4.9.46-stable review

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 arch/sparc/kernel/pci_sun4v.c |    2 --
 1 file changed, 2 deletions(-)

arch/sparc/kernel/pci_sun4v.c +0 -2

@@ -1240,8 +1240,6 @@ static int pci_sun4v_probe(struct platfo
 			 * ATU group, but ATU hcalls won't be available.
 			 */
 			hv_atu = false;
-			pr_err(PFX "Could not register hvapi ATU err=%d\n",
-			       err);
 		} else {
 			pr_info(PFX "Registered hvapi ATU major[%lu] minor[%lu]\n",
 				vatu_major, vatu_minor);

Greg Kroah-Hartman

author maintainer

2017-08-28 08:04 UTC #2 lore raw

PATCH 2/84 af_key: do not use GFP_KERNEL in atomic contexts

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

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

From: Eric Dumazet <[email protected]>

[ Upstream commit 36f41f8fc6d8aa9f8c9072d66ff7cf9055f5e69b ]

pfkey_broadcast() might be called from non process contexts, we can not use GFP_KERNEL in these cases [1].

This patch partially reverts commit ba51b6be38c1 ("net: Fix RCU splat in af_key"), only keeping the GFP_ATOMIC forcing under rcu_read_lock() section.

[1] : syzkaller reported :

in_atomic(): 1, irqs_disabled(): 0, pid: 2932, name: syzkaller183439 3 locks held by syzkaller183439/2932:

 #0:  (&net->xfrm.xfrm_cfg_mutex){+.+.+.}, at: [<ffffffff83b43888>] pfkey_sendmsg+0x4c8/0x9f0 net/key/af_key.c:3649
 #1:  (&pfk->dump_lock){+.+.+.}, at: [<ffffffff83b467f6>] pfkey_do_dump+0x76/0x3f0 net/key/af_key.c:293
 #2:  (&(&net->xfrm.xfrm_policy_lock)->rlock){+...+.}, at: [<ffffffff83957632>] spin_lock_bh include/linux/spinlock.h:304 [inline]
 #2:  (&(&net->xfrm.xfrm_policy_lock)->rlock){+...+.}, at: [<ffffffff83957632>] xfrm_policy_walk+0x192/0xa30 net/xfrm/xfrm_policy.c:1028
CPU: 0 PID: 2932 Comm: syzkaller183439 Not tainted 4.13.0-rc4+ #24
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
 __dump_stack lib/dump_stack.c:16 [inline]
 dump_stack+0x194/0x257 lib/dump_stack.c:52
 ___might_sleep+0x2b2/0x470 kernel/sched/core.c:5994
 __might_sleep+0x95/0x190 kernel/sched/core.c:5947
 slab_pre_alloc_hook mm/slab.h:416 [inline]
 slab_alloc mm/slab.c:3383 [inline]
 kmem_cache_alloc+0x24b/0x6e0 mm/slab.c:3559
 skb_clone+0x1a0/0x400 net/core/skbuff.c:1037
 pfkey_broadcast_one+0x4b2/0x6f0 net/key/af_key.c:207
 pfkey_broadcast+0x4ba/0x770 net/key/af_key.c:281
 dump_sp+0x3d6/0x500 net/key/af_key.c:2685
 xfrm_policy_walk+0x2f1/0xa30 net/xfrm/xfrm_policy.c:1042
 pfkey_dump_sp+0x42/0x50 net/key/af_key.c:2695
 pfkey_do_dump+0xaa/0x3f0 net/key/af_key.c:299
 pfkey_spddump+0x1a0/0x210 net/key/af_key.c:2722
 pfkey_process+0x606/0x710 net/key/af_key.c:2814
 pfkey_sendmsg+0x4d6/0x9f0 net/key/af_key.c:3650
sock_sendmsg_nosec net/socket.c:633 [inline]
 sock_sendmsg+0xca/0x110 net/socket.c:643
 ___sys_sendmsg+0x755/0x890 net/socket.c:2035
 __sys_sendmsg+0xe5/0x210 net/socket.c:2069
 SYSC_sendmsg net/socket.c:2080 [inline]
 SyS_sendmsg+0x2d/0x50 net/socket.c:2076
 entry_SYSCALL_64_fastpath+0x1f/0xbe
RIP: 0033:0x445d79
RSP: 002b:00007f32447c1dc8 EFLAGS: 00000202 ORIG_RAX: 000000000000002e
RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 0000000000445d79
RDX: 0000000000000000 RSI: 000000002023dfc8 RDI: 0000000000000008
RBP: 0000000000000086 R08: 00007f32447c2700 R09: 00007f32447c2700
R10: 00007f32447c2700 R11: 0000000000000202 R12: 0000000000000000
R13: 00007ffe33edec4f R14: 00007f32447c29c0 R15: 0000000000000000

Fixes ba51b6be38c1 ("net: Fix RCU splat in af_key")

Cc David Ahern <[email protected]>

Acked-by David Ahern <[email protected]>

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 net/key/af_key.c |   48 ++++++++++++++++++++++++++----------------------
 1 file changed, 26 insertions(+), 22 deletions(-)

net/key/af_key.c +26 ~~-22~~

@@ -228,7 +228,7 @@ static int pfkey_broadcast_one(struct sk
 #define BROADCAST_ONE		1
 #define BROADCAST_REGISTERED	2
 #define BROADCAST_PROMISC_ONLY	4
-static int pfkey_broadcast(struct sk_buff *skb,
+static int pfkey_broadcast(struct sk_buff *skb, gfp_t allocation,
 			   int broadcast_flags, struct sock *one_sk,
 			   struct net *net)
 {

@@ -278,7 +278,7 @@ static int pfkey_broadcast(struct sk_buf
 	rcu_read_unlock();
 
 	if (one_sk != NULL)
-		err = pfkey_broadcast_one(skb, &skb2, GFP_KERNEL, one_sk);
+		err = pfkey_broadcast_one(skb, &skb2, allocation, one_sk);
 
 	kfree_skb(skb2);
 	kfree_skb(skb);

@@ -311,7 +311,7 @@ static int pfkey_do_dump(struct pfkey_so
 		hdr = (struct sadb_msg *) pfk->dump.skb->data;
 		hdr->sadb_msg_seq = 0;
 		hdr->sadb_msg_errno = rc;
-		pfkey_broadcast(pfk->dump.skb, BROADCAST_ONE,
+		pfkey_broadcast(pfk->dump.skb, GFP_ATOMIC, BROADCAST_ONE,
 				&pfk->sk, sock_net(&pfk->sk));
 		pfk->dump.skb = NULL;
 	}

@@ -355,7 +355,7 @@ static int pfkey_error(const struct sadb
 	hdr->sadb_msg_len = (sizeof(struct sadb_msg) /
 			     sizeof(uint64_t));
 
-	pfkey_broadcast(skb, BROADCAST_ONE, sk, sock_net(sk));
+	pfkey_broadcast(skb, GFP_KERNEL, BROADCAST_ONE, sk, sock_net(sk));
 
 	return 0;
 }

@@ -1396,7 +1396,7 @@ static int pfkey_getspi(struct sock *sk,
 
 	xfrm_state_put(x);
 
-	pfkey_broadcast(resp_skb, BROADCAST_ONE, sk, net);
+	pfkey_broadcast(resp_skb, GFP_KERNEL, BROADCAST_ONE, sk, net);
 
 	return 0;
 }

@@ -1483,7 +1483,7 @@ static int key_notify_sa(struct xfrm_sta
 	hdr->sadb_msg_seq = c->seq;
 	hdr->sadb_msg_pid = c->portid;
 
-	pfkey_broadcast(skb, BROADCAST_ALL, NULL, xs_net(x));
+	pfkey_broadcast(skb, GFP_ATOMIC, BROADCAST_ALL, NULL, xs_net(x));
 
 	return 0;
 }

@@ -1596,7 +1596,7 @@ static int pfkey_get(struct sock *sk, st
 	out_hdr->sadb_msg_reserved = 0;
 	out_hdr->sadb_msg_seq = hdr->sadb_msg_seq;
 	out_hdr->sadb_msg_pid = hdr->sadb_msg_pid;
-	pfkey_broadcast(out_skb, BROADCAST_ONE, sk, sock_net(sk));
+	pfkey_broadcast(out_skb, GFP_ATOMIC, BROADCAST_ONE, sk, sock_net(sk));
 
 	return 0;
 }

@@ -1701,8 +1701,8 @@ static int pfkey_register(struct sock *s
 		return -ENOBUFS;
 	}
 
-	pfkey_broadcast(supp_skb, BROADCAST_REGISTERED, sk, sock_net(sk));
-
+	pfkey_broadcast(supp_skb, GFP_KERNEL, BROADCAST_REGISTERED, sk,
+			sock_net(sk));
 	return 0;
 }

@@ -1720,7 +1720,8 @@ static int unicast_flush_resp(struct soc
 	hdr->sadb_msg_errno = (uint8_t) 0;
 	hdr->sadb_msg_len = (sizeof(struct sadb_msg) / sizeof(uint64_t));
 
-	return pfkey_broadcast(skb, BROADCAST_ONE, sk, sock_net(sk));
+	return pfkey_broadcast(skb, GFP_ATOMIC, BROADCAST_ONE, sk,
+			       sock_net(sk));
 }
 
 static int key_notify_sa_flush(const struct km_event *c)

@@ -1741,7 +1742,7 @@ static int key_notify_sa_flush(const str
 	hdr->sadb_msg_len = (sizeof(struct sadb_msg) / sizeof(uint64_t));
 	hdr->sadb_msg_reserved = 0;
 
-	pfkey_broadcast(skb, BROADCAST_ALL, NULL, c->net);
+	pfkey_broadcast(skb, GFP_ATOMIC, BROADCAST_ALL, NULL, c->net);
 
 	return 0;
 }

@@ -1798,7 +1799,7 @@ static int dump_sa(struct xfrm_state *x,
 	out_hdr->sadb_msg_pid = pfk->dump.msg_portid;
 
 	if (pfk->dump.skb)
-		pfkey_broadcast(pfk->dump.skb, BROADCAST_ONE,
+		pfkey_broadcast(pfk->dump.skb, GFP_ATOMIC, BROADCAST_ONE,
 				&pfk->sk, sock_net(&pfk->sk));
 	pfk->dump.skb = out_skb;

@@ -1886,7 +1887,7 @@ static int pfkey_promisc(struct sock *sk
 		new_hdr->sadb_msg_errno = 0;
 	}
 
-	pfkey_broadcast(skb, BROADCAST_ALL, NULL, sock_net(sk));
+	pfkey_broadcast(skb, GFP_KERNEL, BROADCAST_ALL, NULL, sock_net(sk));
 	return 0;
 }

@@ -2219,7 +2220,7 @@ static int key_notify_policy(struct xfrm
 	out_hdr->sadb_msg_errno = 0;
 	out_hdr->sadb_msg_seq = c->seq;
 	out_hdr->sadb_msg_pid = c->portid;
-	pfkey_broadcast(out_skb, BROADCAST_ALL, NULL, xp_net(xp));
+	pfkey_broadcast(out_skb, GFP_ATOMIC, BROADCAST_ALL, NULL, xp_net(xp));
 	return 0;
 
 }

@@ -2439,7 +2440,7 @@ static int key_pol_get_resp(struct sock
 	out_hdr->sadb_msg_errno = 0;
 	out_hdr->sadb_msg_seq = hdr->sadb_msg_seq;
 	out_hdr->sadb_msg_pid = hdr->sadb_msg_pid;
-	pfkey_broadcast(out_skb, BROADCAST_ONE, sk, xp_net(xp));
+	pfkey_broadcast(out_skb, GFP_ATOMIC, BROADCAST_ONE, sk, xp_net(xp));
 	err = 0;
 
 out:

@@ -2695,7 +2696,7 @@ static int dump_sp(struct xfrm_policy *x
 	out_hdr->sadb_msg_pid = pfk->dump.msg_portid;
 
 	if (pfk->dump.skb)
-		pfkey_broadcast(pfk->dump.skb, BROADCAST_ONE,
+		pfkey_broadcast(pfk->dump.skb, GFP_ATOMIC, BROADCAST_ONE,
 				&pfk->sk, sock_net(&pfk->sk));
 	pfk->dump.skb = out_skb;

@@ -2752,7 +2753,7 @@ static int key_notify_policy_flush(const
 	hdr->sadb_msg_satype = SADB_SATYPE_UNSPEC;
 	hdr->sadb_msg_len = (sizeof(struct sadb_msg) / sizeof(uint64_t));
 	hdr->sadb_msg_reserved = 0;
-	pfkey_broadcast(skb_out, BROADCAST_ALL, NULL, c->net);
+	pfkey_broadcast(skb_out, GFP_ATOMIC, BROADCAST_ALL, NULL, c->net);
 	return 0;
 
 }

@@ -2814,7 +2815,7 @@ static int pfkey_process(struct sock *sk
 	void *ext_hdrs[SADB_EXT_MAX];
 	int err;
 
-	pfkey_broadcast(skb_clone(skb, GFP_KERNEL),
+	pfkey_broadcast(skb_clone(skb, GFP_KERNEL), GFP_KERNEL,
 			BROADCAST_PROMISC_ONLY, NULL, sock_net(sk));
 
 	memset(ext_hdrs, 0, sizeof(ext_hdrs));

@@ -3036,7 +3037,8 @@ static int key_notify_sa_expire(struct x
 	out_hdr->sadb_msg_seq = 0;
 	out_hdr->sadb_msg_pid = 0;
 
-	pfkey_broadcast(out_skb, BROADCAST_REGISTERED, NULL, xs_net(x));
+	pfkey_broadcast(out_skb, GFP_ATOMIC, BROADCAST_REGISTERED, NULL,
+			xs_net(x));
 	return 0;
 }

@@ -3226,7 +3228,8 @@ static int pfkey_send_acquire(struct xfr
 		       xfrm_ctx->ctx_len);
 	}
 
-	return pfkey_broadcast(skb, BROADCAST_REGISTERED, NULL, xs_net(x));
+	return pfkey_broadcast(skb, GFP_ATOMIC, BROADCAST_REGISTERED, NULL,
+			       xs_net(x));
 }
 
 static struct xfrm_policy *pfkey_compile_policy(struct sock *sk, int opt,

@@ -3424,7 +3427,8 @@ static int pfkey_send_new_mapping(struct
 	n_port->sadb_x_nat_t_port_port = sport;
 	n_port->sadb_x_nat_t_port_reserved = 0;
 
-	return pfkey_broadcast(skb, BROADCAST_REGISTERED, NULL, xs_net(x));
+	return pfkey_broadcast(skb, GFP_ATOMIC, BROADCAST_REGISTERED, NULL,
+			       xs_net(x));
 }
 
 #ifdef CONFIG_NET_KEY_MIGRATE

@@ -3616,7 +3620,7 @@ static int pfkey_send_migrate(const stru
 	}
 
 	/* broadcast migrate message to sockets */
-	pfkey_broadcast(skb, BROADCAST_ALL, NULL, &init_net);
+	pfkey_broadcast(skb, GFP_ATOMIC, BROADCAST_ALL, NULL, &init_net);
 
 	return 0;

Greg Kroah-Hartman

author maintainer

2017-08-28 08:10 UTC #3 lore raw

PATCH 3/84 dccp: purge write queue in dccp_destroy_sock()

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

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

From: Eric Dumazet <[email protected]>

[ Upstream commit 7749d4ff88d31b0be17c8683143135adaaadc6a7 ]

syzkaller reported that DCCP could have a non empty write queue at dismantle time.

WARNING: CPU: 1 PID: 2953 at net/core/stream.c:199 sk_stream_kill_queues+0x3ce/0x520 net/core/stream.c:199
Kernel panic - not syncing: panic_on_warn set ...

CPU: 1 PID: 2953 Comm: syz-executor0 Not tainted 4.13.0-rc4+ #2
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
 __dump_stack lib/dump_stack.c:16 [inline]
 dump_stack+0x194/0x257 lib/dump_stack.c:52
 panic+0x1e4/0x417 kernel/panic.c:180
 __warn+0x1c4/0x1d9 kernel/panic.c:541
 report_bug+0x211/0x2d0 lib/bug.c:183
 fixup_bug+0x40/0x90 arch/x86/kernel/traps.c:190
 do_trap_no_signal arch/x86/kernel/traps.c:224 [inline]
 do_trap+0x260/0x390 arch/x86/kernel/traps.c:273
 do_error_trap+0x120/0x390 arch/x86/kernel/traps.c:310
 do_invalid_op+0x1b/0x20 arch/x86/kernel/traps.c:323
 invalid_op+0x1e/0x30 arch/x86/entry/entry_64.S:846
RIP: 0010:sk_stream_kill_queues+0x3ce/0x520 net/core/stream.c:199
RSP: 0018:ffff8801d182f108 EFLAGS: 00010297
RAX: ffff8801d1144140 RBX: ffff8801d13cb280 RCX: 0000000000000000
RDX: 0000000000000000 RSI: ffffffff85137b00 RDI: ffff8801d13cb280
RBP: ffff8801d182f148 R08: 0000000000000001 R09: 0000000000000000
R10: 0000000000000000 R11: 0000000000000000 R12: ffff8801d13cb4d0
R13: ffff8801d13cb3b8 R14: ffff8801d13cb300 R15: ffff8801d13cb3b8
 inet_csk_destroy_sock+0x175/0x3f0 net/ipv4/inet_connection_sock.c:835
 dccp_close+0x84d/0xc10 net/dccp/proto.c:1067
 inet_release+0xed/0x1c0 net/ipv4/af_inet.c:425
 sock_release+0x8d/0x1e0 net/socket.c:597
 sock_close+0x16/0x20 net/socket.c:1126
 __fput+0x327/0x7e0 fs/file_table.c:210
 ____fput+0x15/0x20 fs/file_table.c:246
 task_work_run+0x18a/0x260 kernel/task_work.c:116
 exit_task_work include/linux/task_work.h:21 [inline]
 do_exit+0xa32/0x1b10 kernel/exit.c:865
 do_group_exit+0x149/0x400 kernel/exit.c:969
 get_signal+0x7e8/0x17e0 kernel/signal.c:2330
 do_signal+0x94/0x1ee0 arch/x86/kernel/signal.c:808
 exit_to_usermode_loop+0x21c/0x2d0 arch/x86/entry/common.c:157
 prepare_exit_to_usermode arch/x86/entry/common.c:194 [inline]
 syscall_return_slowpath+0x3a7/0x450 arch/x86/entry/common.c:263

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 net/dccp/proto.c |    5 +----
 1 file changed, 1 insertion(+), 4 deletions(-)

net/dccp/proto.c +1 -4

@@ -201,10 +201,7 @@ void dccp_destroy_sock(struct sock *sk)
 {
 	struct dccp_sock *dp = dccp_sk(sk);
 
-	/*
-	 * DCCP doesn't use sk_write_queue, just sk_send_head
-	 * for retransmissions
-	 */
+	__skb_queue_purge(&sk->sk_write_queue);
 	if (sk->sk_send_head != NULL) {
 		kfree_skb(sk->sk_send_head);
 		sk->sk_send_head = NULL;

Greg Kroah-Hartman

author maintainer

2017-08-28 08:10 UTC #4 lore raw

PATCH 4/84 dccp: defer ccid_hc_tx_delete() at dismantle time

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

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

From: Eric Dumazet <[email protected]>

[ Upstream commit 120e9dabaf551c6dc03d3a10a1f026376cb1811c ]

syszkaller team reported another problem in DCCP [1]

Problem here is that the structure holding RTO timer (ccid2_hc_tx_rto_expire() handler) is freed too soon.

We can not use del_timer_sync() to cancel the timer
since this timer wants to grab socket lock (that would risk a dead lock)

Solution is to defer the freeing of memory when all references to the socket were released. Socket timers do own a reference, so this should fix the issue.

[1]

==================================================================

BUG: KASAN: use-after-free in ccid2_hc_tx_rto_expire+0x51c/0x5c0 net/dccp/ccids/ccid2.c:144
Read of size 4 at addr ffff8801d2660540 by task kworker/u4:7/3365

CPU: 1 PID: 3365 Comm: kworker/u4:7 Not tainted 4.13.0-rc4+ #3
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Workqueue: events_unbound call_usermodehelper_exec_work
Call Trace:
 <IRQ>
 __dump_stack lib/dump_stack.c:16 [inline]
 dump_stack+0x194/0x257 lib/dump_stack.c:52
 print_address_description+0x73/0x250 mm/kasan/report.c:252
 kasan_report_error mm/kasan/report.c:351 [inline]
 kasan_report+0x24e/0x340 mm/kasan/report.c:409
 __asan_report_load4_noabort+0x14/0x20 mm/kasan/report.c:429
 ccid2_hc_tx_rto_expire+0x51c/0x5c0 net/dccp/ccids/ccid2.c:144
 call_timer_fn+0x233/0x830 kernel/time/timer.c:1268
 expire_timers kernel/time/timer.c:1307 [inline]
 __run_timers+0x7fd/0xb90 kernel/time/timer.c:1601
 run_timer_softirq+0x21/0x80 kernel/time/timer.c:1614
 __do_softirq+0x2f5/0xba3 kernel/softirq.c:284
 invoke_softirq kernel/softirq.c:364 [inline]
 irq_exit+0x1cc/0x200 kernel/softirq.c:405
 exiting_irq arch/x86/include/asm/apic.h:638 [inline]
 smp_apic_timer_interrupt+0x76/0xa0 arch/x86/kernel/apic/apic.c:1044
 apic_timer_interrupt+0x93/0xa0 arch/x86/entry/entry_64.S:702
RIP: 0010:arch_local_irq_enable arch/x86/include/asm/paravirt.h:824 [inline]
RIP: 0010:__raw_write_unlock_irq include/linux/rwlock_api_smp.h:267 [inline]
RIP: 0010:_raw_write_unlock_irq+0x56/0x70 kernel/locking/spinlock.c:343
RSP: 0018:ffff8801cd50eaa8 EFLAGS: 00000286 ORIG_RAX: ffffffffffffff10
RAX: dffffc0000000000 RBX: ffffffff85a090c0 RCX: 0000000000000006
RDX: 1ffffffff0b595f3 RSI: 1ffff1003962f989 RDI: ffffffff85acaf98
RBP: ffff8801cd50eab0 R08: 0000000000000001 R09: 0000000000000000
R10: 0000000000000000 R11: 0000000000000000 R12: ffff8801cc96ea60
R13: dffffc0000000000 R14: ffff8801cc96e4c0 R15: ffff8801cc96e4c0
 </IRQ>
 release_task+0xe9e/0x1a40 kernel/exit.c:220
 wait_task_zombie kernel/exit.c:1162 [inline]
 wait_consider_task+0x29b8/0x33c0 kernel/exit.c:1389
 do_wait_thread kernel/exit.c:1452 [inline]
 do_wait+0x441/0xa90 kernel/exit.c:1523
 kernel_wait4+0x1f5/0x370 kernel/exit.c:1665
 SYSC_wait4+0x134/0x140 kernel/exit.c:1677
 SyS_wait4+0x2c/0x40 kernel/exit.c:1673
 call_usermodehelper_exec_sync kernel/kmod.c:286 [inline]
 call_usermodehelper_exec_work+0x1a0/0x2c0 kernel/kmod.c:323
 process_one_work+0xbf3/0x1bc0 kernel/workqueue.c:2097
 worker_thread+0x223/0x1860 kernel/workqueue.c:2231
 kthread+0x35e/0x430 kernel/kthread.c:231
 ret_from_fork+0x2a/0x40 arch/x86/entry/entry_64.S:425

Allocated by task 21267:
 save_stack_trace+0x16/0x20 arch/x86/kernel/stacktrace.c:59
 save_stack+0x43/0xd0 mm/kasan/kasan.c:447
 set_track mm/kasan/kasan.c:459 [inline]
 kasan_kmalloc+0xad/0xe0 mm/kasan/kasan.c:551
 kasan_slab_alloc+0x12/0x20 mm/kasan/kasan.c:489
 kmem_cache_alloc+0x127/0x750 mm/slab.c:3561
 ccid_new+0x20e/0x390 net/dccp/ccid.c:151
 dccp_hdlr_ccid+0x27/0x140 net/dccp/feat.c:44
 __dccp_feat_activate+0x142/0x2a0 net/dccp/feat.c:344
 dccp_feat_activate_values+0x34e/0xa90 net/dccp/feat.c:1538
 dccp_rcv_request_sent_state_process net/dccp/input.c:472 [inline]
 dccp_rcv_state_process+0xed1/0x1620 net/dccp/input.c:677
 dccp_v4_do_rcv+0xeb/0x160 net/dccp/ipv4.c:679
 sk_backlog_rcv include/net/sock.h:911 [inline]
 __release_sock+0x124/0x360 net/core/sock.c:2269
 release_sock+0xa4/0x2a0 net/core/sock.c:2784
 inet_wait_for_connect net/ipv4/af_inet.c:557 [inline]
 __inet_stream_connect+0x671/0xf00 net/ipv4/af_inet.c:643
 inet_stream_connect+0x58/0xa0 net/ipv4/af_inet.c:682
 SYSC_connect+0x204/0x470 net/socket.c:1642
 SyS_connect+0x24/0x30 net/socket.c:1623
 entry_SYSCALL_64_fastpath+0x1f/0xbe

Freed by task 3049:
 save_stack_trace+0x16/0x20 arch/x86/kernel/stacktrace.c:59
 save_stack+0x43/0xd0 mm/kasan/kasan.c:447
 set_track mm/kasan/kasan.c:459 [inline]
 kasan_slab_free+0x71/0xc0 mm/kasan/kasan.c:524
 __cache_free mm/slab.c:3503 [inline]
 kmem_cache_free+0x77/0x280 mm/slab.c:3763
 ccid_hc_tx_delete+0xc5/0x100 net/dccp/ccid.c:190
 dccp_destroy_sock+0x1d1/0x2b0 net/dccp/proto.c:225
 inet_csk_destroy_sock+0x166/0x3f0 net/ipv4/inet_connection_sock.c:833
 dccp_done+0xb7/0xd0 net/dccp/proto.c:145
 dccp_time_wait+0x13d/0x300 net/dccp/minisocks.c:72
 dccp_rcv_reset+0x1d1/0x5b0 net/dccp/input.c:160
 dccp_rcv_state_process+0x8fc/0x1620 net/dccp/input.c:663
 dccp_v4_do_rcv+0xeb/0x160 net/dccp/ipv4.c:679
 sk_backlog_rcv include/net/sock.h:911 [inline]
 __sk_receive_skb+0x33e/0xc00 net/core/sock.c:521
 dccp_v4_rcv+0xef1/0x1c00 net/dccp/ipv4.c:871
 ip_local_deliver_finish+0x2e2/0xba0 net/ipv4/ip_input.c:216
 NF_HOOK include/linux/netfilter.h:248 [inline]
 ip_local_deliver+0x1ce/0x6d0 net/ipv4/ip_input.c:257
 dst_input include/net/dst.h:477 [inline]
 ip_rcv_finish+0x8db/0x19c0 net/ipv4/ip_input.c:397
 NF_HOOK include/linux/netfilter.h:248 [inline]
 ip_rcv+0xc3f/0x17d0 net/ipv4/ip_input.c:488
 __netif_receive_skb_core+0x19af/0x33d0 net/core/dev.c:4417
 __netif_receive_skb+0x2c/0x1b0 net/core/dev.c:4455
 process_backlog+0x203/0x740 net/core/dev.c:5130
 napi_poll net/core/dev.c:5527 [inline]
 net_rx_action+0x792/0x1910 net/core/dev.c:5593
 __do_softirq+0x2f5/0xba3 kernel/softirq.c:284

The buggy address belongs to the object at ffff8801d2660100
 which belongs to the cache ccid2_hc_tx_sock of size 1240
The buggy address is located 1088 bytes inside of
 1240-byte region [ffff8801d2660100, ffff8801d26605d8)
The buggy address belongs to the page:
page:ffffea0007499800 count:1 mapcount:0 mapping:ffff8801d2660100 index:0x0 compound_mapcount: 0
flags: 0x200000000008100(slab|head)
raw: 0200000000008100 ffff8801d2660100 0000000000000000 0000000100000005
raw: ffffea00075271a0 ffffea0007538820 ffff8801d3aef9c0 0000000000000000
page dumped because: kasan: bad access detected

Memory state around the buggy address:
 ffff8801d2660400: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
 ffff8801d2660480: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
>ffff8801d2660500: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
                                           ^
 ffff8801d2660580: fb fb fb fb fb fb fb fb fb fb fb fc fc fc fc fc
 ffff8801d2660600: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc
==================================================================

Cc Gerrit Renker <[email protected]>

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 net/dccp/proto.c |   14 ++++++++++++--
 1 file changed, 12 insertions(+), 2 deletions(-)

net/dccp/proto.c +12 -2

@@ -24,6 +24,7 @@
 #include <net/checksum.h>
 
 #include <net/inet_sock.h>
+#include <net/inet_common.h>
 #include <net/sock.h>
 #include <net/xfrm.h>

@@ -170,6 +171,15 @@ const char *dccp_packet_name(const int t
 
 EXPORT_SYMBOL_GPL(dccp_packet_name);
 
+static void dccp_sk_destruct(struct sock *sk)
+{
+	struct dccp_sock *dp = dccp_sk(sk);
+
+	ccid_hc_tx_delete(dp->dccps_hc_tx_ccid, sk);
+	dp->dccps_hc_tx_ccid = NULL;
+	inet_sock_destruct(sk);
+}
+
 int dccp_init_sock(struct sock *sk, const __u8 ctl_sock_initialized)
 {
 	struct dccp_sock *dp = dccp_sk(sk);

@@ -179,6 +189,7 @@ int dccp_init_sock(struct sock *sk, cons
 	icsk->icsk_syn_retries	= sysctl_dccp_request_retries;
 	sk->sk_state		= DCCP_CLOSED;
 	sk->sk_write_space	= dccp_write_space;
+	sk->sk_destruct		= dccp_sk_destruct;
 	icsk->icsk_sync_mss	= dccp_sync_mss;
 	dp->dccps_mss_cache	= 536;
 	dp->dccps_rate_last	= jiffies;

@@ -219,8 +230,7 @@ void dccp_destroy_sock(struct sock *sk)
 		dp->dccps_hc_rx_ackvec = NULL;
 	}
 	ccid_hc_rx_delete(dp->dccps_hc_rx_ccid, sk);
-	ccid_hc_tx_delete(dp->dccps_hc_tx_ccid, sk);
-	dp->dccps_hc_rx_ccid = dp->dccps_hc_tx_ccid = NULL;
+	dp->dccps_hc_rx_ccid = NULL;
 
 	/* clean up feature negotiation state */
 	dccp_feat_list_purge(&dp->dccps_featneg);

Greg Kroah-Hartman

author maintainer

2017-08-28 08:10 UTC #5 lore raw

PATCH 5/84 ipv4: fix NULL dereference in free_fib_info_rcu()

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

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

From: Eric Dumazet <[email protected]>

[ Upstream commit 187e5b3ac84d3421d2de3aca949b2791fbcad554 ]

If fi->fib_metrics could not be allocated in fib_create_info() we attempt to dereference a NULL pointer in free_fib_info_rcu() :

    m = fi->fib_metrics;
    if (m != &dst_default_metrics && atomic_dec_and_test(&m->refcnt))
            kfree(m);

Before my recent patch, we used to call kfree(NULL) and nothing wrong happened.

Instead of using RCU to defer freeing while we are under memory stress, it seems better to take immediate action.

This was reported by syzkaller team.

Fixes 3fb07daff8e9 ("ipv4: add reference counting to metrics")

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 net/ipv4/fib_semantics.c |   12 +++++++-----
 1 file changed, 7 insertions(+), 5 deletions(-)

net/ipv4/fib_semantics.c +7 -5

@@ -1044,15 +1044,17 @@ struct fib_info *fib_create_info(struct
 	fi = kzalloc(sizeof(*fi)+nhs*sizeof(struct fib_nh), GFP_KERNEL);
 	if (!fi)
 		goto failure;
-	fib_info_cnt++;
 	if (cfg->fc_mx) {
 		fi->fib_metrics = kzalloc(sizeof(*fi->fib_metrics), GFP_KERNEL);
-		if (!fi->fib_metrics)
-			goto failure;
+		if (unlikely(!fi->fib_metrics)) {
+			kfree(fi);
+			return ERR_PTR(err);
+		}
 		atomic_set(&fi->fib_metrics->refcnt, 1);
-	} else
+	} else {
 		fi->fib_metrics = (struct dst_metrics *)&dst_default_metrics;
-
+	}
+	fib_info_cnt++;
 	fi->fib_net = net;
 	fi->fib_protocol = cfg->fc_protocol;
 	fi->fib_scope = cfg->fc_scope;

Greg Kroah-Hartman

author maintainer

2017-08-28 08:04 UTC #6 lore raw

PATCH 6/84 net_sched/sfq: update hierarchical backlog when drop packet

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

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

From: Konstantin Khlebnikov <[email protected]>

[ Upstream commit 325d5dc3f7e7c2840b65e4a2988c082c2c0025c5 ]

When sfq_enqueue() drops head packet or packet from another queue it have to update backlog at upper qdiscs too.

Fixes 2ccccf5fb43f ("net_sched: update hierarchical backlog too")

Signed-off-by Konstantin Khlebnikov <[email protected]>

Acked-by Eric Dumazet <[email protected]>

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 net/sched/sch_sfq.c |    5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

net/sched/sch_sfq.c +4 -1

@@ -434,6 +434,7 @@ congestion_drop:
 		qdisc_drop(head, sch, to_free);
 
 		slot_queue_add(slot, skb);
+		qdisc_tree_reduce_backlog(sch, 0, delta);
 		return NET_XMIT_CN;
 	}

@@ -465,8 +466,10 @@ enqueue:
 	/* Return Congestion Notification only if we dropped a packet
 	 * from this flow.
 	 */
-	if (qlen != slot->qlen)
+	if (qlen != slot->qlen) {
+		qdisc_tree_reduce_backlog(sch, 0, dropped - qdisc_pkt_len(skb));
 		return NET_XMIT_CN;
+	}
 
 	/* As we dropped a packet, better let upper stack know this */
 	qdisc_tree_reduce_backlog(sch, 1, dropped);

Greg Kroah-Hartman

author maintainer

2017-08-28 08:10 UTC #7 lore raw

PATCH 7/84 net_sched: remove warning from qdisc_hash_add

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

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

From: Konstantin Khlebnikov <[email protected]>

[ Upstream commit c90e95147c27b1780e76c6e8fea1b5c78d7d387f ]

It was added in commit e57a784d8cae ("pkt_sched: set root qdisc before change() in attach_default_qdiscs()") to hide duplicates from "tc qdisc show" for incative deivices.

After 59cc1f61f ("net: sched: convert qdisc linked list to hashtable") it triggered when classful qdisc is added to inactive device because default qdiscs are added before switching root qdisc.

Anyway after commit ea3274695353 ("net: sched: avoid duplicates in qdisc dump") duplicates are filtered right in dumper.

Signed-off-by Konstantin Khlebnikov <[email protected]>

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 net/sched/sch_api.c |    3 ---
 1 file changed, 3 deletions(-)

net/sched/sch_api.c +0 -3

@@ -277,9 +277,6 @@ static struct Qdisc *qdisc_match_from_ro
 void qdisc_hash_add(struct Qdisc *q)
 {
 	if ((q->parent != TC_H_ROOT) && !(q->flags & TCQ_F_INGRESS)) {
-		struct Qdisc *root = qdisc_dev(q)->qdisc;
-
-		WARN_ON_ONCE(root == &noop_qdisc);
 		ASSERT_RTNL();
 		hash_add_rcu(qdisc_dev(q)->qdisc_hash, &q->hash, q->handle);
 	}

Greg Kroah-Hartman

author maintainer

2017-08-28 08:04 UTC #8 lore raw

PATCH 8/84 bpf: fix bpf_trace_printk on 32 bit archs

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

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

From: Daniel Borkmann <[email protected]>

[ Upstream commit 88a5c690b66110ad255380d8f629c629cf6ca559 ]

James reported that on MIPS32 bpf_trace_printk() is currently broken while MIPS64 works fine:

bpf_trace_printk() uses conditional operators to attempt to pass different types to __trace_printk() depending on the format operators. This doesn't work as intended on 32-bit architectures where u32 and long are passed differently to u64, since the result of C conditional operators follows the "usual arithmetic conversions" rules, such that the values passed to __trace_printk() will always be u64 [causing issues later in the va_list handling for vscnprintf()].

