4.9.53-stable review

4.9-stable review patch. If anyone has any objections, please let me know.

------------------

From: John Ogness <[email protected]>

commit fd7d56270b526ca3ed0c224362e3c64a0f86687a upstream.

Commit 0a1eb2d474ed ("fs/proc: Stop reporting eip and esp in /proc/PID/stat") stopped reporting eip/esp because it is racy and dangerous for executing tasks. The comment adds:

As far as I know, there are no use programs that make any material use of these fields, so just get rid of them.

However, existing userspace core-dump-handler applications (for example, minicoredumper) are using these fields since they provide an excellent cross-platform interface to these valuable pointers. So that commit introduced a user space visible regression.

Partially revert the change and make the readout possible for tasks with the proper permissions and only if the target task has the PF_DUMPCORE flag set.

---
 fs/proc/array.c |    9 +++++++++
 1 file changed, 9 insertions(+)

@@ -60,6 +60,7 @@
 #include <linux/tty.h>
 #include <linux/string.h>
 #include <linux/mman.h>
+#include <linux/sched.h>
 #include <linux/proc_fs.h>
 #include <linux/ioport.h>
 #include <linux/uaccess.h>

@@ -416,7 +417,15 @@ static int do_task_stat(struct seq_file
 		 * esp and eip are intentionally zeroed out.  There is no
 		 * non-racy way to read them without freezing the task.
 		 * Programs that need reliable values can use ptrace(2).
+		 *
+		 * The only exception is if the task is core dumping because
+		 * a program is not able to use ptrace(2) in that case. It is
+		 * safe because the task has stopped executing permanently.
 		 */
+		if (permitted && (task->flags & PF_DUMPCORE)) {
+			eip = KSTK_EIP(task);
+			esp = KSTK_ESP(task);
+		}
 	}
 
 	get_task_comm(tcomm, task);

4.9-stable review patch. If anyone has any objections, please let me know.

------------------

From: Johannes Berg <[email protected]>

commit 53168215909281a09d3afc6fb51a9d4f81f74d39 upstream.

With TXQs, the AP_VLAN interfaces are resolved to their owner AP interface when enqueuing the frame, which makes sense since the frame really goes out on that as far as the driver is concerned.

However, this introduces a problem: frames to be encrypted with a VLAN-specific GTK will now be encrypted with the AP GTK, since the information about which virtual interface to use to select the key is taken from the TXQ.

Fix this by preserving info->control.vif and using that in the dequeue function. This now requires doing the driver-mapping in the dequeue as well.

Since there's no way to filter the frames that are sitting on a TXQ, drop all frames, which may affect other interfaces, when an AP_VLAN is removed.

---
 include/net/mac80211.h |   15 ++-------------
 net/mac80211/iface.c   |   17 +++++++++++++++--
 net/mac80211/tx.c      |   36 +++++++++++++++++++++++++++++-------
 3 files changed, 46 insertions(+), 22 deletions(-)

@@ -902,21 +902,10 @@ struct ieee80211_tx_info {
 				unsigned long jiffies;
 			};
 			/* NB: vif can be NULL for injected frames */
-			union {
-				/* NB: vif can be NULL for injected frames */
-				struct ieee80211_vif *vif;
-
-				/* When packets are enqueued on txq it's easy
-				 * to re-construct the vif pointer. There's no
-				 * more space in tx_info so it can be used to
-				 * store the necessary enqueue time for packet
-				 * sojourn time computation.
-				 */
-				codel_time_t enqueue_time;
-			};
+			struct ieee80211_vif *vif;
 			struct ieee80211_key_conf *hw_key;
 			u32 flags;
-			/* 4 bytes free */
+			codel_time_t enqueue_time;
 		} control;
 		struct {
 			u64 cookie;

@@ -791,6 +791,7 @@ static int ieee80211_open(struct net_dev
 static void ieee80211_do_stop(struct ieee80211_sub_if_data *sdata,
 			      bool going_down)
 {
+	struct ieee80211_sub_if_data *txq_sdata = sdata;
 	struct ieee80211_local *local = sdata->local;
 	struct fq *fq = &local->fq;
 	unsigned long flags;

@@ -931,6 +932,9 @@ static void ieee80211_do_stop(struct iee
 
 	switch (sdata->vif.type) {
 	case NL80211_IFTYPE_AP_VLAN:
+		txq_sdata = container_of(sdata->bss,
+					 struct ieee80211_sub_if_data, u.ap);
+
 		mutex_lock(&local->mtx);
 		list_del(&sdata->u.vlan.list);
 		mutex_unlock(&local->mtx);

@@ -1001,8 +1005,17 @@ static void ieee80211_do_stop(struct iee
 	}
 	spin_unlock_irqrestore(&local->queue_stop_reason_lock, flags);
 
-	if (sdata->vif.txq) {
-		struct txq_info *txqi = to_txq_info(sdata->vif.txq);
+	if (txq_sdata->vif.txq) {
+		struct txq_info *txqi = to_txq_info(txq_sdata->vif.txq);
+
+		/*
+		 * FIXME FIXME
+		 *
+		 * We really shouldn't purge the *entire* txqi since that
+		 * contains frames for the other AP_VLANs (and possibly
+		 * the AP itself) as well, but there's no API in FQ now
+		 * to be able to filter.
+		 */
 
 		spin_lock_bh(&fq->lock);
 		ieee80211_txq_purge(local, txqi);

@@ -1277,11 +1277,6 @@ static void ieee80211_set_skb_enqueue_ti
 	IEEE80211_SKB_CB(skb)->control.enqueue_time = codel_get_time();
 }
 
-static void ieee80211_set_skb_vif(struct sk_buff *skb, struct txq_info *txqi)
-{
-	IEEE80211_SKB_CB(skb)->control.vif = txqi->txq.vif;
-}
-
 static u32 codel_skb_len_func(const struct sk_buff *skb)
 {
 	return skb->len;

@@ -3388,6 +3383,7 @@ struct sk_buff *ieee80211_tx_dequeue(str
 	struct ieee80211_tx_info *info;
 	struct ieee80211_tx_data tx;
 	ieee80211_tx_result r;
+	struct ieee80211_vif *vif;
 
 	spin_lock_bh(&fq->lock);
 

@@ -3404,8 +3400,6 @@ begin:
 	if (!skb)
 		goto out;
 
-	ieee80211_set_skb_vif(skb, txqi);
-
 	hdr = (struct ieee80211_hdr *)skb->data;
 	info = IEEE80211_SKB_CB(skb);
 

@@ -3462,6 +3456,34 @@ begin:
 		}
 	}
 
+	switch (tx.sdata->vif.type) {
+	case NL80211_IFTYPE_MONITOR:
+		if (tx.sdata->u.mntr.flags & MONITOR_FLAG_ACTIVE) {
+			vif = &tx.sdata->vif;
+			break;
+		}
+		tx.sdata = rcu_dereference(local->monitor_sdata);
+		if (tx.sdata) {
+			vif = &tx.sdata->vif;
+			info->hw_queue =
+				vif->hw_queue[skb_get_queue_mapping(skb)];
+		} else if (ieee80211_hw_check(&local->hw, QUEUE_CONTROL)) {
+			ieee80211_free_txskb(&local->hw, skb);
+			goto begin;
+		} else {
+			vif = NULL;
+		}
+		break;
+	case NL80211_IFTYPE_AP_VLAN:
+		tx.sdata = container_of(tx.sdata->bss,
+					struct ieee80211_sub_if_data, u.ap);
+		/* fall through */
+	default:
+		vif = &tx.sdata->vif;
+		break;
+	}
+
+	IEEE80211_SKB_CB(skb)->control.vif = vif;
 out:
 	spin_unlock_bh(&fq->lock);
 

4.9-stable review patch. If anyone has any objections, please let me know.

------------------

From: Paul Mackerras <[email protected]>

commit 47c5310a8dbe7c2cb9f0083daa43ceed76c257fa upstream, with part of commit edd03602d97236e8fea13cd76886c576186aa307 folded in.

Nixiaoming pointed out that there is a memory leak in kvm_vm_ioctl_create_spapr_tce() if the call to anon_inode_getfd() fails; the memory allocated for the kvmppc_spapr_tce_table struct is not freed, and nor are the pages allocated for the iommu tables. In addition, we have already incremented the process's count of locked memory pages, and this doesn't get restored on error.

David Hildenbrand pointed out that there is a race in that the function checks early on that there is not already an entry in the stt->iommu_tables list with the same LIOBN, but an entry with the same LIOBN could get added between then and when the new entry is added to the list.

This fixes all three problems. To simplify things, we now call anon_inode_getfd() before placing the new entry in the list. The check for an existing entry is done while holding the kvm->lock mutex, immediately before adding the new entry to the list. Finally, on failure we now call kvmppc_account_memlimit to decrement the process's count of locked memory pages.

[[email protected] - folded in that part of edd03602d972 ("KVM:
PPC: Book3S HV: Protect updates to spapr_tce_tables list", 2017-08-28) which restructured the code that 47c5310a8dbe modified, to avoid a build failure caused by the absence of put_unused_fd().]

---
 arch/powerpc/kvm/book3s_64_vio.c |   56 ++++++++++++++++++++++-----------------
 1 file changed, 32 insertions(+), 24 deletions(-)

@@ -150,6 +150,7 @@ long kvm_vm_ioctl_create_spapr_tce(struc
 				   struct kvm_create_spapr_tce_64 *args)
 {
 	struct kvmppc_spapr_tce_table *stt = NULL;
+	struct kvmppc_spapr_tce_table *siter;
 	unsigned long npages, size;
 	int ret = -ENOMEM;
 	int i;

@@ -157,24 +158,16 @@ long kvm_vm_ioctl_create_spapr_tce(struc
 	if (!args->size)
 		return -EINVAL;
 
-	/* Check this LIOBN hasn't been previously allocated */
-	list_for_each_entry(stt, &kvm->arch.spapr_tce_tables, list) {
-		if (stt->liobn == args->liobn)
-			return -EBUSY;
-	}
-
 	size = args->size;
 	npages = kvmppc_tce_pages(size);
 	ret = kvmppc_account_memlimit(kvmppc_stt_pages(npages), true);
-	if (ret) {
-		stt = NULL;
-		goto fail;
-	}
+	if (ret)
+		return ret;
 
 	stt = kzalloc(sizeof(*stt) + npages * sizeof(struct page *),
 		      GFP_KERNEL);
 	if (!stt)
-		goto fail;
+		goto fail_acct;
 
 	stt->liobn = args->liobn;
 	stt->page_shift = args->page_shift;

@@ -188,24 +181,39 @@ long kvm_vm_ioctl_create_spapr_tce(struc
 			goto fail;
 	}
 
-	kvm_get_kvm(kvm);
-
 	mutex_lock(&kvm->lock);
-	list_add_rcu(&stt->list, &kvm->arch.spapr_tce_tables);
 
-	mutex_unlock(&kvm->lock);
+	/* Check this LIOBN hasn't been previously allocated */
+	ret = 0;
+	list_for_each_entry(siter, &kvm->arch.spapr_tce_tables, list) {
+		if (siter->liobn == args->liobn) {
+			ret = -EBUSY;
+			break;
+		}
+	}
+
+	if (!ret)
+		ret = anon_inode_getfd("kvm-spapr-tce", &kvm_spapr_tce_fops,
+				       stt, O_RDWR | O_CLOEXEC);
+
+	if (ret >= 0) {
+		list_add_rcu(&stt->list, &kvm->arch.spapr_tce_tables);
+		kvm_get_kvm(kvm);
+	}
 
-	return anon_inode_getfd("kvm-spapr-tce", &kvm_spapr_tce_fops,
-				stt, O_RDWR | O_CLOEXEC);
+	mutex_unlock(&kvm->lock);
 
-fail:
-	if (stt) {
-		for (i = 0; i < npages; i++)
-			if (stt->pages[i])
-				__free_page(stt->pages[i]);
+	if (ret >= 0)
+		return ret;
 
-		kfree(stt);
-	}
+ fail:
+	for (i = 0; i < npages; i++)
+		if (stt->pages[i])
+			__free_page(stt->pages[i]);
+
+	kfree(stt);
+ fail_acct:
+	kvmppc_account_memlimit(kvmppc_stt_pages(npages), false);
 	return ret;
 }
 

4.9-stable review patch. If anyone has any objections, please let me know.

------------------

From: LEROY Christophe <[email protected]>

commit 886a27c0fc8a34633aadb0986dba11d8c150ae2e upstream.

md5sum on some files gives wrong result

Exemple:

With the md5sum from libkcapi:
c15115c05bad51113f81bdaee735dd09 test

With the original md5sum:
bbdf41d80ba7e8b2b7be3a0772be76cb test

This patch fixes this issue

---
 drivers/crypto/talitos.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

@@ -1769,7 +1769,7 @@ static int common_nonsnoop_hash(struct t
 
 	sg_count = edesc->src_nents ?: 1;
 	if (is_sec1 && sg_count > 1)
-		sg_copy_to_buffer(areq->src, sg_count, edesc->buf, length);
+		sg_copy_to_buffer(req_ctx->psrc, sg_count, edesc->buf, length);
 	else
 		sg_count = dma_map_sg(dev, req_ctx->psrc, sg_count,
 				      DMA_TO_DEVICE);

4.9-stable review patch. If anyone has any objections, please let me know.

------------------

From: Jason A. Donenfeld <[email protected]>

commit 910801809b2e40a4baedd080ef5d80b4a180e70e upstream.

Error paths forgot to zero out sensitive material, so this patch changes some kfrees into a kzfrees.

---
 security/keys/big_key.c |   12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

@@ -194,7 +194,7 @@ int big_key_preparse(struct key_preparse
 		*path = file->f_path;
 		path_get(path);
 		fput(file);
-		kfree(data);
+		kzfree(data);
 	} else {
 		/* Just store the data in a buffer */
 		void *data = kmalloc(datalen, GFP_KERNEL);

@@ -210,9 +210,9 @@ int big_key_preparse(struct key_preparse
 err_fput:
 	fput(file);
 err_enckey:
-	kfree(enckey);
+	kzfree(enckey);
 error:
-	kfree(data);
+	kzfree(data);
 	return ret;
 }
 

@@ -226,7 +226,7 @@ void big_key_free_preparse(struct key_pr
 
 		path_put(path);
 	}
-	kfree(prep->payload.data[big_key_data]);
+	kzfree(prep->payload.data[big_key_data]);
 }
 
 /*

@@ -258,7 +258,7 @@ void big_key_destroy(struct key *key)
 		path->mnt = NULL;
 		path->dentry = NULL;
 	}
-	kfree(key->payload.data[big_key_data]);
+	kzfree(key->payload.data[big_key_data]);
 	key->payload.data[big_key_data] = NULL;
 }
 

@@ -326,7 +326,7 @@ long big_key_read(const struct key *key,
 err_fput:
 		fput(file);
 error:
-		kfree(data);
+		kzfree(data);
 	} else {
 		ret = datalen;
 		if (copy_to_user(buffer, key->payload.data[big_key_data],

4.9-stable review patch. If anyone has any objections, please let me know.

------------------

From: Gustavo Romero <[email protected]>

commit c1fa0768a8713b135848f78fd43ffc208d8ded70 upstream.

Commit cd63f3c ("powerpc/tm: Fix saving of TM SPRs in core dump") added code to access TM SPRs in flush_tmregs_to_thread(). However flush_tmregs_to_thread() does not check if TM feature is available on CPU before trying to access TM SPRs in order to copy live state to thread structures. flush_tmregs_to_thread() is indeed guarded by CONFIG_PPC_TRANSACTIONAL_MEM but it might be the case that kernel was compiled with CONFIG_PPC_TRANSACTIONAL_MEM enabled and ran on a CPU without TM feature available, thus rendering the execution of TM instructions that are treated by the CPU as illegal instructions.

The fix is just to add proper checking in flush_tmregs_to_thread() if CPU has the TM feature before accessing any TM-specific resource, returning immediately if TM is no available on the CPU. Adding that checking in flush_tmregs_to_thread() instead of in places where it is called, like in vsr_get() and vsr_set(), is better because avoids the same problem cropping up elsewhere.

index 07cd22e35405..f52ad5bb7109 100644
@@ -131,7 +131,7 @@ static void flush_tmregs_to_thread(struct task_struct *tsk)
 	 * in the appropriate thread structures from live.
 	 */
 
-	if (tsk != current)
+	if ((!cpu_has_feature(CPU_FTR_TM)) || (tsk != current))
 		return;
 
 	if (MSR_TM_SUSPENDED(mfmsr())) {

4.9-stable review patch. If anyone has any objections, please let me know.

------------------

From: Steve French <[email protected]>

commit 0603c96f3af50e2f9299fa410c224ab1d465e0f9 upstream.

