Merge android-4.4.128 (89904cc) into msm-4.4

* refs/heads/tmp-89904cc
  ANDROID: Add build server config for cuttlefish.
  ANDROID: Add defconfig for cuttlefish.
  FROMLIST: staging: Android: Add 'vsoc' driver for cuttlefish.
  Revert "proc: make oom adjustment files user read-only"
  Revert "fixup! proc: make oom adjustment files user read-only"
  Linux 4.4.128
  Revert "xhci: plat: Register shutdown for xhci_plat"
  vrf: Fix use after free and double free in vrf_finish_output
  ipv6: the entire IPv6 header chain must fit the first fragment
  net/ipv6: Increment OUTxxx counters after netfilter hook
  net sched actions: fix dumping which requires several messages to user space
  r8169: fix setting driver_data after register_netdev
  vti6: better validate user provided tunnel names
  ip6_tunnel: better validate user provided tunnel names
  ip6_gre: better validate user provided tunnel names
  ipv6: sit: better validate user provided tunnel names
  ip_tunnel: better validate user provided tunnel names
  net: fool proof dev_valid_name()
  bonding: process the err returned by dev_set_allmulti properly in bond_enslave
  bonding: move dev_mc_sync after master_upper_dev_link in bond_enslave
  bonding: fix the err path for dev hwaddr sync in bond_enslave
  vlan: also check phy_driver ts_info for vlan's real device
  vhost: correctly remove wait queue during poll failure
  sky2: Increase D3 delay to sky2 stops working after suspend
  sctp: sctp_sockaddr_af must check minimal addr length for AF_INET6
  sctp: do not leak kernel memory to user space
  pptp: remove a buggy dst release in pptp_connect()
  net/sched: fix NULL dereference in the error path of tcf_bpf_init()
  netlink: make sure nladdr has correct size in netlink_connect()
  net/ipv6: Fix route leaking between VRFs
  net: fix possible out-of-bound read in skb_network_protocol()
  arp: fix arp_filter on l3slave devices
  Kbuild: provide a __UNIQUE_ID for clang
  futex: Remove requirement for lock_page() in get_futex_key()
  random: use lockless method of accessing and updating f->reg_idx
  virtio_net: check return value of skb_to_sgvec in one more location
  virtio_net: check return value of skb_to_sgvec always
  rxrpc: check return value of skb_to_sgvec always
  ipsec: check return value of skb_to_sgvec always
  perf tools: Fix copyfile_offset update of output offset
  cxgb4vf: Fix SGE FL buffer initialization logic for 64K pages
  EDAC, mv64x60: Fix an error handling path
  tty: n_gsm: Allow ADM response in addition to UA for control dlci
  blk-mq: fix kernel oops in blk_mq_tag_idle()
  scsi: libsas: initialize sas_phy status according to response of DISCOVER
  scsi: libsas: fix error when getting phy events
  scsi: libsas: fix memory leak in sas_smp_get_phy_events()
  bcache: segregate flash only volume write streams
  bcache: stop writeback thread after detaching
  vxlan: dont migrate permanent fdb entries during learn
  s390/dasd: fix hanging safe offline
  ACPICA: Disassembler: Abort on an invalid/unknown AML opcode
  ACPICA: Events: Add runtime stub support for event APIs
  cpuidle: dt: Add missing 'of_node_put()'
  Bluetooth: Send HCI Set Event Mask Page 2 command only when needed
  iio: magnetometer: st_magn_spi: fix spi_device_id table
  sparc64: ldc abort during vds iso boot
  sctp: fix recursive locking warning in sctp_do_peeloff
  bnx2x: Allow vfs to disable txvlan offload
  xen: avoid type warning in xchg_xen_ulong
  skbuff: only inherit relevant tx_flags
  perf tests: Decompress kernel module before objdump
  net: emac: fix reset timeout with AR8035 phy
  Fix loop device flush before configure v3
  MIPS: kprobes: flush_insn_slot should flush only if probe initialised
  MIPS: mm: adjust PKMAP location
  MIPS: mm: fixed mappings: correct initialisation