For example the samples/bpf/tracex5 test printed lines like below on MIPS32, where the fd and buf have come from the u64 fd argument, and the size from the buf argument:

    [...] 1180.941542: 0x00000001: write(fd=1, buf=  (null), size=6258688)

Instead of this:

    [...] 1625.616026: 0x00000001: write(fd=1, buf=009e4000, size=512)

One way to get it working is to expand various combinations of argument types into 8 different combinations for 32 bit and 64 bit kernels. Fix tested by James on MIPS32 and MIPS64 as well that it resolves the issue.

Fixes 9c959c863f82 ("tracing: Allow BPF programs to call bpf_trace_printk()")

Reported-by James Hogan <[email protected]>

Tested-by James Hogan <[email protected]>

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 kernel/trace/bpf_trace.c |   34 ++++++++++++++++++++++++++++++----
 1 file changed, 30 insertions(+), 4 deletions(-)

kernel/trace/bpf_trace.c +30 -4

@@ -203,10 +203,36 @@ BPF_CALL_5(bpf_trace_printk, char *, fmt
 		fmt_cnt++;
 	}
 
-	return __trace_printk(1/* fake ip will not be printed */, fmt,
-			      mod[0] == 2 ? arg1 : mod[0] == 1 ? (long) arg1 : (u32) arg1,
-			      mod[1] == 2 ? arg2 : mod[1] == 1 ? (long) arg2 : (u32) arg2,
-			      mod[2] == 2 ? arg3 : mod[2] == 1 ? (long) arg3 : (u32) arg3);
+/* Horrid workaround for getting va_list handling working with different
+ * argument type combinations generically for 32 and 64 bit archs.
+ */
+#define __BPF_TP_EMIT()	__BPF_ARG3_TP()
+#define __BPF_TP(...)							\
+	__trace_printk(1 /* Fake ip will not be printed. */,		\
+		       fmt, ##__VA_ARGS__)
+
+#define __BPF_ARG1_TP(...)						\
+	((mod[0] == 2 || (mod[0] == 1 && __BITS_PER_LONG == 64))	\
+	  ? __BPF_TP(arg1, ##__VA_ARGS__)				\
+	  : ((mod[0] == 1 || (mod[0] == 0 && __BITS_PER_LONG == 32))	\
+	      ? __BPF_TP((long)arg1, ##__VA_ARGS__)			\
+	      : __BPF_TP((u32)arg1, ##__VA_ARGS__)))
+
+#define __BPF_ARG2_TP(...)						\
+	((mod[1] == 2 || (mod[1] == 1 && __BITS_PER_LONG == 64))	\
+	  ? __BPF_ARG1_TP(arg2, ##__VA_ARGS__)				\
+	  : ((mod[1] == 1 || (mod[1] == 0 && __BITS_PER_LONG == 32))	\
+	      ? __BPF_ARG1_TP((long)arg2, ##__VA_ARGS__)		\
+	      : __BPF_ARG1_TP((u32)arg2, ##__VA_ARGS__)))
+
+#define __BPF_ARG3_TP(...)						\
+	((mod[2] == 2 || (mod[2] == 1 && __BITS_PER_LONG == 64))	\
+	  ? __BPF_ARG2_TP(arg3, ##__VA_ARGS__)				\
+	  : ((mod[2] == 1 || (mod[2] == 0 && __BITS_PER_LONG == 32))	\
+	      ? __BPF_ARG2_TP((long)arg3, ##__VA_ARGS__)		\
+	      : __BPF_ARG2_TP((u32)arg3, ##__VA_ARGS__)))
+
+	return __BPF_TP_EMIT();
 }
 
 static const struct bpf_func_proto bpf_trace_printk_proto = {

Greg Kroah-Hartman

author maintainer

2017-08-28 08:04 UTC #9 lore raw

PATCH 9/84 openvswitch: fix skb_panic due to the incorrect actions attrlen

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

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

From: Liping Zhang <[email protected]>

[ Upstream commit 494bea39f3201776cdfddc232705f54a0bd210c4 ]

For sw_flow_actions, the actions_len only represents the kernel part's size, and when we dump the actions to the userspace, we will do the convertions, so it's true size may become bigger than the actions_len.

But unfortunately, for OVS_PACKET_ATTR_ACTIONS, we use the actions_len to alloc the skbuff, so the user_skb's size may become insufficient and oops will happen like this:
skbuff: skb_over_panic: text:ffffffff8148fabf len:1749 put:157 head:
ffff881300f39000 data:ffff881300f39000 tail:0x6d5 end:0x6c0 dev:<NULL>

  ------------[ cut here ]------------
  kernel BUG at net/core/skbuff.c:129!
  [...]
  Call Trace:
   <IRQ>
   [<ffffffff8148be82>] skb_put+0x43/0x44
   [<ffffffff8148fabf>] skb_zerocopy+0x6c/0x1f4
   [<ffffffffa0290d36>] queue_userspace_packet+0x3a3/0x448 [openvswitch]
   [<ffffffffa0292023>] ovs_dp_upcall+0x30/0x5c [openvswitch]
   [<ffffffffa028d435>] output_userspace+0x132/0x158 [openvswitch]
   [<ffffffffa01e6890>] ? ip6_rcv_finish+0x74/0x77 [ipv6]
   [<ffffffffa028e277>] do_execute_actions+0xcc1/0xdc8 [openvswitch]
   [<ffffffffa028e3f2>] ovs_execute_actions+0x74/0x106 [openvswitch]
   [<ffffffffa0292130>] ovs_dp_process_packet+0xe1/0xfd [openvswitch]
   [<ffffffffa0292b77>] ? key_extract+0x63c/0x8d5 [openvswitch]
   [<ffffffffa029848b>] ovs_vport_receive+0xa1/0xc3 [openvswitch]
  [...]

Also we can find that the actions_len is much little than the orig_len:
crash> struct sw_flow_actions 0xffff8812f539d000

  struct sw_flow_actions {
    rcu = {
      next = 0xffff8812f5398800,
      func = 0xffffe3b00035db32
    },
    orig_len = 1384,
    actions_len = 592,
    actions = 0xffff8812f539d01c

}

So as a quick fix, use the orig_len instead of the actions_len to alloc the user_skb.

Last, this oops happened on our system running a relative old kernel, but the same risk still exists on the mainline, since we use the wrong actions_len from the beginning.

Fixes ccea74457bbd ("openvswitch: include datapath actions with sampled-packet upcall to userspace")

Cc Neil McKee <[email protected]>

Signed-off-by Liping Zhang <[email protected]>

Acked-by Pravin B Shelar <[email protected]>

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 net/openvswitch/actions.c  |    1 +
 net/openvswitch/datapath.c |    7 ++++---
 net/openvswitch/datapath.h |    2 ++
 3 files changed, 7 insertions(+), 3 deletions(-)

net/openvswitch/actions.c +1 -0

@@ -1240,6 +1240,7 @@ int ovs_execute_actions(struct datapath
 		goto out;
 	}
 
+	OVS_CB(skb)->acts_origlen = acts->orig_len;
 	err = do_execute_actions(dp, skb, key,
 				 acts->actions, acts->actions_len);

net/openvswitch/datapath.c +4 -3

@@ -383,7 +383,7 @@ static int queue_gso_packets(struct data
 }
 
 static size_t upcall_msg_size(const struct dp_upcall_info *upcall_info,
-			      unsigned int hdrlen)
+			      unsigned int hdrlen, int actions_attrlen)
 {
 	size_t size = NLMSG_ALIGN(sizeof(struct ovs_header))
 		+ nla_total_size(hdrlen) /* OVS_PACKET_ATTR_PACKET */

@@ -400,7 +400,7 @@ static size_t upcall_msg_size(const stru
 
 	/* OVS_PACKET_ATTR_ACTIONS */
 	if (upcall_info->actions_len)
-		size += nla_total_size(upcall_info->actions_len);
+		size += nla_total_size(actions_attrlen);
 
 	/* OVS_PACKET_ATTR_MRU */
 	if (upcall_info->mru)

@@ -467,7 +467,8 @@ static int queue_userspace_packet(struct
 	else
 		hlen = skb->len;
 
-	len = upcall_msg_size(upcall_info, hlen - cutlen);
+	len = upcall_msg_size(upcall_info, hlen - cutlen,
+			      OVS_CB(skb)->acts_origlen);
 	user_skb = genlmsg_new(len, GFP_ATOMIC);
 	if (!user_skb) {
 		err = -ENOMEM;

net/openvswitch/datapath.h +2 -0

@@ -100,12 +100,14 @@ struct datapath {
  * @input_vport: The original vport packet came in on. This value is cached
  * when a packet is received by OVS.
  * @mru: The maximum received fragement size; 0 if the packet is not
+ * @acts_origlen: The netlink size of the flow actions applied to this skb.
  * @cutlen: The number of bytes from the packet end to be removed.
  * fragmented.
  */
 struct ovs_skb_cb {
 	struct vport		*input_vport;
 	u16			mru;
+	u16			acts_origlen;
 	u32			cutlen;
 };
 #define OVS_CB(skb) ((struct ovs_skb_cb *)(skb)->cb)

Greg Kroah-Hartman

author maintainer

2017-08-28 08:12 UTC #10 lore raw

PATCH 10/84 ptr_ring: use kmalloc_array()

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

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

From: Eric Dumazet <[email protected]>

[ Upstream commit 81fbfe8adaf38d4f5a98c19bebfd41c5d6acaee8 ]

As found by syzkaller, malicious users can set whatever tx_queue_len on a tun device and eventually crash the kernel.

Lets remove the ALIGN(XXX, SMP_CACHE_BYTES) thing since a small ring buffer is not fast anyway.

Fixes 2e0ab8ca83c1 ("ptr_ring: array based FIFO for pointers")

Cc Michael S. Tsirkin <[email protected]>

Cc Jason Wang <[email protected]>

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 include/linux/ptr_ring.h  |    9 +++++----
 include/linux/skb_array.h |    3 ++-
 2 files changed, 7 insertions(+), 5 deletions(-)

include/linux/ptr_ring.h +5 -4

@@ -340,9 +340,9 @@ static inline void *ptr_ring_consume_bh(
 	__PTR_RING_PEEK_CALL_v; \
 })
 
-static inline void **__ptr_ring_init_queue_alloc(int size, gfp_t gfp)
+static inline void **__ptr_ring_init_queue_alloc(unsigned int size, gfp_t gfp)
 {
-	return kzalloc(ALIGN(size * sizeof(void *), SMP_CACHE_BYTES), gfp);
+	return kcalloc(size, sizeof(void *), gfp);
 }
 
 static inline int ptr_ring_init(struct ptr_ring *r, int size, gfp_t gfp)

@@ -417,7 +417,8 @@ static inline int ptr_ring_resize(struct
  * In particular if you consume ring in interrupt or BH context, you must
  * disable interrupts/BH when doing so.
  */
-static inline int ptr_ring_resize_multiple(struct ptr_ring **rings, int nrings,
+static inline int ptr_ring_resize_multiple(struct ptr_ring **rings,
+					   unsigned int nrings,
 					   int size,
 					   gfp_t gfp, void (*destroy)(void *))
 {

@@ -425,7 +426,7 @@ static inline int ptr_ring_resize_multip
 	void ***queues;
 	int i;
 
-	queues = kmalloc(nrings * sizeof *queues, gfp);
+	queues = kmalloc_array(nrings, sizeof(*queues), gfp);
 	if (!queues)
 		goto noqueues;

include/linux/skb_array.h +2 -1

@@ -162,7 +162,8 @@ static inline int skb_array_resize(struc
 }
 
 static inline int skb_array_resize_multiple(struct skb_array **rings,
-					    int nrings, int size, gfp_t gfp)
+					    int nrings, unsigned int size,
+					    gfp_t gfp)
 {
 	BUILD_BUG_ON(offsetof(struct skb_array, ring));
 	return ptr_ring_resize_multiple((struct ptr_ring **)rings,

Greg Kroah-Hartman

author maintainer

2017-08-28 08:10 UTC #11 lore raw

PATCH 11/84 ipv4: better IP_MAX_MTU enforcement

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

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

From: Eric Dumazet <[email protected]>

[ Upstream commit c780a049f9bf442314335372c9abc4548bfe3e44 ]

While working on yet another syzkaller report, I found that our IP_MAX_MTU enforcements were not properly done.

gcc seems to reload dev->mtu for min(dev->mtu, IP_MAX_MTU), and final result can be bigger than IP_MAX_MTU :/

This is a problem because device mtu can be changed on other cpus or threads.

While this patch does not fix the issue I am working on, it is probably worth addressing it.

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 include/net/ip.h |    4 ++--
 net/ipv4/route.c |    2 +-
 2 files changed, 3 insertions(+), 3 deletions(-)

include/net/ip.h +2 -2

@@ -339,7 +339,7 @@ static inline unsigned int ip_dst_mtu_ma
 	    !forwarding)
 		return dst_mtu(dst);
 
-	return min(dst->dev->mtu, IP_MAX_MTU);
+	return min(READ_ONCE(dst->dev->mtu), IP_MAX_MTU);
 }
 
 static inline unsigned int ip_skb_dst_mtu(struct sock *sk,

@@ -351,7 +351,7 @@ static inline unsigned int ip_skb_dst_mt
 		return ip_dst_mtu_maybe_forward(skb_dst(skb), forwarding);
 	}
 
-	return min(skb_dst(skb)->dev->mtu, IP_MAX_MTU);
+	return min(READ_ONCE(skb_dst(skb)->dev->mtu), IP_MAX_MTU);
 }
 
 u32 ip_idents_reserve(u32 hash, int segs);

net/ipv4/route.c +1 -1

@@ -1247,7 +1247,7 @@ static unsigned int ipv4_mtu(const struc
 	if (mtu)
 		return mtu;
 
-	mtu = dst->dev->mtu;
+	mtu = READ_ONCE(dst->dev->mtu);
 
 	if (unlikely(dst_metric_locked(dst, RTAX_MTU))) {
 		if (rt->rt_uses_gateway && mtu > 576)

Greg Kroah-Hartman

author maintainer

2017-08-28 08:11 UTC #12 lore raw

PATCH 12/84 nfp: fix infinite loop on umapping cleanup

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

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

From: Colin Ian King <[email protected]>

[ Upstream commit eac2c68d663effb077210218788952b5a0c1f60e ]

The while loop that performs the dma page unmapping never decrements index counter f and hence loops forever. Fix this with a pre-decrement on f.

Detected by CoverityScan, CID#1357309 ("Infinite loop")

Fixes 4c3523623dc0 ("net: add driver for Netronome NFP4000/NFP6000 NIC VFs")

Signed-off-by Colin Ian King <[email protected]>

Acked-by Jakub Kicinski <[email protected]>

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 drivers/net/ethernet/netronome/nfp/nfp_net_common.c |    3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

drivers/net/ethernet/netronome/nfp/nfp_net_common.c +1 -2

@@ -871,8 +871,7 @@ static int nfp_net_tx(struct sk_buff *sk
 	return NETDEV_TX_OK;
 
 err_unmap:
-	--f;
-	while (f >= 0) {
+	while (--f >= 0) {
 		frag = &skb_shinfo(skb)->frags[f];
 		dma_unmap_page(&nn->pdev->dev,
 			       tx_ring->txbufs[wr_idx].dma_addr,

Greg Kroah-Hartman

author maintainer

2017-08-28 08:04 UTC #13 lore raw

PATCH 13/84 sctp: fully initialize the IPv6 address in sctp_v6_to_addr()

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

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

From: Alexander Potapenko <[email protected]>

[ Upstream commit 15339e441ec46fbc3bf3486bb1ae4845b0f1bb8d ]

KMSAN reported use of uninitialized sctp_addr->v4.sin_addr.s_addr and sctp_addr->v6.sin6_scope_id in sctp_v6_cmp_addr() (see below). Make sure all fields of an IPv6 address are initialized, which guarantees that the IPv4 fields are also initialized.

==================================================================

 BUG: KMSAN: use of uninitialized memory in sctp_v6_cmp_addr+0x8d4/0x9f0
 net/sctp/ipv6.c:517
 CPU: 2 PID: 31056 Comm: syz-executor1 Not tainted 4.11.0-rc5+ #2944
 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Bochs
 01/01/2011
 Call Trace:
  dump_stack+0x172/0x1c0 lib/dump_stack.c:42
  is_logbuf_locked mm/kmsan/kmsan.c:59 [inline]
  kmsan_report+0x12a/0x180 mm/kmsan/kmsan.c:938
  native_save_fl arch/x86/include/asm/irqflags.h:18 [inline]
  arch_local_save_flags arch/x86/include/asm/irqflags.h:72 [inline]
  arch_local_irq_save arch/x86/include/asm/irqflags.h:113 [inline]
  __msan_warning_32+0x61/0xb0 mm/kmsan/kmsan_instr.c:467
  sctp_v6_cmp_addr+0x8d4/0x9f0 net/sctp/ipv6.c:517
  sctp_v6_get_dst+0x8c7/0x1630 net/sctp/ipv6.c:290
  sctp_transport_route+0x101/0x570 net/sctp/transport.c:292
  sctp_assoc_add_peer+0x66d/0x16f0 net/sctp/associola.c:651
  sctp_sendmsg+0x35a5/0x4f90 net/sctp/socket.c:1871
  inet_sendmsg+0x498/0x670 net/ipv4/af_inet.c:762
  sock_sendmsg_nosec net/socket.c:633 [inline]
  sock_sendmsg net/socket.c:643 [inline]
  SYSC_sendto+0x608/0x710 net/socket.c:1696
  SyS_sendto+0x8a/0xb0 net/socket.c:1664
  entry_SYSCALL_64_fastpath+0x13/0x94
 RIP: 0033:0x44b479
 RSP: 002b:00007f6213f21c08 EFLAGS: 00000286 ORIG_RAX: 000000000000002c
 RAX: ffffffffffffffda RBX: 0000000020000000 RCX: 000000000044b479
 RDX: 0000000000000041 RSI: 0000000020edd000 RDI: 0000000000000006
 RBP: 00000000007080a8 R08: 0000000020b85fe4 R09: 000000000000001c
 R10: 0000000000040005 R11: 0000000000000286 R12: 00000000ffffffff
 R13: 0000000000003760 R14: 00000000006e5820 R15: 0000000000ff8000
 origin description: ----dst_saddr@sctp_v6_get_dst
 local variable created at:
  sk_fullsock include/net/sock.h:2321 [inline]
  inet6_sk include/linux/ipv6.h:309 [inline]
  sctp_v6_get_dst+0x91/0x1630 net/sctp/ipv6.c:241
  sctp_transport_route+0x101/0x570 net/sctp/transport.c:292
==================================================================
 BUG: KMSAN: use of uninitialized memory in sctp_v6_cmp_addr+0x8d4/0x9f0
 net/sctp/ipv6.c:517
 CPU: 2 PID: 31056 Comm: syz-executor1 Not tainted 4.11.0-rc5+ #2944
 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Bochs
 01/01/2011
 Call Trace:
  dump_stack+0x172/0x1c0 lib/dump_stack.c:42
  is_logbuf_locked mm/kmsan/kmsan.c:59 [inline]
  kmsan_report+0x12a/0x180 mm/kmsan/kmsan.c:938
  native_save_fl arch/x86/include/asm/irqflags.h:18 [inline]
  arch_local_save_flags arch/x86/include/asm/irqflags.h:72 [inline]
  arch_local_irq_save arch/x86/include/asm/irqflags.h:113 [inline]
  __msan_warning_32+0x61/0xb0 mm/kmsan/kmsan_instr.c:467
  sctp_v6_cmp_addr+0x8d4/0x9f0 net/sctp/ipv6.c:517
  sctp_v6_get_dst+0x8c7/0x1630 net/sctp/ipv6.c:290
  sctp_transport_route+0x101/0x570 net/sctp/transport.c:292
  sctp_assoc_add_peer+0x66d/0x16f0 net/sctp/associola.c:651
  sctp_sendmsg+0x35a5/0x4f90 net/sctp/socket.c:1871
  inet_sendmsg+0x498/0x670 net/ipv4/af_inet.c:762
  sock_sendmsg_nosec net/socket.c:633 [inline]
  sock_sendmsg net/socket.c:643 [inline]
  SYSC_sendto+0x608/0x710 net/socket.c:1696
  SyS_sendto+0x8a/0xb0 net/socket.c:1664
  entry_SYSCALL_64_fastpath+0x13/0x94
 RIP: 0033:0x44b479
 RSP: 002b:00007f6213f21c08 EFLAGS: 00000286 ORIG_RAX: 000000000000002c
 RAX: ffffffffffffffda RBX: 0000000020000000 RCX: 000000000044b479
 RDX: 0000000000000041 RSI: 0000000020edd000 RDI: 0000000000000006
 RBP: 00000000007080a8 R08: 0000000020b85fe4 R09: 000000000000001c
 R10: 0000000000040005 R11: 0000000000000286 R12: 00000000ffffffff
 R13: 0000000000003760 R14: 00000000006e5820 R15: 0000000000ff8000
 origin description: ----dst_saddr@sctp_v6_get_dst
 local variable created at:
  sk_fullsock include/net/sock.h:2321 [inline]
  inet6_sk include/linux/ipv6.h:309 [inline]
  sctp_v6_get_dst+0x91/0x1630 net/sctp/ipv6.c:241
  sctp_transport_route+0x101/0x570 net/sctp/transport.c:292
==================================================================

Signed-off-by Alexander Potapenko <[email protected]>

Reviewed-by Xin Long <[email protected]>

Acked-by Marcelo Ricardo Leitner <[email protected]>

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 net/sctp/ipv6.c |    2 ++
 1 file changed, 2 insertions(+)

net/sctp/ipv6.c +2 -0

@@ -512,7 +512,9 @@ static void sctp_v6_to_addr(union sctp_a
 {
 	addr->sa.sa_family = AF_INET6;
 	addr->v6.sin6_port = port;
+	addr->v6.sin6_flowinfo = 0;
 	addr->v6.sin6_addr = *saddr;
+	addr->v6.sin6_scope_id = 0;
 }
 
 /* Compare addresses exactly.

Greg Kroah-Hartman

author maintainer

2017-08-28 08:12 UTC #14 lore raw

PATCH 14/84 tipc: fix use-after-free

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

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

From: Eric Dumazet <[email protected]>

[ Upstream commit 5bfd37b4de5c98e86b12bd13be5aa46c7484a125 ]

syszkaller reported use-after-free in tipc [1]

When msg->rep skb is freed, set the pointer to NULL, so that caller does not free it again.

[1]

==================================================================

BUG: KASAN: use-after-free in skb_push+0xd4/0xe0 net/core/skbuff.c:1466
Read of size 8 at addr ffff8801c6e71e90 by task syz-executor5/4115

CPU: 1 PID: 4115 Comm: syz-executor5 Not tainted 4.13.0-rc4+ #32
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
 __dump_stack lib/dump_stack.c:16 [inline]
 dump_stack+0x194/0x257 lib/dump_stack.c:52
 print_address_description+0x73/0x250 mm/kasan/report.c:252
 kasan_report_error mm/kasan/report.c:351 [inline]
 kasan_report+0x24e/0x340 mm/kasan/report.c:409
 __asan_report_load8_noabort+0x14/0x20 mm/kasan/report.c:430
 skb_push+0xd4/0xe0 net/core/skbuff.c:1466
 tipc_nl_compat_recv+0x833/0x18f0 net/tipc/netlink_compat.c:1209
 genl_family_rcv_msg+0x7b7/0xfb0 net/netlink/genetlink.c:598
 genl_rcv_msg+0xb2/0x140 net/netlink/genetlink.c:623
 netlink_rcv_skb+0x216/0x440 net/netlink/af_netlink.c:2397
 genl_rcv+0x28/0x40 net/netlink/genetlink.c:634
 netlink_unicast_kernel net/netlink/af_netlink.c:1265 [inline]
 netlink_unicast+0x4e8/0x6f0 net/netlink/af_netlink.c:1291
 netlink_sendmsg+0xa4a/0xe60 net/netlink/af_netlink.c:1854
 sock_sendmsg_nosec net/socket.c:633 [inline]
 sock_sendmsg+0xca/0x110 net/socket.c:643
 sock_write_iter+0x31a/0x5d0 net/socket.c:898
 call_write_iter include/linux/fs.h:1743 [inline]
 new_sync_write fs/read_write.c:457 [inline]
 __vfs_write+0x684/0x970 fs/read_write.c:470
 vfs_write+0x189/0x510 fs/read_write.c:518
 SYSC_write fs/read_write.c:565 [inline]
 SyS_write+0xef/0x220 fs/read_write.c:557
 entry_SYSCALL_64_fastpath+0x1f/0xbe
RIP: 0033:0x4512e9
RSP: 002b:00007f3bc8184c08 EFLAGS: 00000216 ORIG_RAX: 0000000000000001
RAX: ffffffffffffffda RBX: 0000000000718000 RCX: 00000000004512e9
RDX: 0000000000000020 RSI: 0000000020fdb000 RDI: 0000000000000006
RBP: 0000000000000086 R08: 0000000000000000 R09: 0000000000000000
R10: 0000000000000000 R11: 0000000000000216 R12: 00000000004b5e76
R13: 00007f3bc8184b48 R14: 00000000004b5e86 R15: 0000000000000000

Allocated by task 4115:
 save_stack_trace+0x16/0x20 arch/x86/kernel/stacktrace.c:59
 save_stack+0x43/0xd0 mm/kasan/kasan.c:447
 set_track mm/kasan/kasan.c:459 [inline]
 kasan_kmalloc+0xad/0xe0 mm/kasan/kasan.c:551
 kasan_slab_alloc+0x12/0x20 mm/kasan/kasan.c:489
 kmem_cache_alloc_node+0x13d/0x750 mm/slab.c:3651
 __alloc_skb+0xf1/0x740 net/core/skbuff.c:219
 alloc_skb include/linux/skbuff.h:903 [inline]
 tipc_tlv_alloc+0x26/0xb0 net/tipc/netlink_compat.c:148
 tipc_nl_compat_dumpit+0xf2/0x3c0 net/tipc/netlink_compat.c:248
 tipc_nl_compat_handle net/tipc/netlink_compat.c:1130 [inline]
 tipc_nl_compat_recv+0x756/0x18f0 net/tipc/netlink_compat.c:1199
 genl_family_rcv_msg+0x7b7/0xfb0 net/netlink/genetlink.c:598
 genl_rcv_msg+0xb2/0x140 net/netlink/genetlink.c:623
 netlink_rcv_skb+0x216/0x440 net/netlink/af_netlink.c:2397
 genl_rcv+0x28/0x40 net/netlink/genetlink.c:634
 netlink_unicast_kernel net/netlink/af_netlink.c:1265 [inline]
 netlink_unicast+0x4e8/0x6f0 net/netlink/af_netlink.c:1291
 netlink_sendmsg+0xa4a/0xe60 net/netlink/af_netlink.c:1854
 sock_sendmsg_nosec net/socket.c:633 [inline]
 sock_sendmsg+0xca/0x110 net/socket.c:643
 sock_write_iter+0x31a/0x5d0 net/socket.c:898
 call_write_iter include/linux/fs.h:1743 [inline]
 new_sync_write fs/read_write.c:457 [inline]
 __vfs_write+0x684/0x970 fs/read_write.c:470
 vfs_write+0x189/0x510 fs/read_write.c:518
 SYSC_write fs/read_write.c:565 [inline]
 SyS_write+0xef/0x220 fs/read_write.c:557
 entry_SYSCALL_64_fastpath+0x1f/0xbe

Freed by task 4115:
 save_stack_trace+0x16/0x20 arch/x86/kernel/stacktrace.c:59
 save_stack+0x43/0xd0 mm/kasan/kasan.c:447
 set_track mm/kasan/kasan.c:459 [inline]
 kasan_slab_free+0x71/0xc0 mm/kasan/kasan.c:524
 __cache_free mm/slab.c:3503 [inline]
 kmem_cache_free+0x77/0x280 mm/slab.c:3763
 kfree_skbmem+0x1a1/0x1d0 net/core/skbuff.c:622
 __kfree_skb net/core/skbuff.c:682 [inline]
 kfree_skb+0x165/0x4c0 net/core/skbuff.c:699
 tipc_nl_compat_dumpit+0x36a/0x3c0 net/tipc/netlink_compat.c:260
 tipc_nl_compat_handle net/tipc/netlink_compat.c:1130 [inline]
 tipc_nl_compat_recv+0x756/0x18f0 net/tipc/netlink_compat.c:1199
 genl_family_rcv_msg+0x7b7/0xfb0 net/netlink/genetlink.c:598
 genl_rcv_msg+0xb2/0x140 net/netlink/genetlink.c:623
 netlink_rcv_skb+0x216/0x440 net/netlink/af_netlink.c:2397
 genl_rcv+0x28/0x40 net/netlink/genetlink.c:634
 netlink_unicast_kernel net/netlink/af_netlink.c:1265 [inline]
 netlink_unicast+0x4e8/0x6f0 net/netlink/af_netlink.c:1291
 netlink_sendmsg+0xa4a/0xe60 net/netlink/af_netlink.c:1854
 sock_sendmsg_nosec net/socket.c:633 [inline]
 sock_sendmsg+0xca/0x110 net/socket.c:643
 sock_write_iter+0x31a/0x5d0 net/socket.c:898
 call_write_iter include/linux/fs.h:1743 [inline]
 new_sync_write fs/read_write.c:457 [inline]
 __vfs_write+0x684/0x970 fs/read_write.c:470
 vfs_write+0x189/0x510 fs/read_write.c:518
 SYSC_write fs/read_write.c:565 [inline]
 SyS_write+0xef/0x220 fs/read_write.c:557
 entry_SYSCALL_64_fastpath+0x1f/0xbe

The buggy address belongs to the object at ffff8801c6e71dc0
 which belongs to the cache skbuff_head_cache of size 224
The buggy address is located 208 bytes inside of
 224-byte region [ffff8801c6e71dc0, ffff8801c6e71ea0)
The buggy address belongs to the page:
page:ffffea00071b9c40 count:1 mapcount:0 mapping:ffff8801c6e71000 index:0x0
flags: 0x200000000000100(slab)
raw: 0200000000000100 ffff8801c6e71000 0000000000000000 000000010000000c
raw: ffffea0007224a20 ffff8801d98caf48 ffff8801d9e79040 0000000000000000
page dumped because: kasan: bad access detected

Memory state around the buggy address:
 ffff8801c6e71d80: fc fc fc fc fc fc fc fc fb fb fb fb fb fb fb fb
 ffff8801c6e71e00: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
>ffff8801c6e71e80: fb fb fb fb fc fc fc fc fc fc fc fc fc fc fc fc
                         ^
 ffff8801c6e71f00: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc
 ffff8801c6e71f80: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc
==================================================================

Cc Jon Maloy <[email protected]>

Cc Ying Xue <[email protected]>

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 net/tipc/netlink_compat.c |    6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

net/tipc/netlink_compat.c +4 -2

@@ -258,13 +258,15 @@ static int tipc_nl_compat_dumpit(struct
 	arg = nlmsg_new(0, GFP_KERNEL);
 	if (!arg) {
 		kfree_skb(msg->rep);
+		msg->rep = NULL;
 		return -ENOMEM;
 	}
 
 	err = __tipc_nl_compat_dumpit(cmd, msg, arg);
-	if (err)
+	if (err) {
 		kfree_skb(msg->rep);
-
+		msg->rep = NULL;
+	}
 	kfree_skb(arg);
 
 	return err;

Greg Kroah-Hartman

author maintainer

2017-08-28 08:12 UTC #15 lore raw

PATCH 15/84 ipv6: reset fn->rr_ptr when replacing route

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

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

From: Wei Wang <[email protected]>

[ Upstream commit 383143f31d7d3525a1dbff733d52fff917f82f15 ]

syzcaller reported the following use-after-free issue in rt6_select():

BUG: KASAN: use-after-free in rt6_select net/ipv6/route.c:755 [inline] at addr ffff8800bc6994e8
BUG: KASAN: use-after-free in ip6_pol_route.isra.46+0x1429/0x1470 net/ipv6/route.c:1084 at addr ffff8800bc6994e8
Read of size 4 by task syz-executor1/439628
CPU: 0 PID: 439628 Comm: syz-executor1 Not tainted 4.3.5+ #8
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
 0000000000000000 ffff88018fe435b0 ffffffff81ca384d ffff8801d3588c00
 ffff8800bc699380 ffff8800bc699500 dffffc0000000000 ffff8801d40a47c0
 ffff88018fe435d8 ffffffff81735751 ffff88018fe43660 ffff8800bc699380
Call Trace:
 [<ffffffff81ca384d>] __dump_stack lib/dump_stack.c:15 [inline]
 [<ffffffff81ca384d>] dump_stack+0xc1/0x124 lib/dump_stack.c:51
sctp: [Deprecated]: syz-executor0 (pid 439615) Use of struct sctp_assoc_value in delayed_ack socket option.
Use struct sctp_sack_info instead
 [<ffffffff81735751>] kasan_object_err+0x21/0x70 mm/kasan/report.c:158
 [<ffffffff817359c4>] print_address_description mm/kasan/report.c:196 [inline]
 [<ffffffff817359c4>] kasan_report_error+0x1b4/0x4a0 mm/kasan/report.c:285
 [<ffffffff81735d93>] kasan_report mm/kasan/report.c:305 [inline]
 [<ffffffff81735d93>] __asan_report_load4_noabort+0x43/0x50 mm/kasan/report.c:325
 [<ffffffff82a28e39>] rt6_select net/ipv6/route.c:755 [inline]
 [<ffffffff82a28e39>] ip6_pol_route.isra.46+0x1429/0x1470 net/ipv6/route.c:1084
 [<ffffffff82a28fb1>] ip6_pol_route_output+0x81/0xb0 net/ipv6/route.c:1203
 [<ffffffff82ab0a50>] fib6_rule_action+0x1f0/0x680 net/ipv6/fib6_rules.c:95
 [<ffffffff8265cbb6>] fib_rules_lookup+0x2a6/0x7a0 net/core/fib_rules.c:223
 [<ffffffff82ab1430>] fib6_rule_lookup+0xd0/0x250 net/ipv6/fib6_rules.c:41
 [<ffffffff82a22006>] ip6_route_output+0x1d6/0x2c0 net/ipv6/route.c:1224
 [<ffffffff829e83d2>] ip6_dst_lookup_tail+0x4d2/0x890 net/ipv6/ip6_output.c:943
 [<ffffffff829e889a>] ip6_dst_lookup_flow+0x9a/0x250 net/ipv6/ip6_output.c:1079
 [<ffffffff82a9f7d8>] ip6_datagram_dst_update+0x538/0xd40 net/ipv6/datagram.c:91
 [<ffffffff82aa0978>] __ip6_datagram_connect net/ipv6/datagram.c:251 [inline]
 [<ffffffff82aa0978>] ip6_datagram_connect+0x518/0xe50 net/ipv6/datagram.c:272
 [<ffffffff82aa1313>] ip6_datagram_connect_v6_only+0x63/0x90 net/ipv6/datagram.c:284
 [<ffffffff8292f790>] inet_dgram_connect+0x170/0x1f0 net/ipv4/af_inet.c:564
 [<ffffffff82565547>] SYSC_connect+0x1a7/0x2f0 net/socket.c:1582
 [<ffffffff8256a649>] SyS_connect+0x29/0x30 net/socket.c:1563
 [<ffffffff82c72032>] entry_SYSCALL_64_fastpath+0x12/0x17

Object at ffff8800bc699380, in cache ip6_dst_cache size: 384

The root cause of it is that in fib6_add_rt2node(), when it replaces an existing route with the new one, it does not update fn->rr_ptr. This commit resets fn->rr_ptr to NULL when it points to a route which is replaced in fib6_add_rt2node().

