Merge 4.4.294 into android-4.4-p

Changes in 4.4.294
	staging: ion: Prevent incorrect reference counting behavour
	USB: serial: option: add Telit LE910S1 0x9200 composition
	USB: serial: option: add Fibocom FM101-GL variants
	usb: hub: Fix usb enumeration issue due to address0 race
	usb: hub: Fix locking issues with address0_mutex
	binder: fix test regression due to sender_euid change
	ALSA: ctxfi: Fix out-of-range access
	staging: rtl8192e: Fix use after free in _rtl92e_pci_disconnect()
	xen: don't continue xenstore initialization in case of errors
	xen: detect uninitialized xenbus in xenbus_init
	ARM: dts: BCM5301X: Add interrupt properties to GPIO node
	ASoC: topology: Add missing rwsem around snd_ctl_remove() calls
	net: ieee802154: handle iftypes as u32
	NFSv42: Don't fail clone() unless the OP_CLONE operation failed
	ARM: socfpga: Fix crash with CONFIG_FORTIRY_SOURCE
	scsi: mpt3sas: Fix kernel panic during drive powercycle test
	tcp_cubic: fix spurious Hystart ACK train detections for not-cwnd-limited flows
	tracing: Check pid filtering when creating events
	hugetlbfs: flush TLBs correctly after huge_pmd_unshare
	proc/vmcore: fix clearing user buffer by properly using clear_user()
	NFC: add NCI_UNREG flag to eliminate the race
	fuse: fix page stealing
	fuse: release pipe buf after last use
	shm: extend forced shm destroy to support objects from several IPC nses
	xen: sync include/xen/interface/io/ring.h with Xen's newest version
	xen/blkfront: read response from backend only once
	xen/blkfront: don't take local copy of a request from the ring page
	xen/blkfront: don't trust the backend response data blindly
	xen/netfront: read response from backend only once
	xen/netfront: don't read data from request on the ring page
	xen/netfront: disentangle tx_skb_freelist
	xen/netfront: don't trust the backend response data blindly
	tty: hvc: replace BUG_ON() with negative return value
	hugetlb: take PMD sharing into account when flushing tlb/caches
	net: return correct error code
	platform/x86: thinkpad_acpi: Fix WWAN device disabled issue after S3 deep
	s390/setup: avoid using memblock_enforce_memory_limit
	scsi: iscsi: Unblock session then wake up error handler
	net: tulip: de4x5: fix the problem that the array 'lp->phy[8]' may be out of bound
	net: ethernet: dec: tulip: de4x5: fix possible array overflows in type3_infoblock()
	kprobes: Limit max data_size of the kretprobe instances
	sata_fsl: fix UAF in sata_fsl_port_stop when rmmod sata_fsl
	sata_fsl: fix warning in remove_proc_entry when rmmod sata_fsl
	fs: add fget_many() and fput_many()
	fget: check that the fd still exists after getting a ref to it
	natsemi: xtensa: fix section mismatch warnings
	net: qlogic: qlcnic: Fix a NULL pointer dereference in qlcnic_83xx_add_rings()
	siphash: use _unaligned version by default
	parisc: Fix "make install" on newer debian releases
	vgacon: Propagate console boot parameters before calling `vc_resize'
	tty: serial: msm_serial: Deactivate RX DMA for polling support
	serial: pl011: Add ACPI SBSA UART match id
	Linux 4.4.294

Signed-off-by: Greg Kroah-Hartman <gregkh@google.com>
Change-Id: Id3cafc33da957a0501bcf61d000025167d552797

1 files changed, 47 insertions, 11 deletions

diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 86a5c9852acf..3184845236ee 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -3273,14 +3273,19 @@ void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma,
 	struct page *page;
 	struct hstate *h = hstate_vma(vma);
 	unsigned long sz = huge_page_size(h);
-	const unsigned long mmun_start = start;	/* For mmu_notifiers */
-	const unsigned long mmun_end   = end;	/* For mmu_notifiers */
+	unsigned long mmun_start = start;	/* For mmu_notifiers */
+	unsigned long mmun_end   = end;		/* For mmu_notifiers */
 
