1.4.4 12/09/2008
	Workqueue: events key_garbage_collector
	task: ffff8801294f5680 ti: ffff8801296e2000 task.ti: ffff8801296e2000
	RIP: 0010:[<ffffffff811b4a51>] dput+0x21/0x2d0
	...
	Call Trace:
	 [<ffffffff811a7b06>] path_put+0x16/0x30
	 [<ffffffff81235604>] big_key_destroy+0x44/0x60
	 [<ffffffff8122dc4b>] key_gc_unused_keys.constprop.2+0x5b/0xe0
	 [<ffffffff8122df2f>] key_garbage_collector+0x1df/0x3c0
	 [<ffffffff8107759b>] process_one_work+0x17b/0x460
	 [<ffffffff8107834b>] worker_thread+0x11b/0x400
	 [<ffffffff81078230>] ? rescuer_thread+0x3e0/0x3e0
	 [<ffffffff8107eb00>] kthread+0xc0/0xd0
	 [<ffffffff8107ea40>] ? kthread_create_on_node+0x110/0x110
	 [<ffffffff815c4bec>] ret_from_fork+0x7c/0xb0
	 [<ffffffff8107ea40>] ? kthread_create_on_node+0x110/0x110

Reported-by: Patrik Kis <pkis@redhat.com>
Signed-off-by: David Howells <dhowells@redhat.com>
Reviewed-by: Stephen Gallagher <sgallagh@redhat.com>
---
 security/keys/key.c | 8 +-------
 1 file changed, 1 insertion(+), 7 deletions(-)

(limited to 'security')

diff --git a/security/keys/key.c b/security/keys/key.c
index 55d110f0aced..6e21c11e48bc 100644
--- a/security/keys/key.c
+++ b/security/keys/key.c
@@ -272,7 +272,7 @@ struct key *key_alloc(struct key_type *type, const char *desc,
 	}
 
 	/* allocate and initialise the key and its description */
-	key = kmem_cache_alloc(key_jar, GFP_KERNEL);
+	key = kmem_cache_zalloc(key_jar, GFP_KERNEL);
 	if (!key)
 		goto no_memory_2;
 
@@ -293,18 +293,12 @@ struct key *key_alloc(struct key_type *type, const char *desc,
 	key->uid = uid;
 	key->gid = gid;
 	key->perm = perm;
-	key->flags = 0;
-	key->expiry = 0;
-	key->payload.data = NULL;
-	key->security = NULL;
 
 	if (!(flags & KEY_ALLOC_NOT_IN_QUOTA))
 		key->flags |= 1 << KEY_FLAG_IN_QUOTA;
 	if (flags & KEY_ALLOC_TRUSTED)
 		key->flags |= 1 << KEY_FLAG_TRUSTED;
 
-	memset(&key->type_data, 0, sizeof(key->type_data));
-
 #ifdef KEY_DEBUGGING
 	key->magic = KEY_DEBUG_MAGIC;
 #endif
-- 
cgit v1.2.3


From d54e58b7f01552b0eb7d445f4b58de4499ad5ea6 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Mon, 2 Dec 2013 11:24:18 +0000
Subject: KEYS: Fix the keyring hash function

The keyring hash function (used by the associative array) is supposed to clear
the bottommost nibble of the index key (where the hash value resides) for
keyrings and make sure it is non-zero for non-keyrings.  This is done to make
keyrings cluster together on one branch of the tree separately to other keys.

Unfortunately, the wrong mask is used, so only the bottom two bits are
examined and cleared and not the whole bottom nibble.  This means that keys
and keyrings can still be successfully searched for under most circumstances
as the hash is consistent in its miscalculation, but if a keyring's
associative array bottom node gets filled up then approx 75% of the keyrings
will not be put into the 0 branch.

The consequence of this is that a key in a keyring linked to by another
keyring, ie.

	keyring A -> keyring B -> key

may not be found if the search starts at keyring A and then descends into
keyring B because search_nested_keyrings() only searches up the 0 branch (as it
"knows" all keyrings must be there and not elsewhere in the tree).

The fix is to use the right mask.

This can be tested with:

	r=`keyctl newring sandbox @s`
	for ((i=0; i<=16; i++)); do keyctl newring ring$i $r; done
	for ((i=0; i<=16; i++)); do keyctl add user a$i a %:ring$i; done
	for ((i=0; i<=16; i++)); do keyctl search $r user a$i; done

This creates a sandbox keyring, then creates 17 keyrings therein (labelled
ring0..ring16).  This causes the root node of the sandbox's associative array
to overflow and for the tree to have extra nodes inserted.

Each keyring then is given a user key (labelled aN for ringN) for us to search
for.

We then search for the user keys we added, starting from the sandbox.  If
working correctly, it should return the same ordered list of key IDs as
for...keyctl add... did.  Without this patch, it reports ENOKEY "Required key
not available" for some of the keys.  Just which keys get this depends as the
kernel pointer to the key type forms part of the hash function.

Reported-by: Nalin Dahyabhai <nalin@redhat.com>
Signed-off-by: David Howells <dhowells@redhat.com>
Tested-by: Stephen Gallagher <sgallagh@redhat.com>
---
 security/keys/keyring.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

(limited to 'security')

diff --git a/security/keys/keyring.c b/security/keys/keyring.c
index 69f0cb7bab7e..0adbc77a59b9 100644
--- a/security/keys/keyring.c
+++ b/security/keys/keyring.c
@@ -160,7 +160,7 @@ static u64 mult_64x32_and_fold(u64 x, u32 y)
 static unsigned long hash_key_type_and_desc(const struct keyring_index_key *index_key)
 {
 	const unsigned level_shift = ASSOC_ARRAY_LEVEL_STEP;
-	const unsigned long level_mask = ASSOC_ARRAY_LEVEL_STEP_MASK;
+	const unsigned long fan_mask = ASSOC_ARRAY_FAN_MASK;
 	const char *description = index_key->description;
 	unsigned long hash, type;
 	u32 piece;
@@ -194,10 +194,10 @@ static unsigned long hash_key_type_and_desc(const struct keyring_index_key *inde
 	 * ordinary keys by making sure the lowest level segment in the hash is
 	 * zero for keyrings and non-zero otherwise.
 	 */
-	if (index_key->type != &key_type_keyring && (hash & level_mask) == 0)
+	if (index_key->type != &key_type_keyring && (hash & fan_mask) == 0)
 		return hash | (hash >> (ASSOC_ARRAY_KEY_CHUNK_SIZE - level_shift)) | 1;
-	if (index_key->type == &key_type_keyring && (hash & level_mask) != 0)
-		return (hash + (hash << level_shift)) & ~level_mask;
+	if (index_key->type == &key_type_keyring && (hash & fan_mask) != 0)
+		return (hash + (hash << level_shift)) & ~fan_mask;
 	return hash;
 }
 
-- 
cgit v1.2.3


From 23fd78d76415729b338ff1802a0066b4a62f7fb8 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Mon, 2 Dec 2013 11:24:18 +0000
Subject: KEYS: Fix multiple key add into associative array

If sufficient keys (or keyrings) are added into a keyring such that a node in
the associative array's tree overflows (each node has a capacity N, currently
16) and such that all N+1 keys have the same index key segment for that level
of the tree (the level'th nibble of the index key), then assoc_array_insert()
calls ops->diff_objects() to indicate at which bit position the two index keys
vary.

However, __key_link_begin() passes a NULL object to assoc_array_insert() with
the intention of supplying the correct pointer later before we commit the
change.  This means that keyring_diff_objects() is given a NULL pointer as one
of its arguments which it does not expect.  This results in an oops like the
attached.

With the previous patch to fix the keyring hash function, this can be forced
much more easily by creating a keyring and only adding keyrings to it.  Add any
other sort of key and a different insertion path is taken - all 16+1 objects
must want to cluster in the same node slot.

This can be tested by:

	r=`keyctl newring sandbox @s`
	for ((i=0; i<=16; i++)); do keyctl newring ring$i $r; done

This should work fine, but oopses when the 17th keyring is added.

Since ops->diff_objects() is always called with the first pointer pointing to
the object to be inserted (ie. the NULL pointer), we can fix the problem by
changing the to-be-inserted object pointer to point to the index key passed
into assoc_array_insert() instead.

Whilst we're at it, we also switch the arguments so that they are the same as
for ->compare_object().