As long as signing is supported (ie not a guest user connection) and connection is SMB3 or SMB3.02, then validate negotiate (protect against man in the middle downgrade attacks). We had been doing this only when signing was required, not when signing was just enabled, but this more closely matches recommended SMB3 behavior and is better security. Suggested by Metze.

---
 fs/cifs/smb2pdu.c |   17 ++++++++++++-----
 1 file changed, 12 insertions(+), 5 deletions(-)

@@ -531,15 +531,22 @@ int smb3_validate_negotiate(const unsign
 
 	/*
 	 * validation ioctl must be signed, so no point sending this if we
-	 * can not sign it.  We could eventually change this to selectively
+	 * can not sign it (ie are not known user).  Even if signing is not
+	 * required (enabled but not negotiated), in those cases we selectively
 	 * sign just this, the first and only signed request on a connection.
-	 * This is good enough for now since a user who wants better security
-	 * would also enable signing on the mount. Having validation of
-	 * negotiate info for signed connections helps reduce attack vectors
+	 * Having validation of negotiate info  helps reduce attack vectors.
 	 */
-	if (tcon->ses->server->sign == false)
+	if (tcon->ses->session_flags & SMB2_SESSION_FLAG_IS_GUEST)
 		return 0; /* validation requires signing */
 
+	if (tcon->ses->user_name == NULL) {
+		cifs_dbg(FYI, "Can't validate negotiate: null user mount\n");
+		return 0; /* validation requires signing */
+	}
+
+	if (tcon->ses->session_flags & SMB2_SESSION_FLAG_IS_NULL)
+		cifs_dbg(VFS, "Unexpected null user (anonymous) auth flag sent by server\n");
+
 	vneg_inbuf.Capabilities =
 			cpu_to_le32(tcon->ses->server->vals->req_capabilities);
 	memcpy(vneg_inbuf.Guid, tcon->ses->server->client_guid,

4.9-stable review patch. If anyone has any objections, please let me know.

------------------

From: Boqun Feng <[email protected]>

commit b862789aa5186d5ea3a024b7cfe0f80c3a38b980 upstream.

Sasha Levin reported a WARNING:

| WARNING: CPU: 0 PID: 6974 at kernel/rcu/tree_plugin.h:329
| rcu_preempt_note_context_switch kernel/rcu/tree_plugin.h:329 [inline]
| WARNING: CPU: 0 PID: 6974 at kernel/rcu/tree_plugin.h:329
| rcu_note_context_switch+0x16c/0x2210 kernel/rcu/tree.c:458
...
| CPU: 0 PID: 6974 Comm: syz-fuzzer Not tainted 4.13.0-next-20170908+ #246
| Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS
| 1.10.1-1ubuntu1 04/01/2014
| Call Trace:
...
| RIP: 0010:rcu_preempt_note_context_switch kernel/rcu/tree_plugin.h:329 [inline]
| RIP: 0010:rcu_note_context_switch+0x16c/0x2210 kernel/rcu/tree.c:458
| RSP: 0018:ffff88003b2debc8 EFLAGS: 00010002
| RAX: 0000000000000001 RBX: 1ffff1000765bd85 RCX: 0000000000000000
| RDX: 1ffff100075d7882 RSI: ffffffffb5c7da20 RDI: ffff88003aebc410
| RBP: ffff88003b2def30 R08: dffffc0000000000 R09: 0000000000000001
| R10: 0000000000000000 R11: 0000000000000000 R12: ffff88003b2def08
| R13: 0000000000000000 R14: ffff88003aebc040 R15: ffff88003aebc040
| __schedule+0x201/0x2240 kernel/sched/core.c:3292
| schedule+0x113/0x460 kernel/sched/core.c:3421
| kvm_async_pf_task_wait+0x43f/0x940 arch/x86/kernel/kvm.c:158
| do_async_page_fault+0x72/0x90 arch/x86/kernel/kvm.c:271
| async_page_fault+0x22/0x30 arch/x86/entry/entry_64.S:1069
| RIP: 0010:format_decode+0x240/0x830 lib/vsprintf.c:1996
| RSP: 0018:ffff88003b2df520 EFLAGS: 00010283
| RAX: 000000000000003f RBX: ffffffffb5d1e141 RCX: ffff88003b2df670
| RDX: 0000000000000001 RSI: dffffc0000000000 RDI: ffffffffb5d1e140
| RBP: ffff88003b2df560 R08: dffffc0000000000 R09: 0000000000000000
| R10: ffff88003b2df718 R11: 0000000000000000 R12: ffff88003b2df5d8
| R13: 0000000000000064 R14: ffffffffb5d1e140 R15: 0000000000000000
| vsnprintf+0x173/0x1700 lib/vsprintf.c:2136
| sprintf+0xbe/0xf0 lib/vsprintf.c:2386
| proc_self_get_link+0xfb/0x1c0 fs/proc/self.c:23
| get_link fs/namei.c:1047 [inline]
| link_path_walk+0x1041/0x1490 fs/namei.c:2127

...

This happened when the host hit a page fault, and delivered it as in an async page fault, while the guest was in an RCU read-side critical section. The guest then tries to reschedule in kvm_async_pf_task_wait(), but rcu_preempt_note_context_switch() would treat the reschedule as a sleep in RCU read-side critical section, which is not allowed (even in preemptible RCU). Thus the WARN.

To cure this, make kvm_async_pf_task_wait() go to the halt path if the PF happens in a RCU read-side critical section.

---
 arch/x86/kernel/kvm.c |    3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

@@ -141,7 +141,8 @@ void kvm_async_pf_task_wait(u32 token)
 
 	n.token = token;
 	n.cpu = smp_processor_id();
-	n.halted = is_idle_task(current) || preempt_count() > 1;
+	n.halted = is_idle_task(current) || preempt_count() > 1 ||
+		   rcu_preempt_depth();
 	init_swait_queue_head(&n.wq);
 	hlist_add_head(&n.link, &b->list);
 	raw_spin_unlock(&b->lock);

4.9-stable review patch. If anyone has any objections, please let me know.

------------------

From: Ross Zwisler <[email protected]>

commit 6851a3db7e224bbb85e23b3c64a506c9e0904382 upstream.

Currently only the blocksize is checked, but we should really be calling bdev_dax_supported() which also tests to make sure we can get a struct dax_device and that the dax_direct_access() path is working.

This is the same check that we do for the "-o dax" mount option in xfs_fs_fill_super().

This does not fix the race issues that caused the XFS DAX inode option to be disabled, so that option will still be disabled. If/when we re-enable it, though, I think we will want this issue to have been fixed. I also do think that we want to fix this in stable kernels.

---
 fs/xfs/xfs_ioctl.c |    3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

@@ -1085,6 +1085,7 @@ xfs_ioctl_setattr_dax_invalidate(
 	int			*join_flags)
 {
 	struct inode		*inode = VFS_I(ip);
+	struct super_block	*sb = inode->i_sb;
 	int			error;
 
 	*join_flags = 0;

@@ -1097,7 +1098,7 @@ xfs_ioctl_setattr_dax_invalidate(
 	if (fa->fsx_xflags & FS_XFLAG_DAX) {
 		if (!(S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode)))
 			return -EINVAL;
-		if (ip->i_mount->m_sb.sb_blocksize != PAGE_SIZE)
+		if (bdev_dax_supported(sb, sb->s_blocksize) < 0)
 			return -EINVAL;
 	}
 

4.9-stable review patch. If anyone has any objections, please let me know.

------------------

From: Laurent Dufour <[email protected]>

commit a3c4fb7c9c2ebfd50b8c60f6c069932bb319bc37 upstream.

commit 7b2d0dbac489 ("x86/mm/pkeys: Pass VMA down in to fault signal generation code") passes down a vma pointer to the error path, but that is done once the mmap_sem is released when calling mm_fault_error() from __do_page_fault().

This is dangerous as the vma structure is no more safe to be used once the mmap_sem has been released. As only the protection key value is required in the error processing, we could just pass down this value.

Fix it by passing a pointer to a protection key value down to the fault signal generation code. The use of a pointer allows to keep the check generating a warning message in fill_sig_info_pkey() when the vma was not known. If the pointer is valid, the protection value can be accessed by deferencing the pointer.

[ tglx: Made *pkey u32 as that's the type which is passed in siginfo ]

---
 arch/x86/mm/fault.c |   47 ++++++++++++++++++++++++-----------------------
 1 file changed, 24 insertions(+), 23 deletions(-)

@@ -191,8 +191,7 @@ is_prefetch(struct pt_regs *regs, unsign
  * 6. T1   : reaches here, sees vma_pkey(vma)=5, when we really
  *	     faulted on a pte with its pkey=4.
  */
-static void fill_sig_info_pkey(int si_code, siginfo_t *info,
-		struct vm_area_struct *vma)
+static void fill_sig_info_pkey(int si_code, siginfo_t *info, u32 *pkey)
 {
 	/* This is effectively an #ifdef */
 	if (!boot_cpu_has(X86_FEATURE_OSPKE))

@@ -208,7 +207,7 @@ static void fill_sig_info_pkey(int si_co
 	 * valid VMA, so we should never reach this without a
 	 * valid VMA.
 	 */
-	if (!vma) {
+	if (!pkey) {
 		WARN_ONCE(1, "PKU fault with no VMA passed in");
 		info->si_pkey = 0;
 		return;

@@ -218,13 +217,12 @@ static void fill_sig_info_pkey(int si_co
 	 * absolutely guranteed to be 100% accurate because of
 	 * the race explained above.
 	 */
-	info->si_pkey = vma_pkey(vma);
+	info->si_pkey = *pkey;
 }
 
 static void
 force_sig_info_fault(int si_signo, int si_code, unsigned long address,
-		     struct task_struct *tsk, struct vm_area_struct *vma,
-		     int fault)
+		     struct task_struct *tsk, u32 *pkey, int fault)
 {
 	unsigned lsb = 0;
 	siginfo_t info;

@@ -239,7 +237,7 @@ force_sig_info_fault(int si_signo, int s
 		lsb = PAGE_SHIFT;
 	info.si_addr_lsb = lsb;
 
-	fill_sig_info_pkey(si_code, &info, vma);
+	fill_sig_info_pkey(si_code, &info, pkey);
 
 	force_sig_info(si_signo, &info, tsk);
 }

@@ -718,8 +716,6 @@ no_context(struct pt_regs *regs, unsigne
 	struct task_struct *tsk = current;
 	unsigned long flags;
 	int sig;
-	/* No context means no VMA to pass down */
-	struct vm_area_struct *vma = NULL;
 
 	/* Are we prepared to handle this kernel fault? */
 	if (fixup_exception(regs, X86_TRAP_PF)) {

@@ -744,7 +740,7 @@ no_context(struct pt_regs *regs, unsigne
 
 			/* XXX: hwpoison faults will set the wrong code. */
 			force_sig_info_fault(signal, si_code, address,
-					     tsk, vma, 0);
+					     tsk, NULL, 0);
 		}
 
 		/*

@@ -853,8 +849,7 @@ show_signal_msg(struct pt_regs *regs, un
 
 static void
 __bad_area_nosemaphore(struct pt_regs *regs, unsigned long error_code,
-		       unsigned long address, struct vm_area_struct *vma,
-		       int si_code)
+		       unsigned long address, u32 *pkey, int si_code)
 {
 	struct task_struct *tsk = current;
 

@@ -902,7 +897,7 @@ __bad_area_nosemaphore(struct pt_regs *r
 		tsk->thread.error_code	= error_code;
 		tsk->thread.trap_nr	= X86_TRAP_PF;
 
-		force_sig_info_fault(SIGSEGV, si_code, address, tsk, vma, 0);
+		force_sig_info_fault(SIGSEGV, si_code, address, tsk, pkey, 0);
 
 		return;
 	}

@@ -915,9 +910,9 @@ __bad_area_nosemaphore(struct pt_regs *r
 
 static noinline void
 bad_area_nosemaphore(struct pt_regs *regs, unsigned long error_code,
-		     unsigned long address, struct vm_area_struct *vma)
+		     unsigned long address, u32 *pkey)
 {
-	__bad_area_nosemaphore(regs, error_code, address, vma, SEGV_MAPERR);
+	__bad_area_nosemaphore(regs, error_code, address, pkey, SEGV_MAPERR);
 }
 
 static void

@@ -925,6 +920,10 @@ __bad_area(struct pt_regs *regs, unsigne
 	   unsigned long address,  struct vm_area_struct *vma, int si_code)
 {
 	struct mm_struct *mm = current->mm;
+	u32 pkey;
+
+	if (vma)
+		pkey = vma_pkey(vma);
 
 	/*
 	 * Something tried to access memory that isn't in our memory map..

@@ -932,7 +931,8 @@ __bad_area(struct pt_regs *regs, unsigne
 	 */
 	up_read(&mm->mmap_sem);
 
-	__bad_area_nosemaphore(regs, error_code, address, vma, si_code);
+	__bad_area_nosemaphore(regs, error_code, address,
+			       (vma) ? &pkey : NULL, si_code);
 }
 
 static noinline void

@@ -975,7 +975,7 @@ bad_area_access_error(struct pt_regs *re
 
 static void
 do_sigbus(struct pt_regs *regs, unsigned long error_code, unsigned long address,
-	  struct vm_area_struct *vma, unsigned int fault)
+	  u32 *pkey, unsigned int fault)
 {
 	struct task_struct *tsk = current;
 	int code = BUS_ADRERR;

@@ -1002,13 +1002,12 @@ do_sigbus(struct pt_regs *regs, unsigned
 		code = BUS_MCEERR_AR;
 	}
 #endif
-	force_sig_info_fault(SIGBUS, code, address, tsk, vma, fault);
+	force_sig_info_fault(SIGBUS, code, address, tsk, pkey, fault);
 }
 
 static noinline void
 mm_fault_error(struct pt_regs *regs, unsigned long error_code,
-	       unsigned long address, struct vm_area_struct *vma,
-	       unsigned int fault)
+	       unsigned long address, u32 *pkey, unsigned int fault)
 {
 	if (fatal_signal_pending(current) && !(error_code & PF_USER)) {
 		no_context(regs, error_code, address, 0, 0);

@@ -1032,9 +1031,9 @@ mm_fault_error(struct pt_regs *regs, uns
 	} else {
 		if (fault & (VM_FAULT_SIGBUS|VM_FAULT_HWPOISON|
 			     VM_FAULT_HWPOISON_LARGE))
-			do_sigbus(regs, error_code, address, vma, fault);
+			do_sigbus(regs, error_code, address, pkey, fault);
 		else if (fault & VM_FAULT_SIGSEGV)
-			bad_area_nosemaphore(regs, error_code, address, vma);
+			bad_area_nosemaphore(regs, error_code, address, pkey);
 		else
 			BUG();
 	}

@@ -1220,6 +1219,7 @@ __do_page_fault(struct pt_regs *regs, un
 	struct mm_struct *mm;
 	int fault, major = 0;
 	unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;
+	u32 pkey;
 
 	tsk = current;
 	mm = tsk->mm;

@@ -1420,9 +1420,10 @@ good_area:
 		return;
 	}
 
+	pkey = vma_pkey(vma);
 	up_read(&mm->mmap_sem);
 	if (unlikely(fault & VM_FAULT_ERROR)) {
-		mm_fault_error(regs, error_code, address, vma, fault);
+		mm_fault_error(regs, error_code, address, &pkey, fault);
 		return;
 	}
 

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in the body to [email protected]. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"[email protected]"> [email protected] </a>

4.9-stable review patch. If anyone has any objections, please let me know.

------------------

From: Eric Biggers <[email protected]>

commit 814fb7bb7db5433757d76f4c4502c96fc53b0b5e upstream.

On x86, userspace can use the ptrace() or rt_sigreturn() system calls to set a task's extended state (xstate) or "FPU" registers. ptrace() can set them for another task using the PTRACE_SETREGSET request with NT_X86_XSTATE, while rt_sigreturn() can set them for the current task. In either case, registers can be set to any value, but the kernel assumes that the XSAVE area itself remains valid in the sense that the CPU can restore it.

However, in the case where the kernel is using the uncompacted xstate format (which it does whenever the XSAVES instruction is unavailable), it was possible for userspace to set the xcomp_bv field in the xstate_header to an arbitrary value. However, all bits in that field are reserved in the uncompacted case, so when switching to a task with nonzero xcomp_bv, the XRSTOR instruction failed with a #GP fault. This caused the WARN_ON_FPU(err) in copy_kernel_to_xregs() to be hit. In addition, since the error is otherwise ignored, the FPU registers from the task previously executing on the CPU were leaked.

Fix the bug by checking that the user-supplied value of xcomp_bv is 0 in the uncompacted case, and returning an error otherwise.

The reason for validating xcomp_bv rather than simply overwriting it with 0 is that we want userspace to see an error if it (incorrectly) provides an XSAVE area in compacted format rather than in uncompacted format.

