Merge remote-tracking branch 'common/android-4.4-p' into lineage-18.1-caf-msm8998

* common/android-4.4-p:
  Linux 4.4.296
  xen/netback: don't queue unlimited number of packages
  xen/console: harden hvc_xen against event channel storms
  xen/netfront: harden netfront against event channel storms
  xen/blkfront: harden blkfront against event channel storms
  Input: touchscreen - avoid bitwise vs logical OR warning
  ARM: 8805/2: remove unneeded naked function usage
  net: lan78xx: Avoid unnecessary self assignment
  net: systemport: Add global locking for descriptor lifecycle
  timekeeping: Really make sure wall_to_monotonic isn't positive
  USB: serial: option: add Telit FN990 compositions
  PCI/MSI: Clear PCI_MSIX_FLAGS_MASKALL on error
  USB: gadget: bRequestType is a bitfield, not a enum
  igbvf: fix double free in `igbvf_probe`
  soc/tegra: fuse: Fix bitwise vs. logical OR warning
  nfsd: fix use-after-free due to delegation race
  dm btree remove: fix use after free in rebalance_children()
  recordmcount.pl: look for jgnop instruction as well as bcrl on s390
  mac80211: send ADDBA requests using the tid/queue of the aggregation session
  hwmon: (dell-smm) Fix warning on /proc/i8k creation error
  net: netlink: af_netlink: Prevent empty skb by adding a check on len.
  i2c: rk3x: Handle a spurious start completion interrupt flag
  parisc/agp: Annotate parisc agp init functions with __init
  nfc: fix segfault in nfc_genl_dump_devices_done
  FROMGIT: USB: gadget: bRequestType is a bitfield, not a enum
  Linux 4.4.295
  irqchip: nvic: Fix offset for Interrupt Priority Offsets
  irqchip/irq-gic-v3-its.c: Force synchronisation when issuing INVALL
  iio: accel: kxcjk-1013: Fix possible memory leak in probe and remove
  iio: itg3200: Call iio_trigger_notify_done() on error
  iio: ltr501: Don't return error code in trigger handler
  iio: mma8452: Fix trigger reference couting
  iio: stk3310: Don't return error code in interrupt handler
  usb: core: config: fix validation of wMaxPacketValue entries
  USB: gadget: zero allocate endpoint 0 buffers
  USB: gadget: detect too-big endpoint 0 requests
  net/qla3xxx: fix an error code in ql_adapter_up()
  net, neigh: clear whole pneigh_entry at alloc time
  net: fec: only clear interrupt of handling queue in fec_enet_rx_queue()
  net: altera: set a couple error code in probe()
  net: cdc_ncm: Allow for dwNtbOutMaxSize to be unset or zero
  block: fix ioprio_get(IOPRIO_WHO_PGRP) vs setuid(2)
  tracefs: Set all files to the same group ownership as the mount option
  signalfd: use wake_up_pollfree()
  binder: use wake_up_pollfree()
  wait: add wake_up_pollfree()
  libata: add horkage for ASMedia 1092
  can: pch_can: pch_can_rx_normal: fix use after free
  tracefs: Have new files inherit the ownership of their parent
  ALSA: pcm: oss: Handle missing errors in snd_pcm_oss_change_params*()
  ALSA: pcm: oss: Limit the period size to 16MB
  ALSA: pcm: oss: Fix negative period/buffer sizes
  ALSA: ctl: Fix copy of updated id with element read/write
  mm: bdi: initialize bdi_min_ratio when bdi is unregistered
  nfc: fix potential NULL pointer deref in nfc_genl_dump_ses_done
  can: sja1000: fix use after free in ems_pcmcia_add_card()
  HID: check for valid USB device for many HID drivers
  HID: wacom: fix problems when device is not a valid USB device
  HID: add USB_HID dependancy on some USB HID drivers