BUG: unable to handle kernel NULL pointer dereference at 0000000000000088
IP: [<ffffffff81191ee4>] hash_key_type_and_desc+0x18/0xb0
...
RIP: 0010:[<ffffffff81191ee4>] hash_key_type_and_desc+0x18/0xb0
...
Call Trace:
 [<ffffffff81191f9d>] keyring_diff_objects+0x21/0xd2
 [<ffffffff811f09ef>] assoc_array_insert+0x3b6/0x908
 [<ffffffff811929a7>] __key_link_begin+0x78/0xe5
 [<ffffffff81191a2e>] key_create_or_update+0x17d/0x36a
 [<ffffffff81192e0a>] SyS_add_key+0x123/0x183
 [<ffffffff81400ddb>] tracesys+0xdd/0xe2

Signed-off-by: David Howells <dhowells@redhat.com>
Tested-by: Stephen Gallagher <sgallagh@redhat.com>
---
 Documentation/assoc_array.txt | 6 +++---
 include/linux/assoc_array.h   | 6 +++---
 lib/assoc_array.c             | 4 ++--
 security/keys/keyring.c       | 7 +++----
 4 files changed, 11 insertions(+), 12 deletions(-)

(limited to 'security')

diff --git a/Documentation/assoc_array.txt b/Documentation/assoc_array.txt
index f4faec0f66e4..2f2c6cdd73c0 100644
--- a/Documentation/assoc_array.txt
+++ b/Documentation/assoc_array.txt
@@ -164,10 +164,10 @@ This points to a number of methods, all of which need to be provided:
 
  (4) Diff the index keys of two objects.
 
-	int (*diff_objects)(const void *a, const void *b);
+	int (*diff_objects)(const void *object, const void *index_key);
 
-     Return the bit position at which the index keys of two objects differ or
-     -1 if they are the same.
+     Return the bit position at which the index key of the specified object
+     differs from the given index key or -1 if they are the same.
 
 
  (5) Free an object.
diff --git a/include/linux/assoc_array.h b/include/linux/assoc_array.h
index 9a193b84238a..a89df3be1686 100644
--- a/include/linux/assoc_array.h
+++ b/include/linux/assoc_array.h
@@ -41,10 +41,10 @@ struct assoc_array_ops {
 	/* Is this the object we're looking for? */
 	bool (*compare_object)(const void *object, const void *index_key);
 
-	/* How different are two objects, to a bit position in their keys? (or
-	 * -1 if they're the same)
+	/* How different is an object from an index key, to a bit position in
+	 * their keys? (or -1 if they're the same)
 	 */
-	int (*diff_objects)(const void *a, const void *b);
+	int (*diff_objects)(const void *object, const void *index_key);
 
 	/* Method to free an object. */
 	void (*free_object)(void *object);
diff --git a/lib/assoc_array.c b/lib/assoc_array.c
index 17edeaf19180..1b6a44f1ec3e 100644
--- a/lib/assoc_array.c
+++ b/lib/assoc_array.c
@@ -759,8 +759,8 @@ all_leaves_cluster_together:
 	pr_devel("all leaves cluster together\n");
 	diff = INT_MAX;
 	for (i = 0; i < ASSOC_ARRAY_FAN_OUT; i++) {
-		int x = ops->diff_objects(assoc_array_ptr_to_leaf(edit->leaf),
-					  assoc_array_ptr_to_leaf(node->slots[i]));
+		int x = ops->diff_objects(assoc_array_ptr_to_leaf(node->slots[i]),
+					  index_key);
 		if (x < diff) {
 			BUG_ON(x < 0);
 			diff = x;
diff --git a/security/keys/keyring.c b/security/keys/keyring.c
index 0adbc77a59b9..3dd8445cd489 100644
--- a/security/keys/keyring.c
+++ b/security/keys/keyring.c
@@ -279,12 +279,11 @@ static bool keyring_compare_object(const void *object, const void *data)
  * Compare the index keys of a pair of objects and determine the bit position
  * at which they differ - if they differ.
  */
-static int keyring_diff_objects(const void *_a, const void *_b)
+static int keyring_diff_objects(const void *object, const void *data)
 {
-	const struct key *key_a = keyring_ptr_to_key(_a);
-	const struct key *key_b = keyring_ptr_to_key(_b);
+	const struct key *key_a = keyring_ptr_to_key(object);
 	const struct keyring_index_key *a = &key_a->index_key;
-	const struct keyring_index_key *b = &key_b->index_key;
+	const struct keyring_index_key *b = data;
 	unsigned long seg_a, seg_b;
 	int level, i;
 
-- 
cgit v1.2.3


From 9c5e45df215b4788f7a41c983ce862d08a083c2d Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Mon, 2 Dec 2013 11:24:19 +0000
Subject: KEYS: Fix searching of nested keyrings

If a keyring contains more than 16 keyrings (the capacity of a single node in
the associative array) then those keyrings are split over multiple nodes
arranged as a tree.

If search_nested_keyrings() is called to search the keyring then it will
attempt to manually walk over just the 0 branch of the associative array tree
where all the keyring links are stored.  This works provided the key is found
before the algorithm steps from one node containing keyrings to a child node
or if there are sufficiently few keyring links that the keyrings are all in
one node.

However, if the algorithm does need to step from a node to a child node, it
doesn't change the node pointer unless a shortcut also gets transited.  This
means that the algorithm will keep scanning the same node over and over again
without terminating and without returning.

To fix this, move the internal-pointer-to-node translation from inside the
shortcut transit handler so that it applies it to node arrival as well.

This can be tested by:

	r=`keyctl newring sandbox @s`
	for ((i=0; i<=16; i++)); do keyctl newring ring$i $r; done
	for ((i=0; i<=16; i++)); do keyctl add user a$i a %:ring$i; done
	for ((i=0; i<=16; i++)); do keyctl search $r user a$i; done
	for ((i=17; i<=20; i++)); do keyctl search $r user a$i; done

The searches should all complete successfully (or with an error for 17-20),
but instead one or more of them will hang.

Signed-off-by: David Howells <dhowells@redhat.com>
Tested-by: Stephen Gallagher <sgallagh@redhat.com>
---
 security/keys/keyring.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'security')

diff --git a/security/keys/keyring.c b/security/keys/keyring.c
index 3dd8445cd489..d46cbc5e335e 100644
--- a/security/keys/keyring.c
+++ b/security/keys/keyring.c
@@ -690,8 +690,8 @@ descend_to_node:
 		smp_read_barrier_depends();
 		ptr = ACCESS_ONCE(shortcut->next_node);
 		BUG_ON(!assoc_array_ptr_is_node(ptr));
-		node = assoc_array_ptr_to_node(ptr);
 	}
+	node = assoc_array_ptr_to_node(ptr);
 
 begin_node:
 	kdebug("begin_node");
-- 
cgit v1.2.3


From c7277090927a5e71871e799a355ed2940f6c8fc6 Mon Sep 17 00:00:00 2001
From: Eric Paris <eparis@redhat.com>
Date: Mon, 2 Dec 2013 11:24:19 +0000
Subject: security: shmem: implement kernel private shmem inodes

We have a problem where the big_key key storage implementation uses a
shmem backed inode to hold the key contents.  Because of this detail of
implementation LSM checks are being done between processes trying to
read the keys and the tmpfs backed inode.  The LSM checks are already
being handled on the key interface level and should not be enforced at
the inode level (since the inode is an implementation detail, not a
part of the security model)

This patch implements a new function shmem_kernel_file_setup() which
returns the equivalent to shmem_file_setup() only the underlying inode
has S_PRIVATE set.  This means that all LSM checks for the inode in
question are skipped.  It should only be used for kernel internal
operations where the inode is not exposed to userspace without proper
LSM checking.  It is possible that some other users of
shmem_file_setup() should use the new interface, but this has not been
explored.