Note that as before, in case of error we clear the task's FPU state. This is perhaps non-ideal, especially for PTRACE_SETREGSET; it might be better to return an error before changing anything. But it seems the "clear on error" behavior is fine for now, and it's a little tricky to do otherwise because it would mean we couldn't simply copy the full userspace state into kernel memory in one __copy_from_user().

This bug was found by syzkaller, which hit the above-mentioned WARN_ON_FPU():

    WARNING: CPU: 1 PID: 0 at ./arch/x86/include/asm/fpu/internal.h:373 __switch_to+0x5b5/0x5d0
    CPU: 1 PID: 0 Comm: swapper/1 Not tainted 4.13.0 #453
    Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Bochs 01/01/2011
    task: ffff9ba2bc8e42c0 task.stack: ffffa78cc036c000
    RIP: 0010:__switch_to+0x5b5/0x5d0
    RSP: 0000:ffffa78cc08bbb88 EFLAGS: 00010082
    RAX: 00000000fffffffe RBX: ffff9ba2b8bf2180 RCX: 00000000c0000100
    RDX: 00000000ffffffff RSI: 000000005cb10700 RDI: ffff9ba2b8bf36c0
    RBP: ffffa78cc08bbbd0 R08: 00000000929fdf46 R09: 0000000000000001
    R10: 0000000000000000 R11: 0000000000000000 R12: ffff9ba2bc8e42c0
    R13: 0000000000000000 R14: ffff9ba2b8bf3680 R15: ffff9ba2bf5d7b40
    FS:  00007f7e5cb10700(0000) GS:ffff9ba2bf400000(0000) knlGS:0000000000000000
    CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
    CR2: 00000000004005cc CR3: 0000000079fd5000 CR4: 00000000001406e0
    Call Trace:
    Code: 84 00 00 00 00 00 e9 11 fd ff ff 0f ff 66 0f 1f 84 00 00 00 00 00 e9 e7 fa ff ff 0f ff 66 0f 1f 84 00 00 00 00 00 e9 c2 fa ff ff <0f> ff 66 0f 1f 84 00 00 00 00 00 e9 d4 fc ff ff 66 66 2e 0f 1f

Here is a C reproducer. The expected behavior is that the program spin forever with no output. However, on a buggy kernel running on a processor with the "xsave" feature but without the "xsaves" feature (e.g. Sandy Bridge through Broadwell for Intel), within a second or two the program reports that the xmm registers were corrupted, i.e. were not restored correctly. With CONFIG_X86_DEBUG_FPU=y it also hits the above kernel warning.

    #define _GNU_SOURCE
    #include <stdbool.h>
    #include <inttypes.h>
    #include <linux/elf.h>
    #include <stdio.h>
    #include <sys/ptrace.h>
    #include <sys/uio.h>
    #include <sys/wait.h>
    #include <unistd.h>

    int main(void)
    {
        int pid = fork();
        uint64_t xstate[512];
        struct iovec iov = { .iov_base = xstate, .iov_len = sizeof(xstate) };

        if (pid == 0) {
            bool tracee = true;
            for (int i = 0; i < sysconf(_SC_NPROCESSORS_ONLN) && tracee; i++)
                tracee = (fork() != 0);
            uint32_t xmm0[4] = { [0 ... 3] = tracee ? 0x00000000 : 0xDEADBEEF };
            asm volatile("   movdqu %0, %%xmm0\n"
                         "   mov %0, %%rbx\n"
                         "1: movdqu %%xmm0, %0\n"
                         "   mov %0, %%rax\n"
                         "   cmp %%rax, %%rbx\n"
                         "   je 1b\n"
                         : "+m" (xmm0) : : "rax", "rbx", "xmm0");
            printf("BUG: xmm registers corrupted!  tracee=%d, xmm0=%08X%08X%08X%08X\n",
                   tracee, xmm0[0], xmm0[1], xmm0[2], xmm0[3]);
        } else {
            usleep(100000);
            ptrace(PTRACE_ATTACH, pid, 0, 0);
            wait(NULL);
            ptrace(PTRACE_GETREGSET, pid, NT_X86_XSTATE, &iov);
            xstate[65] = -1;
            ptrace(PTRACE_SETREGSET, pid, NT_X86_XSTATE, &iov);
            ptrace(PTRACE_CONT, pid, 0, 0);
            wait(NULL);
        }
        return 1;
    }

Note: the program only tests for the bug using the ptrace() system call. The bug can also be reproduced using the rt_sigreturn() system call, but only when called from a 32-bit program, since for 64-bit programs the kernel restores the FPU state from the signal frame by doing XRSTOR directly from userspace memory (with proper error checking).

---
 arch/x86/kernel/fpu/regset.c |    9 +++++++--
 arch/x86/kernel/fpu/signal.c |    4 ++++
 2 files changed, 11 insertions(+), 2 deletions(-)

@@ -130,11 +130,16 @@ int xstateregs_set(struct task_struct *t
 
 	fpu__activate_fpstate_write(fpu);
 
-	if (boot_cpu_has(X86_FEATURE_XSAVES))
+	if (boot_cpu_has(X86_FEATURE_XSAVES)) {
 		ret = copyin_to_xsaves(kbuf, ubuf, xsave);
-	else
+	} else {
 		ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, xsave, 0, -1);
 
+		/* xcomp_bv must be 0 when using uncompacted format */
+		if (!ret && xsave->header.xcomp_bv)
+			ret = -EINVAL;
+	}
+
 	/*
 	 * In case of failure, mark all states as init:
 	 */

@@ -329,6 +329,10 @@ static int __fpu__restore_sig(void __use
 		} else {
 			err = __copy_from_user(&fpu->state.xsave,
 					       buf_fx, state_size);
+
+			/* xcomp_bv must be 0 when using uncompacted format */
+			if (!err && state_size > offsetof(struct xregs_state, header) && fpu->state.xsave.header.xcomp_bv)
+				err = -EINVAL;
 		}
 
 		if (err || __copy_from_user(&env, buf, sizeof(env))) {

This is the start of the stable review cycle for the 4.9.53 release. There are 64 patches in this series, all will be posted as a response to this one. If anyone has any issues with these being applied, please let me know.

Responses should be made by Thu Oct 5 11:42:06 UTC 2017. Anything received after that time might be too late.

The whole patch series can be found in one patch at:

	kernel.org/pub/linux/kernel/v4.x/stable-review/patch-4.9.53-rc1.gz

or in the git tree and branch at:
git://git.kernel.org/pub/scm/linux/kernel/git/stable/linux-stable-rc.git linux-4.9.y
and the diffstat can be found below.

thanks,

greg k-h

-------------
Pseudo-Shortlog of commits:

Greg Kroah-Hartman <[email protected]>

    Linux 4.9.53-rc1

Stefano Stabellini <[email protected]>
swiotlb-xen: implement xen_swiotlb_dma_mmap callback

Vladis Dronov <[email protected]>
video: fbdev: aty: do not leak uninitialized padding in clk to userspace

Paolo Bonzini <[email protected]>
KVM: VMX: use cmpxchg64

Frederic Barrat <[email protected]>
cxl: Fix driver use count

Haozhong Zhang <[email protected]>
KVM: VMX: remove WARN_ON_ONCE in kvm_vcpu_trigger_posted_interrupt

Haozhong Zhang <[email protected]>
KVM: VMX: do not change SN bit in vmx_update_pi_irte()

Myungho Jung <[email protected]>
timer/sysclt: Restrict timer migration sysctl values to 0 and 1

Andreas Gruenbacher <[email protected]>
gfs2: Fix debugfs glocks dump

Eric Biggers <[email protected]>
x86/fpu: Don't let userspace set bogus xcomp_bv

Laurent Dufour <[email protected]>
x86/mm: Fix fault error path using unsafe vma pointer

satoru takeuchi <[email protected]>
btrfs: prevent to set invalid default subvolid

Naohiro Aota <[email protected]>
btrfs: propagate error to btrfs_cmp_data_prepare caller

Naohiro Aota <[email protected]>
btrfs: fix NULL pointer dereference from free_reloc_roots()

Nicolai Stange <[email protected]>
PCI: Fix race condition with driver_override

Lucas Stach <[email protected]>
etnaviv: fix gem object list corruption

Ross Zwisler <[email protected]>
xfs: validate bdev support for DAX inode flag

Jim Mattson <[email protected]>
kvm: nVMX: Don't allow L2 to access the hardware CR8

Jan H. Schönherr <[email protected]>
KVM: VMX: Do not BUG() on out-of-bounds guest IRQ

Boqun Feng <[email protected]>
kvm/x86: Handle async PF in RCU read-side critical sections

Paolo Bonzini <[email protected]>
KVM: VMX: simplify and fix vmx_vcpu_pi_load

Paolo Bonzini <[email protected]>
KVM: VMX: avoid double list add with VT-d posted interrupts

Paolo Bonzini <[email protected]>
KVM: VMX: extract __pi_post_block

Will Deacon <[email protected]>
arm64: fault: Route pte translation faults via do_translation_fault

Marc Zyngier <[email protected]>
arm64: Make sure SPsel is always set

Oleg Nesterov <[email protected]>
seccomp: fix the usage of get/put_seccomp_filter() in seccomp_get_filter()

Kees Cook <[email protected]>
selftests/seccomp: Support glibc 2.26 siginfo_t.h

Steve Wise <[email protected]>
iw_cxgb4: put ep reference in pass_accept_req()

Steve Wise <[email protected]>
iw_cxgb4: remove the stid on listen create failure

Christoph Hellwig <[email protected]>
bsg-lib: don't free job in bsg_prepare_job

Vladis Dronov <[email protected]>
nl80211: check for the required netlink attributes presence

Andreas Gruenbacher <[email protected]>
vfs: Return -ENXIO for negative SEEK_HOLE / SEEK_DATA offsets

Steve French <[email protected]>
SMB3: Don't ignore O_SYNC/O_DSYNC and O_DIRECT flags

Steve French <[email protected]>
SMB: Validate negotiate (to protect against downgrade) even if signing off

Steve French <[email protected]>
SMB3: Warn user if trying to sign connection that authenticated as guest

Steve French <[email protected]>
Fix SMB3.1.1 guest authentication to Samba

Rafael J. Wysocki <[email protected]>
PM: core: Fix device_pm_check_callbacks()

Gerald Schaefer <[email protected]>
s390/mm: fix write access check in gup_huge_pmd()

Naveen N. Rao <[email protected]>
powerpc/ftrace: Pass the correct stack pointer for DYNAMIC_FTRACE_WITH_REGS

Gustavo Romero <[email protected]>
powerpc/tm: Flush TM only if CPU has TM feature

Tyrel Datwyler <[email protected]>
powerpc/pseries: Fix parent_dn reference leak in add_dt_node()

Eric Biggers <[email protected]>
KEYS: prevent KEYCTL_READ on negative key

Eric Biggers <[email protected]>
KEYS: prevent creating a different user's keyrings

Eric Biggers <[email protected]>
KEYS: fix writing past end of user-supplied buffer in keyring_read()

Jason A. Donenfeld <[email protected]>
security/keys: rewrite all of big_key crypto

Jason A. Donenfeld <[email protected]>
security/keys: properly zero out sensitive key material in big_key

LEROY Christophe <[email protected]>
crypto: talitos - fix hashing

LEROY Christophe <[email protected]>
crypto: talitos - fix sha224

LEROY Christophe <[email protected]>
crypto: talitos - Don't provide setkey for non hmac hashing algs.

Stephan Mueller <[email protected]>
crypto: drbg - fix freeing of resources

Alex Deucher <[email protected]>
drm/radeon: disable hard reset in hibernate for APUs

Xin Long <[email protected]>
scsi: scsi_transport_iscsi: fix the issue that iscsi_if_rx doesn't parse nlmsg properly

Dennis Yang <[email protected]>
md/raid5: preserve STRIPE_ON_UNPLUG_LIST in break_stripe_batch_list

Shaohua Li <[email protected]>
md/raid5: fix a race condition in stripe batch

Bo Yan <[email protected]>
tracing: Erase irqsoff trace with empty write

Tahsin Erdogan <[email protected]>
tracing: Fix trace_pipe behavior for instance traces

Paul Mackerras <[email protected]>
KVM: PPC: Book3S HV: Protect updates to spapr_tce_tables list

Paul Mackerras <[email protected]>
KVM: PPC: Book3S: Fix race and leak in kvm_vm_ioctl_create_spapr_tce()

Thomas Gleixner <[email protected]>
genirq: Make sparse_irq_lock protect what it should protect

Avraham Stern <[email protected]>
mac80211: flush hw_roc_start work before cancelling the ROC

Beni Lev <[email protected]>
mac80211_hwsim: Use proper TX power

Johannes Berg <[email protected]>
mac80211: fix VLAN handling with TXQs

John Ogness <[email protected]>
fs/proc: Report eip/esp in /prod/PID/stat for coredumping

Shu Wang <[email protected]>
cifs: release auth_key.response for reconnect.

Shu Wang <[email protected]>
cifs: release cifs root_cred after exit_cifs

-------------

Diffstat:

 Makefile                                      |   4 +-
 arch/arm/xen/mm.c                             |   1 +
 arch/arm64/kernel/head.S                      |   1 +
 arch/arm64/mm/fault.c                         |   2 +-
 arch/powerpc/kernel/entry_64.S                |  20 ++-
 arch/powerpc/kernel/ptrace.c                  |   2 +-
 arch/powerpc/kvm/book3s_64_vio.c              |  57 +++---
 arch/powerpc/platforms/pseries/mobility.c     |   4 +-
 arch/s390/mm/gup.c                            |   7 +-
 arch/x86/kernel/fpu/regset.c                  |   9 +-
 arch/x86/kernel/fpu/signal.c                  |   4 +
 arch/x86/kernel/kvm.c                         |   3 +-
 arch/x86/kvm/vmx.c                            | 240 ++++++++++++++------------
 arch/x86/mm/fault.c                           |  47 ++---
 block/bsg-lib.c                               |   1 -
 crypto/drbg.c                                 |   8 +-
 drivers/base/power/main.c                     |   9 +-
 drivers/crypto/talitos.c                      |   9 +-
 drivers/gpu/drm/etnaviv/etnaviv_gem.c         |   3 +
 drivers/gpu/drm/radeon/radeon_device.c        |   2 +-
 drivers/infiniband/hw/cxgb4/cm.c              |   4 +-
 drivers/md/raid5.c                            |  13 +-
 drivers/misc/cxl/api.c                        |   4 +
 drivers/misc/cxl/file.c                       |   8 +-
 drivers/net/wireless/mac80211_hwsim.c         |   2 -
 drivers/pci/pci-sysfs.c                       |  11 +-
 drivers/scsi/scsi_transport_iscsi.c           |   2 +-
 drivers/video/fbdev/aty/atyfb_base.c          |   2 +-
 drivers/xen/swiotlb-xen.c                     |  19 ++
 fs/btrfs/ioctl.c                              |   6 +-
 fs/btrfs/relocation.c                         |   2 +-
 fs/cifs/cifsfs.c                              |   2 +-
 fs/cifs/connect.c                             |   8 +
 fs/cifs/file.c                                |   7 +
 fs/cifs/smb2pdu.c                             |  21 ++-
 fs/gfs2/glock.c                               |  16 +-
 fs/proc/array.c                               |   9 +
 fs/read_write.c                               |   4 +-
 fs/xfs/xfs_ioctl.c                            |   3 +-
 include/linux/key.h                           |   2 +
 include/net/mac80211.h                        |  15 +-
 include/xen/swiotlb-xen.h                     |   5 +
 kernel/irq/irqdesc.c                          |  24 +--
 kernel/seccomp.c                              |  23 ++-
 kernel/sysctl.c                               |   2 +
 kernel/time/timer.c                           |   2 +-
 kernel/trace/trace.c                          |  12 +-
 net/mac80211/iface.c                          |  17 +-
 net/mac80211/offchannel.c                     |   2 +
 net/mac80211/tx.c                             |  36 +++-
 net/wireless/nl80211.c                        |   3 +
 security/keys/Kconfig                         |   4 +-
 security/keys/big_key.c                       | 138 +++++++--------
 security/keys/internal.h                      |   2 +-
 security/keys/key.c                           |   2 +
 security/keys/keyctl.c                        |   5 +
 security/keys/keyring.c                       |  37 ++--
 security/keys/process_keys.c                  |   6 +-
 tools/testing/selftests/seccomp/seccomp_bpf.c |  18 +-
 59 files changed, 549 insertions(+), 382 deletions(-)

4.9-stable review patch. If anyone has any objections, please let me know.