  HID: add USB_HID dependancy to hid-chicony
  HID: add USB_HID dependancy to hid-prodikeys
  HID: add hid_is_usb() function to make it simpler for USB detection
  HID: introduce hid_is_using_ll_driver
  UPSTREAM: USB: gadget: zero allocate endpoint 0 buffers
  UPSTREAM: USB: gadget: detect too-big endpoint 0 requests
  Linux 4.4.294
  serial: pl011: Add ACPI SBSA UART match id
  tty: serial: msm_serial: Deactivate RX DMA for polling support
  vgacon: Propagate console boot parameters before calling `vc_resize'
  parisc: Fix "make install" on newer debian releases
  siphash: use _unaligned version by default
  net: qlogic: qlcnic: Fix a NULL pointer dereference in qlcnic_83xx_add_rings()
  natsemi: xtensa: fix section mismatch warnings
  fget: check that the fd still exists after getting a ref to it
  fs: add fget_many() and fput_many()
  sata_fsl: fix warning in remove_proc_entry when rmmod sata_fsl
  sata_fsl: fix UAF in sata_fsl_port_stop when rmmod sata_fsl
  kprobes: Limit max data_size of the kretprobe instances
  net: ethernet: dec: tulip: de4x5: fix possible array overflows in type3_infoblock()
  net: tulip: de4x5: fix the problem that the array 'lp->phy[8]' may be out of bound
  scsi: iscsi: Unblock session then wake up error handler
  s390/setup: avoid using memblock_enforce_memory_limit
  platform/x86: thinkpad_acpi: Fix WWAN device disabled issue after S3 deep
  net: return correct error code
  hugetlb: take PMD sharing into account when flushing tlb/caches
  tty: hvc: replace BUG_ON() with negative return value
  xen/netfront: don't trust the backend response data blindly
  xen/netfront: disentangle tx_skb_freelist
  xen/netfront: don't read data from request on the ring page
  xen/netfront: read response from backend only once
  xen/blkfront: don't trust the backend response data blindly
  xen/blkfront: don't take local copy of a request from the ring page
  xen/blkfront: read response from backend only once
  xen: sync include/xen/interface/io/ring.h with Xen's newest version
  shm: extend forced shm destroy to support objects from several IPC nses
  fuse: release pipe buf after last use
  fuse: fix page stealing
  NFC: add NCI_UNREG flag to eliminate the race
  proc/vmcore: fix clearing user buffer by properly using clear_user()
  hugetlbfs: flush TLBs correctly after huge_pmd_unshare
  tracing: Check pid filtering when creating events
  tcp_cubic: fix spurious Hystart ACK train detections for not-cwnd-limited flows
  scsi: mpt3sas: Fix kernel panic during drive powercycle test
  ARM: socfpga: Fix crash with CONFIG_FORTIRY_SOURCE
  NFSv42: Don't fail clone() unless the OP_CLONE operation failed
  net: ieee802154: handle iftypes as u32
  ASoC: topology: Add missing rwsem around snd_ctl_remove() calls
  ARM: dts: BCM5301X: Add interrupt properties to GPIO node
  xen: detect uninitialized xenbus in xenbus_init
  xen: don't continue xenstore initialization in case of errors
  staging: rtl8192e: Fix use after free in _rtl92e_pci_disconnect()
  ALSA: ctxfi: Fix out-of-range access
  binder: fix test regression due to sender_euid change
  usb: hub: Fix locking issues with address0_mutex
  usb: hub: Fix usb enumeration issue due to address0 race
  USB: serial: option: add Fibocom FM101-GL variants
  USB: serial: option: add Telit LE910S1 0x9200 composition
  staging: ion: Prevent incorrect reference counting behavour