Reproducing this bug is a little bit difficult.  The steps I used on
Fedora are:

 (1) Turn off selinux enforcing:

	setenforce 0

 (2) Create a huge key

	k=`dd if=/dev/zero bs=8192 count=1 | keyctl padd big_key test-key @s`

 (3) Access the key in another context:

	runcon system_u:system_r:httpd_t:s0-s0:c0.c1023 keyctl print $k >/dev/null

 (4) Examine the audit logs:

	ausearch -m AVC -i --subject httpd_t | audit2allow

If the last command's output includes a line that looks like:

	allow httpd_t user_tmpfs_t:file { open read };

There was an inode check between httpd and the tmpfs filesystem.  With
this patch no such denial will be seen.  (NOTE! you should clear your
audit log if you have tested for this previously)

(Please return you box to enforcing)

Signed-off-by: Eric Paris <eparis@redhat.com>
Signed-off-by: David Howells <dhowells@redhat.com>
cc: Hugh Dickins <hughd@google.com>
cc: linux-mm@kvack.org
---
 include/linux/shmem_fs.h |  2 ++
 mm/shmem.c               | 36 +++++++++++++++++++++++++++++-------
 security/keys/big_key.c  |  2 +-
 3 files changed, 32 insertions(+), 8 deletions(-)

(limited to 'security')

diff --git a/include/linux/shmem_fs.h b/include/linux/shmem_fs.h
index 30aa0dc60d75..9d55438bc4ad 100644
--- a/include/linux/shmem_fs.h
+++ b/include/linux/shmem_fs.h
@@ -47,6 +47,8 @@ extern int shmem_init(void);
 extern int shmem_fill_super(struct super_block *sb, void *data, int silent);
 extern struct file *shmem_file_setup(const char *name,
 					loff_t size, unsigned long flags);
+extern struct file *shmem_kernel_file_setup(const char *name, loff_t size,
+					    unsigned long flags);
 extern int shmem_zero_setup(struct vm_area_struct *);
 extern int shmem_lock(struct file *file, int lock, struct user_struct *user);
 extern void shmem_unlock_mapping(struct address_space *mapping);
diff --git a/mm/shmem.c b/mm/shmem.c
index 8297623fcaed..902a14842b74 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -2918,13 +2918,8 @@ static struct dentry_operations anon_ops = {
 	.d_dname = simple_dname
 };
 
-/**
- * shmem_file_setup - get an unlinked file living in tmpfs
- * @name: name for dentry (to be seen in /proc/<pid>/maps
- * @size: size to be set for the file
- * @flags: VM_NORESERVE suppresses pre-accounting of the entire object size
- */
-struct file *shmem_file_setup(const char *name, loff_t size, unsigned long flags)
+static struct file *__shmem_file_setup(const char *name, loff_t size,
+				       unsigned long flags, unsigned int i_flags)
 {
 	struct file *res;
 	struct inode *inode;
@@ -2957,6 +2952,7 @@ struct file *shmem_file_setup(const char *name, loff_t size, unsigned long flags
 	if (!inode)
 		goto put_dentry;
 
+	inode->i_flags |= i_flags;
 	d_instantiate(path.dentry, inode);
 	inode->i_size = size;
 	clear_nlink(inode);	/* It is unlinked */
@@ -2977,6 +2973,32 @@ put_memory:
 	shmem_unacct_size(flags, size);
 	return res;
 }
+
+/**
+ * shmem_kernel_file_setup - get an unlinked file living in tmpfs which must be
+ * 	kernel internal.  There will be NO LSM permission checks against the
+ * 	underlying inode.  So users of this interface must do LSM checks at a
+ * 	higher layer.  The one user is the big_key implementation.  LSM checks
+ * 	are provided at the key level rather than the inode level.
+ * @name: name for dentry (to be seen in /proc/<pid>/maps
+ * @size: size to be set for the file
+ * @flags: VM_NORESERVE suppresses pre-accounting of the entire object size
+ */
+struct file *shmem_kernel_file_setup(const char *name, loff_t size, unsigned long flags)
+{
+	return __shmem_file_setup(name, size, flags, S_PRIVATE);
+}
+
+/**
+ * shmem_file_setup - get an unlinked file living in tmpfs
+ * @name: name for dentry (to be seen in /proc/<pid>/maps
+ * @size: size to be set for the file
+ * @flags: VM_NORESERVE suppresses pre-accounting of the entire object size
+ */
+struct file *shmem_file_setup(const char *name, loff_t size, unsigned long flags)
+{
+	return __shmem_file_setup(name, size, flags, 0);
+}
 EXPORT_SYMBOL_GPL(shmem_file_setup);
 
 /**
diff --git a/security/keys/big_key.c b/security/keys/big_key.c
index 7f44c3207a9b..8137b27d641d 100644
--- a/security/keys/big_key.c
+++ b/security/keys/big_key.c
@@ -70,7 +70,7 @@ int big_key_instantiate(struct key *key, struct key_preparsed_payload *prep)
 		 *
 		 * TODO: Encrypt the stored data with a temporary key.
 		 */
-		file = shmem_file_setup("", datalen, 0);
+		file = shmem_kernel_file_setup("", datalen, 0);
 		if (IS_ERR(file)) {
 			ret = PTR_ERR(file);
 			goto err_quota;
-- 
cgit v1.2.3


From 09ae6345721afbb7cf3e0920209b140cbe7bff0d Mon Sep 17 00:00:00 2001
From: Christoph Paasch <christoph.paasch@uclouvain.be>
Date: Mon, 2 Dec 2013 00:05:20 +0100
Subject: ima: Do not free 'entry' before it is initialized

7bc5f447ce9d0 (ima: define new function ima_alloc_init_template() to
API) moved the initialization of 'entry' in ima_add_boot_aggregate() a
bit more below, after the if (ima_used_chip).

So, 'entry' is not initialized while being inside this if-block. So, we
should not attempt to free it.

Found by Coverity (CID: 1131971)

Fixes: 7bc5f447ce9d0 (ima: define new function ima_alloc_init_template() to API)
Signed-off-by: Christoph Paasch <christoph.paasch@uclouvain.be>
Signed-off-by: Mimi Zohar <zohar@us.ibm.com>
---
 security/integrity/ima/ima_init.c | 1 -
 1 file changed, 1 deletion(-)

(limited to 'security')

diff --git a/security/integrity/ima/ima_init.c b/security/integrity/ima/ima_init.c
index 15f34bd40abe..76b8e2c4fd38 100644
--- a/security/integrity/ima/ima_init.c
+++ b/security/integrity/ima/ima_init.c
@@ -63,7 +63,6 @@ static void __init ima_add_boot_aggregate(void)
 		result = ima_calc_boot_aggregate(&hash.hdr);
 		if (result < 0) {
 			audit_cause = "hashing_error";
-			kfree(entry);
 			goto err_out;
 		}
 	}
-- 
cgit v1.2.3


From a7ed7c60e14df5b986f93549717235b882643e7e Mon Sep 17 00:00:00 2001
From: Roberto Sassu <roberto.sassu@polito.it>
Date: Mon, 2 Dec 2013 19:40:34 +0100
Subject: ima: properly free ima_template_entry structures

The new templates management mechanism records information associated
to an event into an array of 'ima_field_data' structures and makes it
available through the 'template_data' field of the 'ima_template_entry'
structure (the element of the measurements list created by IMA).

Since 'ima_field_data' contains dynamically allocated data (which length
varies depending on the data associated to a selected template field),
it is not enough to just free the memory reserved for a
'ima_template_entry' structure if something goes wrong.

This patch creates the new function ima_free_template_entry() which
walks the array of 'ima_field_data' structures, frees the memory
referenced by the 'data' pointer and finally the space reserved for
the 'ima_template_entry' structure. Further, it replaces existing kfree()
that have a pointer to an 'ima_template_entry' structure as argument
with calls to the new function.

Fixes: a71dc65: ima: switch to new template management mechanism
Signed-off-by: Roberto Sassu <roberto.sassu@polito.it>
Signed-off-by: Mimi Zohar <zohar@us.ibm.com>
---
 security/integrity/ima/ima.h      |  1 +
 security/integrity/ima/ima_api.c  | 21 +++++++++++++++++----
 security/integrity/ima/ima_init.c |  2 +-
 3 files changed, 19 insertions(+), 5 deletions(-)

(limited to 'security')

diff --git a/security/integrity/ima/ima.h b/security/integrity/ima/ima.h
index 9636e17c9f5d..0356e1d437ca 100644
--- a/security/integrity/ima/ima.h
+++ b/security/integrity/ima/ima.h
@@ -148,6 +148,7 @@ int ima_alloc_init_template(struct integrity_iint_cache *iint,
 			    int xattr_len, struct ima_template_entry **entry);
 int ima_store_template(struct ima_template_entry *entry, int violation,
 		       struct inode *inode, const unsigned char *filename);
+void ima_free_template_entry(struct ima_template_entry *entry);
 const char *ima_d_path(struct path *path, char **pathbuf);
 
 /* rbtree tree calls to lookup, insert, delete
diff --git a/security/integrity/ima/ima_api.c b/security/integrity/ima/ima_api.c
index 80374842fe0b..c38bbce8c6a6 100644
--- a/security/integrity/ima/ima_api.c
+++ b/security/integrity/ima/ima_api.c
@@ -21,6 +21,19 @@
 #include <crypto/hash_info.h>
 #include "ima.h"
 
+/*
+ * ima_free_template_entry - free an existing template entry
+ */
+void ima_free_template_entry(struct ima_template_entry *entry)
+{
+	int i;
+
+	for (i = 0; i < entry->template_desc->num_fields; i++)
+		kfree(entry->template_data[i].data);
+
+	kfree(entry);
+}
+
 /*
  * ima_alloc_init_template - create and initialize a new template entry
  */
@@ -37,6 +50,7 @@ int ima_alloc_init_template(struct integrity_iint_cache *iint,
 	if (!*entry)
 		return -ENOMEM;
 