------------------

From: Shu Wang <[email protected]>

commit 94183331e815617246b1baa97e0916f358c794bb upstream.

memory leak was found by kmemleak. exit_cifs_spnego should be called before cifs module removed, or cifs root_cred will not be released.

kmemleak report:
unreferenced object 0xffff880070a3ce40 (size 192):
backtrace:

     kmemleak_alloc+0x4a/0xa0
     kmem_cache_alloc+0xc7/0x1d0
     prepare_kernel_cred+0x20/0x120
     init_cifs_spnego+0x2d/0x170 [cifs]
     0xffffffffc07801f3
     do_one_initcall+0x51/0x1b0
     do_init_module+0x60/0x1fd
     load_module+0x161e/0x1b60
     SYSC_finit_module+0xa9/0x100
     SyS_finit_module+0xe/0x10

---
 fs/cifs/cifsfs.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

@@ -1360,7 +1360,7 @@ exit_cifs(void)
 	exit_cifs_idmap();
 #endif
 #ifdef CONFIG_CIFS_UPCALL
-	unregister_key_type(&cifs_spnego_key_type);
+	exit_cifs_spnego();
 #endif
 	cifs_destroy_request_bufs();
 	cifs_destroy_mids();

4.9-stable review patch. If anyone has any objections, please let me know.

------------------

From: Tahsin Erdogan <[email protected]>

commit 75df6e688ccd517e339a7c422ef7ad73045b18a2 upstream.

When reading data from trace_pipe, tracing_wait_pipe() performs a check to see if tracing has been turned off after some data was read. Currently, this check always looks at global trace state, but it should be checking the trace instance where trace_pipe is located at.

Because of this bug, cat instances/i1/trace_pipe in the following script will immediately exit instead of waiting for data:

cd /sys/kernel/debug/tracing
echo 0 > tracing_on
mkdir -p instances/i1
echo 1 > instances/i1/tracing_on
echo 1 > instances/i1/events/sched/sched_process_exec/enable cat instances/i1/trace_pipe

---
 kernel/trace/trace.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

@@ -5128,7 +5128,7 @@ static int tracing_wait_pipe(struct file
 		 *
 		 * iter->pos will be 0 if we haven't read anything.
 		 */
-		if (!tracing_is_on() && iter->pos)
+		if (!tracer_tracing_is_on(iter->tr) && iter->pos)
 			break;
 
 		mutex_unlock(&iter->mutex);

4.9-stable review patch. If anyone has any objections, please let me know.

------------------

From: Bo Yan <[email protected]>

commit 8dd33bcb7050dd6f8c1432732f930932c9d3a33e upstream.

One convenient way to erase trace is "echo > trace". However, this is currently broken if the current tracer is irqsoff tracer. This is because irqsoff tracer use max_buffer as the default trace buffer.

Set the max_buffer as the one to be cleared when it's the trace buffer currently in use.

---
 kernel/trace/trace.c |   10 ++++++++--
 1 file changed, 8 insertions(+), 2 deletions(-)

@@ -3569,11 +3569,17 @@ static int tracing_open(struct inode *in
 	/* If this file was open for write, then erase contents */
 	if ((file->f_mode & FMODE_WRITE) && (file->f_flags & O_TRUNC)) {
 		int cpu = tracing_get_cpu(inode);
+		struct trace_buffer *trace_buf = &tr->trace_buffer;
+
+#ifdef CONFIG_TRACER_MAX_TRACE
+		if (tr->current_trace->print_max)
+			trace_buf = &tr->max_buffer;
+#endif
 
 		if (cpu == RING_BUFFER_ALL_CPUS)
-			tracing_reset_online_cpus(&tr->trace_buffer);
+			tracing_reset_online_cpus(trace_buf);
 		else
-			tracing_reset(&tr->trace_buffer, cpu);
+			tracing_reset(trace_buf, cpu);
 	}
 
 	if (file->f_mode & FMODE_READ) {

4.9-stable review patch. If anyone has any objections, please let me know.

------------------

From: Shaohua Li <[email protected]>

commit 3664847d95e60a9a943858b7800f8484669740fc upstream.

We have a race condition in below scenario, say have 3 continuous stripes, sh1, sh2 and sh3, sh1 is the stripe_head of sh2 and sh3:

CPU1 CPU2 CPU3
handle_stripe(sh3)

				stripe_add_to_batch_list(sh3)
				-> lock(sh2, sh3)
				-> lock batch_lock(sh1)
				-> add sh3 to batch_list of sh1
				-> unlock batch_lock(sh1)
								clear_batch_ready(sh1)
								-> lock(sh1) and batch_lock(sh1)
								-> clear STRIPE_BATCH_READY for all stripes in batch_list
								-> unlock(sh1) and batch_lock(sh1)
->clear_batch_ready(sh3)
-->test_and_clear_bit(STRIPE_BATCH_READY, sh3)
--->return 0 as sh->batch == NULL
				-> sh3->batch_head = sh1
				-> unlock (sh2, sh3)

In CPU1, handle_stripe will continue handle sh3 even it's in batch stripe list of sh1. By moving sh3->batch_head assignment in to batch_lock, we make it impossible to clear STRIPE_BATCH_READY before batch_head is set.

Thanks Stephane for helping debug this tricky issue.

---
 drivers/md/raid5.c |   10 ++++++++--
 1 file changed, 8 insertions(+), 2 deletions(-)

@@ -829,6 +829,14 @@ static void stripe_add_to_batch_list(str
 			spin_unlock(&head->batch_head->batch_lock);
 			goto unlock_out;
 		}
+		/*
+		 * We must assign batch_head of this stripe within the
+		 * batch_lock, otherwise clear_batch_ready of batch head
+		 * stripe could clear BATCH_READY bit of this stripe and
+		 * this stripe->batch_head doesn't get assigned, which
+		 * could confuse clear_batch_ready for this stripe
+		 */
+		sh->batch_head = head->batch_head;
 
 		/*
 		 * at this point, head's BATCH_READY could be cleared, but we

@@ -836,8 +844,6 @@ static void stripe_add_to_batch_list(str
 		 */
 		list_add(&sh->batch_list, &head->batch_list);
 		spin_unlock(&head->batch_head->batch_lock);
-
-		sh->batch_head = head->batch_head;
 	} else {
 		head->batch_head = head;
 		sh->batch_head = head->batch_head;

4.9-stable review patch. If anyone has any objections, please let me know.

------------------

From: Dennis Yang <[email protected]>

commit 184a09eb9a2fe425e49c9538f1604b05ed33cfef upstream.

In release_stripe_plug(), if a stripe_head has its STRIPE_ON_UNPLUG_LIST set, it indicates that this stripe_head is already in the raid5_plug_cb list and release_stripe() would be called instead to drop a reference count. Otherwise, the STRIPE_ON_UNPLUG_LIST bit would be set for this stripe_head and it will get queued into the raid5_plug_cb list.

Since break_stripe_batch_list() did not preserve STRIPE_ON_UNPLUG_LIST, A stripe could be re-added to plug list while it is still on that list in the following situation. If stripe_head A is added to another stripe_head B's batch list, in this case A will have its batch_head != NULL and be added into the plug list. After that, stripe_head B gets handled and called break_stripe_batch_list() to reset all the batched stripe_head(including A which is still on the plug list)'s state and reset their batch_head to NULL. Before the plug list gets processed, if there is another write request comes in and get stripe_head A, A will have its batch_head == NULL (cleared by calling break_stripe_batch_list() on B) and be added to plug list once again.

---
 drivers/md/raid5.c |    3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

@@ -4283,7 +4283,8 @@ static void break_stripe_batch_list(stru
 
 		set_mask_bits(&sh->state, ~(STRIPE_EXPAND_SYNC_FLAGS |
 					    (1 << STRIPE_PREREAD_ACTIVE) |
-					    (1 << STRIPE_DEGRADED)),
+					    (1 << STRIPE_DEGRADED) |
+					    (1 << STRIPE_ON_UNPLUG_LIST)),
 			      head_sh->state & (1 << STRIPE_INSYNC));
 
 		sh->check_state = head_sh->check_state;

4.9-stable review patch. If anyone has any objections, please let me know.

------------------

From: Xin Long <[email protected]>

commit c88f0e6b06f4092995688211a631bb436125d77b upstream.

ChunYu found a kernel crash by syzkaller:

[  651.617875] kasan: CONFIG_KASAN_INLINE enabled
[  651.618217] kasan: GPF could be caused by NULL-ptr deref or user memory access
[  651.618731] general protection fault: 0000 [#1] SMP KASAN
[  651.621543] CPU: 1 PID: 9539 Comm: scsi Not tainted 4.11.0.cov #32
[  651.621938] Hardware name: Red Hat KVM, BIOS 0.5.1 01/01/2011
[  651.622309] task: ffff880117780000 task.stack: ffff8800a3188000
[  651.622762] RIP: 0010:skb_release_data+0x26c/0x590
[...]
[  651.627260] Call Trace:
[  651.629156]  skb_release_all+0x4f/0x60
[  651.629450]  consume_skb+0x1a5/0x600
[  651.630705]  netlink_unicast+0x505/0x720
[  651.632345]  netlink_sendmsg+0xab2/0xe70
[  651.633704]  sock_sendmsg+0xcf/0x110
[  651.633942]  ___sys_sendmsg+0x833/0x980
[  651.637117]  __sys_sendmsg+0xf3/0x240
[  651.638820]  SyS_sendmsg+0x32/0x50
[  651.639048]  entry_SYSCALL_64_fastpath+0x1f/0xc2

It's caused by skb_shared_info at the end of sk_buff was overwritten by ISCSI_KEVENT_IF_ERROR when parsing nlmsg info from skb in iscsi_if_rx.

During the loop if skb->len == nlh->nlmsg_len and both are sizeof(*nlh), ev = nlmsg_data(nlh) will acutally get skb_shinfo(SKB) instead and set a new value to skb_shinfo(SKB)->nr_frags by ev->type.

This patch is to fix it by checking nlh->nlmsg_len properly there to avoid over accessing sk_buff.

---
 drivers/scsi/scsi_transport_iscsi.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

@@ -3696,7 +3696,7 @@ iscsi_if_rx(struct sk_buff *skb)
 		uint32_t group;
 
 		nlh = nlmsg_hdr(skb);
-		if (nlh->nlmsg_len < sizeof(*nlh) ||
+		if (nlh->nlmsg_len < sizeof(*nlh) + sizeof(*ev) ||
 		    skb->len < nlh->nlmsg_len) {
 			break;
 		}

4.9-stable review patch. If anyone has any objections, please let me know.

------------------

From: Alex Deucher <[email protected]>

commit 820608548737e315c6f93e3099b4e65bde062334 upstream.

Fixes a hibernation regression on APUs.

---
 drivers/gpu/drm/radeon/radeon_device.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

@@ -1674,7 +1674,7 @@ int radeon_suspend_kms(struct drm_device
 	radeon_agp_suspend(rdev);
 
 	pci_save_state(dev->pdev);
-	if (freeze && rdev->family >= CHIP_CEDAR) {
+	if (freeze && rdev->family >= CHIP_CEDAR && !(rdev->flags & RADEON_IS_IGP)) {
 		rdev->asic->asic_reset(rdev, true);
 		pci_restore_state(dev->pdev);
 	} else if (suspend) {

4.9-stable review patch. If anyone has any objections, please let me know.

------------------

From: Stephan Mueller <[email protected]>

commit bd6227a150fdb56e7bb734976ef6e53a2c1cb334 upstream.

During the change to use aligned buffers, the deallocation code path was not updated correctly. The current code tries to free the aligned buffer pointer and not the original buffer pointer as it is supposed to.

Thus, the code is updated to free the original buffer pointer and set the aligned buffer pointer that is used throughout the code to NULL.

---
 crypto/drbg.c |    8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

@@ -1133,10 +1133,10 @@ static inline void drbg_dealloc_state(st
 {
 	if (!drbg)
 		return;
-	kzfree(drbg->V);
-	drbg->Vbuf = NULL;
-	kzfree(drbg->C);
-	drbg->Cbuf = NULL;
+	kzfree(drbg->Vbuf);
+	drbg->V = NULL;
+	kzfree(drbg->Cbuf);
+	drbg->C = NULL;
 	kzfree(drbg->scratchpadbuf);
 	drbg->scratchpadbuf = NULL;
 	drbg->reseed_ctr = 0;

4.9-stable review patch. If anyone has any objections, please let me know.

------------------

From: LEROY Christophe <[email protected]>

commit 56136631573baa537a15e0012055ffe8cfec1a33 upstream.

Today, md5sum fails with error -ENOKEY because a setkey function is set for non hmac hashing algs, see strace output below:

mmap(NULL, 378880, PROT_READ, MAP_SHARED, 6, 0) = 0x77f50000
accept(3, 0, NULL) = 7
vmsplice(5, [{"bin/\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0"..., 378880}], 1, SPLICE_F_MORE|SPLICE_F_GIFT) = 262144 splice(4, NULL, 7, NULL, 262144, SPLICE_F_MORE) = -1 ENOKEY (Required key not available)
write(2, "Generation of hash for file kcap"..., 50) = 50
munmap(0x77f50000, 378880) = 0

This patch ensures that setkey() function is set only for hmac hashing.

---
 drivers/crypto/talitos.c |    3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

@@ -3057,7 +3057,8 @@ static struct talitos_crypto_alg *talito
 		t_alg->algt.alg.hash.final = ahash_final;
 		t_alg->algt.alg.hash.finup = ahash_finup;
 		t_alg->algt.alg.hash.digest = ahash_digest;
-		t_alg->algt.alg.hash.setkey = ahash_setkey;
+		if (!strncmp(alg->cra_name, "hmac", 4))
+			t_alg->algt.alg.hash.setkey = ahash_setkey;
 		t_alg->algt.alg.hash.import = ahash_import;
 		t_alg->algt.alg.hash.export = ahash_export;
 

4.9-stable review patch. If anyone has any objections, please let me know.

------------------

From: LEROY Christophe <[email protected]>

commit afd62fa26343be6445479e75de9f07092a061459 upstream.

Kernel crypto tests report the following error at startup

[    2.752626] alg: hash: Test 4 failed for sha224-talitos
[    2.757907] 00000000: 30 e2 86 e2 e7 8a dd 0d d7 eb 9f d5 83 fe f1 b0

00000010: 2d 5a 6c a5 f9 55 ea fd 0e 72 05 22

This patch fixes it

---
 drivers/crypto/talitos.c |    4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

@@ -1756,9 +1756,9 @@ static int common_nonsnoop_hash(struct t
 		req_ctx->swinit = 0;
 	} else {
 		desc->ptr[1] = zero_entry;
-		/* Indicate next op is not the first. */
-		req_ctx->first = 0;
 	}
+	/* Indicate next op is not the first. */
+	req_ctx->first = 0;
 
 	/* HMAC key */
 	if (ctx->keylen)

4.9-stable review patch. If anyone has any objections, please let me know.

------------------

From: Shu Wang <[email protected]>

commit f5c4ba816315d3b813af16f5571f86c8d4e897bd upstream.

There is a race that cause cifs reconnect in cifs_mount,
- cifs_mount
- cifs_get_tcp_session
- [ start thread cifs_demultiplex_thread
- cifs_read_from_socket: -ECONNABORTED
- DELAY_WORK smb2_reconnect_server ]
- cifs_setup_session
- [ smb2_reconnect_server ]

auth_key.response was allocated in cifs_setup_session, and will release when the session destoried. So when session re- connect, auth_key.response should be check and released.

Tested with my system:
CIFS VFS: Free previous auth_key.response = ffff8800320bbf80

A simple auth_key.response allocation call trace:
- cifs_setup_session
- SMB2_sess_setup
- SMB2_sess_auth_rawntlmssp_authenticate
- build_ntlmssp_auth_blob
- setup_ntlmv2_rsp

---
 fs/cifs/connect.c |    8 ++++++++
 1 file changed, 8 insertions(+)

@@ -4071,6 +4071,14 @@ cifs_setup_session(const unsigned int xi
 	cifs_dbg(FYI, "Security Mode: 0x%x Capabilities: 0x%x TimeAdjust: %d\n",
 		 server->sec_mode, server->capabilities, server->timeAdj);
 
+	if (ses->auth_key.response) {
+		cifs_dbg(VFS, "Free previous auth_key.response = %p\n",
+			 ses->auth_key.response);
+		kfree(ses->auth_key.response);
+		ses->auth_key.response = NULL;
+		ses->auth_key.len = 0;
+	}
+
 	if (server->ops->sess_setup)
 		rc = server->ops->sess_setup(xid, ses, nls_info);
 

4.9-stable review patch. If anyone has any objections, please let me know.

------------------

From: "Jason A. Donenfeld" <[email protected]>

commit 428490e38b2e352812e0b765d8bceafab0ec441d upstream.