  perf/core: Correct event creation with PERF_FORMAT_GROUP
  e1000e: Undo e1000e_pm_freeze if __e1000_shutdown fails
  ARM: imx: Add MXC_CPU_IMX6ULL and cpu_is_imx6ull
  net: phy: avoid genphy_aneg_done() for PHYs without clause 22 support
  mceusb: sporadic RX truncation corruption fix
  cx25840: fix unchecked return values
  e1000e: fix race condition around skb_tstamp_tx()
  tags: honor COMPILED_SOURCE with apart output directory
  perf report: Ensure the perf DSO mapping matches what libdw sees
  perf header: Set proper module name when build-id event found
  net/mlx4: Check if Granular QoS per VF has been enabled before updating QP qos_vport
  net/mlx4: Fix the check in attaching steering rules
  sit: reload iphdr in ipip6_rcv
  skbuff: return -EMSGSIZE in skb_to_sgvec to prevent overflow
  bio-integrity: Do not allocate integrity context for bio w/o data
  Fix serial console on SNI RM400 machines
  cxgb4: fix incorrect cim_la output for T6
  drm/omap: fix tiled buffer stride calculations
  mISDN: Fix a sleep-in-atomic bug
  qlcnic: Fix a sleep-in-atomic bug in qlcnic_82xx_hw_write_wx_2M and qlcnic_82xx_hw_read_wx_2M
  perf trace: Add mmap alias for s390
  powerpc/spufs: Fix coredump of SPU contexts
  clk: Fix __set_clk_rates error print-string
  clk: scpi: fix return type of __scpi_dvfs_round_rate
  KVM: SVM: do not zero out segment attributes if segment is unusable or not present
  net: freescale: fix potential null pointer dereference
  SUNRPC: ensure correct error is reported by xs_tcp_setup_socket()
  rtc: interface: Validate alarm-time before handling rollover
  rtc: opal: Handle disabled TPO in opal_get_tpo_time()
  cxgb4: FW upgrade fixes
  net/mlx5: avoid build warning for uniprocessor
  arm64: futex: Fix undefined behaviour with FUTEX_OP_OPARG_SHIFT usage
  dmaengine: imx-sdma: Handle return value of clk_prepare_enable
  powerpc/[booke|4xx]: Don't clobber TCR[WP] when setting TCR[DIE]
  ovl: filter trusted xattr for non-admin
  hdlcdrv: Fix divide by zero in hdlcdrv_ioctl
  wl1251: check return from call to wl1251_acx_arp_ip_filter
  ASoC: Intel: sst: Fix the return value of 'sst_send_byte_stream_mrfld()'
  gpio: label descriptors using the device name
  vfb: fix video mode and line_length being set when loaded
  scsi: mpt3sas: Proper handling of set/clear of "ATA command pending" flag.
  scsi: libiscsi: Allow sd_shutdown on bad transport
  ASoC: Intel: cht_bsw_rt5645: Analog Mic support
  media: videobuf2-core: don't go out of the buffer range
  hwmon: (ina2xx) Make calibration register value fixed
  rds; Reset rs->rs_bound_addr in rds_add_bound() failure path
  l2tp: fix missing print session offset info
  perf probe: Add warning message if there is unexpected event name
  thermal: power_allocator: fix one race condition issue for thermal_instances list
  ARM: dts: ls1021a: add "fsl,ls1021a-esdhc" compatible string to esdhc node
  net: llc: add lock_sock in llc_ui_bind to avoid a race condition
  KVM: nVMX: Fix handling of lmsw instruction
  bonding: Don't update slave->link until ready to commit
  Input: elan_i2c - clear INT before resetting controller
  net: move somaxconn init from sysctl code
  tcp: better validation of received ack sequences
  ext4: fix off-by-one on max nr_pages in ext4_find_unwritten_pgoff()
  fix race in drivers/char/random.c:get_reg()
  scsi: bnx2fc: fix race condition in bnx2fc_get_host_stats()
  ASoC: rsnd: SSI PIO adjust to 24bit mode
  pNFS/flexfiles: missing error code in ff_layout_alloc_lseg()
  netfilter: ctnetlink: fix incorrect nf_ct_put during hash resize
  libceph: NULL deref on crush_decode() error path
  net: ieee802154: fix net_device reference release too early
  mlx5: fix bug reading rss_hash_type from CQE
  block: fix an error code in add_partition()
  selinux: do not check open permission on sockets