+	(*entry)->template_desc = template_desc;
 	for (i = 0; i < template_desc->num_fields; i++) {
 		struct ima_template_field *field = template_desc->fields[i];
 		u32 len;
@@ -51,10 +65,9 @@ int ima_alloc_init_template(struct integrity_iint_cache *iint,
 		(*entry)->template_data_len += sizeof(len);
 		(*entry)->template_data_len += len;
 	}
-	(*entry)->template_desc = template_desc;
 	return 0;
 out:
-	kfree(*entry);
+	ima_free_template_entry(*entry);
 	*entry = NULL;
 	return result;
 }
@@ -134,7 +147,7 @@ void ima_add_violation(struct file *file, const unsigned char *filename,
 	}
 	result = ima_store_template(entry, violation, inode, filename);
 	if (result < 0)
-		kfree(entry);
+		ima_free_template_entry(entry);
 err_out:
 	integrity_audit_msg(AUDIT_INTEGRITY_PCR, inode, filename,
 			    op, cause, result, 0);
@@ -269,7 +282,7 @@ void ima_store_measurement(struct integrity_iint_cache *iint,
 	if (!result || result == -EEXIST)
 		iint->flags |= IMA_MEASURED;
 	if (result < 0)
-		kfree(entry);
+		ima_free_template_entry(entry);
 }
 
 void ima_audit_measurement(struct integrity_iint_cache *iint,
diff --git a/security/integrity/ima/ima_init.c b/security/integrity/ima/ima_init.c
index 76b8e2c4fd38..37122768554a 100644
--- a/security/integrity/ima/ima_init.c
+++ b/security/integrity/ima/ima_init.c
@@ -75,7 +75,7 @@ static void __init ima_add_boot_aggregate(void)
 	result = ima_store_template(entry, violation, NULL,
 				    boot_aggregate_name);
 	if (result < 0)
-		kfree(entry);
+		ima_free_template_entry(entry);
 	return;
 err_out:
 	integrity_audit_msg(AUDIT_INTEGRITY_PCR, NULL, boot_aggregate_name, op,
-- 
cgit v1.2.3


From 0af901643fe3f1f8d44e41115d36609ee4bda2bf Mon Sep 17 00:00:00 2001
From: "Geyslan G. Bem" <geyslan@gmail.com>
Date: Wed, 4 Dec 2013 16:10:24 -0500
Subject: selinux: fix possible memory leak

Free 'ctx_str' when necessary.

Signed-off-by: Geyslan G. Bem <geyslan@gmail.com>
Signed-off-by: Paul Moore <pmoore@redhat.com>
---
 security/selinux/xfrm.c | 11 +++++++----
 1 file changed, 7 insertions(+), 4 deletions(-)

(limited to 'security')

diff --git a/security/selinux/xfrm.c b/security/selinux/xfrm.c
index a91d205ec0c6..cf79a4564e38 100644
--- a/security/selinux/xfrm.c
+++ b/security/selinux/xfrm.c
@@ -327,19 +327,22 @@ int selinux_xfrm_state_alloc_acquire(struct xfrm_state *x,
 		return rc;
 
 	ctx = kmalloc(sizeof(*ctx) + str_len, GFP_ATOMIC);
-	if (!ctx)
-		return -ENOMEM;
+	if (!ctx) {
+		rc = -ENOMEM;
+		goto out;
+	}
 
 	ctx->ctx_doi = XFRM_SC_DOI_LSM;
 	ctx->ctx_alg = XFRM_SC_ALG_SELINUX;
 	ctx->ctx_sid = secid;
 	ctx->ctx_len = str_len;
 	memcpy(ctx->ctx_str, ctx_str, str_len);
-	kfree(ctx_str);
 
 	x->security = ctx;
 	atomic_inc(&selinux_xfrm_refcount);
-	return 0;
+out:
+	kfree(ctx_str);
+	return rc;
 }
 
 /*
-- 
cgit v1.2.3


From 47180068276a04ed31d24fe04c673138208b07a9 Mon Sep 17 00:00:00 2001
From: Paul Moore <pmoore@redhat.com>
Date: Wed, 4 Dec 2013 16:10:45 -0500
Subject: selinux: handle TCP SYN-ACK packets correctly in selinux_ip_output()

In selinux_ip_output() we always label packets based on the parent
socket.  While this approach works in almost all cases, it doesn't
work in the case of TCP SYN-ACK packets when the correct label is not
the label of the parent socket, but rather the label of the larval
socket represented by the request_sock struct.

Unfortunately, since the request_sock isn't queued on the parent
socket until *after* the SYN-ACK packet is sent, we can't lookup the
request_sock to determine the correct label for the packet; at this
point in time the best we can do is simply pass/NF_ACCEPT the packet.
It must be said that simply passing the packet without any explicit
labeling action, while far from ideal, is not terrible as the SYN-ACK
packet will inherit any IP option based labeling from the initial
connection request so the label *should* be correct and all our
access controls remain in place so we shouldn't have to worry about
information leaks.

Reported-by: Janak Desai <Janak.Desai@gtri.gatech.edu>
Tested-by: Janak Desai <Janak.Desai@gtri.gatech.edu>
Cc: stable@vger.kernel.org
Signed-off-by: Paul Moore <pmoore@redhat.com>
---
 security/selinux/hooks.c | 25 +++++++++++++++++++++++--
 1 file changed, 23 insertions(+), 2 deletions(-)

(limited to 'security')

diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c
index 777ee98273d1..877bab748c87 100644
--- a/security/selinux/hooks.c
+++ b/security/selinux/hooks.c
@@ -53,6 +53,7 @@
 #include <net/ip.h>		/* for local_port_range[] */
 #include <net/sock.h>
 #include <net/tcp.h>		/* struct or_callable used in sock_rcv_skb */
+#include <net/inet_connection_sock.h>
 #include <net/net_namespace.h>
 #include <net/netlabel.h>
 #include <linux/uaccess.h>
@@ -4731,6 +4732,7 @@ static unsigned int selinux_ipv6_forward(unsigned int hooknum,
 static unsigned int selinux_ip_output(struct sk_buff *skb,
 				      u16 family)
 {
+	struct sock *sk;
 	u32 sid;
 
 	if (!netlbl_enabled())
@@ -4739,8 +4741,27 @@ static unsigned int selinux_ip_output(struct sk_buff *skb,
 	/* we do this in the LOCAL_OUT path and not the POST_ROUTING path
 	 * because we want to make sure we apply the necessary labeling
 	 * before IPsec is applied so we can leverage AH protection */
-	if (skb->sk) {
-		struct sk_security_struct *sksec = skb->sk->sk_security;
+	sk = skb->sk;
+	if (sk) {
+		struct sk_security_struct *sksec;
+
+		if (sk->sk_state == TCP_LISTEN)
+			/* if the socket is the listening state then this
+			 * packet is a SYN-ACK packet which means it needs to
+			 * be labeled based on the connection/request_sock and
+			 * not the parent socket.  unfortunately, we can't
+			 * lookup the request_sock yet as it isn't queued on
+			 * the parent socket until after the SYN-ACK is sent.
+			 * the "solution" is to simply pass the packet as-is
+			 * as any IP option based labeling should be copied
+			 * from the initial connection request (in the IP
+			 * layer).  it is far from ideal, but until we get a
+			 * security label in the packet itself this is the
+			 * best we can do. */
+			return NF_ACCEPT;
+
+		/* standard practice, label using the parent socket */
+		sksec = sk->sk_security;
 		sid = sksec->sid;
 	} else
 		sid = SECINITSID_KERNEL;
-- 
cgit v1.2.3


From 446b802437f285de68ffb8d6fac3c44c3cab5b04 Mon Sep 17 00:00:00 2001
From: Paul Moore <pmoore@redhat.com>
Date: Wed, 4 Dec 2013 16:10:51 -0500
Subject: selinux: handle TCP SYN-ACK packets correctly in
 selinux_ip_postroute()

In selinux_ip_postroute() we perform access checks based on the
packet's security label.  For locally generated traffic we get the
packet's security label from the associated socket; this works in all
cases except for TCP SYN-ACK packets.  In the case of SYN-ACK packet's
the correct security label is stored in the connection's request_sock,
not the server's socket.  Unfortunately, at the point in time when
selinux_ip_postroute() is called we can't query the request_sock
directly, we need to recreate the label using the same logic that
originally labeled the associated request_sock.