Fixes 27596472473a ("ipv6: fix ECMP route replacement")

Signed-off-by Wei Wang <[email protected]>

Acked-by Eric Dumazet <[email protected]>

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 net/ipv6/ip6_fib.c |    4 ++++
 1 file changed, 4 insertions(+)

net/ipv6/ip6_fib.c +4 -0

@@ -897,6 +897,8 @@ add:
 		}
 		nsiblings = iter->rt6i_nsiblings;
 		fib6_purge_rt(iter, fn, info->nl_net);
+		if (fn->rr_ptr == iter)
+			fn->rr_ptr = NULL;
 		rt6_release(iter);
 
 		if (nsiblings) {

@@ -909,6 +911,8 @@ add:
 				if (rt6_qualify_for_ecmp(iter)) {
 					*ins = iter->dst.rt6_next;
 					fib6_purge_rt(iter, fn, info->nl_net);
+					if (fn->rr_ptr == iter)
+						fn->rr_ptr = NULL;
 					rt6_release(iter);
 					nsiblings--;
 				} else {

Greg Kroah-Hartman

author maintainer

2017-08-28 08:12 UTC #16 lore raw

PATCH 16/84 ipv6: repair fib6 tree in failure case

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

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

From: Wei Wang <[email protected]>

[ Upstream commit 348a4002729ccab8b888b38cbc099efa2f2a2036 ]

In fib6_add(), it is possible that fib6_add_1() picks an intermediate node and sets the node's fn->leaf to NULL in order to add this new route. However, if fib6_add_rt2node() fails to add the new route for some reason, fn->leaf will be left as NULL and could potentially cause crash when fn->leaf is accessed in fib6_locate(). This patch makes sure fib6_repair_tree() is called to properly repair fn->leaf in the above failure case.

Here is the syzkaller reported general protection fault in fib6_locate:
kasan: CONFIG_KASAN_INLINE enabled
kasan: GPF could be caused by NULL-ptr deref or user memory access

general protection fault: 0000 [#1] SMP KASAN
Modules linked in:
CPU: 0 PID: 40937 Comm: syz-executor3 Not tainted
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
task: ffff8801d7d64100 ti: ffff8801d01a0000 task.ti: ffff8801d01a0000
RIP: 0010:[<ffffffff82a3e0e1>]  [<ffffffff82a3e0e1>] __ipv6_prefix_equal64_half include/net/ipv6.h:475 [inline]
RIP: 0010:[<ffffffff82a3e0e1>]  [<ffffffff82a3e0e1>] ipv6_prefix_equal include/net/ipv6.h:492 [inline]
RIP: 0010:[<ffffffff82a3e0e1>]  [<ffffffff82a3e0e1>] fib6_locate_1 net/ipv6/ip6_fib.c:1210 [inline]
RIP: 0010:[<ffffffff82a3e0e1>]  [<ffffffff82a3e0e1>] fib6_locate+0x281/0x3c0 net/ipv6/ip6_fib.c:1233
RSP: 0018:ffff8801d01a36a8  EFLAGS: 00010202
RAX: 0000000000000020 RBX: ffff8801bc790e00 RCX: ffffc90002983000
RDX: 0000000000001219 RSI: ffff8801d01a37a0 RDI: 0000000000000100
RBP: ffff8801d01a36f0 R08: 00000000000000ff R09: 0000000000000000
R10: 0000000000000003 R11: 0000000000000000 R12: 0000000000000001
R13: dffffc0000000000 R14: ffff8801d01a37a0 R15: 0000000000000000
FS:  00007f6afd68c700(0000) GS:ffff8801db400000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 00000000004c6340 CR3: 00000000ba41f000 CR4: 00000000001426f0
DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
Stack:
 ffff8801d01a37a8 ffff8801d01a3780 ffffed003a0346f5 0000000c82a23ea0
 ffff8800b7bd7700 ffff8801d01a3780 ffff8800b6a1c940 ffffffff82a23ea0
 ffff8801d01a3920 ffff8801d01a3748 ffffffff82a223d6 ffff8801d7d64988
Call Trace:
 [<ffffffff82a223d6>] ip6_route_del+0x106/0x570 net/ipv6/route.c:2109
 [<ffffffff82a23f9d>] inet6_rtm_delroute+0xfd/0x100 net/ipv6/route.c:3075
 [<ffffffff82621359>] rtnetlink_rcv_msg+0x549/0x7a0 net/core/rtnetlink.c:3450
 [<ffffffff8274c1d1>] netlink_rcv_skb+0x141/0x370 net/netlink/af_netlink.c:2281
 [<ffffffff82613ddf>] rtnetlink_rcv+0x2f/0x40 net/core/rtnetlink.c:3456
 [<ffffffff8274ad38>] netlink_unicast_kernel net/netlink/af_netlink.c:1206 [inline]
 [<ffffffff8274ad38>] netlink_unicast+0x518/0x750 net/netlink/af_netlink.c:1232
 [<ffffffff8274b83e>] netlink_sendmsg+0x8ce/0xc30 net/netlink/af_netlink.c:1778
 [<ffffffff82564aff>] sock_sendmsg_nosec net/socket.c:609 [inline]
 [<ffffffff82564aff>] sock_sendmsg+0xcf/0x110 net/socket.c:619
 [<ffffffff82564d62>] sock_write_iter+0x222/0x3a0 net/socket.c:834
 [<ffffffff8178523d>] new_sync_write+0x1dd/0x2b0 fs/read_write.c:478
 [<ffffffff817853f4>] __vfs_write+0xe4/0x110 fs/read_write.c:491
 [<ffffffff81786c38>] vfs_write+0x178/0x4b0 fs/read_write.c:538
 [<ffffffff817892a9>] SYSC_write fs/read_write.c:585 [inline]
 [<ffffffff817892a9>] SyS_write+0xd9/0x1b0 fs/read_write.c:577
 [<ffffffff82c71e32>] entry_SYSCALL_64_fastpath+0x12/0x17

Note: there is no "Fixes" tag as this seems to be a bug introduced very early.

Signed-off-by Wei Wang <[email protected]>

Acked-by Eric Dumazet <[email protected]>

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 net/ipv6/ip6_fib.c |   22 +++++++++++-----------
 1 file changed, 11 insertions(+), 11 deletions(-)

net/ipv6/ip6_fib.c +11 ~~-11~~

@@ -1001,7 +1001,7 @@ int fib6_add(struct fib6_node *root, str
 			/* Create subtree root node */
 			sfn = node_alloc();
 			if (!sfn)
-				goto st_failure;
+				goto failure;
 
 			sfn->leaf = info->nl_net->ipv6.ip6_null_entry;
 			atomic_inc(&info->nl_net->ipv6.ip6_null_entry->rt6i_ref);

@@ -1017,12 +1017,12 @@ int fib6_add(struct fib6_node *root, str
 
 			if (IS_ERR(sn)) {
 				/* If it is failed, discard just allocated
-				   root, and then (in st_failure) stale node
+				   root, and then (in failure) stale node
 				   in main tree.
 				 */
 				node_free(sfn);
 				err = PTR_ERR(sn);
-				goto st_failure;
+				goto failure;
 			}
 
 			/* Now link new subtree to main tree */

@@ -1036,7 +1036,7 @@ int fib6_add(struct fib6_node *root, str
 
 			if (IS_ERR(sn)) {
 				err = PTR_ERR(sn);
-				goto st_failure;
+				goto failure;
 			}
 		}

@@ -1078,22 +1078,22 @@ out:
 			atomic_inc(&pn->leaf->rt6i_ref);
 		}
 #endif
-		if (!(rt->dst.flags & DST_NOCACHE))
-			dst_free(&rt->dst);
+		goto failure;
 	}
 	return err;
 
-#ifdef CONFIG_IPV6_SUBTREES
-	/* Subtree creation failed, probably main tree node
-	   is orphan. If it is, shoot it.
+failure:
+	/* fn->leaf could be NULL if fn is an intermediate node and we
+	 * failed to add the new route to it in both subtree creation
+	 * failure and fib6_add_rt2node() failure case.
+	 * In both cases, fib6_repair_tree() should be called to fix
+	 * fn->leaf.
 	 */
-st_failure:
 	if (fn && !(fn->fn_flags & (RTN_RTINFO|RTN_ROOT)))
 		fib6_repair_tree(info->nl_net, fn);
 	if (!(rt->dst.flags & DST_NOCACHE))
 		dst_free(&rt->dst);
 	return err;
-#endif
 }
 
 /*

Greg Kroah-Hartman

author maintainer

2017-08-28 08:04 UTC #17 lore raw

PATCH 17/84 tcp: when rearming RTO, if RTO time is in past then fire RTO ASAP

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

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

From: Neal Cardwell <[email protected]>

[ Upstream commit cdbeb633ca71a02b7b63bfeb94994bf4e1a0b894 ]

In some situations tcp_send_loss_probe() can realize that it's unable to send a loss probe (TLP), and falls back to calling tcp_rearm_rto() to schedule an RTO timer. In such cases, sometimes tcp_rearm_rto() realizes that the RTO was eligible to fire immediately or at some point in the past (delta_us <= 0). Previously in such cases tcp_rearm_rto() was scheduling such "overdue" RTOs to happen at now + icsk_rto, which caused needless delays of hundreds of milliseconds (and non-linear behavior that made reproducible testing difficult). This commit changes the logic to schedule "overdue" RTOs ASAP, rather than at now + icsk_rto.

Fixes 6ba8a3b19e76 ("tcp: Tail loss probe (TLP)")

Signed-off-by Neal Cardwell <[email protected]>

Signed-off-by Yuchung Cheng <[email protected]>

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 net/ipv4/tcp_input.c |    3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

net/ipv4/tcp_input.c +1 -2

@@ -3036,8 +3036,7 @@ void tcp_rearm_rto(struct sock *sk)
 			/* delta may not be positive if the socket is locked
 			 * when the retrans timer fires and is rescheduled.
 			 */
-			if (delta > 0)
-				rto = delta;
+			rto = max(delta, 1);
 		}
 		inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS, rto,
 					  TCP_RTO_MAX);

Greg Kroah-Hartman

author maintainer

2017-08-28 08:04 UTC #18 lore raw

PATCH 18/84 net/mlx4_core: Enable 4K UAR if SRIOV module parameter is not enabled

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

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

From: Huy Nguyen <[email protected]>

[ Upstream commit ca3d89a3ebe79367bd41b6b8ba37664478ae2dba ]

enable_4k_uar module parameter was added in patch cited below to address the backward compatibility issue in SRIOV when the VM has system's PAGE_SIZE uar implementation and the Hypervisor has 4k uar implementation.

The above compatibility issue does not exist in the non SRIOV case. In this patch, we always enable 4k uar implementation if SRIOV is not enabled on mlx4's supported cards.

Fixes 76e39ccf9c36 ("net/mlx4_core: Fix backward compatibility on VFs")

Signed-off-by Huy Nguyen <[email protected]>

Reviewed-by Daniel Jurgens <[email protected]>

Signed-off-by Saeed Mahameed <[email protected]>

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 drivers/net/ethernet/mellanox/mlx4/main.c |    4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

drivers/net/ethernet/mellanox/mlx4/main.c +2 -2

@@ -430,7 +430,7 @@ static int mlx4_dev_cap(struct mlx4_dev
 		/* Virtual PCI function needs to determine UAR page size from
 		 * firmware. Only master PCI function can set the uar page size
 		 */
-		if (enable_4k_uar)
+		if (enable_4k_uar || !dev->persist->num_vfs)
 			dev->uar_page_shift = DEFAULT_UAR_PAGE_SHIFT;
 		else
 			dev->uar_page_shift = PAGE_SHIFT;

@@ -2269,7 +2269,7 @@ static int mlx4_init_hca(struct mlx4_dev
 
 		dev->caps.max_fmr_maps = (1 << (32 - ilog2(dev->caps.num_mpts))) - 1;
 
-		if (enable_4k_uar) {
+		if (enable_4k_uar || !dev->persist->num_vfs) {
 			init_hca.log_uar_sz = ilog2(dev->caps.num_uars) +
 						    PAGE_SHIFT - DEFAULT_UAR_PAGE_SHIFT;
 			init_hca.uar_page_sz = DEFAULT_UAR_PAGE_SHIFT - 12;

Greg Kroah-Hartman

author maintainer

2017-08-28 08:12 UTC #19 lore raw

PATCH 19/84 irda: do not leak initialized list.dev to userspace

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

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

From: Colin Ian King <[email protected]>

[ Upstream commit b024d949a3c24255a7ef1a470420eb478949aa4c ]

list.dev has not been initialized and so the copy_to_user is copying data from the stack back to user space which is a potential information leak. Fix this ensuring all of list is initialized to zero.

Detected by CoverityScan, CID#1357894 ("Uninitialized scalar variable")

Signed-off-by Colin Ian King <[email protected]>

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 net/irda/af_irda.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

net/irda/af_irda.c +1 -1

@@ -2223,7 +2223,7 @@ static int irda_getsockopt(struct socket
 {
 	struct sock *sk = sock->sk;
 	struct irda_sock *self = irda_sk(sk);
-	struct irda_device_list list;
+	struct irda_device_list list = { 0 };
 	struct irda_device_info *discoveries;
 	struct irda_ias_set *	ias_opt;	/* IAS get/query params */
 	struct ias_object *	ias_obj;	/* Object in IAS */

Greg Kroah-Hartman

author maintainer

2017-08-28 08:10 UTC #20 lore raw

PATCH 20/84 net: sched: fix NULL pointer dereference when action calls some targets

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

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

From: Xin Long <[email protected]>

[ Upstream commit 4f8a881acc9d1adaf1e552349a0b1df28933a04c ]

As we know in some target's checkentry it may dereference par.entryinfo to check entry stuff inside. But when sched action calls xt_check_target, par.entryinfo is set with NULL. It would cause kernel panic when calling some targets.

It can be reproduce with:

  # tc qd add dev eth1 ingress handle ffff:
  # tc filter add dev eth1 parent ffff: u32 match u32 0 0 action xt \
    -j ECN --ecn-tcp-remove

It could also crash kernel when using target CLUSTERIP or TPROXY.

By now there's no proper value for par.entryinfo in ipt_init_target, but it can not be set with NULL. This patch is to void all these panics by setting it with an ipt_entry obj with all members = 0.

Note that this issue has been there since the very beginning.

Signed-off-by Xin Long <[email protected]>

Acked-by Pablo Neira Ayuso <[email protected]>

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 net/sched/act_ipt.c |    2 ++
 1 file changed, 2 insertions(+)

net/sched/act_ipt.c +2 -0

@@ -41,6 +41,7 @@ static int ipt_init_target(struct xt_ent
 {
 	struct xt_tgchk_param par;
 	struct xt_target *target;
+	struct ipt_entry e = {};
 	int ret = 0;
 
 	target = xt_request_find_target(AF_INET, t->u.user.name,

@@ -51,6 +52,7 @@ static int ipt_init_target(struct xt_ent
 	t->u.kernel.target = target;
 	memset(&par, 0, sizeof(par));
 	par.table     = table;
+	par.entryinfo = &e;
 	par.target    = target;
 	par.targinfo  = t->data;
 	par.hook_mask = hook;

Greg Kroah-Hartman

author maintainer

2017-08-28 08:04 UTC #21 lore raw

PATCH 21/84 net_sched: fix order of queue length updates in qdisc_replace()

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

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

From: Konstantin Khlebnikov <[email protected]>

[ Upstream commit 68a66d149a8c78ec6720f268597302883e48e9fa ]

This important to call qdisc_tree_reduce_backlog() after changing queue length. Parent qdisc should deactivate class in ->qlen_notify() called from qdisc_tree_reduce_backlog() but this happens only if qdisc->q.qlen in zero.

Missed class deactivations leads to crashes/warnings at picking packets from empty qdisc and corrupting state at reactivating this class in future.

Signed-off-by Konstantin Khlebnikov <[email protected]>

Fixes 86a7996cc8a0 ("net_sched: introduce qdisc_replace() helper")

Acked-by Cong Wang <[email protected]>

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 include/net/sch_generic.h |    5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

include/net/sch_generic.h +4 -1

@@ -768,8 +768,11 @@ static inline struct Qdisc *qdisc_replac
 	old = *pold;
 	*pold = new;
 	if (old != NULL) {
-		qdisc_tree_reduce_backlog(old, old->q.qlen, old->qstats.backlog);
+		unsigned int qlen = old->q.qlen;
+		unsigned int backlog = old->qstats.backlog;
+
 		qdisc_reset(old);
+		qdisc_tree_reduce_backlog(old, qlen, backlog);
 	}
 	sch_tree_unlock(sch);

Greg Kroah-Hartman

author maintainer

2017-08-28 08:10 UTC #22 lore raw

PATCH 22/84 bpf, verifier: add additional patterns to evaluate_reg_imm_alu

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

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

From: John Fastabend <[email protected]>

[ Upstream commit 43188702b3d98d2792969a3377a30957f05695e6 ]

Currently the verifier does not track imm across alu operations when the source register is of unknown type. This adds additional pattern matching to catch this and track imm. We've seen LLVM generating this pattern while working on cilium.

Signed-off-by John Fastabend <[email protected]>

Acked-by Daniel Borkmann <[email protected]>

Acked-by Alexei Starovoitov <[email protected]>

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 kernel/bpf/verifier.c |   62 ++++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 62 insertions(+)

kernel/bpf/verifier.c +62 -0

@@ -1467,6 +1467,65 @@ static int evaluate_reg_alu(struct bpf_v
 	return 0;
 }
 
+static int evaluate_reg_imm_alu_unknown(struct bpf_verifier_env *env,
+					struct bpf_insn *insn)
+{
+	struct bpf_reg_state *regs = env->cur_state.regs;
+	struct bpf_reg_state *dst_reg = &regs[insn->dst_reg];
+	struct bpf_reg_state *src_reg = &regs[insn->src_reg];
+	u8 opcode = BPF_OP(insn->code);
+	s64 imm_log2 = __ilog2_u64((long long)dst_reg->imm);
+
+	/* BPF_X code with src_reg->type UNKNOWN_VALUE here. */
+	if (src_reg->imm > 0 && dst_reg->imm) {
+		switch (opcode) {
+		case BPF_ADD:
+			/* dreg += sreg
+			 * where both have zero upper bits. Adding them
+			 * can only result making one more bit non-zero
+			 * in the larger value.
+			 * Ex. 0xffff (imm=48) + 1 (imm=63) = 0x10000 (imm=47)
+			 *     0xffff (imm=48) + 0xffff = 0x1fffe (imm=47)
+			 */
+			dst_reg->imm = min(src_reg->imm, 63 - imm_log2);
+			dst_reg->imm--;
+			break;
+		case BPF_AND:
+			/* dreg &= sreg
+			 * AND can not extend zero bits only shrink
+			 * Ex.  0x00..00ffffff
+			 *    & 0x0f..ffffffff
+			 *     ----------------
+			 *      0x00..00ffffff
+			 */
+			dst_reg->imm = max(src_reg->imm, 63 - imm_log2);
+			break;
+		case BPF_OR:
+			/* dreg |= sreg
+			 * OR can only extend zero bits
+			 * Ex.  0x00..00ffffff
+			 *    | 0x0f..ffffffff
+			 *     ----------------
+			 *      0x0f..00ffffff
+			 */
+			dst_reg->imm = min(src_reg->imm, 63 - imm_log2);
+			break;
+		case BPF_SUB:
+		case BPF_MUL:
+		case BPF_RSH:
+		case BPF_LSH:
+			/* These may be flushed out later */
+		default:
+			mark_reg_unknown_value(regs, insn->dst_reg);
+		}
+	} else {
+		mark_reg_unknown_value(regs, insn->dst_reg);
+	}
+
+	dst_reg->type = UNKNOWN_VALUE;
+	return 0;
+}
+
 static int evaluate_reg_imm_alu(struct bpf_verifier_env *env,
 				struct bpf_insn *insn)
 {

@@ -1475,6 +1534,9 @@ static int evaluate_reg_imm_alu(struct b
 	struct bpf_reg_state *src_reg = &regs[insn->src_reg];
 	u8 opcode = BPF_OP(insn->code);
 
+	if (BPF_SRC(insn->code) == BPF_X && src_reg->type == UNKNOWN_VALUE)
+		return evaluate_reg_imm_alu_unknown(env, insn);
+
 	/* dst_reg->type == CONST_IMM here, simulate execution of 'add' insn.
 	 * Don't care about overflow or negative values, just add them
 	 */

Greg Kroah-Hartman

author maintainer

2017-08-28 08:10 UTC #23 lore raw

PATCH 23/84 bpf: adjust verifier heuristics

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

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

From: Daniel Borkmann <[email protected]>

[ Upstream commit 3c2ce60bdd3d57051bf85615deec04a694473840 ]

Current limits with regards to processing program paths do not really reflect today's needs anymore due to programs becoming more complex and verifier smarter, keeping track of more data such as const ALU operations, alignment tracking, spilling of PTR_TO_MAP_VALUE_ADJ registers, and other features allowing for smarter matching of what LLVM generates.

This also comes with the side-effect that we result in fewer opportunities to prune search states and thus often need to do more work to prove safety than in the past due to different register states and stack layout where we mismatch. Generally, it's quite hard to determine what caused a sudden increase in complexity, it could be caused by something as trivial as a single branch somewhere at the beginning of the program where LLVM assigned a stack slot that is marked differently throughout other branches and thus causing a mismatch, where verifier then needs to prove safety for the whole rest of the program. Subsequently, programs with even less than half the insn size limit can get rejected. We noticed that while some programs load fine under pre 4.11, they get rejected due to hitting limits on more recent kernels. We saw that in the vast majority of cases (90+%) pruning failed due to register mismatches. In case of stack mismatches, majority of cases failed due to different stack slot types (invalid, spill, misc) rather than differences in spilled registers.

This patch makes pruning more aggressive by also adding markers that sit at conditional jumps as well. Currently, we only mark jump targets for pruning. For example in direct packet access, these are usually error paths where we bail out. We found that adding these markers, it can reduce number of processed insns by up to 30%. Another option is to ignore reg->id in probing PTR_TO_MAP_VALUE_OR_NULL registers, which can help pruning slightly as well by up to 7% observed complexity reduction as stand-alone. Meaning, if a previous path with register type PTR_TO_MAP_VALUE_OR_NULL for map X was found to be safe, then in the current state a PTR_TO_MAP_VALUE_OR_NULL register for the same map X must be safe as well. Last but not least the patch also adds a scheduling point and bumps the current limit for instructions to be processed to a more adequate value.

Acked-by Alexei Starovoitov <[email protected]>

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 kernel/bpf/verifier.c |   12 +++++++++++-
 1 file changed, 11 insertions(+), 1 deletion(-)

kernel/bpf/verifier.c +11 -1

@@ -139,7 +139,7 @@ struct bpf_verifier_stack_elem {
 	struct bpf_verifier_stack_elem *next;
 };
 
-#define BPF_COMPLEXITY_LIMIT_INSNS	65536
+#define BPF_COMPLEXITY_LIMIT_INSNS	98304
 #define BPF_COMPLEXITY_LIMIT_STACK	1024
 
 struct bpf_call_arg_meta {

@@ -2452,6 +2452,7 @@ peek_stack:
 				env->explored_states[t + 1] = STATE_LIST_MARK;
 		} else {
 			/* conditional jump with two edges */
+			env->explored_states[t] = STATE_LIST_MARK;
 			ret = push_insn(t, t + 1, FALLTHROUGH, env);
 			if (ret == 1)
 				goto peek_stack;

@@ -2610,6 +2611,12 @@ static bool states_equal(struct bpf_veri
 		     rcur->type != NOT_INIT))
 			continue;
 
+		/* Don't care about the reg->id in this case. */
+		if (rold->type == PTR_TO_MAP_VALUE_OR_NULL &&
+		    rcur->type == PTR_TO_MAP_VALUE_OR_NULL &&
+		    rold->map_ptr == rcur->map_ptr)
+			continue;
+
 		if (rold->type == PTR_TO_PACKET && rcur->type == PTR_TO_PACKET &&
 		    compare_ptrs_to_packet(rold, rcur))
 			continue;

@@ -2744,6 +2751,9 @@ static int do_check(struct bpf_verifier_
 			goto process_bpf_exit;
 		}
 
+		if (need_resched())
+			cond_resched();
+
 		if (log_level && do_print_state) {
 			verbose("\nfrom %d to %d:", prev_insn_idx, insn_idx);
 			print_verifier_state(&env->cur_state);

Greg Kroah-Hartman

author maintainer

2017-08-28 08:10 UTC #24 lore raw

PATCH 24/84 bpf, verifier: fix alu ops against map_value{, _adj} register types

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

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

From: Daniel Borkmann <[email protected]>

[ Upstream commit fce366a9dd0ddc47e7ce05611c266e8574a45116 ]

While looking into map_value_adj, I noticed that alu operations directly on the map_value() resp. map_value_adj() register (any alu operation on a map_value() register will turn it into a map_value_adj() typed register) are not sufficiently protected against some of the operations. Two non-exhaustive examples are provided that the verifier needs to reject:

i) BPF_AND on r0 (map_value_adj):

0: (bf) r2 = r10
1: (07) r2 += -8
2: (7a) *(u64 *)(r2 +0) = 0
3: (18) r1 = 0xbf842a00
5: (85) call bpf_map_lookup_elem#1
6: (15) if r0 == 0x0 goto pc+2
R0=map_value(ks=8,vs=48,id=0),min_value=0,max_value=0 R10=fp
7: (57) r0 &= 8
8: (7a) *(u64 *)(r0 +0) = 22
R0=map_value_adj(ks=8,vs=48,id=0),min_value=0,max_value=8 R10=fp
9: (95) exit

from 6 to 9: R0=inv,min_value=0,max_value=0 R10=fp 9: (95) exit
processed 10 insns

ii) BPF_ADD in 32 bit mode on r0 (map_value_adj):

0: (bf) r2 = r10
1: (07) r2 += -8
2: (7a) *(u64 *)(r2 +0) = 0
3: (18) r1 = 0xc24eee00
5: (85) call bpf_map_lookup_elem#1
6: (15) if r0 == 0x0 goto pc+2
R0=map_value(ks=8,vs=48,id=0),min_value=0,max_value=0 R10=fp
7: (04) (u32) r0 += (u32) 0
8: (7a) *(u64 *)(r0 +0) = 22
R0=map_value_adj(ks=8,vs=48,id=0),min_value=0,max_value=0 R10=fp
9: (95) exit

from 6 to 9: R0=inv,min_value=0,max_value=0 R10=fp 9: (95) exit
processed 10 insns

Issue is, while min_value / max_value boundaries for the access are adjusted appropriately, we change the pointer value in a way that cannot be sufficiently tracked anymore from its origin. Operations like BPF_{AND,OR,DIV,MUL,etc} on a destination register that is PTR_TO_MAP_VALUE{,_ADJ} was probably unintended, in fact, all the test cases coming with 484611357c19 ("bpf: allow access into map value arrays") perform BPF_ADD only on the destination register that is PTR_TO_MAP_VALUE_ADJ.

Only for UNKNOWN_VALUE register types such operations make sense, f.e. with unknown memory content fetched initially from a constant offset from the map value memory into a register. That register is then later tested against lower / upper bounds, so that the verifier can then do the tracking of min_value / max_value, and properly check once that UNKNOWN_VALUE register is added to the destination register with type PTR_TO_MAP_VALUE{,_ADJ}. This is also what the original use-case is solving. Note, tracking on what is being added is done through adjust_reg_min_max_vals() and later access to the map value enforced with these boundaries and the given offset from the insn through check_map_access_adj().

Tests will fail for non-root environment due to prohibited pointer arithmetic, in particular in check_alu_op(), we bail out on the is_pointer_value() check on the dst_reg (which is false in root case as we allow for pointer arithmetic via env->allow_ptr_leaks).

Similarly to PTR_TO_PACKET, one way to fix it is to restrict the allowed operations on PTR_TO_MAP_VALUE{,_ADJ} registers to 64 bit mode BPF_ADD. The test_verifier suite runs fine after the patch and it also rejects mentioned test cases.

Fixes 484611357c19 ("bpf: allow access into map value arrays")

Reviewed-by Josef Bacik <[email protected]>

Acked-by Alexei Starovoitov <[email protected]>

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 kernel/bpf/verifier.c |    1 +
 1 file changed, 1 insertion(+)

kernel/bpf/verifier.c +1 -0

@@ -1870,6 +1870,7 @@ static int check_alu_op(struct bpf_verif
 		 * register as unknown.
 		 */
 		if (env->allow_ptr_leaks &&
+		    BPF_CLASS(insn->code) == BPF_ALU64 && opcode == BPF_ADD &&
 		    (dst_reg->type == PTR_TO_MAP_VALUE ||
 		     dst_reg->type == PTR_TO_MAP_VALUE_ADJ))
 			dst_reg->type = PTR_TO_MAP_VALUE_ADJ;

Greg Kroah-Hartman

author maintainer

2017-08-28 08:04 UTC #25 lore raw

PATCH 25/84 bpf: fix mixed signed/unsigned derived min/max value bounds

[0] https://lists.iovisor.org/pipermail/iovisor-dev/2017-June/000822.html

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

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

From: Daniel Borkmann <[email protected]>

[ Upstream commit 4cabc5b186b5427b9ee5a7495172542af105f02b ]

Edward reported that there's an issue in min/max value bounds tracking when signed and unsigned compares both provide hints on limits when having unknown variables. E.g. a program such as the following should have been rejected:

0: (7a) *(u64 *)(r10 -8) = 0
1: (bf) r2 = r10
2: (07) r2 += -8
3: (18) r1 = 0xffff8a94cda93400
5: (85) call bpf_map_lookup_elem#1
6: (15) if r0 == 0x0 goto pc+7
R0=map_value(ks=8,vs=8,id=0),min_value=0,max_value=0 R10=fp
7: (7a) *(u64 *)(r10 -16) = -8
8: (79) r1 = *(u64 *)(r10 -16)
9: (b7) r2 = -1
10: (2d) if r1 > r2 goto pc+3 R0=map_value(ks=8,vs=8,id=0),min_value=0,max_value=0 R1=inv,min_value=0 R2=imm-1,max_value=18446744073709551615,min_align=1 R10=fp
11: (65) if r1 s> 0x1 goto pc+2 R0=map_value(ks=8,vs=8,id=0),min_value=0,max_value=0 R1=inv,min_value=0,max_value=1 R2=imm-1,max_value=18446744073709551615,min_align=1 R10=fp
12: (0f) r0 += r1
13: (72) *(u8 *)(r0 +0) = 0 R0=map_value_adj(ks=8,vs=8,id=0),min_value=0,max_value=1 R1=inv,min_value=0,max_value=1 R2=imm-1,max_value=18446744073709551615,min_align=1 R10=fp
14: (b7) r0 = 0
15: (95) exit

What happens is that in the first part ...

8: (79) r1 = *(u64 *)(r10 -16)
9: (b7) r2 = -1
10: (2d) if r1 > r2 goto pc+3

... r1 carries an unsigned value, and is compared as unsigned against a register carrying an immediate. Verifier deduces in reg_set_min_max() that since the compare is unsigned and operation is greater than (>), that in the fall-through/false case, r1's minimum bound must be 0 and maximum bound must be r2. Latter is larger than the bound and thus max value is reset back to being 'invalid' aka BPF_REGISTER_MAX_RANGE. Thus, r1 state is now 'R1=inv,min_value=0'. The subsequent test ...

11: (65) if r1 s> 0x1 goto pc+2

... is a signed compare of r1 with immediate value 1. Here, verifier deduces in reg_set_min_max() that since the compare is signed this time and operation is greater than (>), that in the fall-through/false case, we can deduce that r1's maximum bound must be 1, meaning with prior test, we result in r1 having the following state: R1=inv,min_value=0,max_value=1. Given that the actual value this holds is -8, the bounds are wrongly deduced. When this is being added to r0 which holds the map_value(_adj) type, then subsequent store access in above case will go through check_mem_access() which invokes check_map_access_adj(), that will then probe whether the map memory is in bounds based on the min_value and max_value as well as access size since the actual unknown value is min_value <= x <= max_value; commit fce366a9dd0d ("bpf, verifier: fix alu ops against map_value{, _adj} register types") provides some more explanation on the semantics.

It's worth to note in this context that in the current code, min_value and max_value tracking are used for two things, i) dynamic map value access via check_map_access_adj() and since commit 06c1c049721a ("bpf: allow helpers access to variable memory") ii) also enforced at check_helper_mem_access() when passing a memory address (pointer to packet, map value, stack) and length pair to a helper and the length in this case is an unknown value defining an access range through min_value/max_value in that case. The min_value/max_value tracking is /not/ used in the direct packet access case to track ranges. However, the issue also affects case ii), for example, the following crafted program based on the same principle must be rejected as well:

0: (b7) r2 = 0
1: (bf) r3 = r10
2: (07) r3 += -512
3: (7a) *(u64 *)(r10 -16) = -8
4: (79) r4 = *(u64 *)(r10 -16)
5: (b7) r6 = -1
6: (2d) if r4 > r6 goto pc+5
R1=ctx R2=imm0,min_value=0,max_value=0,min_align=2147483648 R3=fp-512 R4=inv,min_value=0 R6=imm-1,max_value=18446744073709551615,min_align=1 R10=fp
7: (65) if r4 s> 0x1 goto pc+4
R1=ctx R2=imm0,min_value=0,max_value=0,min_align=2147483648 R3=fp-512 R4=inv,min_value=0,max_value=1 R6=imm-1,max_value=18446744073709551615,min_align=1 R10=fp
8: (07) r4 += 1
9: (b7) r5 = 0
10: (6a) *(u16 *)(r10 -512) = 0
11: (85) call bpf_skb_load_bytes#26
12: (b7) r0 = 0
13: (95) exit

Meaning, while we initialize the max_value stack slot that the verifier thinks we access in the [1,2] range, in reality we pass -7 as length which is interpreted as u32 in the helper. Thus, this issue is relevant also for the case of helper ranges. Resetting both bounds in check_reg_overflow() in case only one of them exceeds limits is also not enough as similar test can be created that uses values which are within range, thus also here learned min value in r1 is incorrect when mixed with later signed test to create a range:

0: (7a) *(u64 *)(r10 -8) = 0
1: (bf) r2 = r10
2: (07) r2 += -8
3: (18) r1 = 0xffff880ad081fa00
5: (85) call bpf_map_lookup_elem#1
6: (15) if r0 == 0x0 goto pc+7
R0=map_value(ks=8,vs=8,id=0),min_value=0,max_value=0 R10=fp
7: (7a) *(u64 *)(r10 -16) = -8
8: (79) r1 = *(u64 *)(r10 -16)
9: (b7) r2 = 2
10: (3d) if r2 >= r1 goto pc+3 R0=map_value(ks=8,vs=8,id=0),min_value=0,max_value=0 R1=inv,min_value=3 R2=imm2,min_value=2,max_value=2,min_align=2 R10=fp
11: (65) if r1 s> 0x4 goto pc+2 R0=map_value(ks=8,vs=8,id=0),min_value=0,max_value=0 R1=inv,min_value=3,max_value=4 R2=imm2,min_value=2,max_value=2,min_align=2 R10=fp 12: (0f) r0 += r1
13: (72) *(u8 *)(r0 +0) = 0 R0=map_value_adj(ks=8,vs=8,id=0),min_value=3,max_value=4 R1=inv,min_value=3,max_value=4 R2=imm2,min_value=2,max_value=2,min_align=2 R10=fp 14: (b7) r0 = 0
15: (95) exit

This leaves us with two options for fixing this: i) to invalidate all prior learned information once we switch signed context, ii) to track min/max signed and unsigned boundaries separately as done in [0]. (Given latter introduces major changes throughout the whole verifier, it's rather net-next material, thus this patch follows option i), meaning we can derive bounds either from only signed tests or only unsigned tests.) There is still the case of adjust_reg_min_max_vals(), where we adjust bounds on ALU operations, meaning programs like the following where boundaries on the reg get mixed in context later on when bounds are merged on the dst reg must get rejected, too:

0: (7a) *(u64 *)(r10 -8) = 0
1: (bf) r2 = r10
2: (07) r2 += -8
3: (18) r1 = 0xffff89b2bf87ce00
5: (85) call bpf_map_lookup_elem#1
6: (15) if r0 == 0x0 goto pc+6
R0=map_value(ks=8,vs=8,id=0),min_value=0,max_value=0 R10=fp
7: (7a) *(u64 *)(r10 -16) = -8
8: (79) r1 = *(u64 *)(r10 -16)
9: (b7) r2 = 2
10: (3d) if r2 >= r1 goto pc+2 R0=map_value(ks=8,vs=8,id=0),min_value=0,max_value=0 R1=inv,min_value=3 R2=imm2,min_value=2,max_value=2,min_align=2 R10=fp
11: (b7) r7 = 1
12: (65) if r7 s> 0x0 goto pc+2 R0=map_value(ks=8,vs=8,id=0),min_value=0,max_value=0 R1=inv,min_value=3 R2=imm2,min_value=2,max_value=2,min_align=2 R7=imm1,max_value=0 R10=fp 13: (b7) r0 = 0
14: (95) exit

from 12 to 15: R0=map_value(ks=8,vs=8,id=0),min_value=0,max_value=0 R1=inv,min_value=3 R2=imm2,min_value=2,max_value=2,min_align=2 R7=imm1,min_value=1 R10=fp 15: (0f) r7 += r1
16: (65) if r7 s> 0x4 goto pc+2 R0=map_value(ks=8,vs=8,id=0),min_value=0,max_value=0 R1=inv,min_value=3 R2=imm2,min_value=2,max_value=2,min_align=2 R7=inv,min_value=4,max_value=4 R10=fp 17: (0f) r0 += r7
18: (72) *(u8 *)(r0 +0) = 0 R0=map_value_adj(ks=8,vs=8,id=0),min_value=4,max_value=4 R1=inv,min_value=3 R2=imm2,min_value=2,max_value=2,min_align=2 R7=inv,min_value=4,max_value=4 R10=fp 19: (b7) r0 = 0
20: (95) exit

Meaning, in adjust_reg_min_max_vals() we must also reset range values on the dst when src/dst registers have mixed signed/ unsigned derived min/max value bounds with one unbounded value as otherwise they can be added together deducing false boundaries. Once both boundaries are established from either ALU ops or compare operations w/o mixing signed/unsigned insns, then they can safely be added to other regs also having both boundaries established. Adding regs with one unbounded side to a map value where the bounded side has been learned w/o mixing ops is possible, but the resulting map value won't recover from that, meaning such op is considered invalid on the time of actual access. Invalid bounds are set on the dst reg in case i) src reg, or ii) in case dst reg already had them. The only way to recover would be to perform i) ALU ops but only 'add' is allowed on map value types or ii) comparisons, but these are disallowed on pointers in case they span a range. This is fine as only BPF_JEQ and BPF_JNE may be performed on PTR_TO_MAP_VALUE_OR_NULL registers which potentially turn them into PTR_TO_MAP_VALUE type depending on the branch, so only here min/max value cannot be invalidated for them.