  net/mlx5: Tolerate irq_set_affinity_hint() failures
  sched/numa: Use down_read_trylock() for the mmap_sem
  leds: pca955x: Correct I2C Functionality
  ray_cs: Avoid reading past end of buffer
  ARM: davinci: da8xx: Create DSP device only when assigned memory
  md-cluster: fix potential lock issue in add_new_disk
  ext4: handle the rest of ext4_mb_load_buddy() ENOMEM errors
  iio: hi8435: cleanup reset gpio
  iio: hi8435: avoid garbage event at first enable
  xfrm: fix state migration copy replay sequence numbers
  selftests/powerpc: Fix TM resched DSCR test with some compilers
  ath5k: fix memory leak on buf on failed eeprom read
  powerpc/mm: Fix virt_addr_valid() etc. on 64-bit hash
  scsi: csiostor: fix use after free in csio_hw_use_fwconfig()
  sh_eth: Use platform device for printing before register_netdev()
  serial: sh-sci: Fix race condition causing garbage during shutdown
  serial: 8250: omap: Disable DMA for console UART
  USB: ene_usb6250: fix SCSI residue overwriting
  net: x25: fix one potential use-after-free issue
  USB: ene_usb6250: fix first command execution
  usb: chipidea: properly handle host or gadget initialization failure
  arp: honour gratuitous ARP _replies_
  neighbour: update neigh timestamps iff update is effective
  ata: libahci: properly propagate return value of platform_get_irq()
  btrfs: fix incorrect error return ret being passed to mapping_set_error
  usb: dwc3: keystone: check return value
  async_tx: Fix DMA_PREP_FENCE usage in do_async_gen_syndrome()
  ipv6: avoid dad-failures for addresses with NODAD
  ARM: dts: imx6qdl-wandboard: Fix audio channel swap
  x86/tsc: Provide 'tsc=unstable' boot parameter
  staging: wlan-ng: prism2mgmt.c: fixed a double endian conversion before calling hfa384x_drvr_setconfig16, also fixes relative sparse warning
  ARM: dts: imx53-qsrb: Pulldown PMIC IRQ pin
  PowerCap: Fix an error code in powercap_register_zone()
  bus: brcmstb_gisb: correct support for 64-bit address output
  bus: brcmstb_gisb: Use register offsets with writes too
  SMB2: Fix share type handling
  vmxnet3: ensure that adapter is in proper state during force_close
  KVM: PPC: Book3S PR: Check copy_to/from_user return values
  Input: elantech - force relative mode on a certain module
  Input: elan_i2c - check if device is there before really probing
  netxen_nic: set rcode to the return status from the call to netxen_issue_cmd
  net: qca_spi: Fix alignment issues in rx path
  blk-mq: NVMe 512B/4K+T10 DIF/DIX format returns I/O error on dd with split op
  CIFS: silence lockdep splat in cifs_relock_file()
  NFSv4.1: Work around a Linux server bug...
  net/mlx4_en: Avoid adding steering rules with invalid ring
  s390: move _text symbol to address higher than zero
  pidns: disable pid allocation if pid_ns_prepare_proc() is failed in alloc_pid()
  drivers/misc/vmw_vmci/vmci_queue_pair.c: fix a couple integer overflow tests
  lockd: fix lockd shutdown race
  net: ethernet: ti: cpsw: adjust cpsw fifos depth for fullduplex flow control
  net: cdc_ncm: Fix TX zero padding
  ipmi_ssif: unlock on allocation failure
  qlge: Avoid reading past end of buffer
  bna: Avoid reading past end of buffer
  mac80211: bail out from prep_connection() if a reconfig is ongoing
  af_key: Fix slab-out-of-bounds in pfkey_compile_policy.
  IB/srpt: Fix abort handling
  NFSv4.1: RECLAIM_COMPLETE must handle NFS4ERR_CONN_NOT_BOUND_TO_SESSION
  x86/asm: Don't use RBP as a temporary register in csum_partial_copy_generic()
  rtc: snvs: fix an incorrect check of return value
  md/raid5: make use of spin_lock_irq over local_irq_disable + spin_lock
  cfg80211: make RATE_INFO_BW_20 the default
  ANDROID: proc: add null check in proc_uid_init
  f2fs/fscrypt: updates to v4.17-rc1
  Reduce amount of casting in drivers/tty/goldfish.c.

