Merge branch 'android-4.4-p' of https://android.googlesource.com/kernel/common into lineage-18.1-caf-msm8998

# By Pavel Skripkin (6) and others
# Via Greg Kroah-Hartman
* android-4.4-p:
  Linux 4.4.278
  sis900: Fix missing pci_disable_device() in probe and remove
  tulip: windbond-840: Fix missing pci_disable_device() in probe and remove
  net: llc: fix skb_over_panic
  mlx4: Fix missing error code in mlx4_load_one()
  tipc: fix sleeping in tipc accept routine
  netfilter: nft_nat: allow to specify layer 4 protocol NAT only
  cfg80211: Fix possible memory leak in function cfg80211_bss_update
  x86/asm: Ensure asm/proto.h can be included stand-alone
  NIU: fix incorrect error return, missed in previous revert
  can: esd_usb2: fix memory leak
  can: ems_usb: fix memory leak
  can: usb_8dev: fix memory leak
  ocfs2: issue zeroout to EOF blocks
  ocfs2: fix zero out valid data
  ARM: ensure the signal page contains defined contents
  lib/string.c: add multibyte memset functions
  ARM: dts: versatile: Fix up interrupt controller node names
  hfs: add lock nesting notation to hfs_find_init
  hfs: fix high memory mapping in hfs_bnode_read
  hfs: add missing clean-up in hfs_fill_super
  sctp: move 198 addresses from unusable to private scope
  net/802/garp: fix memleak in garp_request_join()
  net/802/mrp: fix memleak in mrp_request_join()
  workqueue: fix UAF in pwq_unbound_release_workfn()
  af_unix: fix garbage collect vs MSG_PEEK
  net: split out functions related to registering inflight socket files
  Linux 4.4.277
  btrfs: compression: don't try to compress if we don't have enough pages
  iio: accel: bma180: Fix BMA25x bandwidth register values
  iio: accel: bma180: Use explicit member assignment
  net: bcmgenet: ensure EXT_ENERGY_DET_MASK is clear
  media: ngene: Fix out-of-bounds bug in ngene_command_config_free_buf()
  tracing: Fix bug in rb_per_cpu_empty() that might cause deadloop.
  USB: serial: cp210x: add ID for CEL EM3588 USB ZigBee stick
  USB: serial: cp210x: fix comments for GE CS1000
  USB: serial: option: add support for u-blox LARA-R6 family
  usb: renesas_usbhs: Fix superfluous irqs happen after usb_pkt_pop()
  usb: max-3421: Prevent corruption of freed memory
  USB: usb-storage: Add LaCie Rugged USB3-FW to IGNORE_UAS
  usb: hub: Disable USB 3 device initiated lpm if exit latency is too high
  KVM: PPC: Book3S: Fix H_RTAS rets buffer overflow
  xhci: Fix lost USB 2 remote wake
  ALSA: sb: Fix potential ABBA deadlock in CSP driver
  s390/ftrace: fix ftrace_update_ftrace_func implementation
  proc: Avoid mixing integer types in mem_rw()
  Revert "USB: quirks: ignore remote wake-up on Fibocom L850-GL LTE modem"
  scsi: target: Fix protect handling in WRITE SAME(32)
  scsi: iscsi: Fix iface sysfs attr detection
  netrom: Decrease sock refcount when sock timers expire
  net: decnet: Fix sleeping inside in af_decnet
  net: fix uninit-value in caif_seqpkt_sendmsg
  s390/bpf: Perform r1 range checking before accessing jit->seen_reg[r1]
  perf probe-file: Delete namelist in del_events() on the error path
  perf test bpf: Free obj_buf
  igb: Check if num of q_vectors is smaller than max before array access
  iavf: Fix an error handling path in 'iavf_probe()'
  ipv6: tcp: drop silly ICMPv6 packet too big messages
  tcp: annotate data races around tp->mtu_info
  net: validate lwtstate->data before returning from skb_tunnel_info()
  net: ti: fix UAF in tlan_remove_one
  net: moxa: fix UAF in moxart_mac_probe
  net: bcmgenet: Ensure all TX/RX queues DMAs are disabled
  net: ipv6: fix return value of ip6_skb_dst_mtu
  x86/fpu: Make init_fpstate correct with optimized XSAVE
  Revert "memory: fsl_ifc: fix leak of IO mapping on probe failure"
  sched/fair: Fix CFS bandwidth hrtimer expiry type
  scsi: aic7xxx: Fix unintentional sign extension issue on left shift of u8
  kbuild: mkcompile_h: consider timestamp if KBUILD_BUILD_TIMESTAMP is set
  thermal/core: Correct function name thermal_zone_device_unregister()
  ARM: imx: pm-imx5: Fix references to imx5_cpu_suspend_info
  ARM: dts: imx6: phyFLEX: Fix UART hardware flow control
  ARM: dts: BCM63xx: Fix NAND nodes names
  ARM: brcmstb: dts: fix NAND nodes names

Change-Id: Id59b93b8704270f45923f262facbadde4c486a15

1 files changed, 45 insertions, 70 deletions

diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index a0e8cb24af35..79687d5a95ac 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -118,6 +118,8 @@
 #include <linux/security.h>
 #include <linux/freezer.h>
 
+#include "scm.h"
+
 struct hlist_head unix_socket_table[2 * UNIX_HASH_SIZE];
 EXPORT_SYMBOL_GPL(unix_socket_table);
 DEFINE_SPINLOCK(unix_table_lock);
@@ -1504,78 +1506,51 @@ out:
 	return err;
 }
 