In terms of state pruning, value_from_signed is considered as well in states_equal() when dealing with adjusted map values. With regards to breaking existing programs, there is a small risk, but use-cases are rather quite narrow where this could occur and mixing compares probably unlikely.

Joint work with Josef and Edward.

Fixes 484611357c19 ("bpf: allow access into map value arrays")

Reported-by Edward Cree <[email protected]>

Signed-off-by Edward Cree <[email protected]>

Signed-off-by Josef Bacik <[email protected]>

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 include/linux/bpf_verifier.h |    1 
 kernel/bpf/verifier.c        |  110 +++++++++++++++++++++++++++++++++++++------
 2 files changed, 97 insertions(+), 14 deletions(-)

include/linux/bpf_verifier.h +1 -0

@@ -40,6 +40,7 @@ struct bpf_reg_state {
 	 */
 	s64 min_value;
 	u64 max_value;
+	bool value_from_signed;
 };
 
 enum bpf_stack_slot_type {

kernel/bpf/verifier.c +96 ~~-14~~

213 lines not on this page · raw message

Greg Kroah-Hartman

author maintainer

2017-08-28 08:11 UTC #26 lore raw

PATCH 26/84 bpf/verifier: fix min/max handling in BPF_SUB

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

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

From: Edward Cree <[email protected]>

[ Upstream commit 9305706c2e808ae59f1eb201867f82f1ddf6d7a6 ]

We have to subtract the src max from the dst min, and vice-versa, since
(e.g.) the smallest result comes from the largest subtrahend.

Fixes 484611357c19 ("bpf: allow access into map value arrays")

Signed-off-by Edward Cree <[email protected]>

Acked-by Daniel Borkmann <[email protected]>

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 kernel/bpf/verifier.c |   21 +++++++++++++++------
 1 file changed, 15 insertions(+), 6 deletions(-)

kernel/bpf/verifier.c +15 -6

@@ -1624,10 +1624,12 @@ static void adjust_reg_min_max_vals(stru
 	 * do our normal operations to the register, we need to set the values
 	 * to the min/max since they are undefined.
 	 */
-	if (min_val == BPF_REGISTER_MIN_RANGE)
-		dst_reg->min_value = BPF_REGISTER_MIN_RANGE;
-	if (max_val == BPF_REGISTER_MAX_RANGE)
-		dst_reg->max_value = BPF_REGISTER_MAX_RANGE;
+	if (opcode != BPF_SUB) {
+		if (min_val == BPF_REGISTER_MIN_RANGE)
+			dst_reg->min_value = BPF_REGISTER_MIN_RANGE;
+		if (max_val == BPF_REGISTER_MAX_RANGE)
+			dst_reg->max_value = BPF_REGISTER_MAX_RANGE;
+	}
 
 	switch (opcode) {
 	case BPF_ADD:

@@ -1637,10 +1639,17 @@ static void adjust_reg_min_max_vals(stru
 			dst_reg->max_value += max_val;
 		break;
 	case BPF_SUB:
+		/* If one of our values was at the end of our ranges, then the
+		 * _opposite_ value in the dst_reg goes to the end of our range.
+		 */
+		if (min_val == BPF_REGISTER_MIN_RANGE)
+			dst_reg->max_value = BPF_REGISTER_MAX_RANGE;
+		if (max_val == BPF_REGISTER_MAX_RANGE)
+			dst_reg->min_value = BPF_REGISTER_MIN_RANGE;
 		if (dst_reg->min_value != BPF_REGISTER_MIN_RANGE)
-			dst_reg->min_value -= min_val;
+			dst_reg->min_value -= max_val;
 		if (dst_reg->max_value != BPF_REGISTER_MAX_RANGE)
-			dst_reg->max_value -= max_val;
+			dst_reg->max_value -= min_val;
 		break;
 	case BPF_MUL:
 		if (dst_reg->min_value != BPF_REGISTER_MIN_RANGE)

Greg Kroah-Hartman

author maintainer

2017-08-28 08:11 UTC #27 lore raw

PATCH 27/84 Input: trackpoint - add new trackpoint firmware ID

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

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

From: Aaron Ma <[email protected]>

commit ec667683c532c93fb41e100e5d61a518971060e2 upstream.

Synaptics add new TP firmware ID: 0x2 and 0x3, for now both lower 2 bits are indicated as TP. Change the constant to bitwise values.

This makes trackpoint to be recognized on Lenovo Carbon X1 Gen5 instead of it being identified as "PS/2 Generic Mouse".

Signed-off-by Aaron Ma <[email protected]>

Signed-off-by Dmitry Torokhov <[email protected]>

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 drivers/input/mouse/trackpoint.c |    3 ++-
 drivers/input/mouse/trackpoint.h |    3 ++-
 2 files changed, 4 insertions(+), 2 deletions(-)

drivers/input/mouse/trackpoint.c +2 -1

@@ -265,7 +265,8 @@ static int trackpoint_start_protocol(str
 	if (ps2_command(&psmouse->ps2dev, param, MAKE_PS2_CMD(0, 2, TP_READ_ID)))
 		return -1;
 
-	if (param[0] != TP_MAGIC_IDENT)
+	/* add new TP ID. */
+	if (!(param[0] & TP_MAGIC_IDENT))
 		return -1;
 
 	if (firmware_id)

drivers/input/mouse/trackpoint.h +2 -1

@@ -21,8 +21,9 @@
 #define TP_COMMAND		0xE2	/* Commands start with this */
 
 #define TP_READ_ID		0xE1	/* Sent for device identification */
-#define TP_MAGIC_IDENT		0x01	/* Sent after a TP_READ_ID followed */
+#define TP_MAGIC_IDENT		0x03	/* Sent after a TP_READ_ID followed */
 					/* by the firmware ID */
+					/* Firmware ID includes 0x1, 0x2, 0x3 */
 
 
 /*

Greg Kroah-Hartman

author maintainer

2017-08-28 08:11 UTC #28 lore raw

PATCH 28/84 Input: elan_i2c - add ELAN0602 ACPI ID to support Lenovo Yoga310

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

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

From: KT Liao <[email protected]>

commit 1d2226e45040ed4aee95b633cbd64702bf7fc2a1 upstream.

Add ELAN0602 to the list of known ACPI IDs to enable support for ELAN touchpads found in Lenovo Yoga310.

Signed-off-by KT Liao <[email protected]>

Signed-off-by Dmitry Torokhov <[email protected]>

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 drivers/input/mouse/elan_i2c_core.c |    1 +
 1 file changed, 1 insertion(+)

drivers/input/mouse/elan_i2c_core.c +1 -0

@@ -1234,6 +1234,7 @@ static const struct acpi_device_id elan_
 	{ "ELAN0000", 0 },
 	{ "ELAN0100", 0 },
 	{ "ELAN0600", 0 },
+	{ "ELAN0602", 0 },
 	{ "ELAN0605", 0 },
 	{ "ELAN0608", 0 },
 	{ "ELAN0605", 0 },

Greg Kroah-Hartman

author maintainer

2017-08-28 08:04 UTC #29 lore raw

PATCH 29/84 Input: ALPS - fix two-finger scroll breakage in right side on ALPS touchpad

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

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

From: Masaki Ota <[email protected]>

commit 4a646580f793d19717f7e034c8d473b509c27d49 upstream.

Fixed the issue that two finger scroll does not work correctly on V8 protocol. The cause is that V8 protocol X-coordinate decode is wrong at SS4 PLUS device. I added SS4 PLUS X decode definition.

Mote notes:
the problem manifests itself by the commit e7348396c6d5 ("Input: ALPS
- fix V8+ protocol handling (73 03 28)"), where a fix for the V8+ protocol was applied. Although the culprit must have been present beforehand, the two-finger scroll worked casually even with the wrongly reported values by some reason. It got broken by the commit above just because it changed x_max value, and this made libinput correctly figuring the MT events. Since the X coord is reported as falsely doubled, the events on the right-half side go outside the boundary, thus they are no longer handled. This resulted as a broken two-finger scroll.

One finger event is decoded differently, and it didn't suffer from this problem. The problem was only about MT events. --tiwai

Fixes e7348396c6d5 ("Input: ALPS - fix V8+ protocol handling (73 03 28)")

Signed-off-by Masaki Ota <[email protected]>

Tested-by Takashi Iwai <[email protected]>

Tested-by Paul Donohue <[email protected]>

Signed-off-by Dmitry Torokhov <[email protected]>

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 drivers/input/mouse/alps.c |   41 +++++++++++++++++++++++++++++++----------
 drivers/input/mouse/alps.h |    8 ++++++++
 2 files changed, 39 insertions(+), 10 deletions(-)

drivers/input/mouse/alps.c +31 ~~-10~~

@@ -1212,14 +1212,24 @@ static int alps_decode_ss4_v2(struct alp
 
 	case SS4_PACKET_ID_TWO:
 		if (priv->flags & ALPS_BUTTONPAD) {
-			f->mt[0].x = SS4_BTL_MF_X_V2(p, 0);
+			if (IS_SS4PLUS_DEV(priv->dev_id)) {
+				f->mt[0].x = SS4_PLUS_BTL_MF_X_V2(p, 0);
+				f->mt[1].x = SS4_PLUS_BTL_MF_X_V2(p, 1);
+			} else {
+				f->mt[0].x = SS4_BTL_MF_X_V2(p, 0);
+				f->mt[1].x = SS4_BTL_MF_X_V2(p, 1);
+			}
 			f->mt[0].y = SS4_BTL_MF_Y_V2(p, 0);
-			f->mt[1].x = SS4_BTL_MF_X_V2(p, 1);
 			f->mt[1].y = SS4_BTL_MF_Y_V2(p, 1);
 		} else {
-			f->mt[0].x = SS4_STD_MF_X_V2(p, 0);
+			if (IS_SS4PLUS_DEV(priv->dev_id)) {
+				f->mt[0].x = SS4_PLUS_STD_MF_X_V2(p, 0);
+				f->mt[1].x = SS4_PLUS_STD_MF_X_V2(p, 1);
+			} else {
+				f->mt[0].x = SS4_STD_MF_X_V2(p, 0);
+				f->mt[1].x = SS4_STD_MF_X_V2(p, 1);
+			}
 			f->mt[0].y = SS4_STD_MF_Y_V2(p, 0);
-			f->mt[1].x = SS4_STD_MF_X_V2(p, 1);
 			f->mt[1].y = SS4_STD_MF_Y_V2(p, 1);
 		}
 		f->pressure = SS4_MF_Z_V2(p, 0) ? 0x30 : 0;

@@ -1236,16 +1246,27 @@ static int alps_decode_ss4_v2(struct alp
 
 	case SS4_PACKET_ID_MULTI:
 		if (priv->flags & ALPS_BUTTONPAD) {
-			f->mt[2].x = SS4_BTL_MF_X_V2(p, 0);
+			if (IS_SS4PLUS_DEV(priv->dev_id)) {
+				f->mt[0].x = SS4_PLUS_BTL_MF_X_V2(p, 0);
+				f->mt[1].x = SS4_PLUS_BTL_MF_X_V2(p, 1);
+			} else {
+				f->mt[2].x = SS4_BTL_MF_X_V2(p, 0);
+				f->mt[3].x = SS4_BTL_MF_X_V2(p, 1);
+			}
+
 			f->mt[2].y = SS4_BTL_MF_Y_V2(p, 0);
-			f->mt[3].x = SS4_BTL_MF_X_V2(p, 1);
 			f->mt[3].y = SS4_BTL_MF_Y_V2(p, 1);
 			no_data_x = SS4_MFPACKET_NO_AX_BL;
 			no_data_y = SS4_MFPACKET_NO_AY_BL;
 		} else {
-			f->mt[2].x = SS4_STD_MF_X_V2(p, 0);
+			if (IS_SS4PLUS_DEV(priv->dev_id)) {
+				f->mt[0].x = SS4_PLUS_STD_MF_X_V2(p, 0);
+				f->mt[1].x = SS4_PLUS_STD_MF_X_V2(p, 1);
+			} else {
+				f->mt[0].x = SS4_STD_MF_X_V2(p, 0);
+				f->mt[1].x = SS4_STD_MF_X_V2(p, 1);
+			}
 			f->mt[2].y = SS4_STD_MF_Y_V2(p, 0);
-			f->mt[3].x = SS4_STD_MF_X_V2(p, 1);
 			f->mt[3].y = SS4_STD_MF_Y_V2(p, 1);
 			no_data_x = SS4_MFPACKET_NO_AX;
 			no_data_y = SS4_MFPACKET_NO_AY;

@@ -2535,8 +2556,8 @@ static int alps_set_defaults_ss4_v2(stru
 
 	memset(otp, 0, sizeof(otp));
 
-	if (alps_get_otp_values_ss4_v2(psmouse, 0, &otp[0][0]) ||
-	    alps_get_otp_values_ss4_v2(psmouse, 1, &otp[1][0]))
+	if (alps_get_otp_values_ss4_v2(psmouse, 1, &otp[1][0]) ||
+	    alps_get_otp_values_ss4_v2(psmouse, 0, &otp[0][0]))
 		return -1;
 
 	alps_update_device_area_ss4_v2(otp, priv);

drivers/input/mouse/alps.h +8 -0

@@ -91,6 +91,10 @@ enum SS4_PACKET_ID {
 				 ((_b[1 + _i * 3]  << 5) & 0x1F00)	\
 				)
 
+#define SS4_PLUS_STD_MF_X_V2(_b, _i) (((_b[0 + (_i) * 3] << 4) & 0x0070) | \
+				 ((_b[1 + (_i) * 3]  << 4) & 0x0F80)	\
+				)
+
 #define SS4_STD_MF_Y_V2(_b, _i)	(((_b[1 + (_i) * 3] << 3) & 0x0010) |	\
 				 ((_b[2 + (_i) * 3] << 5) & 0x01E0) |	\
 				 ((_b[2 + (_i) * 3] << 4) & 0x0E00)	\

@@ -100,6 +104,10 @@ enum SS4_PACKET_ID {
 				 ((_b[0 + (_i) * 3] >> 3) & 0x0010)	\
 				)
 
+#define SS4_PLUS_BTL_MF_X_V2(_b, _i) (SS4_PLUS_STD_MF_X_V2(_b, _i) |	\
+				 ((_b[0 + (_i) * 3] >> 4) & 0x0008)	\
+				)
+
 #define SS4_BTL_MF_Y_V2(_b, _i)	(SS4_STD_MF_Y_V2(_b, _i) | \
 				 ((_b[0 + (_i) * 3] >> 3) & 0x0008)	\
 				)

Greg Kroah-Hartman

author maintainer

2017-08-28 08:11 UTC #30 lore raw

PATCH 30/84 KVM: s390: sthyi: fix sthyi inline assembly

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

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

From: Heiko Carstens <[email protected]>

commit 4a4eefcd0e49f9f339933324c1bde431186a0a7d upstream.

The sthyi inline assembly misses register r3 within the clobber list. The sthyi instruction will always write a return code to register "R2+1", which in this case would be r3. Due to that we may have register corruption and see host crashes or data corruption depending on how gcc decided to allocate and use registers during compile time.

Fixes 95ca2cb57985 ("KVM: s390: Add sthyi emulation")

Reviewed-by Janosch Frank <[email protected]>

Signed-off-by Heiko Carstens <[email protected]>

Reviewed-by David Hildenbrand <[email protected]>

Reviewed-by Cornelia Huck <[email protected]>

Signed-off-by Christian Borntraeger <[email protected]>

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 arch/s390/kvm/sthyi.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

arch/s390/kvm/sthyi.c +1 -1

@@ -394,7 +394,7 @@ static int sthyi(u64 vaddr)
 		"srl     %[cc],28\n"
 		: [cc] "=d" (cc)
 		: [code] "d" (code), [addr] "a" (addr)
-		: "memory", "cc");
+		: "3", "memory", "cc");
 	return cc;
 }

Greg Kroah-Hartman

author maintainer

2017-08-28 08:11 UTC #31 lore raw

PATCH 31/84 KVM: s390: sthyi: fix specification exception detection

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

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

From: Heiko Carstens <[email protected]>

commit 857b8de96795646c5891cf44ae6fb19b9ff74bf9 upstream.

sthyi should only generate a specification exception if the function code is zero and the response buffer is not on a 4k boundary.

The current code would also test for unknown function codes if the response buffer, that is currently only defined for function code 0, is not on a 4k boundary and incorrectly inject a specification exception instead of returning with condition code 3 and return code 4 (unsupported function code).

Fix this by moving the boundary check.

Fixes 95ca2cb57985 ("KVM: s390: Add sthyi emulation")

Reviewed-by Janosch Frank <[email protected]>

Signed-off-by Heiko Carstens <[email protected]>

Reviewed-by David Hildenbrand <[email protected]>

Reviewed-by Cornelia Huck <[email protected]>

Signed-off-by Christian Borntraeger <[email protected]>

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 arch/s390/kvm/sthyi.c |    5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

arch/s390/kvm/sthyi.c +4 -1

@@ -422,7 +422,7 @@ int handle_sthyi(struct kvm_vcpu *vcpu)
 	VCPU_EVENT(vcpu, 3, "STHYI: fc: %llu addr: 0x%016llx", code, addr);
 	trace_kvm_s390_handle_sthyi(vcpu, code, addr);
 
-	if (reg1 == reg2 || reg1 & 1 || reg2 & 1 || addr & ~PAGE_MASK)
+	if (reg1 == reg2 || reg1 & 1 || reg2 & 1)
 		return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
 
 	if (code & 0xffff) {

@@ -430,6 +430,9 @@ int handle_sthyi(struct kvm_vcpu *vcpu)
 		goto out;
 	}
 
+	if (addr & ~PAGE_MASK)
+		return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
+
 	/*
 	 * If the page has not yet been faulted in, we want to do that
 	 * now and not after all the expensive calculations.

Greg Kroah-Hartman

author maintainer

2017-08-28 08:04 UTC #32 lore raw

PATCH 32/84 KVM: x86: block guest protection keys unless the host has them enabled

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

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

From: Paolo Bonzini <[email protected]>

commit c469268cd523245cc58255f6696e0c295485cb0b upstream.

If the host has protection keys disabled, we cannot read and write the guest PKRU---RDPKRU and WRPKRU fail with #GP(0) if CR4.PKE=0. Block the PKU cpuid bit in that case.

This ensures that guest_CR4.PKE=1 implies host_CR4.PKE=1.

Fixes 1be0e61c1f255faaeab04a390e00c8b9b9042870

Reviewed-by David Hildenbrand <[email protected]>

Signed-off-by Paolo Bonzini <[email protected]>

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 arch/x86/kvm/cpuid.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

arch/x86/kvm/cpuid.c +1 -1

@@ -456,7 +456,7 @@ static inline int __do_cpuid_ent(struct
 			entry->ecx &= kvm_cpuid_7_0_ecx_x86_features;
 			cpuid_mask(&entry->ecx, CPUID_7_ECX);
 			/* PKU is not yet implemented for shadow paging. */
-			if (!tdp_enabled)
+			if (!tdp_enabled || !boot_cpu_has(X86_FEATURE_OSPKE))
 				entry->ecx &= ~F(PKU);
 		} else {
 			entry->ebx = 0;

Greg Kroah-Hartman

author maintainer

2017-08-28 08:11 UTC #33 lore raw

PATCH 33/84 ALSA: usb-audio: Add delay quirk for H650e/Jabra 550a USB headsets

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

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

From: Joakim Tjernlund <[email protected]>

commit 07b3b5e9ed807a0d2077319b8e43a42e941db818 upstream.

These headsets reports a lot of: cannot set freq 44100 to ep 0x81 and need a small delay between sample rate settings, just like Zoom R16/24. Add both headsets to the Zoom R16/24 quirk for a 1 ms delay between control msgs.

Signed-off-by Joakim Tjernlund <[email protected]>

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 sound/usb/quirks.c |    9 ++++++---
 1 file changed, 6 insertions(+), 3 deletions(-)

sound/usb/quirks.c +6 -3

@@ -1309,10 +1309,13 @@ void snd_usb_ctl_msg_quirk(struct usb_de
 	    && (requesttype & USB_TYPE_MASK) == USB_TYPE_CLASS)
 		mdelay(20);
 
-	/* Zoom R16/24 needs a tiny delay here, otherwise requests like
-	 * get/set frequency return as failed despite actually succeeding.
+	/* Zoom R16/24, Logitech H650e, Jabra 550a needs a tiny delay here,
+	 * otherwise requests like get/set frequency return as failed despite
+	 * actually succeeding.
 	 */
-	if (chip->usb_id == USB_ID(0x1686, 0x00dd) &&
+	if ((chip->usb_id == USB_ID(0x1686, 0x00dd) ||
+	     chip->usb_id == USB_ID(0x046d, 0x0a46) ||
+	     chip->usb_id == USB_ID(0x0b0e, 0x0349)) &&
 	    (requesttype & USB_TYPE_MASK) == USB_TYPE_CLASS)
 		mdelay(1);
 }

Greg Kroah-Hartman

author maintainer

2017-08-28 08:11 UTC #34 lore raw

PATCH 34/84 ALSA: core: Fix unexpected error at replacing user TLV

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

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

From: Takashi Iwai <[email protected]>

commit 88c54cdf61f508ebcf8da2d819f5dfc03e954d1d upstream.

When user tries to replace the user-defined control TLV, the kernel checks the change of its content via memcmp(). The problem is that the kernel passes the return value from memcmp() as is. memcmp() gives a non-zero negative value depending on the comparison result, and this shall be recognized as an error code.

The patch covers that corner-case, return 1 properly for the changed TLV.

Fixes 8aa9b586e420 ("[ALSA] Control API - more robust TLV implementation")

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 sound/core/control.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

sound/core/control.c +1 -1

@@ -1156,7 +1156,7 @@ static int snd_ctl_elem_user_tlv(struct
 		mutex_lock(&ue->card->user_ctl_lock);
 		change = ue->tlv_data_size != size;
 		if (!change)
-			change = memcmp(ue->tlv_data, new_data, size);
+			change = memcmp(ue->tlv_data, new_data, size) != 0;
 		kfree(ue->tlv_data);
 		ue->tlv_data = new_data;
 		ue->tlv_data_size = size;

Greg Kroah-Hartman

author maintainer

2017-08-28 08:11 UTC #35 lore raw

PATCH 35/84 ALSA: hda - Add stereo mic quirk for Lenovo G50-70 (17aa:3978)

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

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

From: Takashi Iwai <[email protected]>

commit bbba6f9d3da357bbabc6fda81e99ff5584500e76 upstream.

Lenovo G50-70 (17aa:3978) with Conexant codec chip requires the similar workaround for the inverted stereo dmic like other Lenovo models.

Bugzilla: https://bugzilla.suse.com/show_bug.cgi?id=1020657

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 sound/pci/hda/patch_conexant.c |    1 +
 1 file changed, 1 insertion(+)

sound/pci/hda/patch_conexant.c +1 -0

@@ -854,6 +854,7 @@ static const struct snd_pci_quirk cxt506
 	SND_PCI_QUIRK(0x17aa, 0x390b, "Lenovo G50-80", CXT_FIXUP_STEREO_DMIC),
 	SND_PCI_QUIRK(0x17aa, 0x3975, "Lenovo U300s", CXT_FIXUP_STEREO_DMIC),
 	SND_PCI_QUIRK(0x17aa, 0x3977, "Lenovo IdeaPad U310", CXT_FIXUP_STEREO_DMIC),
+	SND_PCI_QUIRK(0x17aa, 0x3978, "Lenovo G50-70", CXT_FIXUP_STEREO_DMIC),
 	SND_PCI_QUIRK(0x17aa, 0x397b, "Lenovo S205", CXT_FIXUP_STEREO_DMIC),
 	SND_PCI_QUIRK_VENDOR(0x17aa, "Thinkpad", CXT_FIXUP_THINKPAD_ACPI),
 	SND_PCI_QUIRK(0x1c06, 0x2011, "Lemote A1004", CXT_PINCFG_LEMOTE_A1004),

Greg Kroah-Hartman

author maintainer

2017-08-28 08:11 UTC #36 lore raw

PATCH 36/84 ALSA: firewire: fix NULL pointer dereference when releasing uninitialized data of iso-resource

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

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

From: Takashi Sakamoto <[email protected]>

commit 0c264af7be2013266c5b4c644f3f366399ee490a upstream.

When calling 'iso_resource_free()' for uninitialized data, this function causes NULL pointer dereference due to its 'unit' member. This occurs when unplugging audio and music units on IEEE 1394 bus at failure of card registration.

This commit fixes the bug. The bug exists since kernel v4.5.

Fixes 324540c4e05c ('ALSA: fireface: postpone sound card registration') at v4.12

Fixes 8865a31e0fd8 ('ALSA: firewire-motu: postpone sound card registration') at v4.12

Fixes b610386c8afb ('ALSA: firewire-tascam: deleyed registration of sound card') at v4.7

Fixes 86c8dd7f4da3 ('ALSA: firewire-digi00x: delayed registration of sound card') at v4.7

Fixes 6c29230e2a5f ('ALSA: oxfw: delayed registration of sound card') at v4.7

Fixes 7d3c1d5901aa ('ALSA: fireworks: delayed registration of sound card') at v4.7

Fixes 04a2c73c97eb ('ALSA: bebob: delayed registration of sound card') at v4.7

Fixes b59fb1900b4f ('ALSA: dice: postpone card registration') at v4.5

Signed-off-by Takashi Sakamoto <[email protected]>

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 sound/firewire/iso-resources.c |    7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

sound/firewire/iso-resources.c +6 -1

@@ -210,9 +210,14 @@ EXPORT_SYMBOL(fw_iso_resources_update);
  */
 void fw_iso_resources_free(struct fw_iso_resources *r)
 {
-	struct fw_card *card = fw_parent_device(r->unit)->card;
+	struct fw_card *card;
 	int bandwidth, channel;
 
+	/* Not initialized. */
+	if (r->unit == NULL)
+		return;
+	card = fw_parent_device(r->unit)->card;
+
 	mutex_lock(&r->mutex);
 
 	if (r->allocated) {

Greg Kroah-Hartman

author maintainer

2017-08-28 08:11 UTC #37 lore raw

PATCH 37/84 ARCv2: PAE40: Explicitly set MSB counterpart of SLC region ops addresses

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

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

From: Alexey Brodkin <[email protected]>

commit 7d79cee2c6540ea64dd917a14e2fd63d4ac3d3c0 upstream.

It is necessary to explicitly set both SLC_AUX_RGN_START1 and SLC_AUX_RGN_END1 which hold MSB bits of the physical address correspondingly of region start and end otherwise SLC region operation is executed in unpredictable manner

Without this patch, SLC flushes on HSDK (IOC disabled) were taking seconds.

Reported-by Vladimir Kondratiev <[email protected]>

Signed-off-by Alexey Brodkin <[email protected]>

Signed-off-by Vineet Gupta <[email protected]>

[vgupta: PAR40 regs only written if PAE40 exist]

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 arch/arc/include/asm/cache.h |    2 ++
 arch/arc/mm/cache.c          |   13 +++++++++++--
 2 files changed, 13 insertions(+), 2 deletions(-)

arch/arc/include/asm/cache.h +2 -0

@@ -89,7 +89,9 @@ extern unsigned long perip_base, perip_e
 #define ARC_REG_SLC_FLUSH	0x904
 #define ARC_REG_SLC_INVALIDATE	0x905
 #define ARC_REG_SLC_RGN_START	0x914
+#define ARC_REG_SLC_RGN_START1	0x915
 #define ARC_REG_SLC_RGN_END	0x916
+#define ARC_REG_SLC_RGN_END1	0x917
 
 /* Bit val in SLC_CONTROL */
 #define SLC_CTRL_IM		0x040

arch/arc/mm/cache.c +11 -2

@@ -562,6 +562,7 @@ noinline void slc_op(phys_addr_t paddr,
 	static DEFINE_SPINLOCK(lock);
 	unsigned long flags;
 	unsigned int ctrl;
+	phys_addr_t end;
 
 	spin_lock_irqsave(&lock, flags);

@@ -591,8 +592,16 @@ noinline void slc_op(phys_addr_t paddr,
 	 * END needs to be setup before START (latter triggers the operation)
 	 * END can't be same as START, so add (l2_line_sz - 1) to sz
 	 */
-	write_aux_reg(ARC_REG_SLC_RGN_END, (paddr + sz + l2_line_sz - 1));
-	write_aux_reg(ARC_REG_SLC_RGN_START, paddr);
+	end = paddr + sz + l2_line_sz - 1;
+	if (is_pae40_enabled())
+		write_aux_reg(ARC_REG_SLC_RGN_END1, upper_32_bits(end));
+
+	write_aux_reg(ARC_REG_SLC_RGN_END, lower_32_bits(end));
+
+	if (is_pae40_enabled())
+		write_aux_reg(ARC_REG_SLC_RGN_START1, upper_32_bits(paddr));
+
+	write_aux_reg(ARC_REG_SLC_RGN_START, lower_32_bits(paddr));
 
 	while (read_aux_reg(ARC_REG_SLC_CTRL) & SLC_CTRL_BUSY);

Greg Kroah-Hartman

author maintainer

2017-08-28 08:11 UTC #38 lore raw

PATCH 38/84 mm, shmem: fix handling /sys/kernel/mm/transparent_hugepage/shmem_enabled

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

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

From: Kirill A. Shutemov <[email protected]>

commit 435c0b87d661da83771c30ed775f7c37eed193fb upstream.

/sys/kernel/mm/transparent_hugepage/shmem_enabled controls if we want to allocate huge pages when allocate pages for private in-kernel shmem mount.

Unfortunately, as Dan noticed, I've screwed it up and the only way to make kernel allocate huge page for the mount is to use "force" there. All other values will be effectively ignored.

Link http://lkml.kernel.org/r/[email protected] open here

Fixes 5a6e75f8110c ("shmem: prepare huge= mount option and sysfs knob")

Signed-off-by Kirill A. Shutemov <[email protected]>

Reported-by Dan Carpenter <[email protected]>

Signed-off-by Greg Kroah-Hartman <[email protected]>

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

mm/shmem.c +2 -2

@@ -3810,7 +3810,7 @@ int __init shmem_init(void)
 	}
 
 #ifdef CONFIG_TRANSPARENT_HUGE_PAGECACHE
-	if (has_transparent_hugepage() && shmem_huge < SHMEM_HUGE_DENY)
+	if (has_transparent_hugepage() && shmem_huge > SHMEM_HUGE_DENY)
 		SHMEM_SB(shm_mnt->mnt_sb)->huge = shmem_huge;
 	else
 		shmem_huge = 0; /* just in case it was patched */

@@ -3871,7 +3871,7 @@ static ssize_t shmem_enabled_store(struc
 		return -EINVAL;
 
 	shmem_huge = huge;
-	if (shmem_huge < SHMEM_HUGE_DENY)
+	if (shmem_huge > SHMEM_HUGE_DENY)
 		SHMEM_SB(shm_mnt->mnt_sb)->huge = shmem_huge;
 	return count;
 }

Greg Kroah-Hartman

author maintainer

2017-08-28 08:11 UTC #39 lore raw

PATCH 39/84 i2c: designware: Fix system suspend

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

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

From: Ulf Hansson <[email protected]>

commit a23318feeff662c8d25d21623daebdd2e55ec221 upstream.

The commit 8503ff166504 ("i2c: designware: Avoid unnecessary resuming during system suspend"), may suggest to the PM core to try out the so called direct_complete path for system sleep. In this path, the PM core treats a runtime suspended device as it's already in a proper low power state for system sleep, which makes it skip calling the system sleep callbacks for the device, except for the ->prepare() and the ->complete() callbacks.

However, the PM core may unset the direct_complete flag for a parent device, in case its child device are being system suspended before. In this scenario, the PM core invokes the system sleep callbacks, no matter if the device is runtime suspended or not.

Particularly in cases of an existing i2c slave device, the above path is triggered, which breaks the assumption that the i2c device is always runtime resumed whenever the dw_i2c_plat_suspend() is being called.

More precisely, dw_i2c_plat_suspend() calls clk_core_disable() and clk_core_unprepare(), for an already disabled/unprepared clock, leading to a splat in the log about clocks calls being wrongly balanced and breaking system sleep.

To still allow the direct_complete path in cases when it's possible, but also to keep the fix simple, let's runtime resume the i2c device in the ->suspend() callback, before continuing to put the device into low power state.

Note, in cases when the i2c device is attached to the ACPI PM domain, this problem doesn't occur, because ACPI's ->suspend() callback, assigned to acpi_subsys_suspend(), already calls pm_runtime_resume() for the device.

It should also be noted that this change does not fix commit 8503ff166504 ("i2c: designware: Avoid unnecessary resuming during system suspend"). Because for the non-ACPI case, the system sleep support was already broken prior that point.