This started out as just replacing the use of crypto/rng with get_random_bytes_wait, so that we wouldn't use bad randomness at boot time. But, upon looking further, it appears that there were even deeper underlying cryptographic problems, and that this seems to have been committed with very little crypto review. So, I rewrote the whole thing, trying to keep to the conventions introduced by the previous author, to fix these cryptographic flaws.

It makes no sense to seed crypto/rng at boot time and then keep using it like this, when in fact there's already get_random_bytes_wait, which can ensure there's enough entropy and be a much more standard way of generating keys. Since this sensitive material is being stored untrusted, using ECB and no authentication is simply not okay at all. I find it surprising and a bit horrifying that this code even made it past basic crypto review, which perhaps points to some larger issues. This patch moves from using AES-ECB to using AES-GCM. Since keys are uniquely generated each time, we can set the nonce to zero. There was also a race condition in which the same key would be reused at the same time in different threads. A mutex fixes this issue now.

So, to summarize, this commit fixes the following vulnerabilities:

* Low entropy key generation, allowing an attacker to potentially guess or predict keys.
* Unauthenticated encryption, allowing an attacker to modify the cipher text in particular ways in order to manipulate the plaintext, which is is even more frightening considering the next point.
* Use of ECB mode, allowing an attacker to trivially swap blocks or compare identical plaintext blocks.
* Key re-use.
* Faulty memory zeroing.

[Note that in backporting this commit to 4.9, get_random_bytes_wait was replaced with get_random_bytes, since 4.9 does not have the former function. This might result in slightly worse entropy in key generation, but common use cases of big_keys makes that likely not a huge deal. And, this is the best we can do with this old kernel. Alas.]

---
The current patch in queue-4.9 is broken. This is a better backport.

 security/keys/Kconfig   |    4 -
 security/keys/big_key.c |  124 ++++++++++++++++++++++--------------------------
 2 files changed, 58 insertions(+), 70 deletions(-)

@@ -41,10 +41,8 @@ config BIG_KEYS
 	bool "Large payload keys"
 	depends on KEYS
 	depends on TMPFS
-	depends on (CRYPTO_ANSI_CPRNG = y || CRYPTO_DRBG = y)
 	select CRYPTO_AES
-	select CRYPTO_ECB
-	select CRYPTO_RNG
+	select CRYPTO_GCM
 	help
 	  This option provides support for holding large keys within the kernel
 	  (for example Kerberos ticket caches).  The data may be stored out to

4.9-stable review patch. If anyone has any objections, please let me know.

------------------

From: Eric Biggers <[email protected]>

commit e645016abc803dafc75e4b8f6e4118f088900ffb upstream.

Userspace can call keyctl_read() on a keyring to get the list of IDs of keys in the keyring. But if the user-supplied buffer is too small, the kernel would write the full list anyway --- which will corrupt whatever userspace memory happened to be past the end of the buffer. Fix it by only filling the space that is available.

---
 security/keys/keyring.c |   14 +++++---------
 1 file changed, 5 insertions(+), 9 deletions(-)

@@ -416,7 +416,7 @@ static void keyring_describe(const struc
 }
 
 struct keyring_read_iterator_context {
-	size_t			qty;
+	size_t			buflen;
 	size_t			count;
 	key_serial_t __user	*buffer;
 };

@@ -428,9 +428,9 @@ static int keyring_read_iterator(const v
 	int ret;
 
 	kenter("{%s,%d},,{%zu/%zu}",
-	       key->type->name, key->serial, ctx->count, ctx->qty);
+	       key->type->name, key->serial, ctx->count, ctx->buflen);
 
-	if (ctx->count >= ctx->qty)
+	if (ctx->count >= ctx->buflen)
 		return 1;
 
 	ret = put_user(key->serial, ctx->buffer);

@@ -465,16 +465,12 @@ static long keyring_read(const struct ke
 		return 0;
 
 	/* 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;
+		return nr_keys * sizeof(key_serial_t);
 
 	/* Copy the IDs of the subscribed keys into the buffer */
 	ctx.buffer = (key_serial_t __user *)buffer;
+	ctx.buflen = buflen;
 	ctx.count = 0;
 	ret = assoc_array_iterate(&keyring->keys, keyring_read_iterator, &ctx);
 	if (ret < 0) {

4.9-stable review patch. If anyone has any objections, please let me know.

------------------

From: Eric Biggers <[email protected]>

commit 237bbd29f7a049d310d907f4b2716a7feef9abf3 upstream.

It was possible for an unprivileged user to create the user and user session keyrings for another user. For example:

    sudo -u '#3000' sh -c 'keyctl add keyring _uid.4000 "" @u
                           keyctl add keyring _uid_ses.4000 "" @u
                           sleep 15' &
    sleep 1
    sudo -u '#4000' keyctl describe @u
    sudo -u '#4000' keyctl describe @us

This is problematic because these "fake" keyrings won't have the right permissions. In particular, the user who created them first will own them and will have full access to them via the possessor permissions, which can be used to compromise the security of a user's keys:

    -4: alswrv-----v------------  3000     0 keyring: _uid.4000
    -5: alswrv-----v------------  3000     0 keyring: _uid_ses.4000

Fix it by marking user and user session keyrings with a flag KEY_FLAG_UID_KEYRING. Then, when searching for a user or user session keyring by name, skip all keyrings that don't have the flag set.

---
 include/linux/key.h          |    2 ++
 security/keys/internal.h     |    2 +-
 security/keys/key.c          |    2 ++
 security/keys/keyring.c      |   23 ++++++++++++++---------
 security/keys/process_keys.c |    6 ++++--
 5 files changed, 23 insertions(+), 12 deletions(-)

@@ -176,6 +176,7 @@ struct key {
 #define KEY_FLAG_BUILTIN	8	/* set if key is built in to the kernel */
 #define KEY_FLAG_ROOT_CAN_INVAL	9	/* set if key can be invalidated by root without permission */
 #define KEY_FLAG_KEEP		10	/* set if key should not be removed */
+#define KEY_FLAG_UID_KEYRING	11	/* set if key is a user or user session keyring */
 
 	/* the key type and key description string
 	 * - the desc is used to match a key against search criteria

@@ -235,6 +236,7 @@ extern struct key *key_alloc(struct key_
 #define KEY_ALLOC_NOT_IN_QUOTA		0x0002	/* not in quota */
 #define KEY_ALLOC_BUILT_IN		0x0004	/* Key is built into kernel */
 #define KEY_ALLOC_BYPASS_RESTRICTION	0x0008	/* Override the check on restricted keyrings */
+#define KEY_ALLOC_UID_KEYRING		0x0010	/* allocating a user or user session keyring */
 
 extern void key_revoke(struct key *key);
 extern void key_invalidate(struct key *key);

@@ -137,7 +137,7 @@ extern key_ref_t keyring_search_aux(key_
 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);
+extern struct key *find_keyring_by_name(const char *name, bool uid_keyring);
 
 extern int install_user_keyrings(void);
 extern int install_thread_keyring_to_cred(struct cred *);

@@ -301,6 +301,8 @@ struct key *key_alloc(struct key_type *t
 		key->flags |= 1 << KEY_FLAG_IN_QUOTA;
 	if (flags & KEY_ALLOC_BUILT_IN)
 		key->flags |= 1 << KEY_FLAG_BUILTIN;
+	if (flags & KEY_ALLOC_UID_KEYRING)
+		key->flags |= 1 << KEY_FLAG_UID_KEYRING;
 
 #ifdef KEY_DEBUGGING
 	key->magic = KEY_DEBUG_MAGIC;

@@ -985,15 +985,15 @@ found:
 /*
  * Find a keyring with the specified name.
  *
- * All named keyrings in the current user namespace are searched, provided they
- * grant Search permission directly to the caller (unless this check is
- * skipped).  Keyrings whose usage points have reached zero or who have been
- * revoked are skipped.
+ * Only keyrings that have nonzero refcount, are not revoked, and are owned by a
+ * user in the current user namespace are considered.  If @uid_keyring is %true,
+ * the keyring additionally must have been allocated as a user or user session
+ * keyring; otherwise, it must grant Search permission directly to the caller.
  *
  * Returns a pointer to the keyring with the keyring's refcount having being
  * incremented on success.  -ENOKEY is returned if a key could not be found.
  */
-struct key *find_keyring_by_name(const char *name, bool skip_perm_check)
+struct key *find_keyring_by_name(const char *name, bool uid_keyring)
 {
 	struct key *keyring;
 	int bucket;

@@ -1021,10 +1021,15 @@ struct key *find_keyring_by_name(const c
 			if (strcmp(keyring->description, name) != 0)
 				continue;
 
-			if (!skip_perm_check &&
-			    key_permission(make_key_ref(keyring, 0),
-					   KEY_NEED_SEARCH) < 0)
-				continue;
+			if (uid_keyring) {
+				if (!test_bit(KEY_FLAG_UID_KEYRING,
+					      &keyring->flags))
+					continue;
+			} else {
+				if (key_permission(make_key_ref(keyring, 0),
+						   KEY_NEED_SEARCH) < 0)
+					continue;
+			}
 
 			/* we've got a match but we might end up racing with
 			 * key_cleanup() if the keyring is currently 'dead'

@@ -76,7 +76,8 @@ int install_user_keyrings(void)
 		if (IS_ERR(uid_keyring)) {
 			uid_keyring = keyring_alloc(buf, user->uid, INVALID_GID,
 						    cred, user_keyring_perm,
-						    KEY_ALLOC_IN_QUOTA,
+						    KEY_ALLOC_UID_KEYRING |
+							KEY_ALLOC_IN_QUOTA,
 						    NULL, NULL);
 			if (IS_ERR(uid_keyring)) {
 				ret = PTR_ERR(uid_keyring);

@@ -93,7 +94,8 @@ int install_user_keyrings(void)
 			session_keyring =
 				keyring_alloc(buf, user->uid, INVALID_GID,
 					      cred, user_keyring_perm,
-					      KEY_ALLOC_IN_QUOTA,
+					      KEY_ALLOC_UID_KEYRING |
+						  KEY_ALLOC_IN_QUOTA,
 					      NULL, NULL);
 			if (IS_ERR(session_keyring)) {
 				ret = PTR_ERR(session_keyring);

4.9-stable review patch. If anyone has any objections, please let me know.

------------------

From: Eric Biggers <[email protected]>

commit 37863c43b2c6464f252862bf2e9768264e961678 upstream.

Because keyctl_read_key() looks up the key with no permissions requested, it may find a negatively instantiated key. If the key is also possessed, we went ahead and called ->read() on the key. But the key payload will actually contain the ->reject_error rather than the normal payload. Thus, the kernel oopses trying to read the user_key_payload from memory address (int)-ENOKEY = 0x00000000ffffff82.

Fortunately the payload data is stored inline, so it shouldn't be possible to abuse this as an arbitrary memory read primitive...

Reproducer:
keyctl new_session
keyctl request2 user desc '' @s
keyctl read $(keyctl show | awk '/user: desc/ {print $1}')

It causes a crash like the following:

     BUG: unable to handle kernel paging request at 00000000ffffff92
     IP: user_read+0x33/0xa0
     PGD 36a54067 P4D 36a54067 PUD 0
     Oops: 0000 [#1] SMP
     CPU: 0 PID: 211 Comm: keyctl Not tainted 4.14.0-rc1 #337
     Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.10.2-20170228_101828-anatol 04/01/2014
     task: ffff90aa3b74c3c0 task.stack: ffff9878c0478000
     RIP: 0010:user_read+0x33/0xa0
     RSP: 0018:ffff9878c047bee8 EFLAGS: 00010246
     RAX: 0000000000000001 RBX: ffff90aa3d7da340 RCX: 0000000000000017
     RDX: 0000000000000000 RSI: 00000000ffffff82 RDI: ffff90aa3d7da340
     RBP: ffff9878c047bf00 R08: 00000024f95da94f R09: 0000000000000000
     R10: 0000000000000001 R11: 0000000000000000 R12: 0000000000000000
     R13: 0000000000000000 R14: 0000000000000000 R15: 0000000000000000
     FS:  00007f58ece69740(0000) GS:ffff90aa3e200000(0000) knlGS:0000000000000000
     CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
     CR2: 00000000ffffff92 CR3: 0000000036adc001 CR4: 00000000003606f0
     Call Trace:
      keyctl_read_key+0xac/0xe0
      SyS_keyctl+0x99/0x120
      entry_SYSCALL_64_fastpath+0x1f/0xbe
     RIP: 0033:0x7f58ec787bb9
     RSP: 002b:00007ffc8d401678 EFLAGS: 00000206 ORIG_RAX: 00000000000000fa
     RAX: ffffffffffffffda RBX: 00007ffc8d402800 RCX: 00007f58ec787bb9
     RDX: 0000000000000000 RSI: 00000000174a63ac RDI: 000000000000000b
     RBP: 0000000000000004 R08: 00007ffc8d402809 R09: 0000000000000020
     R10: 0000000000000000 R11: 0000000000000206 R12: 00007ffc8d402800
     R13: 00007ffc8d4016e0 R14: 0000000000000000 R15: 0000000000000000
     Code: e5 41 55 49 89 f5 41 54 49 89 d4 53 48 89 fb e8 a4 b4 ad ff 85 c0 74 09 80 3d b9 4c 96 00 00 74 43 48 8b b3 20 01 00 00 4d 85 ed <0f> b7 5e 10 74 29 4d 85 e4 74 24 4c 39 e3 4c 89 e2 4c 89 ef 48
     RIP: user_read+0x33/0xa0 RSP: ffff9878c047bee8
     CR2: 00000000ffffff92

---
 security/keys/keyctl.c |    5 +++++
 1 file changed, 5 insertions(+)

@@ -766,6 +766,11 @@ long keyctl_read_key(key_serial_t keyid,
 
 	key = key_ref_to_ptr(key_ref);
 
+	if (test_bit(KEY_FLAG_NEGATIVE, &key->flags)) {
+		ret = -ENOKEY;
+		goto error2;
+	}
+
 	/* see if we can read it directly */
 	ret = key_permission(key_ref, KEY_NEED_READ);
 	if (ret == 0)

4.9-stable review patch. If anyone has any objections, please let me know.

------------------

From: Tyrel Datwyler <[email protected]>

commit b537ca6fede69a281dc524983e5e633d79a10a08 upstream.

A reference to the parent device node is held by add_dt_node() for the node to be added. If the call to dlpar_configure_connector() fails add_dt_node() returns ENOENT and that reference is not freed.

Add a call to of_node_put(parent_dn) prior to bailing out after a failed dlpar_configure_connector() call.

---
 arch/powerpc/platforms/pseries/mobility.c |    4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

@@ -225,8 +225,10 @@ static int add_dt_node(__be32 parent_pha
 		return -ENOENT;
 
 	dn = dlpar_configure_connector(drc_index, parent_dn);
-	if (!dn)
+	if (!dn) {
+		of_node_put(parent_dn);
 		return -ENOENT;
+	}
 
 	rc = dlpar_attach_node(dn);
 	if (rc)

4.9-stable review patch. If anyone has any objections, please let me know.

------------------

From: "Naveen N. Rao" <[email protected]>

commit a4979a7e71eb8da976cbe4a0a1fa50636e76b04f upstream.

For DYNAMIC_FTRACE_WITH_REGS, we should be passing-in the original set of registers in pt_regs, to capture the state _before_ ftrace_caller. However, we are instead passing the stack pointer *after* allocating a stack frame in ftrace_caller. Fix this by saving the proper value of r1 in pt_regs. Also, use SAVE_10GPRS() to simplify the code.

---
 arch/powerpc/kernel/entry_64.S |   20 ++++++++++++--------
 1 file changed, 12 insertions(+), 8 deletions(-)

@@ -1235,10 +1235,14 @@ _GLOBAL(ftrace_caller)
 	stdu	r1,-SWITCH_FRAME_SIZE(r1)
 
 	/* Save all gprs to pt_regs */
-	SAVE_8GPRS(0,r1)
-	SAVE_8GPRS(8,r1)
-	SAVE_8GPRS(16,r1)
-	SAVE_8GPRS(24,r1)
+	SAVE_GPR(0, r1)
+	SAVE_10GPRS(2, r1)
+	SAVE_10GPRS(12, r1)
+	SAVE_10GPRS(22, r1)
+
+	/* Save previous stack pointer (r1) */
+	addi	r8, r1, SWITCH_FRAME_SIZE
+	std	r8, GPR1(r1)
 
 	/* Load special regs for save below */
 	mfmsr   r8

@@ -1292,10 +1296,10 @@ ftrace_call:
 #endif
 
 	/* Restore gprs */
-	REST_8GPRS(0,r1)
-	REST_8GPRS(8,r1)
-	REST_8GPRS(16,r1)
-	REST_8GPRS(24,r1)
+	REST_GPR(0,r1)
+	REST_10GPRS(2,r1)
+	REST_10GPRS(12,r1)
+	REST_10GPRS(22,r1)
 
 	/* Restore callee's TOC */
 	ld	r2, 24(r1)

4.9-stable review patch. If anyone has any objections, please let me know.

