Merge 4.4.106 into android-4.4

Changes in 4.4.106
	can: ti_hecc: Fix napi poll return value for repoll
	can: kvaser_usb: free buf in error paths
	can: kvaser_usb: Fix comparison bug in kvaser_usb_read_bulk_callback()
	can: kvaser_usb: ratelimit errors if incomplete messages are received
	can: kvaser_usb: cancel urb on -EPIPE and -EPROTO
	can: ems_usb: cancel urb on -EPIPE and -EPROTO
	can: esd_usb2: cancel urb on -EPIPE and -EPROTO
	can: usb_8dev: cancel urb on -EPIPE and -EPROTO
	virtio: release virtio index when fail to device_register
	hv: kvp: Avoid reading past allocated blocks from KVP file
	isa: Prevent NULL dereference in isa_bus driver callbacks
	scsi: libsas: align sata_device's rps_resp on a cacheline
	efi: Move some sysfs files to be read-only by root
	ASN.1: fix out-of-bounds read when parsing indefinite length item
	ASN.1: check for error from ASN1_OP_END__ACT actions
	X.509: reject invalid BIT STRING for subjectPublicKey
	x86/PCI: Make broadcom_postcore_init() check acpi_disabled
	ALSA: pcm: prevent UAF in snd_pcm_info
	ALSA: seq: Remove spurious WARN_ON() at timer check
	ALSA: usb-audio: Fix out-of-bound error
	ALSA: usb-audio: Add check return value for usb_string()
	iommu/vt-d: Fix scatterlist offset handling
	s390: fix compat system call table
	kdb: Fix handling of kallsyms_symbol_next() return value
	drm: extra printk() wrapper macros
	drm/exynos: gem: Drop NONCONTIG flag for buffers allocated without IOMMU
	media: dvb: i2c transfers over usb cannot be done from stack
	arm64: KVM: fix VTTBR_BADDR_MASK BUG_ON off-by-one
	KVM: VMX: remove I/O port 0x80 bypass on Intel hosts
	arm64: fpsimd: Prevent registers leaking from dead tasks
	ARM: BUG if jumping to usermode address in kernel mode
	ARM: avoid faulting on qemu
	scsi: storvsc: Workaround for virtual DVD SCSI version
	thp: reduce indentation level in change_huge_pmd()
	thp: fix MADV_DONTNEED vs. numa balancing race
	mm: drop unused pmdp_huge_get_and_clear_notify()
	Revert "drm/armada: Fix compile fail"
	Revert "spi: SPI_FSL_DSPI should depend on HAS_DMA"
	Revert "s390/kbuild: enable modversions for symbols exported from asm"
	vti6: Don't report path MTU below IPV6_MIN_MTU.
	ARM: OMAP2+: gpmc-onenand: propagate error on initialization failure
	x86/hpet: Prevent might sleep splat on resume
	selftest/powerpc: Fix false failures for skipped tests
	module: set __jump_table alignment to 8
	ARM: OMAP2+: Fix device node reference counts
	ARM: OMAP2+: Release device node after it is no longer needed.
	gpio: altera: Use handle_level_irq when configured as a level_high
	HID: chicony: Add support for another ASUS Zen AiO keyboard
	usb: gadget: configs: plug memory leak
	USB: gadgetfs: Fix a potential memory leak in 'dev_config()'
	kvm: nVMX: VMCLEAR should not cause the vCPU to shut down
	libata: drop WARN from protocol error in ata_sff_qc_issue()
	workqueue: trigger WARN if queue_delayed_work() is called with NULL @wq
	scsi: lpfc: Fix crash during Hardware error recovery on SLI3 adapters
	irqchip/crossbar: Fix incorrect type of register size
	KVM: nVMX: reset nested_run_pending if the vCPU is going to be reset
	arm: KVM: Survive unknown traps from guests
	arm64: KVM: Survive unknown traps from guests
	spi_ks8995: fix "BUG: key accdaa28 not in .data!"
	bnx2x: prevent crash when accessing PTP with interface down
	bnx2x: fix possible overrun of VFPF multicast addresses array
	bnx2x: do not rollback VF MAC/VLAN filters we did not configure
	ipv6: reorder icmpv6_init() and ip6_mr_init()
	crypto: s5p-sss - Fix completing crypto request in IRQ handler
	i2c: riic: fix restart condition
	zram: set physical queue limits to avoid array out of bounds accesses
	netfilter: don't track fragmented packets
	axonram: Fix gendisk handling
	drm/amd/amdgpu: fix console deadlock if late init failed
	powerpc/powernv/ioda2: Gracefully fail if too many TCE levels requested
	EDAC, i5000, i5400: Fix use of MTR_DRAM_WIDTH macro
	EDAC, i5000, i5400: Fix definition of NRECMEMB register
	kbuild: pkg: use --transform option to prefix paths in tar
	mac80211_hwsim: Fix memory leak in hwsim_new_radio_nl()
	route: also update fnhe_genid when updating a route cache
	route: update fnhe_expires for redirect when the fnhe exists
	lib/genalloc.c: make the avail variable an atomic_long_t
	dynamic-debug-howto: fix optional/omitted ending line number to be LARGE instead of 0
	NFS: Fix a typo in nfs_rename()
	sunrpc: Fix rpc_task_begin trace point
	block: wake up all tasks blocked in get_request()
	sparc64/mm: set fields in deferred pages
	sctp: do not free asoc when it is already dead in sctp_sendmsg
	sctp: use the right sk after waking up from wait_buf sleep
	atm: horizon: Fix irq release error
	jump_label: Invoke jump_label_test() via early_initcall()
	xfrm: Copy policy family in clone_policy
	IB/mlx4: Increase maximal message size under UD QP
	IB/mlx5: Assign send CQ and recv CQ of UMR QP
	afs: Connect up the CB.ProbeUuid
	ipvlan: fix ipv6 outbound device
	audit: ensure that 'audit=1' actually enables audit for PID 1
	ipmi: Stop timers before cleaning up the module
	s390: always save and restore all registers on context switch
	more bio_map_user_iov() leak fixes
	tipc: fix memory leak in tipc_accept_from_sock()
	rds: Fix NULL pointer dereference in __rds_rdma_map
	sit: update frag_off info
	packet: fix crash in fanout_demux_rollover()
	net/packet: fix a race in packet_bind() and packet_notifier()
	Revert "x86/efi: Build our own page table structures"
	Revert "x86/efi: Hoist page table switching code into efi_call_virt()"
	Revert "x86/mm/pat: Ensure cpa->pfn only contains page frame numbers"
	arm: KVM: Fix VTTBR_BADDR_MASK BUG_ON off-by-one
	usb: gadget: ffs: Forbid usb_ep_alloc_request from sleeping
	Linux 4.4.106