See the inline comments for more explanation.

Reported-by: Janak Desai <Janak.Desai@gtri.gatech.edu>
Tested-by: Janak Desai <Janak.Desai@gtri.gatech.edu>
Cc: stable@vger.kernel.org
Signed-off-by: Paul Moore <pmoore@redhat.com>
---
 security/selinux/hooks.c | 68 +++++++++++++++++++++++++++++++++++++-----------
 1 file changed, 53 insertions(+), 15 deletions(-)

(limited to 'security')

diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c
index 877bab748c87..cc076a9b0344 100644
--- a/security/selinux/hooks.c
+++ b/security/selinux/hooks.c
@@ -3847,6 +3847,30 @@ static int selinux_skb_peerlbl_sid(struct sk_buff *skb, u16 family, u32 *sid)
 	return 0;
 }
 
+/**
+ * selinux_conn_sid - Determine the child socket label for a connection
+ * @sk_sid: the parent socket's SID
+ * @skb_sid: the packet's SID
+ * @conn_sid: the resulting connection SID
+ *
+ * If @skb_sid is valid then the user:role:type information from @sk_sid is
+ * combined with the MLS information from @skb_sid in order to create
+ * @conn_sid.  If @skb_sid is not valid then then @conn_sid is simply a copy
+ * of @sk_sid.  Returns zero on success, negative values on failure.
+ *
+ */
+static int selinux_conn_sid(u32 sk_sid, u32 skb_sid, u32 *conn_sid)
+{
+	int err = 0;
+
+	if (skb_sid != SECSID_NULL)
+		err = security_sid_mls_copy(sk_sid, skb_sid, conn_sid);
+	else
+		*conn_sid = sk_sid;
+
+	return err;
+}
+
 /* socket security operations */
 
 static int socket_sockcreate_sid(const struct task_security_struct *tsec,
@@ -4453,7 +4477,7 @@ static int selinux_inet_conn_request(struct sock *sk, struct sk_buff *skb,
 	struct sk_security_struct *sksec = sk->sk_security;
 	int err;
 	u16 family = sk->sk_family;
-	u32 newsid;
+	u32 connsid;
 	u32 peersid;
 
 	/* handle mapped IPv4 packets arriving via IPv6 sockets */
@@ -4463,16 +4487,11 @@ static int selinux_inet_conn_request(struct sock *sk, struct sk_buff *skb,
 	err = selinux_skb_peerlbl_sid(skb, family, &peersid);
 	if (err)
 		return err;
-	if (peersid == SECSID_NULL) {
-		req->secid = sksec->sid;
-		req->peer_secid = SECSID_NULL;
-	} else {
-		err = security_sid_mls_copy(sksec->sid, peersid, &newsid);
-		if (err)
-			return err;
-		req->secid = newsid;
-		req->peer_secid = peersid;
-	}
+	err = selinux_conn_sid(sksec->sid, peersid, &connsid);
+	if (err)
+		return err;
+	req->secid = connsid;
+	req->peer_secid = peersid;
 
 	return selinux_netlbl_inet_conn_request(req, family);
 }
@@ -4846,12 +4865,12 @@ static unsigned int selinux_ip_postroute(struct sk_buff *skb, int ifindex,
 	if (!secmark_active && !peerlbl_active)
 		return NF_ACCEPT;
 
-	/* if the packet is being forwarded then get the peer label from the
-	 * packet itself; otherwise check to see if it is from a local
-	 * application or the kernel, if from an application get the peer label
-	 * from the sending socket, otherwise use the kernel's sid */
 	sk = skb->sk;
 	if (sk == NULL) {
+		/* Without an associated socket the packet is either coming
+		 * from the kernel or it is being forwarded; check the packet
+		 * to determine which and if the packet is being forwarded
+		 * query the packet directly to determine the security label. */
 		if (skb->skb_iif) {
 			secmark_perm = PACKET__FORWARD_OUT;
 			if (selinux_skb_peerlbl_sid(skb, family, &peer_sid))
@@ -4860,7 +4879,26 @@ static unsigned int selinux_ip_postroute(struct sk_buff *skb, int ifindex,
 			secmark_perm = PACKET__SEND;
 			peer_sid = SECINITSID_KERNEL;
 		}
+	} else if (sk->sk_state == TCP_LISTEN) {
+		/* Locally generated packet but the associated socket is in the
+		 * listening state which means this is a SYN-ACK packet.  In
+		 * this particular case the correct security label is assigned
+		 * to the connection/request_sock but unfortunately we can't
+		 * query the request_sock as it isn't queued on the parent
+		 * socket until after the SYN-ACK packet is sent; the only
+		 * viable choice is to regenerate the label like we do in
+		 * selinux_inet_conn_request().  See also selinux_ip_output()
+		 * for similar problems. */
+		u32 skb_sid;
+		struct sk_security_struct *sksec = sk->sk_security;
+		if (selinux_skb_peerlbl_sid(skb, family, &skb_sid))
+			return NF_DROP;
+		if (selinux_conn_sid(sksec->sid, skb_sid, &peer_sid))
+			return NF_DROP;
+		secmark_perm = PACKET__SEND;
 	} else {
+		/* Locally generated packet, fetch the security label from the
+		 * associated socket. */
 		struct sk_security_struct *sksec = sk->sk_security;
 		peer_sid = sksec->sid;
 		secmark_perm = PACKET__SEND;
-- 
cgit v1.2.3


From 817eff718dca4e54d5721211ddde0914428fbb7c Mon Sep 17 00:00:00 2001
From: Paul Moore <pmoore@redhat.com>
Date: Tue, 10 Dec 2013 14:57:54 -0500
Subject: selinux: look for IPsec labels on both inbound and outbound packets

Previously selinux_skb_peerlbl_sid() would only check for labeled
IPsec security labels on inbound packets, this patch enables it to
check both inbound and outbound traffic for labeled IPsec security
labels.

Reported-by: Janak Desai <Janak.Desai@gtri.gatech.edu>
Cc: stable@vger.kernel.org
Signed-off-by: Paul Moore <pmoore@redhat.com>
---
 security/selinux/hooks.c        |  2 +-
 security/selinux/include/xfrm.h |  8 ++++---
 security/selinux/xfrm.c         | 51 +++++++++++++++++++++++++++++++++--------
 3 files changed, 47 insertions(+), 14 deletions(-)

(limited to 'security')

diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c
index cc076a9b0344..8b2812312ae4 100644
--- a/security/selinux/hooks.c
+++ b/security/selinux/hooks.c
@@ -3829,7 +3829,7 @@ static int selinux_skb_peerlbl_sid(struct sk_buff *skb, u16 family, u32 *sid)
 	u32 nlbl_sid;
 	u32 nlbl_type;
 
-	err = selinux_skb_xfrm_sid(skb, &xfrm_sid);
+	err = selinux_xfrm_skb_sid(skb, &xfrm_sid);
 	if (unlikely(err))
 		return -EACCES;
 	err = selinux_netlbl_skbuff_getsid(skb, family, &nlbl_type, &nlbl_sid);
diff --git a/security/selinux/include/xfrm.h b/security/selinux/include/xfrm.h
index 0dec76c64cf5..48c3cc94c168 100644
--- a/security/selinux/include/xfrm.h
+++ b/security/selinux/include/xfrm.h
@@ -39,6 +39,7 @@ int selinux_xfrm_sock_rcv_skb(u32 sk_sid, struct sk_buff *skb,
 int selinux_xfrm_postroute_last(u32 sk_sid, struct sk_buff *skb,
 				struct common_audit_data *ad, u8 proto);
 int selinux_xfrm_decode_session(struct sk_buff *skb, u32 *sid, int ckall);
+int selinux_xfrm_skb_sid(struct sk_buff *skb, u32 *sid);
 
 static inline void selinux_xfrm_notify_policyload(void)
 {
@@ -79,11 +80,12 @@ static inline int selinux_xfrm_decode_session(struct sk_buff *skb, u32 *sid,
 static inline void selinux_xfrm_notify_policyload(void)
 {
 }
-#endif
 
-static inline int selinux_skb_xfrm_sid(struct sk_buff *skb, u32 *sid)
+static inline int selinux_xfrm_skb_sid(struct sk_buff *skb, u32 *sid)
 {
-	return selinux_xfrm_decode_session(skb, sid, 0);
+	*sid = SECSID_NULL;
+	return 0;
 }
+#endif
 