------------------

From: Gerald Schaefer <[email protected]>

commit ba385c0594e723d41790ecfb12c610e6f90c7785 upstream.

The check for the _SEGMENT_ENTRY_PROTECT bit in gup_huge_pmd() is the wrong way around. It must not be set for write==1, and not be checked for write==0. Fix this similar to how it was fixed for ptes long time ago in commit 25591b070336 ("[S390] fix get_user_pages_fast").

One impact of this bug would be unnecessarily using the gup slow path for write==0 on r/w mappings. A potentially more severe impact would be that gup_huge_pmd() will succeed for write==1 on r/o mappings.

---
 arch/s390/mm/gup.c |    7 +++----
 1 file changed, 3 insertions(+), 4 deletions(-)

@@ -56,13 +56,12 @@ static inline int gup_pte_range(pmd_t *p
 static inline int gup_huge_pmd(pmd_t *pmdp, pmd_t pmd, unsigned long addr,
 		unsigned long end, int write, struct page **pages, int *nr)
 {
-	unsigned long mask, result;
 	struct page *head, *page;
+	unsigned long mask;
 	int refs;
 
-	result = write ? 0 : _SEGMENT_ENTRY_PROTECT;
-	mask = result | _SEGMENT_ENTRY_INVALID;
-	if ((pmd_val(pmd) & mask) != result)
+	mask = (write ? _SEGMENT_ENTRY_PROTECT : 0) | _SEGMENT_ENTRY_INVALID;
+	if ((pmd_val(pmd) & mask) != 0)
 		return 0;
 	VM_BUG_ON(!pfn_valid(pmd_val(pmd) >> PAGE_SHIFT));
 

4.9-stable review patch. If anyone has any objections, please let me know.

------------------

From: Rafael J. Wysocki <[email protected]>

commit 157c460e10cb6eca29ccbd0f023db159d0c55ec7 upstream.

The device_pm_check_callbacks() function doesn't check legacy ->suspend and ->resume callback pointers under the device's bus type, class and driver, so in some cases it may set the no_pm_callbacks flag for the device incorrectly and then the callbacks may be skipped during system suspend/resume, which shouldn't happen.

---
 drivers/base/power/main.c |    9 ++++++---
 1 file changed, 6 insertions(+), 3 deletions(-)

@@ -1757,10 +1757,13 @@ void device_pm_check_callbacks(struct de
 {
 	spin_lock_irq(&dev->power.lock);
 	dev->power.no_pm_callbacks =
-		(!dev->bus || pm_ops_is_empty(dev->bus->pm)) &&
-		(!dev->class || pm_ops_is_empty(dev->class->pm)) &&
+		(!dev->bus || (pm_ops_is_empty(dev->bus->pm) &&
+		 !dev->bus->suspend && !dev->bus->resume)) &&
+		(!dev->class || (pm_ops_is_empty(dev->class->pm) &&
+		 !dev->class->suspend && !dev->class->resume)) &&
 		(!dev->type || pm_ops_is_empty(dev->type->pm)) &&
 		(!dev->pm_domain || pm_ops_is_empty(&dev->pm_domain->ops)) &&
-		(!dev->driver || pm_ops_is_empty(dev->driver->pm));
+		(!dev->driver || (pm_ops_is_empty(dev->driver->pm) &&
+		 !dev->driver->suspend && !dev->driver->resume));
 	spin_unlock_irq(&dev->power.lock);
 }

4.9-stable review patch. If anyone has any objections, please let me know.

------------------

From: Steve French <[email protected]>

commit 23586b66d84ba3184b8820277f3fc42761640f87 upstream.

Samba rejects SMB3.1.1 dialect (vers=3.1.1) negotiate requests from the kernel client due to the two byte pad at the end of the negotiate contexts.

---
 fs/cifs/smb2pdu.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

@@ -366,7 +366,7 @@ assemble_neg_contexts(struct smb2_negoti
 	build_encrypt_ctxt((struct smb2_encryption_neg_context *)pneg_ctxt);
 	req->NegotiateContextOffset = cpu_to_le32(OFFSET_OF_NEG_CONTEXT);
 	req->NegotiateContextCount = cpu_to_le16(2);
-	inc_rfc1001_len(req, 4 + sizeof(struct smb2_preauth_neg_context) + 2
+	inc_rfc1001_len(req, 4 + sizeof(struct smb2_preauth_neg_context)
 			+ sizeof(struct smb2_encryption_neg_context)); /* calculate hash */
 }
 #else

4.9-stable review patch. If anyone has any objections, please let me know.

------------------

From: Steve French <[email protected]>

commit c721c38957fb19982416f6be71aae7b30630d83b upstream.

It can be confusing if user ends up authenticated as guest but they requested signing (server will return error validating signed packets) so add log message for this.

---
 fs/cifs/smb2pdu.c |    2 ++
 1 file changed, 2 insertions(+)

@@ -1010,6 +1010,8 @@ SMB2_sess_setup(const unsigned int xid,
 	while (sess_data->func)
 		sess_data->func(sess_data);
 
+	if ((ses->session_flags & SMB2_SESSION_FLAG_IS_GUEST) && (ses->sign))
+		cifs_dbg(VFS, "signing requested but authenticated as guest\n");
 	rc = sess_data->result;
 out:
 	kfree(sess_data);

4.9-stable review patch. If anyone has any objections, please let me know.

------------------

From: Steve French <[email protected]>

commit 1013e760d10e614dc10b5624ce9fc41563ba2e65 upstream.

---
 fs/cifs/file.c |    7 +++++++
 1 file changed, 7 insertions(+)

@@ -224,6 +224,13 @@ cifs_nt_open(char *full_path, struct ino
 	if (backup_cred(cifs_sb))
 		create_options |= CREATE_OPEN_BACKUP_INTENT;
 
+	/* O_SYNC also has bit for O_DSYNC so following check picks up either */
+	if (f_flags & O_SYNC)
+		create_options |= CREATE_WRITE_THROUGH;
+
+	if (f_flags & O_DIRECT)
+		create_options |= CREATE_NO_BUFFER;
+
 	oparms.tcon = tcon;
 	oparms.cifs_sb = cifs_sb;
 	oparms.desired_access = desired_access;

4.9-stable review patch. If anyone has any objections, please let me know.

------------------

From: Andreas Gruenbacher <[email protected]>

commit fc46820b27a2d9a46f7e90c9ceb4a64a1bc5fab8 upstream.

In generic_file_llseek_size, return -ENXIO for negative offsets as well as offsets beyond EOF. This affects filesystems which don't implement SEEK_HOLE / SEEK_DATA internally, possibly because they don't support holes.

Fixes xfstest generic/448.

---
 fs/read_write.c |    4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

@@ -114,7 +114,7 @@ generic_file_llseek_size(struct file *fi
 		 * In the generic case the entire file is data, so as long as
 		 * offset isn't at the end of the file then the offset is data.
 		 */
-		if (offset >= eof)
+		if ((unsigned long long)offset >= eof)
 			return -ENXIO;
 		break;
 	case SEEK_HOLE:

@@ -122,7 +122,7 @@ generic_file_llseek_size(struct file *fi
 		 * There is a virtual hole at the end of the file, so as long as
 		 * offset isn't i_size or larger, return i_size.
 		 */
-		if (offset >= eof)
+		if ((unsigned long long)offset >= eof)
 			return -ENXIO;
 		offset = eof;
 		break;

4.9-stable review patch. If anyone has any objections, please let me know.

------------------

From: Vladis Dronov <[email protected]>

commit e785fa0a164aa11001cba931367c7f94ffaff888 upstream.

nl80211_set_rekey_data() does not check if the required attributes NL80211_REKEY_DATA_{REPLAY_CTR,KEK,KCK} are present when processing NL80211_CMD_SET_REKEY_OFFLOAD request. This request can be issued by users with CAP_NET_ADMIN privilege and may result in NULL dereference and a system crash. Add a check for the required attributes presence. This patch is based on the patch by bo Zhang.

This fixes CVE-2017-12153.

References: https://bugzilla.redhat.com/show_bug.cgi?id=1491046

---
 net/wireless/nl80211.c |    3 +++
 1 file changed, 3 insertions(+)

@@ -10385,6 +10385,9 @@ static int nl80211_set_rekey_data(struct
 	if (err)
 		return err;
 
+	if (!tb[NL80211_REKEY_DATA_REPLAY_CTR] || !tb[NL80211_REKEY_DATA_KEK] ||
+	    !tb[NL80211_REKEY_DATA_KCK])
+		return -EINVAL;
 	if (nla_len(tb[NL80211_REKEY_DATA_REPLAY_CTR]) != NL80211_REPLAY_CTR_LEN)
 		return -ERANGE;
 	if (nla_len(tb[NL80211_REKEY_DATA_KEK]) != NL80211_KEK_LEN)

4.9-stable review patch. If anyone has any objections, please let me know.

------------------

From: Beni Lev <[email protected]>

commit 9de981f507474f326e42117858dc9a9321331ae5 upstream.

In struct ieee80211_tx_info, control.vif pointer and rate_driver_data[0] falls on the same place, depending on the union usage.
During the whole TX process, the union is referred to as a control struct, which holds the vif that is later used in the tx flow, especially in order to derive the used tx power.
Referring direcly to rate_driver_data[0] and assigning a value to it, overwrites the vif pointer, hence making all later references irrelevant. Moreover, rate_driver_data[0] isn't used later in the flow in order to retrieve the channel that it is pointing to.

---
 drivers/net/wireless/mac80211_hwsim.c |    2 --
 1 file changed, 2 deletions(-)

@@ -1357,8 +1357,6 @@ static void mac80211_hwsim_tx(struct iee
 				       txi->control.rates,
 				       ARRAY_SIZE(txi->control.rates));
 
-	txi->rate_driver_data[0] = channel;
-
 	if (skb->len >= 24 + 8 &&
 	    ieee80211_is_probe_resp(hdr->frame_control)) {
 		/* fake header transmission time */

4.9-stable review patch. If anyone has any objections, please let me know.

------------------

From: Avraham Stern <[email protected]>

commit 6e46d8ce894374fc135c96a8d1057c6af1fef237 upstream.

When HW ROC is supported it is possible that after the HW notified that the ROC has started, the ROC was cancelled and another ROC was added while the hw_roc_start worker is waiting on the mutex (since cancelling the ROC and adding another one also holds the same mutex). As a result, the hw_roc_start worker will continue to run after the new ROC is added but before it is actually started by the HW. This may result in notifying userspace that the ROC has started before it actually does, or in case of management tx ROC, in an attempt to tx while not on the right channel.

In addition, when the driver will notify mac80211 that the second ROC has started, mac80211 will warn that this ROC has already been notified.

Fix this by flushing the hw_roc_start work before cancelling an ROC.

---
 net/mac80211/offchannel.c |    2 ++
 1 file changed, 2 insertions(+)

@@ -707,6 +707,8 @@ static int ieee80211_cancel_roc(struct i
 	if (!cookie)
 		return -ENOENT;
 
+	flush_work(&local->hw_roc_start);
+
 	mutex_lock(&local->mtx);
 	list_for_each_entry_safe(roc, tmp, &local->roc_list, list) {
 		if (!mgmt_tx && roc->cookie != cookie)

4.9-stable review patch. If anyone has any objections, please let me know.

------------------

From: Thomas Gleixner <[email protected]>

commit 12ac1d0f6c3e95732d144ffa65c8b20fbd9aa462 upstream.

for_each_active_irq() iterates the sparse irq allocation bitmap. The caller must hold sparse_irq_lock. Several code pathes expect that an active bit in the sparse bitmap also has a valid interrupt descriptor.

Unfortunately that's not true. The (de)allocation is a two step process, which holds the sparse_irq_lock only across the queue/remove from the radix tree and the set/clear in the allocation bitmap.

If a iteration locks sparse_irq_lock between the two steps, then it might see an active bit but the corresponding irq descriptor is NULL. If that is dereferenced unconditionally, then the kernel oopses. Of course, all iterator sites could be audited and fixed, but....

There is no reason why the sparse_irq_lock needs to be dropped between the two steps, in fact the code becomes simpler when the mutex is held across both and the semantics become more straight forward, so future problems of missing NULL pointer checks in the iteration are avoided and all existing sites are fixed in one go.

Expand the lock held sections so both operations are covered and the bitmap and the radixtree are in sync.

---
 kernel/irq/irqdesc.c |   24 +++++++-----------------
 1 file changed, 7 insertions(+), 17 deletions(-)

@@ -405,10 +405,8 @@ static void free_desc(unsigned int irq)
 	 * The sysfs entry must be serialized against a concurrent
 	 * irq_sysfs_init() as well.
 	 */
-	mutex_lock(&sparse_irq_lock);
 	kobject_del(&desc->kobj);
 	delete_irq_desc(irq);
-	mutex_unlock(&sparse_irq_lock);
 
 	/*
 	 * We free the descriptor, masks and stat fields via RCU. That

@@ -446,20 +444,15 @@ static int alloc_descs(unsigned int star
 		desc = alloc_desc(start + i, node, flags, mask, owner);
 		if (!desc)
 			goto err;
-		mutex_lock(&sparse_irq_lock);
 		irq_insert_desc(start + i, desc);
 		irq_sysfs_add(start + i, desc);
-		mutex_unlock(&sparse_irq_lock);
 	}
+	bitmap_set(allocated_irqs, start, cnt);
 	return start;
 
 err:
 	for (i--; i >= 0; i--)
 		free_desc(start + i);
-
-	mutex_lock(&sparse_irq_lock);
-	bitmap_clear(allocated_irqs, start, cnt);
-	mutex_unlock(&sparse_irq_lock);
 	return -ENOMEM;
 }
 

@@ -558,6 +551,7 @@ static inline int alloc_descs(unsigned i
 
 		desc->owner = owner;
 	}
+	bitmap_set(allocated_irqs, start, cnt);
 	return start;
 }
 

@@ -653,10 +647,10 @@ void irq_free_descs(unsigned int from, u
 	if (from >= nr_irqs || (from + cnt) > nr_irqs)
 		return;
 
+	mutex_lock(&sparse_irq_lock);
 	for (i = 0; i < cnt; i++)
 		free_desc(from + i);
 
-	mutex_lock(&sparse_irq_lock);
 	bitmap_clear(allocated_irqs, from, cnt);
 	mutex_unlock(&sparse_irq_lock);
 }

@@ -703,19 +697,15 @@ __irq_alloc_descs(int irq, unsigned int
 					   from, cnt, 0);
 	ret = -EEXIST;
 	if (irq >=0 && start != irq)
-		goto err;
+		goto unlock;
 
 	if (start + cnt > nr_irqs) {
 		ret = irq_expand_nr_irqs(start + cnt);
 		if (ret)
-			goto err;
+			goto unlock;
 	}
-
-	bitmap_set(allocated_irqs, start, cnt);
-	mutex_unlock(&sparse_irq_lock);
-	return alloc_descs(start, cnt, node, affinity, owner);
-
-err:
+	ret = alloc_descs(start, cnt, node, affinity, owner);
+unlock:
 	mutex_unlock(&sparse_irq_lock);
 	return ret;
 }

4.9-stable review patch. If anyone has any objections, please let me know.

------------------

From: Paul Mackerras <[email protected]>

commit edd03602d97236e8fea13cd76886c576186aa307 upstream.

Al Viro pointed out that while one thread of a process is executing in kvm_vm_ioctl_create_spapr_tce(), another thread could guess the file descriptor returned by anon_inode_getfd() and close() it before the first thread has added it to the kvm->arch.spapr_tce_tables list. That highlights a more general problem: there is no mutual exclusion between writers to the spapr_tce_tables list, leading to the possibility of the list becoming corrupted, which could cause a host kernel crash.

To fix the mutual exclusion problem, we add a mutex_lock/unlock pair around the list_del_rce in kvm_spapr_tce_release().

If another thread does guess the file descriptor returned by the anon_inode_getfd() call in kvm_vm_ioctl_create_spapr_tce() and closes it, its call to kvm_spapr_tce_release() will not do any harm because it will have to wait until the first thread has released kvm->lock.

The other things that the second thread could do with the guessed file descriptor are to mmap it or to pass it as a parameter to a KVM_DEV_VFIO_GROUP_SET_SPAPR_TCE ioctl on a KVM device fd. An mmap call won't cause any harm because kvm_spapr_tce_mmap() and kvm_spapr_tce_fault() don't access the spapr_tce_tables list or the kvmppc_spapr_tce_table.list field, and the fields that they do use have been properly initialized by the time of the anon_inode_getfd() call.