Signed-off-by Ulf Hansson <[email protected]>

Acked-by Rafael J. Wysocki <[email protected]>

Tested-by John Stultz <[email protected]>

Tested-by Jarkko Nikula <[email protected]>

Acked-by Jarkko Nikula <[email protected]>

Reviewed-by Mika Westerberg <[email protected]>

Signed-off-by Wolfram Sang <[email protected]>

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 drivers/i2c/busses/i2c-designware-platdrv.c |   14 ++++++++++++--
 1 file changed, 12 insertions(+), 2 deletions(-)

drivers/i2c/busses/i2c-designware-platdrv.c +12 -2

@@ -319,7 +319,7 @@ static void dw_i2c_plat_complete(struct
 #endif
 
 #ifdef CONFIG_PM
-static int dw_i2c_plat_suspend(struct device *dev)
+static int dw_i2c_plat_runtime_suspend(struct device *dev)
 {
 	struct platform_device *pdev = to_platform_device(dev);
 	struct dw_i2c_dev *i_dev = platform_get_drvdata(pdev);

@@ -343,11 +343,21 @@ static int dw_i2c_plat_resume(struct dev
 	return 0;
 }
 
+#ifdef CONFIG_PM_SLEEP
+static int dw_i2c_plat_suspend(struct device *dev)
+{
+	pm_runtime_resume(dev);
+	return dw_i2c_plat_runtime_suspend(dev);
+}
+#endif
+
 static const struct dev_pm_ops dw_i2c_dev_pm_ops = {
 	.prepare = dw_i2c_plat_prepare,
 	.complete = dw_i2c_plat_complete,
 	SET_SYSTEM_SLEEP_PM_OPS(dw_i2c_plat_suspend, dw_i2c_plat_resume)
-	SET_RUNTIME_PM_OPS(dw_i2c_plat_suspend, dw_i2c_plat_resume, NULL)
+	SET_RUNTIME_PM_OPS(dw_i2c_plat_runtime_suspend,
+			   dw_i2c_plat_resume,
+			   NULL)
 };
 
 #define DW_I2C_DEV_PMOPS (&dw_i2c_dev_pm_ops)

Greg Kroah-Hartman

author maintainer

2017-08-28 08:11 UTC #40 lore raw

PATCH 40/84 mm/madvise.c: fix freeing of locked page with MADV_FREE

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

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

From: Eric Biggers <[email protected]>

commit 263630e8d176d87308481ebdcd78ef9426739c6b upstream.

If madvise(..., MADV_FREE) split a transparent hugepage, it called put_page() before unlock_page().

This was wrong because put_page() can free the page, e.g. if a concurrent madvise(..., MADV_DONTNEED) has removed it from the memory mapping. put_page() then rightfully complained about freeing a locked page.

Fix this by moving the unlock_page() before put_page().

This bug was found by syzkaller, which encountered the following splat:

    BUG: Bad page state in process syzkaller412798  pfn:1bd800
    page:ffffea0006f60000 count:0 mapcount:0 mapping:          (null) index:0x20a00
    flags: 0x200000000040019(locked|uptodate|dirty|swapbacked)
    raw: 0200000000040019 0000000000000000 0000000000020a00 00000000ffffffff
    raw: ffffea0006f60020 ffffea0006f60020 0000000000000000 0000000000000000
    page dumped because: PAGE_FLAGS_CHECK_AT_FREE flag(s) set
    bad because of flags: 0x1(locked)
    Modules linked in:
    CPU: 1 PID: 3037 Comm: syzkaller412798 Not tainted 4.13.0-rc5+ #35
    Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
    Call Trace:
     __dump_stack lib/dump_stack.c:16 [inline]
     dump_stack+0x194/0x257 lib/dump_stack.c:52
     bad_page+0x230/0x2b0 mm/page_alloc.c:565
     free_pages_check_bad+0x1f0/0x2e0 mm/page_alloc.c:943
     free_pages_check mm/page_alloc.c:952 [inline]
     free_pages_prepare mm/page_alloc.c:1043 [inline]
     free_pcp_prepare mm/page_alloc.c:1068 [inline]
     free_hot_cold_page+0x8cf/0x12b0 mm/page_alloc.c:2584
     __put_single_page mm/swap.c:79 [inline]
     __put_page+0xfb/0x160 mm/swap.c:113
     put_page include/linux/mm.h:814 [inline]
     madvise_free_pte_range+0x137a/0x1ec0 mm/madvise.c:371
     walk_pmd_range mm/pagewalk.c:50 [inline]
     walk_pud_range mm/pagewalk.c:108 [inline]
     walk_p4d_range mm/pagewalk.c:134 [inline]
     walk_pgd_range mm/pagewalk.c:160 [inline]
     __walk_page_range+0xc3a/0x1450 mm/pagewalk.c:249
     walk_page_range+0x200/0x470 mm/pagewalk.c:326
     madvise_free_page_range.isra.9+0x17d/0x230 mm/madvise.c:444
     madvise_free_single_vma+0x353/0x580 mm/madvise.c:471
     madvise_dontneed_free mm/madvise.c:555 [inline]
     madvise_vma mm/madvise.c:664 [inline]
     SYSC_madvise mm/madvise.c:832 [inline]
     SyS_madvise+0x7d3/0x13c0 mm/madvise.c:760
     entry_SYSCALL_64_fastpath+0x1f/0xbe

Here is a C reproducer:

    #define _GNU_SOURCE
    #include <pthread.h>
    #include <sys/mman.h>
    #include <unistd.h>

    #define MADV_FREE	8
    #define PAGE_SIZE	4096

    static void *mapping;
    static const size_t mapping_size = 0x1000000;

    static void *madvise_thrproc(void *arg)
    {
        madvise(mapping, mapping_size, (long)arg);
    }

    int main(void)
    {
        pthread_t t[2];

        for (;;) {
            mapping = mmap(NULL, mapping_size, PROT_WRITE,
                           MAP_POPULATE|MAP_ANONYMOUS|MAP_PRIVATE, -1, 0);

            munmap(mapping + mapping_size / 2, PAGE_SIZE);

            pthread_create(&t[0], 0, madvise_thrproc, (void*)MADV_DONTNEED);
            pthread_create(&t[1], 0, madvise_thrproc, (void*)MADV_FREE);
            pthread_join(t[0], NULL);
            pthread_join(t[1], NULL);
            munmap(mapping, mapping_size);
        }
    }

Note: to see the splat, CONFIG_TRANSPARENT_HUGEPAGE=y and CONFIG_DEBUG_VM=y are needed.

Google Bug Id: 64696096

Link http://lkml.kernel.org/r/[email protected] open here

Fixes 854e9ed09ded ("mm: support madvise(MADV_FREE)")

Signed-off-by Eric Biggers <[email protected]>

Acked-by David Rientjes <[email protected]>

Acked-by Minchan Kim <[email protected]>

Acked-by Michal Hocko <[email protected]>

Cc Dmitry Vyukov <[email protected]>

Cc Hugh Dickins <[email protected]>

Cc Andrea Arcangeli <[email protected]>

Signed-off-by Greg Kroah-Hartman <[email protected]>

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

mm/madvise.c +1 -1

@@ -331,8 +331,8 @@ static int madvise_free_pte_range(pmd_t
 				pte_offset_map_lock(mm, pmd, addr, &ptl);
 				goto out;
 			}
-			put_page(page);
 			unlock_page(page);
+			put_page(page);
 			pte = pte_offset_map_lock(mm, pmd, addr, &ptl);
 			pte--;
 			addr -= PAGE_SIZE;

Greg Kroah-Hartman

author maintainer

2017-08-28 08:11 UTC #41 lore raw

PATCH 41/84 fork: fix incorrect fput of ->exe_file causing use-after-free

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

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

From: Eric Biggers <[email protected]>

commit 2b7e8665b4ff51c034c55df3cff76518d1a9ee3a upstream.

Commit 7c051267931a ("mm, fork: make dup_mmap wait for mmap_sem for write killable") made it possible to kill a forking task while it is waiting to acquire its ->mmap_sem for write, in dup_mmap().

However, it was overlooked that this introduced an new error path before a reference is taken on the mm_struct's ->exe_file. Since the ->exe_file of the new mm_struct was already set to the old ->exe_file by the memcpy() in dup_mm(), it was possible for the mmput() in the error path of dup_mm() to drop a reference to ->exe_file which was never taken.

This caused the struct file to later be freed prematurely.

Fix it by updating mm_init() to NULL out the ->exe_file, in the same place it clears other things like the list of mmaps.

This bug was found by syzkaller. It can be reproduced using the following C program:

    #define _GNU_SOURCE
    #include <pthread.h>
    #include <stdlib.h>
    #include <sys/mman.h>
    #include <sys/syscall.h>
    #include <sys/wait.h>
    #include <unistd.h>

    static void *mmap_thread(void *_arg)
    {
        for (;;) {
            mmap(NULL, 0x1000000, PROT_READ,
                 MAP_POPULATE|MAP_ANONYMOUS|MAP_PRIVATE, -1, 0);
        }
    }

    static void *fork_thread(void *_arg)
    {
        usleep(rand() % 10000);
        fork();
    }

    int main(void)
    {
        fork();
        fork();
        fork();
        for (;;) {
            if (fork() == 0) {
                pthread_t t;

                pthread_create(&t, NULL, mmap_thread, NULL);
                pthread_create(&t, NULL, fork_thread, NULL);
                usleep(rand() % 10000);
                syscall(__NR_exit_group, 0);
            }
            wait(NULL);
        }
    }

No special kernel config options are needed. It usually causes a NULL pointer dereference in __remove_shared_vm_struct() during exit, or in dup_mmap() (which is usually inlined into copy_process()) during fork. Both are due to a vm_area_struct's ->vm_file being used after it's already been freed.

Google Bug Id: 64772007

Link http://lkml.kernel.org/r/[email protected] open here

Fixes 7c051267931a ("mm, fork: make dup_mmap wait for mmap_sem for write killable")

Signed-off-by Eric Biggers <[email protected]>

Tested-by Mark Rutland <[email protected]>

Acked-by Michal Hocko <[email protected]>

Cc Dmitry Vyukov <[email protected]>

Cc Ingo Molnar <[email protected]>

Cc Konstantin Khlebnikov <[email protected]>

Cc Oleg Nesterov <[email protected]>

Cc Peter Zijlstra <[email protected]>

Cc Vlastimil Babka <[email protected]>

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 kernel/fork.c |    1 +
 1 file changed, 1 insertion(+)

kernel/fork.c +1 -0

@@ -766,6 +766,7 @@ static struct mm_struct *mm_init(struct
 	mm_init_cpumask(mm);
 	mm_init_aio(mm);
 	mm_init_owner(mm, p);
+	RCU_INIT_POINTER(mm->exe_file, NULL);
 	mmu_notifier_mm_init(mm);
 	clear_tlb_flush_pending(mm);
 #if defined(CONFIG_TRANSPARENT_HUGEPAGE) && !USE_SPLIT_PMD_PTLOCKS

Greg Kroah-Hartman

author maintainer

2017-08-28 08:11 UTC #42 lore raw

PATCH 42/84 mm/memblock.c: reversed logic in memblock_discard()

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

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

From: Pavel Tatashin <[email protected]>

commit 91b540f98872a206ea1c49e4aa6ea8eed0886644 upstream.

In recently introduced memblock_discard() there is a reversed logic bug. Memory is freed of static array instead of dynamically allocated one.

Link http://lkml.kernel.org/r/[email protected] open here

Fixes 3010f876500f ("mm: discard memblock data later")

Signed-off-by Pavel Tatashin <[email protected]>

Reported-by Woody Suwalski <[email protected]>

Tested-by Woody Suwalski <[email protected]>

Acked-by Michal Hocko <[email protected]>

Cc Vlastimil Babka <[email protected]>

Signed-off-by Greg Kroah-Hartman <[email protected]>

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

mm/memblock.c +1 -1

@@ -311,7 +311,7 @@ void __init memblock_discard(void)
 		__memblock_free_late(addr, size);
 	}
 
-	if (memblock.memory.regions == memblock_memory_init_regions) {
+	if (memblock.memory.regions != memblock_memory_init_regions) {
 		addr = __pa(memblock.memory.regions);
 		size = PAGE_ALIGN(sizeof(struct memblock_region) *
 				  memblock.memory.max);

Greg Kroah-Hartman

author maintainer

2017-08-28 08:05 UTC #43 lore raw

PATCH 44/84 drm/atomic: If the atomic check fails, return its value first

Link https://patchwork.freedesktop.org/patch/msgid/[email protected]

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

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

From: Maarten Lankhorst <[email protected]>

commit a0ffc51e20e90e0c1c2491de2b4b03f48b6caaba upstream.

The last part of drm_atomic_check_only is testing whether we need to fail with -EINVAL when modeset is not allowed, but forgets to return the value when atomic_check() fails first.

This results in -EDEADLK being replaced by -EINVAL, and the sanity check in drm_modeset_drop_locks kicks in:

[  308.531734] ------------[ cut here ]------------
[  308.531791] WARNING: CPU: 0 PID: 1886 at drivers/gpu/drm/drm_modeset_lock.c:217 drm_modeset_drop_locks+0x33/0xc0 [drm]
[  308.531828] Modules linked in:
[  308.532050] CPU: 0 PID: 1886 Comm: kms_atomic Tainted: G     U  W 4.13.0-rc5-patser+ #5225
[  308.532082] Hardware name: NUC5i7RYB, BIOS RYBDWi35.86A.0246.2015.0309.1355 03/09/2015
[  308.532124] task: ffff8800cd9dae00 task.stack: ffff8800ca3b8000
[  308.532168] RIP: 0010:drm_modeset_drop_locks+0x33/0xc0 [drm]
[  308.532189] RSP: 0018:ffff8800ca3bf980 EFLAGS: 00010282
[  308.532211] RAX: dffffc0000000000 RBX: ffff8800ca3bfaf8 RCX: 0000000013a171e6
[  308.532235] RDX: 1ffff10019477f69 RSI: ffffffffa8ba4fa0 RDI: ffff8800ca3bfb48
[  308.532258] RBP: ffff8800ca3bf998 R08: 0000000000000000 R09: 0000000000000003
[  308.532281] R10: 0000000079dbe066 R11: 00000000f760b34b R12: 0000000000000001
[  308.532304] R13: dffffc0000000000 R14: 00000000ffffffea R15: ffff880096889680
[  308.532328] FS:  00007ff00959cec0(0000) GS:ffff8800d4e00000(0000) knlGS:0000000000000000
[  308.532359] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[  308.532380] CR2: 0000000000000008 CR3: 00000000ca2e3000 CR4: 00000000003406f0
[  308.532402] Call Trace:
[  308.532440]  drm_mode_atomic_ioctl+0x19fa/0x1c00 [drm]
[  308.532488]  ? drm_atomic_set_property+0x1220/0x1220 [drm]
[  308.532565]  ? avc_has_extended_perms+0xc39/0xff0
[  308.532593]  ? lock_downgrade+0x610/0x610
[  308.532640]  ? drm_atomic_set_property+0x1220/0x1220 [drm]
[  308.532680]  drm_ioctl_kernel+0x154/0x1a0 [drm]
[  308.532755]  drm_ioctl+0x624/0x8f0 [drm]
[  308.532858]  ? drm_atomic_set_property+0x1220/0x1220 [drm]
[  308.532976]  ? drm_getunique+0x210/0x210 [drm]
[  308.533061]  do_vfs_ioctl+0xd92/0xe40
[  308.533121]  ? ioctl_preallocate+0x1b0/0x1b0
[  308.533160]  ? selinux_capable+0x20/0x20
[  308.533191]  ? do_fcntl+0x1b1/0xbf0
[  308.533219]  ? kasan_slab_free+0xa2/0xb0
[  308.533249]  ? f_getown+0x4b/0xa0
[  308.533278]  ? putname+0xcf/0xe0
[  308.533309]  ? security_file_ioctl+0x57/0x90
[  308.533342]  SyS_ioctl+0x4e/0x80
[  308.533374]  entry_SYSCALL_64_fastpath+0x18/0xad
[  308.533405] RIP: 0033:0x7ff00779e4d7
[  308.533431] RSP: 002b:00007fff66a043d8 EFLAGS: 00000246 ORIG_RAX: 0000000000000010
[  308.533481] RAX: ffffffffffffffda RBX: 000000e7c7ca5910 RCX: 00007ff00779e4d7
[  308.533560] RDX: 00007fff66a04430 RSI: 00000000c03864bc RDI: 0000000000000003
[  308.533608] RBP: 00007ff007a5fb00 R08: 000000e7c7ca4620 R09: 000000e7c7ca5e60
[  308.533647] R10: 0000000000000001 R11: 0000000000000246 R12: 0000000000000070
[  308.533685] R13: 0000000000000000 R14: 0000000000000000 R15: 000000e7c7ca5930
[  308.533770] Code: ff df 55 48 89 e5 41 55 41 54 53 48 89 fb 48 83 c7
50 48 89 fa 48 c1 ea 03 80 3c 02 00 74 05 e8 94 d4 16 e7 48 83 7b 50 00
74 02 <0f> ff 4c 8d 6b 58 48 b8 00 00 00 00 00 fc ff df 4c 89 ea 48 c1
[  308.534086] ---[ end trace 77f11e53b1df44ad ]---

Solve this by adding the missing return.

This is also a bugfix because we could end up rejecting updates with -EINVAL because of a early -EDEADLK, while if atomic_check ran to completion it might have downgraded the modeset to a fastset.

Signed-off-by Maarten Lankhorst <[email protected]>

Testcase: kms_atomic

Fixes d34f20d6e2f2 ("drm: Atomic modeset ioctl")

Reviewed-by Daniel Vetter <[email protected]>

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 drivers/gpu/drm/drm_atomic.c |    5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

drivers/gpu/drm/drm_atomic.c +4 -1

@@ -1386,6 +1386,9 @@ int drm_atomic_check_only(struct drm_ato
 	if (config->funcs->atomic_check)
 		ret = config->funcs->atomic_check(state->dev, state);
 
+	if (ret)
+		return ret;
+
 	if (!state->allow_modeset) {
 		for_each_crtc_in_state(state, crtc, crtc_state, i) {
 			if (drm_atomic_crtc_needs_modeset(crtc_state)) {

@@ -1396,7 +1399,7 @@ int drm_atomic_check_only(struct drm_ato
 		}
 	}
 
-	return ret;
+	return 0;
 }
 EXPORT_SYMBOL(drm_atomic_check_only);

Greg Kroah-Hartman

author maintainer

2017-08-28 08:11 UTC #44 lore raw

PATCH 45/84 drm: rcar-du: Fix crash in encoder failure error path

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

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

From: Laurent Pinchart <[email protected]>

commit 05ee29e94acf0d4b3998c3f93374952de8f90176 upstream.

When an encoder fails to initialize the driver prints an error message to the kernel log. The message contains the name of the encoder's DT node, which is NULL for internal encoders. Use the of_node_full_name() macro to avoid dereferencing a NULL pointer, print the output number to add more context to the error, and make sure we still own a reference to the encoder's DT node by delaying the of_node_put() call.

Signed-off-by Laurent Pinchart <[email protected]>

Reviewed-by Gustavo Padovan <[email protected]>

Signed-off-by Thong Ho <[email protected]>

Signed-off-by Nhan Nguyen <[email protected]>

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 drivers/gpu/drm/rcar-du/rcar_du_kms.c |   10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

drivers/gpu/drm/rcar-du/rcar_du_kms.c +5 -5

@@ -453,13 +453,13 @@ static int rcar_du_encoders_init_one(str
 	}
 
 	ret = rcar_du_encoder_init(rcdu, enc_type, output, encoder, connector);
-	of_node_put(encoder);
-	of_node_put(connector);
-
 	if (ret && ret != -EPROBE_DEFER)
 		dev_warn(rcdu->dev,
-			 "failed to initialize encoder %s (%d), skipping\n",
-			 encoder->full_name, ret);
+			 "failed to initialize encoder %s on output %u (%d), skipping\n",
+			 of_node_full_name(encoder), output, ret);
+
+	of_node_put(encoder);
+	of_node_put(connector);
 
 	return ret;
 }

Greg Kroah-Hartman

author maintainer

2017-08-28 08:11 UTC #45 lore raw

PATCH 46/84 drm: rcar-du: Fix display timing controller parameter

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

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

From: Koji Matsuoka <[email protected]>

commit 9cdced8a39c04cf798ddb2a27cb5952f7d39f633 upstream.

There is a bug in the setting of the DES (Display Enable Signal) register. This current setting occurs 1 dot left shift. The DES register should be set minus one value about the specifying value with H/W specification. This patch corrects it.

Signed-off-by Koji Matsuoka <[email protected]>

Signed-off-by Laurent Pinchart <[email protected]>

Signed-off-by Thong Ho <[email protected]>

Signed-off-by Nhan Nguyen <[email protected]>

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 drivers/gpu/drm/rcar-du/rcar_du_crtc.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

drivers/gpu/drm/rcar-du/rcar_du_crtc.c +1 -1

@@ -172,7 +172,7 @@ static void rcar_du_crtc_set_display_tim
 					mode->crtc_vsync_start - 1);
 	rcar_du_crtc_write(rcrtc, VCR,  mode->crtc_vtotal - 1);
 
-	rcar_du_crtc_write(rcrtc, DESR,  mode->htotal - mode->hsync_start);
+	rcar_du_crtc_write(rcrtc, DESR,  mode->htotal - mode->hsync_start - 1);
 	rcar_du_crtc_write(rcrtc, DEWR,  mode->hdisplay);
 }

Greg Kroah-Hartman

author maintainer

2017-08-28 08:05 UTC #46 lore raw

PATCH 47/84 drm: rcar-du: Fix H/V sync signal polarity configuration

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

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

From: Koji Matsuoka <[email protected]>

commit fd1adef3bff0663c5ac31b45bc4a05fafd43d19b upstream.

The VSL and HSL bits in the DSMR register set the corresponding horizontal and vertical sync signal polarity to active high. The code got it the wrong way around, fix it.

Signed-off-by Koji Matsuoka <[email protected]>

Signed-off-by Laurent Pinchart <[email protected]>

Signed-off-by Thong Ho <[email protected]>

Signed-off-by Nhan Nguyen <[email protected]>

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 drivers/gpu/drm/rcar-du/rcar_du_crtc.c |    4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

drivers/gpu/drm/rcar-du/rcar_du_crtc.c +2 -2

@@ -149,8 +149,8 @@ static void rcar_du_crtc_set_display_tim
 	rcar_du_group_write(rcrtc->group, rcrtc->index % 2 ? OTAR2 : OTAR, 0);
 
 	/* Signal polarities */
-	value = ((mode->flags & DRM_MODE_FLAG_PVSYNC) ? 0 : DSMR_VSL)
-	      | ((mode->flags & DRM_MODE_FLAG_PHSYNC) ? 0 : DSMR_HSL)
+	value = ((mode->flags & DRM_MODE_FLAG_PVSYNC) ? DSMR_VSL : 0)
+	      | ((mode->flags & DRM_MODE_FLAG_PHSYNC) ? DSMR_HSL : 0)
 	      | DSMR_DIPM_DISP | DSMR_CSPM;
 	rcar_du_crtc_write(rcrtc, DSMR, value);

Greg Kroah-Hartman

author maintainer

2017-08-28 08:05 UTC #47 lore raw

PATCH 48/84 tracing: Call clear_boot_tracer() at lateinit_sync

Link https://bugzilla.kernel.org/show_bug.cgi?id=196551

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

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

From: Steven Rostedt (VMware) <[email protected]>

commit 4bb0f0e73c8c30917d169c4a0f1ac083690c545b upstream.

The clear_boot_tracer function is used to reset the default_bootup_tracer string to prevent it from being accessed after boot, as it originally points to init data. But since clear_boot_tracer() is called via the init_lateinit() call, it races with the initcall for registering the hwlat tracer. If someone adds "ftrace=hwlat" to the kernel command line, depending on how the linker sets up the text, the saved command line may be cleared, and the hwlat tracer never is initialized.

Simply have the clear_boot_tracer() be called by initcall_lateinit_sync() as that's for tasks to be called after lateinit.

Fixes e7c15cd8a ("tracing: Added hardware latency tracer")

Reported-by Zamir SUN <[email protected]>

Signed-off-by Steven Rostedt (VMware) <[email protected]>

Signed-off-by Greg Kroah-Hartman <[email protected]>

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

kernel/trace/trace.c +1 -1

@@ -7767,4 +7767,4 @@ __init static int clear_boot_tracer(void
 }
 
 fs_initcall(tracer_init_tracefs);
-late_initcall(clear_boot_tracer);
+late_initcall_sync(clear_boot_tracer);

Greg Kroah-Hartman

author maintainer

2017-08-28 08:12 UTC #48 lore raw

PATCH 49/84 tracing: Fix kmemleak in tracing_map_array_free()

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

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

From: Chunyu Hu <[email protected]>

commit 475bb3c69ab05df2a6ecef6acc2393703d134180 upstream.

kmemleak reported the below leak when I was doing clear of the hist trigger. With this patch, the kmeamleak is gone.

unreferenced object 0xffff94322b63d760 (size 32):
comm "bash", pid 1522, jiffies 4403687962 (age 2442.311s) hex dump (first 32 bytes):

    00 01 00 00 04 00 00 00 08 00 00 00 ff 00 00 00  ................
    10 00 00 00 00 00 00 00 80 a8 7a f2 31 94 ff ff  ..........z.1...
  backtrace:
    [<ffffffff9e96c27a>] kmemleak_alloc+0x4a/0xa0
    [<ffffffff9e424cba>] kmem_cache_alloc_trace+0xca/0x1d0
    [<ffffffff9e377736>] tracing_map_array_alloc+0x26/0x140
    [<ffffffff9e261be0>] kretprobe_trampoline+0x0/0x50
    [<ffffffff9e38b935>] create_hist_data+0x535/0x750
    [<ffffffff9e38bd47>] event_hist_trigger_func+0x1f7/0x420
    [<ffffffff9e38893d>] event_trigger_write+0xfd/0x1a0
    [<ffffffff9e44dfc7>] __vfs_write+0x37/0x170
    [<ffffffff9e44f552>] vfs_write+0xb2/0x1b0
    [<ffffffff9e450b85>] SyS_write+0x55/0xc0
    [<ffffffff9e203857>] do_syscall_64+0x67/0x150
    [<ffffffff9e977ce7>] return_from_SYSCALL_64+0x0/0x6a
    [<ffffffffffffffff>] 0xffffffffffffffff
unreferenced object 0xffff9431f27aa880 (size 128):
  comm "bash", pid 1522, jiffies 4403687962 (age 2442.311s)
  hex dump (first 32 bytes):
    00 00 8c 2a 32 94 ff ff 00 f0 8b 2a 32 94 ff ff  ...*2......*2...
    00 e0 8b 2a 32 94 ff ff 00 d0 8b 2a 32 94 ff ff  ...*2......*2...
  backtrace:
    [<ffffffff9e96c27a>] kmemleak_alloc+0x4a/0xa0
    [<ffffffff9e425348>] __kmalloc+0xe8/0x220
    [<ffffffff9e3777c1>] tracing_map_array_alloc+0xb1/0x140
    [<ffffffff9e261be0>] kretprobe_trampoline+0x0/0x50
    [<ffffffff9e38b935>] create_hist_data+0x535/0x750
    [<ffffffff9e38bd47>] event_hist_trigger_func+0x1f7/0x420
    [<ffffffff9e38893d>] event_trigger_write+0xfd/0x1a0
    [<ffffffff9e44dfc7>] __vfs_write+0x37/0x170
    [<ffffffff9e44f552>] vfs_write+0xb2/0x1b0
    [<ffffffff9e450b85>] SyS_write+0x55/0xc0
    [<ffffffff9e203857>] do_syscall_64+0x67/0x150
    [<ffffffff9e977ce7>] return_from_SYSCALL_64+0x0/0x6a
    [<ffffffffffffffff>] 0xffffffffffffffff

Link http://lkml.kernel.org/r/[email protected] open here

Fixes 08d43a5fa063 ("tracing: Add lock-free tracing_map")

Signed-off-by Chunyu Hu <[email protected]>

Signed-off-by Steven Rostedt (VMware) <[email protected]>

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 kernel/trace/tracing_map.c |   11 +++++++----
 1 file changed, 7 insertions(+), 4 deletions(-)

kernel/trace/tracing_map.c +7 -4

@@ -221,16 +221,19 @@ void tracing_map_array_free(struct traci
 	if (!a)
 		return;
 
-	if (!a->pages) {
-		kfree(a);
-		return;
-	}
+	if (!a->pages)
+		goto free;
 
 	for (i = 0; i < a->n_pages; i++) {
 		if (!a->pages[i])
 			break;
 		free_page((unsigned long)a->pages[i]);
 	}
+
+	kfree(a->pages);
+
+ free:
+	kfree(a);
 }
 
 struct tracing_map_array *tracing_map_array_alloc(unsigned int n_elts,

Greg Kroah-Hartman

author maintainer

2017-08-28 08:12 UTC #49 lore raw

PATCH 50/84 tracing: Fix freeing of filter in create_filter() when set_str is false

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

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

From: Steven Rostedt (VMware) <[email protected]>

commit 8b0db1a5bdfcee0dbfa89607672598ae203c9045 upstream.

Performing the following task with kmemleak enabled:

 # cd /sys/kernel/tracing/events/irq/irq_handler_entry/
 # echo 'enable_event:kmem:kmalloc:3 if irq >' > trigger
 # echo 'enable_event:kmem:kmalloc:3 if irq > 31' > trigger
 # echo scan > /sys/kernel/debug/kmemleak
 # cat /sys/kernel/debug/kmemleak
unreferenced object 0xffff8800b9290308 (size 32):
  comm "bash", pid 1114, jiffies 4294848451 (age 141.139s)
  hex dump (first 32 bytes):
    00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00  ................
    00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00  ................
  backtrace:
    [<ffffffff81cef5aa>] kmemleak_alloc+0x4a/0xa0
    [<ffffffff81357938>] kmem_cache_alloc_trace+0x158/0x290
    [<ffffffff81261c09>] create_filter_start.constprop.28+0x99/0x940
    [<ffffffff812639c9>] create_filter+0xa9/0x160
    [<ffffffff81263bdc>] create_event_filter+0xc/0x10
    [<ffffffff812655e5>] set_trigger_filter+0xe5/0x210
    [<ffffffff812660c4>] event_enable_trigger_func+0x324/0x490
    [<ffffffff812652e2>] event_trigger_write+0x1a2/0x260
    [<ffffffff8138cf87>] __vfs_write+0xd7/0x380
    [<ffffffff8138f421>] vfs_write+0x101/0x260
    [<ffffffff8139187b>] SyS_write+0xab/0x130
    [<ffffffff81cfd501>] entry_SYSCALL_64_fastpath+0x1f/0xbe
    [<ffffffffffffffff>] 0xffffffffffffffff

The function create_filter() is passed a 'filterp' pointer that gets allocated, and if "set_str" is true, it is up to the caller to free it, even on error. The problem is that the pointer is not freed by create_filter() when set_str is false. This is a bug, and it is not up to the caller to free the filter on error if it doesn't care about the string.

Link http://lkml.kernel.org/r/[email protected] open here

Fixes 38b78eb85 ("tracing: Factorize filter creation")

Reported-by Chunyu Hu <[email protected]>

Tested-by Chunyu Hu <[email protected]>

Signed-off-by Steven Rostedt (VMware) <[email protected]>

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 kernel/trace/trace_events_filter.c |    4 ++++
 1 file changed, 4 insertions(+)

kernel/trace/trace_events_filter.c +4 -0

@@ -1926,6 +1926,10 @@ static int create_filter(struct trace_ev
 		if (err && set_str)
 			append_filter_err(ps, filter);
 	}
+	if (err && !set_str) {
+		free_event_filter(filter);
+		filter = NULL;
+	}
 	create_filter_finish(ps);
 
 	*filterp = filter;

Greg Kroah-Hartman

author maintainer

2017-08-28 08:12 UTC #50 lore raw

PATCH 51/84 kbuild: linker script do not match C names unless LD_DEAD_CODE_DATA_ELIMINATION is configured

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

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

From: Nicholas Piggin <[email protected]>

commit cb87481ee89dbd6609e227afbf64900fb4e5c930 upstream.

The .data and .bss sections were modified in the generic linker script to pull in sections named .data.<C identifier>, which are generated by gcc with -ffunction-sections and -fdata-sections options.

The problem with this pattern is it can also match section names that Linux defines explicitly, e.g., .data.unlikely. This can cause Linux sections to get moved into the wrong place.

The way to avoid this is to use ".." separators for explicit section names (the dot character is valid in a section name but not a C identifier). However currently there are sections which don't follow this rule, so for now just disable the wild card by default.

Example: http://marc.info/?l=linux-arm-kernel&m=150106824024221&w=2

Fixes b67067f1176df ("kbuild: allow archs to select link dead code/data elimination")

Signed-off-by Nicholas Piggin <[email protected]>

Signed-off-by Masahiro Yamada <[email protected]>

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 include/asm-generic/vmlinux.lds.h |   38 ++++++++++++++++++++++++++------------
 1 file changed, 26 insertions(+), 12 deletions(-)

include/asm-generic/vmlinux.lds.h +26 ~~-12~~

@@ -60,6 +60,22 @@
 #define ALIGN_FUNCTION()  . = ALIGN(8)
 
 /*
+ * LD_DEAD_CODE_DATA_ELIMINATION option enables -fdata-sections, which
+ * generates .data.identifier sections, which need to be pulled in with
+ * .data. We don't want to pull in .data..other sections, which Linux
+ * has defined. Same for text and bss.
+ */
+#ifdef CONFIG_LD_DEAD_CODE_DATA_ELIMINATION
+#define TEXT_MAIN .text .text.[0-9a-zA-Z_]*
+#define DATA_MAIN .data .data.[0-9a-zA-Z_]*
+#define BSS_MAIN .bss .bss.[0-9a-zA-Z_]*
+#else
+#define TEXT_MAIN .text
+#define DATA_MAIN .data
+#define BSS_MAIN .bss
+#endif
+
+/*
  * Align to a 32 byte boundary equal to the
  * alignment gcc 4.5 uses for a struct
  */

@@ -198,12 +214,9 @@
 
 /*
  * .data section
- * LD_DEAD_CODE_DATA_ELIMINATION option enables -fdata-sections generates
- * .data.identifier which needs to be pulled in with .data, but don't want to
- * pull in .data..stuff which has its own requirements. Same for bss.
  */
 #define DATA_DATA							\
-	*(.data .data.[0-9a-zA-Z_]*)					\
+	*(DATA_MAIN)							\
 	*(.ref.data)							\
 	*(.data..shared_aligned) /* percpu related */			\
 	MEM_KEEP(init.data)						\

@@ -436,16 +449,17 @@
 		VMLINUX_SYMBOL(__security_initcall_end) = .;		\
 	}
 
-/* .text section. Map to function alignment to avoid address changes
+/*
+ * .text section. Map to function alignment to avoid address changes
  * during second ld run in second ld pass when generating System.map
- * LD_DEAD_CODE_DATA_ELIMINATION option enables -ffunction-sections generates
- * .text.identifier which needs to be pulled in with .text , but some
- * architectures define .text.foo which is not intended to be pulled in here.
- * Those enabling LD_DEAD_CODE_DATA_ELIMINATION must ensure they don't have
- * conflicting section names, and must pull in .text.[0-9a-zA-Z_]* */
+ *
+ * TEXT_MAIN here will match .text.fixup and .text.unlikely if dead
+ * code elimination is enabled, so these sections should be converted
+ * to use ".." first.
+ */
 #define TEXT_TEXT							\
 		ALIGN_FUNCTION();					\
-		*(.text.hot .text .text.fixup .text.unlikely)		\
+		*(.text.hot TEXT_MAIN .text.fixup .text.unlikely)	\
 		*(.ref.text)						\
 	MEM_KEEP(init.text)						\
 	MEM_KEEP(exit.text)						\

@@ -613,7 +627,7 @@
 		BSS_FIRST_SECTIONS					\
 		*(.bss..page_aligned)					\
 		*(.dynbss)						\
-		*(.bss .bss.[0-9a-zA-Z_]*)				\
+		*(BSS_MAIN)						\
 		*(COMMON)						\
 	}

Greg Kroah-Hartman

author maintainer

2017-08-28 08:13 UTC #51 lore raw

PATCH 52/84 cifs: Fix df output for users with quota limits

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

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

From: Sachin Prabhu <[email protected]>

commit 42bec214d8bd432be6d32a1acb0a9079ecd4d142 upstream.