Change-Id: Iadf9f213915d2a02b27ceb3b2144eac827ade329

1 files changed, 132 insertions, 44 deletions

diff --git a/ipc/shm.c b/ipc/shm.c
index 5095eb3a6a6c..41e5e712da1c 100644
--- a/ipc/shm.c
+++ b/ipc/shm.c
@@ -90,6 +90,7 @@ static void do_shm_rmid(struct ipc_namespace *ns, struct kern_ipc_perm *ipcp)
 {
 	struct shmid_kernel *shp;
 	shp = container_of(ipcp, struct shmid_kernel, shm_perm);
+	WARN_ON(ns != shp->ns);
 
 	if (shp->shm_nattch) {
 		shp->shm_perm.mode |= SHM_DEST;
@@ -180,10 +181,43 @@ static void shm_rcu_free(struct rcu_head *head)
 	ipc_rcu_free(head);
 }
 
-static inline void shm_rmid(struct ipc_namespace *ns, struct shmid_kernel *s)
+/*
+ * It has to be called with shp locked.
+ * It must be called before ipc_rmid()
+ */
+static inline void shm_clist_rm(struct shmid_kernel *shp)
 {
-	list_del(&s->shm_clist);
-	ipc_rmid(&shm_ids(ns), &s->shm_perm);
+	struct task_struct *creator;
+
+	/* ensure that shm_creator does not disappear */
+	rcu_read_lock();
+
+	/*
+	 * A concurrent exit_shm may do a list_del_init() as well.
+	 * Just do nothing if exit_shm already did the work
+	 */
+	if (!list_empty(&shp->shm_clist)) {
+		/*
+		 * shp->shm_creator is guaranteed to be valid *only*
+		 * if shp->shm_clist is not empty.
+		 */
+		creator = shp->shm_creator;
+
+		task_lock(creator);
+		/*
+		 * list_del_init() is a nop if the entry was already removed
+		 * from the list.
+		 */
+		list_del_init(&shp->shm_clist);
+		task_unlock(creator);
+	}
+	rcu_read_unlock();
+}
+
+static inline void shm_rmid(struct shmid_kernel *s)
+{
+	shm_clist_rm(s);
+	ipc_rmid(&shm_ids(s->ns), &s->shm_perm);
 }
 
 
@@ -238,7 +272,7 @@ static void shm_destroy(struct ipc_namespace *ns, struct shmid_kernel *shp)
 	shm_file = shp->shm_file;
 	shp->shm_file = NULL;
 	ns->shm_tot -= (shp->shm_segsz + PAGE_SIZE - 1) >> PAGE_SHIFT;
-	shm_rmid(ns, shp);
+	shm_rmid(shp);
 	shm_unlock(shp);
 	if (!is_file_hugepages(shm_file))
 		shmem_lock(shm_file, 0, shp->mlock_user);
@@ -259,10 +293,10 @@ static void shm_destroy(struct ipc_namespace *ns, struct shmid_kernel *shp)
  *
  * 2) sysctl kernel.shm_rmid_forced is set to 1.
  */
-static bool shm_may_destroy(struct ipc_namespace *ns, struct shmid_kernel *shp)
+static bool shm_may_destroy(struct shmid_kernel *shp)
 {
 	return (shp->shm_nattch == 0) &&
-	       (ns->shm_rmid_forced ||
+	       (shp->ns->shm_rmid_forced ||
 		(shp->shm_perm.mode & SHM_DEST));
 }
 
@@ -293,7 +327,7 @@ static void shm_close(struct vm_area_struct *vma)
 	shp->shm_lprid = task_tgid_vnr(current);
 	shp->shm_dtim = get_seconds();
 	shp->shm_nattch--;
-	if (shm_may_destroy(ns, shp))
+	if (shm_may_destroy(shp))
 		shm_destroy(ns, shp);
 	else
 		shm_unlock(shp);
@@ -314,10 +348,10 @@ static int shm_try_destroy_orphaned(int id, void *p, void *data)
 	 *
 	 * As shp->* are changed under rwsem, it's safe to skip shp locking.
 	 */
-	if (shp->shm_creator != NULL)
+	if (!list_empty(&shp->shm_clist))
 		return 0;
 
-	if (shm_may_destroy(ns, shp)) {
+	if (shm_may_destroy(shp)) {
 		shm_lock_by_ptr(shp);
 		shm_destroy(ns, shp);
 	}
@@ -335,48 +369,97 @@ void shm_destroy_orphaned(struct ipc_namespace *ns)
 /* Locking assumes this will only be called with task == current */
 void exit_shm(struct task_struct *task)
 {
-	struct ipc_namespace *ns = task->nsproxy->ipc_ns;
-	struct shmid_kernel *shp, *n;
+	for (;;) {
+		struct shmid_kernel *shp;
+		struct ipc_namespace *ns;
 
-	if (list_empty(&task->sysvshm.shm_clist))
-		return;
+		task_lock(task);
+
+		if (list_empty(&task->sysvshm.shm_clist)) {
+			task_unlock(task);
+			break;
+		}
+
+		shp = list_first_entry(&task->sysvshm.shm_clist, struct shmid_kernel,
+				shm_clist);
 