 #endif /* _SELINUX_XFRM_H_ */
diff --git a/security/selinux/xfrm.c b/security/selinux/xfrm.c
index cf79a4564e38..0462cb3ff0a7 100644
--- a/security/selinux/xfrm.c
+++ b/security/selinux/xfrm.c
@@ -209,19 +209,26 @@ int selinux_xfrm_state_pol_flow_match(struct xfrm_state *x,
 			    NULL) ? 0 : 1);
 }
 
-/*
- * LSM hook implementation that checks and/or returns the xfrm sid for the
- * incoming packet.
- */
-int selinux_xfrm_decode_session(struct sk_buff *skb, u32 *sid, int ckall)
+static u32 selinux_xfrm_skb_sid_egress(struct sk_buff *skb)
 {
-	u32 sid_session = SECSID_NULL;
-	struct sec_path *sp;
+	struct dst_entry *dst = skb_dst(skb);
+	struct xfrm_state *x;
 
-	if (skb == NULL)
-		goto out;
+	if (dst == NULL)
+		return SECSID_NULL;
+	x = dst->xfrm;
+	if (x == NULL || !selinux_authorizable_xfrm(x))
+		return SECSID_NULL;
+
+	return x->security->ctx_sid;
+}
+
+static int selinux_xfrm_skb_sid_ingress(struct sk_buff *skb,
+					u32 *sid, int ckall)
+{
+	u32 sid_session = SECSID_NULL;
+	struct sec_path *sp = skb->sp;
 
-	sp = skb->sp;
 	if (sp) {
 		int i;
 
@@ -247,6 +254,30 @@ out:
 	return 0;
 }
 
+/*
+ * LSM hook implementation that checks and/or returns the xfrm sid for the
+ * incoming packet.
+ */
+int selinux_xfrm_decode_session(struct sk_buff *skb, u32 *sid, int ckall)
+{
+	if (skb == NULL) {
+		*sid = SECSID_NULL;
+		return 0;
+	}
+	return selinux_xfrm_skb_sid_ingress(skb, sid, ckall);
+}
+
+int selinux_xfrm_skb_sid(struct sk_buff *skb, u32 *sid)
+{
+	int rc;
+
+	rc = selinux_xfrm_skb_sid_ingress(skb, sid, 0);
+	if (rc == 0 && *sid == SECSID_NULL)
+		*sid = selinux_xfrm_skb_sid_egress(skb);
+
+	return rc;
+}
+
 /*
  * LSM hook implementation that allocs and transfers uctx spec to xfrm_policy.
  */
-- 
cgit v1.2.3


From c0828e50485932b7e019df377a6b0a8d1ebd3080 Mon Sep 17 00:00:00 2001
From: Paul Moore <pmoore@redhat.com>
Date: Tue, 10 Dec 2013 14:58:01 -0500
Subject: selinux: process labeled IPsec TCP SYN-ACK packets properly in
 selinux_ip_postroute()

Due to difficulty in arriving at the proper security label for
TCP SYN-ACK packets in selinux_ip_postroute(), we need to check packets
while/before they are undergoing XFRM transforms instead of waiting
until afterwards so that we can determine the correct security label.

Reported-by: Janak Desai <Janak.Desai@gtri.gatech.edu>
Cc: stable@vger.kernel.org
Signed-off-by: Paul Moore <pmoore@redhat.com>
---
 security/selinux/hooks.c | 42 +++++++++++++++++++++++++++++++++++-------
 1 file changed, 35 insertions(+), 7 deletions(-)

(limited to 'security')

diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c
index 8b2812312ae4..6db2e589a1f3 100644
--- a/security/selinux/hooks.c
+++ b/security/selinux/hooks.c
@@ -4850,22 +4850,31 @@ static unsigned int selinux_ip_postroute(struct sk_buff *skb, int ifindex,
 	 * as fast and as clean as possible. */
 	if (!selinux_policycap_netpeer)
 		return selinux_ip_postroute_compat(skb, ifindex, family);
+
+	secmark_active = selinux_secmark_enabled();
+	peerlbl_active = selinux_peerlbl_enabled();
+	if (!secmark_active && !peerlbl_active)
+		return NF_ACCEPT;
+
+	sk = skb->sk;
+
 #ifdef CONFIG_XFRM
 	/* If skb->dst->xfrm is non-NULL then the packet is undergoing an IPsec
 	 * packet transformation so allow the packet to pass without any checks
 	 * since we'll have another chance to perform access control checks
 	 * when the packet is on it's final way out.
 	 * NOTE: there appear to be some IPv6 multicast cases where skb->dst
-	 *       is NULL, in this case go ahead and apply access control. */
-	if (skb_dst(skb) != NULL && skb_dst(skb)->xfrm != NULL)
+	 *       is NULL, in this case go ahead and apply access control.
+	 * NOTE: if this is a local socket (skb->sk != NULL) that is in the
+	 *       TCP listening state we cannot wait until the XFRM processing
+	 *       is done as we will miss out on the SA label if we do;
+	 *       unfortunately, this means more work, but it is only once per
+	 *       connection. */
+	if (skb_dst(skb) != NULL && skb_dst(skb)->xfrm != NULL &&
+	    !(sk != NULL && sk->sk_state == TCP_LISTEN))
 		return NF_ACCEPT;
 #endif
-	secmark_active = selinux_secmark_enabled();
-	peerlbl_active = selinux_peerlbl_enabled();
-	if (!secmark_active && !peerlbl_active)
-		return NF_ACCEPT;
 
-	sk = skb->sk;
 	if (sk == NULL) {
 		/* Without an associated socket the packet is either coming
 		 * from the kernel or it is being forwarded; check the packet
@@ -4893,6 +4902,25 @@ static unsigned int selinux_ip_postroute(struct sk_buff *skb, int ifindex,
 		struct sk_security_struct *sksec = sk->sk_security;
 		if (selinux_skb_peerlbl_sid(skb, family, &skb_sid))
 			return NF_DROP;
+		/* At this point, if the returned skb peerlbl is SECSID_NULL
+		 * and the packet has been through at least one XFRM
+		 * transformation then we must be dealing with the "final"
+		 * form of labeled IPsec packet; since we've already applied
+		 * all of our access controls on this packet we can safely
+		 * pass the packet. */
+		if (skb_sid == SECSID_NULL) {
+			switch (family) {
+			case PF_INET:
+				if (IPCB(skb)->flags & IPSKB_XFRM_TRANSFORMED)
+					return NF_ACCEPT;
+				break;
+			case PF_INET6:
+				if (IP6CB(skb)->flags & IP6SKB_XFRM_TRANSFORMED)
+					return NF_ACCEPT;
+			default:
+				return NF_DROP_ERR(-ECONNREFUSED);
+			}
+		}
 		if (selinux_conn_sid(sksec->sid, skb_sid, &peer_sid))
 			return NF_DROP;
 		secmark_perm = PACKET__SEND;
-- 
cgit v1.2.3


From 29b1deb2a48a9dd02b93597aa4c055a24c0e989f Mon Sep 17 00:00:00 2001
From: Linus Torvalds <torvalds@linux-foundation.org>
Date: Sun, 15 Dec 2013 11:17:45 -0800
Subject: Revert "selinux: consider filesystem subtype in policies"

This reverts commit 102aefdda4d8275ce7d7100bc16c88c74272b260.

Tom London reports that it causes sync() to hang on Fedora rawhide:

  https://bugzilla.redhat.com/show_bug.cgi?id=1033965

and Josh Boyer bisected it down to this commit.  Reverting the commit in
the rawhide kernel fixes the problem.

Eric Paris root-caused it to incorrect subtype matching in that commit
breaking fuse, and has a tentative patch, but by now we're better off
retrying this in 3.14 rather than playing with it any more.