The df for a SMB2 share triggers a GetInfo call for FS_FULL_SIZE_INFORMATION. The values returned are used to populate struct statfs.

The problem is that none of the information returned by the call contains the total blocks available on the filesystem. Instead we use the blocks available to the user ie. quota limitation when filling out statfs.f_blocks. The information returned does contain Actual free units on the filesystem and is used to populate statfs.f_bfree. For users with quota enabled, it can lead to situations where the total free space reported is more than the total blocks on the system ending up with df reports like the following

 # df -h /mnt/a
Filesystem         Size  Used Avail Use% Mounted on
//192.168.22.10/a  2.5G -2.3G  2.5G    - /mnt/a

To fix this problem, we instead populate both statfs.f_bfree with the same value as statfs.f_bavail ie. CallerAvailableAllocationUnits. This is similar to what is done already in the code for cifs and df now reports the quota information for the user used to mount the share.

 # df --si /mnt/a
Filesystem         Size  Used Avail Use% Mounted on
//192.168.22.10/a  2.7G  101M  2.6G   4% /mnt/a

Signed-off-by Sachin Prabhu <[email protected]>

Signed-off-by Pierguido Lambri <[email protected]>

Signed-off-by Steve French <[email protected]>

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 fs/cifs/smb2pdu.c |    4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

fs/cifs/smb2pdu.c +2 -2

@@ -2930,8 +2930,8 @@ copy_fs_info_to_kstatfs(struct smb2_fs_f
 	kst->f_bsize = le32_to_cpu(pfs_inf->BytesPerSector) *
 			  le32_to_cpu(pfs_inf->SectorsPerAllocationUnit);
 	kst->f_blocks = le64_to_cpu(pfs_inf->TotalAllocationUnits);
-	kst->f_bfree  = le64_to_cpu(pfs_inf->ActualAvailableAllocationUnits);
-	kst->f_bavail = le64_to_cpu(pfs_inf->CallerAvailableAllocationUnits);
+	kst->f_bfree  = kst->f_bavail =
+			le64_to_cpu(pfs_inf->CallerAvailableAllocationUnits);
 	return;
 }

Greg Kroah-Hartman

author maintainer

2017-08-28 08:12 UTC #52 lore raw

PATCH 53/84 cifs: return ENAMETOOLONG for overlong names in cifs_open()/cifs_lookup()

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

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

From: Ronnie Sahlberg <[email protected]>

commit d3edede29f74d335f81d95a4588f5f136a9f7dcf upstream.

Add checking for the path component length and verify it is <= the maximum that the server advertizes via FileFsAttributeInformation.

With this patch cifs.ko will now return ENAMETOOLONG instead of ENOENT when users to access an overlong path.

To test this, try to cd into a (non-existing) directory on a CIFS share that has a too long name:
cd /mnt/aaaaaaaaaaaaaaa...

and it now should show a good error message from the shell:
bash: cd: /mnt/aaaaaaaaaaaaaaaa...aaaaaa: File name too long

rh bz 1153996

Signed-off-by Ronnie Sahlberg <[email protected]>

Signed-off-by Steve French <[email protected]>

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 fs/cifs/dir.c |   18 ++++++++++++------
 1 file changed, 12 insertions(+), 6 deletions(-)

fs/cifs/dir.c +12 -6

@@ -183,15 +183,20 @@ cifs_bp_rename_retry:
 }
 
 /*
+ * Don't allow path components longer than the server max.
  * Don't allow the separator character in a path component.
  * The VFS will not allow "/", but "\" is allowed by posix.
  */
 static int
-check_name(struct dentry *direntry)
+check_name(struct dentry *direntry, struct cifs_tcon *tcon)
 {
 	struct cifs_sb_info *cifs_sb = CIFS_SB(direntry->d_sb);
 	int i;
 
+	if (unlikely(direntry->d_name.len >
+		     tcon->fsAttrInfo.MaxPathNameComponentLength))
+		return -ENAMETOOLONG;
+
 	if (!(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_POSIX_PATHS)) {
 		for (i = 0; i < direntry->d_name.len; i++) {
 			if (direntry->d_name.name[i] == '\\') {

@@ -489,10 +494,6 @@ cifs_atomic_open(struct inode *inode, st
 		return finish_no_open(file, res);
 	}
 
-	rc = check_name(direntry);
-	if (rc)
-		return rc;
-
 	xid = get_xid();
 
 	cifs_dbg(FYI, "parent inode = 0x%p name is: %pd and dentry = 0x%p\n",

@@ -505,6 +506,11 @@ cifs_atomic_open(struct inode *inode, st
 	}
 
 	tcon = tlink_tcon(tlink);
+
+	rc = check_name(direntry, tcon);
+	if (rc)
+		goto out_free_xid;
+
 	server = tcon->ses->server;
 
 	if (server->ops->new_lease_key)

@@ -765,7 +771,7 @@ cifs_lookup(struct inode *parent_dir_ino
 	}
 	pTcon = tlink_tcon(tlink);
 
-	rc = check_name(direntry);
+	rc = check_name(direntry, pTcon);
 	if (rc)
 		goto lookup_out;

Greg Kroah-Hartman

author maintainer

2017-08-28 08:12 UTC #53 lore raw

PATCH 54/84 nfsd: Limit end of page list when decoding NFSv4 WRITE

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

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

From: Chuck Lever <[email protected]>

commit fc788f64f1f3eb31e87d4f53bcf1ab76590d5838 upstream.

When processing an NFSv4 WRITE operation, argp->end should never point past the end of the data in the final page of the page list. Otherwise, nfsd4_decode_compound can walk into uninitialized memory.

More critical, nfsd4_decode_write is failing to increment argp->pagelen when it increments argp->pagelist. This can cause later xdr decoders to assume more data is available than really is, which can cause server crashes on malformed requests.

Signed-off-by Chuck Lever <[email protected]>

Signed-off-by J. Bruce Fields <[email protected]>

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 fs/nfsd/nfs4xdr.c |    6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

fs/nfsd/nfs4xdr.c +2 -4

@@ -129,7 +129,7 @@ static void next_decode_page(struct nfsd
 	argp->p = page_address(argp->pagelist[0]);
 	argp->pagelist++;
 	if (argp->pagelen < PAGE_SIZE) {
-		argp->end = argp->p + (argp->pagelen>>2);
+		argp->end = argp->p + XDR_QUADLEN(argp->pagelen);
 		argp->pagelen = 0;
 	} else {
 		argp->end = argp->p + (PAGE_SIZE>>2);

@@ -1246,9 +1246,7 @@ nfsd4_decode_write(struct nfsd4_compound
 		argp->pagelen -= pages * PAGE_SIZE;
 		len -= pages * PAGE_SIZE;
 
-		argp->p = (__be32 *)page_address(argp->pagelist[0]);
-		argp->pagelist++;
-		argp->end = argp->p + XDR_QUADLEN(PAGE_SIZE);
+		next_decode_page(argp);
 	}
 	argp->p += XDR_QUADLEN(len);

Greg Kroah-Hartman

author maintainer

2017-08-28 08:13 UTC #54 lore raw

PATCH 55/84 ftrace: Check for null ret_stack on profile function graph entry function

Link https://bugzilla.kernel.org/show_bug.cgi?id=196611

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

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

From: Steven Rostedt (VMware) <[email protected]>

commit a8f0f9e49956a74718874b800251455680085600 upstream.

There's a small race when function graph shutsdown and the calling of the registered function graph entry callback. The callback must not reference the task's ret_stack without first checking that it is not NULL. Note, when a ret_stack is allocated for a task, it stays allocated until the task exits. The problem here, is that function_graph is shutdown, and a new task was created, which doesn't have its ret_stack allocated. But since some of the functions are still being traced, the callbacks can still be called.

The normal function_graph code handles this, but starting with commit 8861dd303c ("ftrace: Access ret_stack->subtime only in the function profiler") the profiler code references the ret_stack on function entry, but doesn't check if it is NULL first.

Fixes 8861dd303c ("ftrace: Access ret_stack->subtime only in the function profiler")

Reported-by [email protected]

Signed-off-by Steven Rostedt (VMware) <[email protected]>

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 kernel/trace/ftrace.c |    4 ++++
 1 file changed, 4 insertions(+)

kernel/trace/ftrace.c +4 -0

@@ -876,6 +876,10 @@ static int profile_graph_entry(struct ft
 
 	function_profile_call(trace->func, 0, NULL, NULL);
 
+	/* If function graph is shutting down, ret_stack can be NULL */
+	if (!current->ret_stack)
+		return 0;
+
 	if (index >= 0 && index < FTRACE_RETFUNC_DEPTH)
 		current->ret_stack[index].subtime = 0;

Greg Kroah-Hartman

author maintainer

2017-08-28 08:13 UTC #55 lore raw

PATCH 56/84 perf/core: Fix group {cpu,task} validation

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

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

From: Mark Rutland <[email protected]>

commit 64aee2a965cf2954a038b5522f11d2cd2f0f8f3e upstream.

Regardless of which events form a group, it does not make sense for the events to target different tasks and/or CPUs, as this leaves the group inconsistent and impossible to schedule. The core perf code assumes that these are consistent across (successfully intialised) groups.

Core perf code only verifies this when moving SW events into a HW context. Thus, we can violate this requirement for pure SW groups and pure HW groups, unless the relevant PMU driver happens to perform this verification itself. These mismatched groups subsequently wreak havoc elsewhere.

For example, we handle watchpoints as SW events, and reserve watchpoint HW on a per-CPU basis at pmu::event_init() time to ensure that any event that is initialised is guaranteed to have a slot at pmu::add() time. However, the core code only checks the group leader's cpu filter (via event_filter_match()), and can thus install follower events onto CPUs violating thier (mismatched) CPU filters, potentially installing them into a CPU without sufficient reserved slots.

This can be triggered with the below test case, resulting in warnings from arch backends.

  #define _GNU_SOURCE
  #include <linux/hw_breakpoint.h>
  #include <linux/perf_event.h>
  #include <sched.h>
  #include <stdio.h>
  #include <sys/prctl.h>
  #include <sys/syscall.h>
  #include <unistd.h>

static int perf_event_open(struct perf_event_attr *attr, pid_t pid, int cpu,
int group_fd, unsigned long flags)

  {
	return syscall(__NR_perf_event_open, attr, pid, cpu, group_fd, flags);

}

char watched_char;

struct perf_event_attr wp_attr = {
.type = PERF_TYPE_BREAKPOINT,
.bp_type = HW_BREAKPOINT_RW,
.bp_addr = (unsigned long)&watched_char,
.bp_len = 1,
.size = sizeof(wp_attr),
};

int main(int argc, char *argv[])

  {
	int leader, ret;
	cpu_set_t cpus;

	/*
	 * Force use of CPU0 to ensure our CPU0-bound events get scheduled.
	 */
	CPU_ZERO(&cpus);
	CPU_SET(0, &cpus);
	ret = sched_setaffinity(0, sizeof(cpus), &cpus);
	if (ret) {
		printf("Unable to set cpu affinity\n");
		return 1;
	}

	/* open leader event, bound to this task, CPU0 only */
	leader = perf_event_open(&wp_attr, 0, 0, -1, 0);
	if (leader < 0) {
		printf("Couldn't open leader: %d\n", leader);
		return 1;
	}

	/*
	 * Open a follower event that is bound to the same task, but a
	 * different CPU. This means that the group should never be possible to
	 * schedule.
	 */
	ret = perf_event_open(&wp_attr, 0, 1, leader, 0);
	if (ret < 0) {
		printf("Couldn't open mismatched follower: %d\n", ret);
		return 1;
	} else {
		printf("Opened leader/follower with mismastched CPUs\n");
	}

	/*
	 * Open as many independent events as we can, all bound to the same
	 * task, CPU0 only.
	 */
	do {
		ret = perf_event_open(&wp_attr, 0, 0, -1, 0);
	} while (ret >= 0);

	/*
	 * Force enable/disble all events to trigger the erronoeous
	 * installation of the follower event.
	 */
	printf("Opened all events. Toggling..\n");
	for (;;) {
		prctl(PR_TASK_PERF_EVENTS_DISABLE, 0, 0, 0, 0);
		prctl(PR_TASK_PERF_EVENTS_ENABLE, 0, 0, 0, 0);
	}

	return 0;

}

Fix this by validating this requirement regardless of whether we're moving events.

Signed-off-by Mark Rutland <[email protected]>

Signed-off-by Peter Zijlstra (Intel) <[email protected]>

Cc Alexander Shishkin <[email protected]>

Cc Arnaldo Carvalho de Melo <[email protected]>

Cc Linus Torvalds <[email protected]>

Cc Peter Zijlstra <[email protected]>

Cc Thomas Gleixner <[email protected]>

Cc Zhou Chengming <[email protected]>

Link http://lkml.kernel.org/r/[email protected] open here

Signed-off-by Ingo Molnar <[email protected]>

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 kernel/events/core.c |   39 +++++++++++++++++++--------------------
 1 file changed, 19 insertions(+), 20 deletions(-)

kernel/events/core.c +19 ~~-20~~

@@ -9786,28 +9786,27 @@ SYSCALL_DEFINE5(perf_event_open,
 			goto err_context;
 
 		/*
-		 * Do not allow to attach to a group in a different
-		 * task or CPU context:
+		 * Make sure we're both events for the same CPU;
+		 * grouping events for different CPUs is broken; since
+		 * you can never concurrently schedule them anyhow.
 		 */
-		if (move_group) {
-			/*
-			 * Make sure we're both on the same task, or both
-			 * per-cpu events.
-			 */
-			if (group_leader->ctx->task != ctx->task)
-				goto err_context;
+		if (group_leader->cpu != event->cpu)
+			goto err_context;
+
+		/*
+		 * Make sure we're both on the same task, or both
+		 * per-CPU events.
+		 */
+		if (group_leader->ctx->task != ctx->task)
+			goto err_context;
 
-			/*
-			 * Make sure we're both events for the same CPU;
-			 * grouping events for different CPUs is broken; since
-			 * you can never concurrently schedule them anyhow.
-			 */
-			if (group_leader->cpu != event->cpu)
-				goto err_context;
-		} else {
-			if (group_leader->ctx != ctx)
-				goto err_context;
-		}
+		/*
+		 * Do not allow to attach to a group in a different task
+		 * or CPU context. If we're moving SW events, we'll fix
+		 * this up later, so allow that.
+		 */
+		if (!move_group && group_leader->ctx != ctx)
+			goto err_context;
 
 		/*
 		 * Only a group leader can be exclusive or pinned

Greg Kroah-Hartman

author maintainer

2017-08-28 08:05 UTC #56 lore raw

PATCH 57/84 perf probe: Fix --funcs to show correct symbols for offline module

Link http://lkml.kernel.org/r/148350053478.19001.15435255244512631545.stgit@devbox open here

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

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

From: Masami Hiramatsu <[email protected]>

commit eebc509b20881b92d62e317b2c073e57c5f200f0 upstream.

Fix --funcs (-F) option to show correct symbols for offline module. Since previous perf-probe uses machine__findnew_module_map() for offline module, even if user passes a module file (with full path) which is for other architecture, perf-probe always tries to load symbol map for current kernel module.

This fix uses dso__new_map() to load the map from given binary as same as a map for user applications.

Signed-off-by Masami Hiramatsu <[email protected]>

Cc Jiri Olsa <[email protected]>

Cc Namhyung Kim <[email protected]>

Cc Peter Zijlstra <[email protected]>

Signed-off-by Arnaldo Carvalho de Melo <[email protected]>

Cc Krister Johansen <[email protected]>

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 tools/perf/util/probe-event.c |   25 ++++++-------------------
 1 file changed, 6 insertions(+), 19 deletions(-)

tools/perf/util/probe-event.c +6 ~~-19~~

@@ -163,7 +163,7 @@ static struct map *kernel_get_module_map
 
 	/* A file path -- this is an offline module */
 	if (module && strchr(module, '/'))
-		return machine__findnew_module_map(host_machine, 0, module);
+		return dso__new_map(module);
 
 	if (!module)
 		module = "kernel";

@@ -173,6 +173,7 @@ static struct map *kernel_get_module_map
 		if (strncmp(pos->dso->short_name + 1, module,
 			    pos->dso->short_name_len - 2) == 0 &&
 		    module[pos->dso->short_name_len - 2] == '\0') {
+			map__get(pos);
 			return pos;
 		}
 	}

@@ -188,15 +189,6 @@ struct map *get_target_map(const char *t
 		return kernel_get_module_map(target);
 }
 
-static void put_target_map(struct map *map, bool user)
-{
-	if (map && user) {
-		/* Only the user map needs to be released */
-		map__put(map);
-	}
-}
-
-
 static int convert_exec_to_group(const char *exec, char **result)
 {
 	char *ptr1, *ptr2, *exec_copy;

@@ -412,7 +404,7 @@ static int find_alternative_probe_point(
 	}
 
 out:
-	put_target_map(map, uprobes);
+	map__put(map);
 	return ret;
 
 }

@@ -2944,7 +2936,7 @@ static int find_probe_trace_events_from_
 	}
 
 out:
-	put_target_map(map, pev->uprobes);
+	map__put(map);
 	free(syms);
 	return ret;

@@ -3437,10 +3429,7 @@ int show_available_funcs(const char *tar
 		return ret;
 
 	/* Get a symbol map */
-	if (user)
-		map = dso__new_map(target);
-	else
-		map = kernel_get_module_map(target);
+	map = get_target_map(target, user);
 	if (!map) {
 		pr_err("Failed to get a map for %s\n", (target) ? : "kernel");
 		return -EINVAL;

@@ -3472,9 +3461,7 @@ int show_available_funcs(const char *tar
         }
 
 end:
-	if (user) {
-		map__put(map);
-	}
+	map__put(map);
 	exit_probe_symbol_maps();
 
 	return ret;

Greg Kroah-Hartman

author maintainer

2017-08-28 08:13 UTC #57 lore raw

PATCH 58/84 perf/x86/intel/rapl: Make package handling more robust

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

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

From: Thomas Gleixner <[email protected]>

commit dd86e373e09fb16b83e8adf5c48c421a4ca76468 upstream.

The package management code in RAPL relies on package mapping being available before a CPU is started. This changed with:

9d85eb9119f4 ("x86/smpboot: Make logical package management more robust")

because the ACPI/BIOS information turned out to be unreliable, but that left RAPL in broken state. This was not noticed because on a regular boot all CPUs are online before RAPL is initialized.

A possible fix would be to reintroduce the mess which allocates a package data structure in CPU prepare and when it turns out to already exist in starting throw it away later in the CPU online callback. But that's a horrible hack and not required at all because RAPL becomes functional for perf only in the CPU online callback. That's correct because user space is not yet informed about the CPU being onlined, so nothing caan rely on RAPL being available on that particular CPU.

Move the allocation to the CPU online callback and simplify the hotplug handling. At this point the package mapping is established and correct.

This also adds a missing check for available package data in the event_init() function.

Reported-by Yasuaki Ishimatsu <[email protected]>

Signed-off-by Thomas Gleixner <[email protected]>

Cc Alexander Shishkin <[email protected]>

Cc Arnaldo Carvalho de Melo <[email protected]>

Cc Jiri Olsa <[email protected]>

Cc Linus Torvalds <[email protected]>

Cc Peter Zijlstra <[email protected]>

Cc Sebastian Siewior <[email protected]>

Cc Stephane Eranian <[email protected]>

Cc Vince Weaver <[email protected]>

Fixes 9d85eb9119f4 ("x86/smpboot: Make logical package management more robust")

Link http://lkml.kernel.org/r/[email protected] open here

Signed-off-by Ingo Molnar <[email protected]>

[ jwang: backport to 4.9 fix Null pointer deref during hotplug cpu.]

Signed-off-by Jack Wang <[email protected]>

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 arch/x86/events/intel/rapl.c |   58 ++++++++++++++++++-------------------------
 include/linux/cpuhotplug.h   |    1 
 2 files changed, 25 insertions(+), 34 deletions(-)

arch/x86/events/intel/rapl.c +25 ~~-33~~

@@ -161,7 +161,13 @@ static u64 rapl_timer_ms;
 
 static inline struct rapl_pmu *cpu_to_rapl_pmu(unsigned int cpu)
 {
-	return rapl_pmus->pmus[topology_logical_package_id(cpu)];
+	unsigned int pkgid = topology_logical_package_id(cpu);
+
+	/*
+	 * The unsigned check also catches the '-1' return value for non
+	 * existent mappings in the topology map.
+	 */
+	return pkgid < rapl_pmus->maxpkg ? rapl_pmus->pmus[pkgid] : NULL;
 }
 
 static inline u64 rapl_read_counter(struct perf_event *event)

@@ -402,6 +408,8 @@ static int rapl_pmu_event_init(struct pe
 
 	/* must be done before validate_group */
 	pmu = cpu_to_rapl_pmu(event->cpu);
+	if (!pmu)
+		return -EINVAL;
 	event->cpu = pmu->cpu;
 	event->pmu_private = pmu;
 	event->hw.event_base = msr;

@@ -585,6 +593,19 @@ static int rapl_cpu_online(unsigned int
 	struct rapl_pmu *pmu = cpu_to_rapl_pmu(cpu);
 	int target;
 
+	if (!pmu) {
+		pmu = kzalloc_node(sizeof(*pmu), GFP_KERNEL, cpu_to_node(cpu));
+		if (!pmu)
+			return -ENOMEM;
+
+		raw_spin_lock_init(&pmu->lock);
+		INIT_LIST_HEAD(&pmu->active_list);
+		pmu->pmu = &rapl_pmus->pmu;
+		pmu->timer_interval = ms_to_ktime(rapl_timer_ms);
+		rapl_hrtimer_init(pmu);
+
+		rapl_pmus->pmus[topology_logical_package_id(cpu)] = pmu;
+	}
 	/*
 	 * Check if there is an online cpu in the package which collects rapl
 	 * events already.

@@ -598,27 +619,6 @@ static int rapl_cpu_online(unsigned int
 	return 0;
 }
 
-static int rapl_cpu_prepare(unsigned int cpu)
-{
-	struct rapl_pmu *pmu = cpu_to_rapl_pmu(cpu);
-
-	if (pmu)
-		return 0;
-
-	pmu = kzalloc_node(sizeof(*pmu), GFP_KERNEL, cpu_to_node(cpu));
-	if (!pmu)
-		return -ENOMEM;
-
-	raw_spin_lock_init(&pmu->lock);
-	INIT_LIST_HEAD(&pmu->active_list);
-	pmu->pmu = &rapl_pmus->pmu;
-	pmu->timer_interval = ms_to_ktime(rapl_timer_ms);
-	pmu->cpu = -1;
-	rapl_hrtimer_init(pmu);
-	rapl_pmus->pmus[topology_logical_package_id(cpu)] = pmu;
-	return 0;
-}
-
 static int rapl_check_hw_unit(bool apply_quirk)
 {
 	u64 msr_rapl_power_unit_bits;

@@ -804,28 +804,21 @@ static int __init rapl_pmu_init(void)
 	 * Install callbacks. Core will call them for each online cpu.
 	 */
 
-	ret = cpuhp_setup_state(CPUHP_PERF_X86_RAPL_PREP, "PERF_X86_RAPL_PREP",
-				rapl_cpu_prepare, NULL);
-	if (ret)
-		goto out;
-
 	ret = cpuhp_setup_state(CPUHP_AP_PERF_X86_RAPL_ONLINE,
 				"AP_PERF_X86_RAPL_ONLINE",
 				rapl_cpu_online, rapl_cpu_offline);
 	if (ret)
-		goto out1;
+		goto out;
 
 	ret = perf_pmu_register(&rapl_pmus->pmu, "power", -1);
 	if (ret)
-		goto out2;
+		goto out1;
 
 	rapl_advertise();
 	return 0;
 
-out2:
-	cpuhp_remove_state(CPUHP_AP_PERF_X86_RAPL_ONLINE);
 out1:
-	cpuhp_remove_state(CPUHP_PERF_X86_RAPL_PREP);
+	cpuhp_remove_state(CPUHP_AP_PERF_X86_RAPL_ONLINE);
 out:
 	pr_warn("Initialization failed (%d), disabled\n", ret);
 	cleanup_rapl_pmus();

@@ -836,7 +829,6 @@ module_init(rapl_pmu_init);
 static void __exit intel_rapl_exit(void)
 {
 	cpuhp_remove_state_nocalls(CPUHP_AP_PERF_X86_RAPL_ONLINE);
-	cpuhp_remove_state_nocalls(CPUHP_PERF_X86_RAPL_PREP);
 	perf_pmu_unregister(&rapl_pmus->pmu);
 	cleanup_rapl_pmus();
 }

include/linux/cpuhotplug.h +0 -1

@@ -10,7 +10,6 @@ enum cpuhp_state {
 	CPUHP_PERF_X86_PREPARE,
 	CPUHP_PERF_X86_UNCORE_PREP,
 	CPUHP_PERF_X86_AMD_UNCORE_PREP,
-	CPUHP_PERF_X86_RAPL_PREP,
 	CPUHP_PERF_BFIN,
 	CPUHP_PERF_POWER,
 	CPUHP_PERF_SUPERH,

Greg Kroah-Hartman

author maintainer

2017-08-28 08:13 UTC #58 lore raw

PATCH 59/84 timers: Fix excessive granularity of new timers after a nohz idle

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

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

From: Nicholas Piggin <[email protected]>

commit 2fe59f507a65dbd734b990a11ebc7488f6f87a24 upstream.

When a timer base is idle, it is forwarded when a new timer is added to ensure that granularity does not become excessive. When not idle, the timer tick is expected to increment the base.

However there are several problems:

- If an existing timer is modified, the base is forwarded only after the index is calculated.

- The base is not forwarded by add_timer_on.

- There is a window after a timer is restarted from a nohz idle, after it is marked not-idle and before the timer tick on this CPU, where a timer may be added but the ancient base does not get forwarded.

These result in excessive granularity (a 1 jiffy timeout can blow out to 100s of jiffies), which cause the rcu lockup detector to trigger, among other things.

Fix this by keeping track of whether the timer base has been idle since it was last run or forwarded, and if so then forward it before adding a new timer.

There is still a case where mod_timer optimises the case of a pending timer mod with the same expiry time, where the timer can see excessive granularity relative to the new, shorter interval. A comment is added, but it's not changed because it is an important fastpath for networking.

This has been tested and found to fix the RCU softlockup messages.

Testing was also done with tracing to measure requested versus achieved wakeup latencies for all non-deferrable timers in an idle system (with no lockup watchdogs running). Wakeup latency relative to absolute latency is calculated (note this suffers from round-up skew at low absolute times) and analysed:

max avg std

upstream   506.0    1.20     4.68
patched      2.0    1.08     0.15

The bug was noticed due to the lockup detector Kconfig changes dropping it out of people's .configs and resulting in larger base clk skew When the lockup detectors are enabled, no CPU can go idle for longer than 4 seconds, which limits the granularity errors. Sub-optimal timer behaviour is observable on a smaller scale in that case:

max avg std

upstream     9.0    1.05     0.19
patched      2.0    1.04     0.11

Fixes Fixes: a683f390b93f ("timers: Forward the wheel clock whenever possible")

Signed-off-by Nicholas Piggin <[email protected]>

Signed-off-by Thomas Gleixner <[email protected]>

Tested-by Jonathan Cameron <[email protected]>

Tested-by David Miller <[email protected]>

Cc Stephen Boyd <[email protected]>

Cc John Stultz <[email protected]>

Link http://lkml.kernel.org/r/[email protected] open here

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 kernel/time/timer.c |   50 +++++++++++++++++++++++++++++++++++++++++---------
 1 file changed, 41 insertions(+), 9 deletions(-)

kernel/time/timer.c +41 -9

@@ -201,6 +201,7 @@ struct timer_base {
 	bool			migration_enabled;
 	bool			nohz_active;
 	bool			is_idle;
+	bool			must_forward_clk;
 	DECLARE_BITMAP(pending_map, WHEEL_SIZE);
 	struct hlist_head	vectors[WHEEL_SIZE];
 } ____cacheline_aligned;

@@ -891,13 +892,19 @@ get_target_base(struct timer_base *base,
 
 static inline void forward_timer_base(struct timer_base *base)
 {
-	unsigned long jnow = READ_ONCE(jiffies);
+	unsigned long jnow;
 
 	/*
-	 * We only forward the base when it's idle and we have a delta between
-	 * base clock and jiffies.
+	 * We only forward the base when we are idle or have just come out of
+	 * idle (must_forward_clk logic), and have a delta between base clock
+	 * and jiffies. In the common case, run_timers will take care of it.
 	 */
-	if (!base->is_idle || (long) (jnow - base->clk) < 2)
+	if (likely(!base->must_forward_clk))
+		return;
+
+	jnow = READ_ONCE(jiffies);
+	base->must_forward_clk = base->is_idle;
+	if ((long)(jnow - base->clk) < 2)
 		return;
 
 	/*

@@ -973,6 +980,11 @@ __mod_timer(struct timer_list *timer, un
 	 * same array bucket then just return:
 	 */
 	if (timer_pending(timer)) {
+		/*
+		 * The downside of this optimization is that it can result in
+		 * larger granularity than you would get from adding a new
+		 * timer with this expiry.
+		 */
 		if (timer->expires == expires)
 			return 1;

@@ -983,6 +995,7 @@ __mod_timer(struct timer_list *timer, un
 		 * dequeue/enqueue dance.
 		 */
 		base = lock_timer_base(timer, &flags);
+		forward_timer_base(base);
 
 		clk = base->clk;
 		idx = calc_wheel_index(expires, clk);

@@ -999,6 +1012,7 @@ __mod_timer(struct timer_list *timer, un
 		}
 	} else {
 		base = lock_timer_base(timer, &flags);
+		forward_timer_base(base);
 	}
 
 	timer_stats_timer_set_start_info(timer);

@@ -1028,12 +1042,10 @@ __mod_timer(struct timer_list *timer, un
 			spin_lock(&base->lock);
 			WRITE_ONCE(timer->flags,
 				   (timer->flags & ~TIMER_BASEMASK) | base->cpu);
+			forward_timer_base(base);
 		}
 	}
 
-	/* Try to forward a stale timer base clock */
-	forward_timer_base(base);
-
 	timer->expires = expires;
 	/*
 	 * If 'idx' was calculated above and the base time did not advance

@@ -1150,6 +1162,7 @@ void add_timer_on(struct timer_list *tim
 		WRITE_ONCE(timer->flags,
 			   (timer->flags & ~TIMER_BASEMASK) | cpu);
 	}
+	forward_timer_base(base);
 
 	debug_activate(timer, timer->expires);
 	internal_add_timer(base, timer);

@@ -1538,10 +1551,16 @@ u64 get_next_timer_interrupt(unsigned lo
 		if (!is_max_delta)
 			expires = basem + (u64)(nextevt - basej) * TICK_NSEC;
 		/*
-		 * If we expect to sleep more than a tick, mark the base idle:
+		 * If we expect to sleep more than a tick, mark the base idle.
+		 * Also the tick is stopped so any added timer must forward
+		 * the base clk itself to keep granularity small. This idle
+		 * logic is only maintained for the BASE_STD base, deferrable
+		 * timers may still see large granularity skew (by design).
 		 */
-		if ((expires - basem) > TICK_NSEC)
+		if ((expires - basem) > TICK_NSEC) {
+			base->must_forward_clk = true;
 			base->is_idle = true;
+		}
 	}
 	spin_unlock(&base->lock);

@@ -1651,6 +1670,19 @@ static __latent_entropy void run_timer_s
 {
 	struct timer_base *base = this_cpu_ptr(&timer_bases[BASE_STD]);
 
+	/*
+	 * must_forward_clk must be cleared before running timers so that any
+	 * timer functions that call mod_timer will not try to forward the
+	 * base. idle trcking / clock forwarding logic is only used with
+	 * BASE_STD timers.
+	 *
+	 * The deferrable base does not do idle tracking at all, so we do
+	 * not forward it. This can result in very large variations in
+	 * granularity for deferrable timers, but they can be deferred for
+	 * long periods due to idle.
+	 */
+	base->must_forward_clk = false;
+
 	__run_timers(base);
 	if (IS_ENABLED(CONFIG_NO_HZ_COMMON) && base->nohz_active)
 		__run_timers(this_cpu_ptr(&timer_bases[BASE_DEF]));

Greg Kroah-Hartman

author maintainer

2017-08-28 08:05 UTC #59 lore raw

PATCH 60/84 x86/mm: Fix use-after-free of ldt_struct

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

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

From: Eric Biggers <[email protected]>

commit ccd5b3235180eef3cfec337df1c8554ab151b5cc upstream.

The following commit:

39a0526fb3f7 ("x86/mm: Factor out LDT init from context init")

renamed init_new_context() to init_new_context_ldt() and added a new init_new_context() which calls init_new_context_ldt(). However, the error code of init_new_context_ldt() was ignored. Consequently, if a memory allocation in alloc_ldt_struct() failed during a fork(), the ->context.ldt of the new task remained the same as that of the old task (due to the memcpy() in dup_mm()). ldt_struct's are not intended to be shared, so a use-after-free occurred after one task exited.

Fix the bug by making init_new_context() pass through the error code of init_new_context_ldt().

This bug was found by syzkaller, which encountered the following splat:

    BUG: KASAN: use-after-free in free_ldt_struct.part.2+0x10a/0x150 arch/x86/kernel/ldt.c:116
    Read of size 4 at addr ffff88006d2cb7c8 by task kworker/u9:0/3710

    CPU: 1 PID: 3710 Comm: kworker/u9:0 Not tainted 4.13.0-rc4-next-20170811 #2
    Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Bochs 01/01/2011
    Call Trace:
     __dump_stack lib/dump_stack.c:16 [inline]
     dump_stack+0x194/0x257 lib/dump_stack.c:52
     print_address_description+0x73/0x250 mm/kasan/report.c:252
     kasan_report_error mm/kasan/report.c:351 [inline]
     kasan_report+0x24e/0x340 mm/kasan/report.c:409
     __asan_report_load4_noabort+0x14/0x20 mm/kasan/report.c:429
     free_ldt_struct.part.2+0x10a/0x150 arch/x86/kernel/ldt.c:116
     free_ldt_struct arch/x86/kernel/ldt.c:173 [inline]
     destroy_context_ldt+0x60/0x80 arch/x86/kernel/ldt.c:171
     destroy_context arch/x86/include/asm/mmu_context.h:157 [inline]
     __mmdrop+0xe9/0x530 kernel/fork.c:889
     mmdrop include/linux/sched/mm.h:42 [inline]
     exec_mmap fs/exec.c:1061 [inline]
     flush_old_exec+0x173c/0x1ff0 fs/exec.c:1291
     load_elf_binary+0x81f/0x4ba0 fs/binfmt_elf.c:855
     search_binary_handler+0x142/0x6b0 fs/exec.c:1652
     exec_binprm fs/exec.c:1694 [inline]
     do_execveat_common.isra.33+0x1746/0x22e0 fs/exec.c:1816
     do_execve+0x31/0x40 fs/exec.c:1860
     call_usermodehelper_exec_async+0x457/0x8f0 kernel/umh.c:100
     ret_from_fork+0x2a/0x40 arch/x86/entry/entry_64.S:431

    Allocated by task 3700:
     save_stack_trace+0x16/0x20 arch/x86/kernel/stacktrace.c:59
     save_stack+0x43/0xd0 mm/kasan/kasan.c:447
     set_track mm/kasan/kasan.c:459 [inline]
     kasan_kmalloc+0xad/0xe0 mm/kasan/kasan.c:551
     kmem_cache_alloc_trace+0x136/0x750 mm/slab.c:3627
     kmalloc include/linux/slab.h:493 [inline]
     alloc_ldt_struct+0x52/0x140 arch/x86/kernel/ldt.c:67
     write_ldt+0x7b7/0xab0 arch/x86/kernel/ldt.c:277
     sys_modify_ldt+0x1ef/0x240 arch/x86/kernel/ldt.c:307
     entry_SYSCALL_64_fastpath+0x1f/0xbe

    Freed by task 3700:
     save_stack_trace+0x16/0x20 arch/x86/kernel/stacktrace.c:59
     save_stack+0x43/0xd0 mm/kasan/kasan.c:447
     set_track mm/kasan/kasan.c:459 [inline]
     kasan_slab_free+0x71/0xc0 mm/kasan/kasan.c:524
     __cache_free mm/slab.c:3503 [inline]
     kfree+0xca/0x250 mm/slab.c:3820
     free_ldt_struct.part.2+0xdd/0x150 arch/x86/kernel/ldt.c:121
     free_ldt_struct arch/x86/kernel/ldt.c:173 [inline]
     destroy_context_ldt+0x60/0x80 arch/x86/kernel/ldt.c:171
     destroy_context arch/x86/include/asm/mmu_context.h:157 [inline]
     __mmdrop+0xe9/0x530 kernel/fork.c:889
     mmdrop include/linux/sched/mm.h:42 [inline]
     __mmput kernel/fork.c:916 [inline]
     mmput+0x541/0x6e0 kernel/fork.c:927
     copy_process.part.36+0x22e1/0x4af0 kernel/fork.c:1931
     copy_process kernel/fork.c:1546 [inline]
     _do_fork+0x1ef/0xfb0 kernel/fork.c:2025
     SYSC_clone kernel/fork.c:2135 [inline]
     SyS_clone+0x37/0x50 kernel/fork.c:2129
     do_syscall_64+0x26c/0x8c0 arch/x86/entry/common.c:287
     return_from_SYSCALL_64+0x0/0x7a

Here is a C reproducer:

    #include <asm/ldt.h>
    #include <pthread.h>
    #include <signal.h>
    #include <stdlib.h>
    #include <sys/syscall.h>
    #include <sys/wait.h>
    #include <unistd.h>

    static void *fork_thread(void *_arg)
    {
        fork();
    }

    int main(void)
    {
        struct user_desc desc = { .entry_number = 8191 };

        syscall(__NR_modify_ldt, 1, &desc, sizeof(desc));

        for (;;) {
            if (fork() == 0) {
                pthread_t t;

                srand(getpid());
                pthread_create(&t, NULL, fork_thread, NULL);
                usleep(rand() % 10000);
                syscall(__NR_exit_group, 0);
            }
            wait(NULL);
        }
    }

Note: the reproducer takes advantage of the fact that alloc_ldt_struct() may use vmalloc() to allocate a large ->entries array, and after commit:

5d17a73a2ebe ("vmalloc: back off when the current task is killed")

it is possible for userspace to fail a task's vmalloc() by sending a fatal signal, e.g. via exit_group(). It would be more difficult to reproduce this bug on kernels without that commit.