Signed-off-by: Greg Kroah-Hartman <gregkh@google.com>

1 files changed, 58 insertions, 24 deletions

diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 03e3a0c205ec..d64d48ca789c 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1565,35 +1565,69 @@ int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd,
 {
 	struct mm_struct *mm = vma->vm_mm;
 	spinlock_t *ptl;
+	pmd_t entry;
+	bool preserve_write;
+
 	int ret = 0;
 
-	if (__pmd_trans_huge_lock(pmd, vma, &ptl) == 1) {
-		pmd_t entry;
-		bool preserve_write = prot_numa && pmd_write(*pmd);
-		ret = 1;
+	if (__pmd_trans_huge_lock(pmd, vma, &ptl) != 1)
+		return 0;
 
-		/*
-		 * Avoid trapping faults against the zero page. The read-only
-		 * data is likely to be read-cached on the local CPU and
-		 * local/remote hits to the zero page are not interesting.
-		 */
-		if (prot_numa && is_huge_zero_pmd(*pmd)) {
-			spin_unlock(ptl);
-			return ret;
-		}
+	preserve_write = prot_numa && pmd_write(*pmd);
+	ret = 1;
 
-		if (!prot_numa || !pmd_protnone(*pmd)) {
-			entry = pmdp_huge_get_and_clear_notify(mm, addr, pmd);
-			entry = pmd_modify(entry, newprot);
-			if (preserve_write)
-				entry = pmd_mkwrite(entry);
-			ret = HPAGE_PMD_NR;
-			set_pmd_at(mm, addr, pmd, entry);
-			BUG_ON(!preserve_write && pmd_write(entry));
-		}
-		spin_unlock(ptl);
-	}
+	/*
+	 * Avoid trapping faults against the zero page. The read-only
+	 * data is likely to be read-cached on the local CPU and
+	 * local/remote hits to the zero page are not interesting.
+	 */
+	if (prot_numa && is_huge_zero_pmd(*pmd))
+		goto unlock;
 
+	if (prot_numa && pmd_protnone(*pmd))
+		goto unlock;
+
+	/*
+	 * In case prot_numa, we are under down_read(mmap_sem). It's critical
+	 * to not clear pmd intermittently to avoid race with MADV_DONTNEED
+	 * which is also under down_read(mmap_sem):
+	 *
+	 *	CPU0:				CPU1:
+	 *				change_huge_pmd(prot_numa=1)
+	 *				 pmdp_huge_get_and_clear_notify()
+	 * madvise_dontneed()
+	 *  zap_pmd_range()
+	 *   pmd_trans_huge(*pmd) == 0 (without ptl)
+	 *   // skip the pmd
+	 *				 set_pmd_at();
+	 *				 // pmd is re-established
+	 *
+	 * The race makes MADV_DONTNEED miss the huge pmd and don't clear it
+	 * which may break userspace.
+	 *
+	 * pmdp_invalidate() is required to make sure we don't miss
+	 * dirty/young flags set by hardware.
+	 */
+	entry = *pmd;
+	pmdp_invalidate(vma, addr, pmd);
+
+	/*
+	 * Recover dirty/young flags.  It relies on pmdp_invalidate to not
+	 * corrupt them.
+	 */
+	if (pmd_dirty(*pmd))
+		entry = pmd_mkdirty(entry);
+	if (pmd_young(*pmd))
+		entry = pmd_mkyoung(entry);
+
+	entry = pmd_modify(entry, newprot);
+	if (preserve_write)
+		entry = pmd_mkwrite(entry);
+	ret = HPAGE_PMD_NR;
+	set_pmd_at(mm, addr, pmd, entry);
+	BUG_ON(!preserve_write && pmd_write(entry));
+unlock:
+	spin_unlock(ptl);
 	return ret;
 }