Reported-by: Tom London <selinux@gmail.com>
Bisected-by: Josh Boyer <jwboyer@fedoraproject.org>
Acked-by: Eric Paris <eparis@redhat.com>
Cc: James Morris <jmorris@namei.org>
Cc: Anand Avati <avati@redhat.com>
Cc: Paul Moore <paul@paul-moore.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 security/selinux/hooks.c       | 40 ++++++++++++++++++----------------------
 security/selinux/ss/services.c | 42 ++++--------------------------------------
 2 files changed, 22 insertions(+), 60 deletions(-)

(limited to 'security')

diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c
index 794c3ca49eac..98b1caa1c1d3 100644
--- a/security/selinux/hooks.c
+++ b/security/selinux/hooks.c
@@ -95,10 +95,6 @@
 #include "audit.h"
 #include "avc_ss.h"
 
-#define SB_TYPE_FMT "%s%s%s"
-#define SB_SUBTYPE(sb) (sb->s_subtype && sb->s_subtype[0])
-#define SB_TYPE_ARGS(sb) sb->s_type->name, SB_SUBTYPE(sb) ? "." : "", SB_SUBTYPE(sb) ? sb->s_subtype : ""
-
 extern struct security_operations *security_ops;
 
 /* SECMARK reference count */
@@ -413,8 +409,8 @@ static int sb_finish_set_opts(struct super_block *sb)
 		   the first boot of the SELinux kernel before we have
 		   assigned xattr values to the filesystem. */
 		if (!root_inode->i_op->getxattr) {
-			printk(KERN_WARNING "SELinux: (dev %s, type "SB_TYPE_FMT") has no "
-			       "xattr support\n", sb->s_id, SB_TYPE_ARGS(sb));
+			printk(KERN_WARNING "SELinux: (dev %s, type %s) has no "
+			       "xattr support\n", sb->s_id, sb->s_type->name);
 			rc = -EOPNOTSUPP;
 			goto out;
 		}
@@ -422,22 +418,22 @@ static int sb_finish_set_opts(struct super_block *sb)
 		if (rc < 0 && rc != -ENODATA) {
 			if (rc == -EOPNOTSUPP)
 				printk(KERN_WARNING "SELinux: (dev %s, type "
-				       SB_TYPE_FMT") has no security xattr handler\n",
-				       sb->s_id, SB_TYPE_ARGS(sb));
+				       "%s) has no security xattr handler\n",
+				       sb->s_id, sb->s_type->name);
 			else
 				printk(KERN_WARNING "SELinux: (dev %s, type "
-				       SB_TYPE_FMT") getxattr errno %d\n", sb->s_id,
-				       SB_TYPE_ARGS(sb), -rc);
+				       "%s) getxattr errno %d\n", sb->s_id,
+				       sb->s_type->name, -rc);
 			goto out;
 		}
 	}
 
 	if (sbsec->behavior > ARRAY_SIZE(labeling_behaviors))
-		printk(KERN_ERR "SELinux: initialized (dev %s, type "SB_TYPE_FMT"), unknown behavior\n",
-		       sb->s_id, SB_TYPE_ARGS(sb));
+		printk(KERN_ERR "SELinux: initialized (dev %s, type %s), unknown behavior\n",
+		       sb->s_id, sb->s_type->name);
 	else
-		printk(KERN_DEBUG "SELinux: initialized (dev %s, type "SB_TYPE_FMT"), %s\n",
-		       sb->s_id, SB_TYPE_ARGS(sb),
+		printk(KERN_DEBUG "SELinux: initialized (dev %s, type %s), %s\n",
+		       sb->s_id, sb->s_type->name,
 		       labeling_behaviors[sbsec->behavior-1]);
 
 	sbsec->flags |= SE_SBINITIALIZED;
@@ -600,6 +596,7 @@ static int selinux_set_mnt_opts(struct super_block *sb,
 	const struct cred *cred = current_cred();
 	int rc = 0, i;
 	struct superblock_security_struct *sbsec = sb->s_security;
+	const char *name = sb->s_type->name;
 	struct inode *inode = sbsec->sb->s_root->d_inode;
 	struct inode_security_struct *root_isec = inode->i_security;
 	u32 fscontext_sid = 0, context_sid = 0, rootcontext_sid = 0;
@@ -658,8 +655,8 @@ static int selinux_set_mnt_opts(struct super_block *sb,
 					     strlen(mount_options[i]), &sid);
 		if (rc) {
 			printk(KERN_WARNING "SELinux: security_context_to_sid"
-			       "(%s) failed for (dev %s, type "SB_TYPE_FMT") errno=%d\n",
-			       mount_options[i], sb->s_id, SB_TYPE_ARGS(sb), rc);
+			       "(%s) failed for (dev %s, type %s) errno=%d\n",
+			       mount_options[i], sb->s_id, name, rc);
 			goto out;
 		}
 		switch (flags[i]) {
@@ -806,8 +803,7 @@ out:
 out_double_mount:
 	rc = -EINVAL;
 	printk(KERN_WARNING "SELinux: mount invalid.  Same superblock, different "
-	       "security settings for (dev %s, type "SB_TYPE_FMT")\n", sb->s_id,
-	       SB_TYPE_ARGS(sb));
+	       "security settings for (dev %s, type %s)\n", sb->s_id, name);
 	goto out;
 }
 
@@ -2480,8 +2476,8 @@ static int selinux_sb_remount(struct super_block *sb, void *data)
 		rc = security_context_to_sid(mount_options[i], len, &sid);
 		if (rc) {
 			printk(KERN_WARNING "SELinux: security_context_to_sid"
-			       "(%s) failed for (dev %s, type "SB_TYPE_FMT") errno=%d\n",
-			       mount_options[i], sb->s_id, SB_TYPE_ARGS(sb), rc);
+			       "(%s) failed for (dev %s, type %s) errno=%d\n",
+			       mount_options[i], sb->s_id, sb->s_type->name, rc);
 			goto out_free_opts;
 		}
 		rc = -EINVAL;
@@ -2519,8 +2515,8 @@ out_free_secdata:
 	return rc;
 out_bad_option:
 	printk(KERN_WARNING "SELinux: unable to change security options "
-	       "during remount (dev %s, type "SB_TYPE_FMT")\n", sb->s_id,
-	       SB_TYPE_ARGS(sb));
+	       "during remount (dev %s, type=%s)\n", sb->s_id,
+	       sb->s_type->name);
 	goto out_free_opts;
 }
 
diff --git a/security/selinux/ss/services.c b/security/selinux/ss/services.c
index ee470a0b5c27..d106733ad987 100644
--- a/security/selinux/ss/services.c
+++ b/security/selinux/ss/services.c
@@ -2334,50 +2334,16 @@ int security_fs_use(struct super_block *sb)
 	struct ocontext *c;
 	struct superblock_security_struct *sbsec = sb->s_security;
 	const char *fstype = sb->s_type->name;
-	const char *subtype = (sb->s_subtype && sb->s_subtype[0]) ? sb->s_subtype : NULL;
-	struct ocontext *base = NULL;
 
 	read_lock(&policy_rwlock);
 
-	for (c = policydb.ocontexts[OCON_FSUSE]; c; c = c->next) {
-		char *sub;
-		int baselen;
-
-		baselen = strlen(fstype);
-
-		/* if base does not match, this is not the one */
-		if (strncmp(fstype, c->u.name, baselen))
-			continue;
-
-		/* if there is no subtype, this is the one! */
-		if (!subtype)
-			break;
-
-		/* skip past the base in this entry */
-		sub = c->u.name + baselen;
-
-		/* entry is only a base. save it. keep looking for subtype */
-		if (sub[0] == '\0') {
-			base = c;
-			continue;
-		}
-
-		/* entry is not followed by a subtype, so it is not a match */
-		if (sub[0] != '.')
-			continue;
-
-		/* whew, we found a subtype of this fstype */
-		sub++; /* move past '.' */
-
-		/* exact match of fstype AND subtype */
-		if (!strcmp(subtype, sub))
+	c = policydb.ocontexts[OCON_FSUSE];
+	while (c) {
+		if (strcmp(fstype, c->u.name) == 0)
 			break;
+		c = c->next;
 	}
 
-	/* in case we had found an fstype match but no subtype match */
-	if (!c)
-		c = base;
-
 	if (c) {
 		sbsec->behavior = c->v.behavior;
 		if (!c->sid[0]) {
-- 
cgit v1.2.3


From 46d01d63221c3508421dd72ff9c879f61053cffc Mon Sep 17 00:00:00 2001
From: Chad Hanson <chanson@trustedcs.com>
Date: Mon, 23 Dec 2013 17:45:01 -0500
Subject: selinux: fix broken peer recv check

Fix a broken networking check. Return an error if peer recv fails.  If
secmark is active and the packet recv succeeds the peer recv error is
ignored.

Signed-off-by: Chad Hanson <chanson@trustedcs.com>
Cc: stable@vger.kernel.org
Signed-off-by: Paul Moore <pmoore@redhat.com>
---
 security/selinux/hooks.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

(limited to 'security')

diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c
index 419491d8e7d2..5db26468b5c3 100644
--- a/security/selinux/hooks.c
+++ b/security/selinux/hooks.c
@@ -4334,8 +4334,10 @@ static int selinux_socket_sock_rcv_skb(struct sock *sk, struct sk_buff *skb)
 		}
 		err = avc_has_perm(sk_sid, peer_sid, SECCLASS_PEER,
 				   PEER__RECV, &ad);
-		if (err)
+		if (err) {
 			selinux_netlbl_err(skb, err, 0);
+			return err;
+		}
 	}
 
 	if (secmark_active) {
-- 
cgit v1.2.3


From c0c1439541f5305b57a83d599af32b74182933fe Mon Sep 17 00:00:00 2001
From: Oleg Nesterov <oleg@redhat.com>
Date: Mon, 23 Dec 2013 17:45:01 -0500
Subject: selinux: selinux_setprocattr()->ptrace_parent() needs rcu_read_lock()

selinux_setprocattr() does ptrace_parent(p) under task_lock(p),
but task_struct->alloc_lock doesn't pin ->parent or ->ptrace,
this looks confusing and triggers the "suspicious RCU usage"
warning because ptrace_parent() does rcu_dereference_check().