This bug only affected kernels with CONFIG_MODIFY_LDT_SYSCALL=y.

Signed-off-by Eric Biggers <[email protected]>

Acked-by Dave Hansen <[email protected]>

Cc Andrew Morton <[email protected]>

Cc Andy Lutomirski <[email protected]>

Cc Borislav Petkov <[email protected]>

Cc Brian Gerst <[email protected]>

Cc Christoph Hellwig <[email protected]>

Cc Denys Vlasenko <[email protected]>

Cc Dmitry Vyukov <[email protected]>

Cc Linus Torvalds <[email protected]>

Cc Michal Hocko <[email protected]>

Cc Peter Zijlstra <[email protected]>

Cc Rik van Riel <[email protected]>

Cc Tetsuo Handa <[email protected]>

Cc Thomas Gleixner <[email protected]>

Fixes 39a0526fb3f7 ("x86/mm: Factor out LDT init from context init")

Link http://lkml.kernel.org/r/[email protected] open here

Signed-off-by Ingo Molnar <[email protected]>

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 arch/x86/include/asm/mmu_context.h |    4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

arch/x86/include/asm/mmu_context.h +1 -3

@@ -116,9 +116,7 @@ static inline int init_new_context(struc
 		mm->context.execute_only_pkey = -1;
 	}
 	#endif
-	init_new_context_ldt(tsk, mm);
-
-	return 0;
+	return init_new_context_ldt(tsk, mm);
 }
 static inline void destroy_context(struct mm_struct *mm)
 {

--
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>

Greg Kroah-Hartman

author maintainer

2017-08-28 08:13 UTC #60 lore raw

PATCH 61/84 net: sunrpc: svcsock: fix NULL-pointer exception

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

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

From: Vadim Lomovtsev <[email protected]>

commit eebe53e87f97975ee58a21693e44797608bf679c upstream.

While running nfs/connectathon tests kernel NULL-pointer exception has been observed due to races in svcsock.c.

Race is appear when kernel accepts connection by kernel_accept (which creates new socket) and start queuing ingress packets to new socket. This happens in ksoftirq context which could run concurrently on a different core while new socket setup is not done yet.

The fix is to re-order socket user data init sequence and add write/read barrier calls to be sure that we got proper values for callback pointers before actually calling them.

Test results: nfs/connectathon reports '0' failed tests for about 200+ iterations.

Crash log:
---<-snip->---

[ 6708.638984] Unable to handle kernel NULL pointer dereference at virtual address 00000000
[ 6708.647093] pgd = ffff0000094e0000
[ 6708.650497] [00000000] *pgd=0000010ffff90003, *pud=0000010ffff90003, *pmd=0000010ffff80003, *pte=0000000000000000
[ 6708.660761] Internal error: Oops: 86000005 [#1] SMP
[ 6708.665630] Modules linked in: nfsv3 nfnetlink_queue nfnetlink_log nfnetlink rpcsec_gss_krb5 nfsv4 dns_resolver nfs fscache overlay xt_CONNSECMARK xt_SECMARK xt_conntrack iptable_security ip_tables ah4 xfrm4_mode_transport sctp tun binfmt_misc ext4 jbd2 mbcache loop tcp_diag udp_diag inet_diag rpcrdma ib_isert iscsi_target_mod ib_iser rdma_cm iw_cm libiscsi scsi_transport_iscsi ib_srpt target_core_mod ib_srp scsi_transport_srp ib_ipoib ib_ucm ib_uverbs ib_umad ib_cm ib_core nls_koi8_u nls_cp932 ts_kmp nf_conntrack_ipv4 nf_defrag_ipv4 nf_conntrack vfat fat ghash_ce sha2_ce sha1_ce cavium_rng_vf i2c_thunderx sg thunderx_edac i2c_smbus edac_core cavium_rng nfsd auth_rpcgss nfs_acl lockd grace sunrpc xfs libcrc32c nicvf nicpf ast i2c_algo_bit drm_kms_helper syscopyarea sysfillrect sysimgblt fb_sys_fops
[ 6708.736446]  ttm drm i2c_core thunder_bgx thunder_xcv mdio_thunder mdio_cavium dm_mirror dm_region_hash dm_log dm_mod [last unloaded: stap_3c300909c5b3f46dcacd49aab3334af_87021]
[ 6708.752275] CPU: 84 PID: 0 Comm: swapper/84 Tainted: G        W  OE   4.11.0-4.el7.aarch64 #1
[ 6708.760787] Hardware name: www.cavium.com CRB-2S/CRB-2S, BIOS 0.3 Mar 13 2017
[ 6708.767910] task: ffff810006842e80 task.stack: ffff81000689c000
[ 6708.773822] PC is at 0x0
[ 6708.776739] LR is at svc_data_ready+0x38/0x88 [sunrpc]
[ 6708.781866] pc : [<0000000000000000>] lr : [<ffff0000029d7378>] pstate: 60000145
[ 6708.789248] sp : ffff810ffbad3900
[ 6708.792551] x29: ffff810ffbad3900 x28: ffff000008c73d58
[ 6708.797853] x27: 0000000000000000 x26: ffff81000bbe1e00
[ 6708.803156] x25: 0000000000000020 x24: ffff800f7410bf28
[ 6708.808458] x23: ffff000008c63000 x22: ffff000008c63000
[ 6708.813760] x21: ffff800f7410bf28 x20: ffff81000bbe1e00
[ 6708.819063] x19: ffff810012412400 x18: 00000000d82a9df2
[ 6708.824365] x17: 0000000000000000 x16: 0000000000000000
[ 6708.829667] x15: 0000000000000000 x14: 0000000000000001
[ 6708.834969] x13: 0000000000000000 x12: 722e736f622e676e
[ 6708.840271] x11: 00000000f814dd99 x10: 0000000000000000
[ 6708.845573] x9 : 7374687225000000 x8 : 0000000000000000
[ 6708.850875] x7 : 0000000000000000 x6 : 0000000000000000
[ 6708.856177] x5 : 0000000000000028 x4 : 0000000000000000
[ 6708.861479] x3 : 0000000000000000 x2 : 00000000e5000000
[ 6708.866781] x1 : 0000000000000000 x0 : ffff81000bbe1e00
[ 6708.872084]
[ 6708.873565] Process swapper/84 (pid: 0, stack limit = 0xffff81000689c000)
[ 6708.880341] Stack: (0xffff810ffbad3900 to 0xffff8100068a0000)
[ 6708.886075] Call trace:
[ 6708.888513] Exception stack(0xffff810ffbad3710 to 0xffff810ffbad3840)
[ 6708.894942] 3700:                                   ffff810012412400 0001000000000000
[ 6708.902759] 3720: ffff810ffbad3900 0000000000000000 0000000060000145 ffff800f79300000
[ 6708.910577] 3740: ffff000009274d00 00000000000003ea 0000000000000015 ffff000008c63000
[ 6708.918395] 3760: ffff810ffbad3830 ffff800f79300000 000000000000004d 0000000000000000
[ 6708.926212] 3780: ffff810ffbad3890 ffff0000080f88dc ffff800f79300000 000000000000004d
[ 6708.934030] 37a0: ffff800f7930093c ffff000008c63000 0000000000000000 0000000000000140
[ 6708.941848] 37c0: ffff000008c2c000 0000000000040b00 ffff81000bbe1e00 0000000000000000
[ 6708.949665] 37e0: 00000000e5000000 0000000000000000 0000000000000000 0000000000000028
[ 6708.957483] 3800: 0000000000000000 0000000000000000 0000000000000000 7374687225000000
[ 6708.965300] 3820: 0000000000000000 00000000f814dd99 722e736f622e676e 0000000000000000
[ 6708.973117] [<          (null)>]           (null)
[ 6708.977824] [<ffff0000086f9fa4>] tcp_data_queue+0x754/0xc5c
[ 6708.983386] [<ffff0000086fa64c>] tcp_rcv_established+0x1a0/0x67c
[ 6708.989384] [<ffff000008704120>] tcp_v4_do_rcv+0x15c/0x22c
[ 6708.994858] [<ffff000008707418>] tcp_v4_rcv+0xaf0/0xb58
[ 6709.000077] [<ffff0000086df784>] ip_local_deliver_finish+0x10c/0x254
[ 6709.006419] [<ffff0000086dfea4>] ip_local_deliver+0xf0/0xfc
[ 6709.011980] [<ffff0000086dfad4>] ip_rcv_finish+0x208/0x3a4
[ 6709.017454] [<ffff0000086e018c>] ip_rcv+0x2dc/0x3c8
[ 6709.022328] [<ffff000008692fc8>] __netif_receive_skb_core+0x2f8/0xa0c
[ 6709.028758] [<ffff000008696068>] __netif_receive_skb+0x38/0x84
[ 6709.034580] [<ffff00000869611c>] netif_receive_skb_internal+0x68/0xdc
[ 6709.041010] [<ffff000008696bc0>] napi_gro_receive+0xcc/0x1a8
[ 6709.046690] [<ffff0000014b0fc4>] nicvf_cq_intr_handler+0x59c/0x730 [nicvf]
[ 6709.053559] [<ffff0000014b1380>] nicvf_poll+0x38/0xb8 [nicvf]
[ 6709.059295] [<ffff000008697a6c>] net_rx_action+0x2f8/0x464
[ 6709.064771] [<ffff000008081824>] __do_softirq+0x11c/0x308
[ 6709.070164] [<ffff0000080d14e4>] irq_exit+0x12c/0x174
[ 6709.075206] [<ffff00000813101c>] __handle_domain_irq+0x78/0xc4
[ 6709.081027] [<ffff000008081608>] gic_handle_irq+0x94/0x190
[ 6709.086501] Exception stack(0xffff81000689fdf0 to 0xffff81000689ff20)
[ 6709.092929] fde0:                                   0000810ff2ec0000 ffff000008c10000
[ 6709.100747] fe00: ffff000008c70ef4 0000000000000001 0000000000000000 ffff810ffbad9b18
[ 6709.108565] fe20: ffff810ffbad9c70 ffff8100169d3800 ffff810006843ab0 ffff81000689fe80
[ 6709.116382] fe40: 0000000000000bd0 0000ffffdf979cd0 183f5913da192500 0000ffff8a254ce4
[ 6709.124200] fe60: 0000ffff8a254b78 0000aaab10339808 0000000000000000 0000ffff8a0c2a50
[ 6709.132018] fe80: 0000ffffdf979b10 ffff000008d6d450 ffff000008c10000 ffff000008d6d000
[ 6709.139836] fea0: 0000000000000054 ffff000008cd3dbc 0000000000000000 0000000000000000
[ 6709.147653] fec0: 0000000000000000 0000000000000000 0000000000000000 ffff81000689ff20
[ 6709.155471] fee0: ffff000008085240 ffff81000689ff20 ffff000008085244 0000000060000145
[ 6709.163289] ff00: ffff81000689ff10 ffff00000813f1e4 ffffffffffffffff ffff00000813f238
[ 6709.171107] [<ffff000008082eb4>] el1_irq+0xb4/0x140
[ 6709.175976] [<ffff000008085244>] arch_cpu_idle+0x44/0x11c
[ 6709.181368] [<ffff0000087bf3b8>] default_idle_call+0x20/0x30
[ 6709.187020] [<ffff000008116d50>] do_idle+0x158/0x1e4
[ 6709.191973] [<ffff000008116ff4>] cpu_startup_entry+0x2c/0x30
[ 6709.197624] [<ffff00000808e7cc>] secondary_start_kernel+0x13c/0x160
[ 6709.203878] [<0000000001bc71c4>] 0x1bc71c4
[ 6709.207967] Code: bad PC value
[ 6709.211061] SMP: stopping secondary CPUs
[ 6709.218830] Starting crashdump kernel...
[ 6709.222749] Bye!

---<-snip>---

Signed-off-by Vadim Lomovtsev <[email protected]>

Reviewed-by Jeff Layton <[email protected]>

Signed-off-by J. Bruce Fields <[email protected]>

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 net/sunrpc/svcsock.c |   22 ++++++++++++++++++++--
 1 file changed, 20 insertions(+), 2 deletions(-)

net/sunrpc/svcsock.c +20 -2

@@ -408,6 +408,9 @@ static void svc_data_ready(struct sock *
 		dprintk("svc: socket %p(inet %p), busy=%d\n",
 			svsk, sk,
 			test_bit(XPT_BUSY, &svsk->sk_xprt.xpt_flags));
+
+		/* Refer to svc_setup_socket() for details. */
+		rmb();
 		svsk->sk_odata(sk);
 		if (!test_and_set_bit(XPT_DATA, &svsk->sk_xprt.xpt_flags))
 			svc_xprt_enqueue(&svsk->sk_xprt);

@@ -424,6 +427,9 @@ static void svc_write_space(struct sock
 	if (svsk) {
 		dprintk("svc: socket %p(inet %p), write_space busy=%d\n",
 			svsk, sk, test_bit(XPT_BUSY, &svsk->sk_xprt.xpt_flags));
+
+		/* Refer to svc_setup_socket() for details. */
+		rmb();
 		svsk->sk_owspace(sk);
 		svc_xprt_enqueue(&svsk->sk_xprt);
 	}

@@ -748,8 +754,12 @@ static void svc_tcp_listen_data_ready(st
 	dprintk("svc: socket %p TCP (listen) state change %d\n",
 		sk, sk->sk_state);
 
-	if (svsk)
+	if (svsk) {
+		/* Refer to svc_setup_socket() for details. */
+		rmb();
 		svsk->sk_odata(sk);
+	}
+
 	/*
 	 * This callback may called twice when a new connection
 	 * is established as a child socket inherits everything

@@ -782,6 +792,8 @@ static void svc_tcp_state_change(struct
 	if (!svsk)
 		printk("svc: socket %p: no user data\n", sk);
 	else {
+		/* Refer to svc_setup_socket() for details. */
+		rmb();
 		svsk->sk_ostate(sk);
 		if (sk->sk_state != TCP_ESTABLISHED) {
 			set_bit(XPT_CLOSE, &svsk->sk_xprt.xpt_flags);

@@ -1368,12 +1380,18 @@ static struct svc_sock *svc_setup_socket
 		return ERR_PTR(err);
 	}
 
-	inet->sk_user_data = svsk;
 	svsk->sk_sock = sock;
 	svsk->sk_sk = inet;
 	svsk->sk_ostate = inet->sk_state_change;
 	svsk->sk_odata = inet->sk_data_ready;
 	svsk->sk_owspace = inet->sk_write_space;
+	/*
+	 * This barrier is necessary in order to prevent race condition
+	 * with svc_data_ready(), svc_listen_data_ready() and others
+	 * when calling callbacks above.
+	 */
+	wmb();
+	inet->sk_user_data = svsk;
 
 	/* Initialize the socket */
 	if (sock->type == SOCK_DGRAM)

Greg Kroah-Hartman

author maintainer

2017-08-28 08:12 UTC #61 lore raw

PATCH 62/84 Revert "leds: handle suspend/resume in heartbeat trigger"

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

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

From: Zhang Bo <[email protected]>

commit 436c4c45b5b9562b59cedbb51b7343ab4a6dd8cc upstream.

This reverts commit 5ab92a7cb82c66bf30685583a38a18538e3807db.

System cannot enter suspend mode because of heartbeat led trigger. In autosleep_wq, try_to_suspend function will try to enter suspend mode in specific period. it will get wakeup_count then call pm_notifier chain callback function and freeze processes. Heartbeat_pm_notifier is called and it call led_trigger_unregister to change the trigger of led device to none. It will send uevent message and the wakeup source count changed. As wakeup_count changed, suspend will abort.

Fixes 5ab92a7cb82c ("leds: handle suspend/resume in heartbeat trigger")

Signed-off-by Zhang Bo <[email protected]>

Acked-by Pavel Machek <[email protected]>

Reviewed-by Linus Walleij <[email protected]>

Signed-off-by Jacek Anaszewski <[email protected]>

Cc Geert Uytterhoeven <[email protected]>

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 drivers/leds/trigger/ledtrig-heartbeat.c |   31 -------------------------------
 1 file changed, 31 deletions(-)

drivers/leds/trigger/ledtrig-heartbeat.c +0 ~~-31~~

@@ -19,7 +19,6 @@
 #include <linux/sched.h>
 #include <linux/leds.h>
 #include <linux/reboot.h>
-#include <linux/suspend.h>
 #include "../leds.h"
 
 static int panic_heartbeats;

@@ -155,30 +154,6 @@ static struct led_trigger heartbeat_led_
 	.deactivate = heartbeat_trig_deactivate,
 };
 
-static int heartbeat_pm_notifier(struct notifier_block *nb,
-				 unsigned long pm_event, void *unused)
-{
-	int rc;
-
-	switch (pm_event) {
-	case PM_SUSPEND_PREPARE:
-	case PM_HIBERNATION_PREPARE:
-	case PM_RESTORE_PREPARE:
-		led_trigger_unregister(&heartbeat_led_trigger);
-		break;
-	case PM_POST_SUSPEND:
-	case PM_POST_HIBERNATION:
-	case PM_POST_RESTORE:
-		rc = led_trigger_register(&heartbeat_led_trigger);
-		if (rc)
-			pr_err("could not re-register heartbeat trigger\n");
-		break;
-	default:
-		break;
-	}
-	return NOTIFY_DONE;
-}
-
 static int heartbeat_reboot_notifier(struct notifier_block *nb,
 				     unsigned long code, void *unused)
 {

@@ -193,10 +168,6 @@ static int heartbeat_panic_notifier(stru
 	return NOTIFY_DONE;
 }
 
-static struct notifier_block heartbeat_pm_nb = {
-	.notifier_call = heartbeat_pm_notifier,
-};
-
 static struct notifier_block heartbeat_reboot_nb = {
 	.notifier_call = heartbeat_reboot_notifier,
 };

@@ -213,14 +184,12 @@ static int __init heartbeat_trig_init(vo
 		atomic_notifier_chain_register(&panic_notifier_list,
 					       &heartbeat_panic_nb);
 		register_reboot_notifier(&heartbeat_reboot_nb);
-		register_pm_notifier(&heartbeat_pm_nb);
 	}
 	return rc;
 }
 
 static void __exit heartbeat_trig_exit(void)
 {
-	unregister_pm_notifier(&heartbeat_pm_nb);
 	unregister_reboot_notifier(&heartbeat_reboot_nb);
 	atomic_notifier_chain_unregister(&panic_notifier_list,
 					 &heartbeat_panic_nb);

Greg Kroah-Hartman

author maintainer

2017-08-28 08:12 UTC #62 lore raw

PATCH 63/84 netfilter: nat: fix src map lookup

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

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

From: Florian Westphal <[email protected]>

commit 97772bcd56efa21d9d8976db6f205574ea602f51 upstream.

When doing initial conversion to rhashtable I replaced the bucket walk with a single rhashtable_lookup_fast().

When moving to rhlist I failed to properly walk the list of identical tuples, but that is what is needed for this to work correctly. The table contains the original tuples, so the reply tuples are all distinct.

We currently decide that mapping is (not) in range only based on the first entry, but in case its not we need to try the reply tuple of the next entry until we either find an in-range mapping or we checked all the entries.

This bug makes nat core attempt collision resolution while it might be able to use the mapping as-is.

Fixes 870190a9ec90 ("netfilter: nat: convert nat bysrc hash to rhashtable")

Reported-by Jaco Kroon <[email protected]>

Tested-by Jaco Kroon <[email protected]>

Signed-off-by Florian Westphal <[email protected]>

Signed-off-by Pablo Neira Ayuso <[email protected]>

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 net/netfilter/nf_nat_core.c |   17 +++++++++--------
 1 file changed, 9 insertions(+), 8 deletions(-)

net/netfilter/nf_nat_core.c +9 -8

@@ -225,20 +225,21 @@ find_appropriate_src(struct net *net,
 		.tuple = tuple,
 		.zone = zone
 	};
-	struct rhlist_head *hl;
+	struct rhlist_head *hl, *h;
 
 	hl = rhltable_lookup(&nf_nat_bysource_table, &key,
 			     nf_nat_bysource_params);
-	if (!hl)
-		return 0;
 
-	ct = container_of(hl, typeof(*ct), nat_bysource);
+	rhl_for_each_entry_rcu(ct, h, hl, nat_bysource) {
+		nf_ct_invert_tuplepr(result,
+				     &ct->tuplehash[IP_CT_DIR_REPLY].tuple);
+		result->dst = tuple->dst;
 
-	nf_ct_invert_tuplepr(result,
-			     &ct->tuplehash[IP_CT_DIR_REPLY].tuple);
-	result->dst = tuple->dst;
+		if (in_range(l3proto, l4proto, result, range))
+			return 1;
+	}
 
-	return in_range(l3proto, l4proto, result, range);
+	return 0;
 }
 
 /* For [FUTURE] fragmentation handling, we want the least-used

Greg Kroah-Hartman

author maintainer

2017-08-28 08:12 UTC #63 lore raw

PATCH 64/84 Bluetooth: hidp: fix possible might sleep error in hidp_session_thread

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

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

From: Jeffy Chen <[email protected]>

commit 5da8e47d849d3d37b14129f038782a095b9ad049 upstream.

It looks like hidp_session_thread has same pattern as the issue reported in old rfcomm:

	while (1) {
		set_current_state(TASK_INTERRUPTIBLE);
		if (condition)
			break;
		// may call might_sleep here
		schedule();
	}
	__set_current_state(TASK_RUNNING);

Which fixed at:
dfb2fae Bluetooth: Fix nested sleeps

So let's fix it at the same way, also follow the suggestion of:
https://lwn.net/Articles/628628/

Signed-off-by Jeffy Chen <[email protected]>

Tested-by AL Yu-Chen Cho <[email protected]>

Tested-by Rohit Vaswani <[email protected]>

Signed-off-by Marcel Holtmann <[email protected]>

Cc Jiri Slaby <[email protected]>

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 net/bluetooth/hidp/core.c |   33 ++++++++++++++++++++++-----------
 1 file changed, 22 insertions(+), 11 deletions(-)

net/bluetooth/hidp/core.c +22 ~~-11~~

@@ -36,6 +36,7 @@
 #define VERSION "1.2"
 
 static DECLARE_RWSEM(hidp_session_sem);
+static DECLARE_WAIT_QUEUE_HEAD(hidp_session_wq);
 static LIST_HEAD(hidp_session_list);
 
 static unsigned char hidp_keycode[256] = {

@@ -1068,12 +1069,12 @@ static int hidp_session_start_sync(struc
  * Wake up session thread and notify it to stop. This is asynchronous and
  * returns immediately. Call this whenever a runtime error occurs and you want
  * the session to stop.
- * Note: wake_up_process() performs any necessary memory-barriers for us.
+ * Note: wake_up_interruptible() performs any necessary memory-barriers for us.
  */
 static void hidp_session_terminate(struct hidp_session *session)
 {
 	atomic_inc(&session->terminate);
-	wake_up_process(session->task);
+	wake_up_interruptible(&hidp_session_wq);
 }
 
 /*

@@ -1180,7 +1181,9 @@ static void hidp_session_run(struct hidp
 	struct sock *ctrl_sk = session->ctrl_sock->sk;
 	struct sock *intr_sk = session->intr_sock->sk;
 	struct sk_buff *skb;
+	DEFINE_WAIT_FUNC(wait, woken_wake_function);
 
+	add_wait_queue(&hidp_session_wq, &wait);
 	for (;;) {
 		/*
 		 * This thread can be woken up two ways:

@@ -1188,12 +1191,10 @@ static void hidp_session_run(struct hidp
 		 *    session->terminate flag and wakes this thread up.
 		 *  - Via modifying the socket state of ctrl/intr_sock. This
 		 *    thread is woken up by ->sk_state_changed().
-		 *
-		 * Note: set_current_state() performs any necessary
-		 * memory-barriers for us.
 		 */
-		set_current_state(TASK_INTERRUPTIBLE);
 
+		/* Ensure session->terminate is updated */
+		smp_mb__before_atomic();
 		if (atomic_read(&session->terminate))
 			break;

@@ -1227,11 +1228,22 @@ static void hidp_session_run(struct hidp
 		hidp_process_transmit(session, &session->ctrl_transmit,
 				      session->ctrl_sock);
 
-		schedule();
+		wait_woken(&wait, TASK_INTERRUPTIBLE, MAX_SCHEDULE_TIMEOUT);
 	}
+	remove_wait_queue(&hidp_session_wq, &wait);
 
 	atomic_inc(&session->terminate);
-	set_current_state(TASK_RUNNING);
+
+	/* Ensure session->terminate is updated */
+	smp_mb__after_atomic();
+}
+
+static int hidp_session_wake_function(wait_queue_t *wait,
+				      unsigned int mode,
+				      int sync, void *key)
+{
+	wake_up_interruptible(&hidp_session_wq);
+	return false;
 }
 
 /*

@@ -1244,7 +1256,8 @@ static void hidp_session_run(struct hidp
 static int hidp_session_thread(void *arg)
 {
 	struct hidp_session *session = arg;
-	wait_queue_t ctrl_wait, intr_wait;
+	DEFINE_WAIT_FUNC(ctrl_wait, hidp_session_wake_function);
+	DEFINE_WAIT_FUNC(intr_wait, hidp_session_wake_function);
 
 	BT_DBG("session %p", session);

@@ -1254,8 +1267,6 @@ static int hidp_session_thread(void *arg
 	set_user_nice(current, -15);
 	hidp_set_timer(session);
 
-	init_waitqueue_entry(&ctrl_wait, current);
-	init_waitqueue_entry(&intr_wait, current);
 	add_wait_queue(sk_sleep(session->ctrl_sock->sk), &ctrl_wait);
 	add_wait_queue(sk_sleep(session->intr_sock->sk), &intr_wait);
 	/* This memory barrier is paired with wq_has_sleeper(). See

Greg Kroah-Hartman

author maintainer

2017-08-28 08:05 UTC #64 lore raw

PATCH 65/84 Bluetooth: cmtp: fix possible might sleep error in cmtp_session

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

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

From: Jeffy Chen <[email protected]>

commit f06d977309d09253c744e54e75c5295ecc52b7b4 upstream.

It looks like cmtp_session has same pattern as the issue reported in old rfcomm:

	while (1) {
		set_current_state(TASK_INTERRUPTIBLE);
		if (condition)
			break;
		// may call might_sleep here
		schedule();
	}
	__set_current_state(TASK_RUNNING);

Which fixed at:
dfb2fae Bluetooth: Fix nested sleeps

So let's fix it at the same way, also follow the suggestion of:
https://lwn.net/Articles/628628/

Signed-off-by Jeffy Chen <[email protected]>

Reviewed-by Brian Norris <[email protected]>

Reviewed-by AL Yu-Chen Cho <[email protected]>

Signed-off-by Marcel Holtmann <[email protected]>

Cc Jiri Slaby <[email protected]>

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 net/bluetooth/cmtp/core.c |   17 ++++++++++-------
 1 file changed, 10 insertions(+), 7 deletions(-)

net/bluetooth/cmtp/core.c +10 -7

@@ -280,16 +280,16 @@ static int cmtp_session(void *arg)
 	struct cmtp_session *session = arg;
 	struct sock *sk = session->sock->sk;
 	struct sk_buff *skb;
-	wait_queue_t wait;
+	DEFINE_WAIT_FUNC(wait, woken_wake_function);
 
 	BT_DBG("session %p", session);
 
 	set_user_nice(current, -15);
 
-	init_waitqueue_entry(&wait, current);
 	add_wait_queue(sk_sleep(sk), &wait);
 	while (1) {
-		set_current_state(TASK_INTERRUPTIBLE);
+		/* Ensure session->terminate is updated */
+		smp_mb__before_atomic();
 
 		if (atomic_read(&session->terminate))
 			break;

@@ -306,9 +306,8 @@ static int cmtp_session(void *arg)
 
 		cmtp_process_transmit(session);
 
-		schedule();
+		wait_woken(&wait, TASK_INTERRUPTIBLE, MAX_SCHEDULE_TIMEOUT);
 	}
-	__set_current_state(TASK_RUNNING);
 	remove_wait_queue(sk_sleep(sk), &wait);
 
 	down_write(&cmtp_session_sem);

@@ -393,7 +392,7 @@ int cmtp_add_connection(struct cmtp_conn
 		err = cmtp_attach_device(session);
 		if (err < 0) {
 			atomic_inc(&session->terminate);
-			wake_up_process(session->task);
+			wake_up_interruptible(sk_sleep(session->sock->sk));
 			up_write(&cmtp_session_sem);
 			return err;
 		}

@@ -431,7 +430,11 @@ int cmtp_del_connection(struct cmtp_conn
 
 		/* Stop session thread */
 		atomic_inc(&session->terminate);
-		wake_up_process(session->task);
+
+		/* Ensure session->terminate is updated */
+		smp_mb__after_atomic();
+
+		wake_up_interruptible(sk_sleep(session->sock->sk));
 	} else
 		err = -ENOENT;

Greg Kroah-Hartman

author maintainer

2017-08-28 08:05 UTC #65 lore raw

PATCH 66/84 Bluetooth: bnep: fix possible might sleep error in bnep_session

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

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

From: Jeffy Chen <[email protected]>

commit 25717382c1dd0ddced2059053e3ca5088665f7a5 upstream.

It looks like bnep_session has same pattern as the issue reported in old rfcomm:

	while (1) {
		set_current_state(TASK_INTERRUPTIBLE);
		if (condition)
			break;
		// may call might_sleep here
		schedule();
	}
	__set_current_state(TASK_RUNNING);

Which fixed at:
dfb2fae Bluetooth: Fix nested sleeps

So let's fix it at the same way, also follow the suggestion of:
https://lwn.net/Articles/628628/

Signed-off-by Jeffy Chen <[email protected]>

Reviewed-by Brian Norris <[email protected]>

Reviewed-by AL Yu-Chen Cho <[email protected]>

Signed-off-by Marcel Holtmann <[email protected]>

Cc Jiri Slaby <[email protected]>

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 net/bluetooth/bnep/core.c |   11 +++++------
 1 file changed, 5 insertions(+), 6 deletions(-)

net/bluetooth/bnep/core.c +5 -6

@@ -484,16 +484,16 @@ static int bnep_session(void *arg)
 	struct net_device *dev = s->dev;
 	struct sock *sk = s->sock->sk;
 	struct sk_buff *skb;
-	wait_queue_t wait;
+	DEFINE_WAIT_FUNC(wait, woken_wake_function);
 
 	BT_DBG("");
 
 	set_user_nice(current, -15);
 
-	init_waitqueue_entry(&wait, current);
 	add_wait_queue(sk_sleep(sk), &wait);
 	while (1) {
-		set_current_state(TASK_INTERRUPTIBLE);
+		/* Ensure session->terminate is updated */
+		smp_mb__before_atomic();
 
 		if (atomic_read(&s->terminate))
 			break;

@@ -515,9 +515,8 @@ static int bnep_session(void *arg)
 				break;
 		netif_wake_queue(dev);
 
-		schedule();
+		wait_woken(&wait, TASK_INTERRUPTIBLE, MAX_SCHEDULE_TIMEOUT);
 	}
-	__set_current_state(TASK_RUNNING);
 	remove_wait_queue(sk_sleep(sk), &wait);
 
 	/* Cleanup session */

@@ -666,7 +665,7 @@ int bnep_del_connection(struct bnep_conn
 	s = __bnep_get_session(req->dst);
 	if (s) {
 		atomic_inc(&s->terminate);
-		wake_up_process(s->task);
+		wake_up_interruptible(sk_sleep(s->sock->sk));
 	} else
 		err = -ENOENT;

Greg Kroah-Hartman

author maintainer

2017-08-28 08:12 UTC #66 lore raw

PATCH 67/84 Revert "android: binder: Sanity check at binder ioctl"

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

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

From: Todd Kjos <[email protected]>

commit a2b18708ee14baec4ef9c0fba96070bba14d0081 upstream.

This reverts commit a906d6931f3ccaf7de805643190765ddd7378e27.

The patch introduced a race in the binder driver. An attempt to fix the race was submitted in "[PATCH v2] android: binder: fix dangling pointer comparison", however the conclusion in the discussion for that patch was that the original patch should be reverted.

The reversion is being done as part of the fine-grained locking patchset since the patch would need to be refactored when proc->vmm_vm_mm is removed from struct binder_proc and added in the binder allocator.

Signed-off-by Todd Kjos <[email protected]>

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 drivers/android/binder.c |    5 -----
 1 file changed, 5 deletions(-)

drivers/android/binder.c +0 -5

@@ -2760,10 +2760,6 @@ static long binder_ioctl(struct file *fi
 	/*pr_info("binder_ioctl: %d:%d %x %lx\n",
 			proc->pid, current->pid, cmd, arg);*/
 
-	if (unlikely(current->mm != proc->vma_vm_mm)) {
-		pr_err("current mm mismatch proc mm\n");
-		return -EINVAL;
-	}
 	trace_binder_ioctl(cmd, arg);
 
 	ret = wait_event_interruptible(binder_user_error_wait, binder_stop_on_user_error < 2);

@@ -2978,7 +2974,6 @@ static int binder_open(struct inode *nod
 		return -ENOMEM;
 	get_task_struct(current);
 	proc->tsk = current;
-	proc->vma_vm_mm = current->mm;
 	INIT_LIST_HEAD(&proc->todo);
 	init_waitqueue_head(&proc->wait);
 	proc->default_priority = task_nice(current);

Greg Kroah-Hartman

author maintainer

2017-08-28 08:12 UTC #67 lore raw

PATCH 68/84 binder: use group leader instead of open thread

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

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

From: Todd Kjos <[email protected]>

commit c4ea41ba195d01c9af66fb28711a16cc97caa9c5 upstream.