-	/*
-	 * If kernel.shm_rmid_forced is not set then only keep track of
-	 * which shmids are orphaned, so that a later set of the sysctl
-	 * can clean them up.
-	 */
-	if (!ns->shm_rmid_forced) {
-		down_read(&shm_ids(ns).rwsem);
-		list_for_each_entry(shp, &task->sysvshm.shm_clist, shm_clist)
-			shp->shm_creator = NULL;
 		/*
-		 * Only under read lock but we are only called on current
-		 * so no entry on the list will be shared.
+		 * 1) Get pointer to the ipc namespace. It is worth to say
+		 * that this pointer is guaranteed to be valid because
+		 * shp lifetime is always shorter than namespace lifetime
+		 * in which shp lives.
+		 * We taken task_lock it means that shp won't be freed.
 		 */
-		list_del(&task->sysvshm.shm_clist);
-		up_read(&shm_ids(ns).rwsem);
-		return;
-	}
+		ns = shp->ns;
 
-	/*
-	 * Destroy all already created segments, that were not yet mapped,
-	 * and mark any mapped as orphan to cover the sysctl toggling.
-	 * Destroy is skipped if shm_may_destroy() returns false.
-	 */
-	down_write(&shm_ids(ns).rwsem);
-	list_for_each_entry_safe(shp, n, &task->sysvshm.shm_clist, shm_clist) {
-		shp->shm_creator = NULL;
+		/*
+		 * 2) If kernel.shm_rmid_forced is not set then only keep track of
+		 * which shmids are orphaned, so that a later set of the sysctl
+		 * can clean them up.
+		 */
+		if (!ns->shm_rmid_forced)
+			goto unlink_continue;
 
-		if (shm_may_destroy(ns, shp)) {
-			shm_lock_by_ptr(shp);
-			shm_destroy(ns, shp);
+		/*
+		 * 3) get a reference to the namespace.
+		 *    The refcount could be already 0. If it is 0, then
+		 *    the shm objects will be free by free_ipc_work().
+		 */
+		ns = get_ipc_ns_not_zero(ns);
+		if (!ns) {
+unlink_continue:
+			list_del_init(&shp->shm_clist);
+			task_unlock(task);
+			continue;
 		}
-	}
 
-	/* Remove the list head from any segments still attached. */
-	list_del(&task->sysvshm.shm_clist);
-	up_write(&shm_ids(ns).rwsem);
+		/*
+		 * 4) get a reference to shp.
+		 *   This cannot fail: shm_clist_rm() is called before
+		 *   ipc_rmid(), thus the refcount cannot be 0.
+		 */
+		WARN_ON(!ipc_rcu_getref(&shp->shm_perm));
+
+		/*
+		 * 5) unlink the shm segment from the list of segments
+		 *    created by current.
+		 *    This must be done last. After unlinking,
+		 *    only the refcounts obtained above prevent IPC_RMID
+		 *    from destroying the segment or the namespace.
+		 */
+		list_del_init(&shp->shm_clist);
+
+		task_unlock(task);
+
+		/*
+		 * 6) we have all references
+		 *    Thus lock & if needed destroy shp.
+		 */
+		down_write(&shm_ids(ns).rwsem);
+		shm_lock_by_ptr(shp);
+		/*
+		 * rcu_read_lock was implicitly taken in shm_lock_by_ptr, it's
+		 * safe to call ipc_rcu_putref here
+		 */
+		ipc_rcu_putref(&shp->shm_perm, shm_rcu_free);
+
+		if (ipc_valid_object(&shp->shm_perm)) {
+			if (shm_may_destroy(shp))
+				shm_destroy(ns, shp);
+			else
+				shm_unlock(shp);
+		} else {
+			/*
+			 * Someone else deleted the shp from namespace
+			 * idr/kht while we have waited.
+			 * Just unlock and continue.
+			 */
+			shm_unlock(shp);
+		}
+
+		up_write(&shm_ids(ns).rwsem);
+		put_ipc_ns(ns); /* paired with get_ipc_ns_not_zero */
+	}
 }
 
 static int shm_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
@@ -607,7 +690,11 @@ static int newseg(struct ipc_namespace *ns, struct ipc_params *params)
 		goto no_id;
 	}
 
+	shp->ns = ns;
+
+	task_lock(current);
 	list_add(&shp->shm_clist, &current->sysvshm.shm_clist);
+	task_unlock(current);
 
 	/*
 	 * shmid gets reported as "inode#" in /proc/pid/maps.
@@ -1252,7 +1339,8 @@ out_nattch:
 	down_write(&shm_ids(ns).rwsem);
 	shp = shm_lock(ns, shmid);
 	shp->shm_nattch--;
-	if (shm_may_destroy(ns, shp))
+
+	if (shm_may_destroy(shp))
 		shm_destroy(ns, shp);
 	else
 		shm_unlock(shp);