And in theory this is wrong, spin_lock()->preempt_disable()
doesn't necessarily imply rcu_read_lock() we need to access
the ->parent.

Reported-by: Evan McNabb <emcnabb@redhat.com>
Signed-off-by: Oleg Nesterov <oleg@redhat.com>
Cc: stable@vger.kernel.org
Signed-off-by: Paul Moore <pmoore@redhat.com>
---
 security/selinux/hooks.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'security')

diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c
index 5db26468b5c3..6625699f497c 100644
--- a/security/selinux/hooks.c
+++ b/security/selinux/hooks.c
@@ -5588,11 +5588,11 @@ static int selinux_setprocattr(struct task_struct *p,
 		/* Check for ptracing, and update the task SID if ok.
 		   Otherwise, leave SID unchanged and fail. */
 		ptsid = 0;
-		task_lock(p);
+		rcu_read_lock();
 		tracer = ptrace_parent(p);
 		if (tracer)
 			ptsid = task_sid(tracer);
-		task_unlock(p);
+		rcu_read_unlock();
 
 		if (tracer) {
 			error = avc_has_perm(ptsid, sid, SECCLASS_PROCESS,
-- 
cgit v1.2.3


From 3dc91d4338d698ce77832985f9cb183d8eeaf6be Mon Sep 17 00:00:00 2001
From: Steven Rostedt <rostedt@goodmis.org>
Date: Thu, 9 Jan 2014 21:46:34 -0500
Subject: SELinux: Fix possible NULL pointer dereference in
 selinux_inode_permission()

While running stress tests on adding and deleting ftrace instances I hit
this bug:

  BUG: unable to handle kernel NULL pointer dereference at 0000000000000020
  IP: selinux_inode_permission+0x85/0x160
  PGD 63681067 PUD 7ddbe067 PMD 0
  Oops: 0000 [#1] PREEMPT
  CPU: 0 PID: 5634 Comm: ftrace-test-mki Not tainted 3.13.0-rc4-test-00033-gd2a6dde-dirty #20
  Hardware name:                  /DG965MQ, BIOS MQ96510J.86A.0372.2006.0605.1717 06/05/2006
  task: ffff880078375800 ti: ffff88007ddb0000 task.ti: ffff88007ddb0000
  RIP: 0010:[<ffffffff812d8bc5>]  [<ffffffff812d8bc5>] selinux_inode_permission+0x85/0x160
  RSP: 0018:ffff88007ddb1c48  EFLAGS: 00010246
  RAX: 0000000000000000 RBX: 0000000000800000 RCX: ffff88006dd43840
  RDX: 0000000000000001 RSI: 0000000000000081 RDI: ffff88006ee46000
  RBP: ffff88007ddb1c88 R08: 0000000000000000 R09: ffff88007ddb1c54
  R10: 6e6576652f6f6f66 R11: 0000000000000003 R12: 0000000000000000
  R13: 0000000000000081 R14: ffff88006ee46000 R15: 0000000000000000
  FS:  00007f217b5b6700(0000) GS:ffffffff81e21000(0000) knlGS:0000000000000000
  CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033^M
  CR2: 0000000000000020 CR3: 000000006a0fe000 CR4: 00000000000007f0
  Call Trace:
    security_inode_permission+0x1c/0x30
    __inode_permission+0x41/0xa0
    inode_permission+0x18/0x50
    link_path_walk+0x66/0x920
    path_openat+0xa6/0x6c0
    do_filp_open+0x43/0xa0
    do_sys_open+0x146/0x240
    SyS_open+0x1e/0x20
    system_call_fastpath+0x16/0x1b
  Code: 84 a1 00 00 00 81 e3 00 20 00 00 89 d8 83 c8 02 40 f6 c6 04 0f 45 d8 40 f6 c6 08 74 71 80 cf 02 49 8b 46 38 4c 8d 4d cc 45 31 c0 <0f> b7 50 20 8b 70 1c 48 8b 41 70 89 d9 8b 78 04 e8 36 cf ff ff
  RIP  selinux_inode_permission+0x85/0x160
  CR2: 0000000000000020

Investigating, I found that the inode->i_security was NULL, and the
dereference of it caused the oops.

in selinux_inode_permission():

	isec = inode->i_security;

	rc = avc_has_perm_noaudit(sid, isec->sid, isec->sclass, perms, 0, &avd);

Note, the crash came from stressing the deletion and reading of debugfs
files.  I was not able to recreate this via normal files.  But I'm not
sure they are safe.  It may just be that the race window is much harder
to hit.

What seems to have happened (and what I have traced), is the file is
being opened at the same time the file or directory is being deleted.
As the dentry and inode locks are not held during the path walk, nor is
the inodes ref counts being incremented, there is nothing saving these
structures from being discarded except for an rcu_read_lock().

The rcu_read_lock() protects against freeing of the inode, but it does
not protect freeing of the inode_security_struct.  Now if the freeing of
the i_security happens with a call_rcu(), and the i_security field of
the inode is not changed (it gets freed as the inode gets freed) then
there will be no issue here.  (Linus Torvalds suggested not setting the
field to NULL such that we do not need to check if it is NULL in the
permission check).

Note, this is a hack, but it fixes the problem at hand.  A real fix is
to restructure the destroy_inode() to call all the destructor handlers
from the RCU callback.  But that is a major job to do, and requires a
lot of work.  For now, we just band-aid this bug with this fix (it
works), and work on a more maintainable solution in the future.

Link: http://lkml.kernel.org/r/20140109101932.0508dec7@gandalf.local.home
Link: http://lkml.kernel.org/r/20140109182756.17abaaa8@gandalf.local.home

Cc: stable@vger.kernel.org
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 security/selinux/hooks.c          | 20 ++++++++++++++++++--
 security/selinux/include/objsec.h |  5 ++++-
 2 files changed, 22 insertions(+), 3 deletions(-)

(limited to 'security')

diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c
index 6625699f497c..57b0b49f4e6e 100644
--- a/security/selinux/hooks.c
+++ b/security/selinux/hooks.c
@@ -234,6 +234,14 @@ static int inode_alloc_security(struct inode *inode)
 	return 0;
 }
 
+static void inode_free_rcu(struct rcu_head *head)
+{
+	struct inode_security_struct *isec;
+
+	isec = container_of(head, struct inode_security_struct, rcu);
+	kmem_cache_free(sel_inode_cache, isec);
+}
+
 static void inode_free_security(struct inode *inode)
 {
 	struct inode_security_struct *isec = inode->i_security;
@@ -244,8 +252,16 @@ static void inode_free_security(struct inode *inode)
 		list_del_init(&isec->list);
 	spin_unlock(&sbsec->isec_lock);
 
-	inode->i_security = NULL;
-	kmem_cache_free(sel_inode_cache, isec);
+	/*
+	 * The inode may still be referenced in a path walk and
+	 * a call to selinux_inode_permission() can be made
+	 * after inode_free_security() is called. Ideally, the VFS
+	 * wouldn't do this, but fixing that is a much harder
+	 * job. For now, simply free the i_security via RCU, and
+	 * leave the current inode->i_security pointer intact.
+	 * The inode will be freed after the RCU grace period too.
+	 */
+	call_rcu(&isec->rcu, inode_free_rcu);
 }
 
 static int file_alloc_security(struct file *file)
diff --git a/security/selinux/include/objsec.h b/security/selinux/include/objsec.h
index b1dfe1049450..078e553f52f2 100644
--- a/security/selinux/include/objsec.h
+++ b/security/selinux/include/objsec.h
@@ -38,7 +38,10 @@ struct task_security_struct {
 
 struct inode_security_struct {
 	struct inode *inode;	/* back pointer to inode object */
-	struct list_head list;	/* list of inode_security_struct */
+	union {
+		struct list_head list;	/* list of inode_security_struct */
+		struct rcu_head rcu;	/* for freeing the inode_security_struct */
+	};
 	u32 task_sid;		/* SID of creating task */
 	u32 sid;		/* SID of this object */
 	u16 sclass;		/* security class of this object */
-- 
cgit v1.2.3