The KVM_DEV_VFIO_GROUP_SET_SPAPR_TCE ioctl calls kvm_spapr_tce_attach_iommu_group(), which scans the spapr_tce_tables list looking for the kvmppc_spapr_tce_table struct corresponding to the fd given as the parameter. Either it will find the new entry or it won't; if it doesn't, it just returns an error, and if it does, it will function normally. So, in each case there is no harmful effect.

[[email protected] - moved parts of the upstream patch into the backport
of 47c5310a8dbe, adjusted this commit message accordingly.]

---
 arch/powerpc/kvm/book3s_64_vio.c |    3 +++
 1 file changed, 3 insertions(+)

@@ -129,8 +129,11 @@ static int kvm_spapr_tce_mmap(struct fil
 static int kvm_spapr_tce_release(struct inode *inode, struct file *filp)
 {
 	struct kvmppc_spapr_tce_table *stt = filp->private_data;
+	struct kvm *kvm = stt->kvm;
 
+	mutex_lock(&kvm->lock);
 	list_del_rcu(&stt->list);
+	mutex_unlock(&kvm->lock);
 
 	kvm_put_kvm(stt->kvm);
 

4.9-stable review patch. If anyone has any objections, please let me know.

------------------

From: Steve Wise <[email protected]>

commit 8b1bbf36b7452c4acb20e91948eaa5e225ea6978 upstream.

If a listen create fails, then the server tid (stid) is incorrectly left in the stid idr table, which can cause a touch-after-free if the stid is looked up and the already freed endpoint is touched. So make sure and remove it in the error path.

---
 drivers/infiniband/hw/cxgb4/cm.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

@@ -3441,7 +3441,7 @@ int c4iw_create_listen(struct iw_cm_id *
 		cm_id->provider_data = ep;
 		goto out;
 	}
-
+	remove_handle(ep->com.dev, &ep->com.dev->stid_idr, ep->stid);
 	cxgb4_free_stid(ep->com.dev->rdev.lldi.tids, ep->stid,
 			ep->com.local_addr.ss_family);
 fail2:

4.9-stable review patch. If anyone has any objections, please let me know.

------------------

From: Jim Mattson <[email protected]>

commit 51aa68e7d57e3217192d88ce90fd5b8ef29ec94f upstream.

If L1 does not specify the "use TPR shadow" VM-execution control in vmcs12, then L0 must specify the "CR8-load exiting" and "CR8-store exiting" VM-execution controls in vmcs02. Failure to do so will give the L2 VM unrestricted read/write access to the hardware CR8.

This fixes CVE-2017-12154.

---
 arch/x86/kvm/vmx.c |    5 +++++
 1 file changed, 5 insertions(+)

@@ -10001,6 +10001,11 @@ static void prepare_vmcs02(struct kvm_vc
 		vmcs_write64(VIRTUAL_APIC_PAGE_ADDR,
 				page_to_phys(vmx->nested.virtual_apic_page));
 		vmcs_write32(TPR_THRESHOLD, vmcs12->tpr_threshold);
+	} else {
+#ifdef CONFIG_X86_64
+		exec_control |= CPU_BASED_CR8_LOAD_EXITING |
+				CPU_BASED_CR8_STORE_EXITING;
+#endif
 	}
 
 	if (cpu_has_vmx_msr_bitmap() &&

4.9-stable review patch. If anyone has any objections, please let me know.

------------------

From: Lucas Stach <[email protected]>

commit 518417525f3652c12fb5fad6da4ade66c0072fa3 upstream.

All manipulations of the gem_object list need to be protected by the list mutex, as GEM objects can be created and freed in parallel. This fixes a kernel memory corruption.

---
 drivers/gpu/drm/etnaviv/etnaviv_gem.c |    3 +++
 1 file changed, 3 insertions(+)

@@ -549,12 +549,15 @@ static const struct etnaviv_gem_ops etna
 void etnaviv_gem_free_object(struct drm_gem_object *obj)
 {
 	struct etnaviv_gem_object *etnaviv_obj = to_etnaviv_bo(obj);
+	struct etnaviv_drm_private *priv = obj->dev->dev_private;
 	struct etnaviv_vram_mapping *mapping, *tmp;
 
 	/* object should not be active */
 	WARN_ON(is_active(etnaviv_obj));
 
+	mutex_lock(&priv->gem_lock);
 	list_del(&etnaviv_obj->gem_node);
+	mutex_unlock(&priv->gem_lock);
 
 	list_for_each_entry_safe(mapping, tmp, &etnaviv_obj->vram_list,
 				 obj_node) {

4.9-stable review patch. If anyone has any objections, please let me know.

------------------

From: Nicolai Stange <[email protected]>

commit 9561475db680f7144d2223a409dd3d7e322aca03 upstream.

The driver_override implementation is susceptible to a race condition when different threads are reading vs. storing a different driver override. Add locking to avoid the race condition.

This is in close analogy to commit 6265539776a0 ("driver core: platform:
fix race condition with driver_override") from Adrian Salido.

---
 drivers/pci/pci-sysfs.c |   11 +++++++++--
 1 file changed, 9 insertions(+), 2 deletions(-)

@@ -527,7 +527,7 @@ static ssize_t driver_override_store(str
 				     const char *buf, size_t count)
 {
 	struct pci_dev *pdev = to_pci_dev(dev);
-	char *driver_override, *old = pdev->driver_override, *cp;
+	char *driver_override, *old, *cp;
 
 	/* We need to keep extra room for a newline */
 	if (count >= (PAGE_SIZE - 1))

@@ -541,12 +541,15 @@ static ssize_t driver_override_store(str
 	if (cp)
 		*cp = '\0';
 
+	device_lock(dev);
+	old = pdev->driver_override;
 	if (strlen(driver_override)) {
 		pdev->driver_override = driver_override;
 	} else {
 		kfree(driver_override);
 		pdev->driver_override = NULL;
 	}
+	device_unlock(dev);
 
 	kfree(old);
 

@@ -557,8 +560,12 @@ static ssize_t driver_override_show(stru
 				    struct device_attribute *attr, char *buf)
 {
 	struct pci_dev *pdev = to_pci_dev(dev);
+	ssize_t len;
 
-	return snprintf(buf, PAGE_SIZE, "%s\n", pdev->driver_override);
+	device_lock(dev);
+	len = snprintf(buf, PAGE_SIZE, "%s\n", pdev->driver_override);
+	device_unlock(dev);
+	return len;
 }
 static DEVICE_ATTR_RW(driver_override);
 

4.9-stable review patch. If anyone has any objections, please let me know.

------------------

From: Naohiro Aota <[email protected]>

commit bb166d7207432d3c7d10c45dc052f12ba3a2121d upstream.

__del_reloc_root should be called before freeing up reloc_root->node. If not, calling __del_reloc_root() dereference reloc_root->node, causing the system BUG.

---
 fs/btrfs/relocation.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

@@ -2367,11 +2367,11 @@ void free_reloc_roots(struct list_head *
 	while (!list_empty(list)) {
 		reloc_root = list_entry(list->next, struct btrfs_root,
 					root_list);
+		__del_reloc_root(reloc_root);
 		free_extent_buffer(reloc_root->node);
 		free_extent_buffer(reloc_root->commit_root);
 		reloc_root->node = NULL;
 		reloc_root->commit_root = NULL;
-		__del_reloc_root(reloc_root);
 	}
 }
 

4.9-stable review patch. If anyone has any objections, please let me know.

------------------

From: Naohiro Aota <[email protected]>

commit 78ad4ce014d025f41b8dde3a81876832ead643cf upstream.

btrfs_cmp_data_prepare() (almost) always returns 0 i.e. ignoring errors from gather_extent_pages(). While the pages are freed by btrfs_cmp_data_free(), cmp->num_pages still has > 0. Then, btrfs_extent_same() try to access the already freed pages causing faults (or violates PageLocked assertion).

This patch just return the error as is so that the caller stop the process.

---
 fs/btrfs/ioctl.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

@@ -3052,7 +3052,7 @@ static int btrfs_cmp_data_prepare(struct
 out:
 	if (ret)
 		btrfs_cmp_data_free(cmp);
-	return 0;
+	return ret;
 }
 
 static int btrfs_cmp_data(struct inode *src, u64 loff, struct inode *dst,

4.9-stable review patch. If anyone has any objections, please let me know.

------------------

From: satoru takeuchi <[email protected]>

commit 6d6d282932d1a609e60dc4467677e0e863682f57 upstream.

btrfs sub set-default succeeds to set an ID which isn't corresponding to any fs/file tree. If such the bad ID is set to a filesystem, we can't mount this filesystem without specifying subvol or subvolid mount options.

---
 fs/btrfs/ioctl.c |    4 ++++
 1 file changed, 4 insertions(+)

@@ -4082,6 +4082,10 @@ static long btrfs_ioctl_default_subvol(s
 		ret = PTR_ERR(new_root);
 		goto out;
 	}
+	if (!is_fstree(new_root->objectid)) {
+		ret = -ENOENT;
+		goto out;
+	}
 
 	path = btrfs_alloc_path();
 	if (!path) {

4.9-stable review patch. If anyone has any objections, please let me know.

------------------

From: Steve Wise <[email protected]>

commit 3d318605f5e32ff44fb290d9b67573b34213c4c8 upstream.

The listening endpoint should always be dereferenced at the end of pass_accept_req().

---
 drivers/infiniband/hw/cxgb4/cm.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

@@ -2577,9 +2577,9 @@ fail:
 	c4iw_put_ep(&child_ep->com);
 reject:
 	reject_cr(dev, hwtid, skb);
+out:
 	if (parent_ep)
 		c4iw_put_ep(&parent_ep->com);
-out:
 	return 0;
 }
 

4.9-stable review patch. If anyone has any objections, please let me know.

------------------

From: Andreas Gruenbacher <[email protected]>

commit 10201655b085df8e000822e496e5d4016a167a36 upstream.

The switch to rhashtables (commit 88ffbf3e03) broke the debugfs glock dump (/sys/kernel/debug/gfs2/<device>/glocks) for dumps bigger than a single buffer: the right function for restarting an rhashtable iteration from the beginning of the hash table is rhashtable_walk_enter; rhashtable_walk_stop + rhashtable_walk_start will just resume from the current position.

The upstream commit doesn't directly apply to 4.9.y because 4.9.y doesn't have the following mainline commits:

92ecd73a887c4a2b94daf5fc35179d75d1c4ef95
gfs2: Deduplicate gfs2_{glocks,glstats}_open
cc37a62785a584f4875788689f3fd1fa6e4eb291
gfs2: Replace rhashtable_walk_init with rhashtable_walk_enter

---
 fs/gfs2/glock.c |   16 +++++-----------
 1 file changed, 5 insertions(+), 11 deletions(-)

@@ -1836,13 +1836,9 @@ static void *gfs2_glock_seq_start(struct
 {
 	struct gfs2_glock_iter *gi = seq->private;
 	loff_t n = *pos;
-	int ret;
 
-	if (gi->last_pos <= *pos)
-		n = (*pos - gi->last_pos);
-
-	ret = rhashtable_walk_start(&gi->hti);
-	if (ret)
+	rhashtable_walk_enter(&gl_hash_table, &gi->hti);
+	if (rhashtable_walk_start(&gi->hti) != 0)
 		return NULL;
 
 	do {

@@ -1850,6 +1846,7 @@ static void *gfs2_glock_seq_start(struct
 	} while (gi->gl && n--);
 
 	gi->last_pos = *pos;
+
 	return gi->gl;
 }
 

@@ -1861,6 +1858,7 @@ static void *gfs2_glock_seq_next(struct
 	(*pos)++;
 	gi->last_pos = *pos;
 	gfs2_glock_iter_next(gi);
+
 	return gi->gl;
 }
 

@@ -1870,6 +1868,7 @@ static void gfs2_glock_seq_stop(struct s
 
 	gi->gl = NULL;
 	rhashtable_walk_stop(&gi->hti);
+	rhashtable_walk_exit(&gi->hti);
 }
 
 static int gfs2_glock_seq_show(struct seq_file *seq, void *iter_ptr)

@@ -1932,12 +1931,10 @@ static int gfs2_glocks_open(struct inode
 		struct gfs2_glock_iter *gi = seq->private;
 
 		gi->sdp = inode->i_private;
-		gi->last_pos = 0;
 		seq->buf = kmalloc(GFS2_SEQ_GOODSIZE, GFP_KERNEL | __GFP_NOWARN);
 		if (seq->buf)
 			seq->size = GFS2_SEQ_GOODSIZE;
 		gi->gl = NULL;
-		ret = rhashtable_walk_init(&gl_hash_table, &gi->hti, GFP_KERNEL);
 	}
 	return ret;
 }

@@ -1948,7 +1945,6 @@ static int gfs2_glocks_release(struct in
 	struct gfs2_glock_iter *gi = seq->private;
 
 	gi->gl = NULL;
-	rhashtable_walk_exit(&gi->hti);
 	return seq_release_private(inode, file);
 }
 

@@ -1960,12 +1956,10 @@ static int gfs2_glstats_open(struct inod
 		struct seq_file *seq = file->private_data;
 		struct gfs2_glock_iter *gi = seq->private;
 		gi->sdp = inode->i_private;
-		gi->last_pos = 0;
 		seq->buf = kmalloc(GFS2_SEQ_GOODSIZE, GFP_KERNEL | __GFP_NOWARN);
 		if (seq->buf)
 			seq->size = GFS2_SEQ_GOODSIZE;
 		gi->gl = NULL;
-		ret = rhashtable_walk_init(&gl_hash_table, &gi->hti, GFP_KERNEL);
 	}
 	return ret;
 }

4.9-stable review patch. If anyone has any objections, please let me know.

------------------

From: Myungho Jung <[email protected]>

commit b94bf594cf8ed67cdd0439e70fa939783471597a upstream.

timer_migration sysctl acts as a boolean switch, so the allowed values should be restricted to 0 and 1.

Add the necessary extra fields to the sysctl table entry to enforce that.

[ tglx: Rewrote changelog ]

---
 kernel/sysctl.c     |    2 ++
 kernel/time/timer.c |    2 +-
 2 files changed, 3 insertions(+), 1 deletion(-)

@@ -1189,6 +1189,8 @@ static struct ctl_table kern_table[] = {
 		.maxlen		= sizeof(unsigned int),
 		.mode		= 0644,
 		.proc_handler	= timer_migration_handler,
+		.extra1		= &zero,
+		.extra2		= &one,
 	},
 #endif
 #ifdef CONFIG_BPF_SYSCALL

@@ -240,7 +240,7 @@ int timer_migration_handler(struct ctl_t
 	int ret;
 
 	mutex_lock(&mutex);
-	ret = proc_dointvec(table, write, buffer, lenp, ppos);
+	ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos);
 	if (!ret && write)
 		timers_update_migration(false);
 	mutex_unlock(&mutex);

4.9-stable review patch. If anyone has any objections, please let me know.

------------------

From: Paolo Bonzini <[email protected]>

commit c0a1666bcb2a33e84187a15eabdcd54056be9a97 upstream.

This fixes a compilation failure on 32-bit systems.

---
 arch/x86/kvm/vmx.c |   12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

@@ -2203,8 +2203,8 @@ static void vmx_vcpu_pi_load(struct kvm_
 			new.ndst = (dest << 8) & 0xFF00;
 
 		new.sn = 0;
-	} while (cmpxchg(&pi_desc->control, old.control,
-			new.control) != old.control);
+	} while (cmpxchg64(&pi_desc->control, old.control,
+			   new.control) != old.control);
 }
 
 static void decache_tsc_multiplier(struct vcpu_vmx *vmx)

@@ -11039,8 +11039,8 @@ static void __pi_post_block(struct kvm_v
 
 		/* set 'NV' to 'notification vector' */
 		new.nv = POSTED_INTR_VECTOR;
-	} while (cmpxchg(&pi_desc->control, old.control,
-			new.control) != old.control);
+	} while (cmpxchg64(&pi_desc->control, old.control,
+			   new.control) != old.control);
 
 	if (!WARN_ON_ONCE(vcpu->pre_pcpu == -1)) {
 		spin_lock(&per_cpu(blocked_vcpu_on_cpu_lock, vcpu->pre_pcpu));

@@ -11109,8 +11109,8 @@ static int pi_pre_block(struct kvm_vcpu
 
 		/* set 'NV' to 'wakeup vector' */
 		new.nv = POSTED_INTR_WAKEUP_VECTOR;
-	} while (cmpxchg(&pi_desc->control, old.control,
-			new.control) != old.control);
+	} while (cmpxchg64(&pi_desc->control, old.control,
+			   new.control) != old.control);
 
 	/* We should not block the vCPU if an interrupt is posted for it.  */
 	if (pi_test_on(pi_desc) == 1)

4.9-stable review patch. If anyone has any objections, please let me know.