 	WARN_ON(!is_vm_hugetlb_page(vma));
 	BUG_ON(start & ~huge_page_mask(h));
 	BUG_ON(end & ~huge_page_mask(h));
 
 	tlb_start_vma(tlb, vma);
+
+	/*
+	 * If sharing possible, alert mmu notifiers of worst case.
+	 */
+	adjust_range_if_pmd_sharing_possible(vma, &mmun_start, &mmun_end);
 	mmu_notifier_invalidate_range_start(mm, mmun_start, mmun_end);
 	address = start;
 again:
@@ -3290,8 +3295,11 @@ again:
 			continue;
 
 		ptl = huge_pte_lock(h, mm, ptep);
-		if (huge_pmd_unshare(mm, &address, ptep))
+		if (huge_pmd_unshare(mm, &address, ptep)) {
+			tlb_flush_pmd_range(tlb, address & PUD_MASK, PUD_SIZE);
+			force_flush = 1;
 			goto unlock;
+		}
 
 		pte = huge_ptep_get(ptep);
 		if (huge_pte_none(pte))
@@ -3384,12 +3392,23 @@ void unmap_hugepage_range(struct vm_area_struct *vma, unsigned long start,
 {
 	struct mm_struct *mm;
 	struct mmu_gather tlb;
+	unsigned long tlb_start = start;
+	unsigned long tlb_end = end;
+
+	/*
+	 * If shared PMDs were possibly used within this vma range, adjust
+	 * start/end for worst case tlb flushing.
+	 * Note that we can not be sure if PMDs are shared until we try to
+	 * unmap pages.  However, we want to make sure TLB flushing covers
+	 * the largest possible range.
+	 */
+	adjust_range_if_pmd_sharing_possible(vma, &tlb_start, &tlb_end);
 
 	mm = vma->vm_mm;
 
-	tlb_gather_mmu(&tlb, mm, start, end);
+	tlb_gather_mmu(&tlb, mm, tlb_start, tlb_end);
 	__unmap_hugepage_range(&tlb, vma, start, end, ref_page);
-	tlb_finish_mmu(&tlb, start, end);
+	tlb_finish_mmu(&tlb, tlb_start, tlb_end);
 }
 
 /*
@@ -4065,11 +4084,21 @@ unsigned long hugetlb_change_protection(struct vm_area_struct *vma,
 	pte_t pte;
 	struct hstate *h = hstate_vma(vma);
 	unsigned long pages = 0;
+	unsigned long f_start = start;
+	unsigned long f_end = end;
+	bool shared_pmd = false;
+
+	/*
+	 * In the case of shared PMDs, the area to flush could be beyond
+	 * start/end.  Set f_start/f_end to cover the maximum possible
+	 * range if PMD sharing is possible.
+	 */
+	adjust_range_if_pmd_sharing_possible(vma, &f_start, &f_end);
 
 	BUG_ON(address >= end);
-	flush_cache_range(vma, address, end);
+	flush_cache_range(vma, f_start, f_end);
 
-	mmu_notifier_invalidate_range_start(mm, start, end);
+	mmu_notifier_invalidate_range_start(mm, f_start, f_end);
 	i_mmap_lock_write(vma->vm_file->f_mapping);
 	for (; address < end; address += huge_page_size(h)) {
 		spinlock_t *ptl;
@@ -4080,6 +4109,7 @@ unsigned long hugetlb_change_protection(struct vm_area_struct *vma,
 		if (huge_pmd_unshare(mm, &address, ptep)) {
 			pages++;
 			spin_unlock(ptl);
+			shared_pmd = true;
 			continue;
 		}
 		pte = huge_ptep_get(ptep);
@@ -4114,12 +4144,18 @@ unsigned long hugetlb_change_protection(struct vm_area_struct *vma,
 	 * Must flush TLB before releasing i_mmap_rwsem: x86's huge_pmd_unshare
 	 * may have cleared our pud entry and done put_page on the page table:
 	 * once we release i_mmap_rwsem, another task can do the final put_page
-	 * and that page table be reused and filled with junk.
+	 * and that page table be reused and filled with junk.  If we actually
+	 * did unshare a page of pmds, flush the range corresponding to the pud.
 	 */
-	flush_tlb_range(vma, start, end);
-	mmu_notifier_invalidate_range(mm, start, end);
+	if (shared_pmd) {
+		flush_tlb_range(vma, f_start, f_end);
+		mmu_notifier_invalidate_range(mm, f_start, f_end);
+	} else {
+		flush_tlb_range(vma, start, end);
+		mmu_notifier_invalidate_range(mm, start, end);
+	}
 	i_mmap_unlock_write(vma->vm_file->f_mapping);
-	mmu_notifier_invalidate_range_end(mm, start, end);
+	mmu_notifier_invalidate_range_end(mm, f_start, f_end);
 
 	return pages << h->order;
 }