Conflicts:
	drivers/staging/android/Kconfig
	drivers/staging/android/Makefile

Change-Id: Ic7aa3df76a0312b8d6d84f8a8e11e793311a239a
Signed-off-by: Srinivasarao P <spathi@codeaurora.org>

4 files changed, 106 insertions, 14 deletions

diff --git a/kernel/events/core.c b/kernel/events/core.c
index 322f63370038..656d55d30f8d 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -5387,9 +5387,6 @@ static void perf_output_read_one(struct perf_output_handle *handle,
 	__output_copy(handle, values, n * sizeof(u64));
 }
 
-/*
- * XXX PERF_FORMAT_GROUP vs inherited events seems difficult.
- */
 static void perf_output_read_group(struct perf_output_handle *handle,
 			    struct perf_event *event,
 			    u64 enabled, u64 running)
@@ -5434,6 +5431,13 @@ static void perf_output_read_group(struct perf_output_handle *handle,
 #define PERF_FORMAT_TOTAL_TIMES (PERF_FORMAT_TOTAL_TIME_ENABLED|\
 				 PERF_FORMAT_TOTAL_TIME_RUNNING)
 
+/*
+ * XXX PERF_SAMPLE_READ vs inherited events seems difficult.
+ *
+ * The problem is that its both hard and excessively expensive to iterate the
+ * child list, not to mention that its impossible to IPI the children running
+ * on another CPU, from interrupt/NMI context.
+ */
 static void perf_output_read(struct perf_output_handle *handle,
 			     struct perf_event *event)
 {
@@ -8167,9 +8171,10 @@ perf_event_alloc(struct perf_event_attr *attr, int cpu,
 	local64_set(&hwc->period_left, hwc->sample_period);
 
 	/*
-	 * we currently do not support PERF_FORMAT_GROUP on inherited events
+	 * We currently do not support PERF_SAMPLE_READ on inherited events.
+	 * See perf_output_read().
 	 */
-	if (attr->inherit && (attr->read_format & PERF_FORMAT_GROUP))
+	if (attr->inherit && (attr->sample_type & PERF_SAMPLE_READ))
 		goto err_ns;
 
 	if (!has_branch_stack(event))
diff --git a/kernel/futex.c b/kernel/futex.c
index a09c1dd1f659..760a97da1050 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -470,6 +470,7 @@ get_futex_key(u32 __user *uaddr, int fshared, union futex_key *key, int rw)
 	unsigned long address = (unsigned long)uaddr;
 	struct mm_struct *mm = current->mm;
 	struct page *page, *page_head;
+	struct address_space *mapping;
 	int err, ro = 0;
 
 	/*
@@ -555,7 +556,19 @@ again:
 	}
 #endif
 
-	lock_page(page_head);
+	/*
+	 * The treatment of mapping from this point on is critical. The page
+	 * lock protects many things but in this context the page lock
+	 * stabilizes mapping, prevents inode freeing in the shared
+	 * file-backed region case and guards against movement to swap cache.
+	 *
+	 * Strictly speaking the page lock is not needed in all cases being
+	 * considered here and page lock forces unnecessarily serialization
+	 * From this point on, mapping will be re-verified if necessary and
+	 * page lock will be acquired only if it is unavoidable
+	 */
+
+	mapping = READ_ONCE(page_head->mapping);
 
 	/*
 	 * If page_head->mapping is NULL, then it cannot be a PageAnon
@@ -572,18 +585,31 @@ again:
 	 * shmem_writepage move it from filecache to swapcache beneath us:
 	 * an unlikely race, but we do need to retry for page_head->mapping.
 	 */
-	if (!page_head->mapping) {
-		int shmem_swizzled = PageSwapCache(page_head);
+	if (unlikely(!mapping)) {
+		int shmem_swizzled;
+
+		/*
+		 * Page lock is required to identify which special case above
+		 * applies. If this is really a shmem page then the page lock
+		 * will prevent unexpected transitions.
+		 */
+		lock_page(page);
+		shmem_swizzled = PageSwapCache(page) || page->mapping;
 		unlock_page(page_head);
 		put_page(page_head);
+
 		if (shmem_swizzled)
 			goto again;
+
 		return -EFAULT;
 	}
 