------------------

From: Vladis Dronov <[email protected]>

commit 8e75f7a7a00461ef6d91797a60b606367f6e344d upstream.

'clk' is copied to a userland with padding byte(s) after 'vclk_post_div' field unitialized, leaking data from the stack. Fix this ensuring all of 'clk' is initialized to zero.

References: https://github.com/torvalds/linux/pull/441

---
 drivers/video/fbdev/aty/atyfb_base.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

@@ -1861,7 +1861,7 @@ static int atyfb_ioctl(struct fb_info *i
 #if defined(DEBUG) && defined(CONFIG_FB_ATY_CT)
 	case ATYIO_CLKR:
 		if (M64_HAS(INTEGRATED)) {
-			struct atyclk clk;
+			struct atyclk clk = { 0 };
 			union aty_pll *pll = &par->pll;
 			u32 dsp_config = pll->ct.dsp_config;
 			u32 dsp_on_off = pll->ct.dsp_on_off;

4.9-stable review patch. If anyone has any objections, please let me know.

------------------

From: Stefano Stabellini <[email protected]>

commit 7e91c7df29b5e196de3dc6f086c8937973bd0b88 upstream.

This function creates userspace mapping for the DMA-coherent memory.

---
 arch/arm/xen/mm.c         |    1 +
 drivers/xen/swiotlb-xen.c |   19 +++++++++++++++++++
 include/xen/swiotlb-xen.h |    5 +++++
 3 files changed, 25 insertions(+)

@@ -199,6 +199,7 @@ static struct dma_map_ops xen_swiotlb_dm
 	.unmap_page = xen_swiotlb_unmap_page,
 	.dma_supported = xen_swiotlb_dma_supported,
 	.set_dma_mask = xen_swiotlb_set_dma_mask,
+	.mmap = xen_swiotlb_dma_mmap,
 };
 
 int __init xen_mm_init(void)

@@ -680,3 +680,22 @@ xen_swiotlb_set_dma_mask(struct device *
 	return 0;
 }
 EXPORT_SYMBOL_GPL(xen_swiotlb_set_dma_mask);
+
+/*
+ * Create userspace mapping for the DMA-coherent memory.
+ * This function should be called with the pages from the current domain only,
+ * passing pages mapped from other domains would lead to memory corruption.
+ */
+int
+xen_swiotlb_dma_mmap(struct device *dev, struct vm_area_struct *vma,
+		     void *cpu_addr, dma_addr_t dma_addr, size_t size,
+		     unsigned long attrs)
+{
+#if defined(CONFIG_ARM) || defined(CONFIG_ARM64)
+	if (__generic_dma_ops(dev)->mmap)
+		return __generic_dma_ops(dev)->mmap(dev, vma, cpu_addr,
+						    dma_addr, size, attrs);
+#endif
+	return dma_common_mmap(dev, vma, cpu_addr, dma_addr, size);
+}
+EXPORT_SYMBOL_GPL(xen_swiotlb_dma_mmap);

@@ -58,4 +58,9 @@ xen_swiotlb_dma_supported(struct device
 
 extern int
 xen_swiotlb_set_dma_mask(struct device *dev, u64 dma_mask);
+
+extern int
+xen_swiotlb_dma_mmap(struct device *dev, struct vm_area_struct *vma,
+		     void *cpu_addr, dma_addr_t dma_addr, size_t size,
+		     unsigned long attrs);
 #endif /* __LINUX_SWIOTLB_XEN_H */

4.9-stable review patch. If anyone has any objections, please let me know.

------------------

From: Kees Cook <[email protected]>

commit 10859f3855db4c6f10dc7974ff4b3a292f3de8e0 upstream.

The 2.26 release of glibc changed how siginfo_t is defined, and the earlier work-around to using the kernel definition are no longer needed. The old way needs to stay around for a while, though.

---
 tools/testing/selftests/seccomp/seccomp_bpf.c |   18 +++++++++++++-----
 1 file changed, 13 insertions(+), 5 deletions(-)

@@ -6,10 +6,18 @@
  */
 
 #include <sys/types.h>
-#include <asm/siginfo.h>
-#define __have_siginfo_t 1
-#define __have_sigval_t 1
-#define __have_sigevent_t 1
+
+/*
+ * glibc 2.26 and later have SIGSYS in siginfo_t. Before that,
+ * we need to use the kernel's siginfo.h file and trick glibc
+ * into accepting it.
+ */
+#if !__GLIBC_PREREQ(2, 26)
+# include <asm/siginfo.h>
+# define __have_siginfo_t 1
+# define __have_sigval_t 1
+# define __have_sigevent_t 1
+#endif
 
 #include <errno.h>
 #include <linux/filter.h>

@@ -676,7 +684,7 @@ TEST_F_SIGNAL(TRAP, ign, SIGSYS)
 	syscall(__NR_getpid);
 }
 
-static struct siginfo TRAP_info;
+static siginfo_t TRAP_info;
 static volatile int TRAP_nr;
 static void TRAP_action(int nr, siginfo_t *info, void *void_context)
 {

4.9-stable review patch. If anyone has any objections, please let me know.

------------------

From: Oleg Nesterov <[email protected]>

commit 66a733ea6b611aecf0119514d2dddab5f9d6c01e upstream.

As Chris explains, get_seccomp_filter() and put_seccomp_filter() can end up using different filters. Once we drop ->siglock it is possible for task->seccomp.filter to have been replaced by SECCOMP_FILTER_FLAG_TSYNC.

---
 kernel/seccomp.c |   23 ++++++++++++++++-------
 1 file changed, 16 insertions(+), 7 deletions(-)

@@ -457,14 +457,19 @@ static long seccomp_attach_filter(unsign
 	return 0;
 }
 
+void __get_seccomp_filter(struct seccomp_filter *filter)
+{
+	/* Reference count is bounded by the number of total processes. */
+	atomic_inc(&filter->usage);
+}
+
 /* get_seccomp_filter - increments the reference count of the filter on @tsk */
 void get_seccomp_filter(struct task_struct *tsk)
 {
 	struct seccomp_filter *orig = tsk->seccomp.filter;
 	if (!orig)
 		return;
-	/* Reference count is bounded by the number of total processes. */
-	atomic_inc(&orig->usage);
+	__get_seccomp_filter(orig);
 }
 
 static inline void seccomp_filter_free(struct seccomp_filter *filter)

@@ -475,10 +480,8 @@ static inline void seccomp_filter_free(s
 	}
 }
 
-/* put_seccomp_filter - decrements the ref count of tsk->seccomp.filter */
-void put_seccomp_filter(struct task_struct *tsk)
+static void __put_seccomp_filter(struct seccomp_filter *orig)
 {
-	struct seccomp_filter *orig = tsk->seccomp.filter;
 	/* Clean up single-reference branches iteratively. */
 	while (orig && atomic_dec_and_test(&orig->usage)) {
 		struct seccomp_filter *freeme = orig;

@@ -487,6 +490,12 @@ void put_seccomp_filter(struct task_stru
 	}
 }
 
+/* put_seccomp_filter - decrements the ref count of tsk->seccomp.filter */
+void put_seccomp_filter(struct task_struct *tsk)
+{
+	__put_seccomp_filter(tsk->seccomp.filter);
+}
+
 /**
  * seccomp_send_sigsys - signals the task to allow in-process syscall emulation
  * @syscall: syscall number to send to userland

@@ -892,13 +901,13 @@ long seccomp_get_filter(struct task_stru
 	if (!data)
 		goto out;
 
-	get_seccomp_filter(task);
+	__get_seccomp_filter(filter);
 	spin_unlock_irq(&task->sighand->siglock);
 
 	if (copy_to_user(data, fprog->filter, bpf_classic_proglen(fprog)))
 		ret = -EFAULT;
 
-	put_seccomp_filter(task);
+	__put_seccomp_filter(filter);
 	return ret;
 
 out:

4.9-stable review patch. If anyone has any objections, please let me know.

------------------

From: Marc Zyngier <[email protected]>

commit 5371513fb338fb9989c569dc071326d369d6ade8 upstream.

When the kernel is entered at EL2 on an ARMv8.0 system, we construct the EL1 pstate and make sure this uses the the EL1 stack pointer (we perform an exception return to EL1h).

But if the kernel is either entered at EL1 or stays at EL2 (because we're on a VHE-capable system), we fail to set SPsel, and use whatever stack selection the higher exception level has choosen for us.

Let's not take any chance, and make sure that SPsel is set to one before we decide the mode we're going to run in.

---
 arch/arm64/kernel/head.S |    1 +
 1 file changed, 1 insertion(+)

@@ -486,6 +486,7 @@ ENTRY(kimage_vaddr)
  * booted in EL1 or EL2 respectively.
  */
 ENTRY(el2_setup)
+	msr	SPsel, #1			// We want to use SP_EL{1,2}
 	mrs	x0, CurrentEL
 	cmp	x0, #CurrentEL_EL2
 	b.ne	1f

4.9-stable review patch. If anyone has any objections, please let me know.

------------------

From: Will Deacon <[email protected]>

commit 760bfb47c36a07741a089bf6a28e854ffbee7dc9 upstream.

We currently route pte translation faults via do_page_fault, which elides the address check against TASK_SIZE before invoking the mm fault handling code. However, this can cause issues with the path walking code in conjunction with our word-at-a-time implementation because load_unaligned_zeropad can end up faulting in kernel space if it reads across a page boundary and runs into a page fault (e.g. by attempting to read from a guard region).

In the case of such a fault, load_unaligned_zeropad has registered a fixup to shift the valid data and pad with zeroes, however the abort is reported as a level 3 translation fault and we dispatch it straight to do_page_fault, despite it being a kernel address. This results in calling a sleeping function from atomic context:

  BUG: sleeping function called from invalid context at arch/arm64/mm/fault.c:313
  in_atomic(): 0, irqs_disabled(): 0, pid: 10290
  Internal error: Oops - BUG: 0 [#1] PREEMPT SMP
  [...]
  [<ffffff8e016cd0cc>] ___might_sleep+0x134/0x144
  [<ffffff8e016cd158>] __might_sleep+0x7c/0x8c
  [<ffffff8e016977f0>] do_page_fault+0x140/0x330
  [<ffffff8e01681328>] do_mem_abort+0x54/0xb0
  Exception stack(0xfffffffb20247a70 to 0xfffffffb20247ba0)
  [...]
  [<ffffff8e016844fc>] el1_da+0x18/0x78
  [<ffffff8e017f399c>] path_parentat+0x44/0x88
  [<ffffff8e017f4c9c>] filename_parentat+0x5c/0xd8
  [<ffffff8e017f5044>] filename_create+0x4c/0x128
  [<ffffff8e017f59e4>] SyS_mkdirat+0x50/0xc8
  [<ffffff8e01684e30>] el0_svc_naked+0x24/0x28
  Code: 36380080 d5384100 f9400800 9402566d (d4210000)
  ---[ end trace 2d01889f2bca9b9f ]---

Fix this by dispatching all translation faults to do_translation_faults, which avoids invoking the page fault logic for faults on kernel addresses.

---
 arch/arm64/mm/fault.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

@@ -509,7 +509,7 @@ static const struct fault_info fault_inf
 	{ do_translation_fault,	SIGSEGV, SEGV_MAPERR,	"level 0 translation fault"	},
 	{ do_translation_fault,	SIGSEGV, SEGV_MAPERR,	"level 1 translation fault"	},
 	{ do_translation_fault,	SIGSEGV, SEGV_MAPERR,	"level 2 translation fault"	},
-	{ do_page_fault,	SIGSEGV, SEGV_MAPERR,	"level 3 translation fault"	},
+	{ do_translation_fault,	SIGSEGV, SEGV_MAPERR,	"level 3 translation fault"	},
 	{ do_bad,		SIGBUS,  0,		"unknown 8"			},
 	{ do_page_fault,	SIGSEGV, SEGV_ACCERR,	"level 1 access flag fault"	},
 	{ do_page_fault,	SIGSEGV, SEGV_ACCERR,	"level 2 access flag fault"	},

4.9-stable review patch. If anyone has any objections, please let me know.

------------------

From: Christoph Hellwig <[email protected]>

commit f507b54dccfd8000c517d740bc45f20c74532d18 upstream.

The job structure is allocated as part of the request, so we should not free it in the error path of bsg_prepare_job.

---
 block/bsg-lib.c |    1 -
 1 file changed, 1 deletion(-)

@@ -147,7 +147,6 @@ static int bsg_create_job(struct device
 failjob_rls_rqst_payload:
 	kfree(job->request_payload.sg_list);
 failjob_rls_job:
-	kfree(job);
 	return -ENOMEM;
 }
 

4.9-stable review patch. If anyone has any objections, please let me know.

------------------

From: Frederic Barrat <[email protected]>

commit 197267d0356004a31c4d6b6336598f5dff3301e1 upstream.

cxl keeps a driver use count, which is used with the hash memory model on p8 to know when to upgrade local TLBIs to global and to trigger callbacks to manage the MMU for PSL8.

If a process opens a context and closes without attaching or fails the attachment, the driver use count is never decremented. As a consequence, TLB invalidations remain global, even if there are no active cxl contexts.

We should increment the driver use count when the process is attaching to the cxl adapter, and not on open. It's not needed before the adapter starts using the context and the use count is decremented on the detach path, so it makes more sense.

It affects only the user api. The kernel api is already doing The Right Thing.

---
 drivers/misc/cxl/api.c  |    4 ++++
 drivers/misc/cxl/file.c |    8 +++++++-
 2 files changed, 11 insertions(+), 1 deletion(-)

@@ -244,6 +244,10 @@ int cxl_start_context(struct cxl_context
 		ctx->real_mode = false;
 	}
 
+	/*
+	 * Increment driver use count. Enables global TLBIs for hash
+	 * and callbacks to handle the segment table
+	 */
 	cxl_ctx_get();
 
 	if ((rc = cxl_ops->attach_process(ctx, kernel, wed, 0))) {

@@ -91,7 +91,6 @@ static int __afu_open(struct inode *inod
 
 	pr_devel("afu_open pe: %i\n", ctx->pe);
 	file->private_data = ctx;
-	cxl_ctx_get();
 
 	/* indicate success */
 	rc = 0;

@@ -213,6 +212,12 @@ static long afu_ioctl_start_work(struct
 	ctx->glpid = get_task_pid(current->group_leader, PIDTYPE_PID);
 
 
+	/*
+	 * Increment driver use count. Enables global TLBIs for hash
+	 * and callbacks to handle the segment table
+	 */
+	cxl_ctx_get();
+
 	trace_cxl_attach(ctx, work.work_element_descriptor, work.num_interrupts, amr);
 
 	if ((rc = cxl_ops->attach_process(ctx, false, work.work_element_descriptor,

@@ -222,6 +227,7 @@ static long afu_ioctl_start_work(struct
 		put_pid(ctx->glpid);
 		put_pid(ctx->pid);
 		ctx->glpid = ctx->pid = NULL;
+		cxl_ctx_put();
 		goto out;
 	}
 

Compiled and booted on my test system. No dmesg regressions.

thanks,
-- Shuah

Test results from the linaro linux kernel functional test farm:

kernel: 4.9.53-rc1
git repo: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux-stable-rc.git
git branch: linux-4.9.y
git commit: aceea42c68d96c58958954e4c8c23a26f8883d62
git describe: v4.9.52-65-gaceea42c68d9
Test details: https://qa-reports.linaro.org/lkft/linux-stable-rc-4.9-oe/build/v4.9.52-65-gaceea42c68d9

No regressions (compared to build v4.9.51-78-ge009129d09cb)

Boards, architectures and test suites:
-------------------------------------

hi6220-hikey - arm64
* boot - 1 pass
* kselftest - 38 pass - 1 skip - 15 known failures
* libhugetlbfs - 90 pass - 1 skip
* ltp-syscalls-tests - 964 pass - 136 skip

juno-r2 - arm64
* boot - 1 pass
* kselftest - 37 pass - 1 skip - 14 known failures
* libhugetlbfs - 90 pass - 1 skip

dell-poweredge-r200 - x86_64
* boot - 1 pass
* kselftest - 52 pass - 15 known failures
* libhugetlbfs - 76 pass - 1 skip
* ltp-syscalls-tests - 941 pass - 175 skip - 11known failures

Tom

Director, Linaro Mobile Group

Linaro.org │ Open source software for ARM SoCs
irc: tgall_foo | skype : tom_gall  

"Where's the kaboom!? There was supposed to be an earth-shattering kaboom!" Marvin Martian

Build results:

	total: 145 pass: 145 fail: 0
Qemu test results:
	total: 123 pass: 123 fail: 0

Details are available at http://kerneltests.org/builders.

Guenter

Looks like you lost a ' ' in that last line somehow :)

Anyway, again, lots of "known failures", do these also show up in 4.13-stable?

thanks for testing and letting me know.

greg k-h