-static void unix_detach_fds(struct scm_cookie *scm, struct sk_buff *skb)
-{
-	int i;
-
-	scm->fp = UNIXCB(skb).fp;
-	UNIXCB(skb).fp = NULL;
-
-	for (i = scm->fp->count-1; i >= 0; i--)
-		unix_notinflight(scm->fp->user, scm->fp->fp[i]);
-}
-
-static void unix_destruct_scm(struct sk_buff *skb)
-{
-	struct scm_cookie scm;
-	memset(&scm, 0, sizeof(scm));
-	scm.pid  = UNIXCB(skb).pid;
-	if (UNIXCB(skb).fp)
-		unix_detach_fds(&scm, skb);
-
-	/* Alas, it calls VFS */
-	/* So fscking what? fput() had been SMP-safe since the last Summer */
-	scm_destroy(&scm);
-	sock_wfree(skb);
-}
-
-/*
- * The "user->unix_inflight" variable is protected by the garbage
- * collection lock, and we just read it locklessly here. If you go
- * over the limit, there might be a tiny race in actually noticing
- * it across threads. Tough.
- */
-static inline bool too_many_unix_fds(struct task_struct *p)
-{
-	struct user_struct *user = current_user();
-
-	if (unlikely(user->unix_inflight > task_rlimit(p, RLIMIT_NOFILE)))
-		return !capable(CAP_SYS_RESOURCE) && !capable(CAP_SYS_ADMIN);
-	return false;
-}
-
-#define MAX_RECURSION_LEVEL 4
-
-static int unix_attach_fds(struct scm_cookie *scm, struct sk_buff *skb)
+static void unix_peek_fds(struct scm_cookie *scm, struct sk_buff *skb)
 {
-	int i;
-	unsigned char max_level = 0;
-
-	if (too_many_unix_fds(current))
-		return -ETOOMANYREFS;
-
-	for (i = scm->fp->count - 1; i >= 0; i--) {
-		struct sock *sk = unix_get_socket(scm->fp->fp[i]);
-
-		if (sk)
-			max_level = max(max_level,
-					unix_sk(sk)->recursion_level);
-	}
-	if (unlikely(max_level > MAX_RECURSION_LEVEL))
-		return -ETOOMANYREFS;
+	scm->fp = scm_fp_dup(UNIXCB(skb).fp);
 
 	/*
-	 * Need to duplicate file references for the sake of garbage
-	 * collection.  Otherwise a socket in the fps might become a
-	 * candidate for GC while the skb is not yet queued.
+	 * Garbage collection of unix sockets starts by selecting a set of
+	 * candidate sockets which have reference only from being in flight
+	 * (total_refs == inflight_refs).  This condition is checked once during
+	 * the candidate collection phase, and candidates are marked as such, so
+	 * that non-candidates can later be ignored.  While inflight_refs is
+	 * protected by unix_gc_lock, total_refs (file count) is not, hence this
+	 * is an instantaneous decision.
+	 *
+	 * Once a candidate, however, the socket must not be reinstalled into a
+	 * file descriptor while the garbage collection is in progress.
+	 *
+	 * If the above conditions are met, then the directed graph of
+	 * candidates (*) does not change while unix_gc_lock is held.
+	 *
+	 * Any operations that changes the file count through file descriptors
+	 * (dup, close, sendmsg) does not change the graph since candidates are
+	 * not installed in fds.
+	 *
+	 * Dequeing a candidate via recvmsg would install it into an fd, but
+	 * that takes unix_gc_lock to decrement the inflight count, so it's
+	 * serialized with garbage collection.
+	 *
+	 * MSG_PEEK is special in that it does not change the inflight count,
+	 * yet does install the socket into an fd.  The following lock/unlock
+	 * pair is to ensure serialization with garbage collection.  It must be
+	 * done between incrementing the file count and installing the file into
+	 * an fd.
+	 *
+	 * If garbage collection starts after the barrier provided by the
+	 * lock/unlock, then it will see the elevated refcount and not mark this
+	 * as a candidate.  If a garbage collection is already in progress
+	 * before the file count was incremented, then the lock/unlock pair will
+	 * ensure that garbage collection is finished before progressing to
+	 * installing the fd.
+	 *
+	 * (*) A -> B where B is on the queue of A or B is on the queue of C
+	 * which is on the queue of listening socket A.
 	 */
-	UNIXCB(skb).fp = scm_fp_dup(scm->fp);
-	if (!UNIXCB(skb).fp)
-		return -ENOMEM;
-
-	for (i = scm->fp->count - 1; i >= 0; i--)
-		unix_inflight(scm->fp->user, scm->fp->fp[i]);
-	return max_level;
+	spin_lock(&unix_gc_lock);
+	spin_unlock(&unix_gc_lock);
 }
 
 static int unix_scm_to_skb(struct scm_cookie *scm, struct sk_buff *skb, bool send_fds)
@@ -2203,7 +2178,7 @@ static int unix_dgram_recvmsg(struct socket *sock, struct msghdr *msg,
 		sk_peek_offset_fwd(sk, size);
 
 		if (UNIXCB(skb).fp)
-			scm.fp = scm_fp_dup(UNIXCB(skb).fp);
+			unix_peek_fds(&scm, skb);
 	}
 	err = (flags & MSG_TRUNC) ? skb->len - skip : size;
 
@@ -2448,7 +2423,7 @@ unlock:
 			/* It is questionable, see note in unix_dgram_recvmsg.
 			 */
 			if (UNIXCB(skb).fp)
-				scm.fp = scm_fp_dup(UNIXCB(skb).fp);
+				unix_peek_fds(&scm, skb);
 
 			sk_peek_offset_fwd(sk, chunk);