 	/*
 	 * Private mappings are handled in a simple way.
 	 *
+	 * If the futex key is stored on an anonymous page, then the associated
+	 * object is the mm which is implicitly pinned by the calling process.
+	 *
 	 * NOTE: When userspace waits on a MAP_SHARED mapping, even if
 	 * it's a read-only handle, it's expected that futexes attach to
 	 * the object not the particular process.
@@ -601,16 +627,74 @@ again:
 		key->both.offset |= FUT_OFF_MMSHARED; /* ref taken on mm */
 		key->private.mm = mm;
 		key->private.address = address;
+
+		get_futex_key_refs(key); /* implies smp_mb(); (B) */
+
 	} else {
+		struct inode *inode;
+
+		/*
+		 * The associated futex object in this case is the inode and
+		 * the page->mapping must be traversed. Ordinarily this should
+		 * be stabilised under page lock but it's not strictly
+		 * necessary in this case as we just want to pin the inode, not
+		 * update the radix tree or anything like that.
+		 *
+		 * The RCU read lock is taken as the inode is finally freed
+		 * under RCU. If the mapping still matches expectations then the
+		 * mapping->host can be safely accessed as being a valid inode.
+		 */
+		rcu_read_lock();
+
+		if (READ_ONCE(page_head->mapping) != mapping) {
+			rcu_read_unlock();
+			put_page(page_head);
+
+			goto again;
+		}
+
+		inode = READ_ONCE(mapping->host);
+		if (!inode) {
+			rcu_read_unlock();
+			put_page(page_head);
+
+			goto again;
+		}
+
+		/*
+		 * Take a reference unless it is about to be freed. Previously
+		 * this reference was taken by ihold under the page lock
+		 * pinning the inode in place so i_lock was unnecessary. The
+		 * only way for this check to fail is if the inode was
+		 * truncated in parallel so warn for now if this happens.
+		 *
+		 * We are not calling into get_futex_key_refs() in file-backed
+		 * cases, therefore a successful atomic_inc return below will
+		 * guarantee that get_futex_key() will still imply smp_mb(); (B).
+		 */
+		if (WARN_ON_ONCE(!atomic_inc_not_zero(&inode->i_count))) {
+			rcu_read_unlock();
+			put_page(page_head);
+
+			goto again;
+		}
+
+		/* Should be impossible but lets be paranoid for now */
+		if (WARN_ON_ONCE(inode->i_mapping != mapping)) {
+			err = -EFAULT;
+			rcu_read_unlock();
+			iput(inode);
+
+			goto out;
+		}
+
 		key->both.offset |= FUT_OFF_INODE; /* inode-based key */
-		key->shared.inode = page_head->mapping->host;
+		key->shared.inode = inode;
 		key->shared.pgoff = basepage_index(page);
+		rcu_read_unlock();
 	}
 
-	get_futex_key_refs(key); /* implies MB (B) */
-
 out:
-	unlock_page(page_head);
 	put_page(page_head);
 	return err;
 }
diff --git a/kernel/pid.c b/kernel/pid.c
index b17263be9082..5fe7cdb6d05f 100644
--- a/kernel/pid.c
+++ b/kernel/pid.c
@@ -322,8 +322,10 @@ struct pid *alloc_pid(struct pid_namespace *ns)
 	}
 
 	if (unlikely(is_child_reaper(pid))) {
-		if (pid_ns_prepare_proc(ns))
+		if (pid_ns_prepare_proc(ns)) {
+			disable_pid_allocation(ns);
 			goto out_free;
+		}
 	}
 
 	get_pid_ns(ns);
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 23e37b0674df..f962ab1eb046 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -2402,7 +2402,8 @@ void task_numa_work(struct callback_head *work)
 		return;
 
 
-	down_read(&mm->mmap_sem);
+	if (!down_read_trylock(&mm->mmap_sem))
+		return;
 	vma = find_vma(mm, start);
 	if (!vma) {
 		reset_ptenuma_scan(p);