The binder allocator assumes that the thread that called binder_open will never die for the lifetime of that proc. That thread is normally the group_leader, however it may not be. Use the group_leader instead of current.

Signed-off-by Todd Kjos <[email protected]>

Signed-off-by Greg Kroah-Hartman <[email protected]>

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

drivers/android/binder.c +2 -2

@@ -2972,8 +2972,8 @@ static int binder_open(struct inode *nod
 	proc = kzalloc(sizeof(*proc), GFP_KERNEL);
 	if (proc == NULL)
 		return -ENOMEM;
-	get_task_struct(current);
-	proc->tsk = current;
+	get_task_struct(current->group_leader);
+	proc->tsk = current->group_leader;
 	INIT_LIST_HEAD(&proc->todo);
 	init_waitqueue_head(&proc->wait);
 	proc->default_priority = task_nice(current);

Greg Kroah-Hartman

author maintainer

2017-08-28 08:12 UTC #68 lore raw

PATCH 69/84 binder: Use wake up hint for synchronous transactions.

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

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

From: Riley Andrews <[email protected]>

commit 00b40d613352c623aaae88a44e5ded7c912909d7 upstream.

Use wake_up_interruptible_sync() to hint to the scheduler binder transactions are synchronous wakeups. Disable preemption while waking to avoid ping-ponging on the binder lock.

Signed-off-by Todd Kjos <[email protected]>

Signed-off-by Omprakash Dhyade <[email protected]>

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 drivers/android/binder.c |    8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

drivers/android/binder.c +6 -2

@@ -1724,8 +1724,12 @@ static void binder_transaction(struct bi
 	list_add_tail(&t->work.entry, target_list);
 	tcomplete->type = BINDER_WORK_TRANSACTION_COMPLETE;
 	list_add_tail(&tcomplete->entry, &thread->todo);
-	if (target_wait)
-		wake_up_interruptible(target_wait);
+	if (target_wait) {
+		if (reply || !(t->flags & TF_ONE_WAY))
+			wake_up_interruptible_sync(target_wait);
+		else
+			wake_up_interruptible(target_wait);
+	}
 	return;
 
 err_get_unused_fd_failed:

Greg Kroah-Hartman

author maintainer

2017-08-28 08:12 UTC #69 lore raw

PATCH 70/84 ANDROID: binder: fix proc->tsk check.

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

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

From: Martijn Coenen <[email protected]>

commit b2a6d1b999a4c13e5997bb864694e77172d45250 upstream.

Commit c4ea41ba195d ("binder: use group leader instead of open thread")' was incomplete and didn't update a check in binder_mmap(), causing all mmap() calls into the binder driver to fail.

Signed-off-by Martijn Coenen <[email protected]>

Tested-by John Stultz <[email protected]>

Signed-off-by Greg Kroah-Hartman <[email protected]>

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

drivers/android/binder.c +1 -1

@@ -2875,7 +2875,7 @@ static int binder_mmap(struct file *filp
 	const char *failure_string;
 	struct binder_buffer *buffer;
 
-	if (proc->tsk != current)
+	if (proc->tsk != current->group_leader)
 		return -EINVAL;
 
 	if ((vma->vm_end - vma->vm_start) > SZ_4M)

Greg Kroah-Hartman

author maintainer

2017-08-28 08:05 UTC #70 lore raw

PATCH 71/84 iio: imu: adis16480: Fix acceleration scale factor for adis16480

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

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

From: Dragos Bogdan <[email protected]>

commit fdd0d32eb95f135041236a6885d9006315aa9a1d upstream.

According to the datasheet, the range of the acceleration is [-10 g, + 10 g], so the scale factor should be 10 instead of 5.

Signed-off-by Dragos Bogdan <[email protected]>

Acked-by Lars-Peter Clausen <[email protected]>

Signed-off-by Jonathan Cameron <[email protected]>

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 drivers/iio/imu/adis16480.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

drivers/iio/imu/adis16480.c +1 -1

@@ -696,7 +696,7 @@ static const struct adis16480_chip_info
 		.gyro_max_val = IIO_RAD_TO_DEGREE(22500),
 		.gyro_max_scale = 450,
 		.accel_max_val = IIO_M_S_2_TO_G(12500),
-		.accel_max_scale = 5,
+		.accel_max_scale = 10,
 	},
 	[ADIS16485] = {
 		.channels = adis16485_channels,

Greg Kroah-Hartman

author maintainer

2017-08-28 08:13 UTC #71 lore raw

PATCH 72/84 iio: hid-sensor-trigger: Fix the race with user space powering up sensors

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

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

From: Srinivas Pandruvada <[email protected]>

commit f1664eaacec31035450132c46ed2915fd2b2049a upstream.

It has been reported for a while that with iio-sensor-proxy service the rotation only works after one suspend/resume cycle. This required a wait in the systemd unit file to avoid race. I found a Yoga 900 where I could reproduce this.

The problem scenerio is:
- During sensor driver init, enable run time PM and also set a auto-suspend for 3 seconds.
This result in one runtime resume. But there is a check to avoid
a powerup in this sequence, but rpm is active
- User space iio-sensor-proxy tries to power up the sensor. Since rpm is active it will simply return. But sensors were not actually
powered up in the prior sequence, so actaully the sensors will not work
- After 3 seconds the auto suspend kicks

If we add a wait in systemd service file to fire iio-sensor-proxy after 3 seconds, then now everything will work as the runtime resume will actually powerup the sensor as this is a user request.

To avoid this:
- Remove the check to match user requested state, this will cause a brief powerup, but if the iio-sensor-proxy starts immediately it will
still work as the sensors are ON.
- Also move the autosuspend delay to place when user requested turn off of sensors, like after user finished raw read or buffer disable

Signed-off-by Srinivas Pandruvada <[email protected]>

Tested-by Bastien Nocera <[email protected]>

Signed-off-by Jonathan Cameron <[email protected]>

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 drivers/iio/common/hid-sensors/hid-sensor-trigger.c |    8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

drivers/iio/common/hid-sensors/hid-sensor-trigger.c +4 -4

@@ -36,8 +36,6 @@ static int _hid_sensor_power_state(struc
 	s32 poll_value = 0;
 
 	if (state) {
-		if (!atomic_read(&st->user_requested_state))
-			return 0;
 		if (sensor_hub_device_open(st->hsdev))
 			return -EIO;

@@ -86,6 +84,9 @@ static int _hid_sensor_power_state(struc
 				       &report_val);
 	}
 
+	pr_debug("HID_SENSOR %s set power_state %d report_state %d\n",
+		 st->pdev->name, state_val, report_val);
+
 	sensor_hub_get_feature(st->hsdev, st->power_state.report_id,
 			       st->power_state.index,
 			       sizeof(state_val), &state_val);

@@ -107,6 +108,7 @@ int hid_sensor_power_state(struct hid_se
 		ret = pm_runtime_get_sync(&st->pdev->dev);
 	else {
 		pm_runtime_mark_last_busy(&st->pdev->dev);
+		pm_runtime_use_autosuspend(&st->pdev->dev);
 		ret = pm_runtime_put_autosuspend(&st->pdev->dev);
 	}
 	if (ret < 0) {

@@ -201,8 +203,6 @@ int hid_sensor_setup_trigger(struct iio_
 	/* Default to 3 seconds, but can be changed from sysfs */
 	pm_runtime_set_autosuspend_delay(&attrb->pdev->dev,
 					 3000);
-	pm_runtime_use_autosuspend(&attrb->pdev->dev);
-
 	return ret;
 error_unreg_trigger:
 	iio_trigger_unregister(trig);

Greg Kroah-Hartman

author maintainer

2017-08-28 08:13 UTC #72 lore raw

PATCH 73/84 staging: rtl8188eu: add RNX-N150NUB support

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

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

From: Charles Milette <[email protected]>

commit f299aec6ebd747298e35934cff7709c6b119ca52 upstream.

Add support for USB Device Rosewill RNX-N150NUB.
VendorID: 0x0bda, ProductID: 0xffef

Signed-off-by Charles Milette <[email protected]>

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 drivers/staging/rtl8188eu/os_dep/usb_intf.c |    1 +
 1 file changed, 1 insertion(+)

drivers/staging/rtl8188eu/os_dep/usb_intf.c +1 -0

@@ -45,6 +45,7 @@ static struct usb_device_id rtw_usb_id_t
 	{USB_DEVICE(0x2001, 0x3311)}, /* DLink GO-USB-N150 REV B1 */
 	{USB_DEVICE(0x2357, 0x010c)}, /* TP-Link TL-WN722N v2 */
 	{USB_DEVICE(0x0df6, 0x0076)}, /* Sitecom N150 v2 */
+	{USB_DEVICE(USB_VENDER_ID_REALTEK, 0xffef)}, /* Rosewill RNX-N150NUB */
 	{}	/* Terminating entry */
 };

Greg Kroah-Hartman

author maintainer

2017-08-28 08:13 UTC #73 lore raw

PATCH 74/84 Clarify (and fix) MAX_LFS_FILESIZE macros

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

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

From: Linus Torvalds <[email protected]>

commit 0cc3b0ec23ce4c69e1e890ed2b8d2fa932b14aad upstream.

We have a MAX_LFS_FILESIZE macro that is meant to be filled in by filesystems (and other IO targets) that know they are 64-bit clean and don't have any 32-bit limits in their IO path.

It turns out that our 32-bit value for that limit was bogus. On 32-bit, the VM layer is limited by the page cache to only 32-bit index values, but our logic for that was confusing and actually wrong. We used to define that value to

	(((loff_t)PAGE_SIZE << (BITS_PER_LONG-1))-1)

which is actually odd in several ways: it limits the index to 31 bits, and then it limits files so that they can't have data in that last byte of a page that has the highest 31-bit index (ie page index 0x7fffffff).

Neither of those limitations make sense. The index is actually the full 32 bit unsigned value, and we can use that whole full page. So the maximum size of the file would logically be "PAGE_SIZE << BITS_PER_LONG".

However, we do wan tto avoid the maximum index, because we have code that iterates over the page indexes, and we don't want that code to overflow. So the maximum size of a file on a 32-bit host should actually be one page less than the full 32-bit index.

So the actual limit is ULONG_MAX << PAGE_SHIFT. That means that we will not actually be using the page of that last index (ULONG_MAX), but we can grow a file up to that limit.

The wrong value of MAX_LFS_FILESIZE actually caused problems for Doug Nazar, who was still using a 32-bit host, but with a 9.7TB 2 x RAID5 volume. It turns out that our old MAX_LFS_FILESIZE was 8TiB (well, one byte less), but the actual true VM limit is one page less than 16TiB.

This was invisible until commit c2a9737f45e2 ("vfs,mm: fix a dead loop in truncate_inode_pages_range()"), which started applying that MAX_LFS_FILESIZE limit to block devices too.

NOTE! On 64-bit, the page index isn't a limiter at all, and the limit is actually just the offset type itself (loff_t), which is signed. But for clarity, on 64-bit, just use the maximum signed value, and don't make people have to count the number of 'f' characters in the hex constant.

So just use LLONG_MAX for the 64-bit case. That was what the value had been before too, just written out as a hex constant.

Fixes c2a9737f45e2 ("vfs,mm: fix a dead loop in truncate_inode_pages_range()")

Reported-and-tested-by Doug Nazar <[email protected]>

Cc Andreas Dilger <[email protected]>

Cc Mark Fasheh <[email protected]>

Cc Joel Becker <[email protected]>

Cc Dave Kleikamp <[email protected]>

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 include/linux/fs.h |    4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

include/linux/fs.h +2 -2

@@ -941,9 +941,9 @@ static inline struct file *get_file(stru
 /* Page cache limit. The filesystems should put that into their s_maxbytes 
    limits, otherwise bad things can happen in VM. */ 
 #if BITS_PER_LONG==32
-#define MAX_LFS_FILESIZE	(((loff_t)PAGE_SIZE << (BITS_PER_LONG-1))-1)
+#define MAX_LFS_FILESIZE	((loff_t)ULONG_MAX << PAGE_SHIFT)
 #elif BITS_PER_LONG==64
-#define MAX_LFS_FILESIZE 	((loff_t)0x7fffffffffffffffLL)
+#define MAX_LFS_FILESIZE 	((loff_t)LLONG_MAX)
 #endif
 
 #define FL_POSIX	1

Greg Kroah-Hartman

author maintainer

2017-08-28 08:05 UTC #74 lore raw

PATCH 75/84 ntb_transport: fix qp count bug

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

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

From: Logan Gunthorpe <[email protected]>

commit cb827ee6ccc3e480f0d9c0e8e53eef55be5b0414 upstream.

In cases where there are more mw's than spads/2-2, the mw count gets reduced to match the limitation. ntb_transport also tries to ensure that there are fewer qps than mws but uses the full mw count instead of the reduced one. When this happens, the math in 'ntb_transport_setup_qp_mw' will get confused and result in a kernel paging request bug.

This patch fixes the bug by reducing qp_count to the reduced mw count instead of the full mw count.

Fixes e26a5843f7f5 ("NTB: Split ntb_hw_intel and ntb_transport drivers")

Signed-off-by Jon Mason <[email protected]>

Signed-off-by Greg Kroah-Hartman <[email protected]>

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

drivers/ntb/ntb_transport.c +2 -2

@@ -1125,8 +1125,8 @@ static int ntb_transport_probe(struct nt
 	qp_count = ilog2(qp_bitmap);
 	if (max_num_clients && max_num_clients < qp_count)
 		qp_count = max_num_clients;
-	else if (mw_count < qp_count)
-		qp_count = mw_count;
+	else if (nt->mw_count < qp_count)
+		qp_count = nt->mw_count;
 
 	qp_bitmap &= BIT_ULL(qp_count) - 1;

Greg Kroah-Hartman

author maintainer

2017-08-28 08:13 UTC #75 lore raw

PATCH 76/84 ntb_transport: fix bug calculating num_qps_mw

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

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

From: Logan Gunthorpe <[email protected]>

commit 8e8496e0e9564b66165f5219a4e8ed20b0d3fc6b upstream.

A divide by zero error occurs if qp_count is less than mw_count because num_qps_mw is calculated to be zero. The calculation appears to be incorrect.

The requirement is for num_qps_mw to be set to qp_count / mw_count with any remainder divided among the earlier mws.

For example, if mw_count is 5 and qp_count is 12 then mws 0 and 1 will have 3 qps per window and mws 2 through 4 will have 2 qps per window. Thus, when mw_num < qp_count % mw_count, num_qps_mw is 1 higher than when mw_num >= qp_count.

Fixes e26a5843f7f5 ("NTB: Split ntb_hw_intel and ntb_transport drivers")

Signed-off-by Jon Mason <[email protected]>

Signed-off-by Greg Kroah-Hartman <[email protected]>

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

drivers/ntb/ntb_transport.c +2 -2

@@ -625,7 +625,7 @@ static int ntb_transport_setup_qp_mw(str
 	if (!mw->virt_addr)
 		return -ENOMEM;
 
-	if (qp_count % mw_count && mw_num + 1 < qp_count / mw_count)
+	if (mw_num < qp_count % mw_count)
 		num_qps_mw = qp_count / mw_count + 1;
 	else
 		num_qps_mw = qp_count / mw_count;

@@ -1002,7 +1002,7 @@ static int ntb_transport_init_queue(stru
 	qp->event_handler = NULL;
 	ntb_qp_link_down_reset(qp);
 
-	if (qp_count % mw_count && mw_num + 1 < qp_count / mw_count)
+	if (mw_num < qp_count % mw_count)
 		num_qps_mw = qp_count / mw_count + 1;
 	else
 		num_qps_mw = qp_count / mw_count;

Greg Kroah-Hartman

author maintainer

2017-08-28 08:05 UTC #76 lore raw

PATCH 77/84 NTB: ntb_test: fix bug printing ntb_perf results

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

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

From: Logan Gunthorpe <[email protected]>

commit 07b0b22b3e58824f70b9188d085d400069ca3240 upstream.

The code mistakenly prints the local perf results for the remote test so the script reports identical results for both directions. Fix this by ensuring we print the remote result.

Fixes a9c59ef77458 ("ntb_test: Add a selftest script for the NTB subsystem")

Signed-off-by Jon Mason <[email protected]>

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 tools/testing/selftests/ntb/ntb_test.sh |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

tools/testing/selftests/ntb/ntb_test.sh +1 -1

@@ -305,7 +305,7 @@ function perf_test()
 	echo "Running remote perf test $WITH DMA"
 	write_file "" $REMOTE_PERF/run
 	echo -n "  "
-	read_file $LOCAL_PERF/run
+	read_file $REMOTE_PERF/run
 	echo "  Passed"
 
 	_modprobe -r ntb_perf

Greg Kroah-Hartman

author maintainer

2017-08-28 08:05 UTC #77 lore raw

PATCH 78/84 ntb: no sleep in ntb_async_tx_submit

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

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

From: Allen Hubbe <[email protected]>

commit 88931ec3dc11e7dbceb3b0df455693873b508fbe upstream.

Do not sleep in ntb_async_tx_submit, which could deadlock. This reverts commit "8c874cc140d667f84ae4642bb5b5e0d6396d2ca4"

Fixes 8c874cc140d6 ("NTB: Address out of DMA descriptor issue with NTB")

Reported-by Jia-Ju Bai <[email protected]>

Signed-off-by Allen Hubbe <[email protected]>

Acked-by Dave Jiang <[email protected]>

Signed-off-by Jon Mason <[email protected]>

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 drivers/ntb/ntb_transport.c |   50 ++++++--------------------------------------
 1 file changed, 7 insertions(+), 43 deletions(-)

drivers/ntb/ntb_transport.c +7 ~~-43~~

@@ -176,14 +176,12 @@ struct ntb_transport_qp {
 	u64 rx_err_ver;
 	u64 rx_memcpy;
 	u64 rx_async;
-	u64 dma_rx_prep_err;
 	u64 tx_bytes;
 	u64 tx_pkts;
 	u64 tx_ring_full;
 	u64 tx_err_no_buf;
 	u64 tx_memcpy;
 	u64 tx_async;
-	u64 dma_tx_prep_err;
 };
 
 struct ntb_transport_mw {

@@ -256,8 +254,6 @@ enum {
 #define QP_TO_MW(nt, qp)	((qp) % nt->mw_count)
 #define NTB_QP_DEF_NUM_ENTRIES	100
 #define NTB_LINK_DOWN_TIMEOUT	10
-#define DMA_RETRIES		20
-#define DMA_OUT_RESOURCE_TO	msecs_to_jiffies(50)
 
 static void ntb_transport_rxc_db(unsigned long data);
 static const struct ntb_ctx_ops ntb_transport_ops;

@@ -518,12 +514,6 @@ static ssize_t debugfs_read(struct file
 	out_offset += snprintf(buf + out_offset, out_count - out_offset,
 			       "free tx - \t%u\n",
 			       ntb_transport_tx_free_entry(qp));
-	out_offset += snprintf(buf + out_offset, out_count - out_offset,
-			       "DMA tx prep err - \t%llu\n",
-			       qp->dma_tx_prep_err);
-	out_offset += snprintf(buf + out_offset, out_count - out_offset,
-			       "DMA rx prep err - \t%llu\n",
-			       qp->dma_rx_prep_err);
 
 	out_offset += snprintf(buf + out_offset, out_count - out_offset,
 			       "\n");

@@ -770,8 +760,6 @@ static void ntb_qp_link_down_reset(struc
 	qp->tx_err_no_buf = 0;
 	qp->tx_memcpy = 0;
 	qp->tx_async = 0;
-	qp->dma_tx_prep_err = 0;
-	qp->dma_rx_prep_err = 0;
 }
 
 static void ntb_qp_link_cleanup(struct ntb_transport_qp *qp)

@@ -1314,7 +1302,6 @@ static int ntb_async_rx_submit(struct nt
 	struct dmaengine_unmap_data *unmap;
 	dma_cookie_t cookie;
 	void *buf = entry->buf;
-	int retries = 0;
 
 	len = entry->len;
 	device = chan->device;

@@ -1343,22 +1330,11 @@ static int ntb_async_rx_submit(struct nt
 
 	unmap->from_cnt = 1;
 
-	for (retries = 0; retries < DMA_RETRIES; retries++) {
-		txd = device->device_prep_dma_memcpy(chan,
-						     unmap->addr[1],
-						     unmap->addr[0], len,
-						     DMA_PREP_INTERRUPT);
-		if (txd)
-			break;
-
-		set_current_state(TASK_INTERRUPTIBLE);
-		schedule_timeout(DMA_OUT_RESOURCE_TO);
-	}
-
-	if (!txd) {
-		qp->dma_rx_prep_err++;
+	txd = device->device_prep_dma_memcpy(chan, unmap->addr[1],
+					     unmap->addr[0], len,
+					     DMA_PREP_INTERRUPT);
+	if (!txd)
 		goto err_get_unmap;
-	}
 
 	txd->callback_result = ntb_rx_copy_callback;
 	txd->callback_param = entry;

@@ -1603,7 +1579,6 @@ static int ntb_async_tx_submit(struct nt
 	struct dmaengine_unmap_data *unmap;
 	dma_addr_t dest;
 	dma_cookie_t cookie;
-	int retries = 0;
 
 	device = chan->device;
 	dest = qp->tx_mw_phys + qp->tx_max_frame * entry->tx_index;

@@ -1625,21 +1600,10 @@ static int ntb_async_tx_submit(struct nt
 
 	unmap->to_cnt = 1;
 
-	for (retries = 0; retries < DMA_RETRIES; retries++) {
-		txd = device->device_prep_dma_memcpy(chan, dest,
-						     unmap->addr[0], len,
-						     DMA_PREP_INTERRUPT);
-		if (txd)
-			break;
-
-		set_current_state(TASK_INTERRUPTIBLE);
-		schedule_timeout(DMA_OUT_RESOURCE_TO);
-	}
-
-	if (!txd) {
-		qp->dma_tx_prep_err++;
+	txd = device->device_prep_dma_memcpy(chan, dest, unmap->addr[0], len,
+					     DMA_PREP_INTERRUPT);
+	if (!txd)
 		goto err_get_unmap;
-	}
 
 	txd->callback_result = ntb_tx_copy_callback;
 	txd->callback_param = entry;

Greg Kroah-Hartman

author maintainer

2017-08-28 08:13 UTC #78 lore raw

PATCH 79/84 ntb: ntb_test: ensure the link is up before trying to configure the mws

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

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

From: Logan Gunthorpe <[email protected]>

commit 0eb46345364d7318b11068c46e8a68d5dc10f65e upstream.

After the link tests, there is a race on one side of the test for the link coming up. It's possible, in some cases, for the test script to write to the 'peer_trans' files before the link has come up.

To fix this, we simply use the link event file to ensure both sides see the link as up before continuning.

Signed-off-by Jon Mason <[email protected]>

Fixes a9c59ef77458 ("ntb_test: Add a selftest script for the NTB subsystem")

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 tools/testing/selftests/ntb/ntb_test.sh |    4 ++++
 1 file changed, 4 insertions(+)

tools/testing/selftests/ntb/ntb_test.sh +4 -0

@@ -326,6 +326,10 @@ function ntb_tool_tests()
 	link_test $LOCAL_TOOL $REMOTE_TOOL
 	link_test $REMOTE_TOOL $LOCAL_TOOL
 
+	#Ensure the link is up on both sides before continuing
+	write_file Y $LOCAL_TOOL/link_event
+	write_file Y $REMOTE_TOOL/link_event
+
 	for PEER_TRANS in $(ls $LOCAL_TOOL/peer_trans*); do
 		PT=$(basename $PEER_TRANS)
 		write_file $MW_SIZE $LOCAL_TOOL/$PT

Greg Kroah-Hartman

author maintainer

2017-08-28 08:13 UTC #79 lore raw

PATCH 80/84 ntb: transport shouldnt disable link due to bogus values in SPADs

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

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

From: Dave Jiang <[email protected]>

commit f3fd2afed8eee91620d05b69ab94c14793c849d7 upstream.

It seems that under certain scenarios the SPAD can have bogus values caused by an agent (i.e. BIOS or other software) that is not the kernel driver, and that causes memory window setup failure. This should not cause the link to be disabled because if we do that, the driver will never recover again. We have verified in testing that this issue happens and prevents proper link recovery.

Signed-off-by Dave Jiang <[email protected]>

Signed-off-by Jon Mason <[email protected]>

Fixes 84f766855f61 ("ntb: stop link work when we do not have memory")

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 drivers/ntb/ntb_transport.c |    4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

drivers/ntb/ntb_transport.c +1 -3

@@ -921,10 +921,8 @@ out1:
 		ntb_free_mw(nt, i);
 
 	/* if there's an actual failure, we should just bail */
-	if (rc < 0) {
-		ntb_link_disable(ndev);
+	if (rc < 0)
 		return;
-	}
 
 out:
 	if (ntb_link_is_up(ndev, NULL, NULL) == 1)

Greg Kroah-Hartman

author maintainer

2017-08-28 08:05 UTC #80 lore raw

PATCH 81/84 ACPI: ioapic: Clear on-stack resource before using it

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

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

From: Joerg Roedel <[email protected]>

commit e3d5092b6756b9e0b08f94bbeafcc7afe19f0996 upstream.

The on-stack resource-window 'win' in setup_res() is not properly initialized. This causes the pointers in the embedded 'struct resource' to contain stale addresses.

These pointers (in my case the ->child pointer) later get propagated to the global iomem_resources list, causing a #GP exception when the list is traversed in iomem_map_sanity_check().

Fixes c183619b63ec (x86/irq, ACPI: Implement ACPI driver to support IOAPIC hotplug)

Signed-off-by Joerg Roedel <[email protected]>

Signed-off-by Rafael J. Wysocki <[email protected]>

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 drivers/acpi/ioapic.c |    6 ++++++
 1 file changed, 6 insertions(+)

drivers/acpi/ioapic.c +6 -0

@@ -45,6 +45,12 @@ static acpi_status setup_res(struct acpi
 	struct resource *res = data;
 	struct resource_win win;
 
+	/*
+	 * We might assign this to 'res' later, make sure all pointers are
+	 * cleared before the resource is added to the global list
+	 */
+	memset(&win, 0, sizeof(win));
+
 	res->flags = 0;
 	if (acpi_dev_filter_resource_type(acpi_res, IORESOURCE_MEM))
 		return AE_OK;

Greg Kroah-Hartman

author maintainer

2017-08-28 08:13 UTC #81 lore raw

PATCH 82/84 ACPI / APEI: Add missing synchronize_rcu() on NOTIFY_SCI removal

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

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

From: James Morse <[email protected]>

commit 7d64f82cceb21e6d95db312d284f5f195e120154 upstream.

When removing a GHES device notified by SCI, list_del_rcu() is used, ghes_remove() should call synchronize_rcu() before it goes on to call kfree(ghes), otherwise concurrent RCU readers may still hold this list entry after it has been freed.

Signed-off-by James Morse <[email protected]>

Reviewed-by "Huang, Ying" <[email protected]>

Fixes 81e88fdc432a (ACPI, APEI, Generic Hardware Error Source POLL/IRQ/NMI notification type support)

Signed-off-by Rafael J. Wysocki <[email protected]>

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 drivers/acpi/apei/ghes.c |    1 +
 1 file changed, 1 insertion(+)

drivers/acpi/apei/ghes.c +1 -0

@@ -1072,6 +1072,7 @@ static int ghes_remove(struct platform_d
 		if (list_empty(&ghes_sci))
 			unregister_acpi_hed_notifier(&ghes_notifier_sci);
 		mutex_unlock(&ghes_list_mutex);
+		synchronize_rcu();
 		break;
 	case ACPI_HEST_NOTIFY_NMI:
 		ghes_nmi_remove(ghes);

Greg Kroah-Hartman

author maintainer

2017-08-28 08:13 UTC #82 lore raw

PATCH 83/84 ACPI: EC: Fix regression related to wrong ECDT initialization order

Link https://jira01.devtools.intel.com/browse/LCK-4348

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

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

From: Lv Zheng <[email protected]>

commit 98529b9272e06a7767034fb8a32e43cdecda240a upstream.

Commit 2a5708409e4e (ACPI / EC: Fix a gap that ECDT EC cannot handle EC events) introduced acpi_ec_ecdt_start(), but that function is invoked before acpi_ec_query_init(), which is too early. This causes the kernel to crash if an EC event occurs after boot, when ec_query_wq is not valid:

 BUG: unable to handle kernel NULL pointer dereference at 0000000000000102
 ...
 Workqueue: events acpi_ec_event_handler
 task: ffff9f539790dac0 task.stack: ffffb437c0e10000
 RIP: 0010:__queue_work+0x32/0x430

Normally, the DSDT EC should always be valid, so acpi_ec_ecdt_start() is actually a no-op in the majority of cases. However, commit c712bb58d827 (ACPI / EC: Add support to skip boot stage DSDT probe) caused the probing of the DSDT EC as the "boot EC" to be skipped when the ECDT EC is valid and uncovered the bug.

Fix this issue by invoking acpi_ec_ecdt_start() after acpi_ec_query_init() in acpi_ec_init().

Fixes 2a5708409e4e (ACPI / EC: Fix a gap that ECDT EC cannot handle EC events)

Fixes c712bb58d827 (ACPI / EC: Add support to skip boot stage DSDT probe)

Reported-by Wang Wendy <[email protected]>

Tested-by Feng Chenzhou <[email protected]>

Signed-off-by Lv Zheng <[email protected]>

[ rjw: Changelog ]

Signed-off-by Rafael J. Wysocki <[email protected]>

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 drivers/acpi/ec.c       |   17 +++++++----------
 drivers/acpi/internal.h |    1 -
 drivers/acpi/scan.c     |    1 -
 3 files changed, 7 insertions(+), 12 deletions(-)

drivers/acpi/ec.c +7 ~~-10~~

@@ -1728,7 +1728,7 @@ error:
  * functioning ECDT EC first in order to handle the events.
  * https://bugzilla.kernel.org/show_bug.cgi?id=115021
  */
-int __init acpi_ec_ecdt_start(void)
+static int __init acpi_ec_ecdt_start(void)
 {
 	acpi_handle handle;

@@ -1959,20 +1959,17 @@ static inline void acpi_ec_query_exit(vo
 int __init acpi_ec_init(void)
 {
 	int result;
+	int ecdt_fail, dsdt_fail;
 
 	/* register workqueue for _Qxx evaluations */
 	result = acpi_ec_query_init();
 	if (result)
-		goto err_exit;
-	/* Now register the driver for the EC */
-	result = acpi_bus_register_driver(&acpi_ec_driver);
-	if (result)
-		goto err_exit;
+		return result;
 
-err_exit:
-	if (result)
-		acpi_ec_query_exit();
-	return result;
+	/* Drivers must be started after acpi_ec_query_init() */
+	ecdt_fail = acpi_ec_ecdt_start();
+	dsdt_fail = acpi_bus_register_driver(&acpi_ec_driver);
+	return ecdt_fail && dsdt_fail ? -ENODEV : 0;
 }
 
 /* EC driver currently not unloadable */

drivers/acpi/internal.h +0 -1

@@ -185,7 +185,6 @@ typedef int (*acpi_ec_query_func) (void
 int acpi_ec_init(void);
 int acpi_ec_ecdt_probe(void);
 int acpi_ec_dsdt_probe(void);
-int acpi_ec_ecdt_start(void);
 void acpi_ec_block_transactions(void);
 void acpi_ec_unblock_transactions(void);
 int acpi_ec_add_query_handler(struct acpi_ec *ec, u8 query_bit,

drivers/acpi/scan.c +0 -1

@@ -2051,7 +2051,6 @@ int __init acpi_scan_init(void)
 
 	acpi_gpe_apply_masked_gpes();
 	acpi_update_all_gpes();
-	acpi_ec_ecdt_start();
 
 	acpi_scan_initialized = true;

Greg Kroah-Hartman

author maintainer

2017-08-28 08:05 UTC #83 lore raw

PATCH 84/84 powerpc/mm: Ensure cpumask update is ordered

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

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

From: Benjamin Herrenschmidt <[email protected]>

commit 1a92a80ad386a1a6e3b36d576d52a1a456394b70 upstream.

There is no guarantee that the various isync's involved with the context switch will order the update of the CPU mask with the first TLB entry for the new context being loaded by the HW.

Be safe here and add a memory barrier to order any subsequent load/store which may bring entries into the TLB.

The corresponding barrier on the other side already exists as pte updates use pte_xchg() which uses __cmpxchg_u64 which has a sync after the atomic operation.

Signed-off-by Benjamin Herrenschmidt <[email protected]>

Reviewed-by Nicholas Piggin <[email protected]>

[mpe: Add comments in the code]

[mpe: Backport to 4.12, minor context change]

Signed-off-by Michael Ellerman <[email protected]>

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 arch/powerpc/include/asm/mmu_context.h      |   20 +++++++++++++++++++-
 arch/powerpc/include/asm/pgtable-be-types.h |    1 +
 arch/powerpc/include/asm/pgtable-types.h    |    1 +
 3 files changed, 21 insertions(+), 1 deletion(-)

arch/powerpc/include/asm/mmu_context.h +19 -1

@@ -75,9 +75,27 @@ static inline void switch_mm_irqs_off(st
 				      struct task_struct *tsk)
 {
 	/* Mark this context has been used on the new CPU */
-	if (!cpumask_test_cpu(smp_processor_id(), mm_cpumask(next)))
+	if (!cpumask_test_cpu(smp_processor_id(), mm_cpumask(next))) {
 		cpumask_set_cpu(smp_processor_id(), mm_cpumask(next));
 
+		/*
+		 * This full barrier orders the store to the cpumask above vs
+		 * a subsequent operation which allows this CPU to begin loading
+		 * translations for next.
+		 *
+		 * When using the radix MMU that operation is the load of the
+		 * MMU context id, which is then moved to SPRN_PID.
+		 *
+		 * For the hash MMU it is either the first load from slb_cache
+		 * in switch_slb(), and/or the store of paca->mm_ctx_id in
+		 * copy_mm_to_paca().
+		 *
+		 * On the read side the barrier is in pte_xchg(), which orders
+		 * the store to the PTE vs the load of mm_cpumask.
+		 */
+		smp_mb();
+	}
+
 	/* 32-bit keeps track of the current PGDIR in the thread struct */
 #ifdef CONFIG_PPC32
 	tsk->thread.pgdir = next->pgd;

arch/powerpc/include/asm/pgtable-be-types.h +1 -0

@@ -87,6 +87,7 @@ static inline bool pte_xchg(pte_t *ptep,
 	unsigned long *p = (unsigned long *)ptep;
 	__be64 prev;
 
+	/* See comment in switch_mm_irqs_off() */
 	prev = (__force __be64)__cmpxchg_u64(p, (__force unsigned long)pte_raw(old),
 					     (__force unsigned long)pte_raw(new));

arch/powerpc/include/asm/pgtable-types.h +1 -0

@@ -62,6 +62,7 @@ static inline bool pte_xchg(pte_t *ptep,
 {
 	unsigned long *p = (unsigned long *)ptep;
 
+	/* See comment in switch_mm_irqs_off() */
 	return pte_val(old) == __cmpxchg_u64(p, pte_val(old), pte_val(new));
 }
 #endif

Shuah Khan

2017-08-28 19:39 UTC #84 lore raw

Quoted 9 lines · Greg Kroah-Hartman

This is the start of the stable review cycle for the 4.9.46 release. There are 84 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 Wed Aug 30 08:05:10 UTC 2017. Anything received after that time might be too late.
The whole patch series can be found in one patch at:

Quoted 9 lines

	kernel.org/pub/linux/kernel/v4.x/stable-review/patch-4.9.46-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

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

thanks,
-- Shuah

Guenter Roeck

2017-08-29 00:10 UTC #85 lore raw

Quoted 8 lines · Greg Kroah-Hartman

This is the start of the stable review cycle for the 4.9.46 release. There are 84 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 Wed Aug 30 08:05:10 UTC 2017. Anything received after that time might be too late.

Build results:

	total: 145 pass: 145 fail: 0
Qemu test results:
	total: 122 pass: 122 fail: 0

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

Guenter

Sumit Semwal

2017-08-29 12:02 UTC #86 lore raw