Merge 4.4.115 into android-4.4

Changes in 4.4.115
	loop: fix concurrent lo_open/lo_release
	bpf: fix branch pruning logic
	x86: bpf_jit: small optimization in emit_bpf_tail_call()
	bpf: fix bpf_tail_call() x64 JIT
	bpf: introduce BPF_JIT_ALWAYS_ON config
	bpf: arsh is not supported in 32 bit alu thus reject it
	bpf: avoid false sharing of map refcount with max_entries
	bpf: fix divides by zero
	bpf: fix 32-bit divide by zero
	bpf: reject stores into ctx via st and xadd
	x86/pti: Make unpoison of pgd for trusted boot work for real
	kaiser: fix intel_bts perf crashes
	ALSA: seq: Make ioctls race-free
	crypto: aesni - handle zero length dst buffer
	crypto: af_alg - whitelist mask and type
	power: reset: zx-reboot: add missing MODULE_DESCRIPTION/AUTHOR/LICENSE
	gpio: iop: add missing MODULE_DESCRIPTION/AUTHOR/LICENSE
	gpio: ath79: add missing MODULE_DESCRIPTION/LICENSE
	mtd: nand: denali_pci: add missing MODULE_DESCRIPTION/AUTHOR/LICENSE
	igb: Free IRQs when device is hotplugged
	KVM: x86: emulator: Return to user-mode on L1 CPL=0 emulation failure
	KVM: x86: Don't re-execute instruction when not passing CR2 value
	KVM: X86: Fix operand/address-size during instruction decoding
	KVM: x86: ioapic: Fix level-triggered EOI and IOAPIC reconfigure race
	KVM: x86: ioapic: Clear Remote IRR when entry is switched to edge-triggered
	KVM: x86: ioapic: Preserve read-only values in the redirection table
	ACPI / bus: Leave modalias empty for devices which are not present
	cpufreq: Add Loongson machine dependencies
	bcache: check return value of register_shrinker
	drm/amdgpu: Fix SDMA load/unload sequence on HWS disabled mode
	drm/amdkfd: Fix SDMA ring buffer size calculation
	drm/amdkfd: Fix SDMA oversubsription handling
	openvswitch: fix the incorrect flow action alloc size
	mac80211: fix the update of path metric for RANN frame
	btrfs: fix deadlock when writing out space cache
	KVM: VMX: Fix rflags cache during vCPU reset
	xen-netfront: remove warning when unloading module
	nfsd: CLOSE SHOULD return the invalid special stateid for NFSv4.x (x>0)
	nfsd: Ensure we check stateid validity in the seqid operation checks
	grace: replace BUG_ON by WARN_ONCE in exit_net hook
	nfsd: check for use of the closed special stateid
	lockd: fix "list_add double add" caused by legacy signal interface
	hwmon: (pmbus) Use 64bit math for DIRECT format values
	net: ethernet: xilinx: Mark XILINX_LL_TEMAC broken on 64-bit
	quota: Check for register_shrinker() failure.
	SUNRPC: Allow connect to return EHOSTUNREACH
	kmemleak: add scheduling point to kmemleak_scan()
	drm/omap: Fix error handling path in 'omap_dmm_probe()'
	xfs: ubsan fixes
	scsi: aacraid: Prevent crash in case of free interrupt during scsi EH path
	scsi: ufs: ufshcd: fix potential NULL pointer dereference in ufshcd_config_vreg
	media: usbtv: add a new usbid
	usb: gadget: don't dereference g until after it has been null checked
	staging: rtl8188eu: Fix incorrect response to SIOCGIWESSID
	usb: option: Add support for FS040U modem
	USB: serial: pl2303: new device id for Chilitag
	USB: cdc-acm: Do not log urb submission errors on disconnect
	CDC-ACM: apply quirk for card reader
	USB: serial: io_edgeport: fix possible sleep-in-atomic
	usbip: prevent bind loops on devices attached to vhci_hcd
	usbip: list: don't list devices attached to vhci_hcd
	USB: serial: simple: add Motorola Tetra driver
	usb: f_fs: Prevent gadget unbind if it is already unbound
	usb: uas: unconditionally bring back host after reset
	selinux: general protection fault in sock_has_perm
	serial: imx: Only wakeup via RTSDEN bit if the system has RTS/CTS
	spi: imx: do not access registers while clocks disabled
	Linux 4.4.115

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

12 files changed, 82 insertions, 26 deletions

diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 251aa1b453c2..768151fcb2cb 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -59,6 +59,7 @@ config ARM64
 	select HAVE_ARCH_SECCOMP_FILTER
 	select HAVE_ARCH_TRACEHOOK
 	select HAVE_BPF_JIT
+	select HAVE_EBPF_JIT
 	select HAVE_C_RECORDMCOUNT
 	select HAVE_CC_STACKPROTECTOR
 	select HAVE_CMPXCHG_DOUBLE
diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig
index 5ad7b721b769..2ee95ece0498 100644
--- a/arch/s390/Kconfig
+++ b/arch/s390/Kconfig
@@ -123,6 +123,7 @@ config S390
 	select HAVE_ARCH_TRACEHOOK
 	select HAVE_ARCH_TRANSPARENT_HUGEPAGE
 	select HAVE_BPF_JIT if PACK_STACK && HAVE_MARCH_Z196_FEATURES
+	select HAVE_EBPF_JIT if PACK_STACK && HAVE_MARCH_Z196_FEATURES
 	select HAVE_CMPXCHG_DOUBLE
 	select HAVE_CMPXCHG_LOCAL
 	select HAVE_DEBUG_KMEMLEAK
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 0c4157470e45..02eb4db5d0b7 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -93,6 +93,7 @@ config X86
 	select HAVE_ARCH_TRANSPARENT_HUGEPAGE
 	select HAVE_ARCH_WITHIN_STACK_FRAMES
 	select HAVE_BPF_JIT			if X86_64
+	select HAVE_EBPF_JIT			if X86_64
 	select HAVE_CC_STACKPROTECTOR
 	select HAVE_CMPXCHG_DOUBLE
 	select HAVE_CMPXCHG_LOCAL
diff --git a/arch/x86/crypto/aesni-intel_glue.c b/arch/x86/crypto/aesni-intel_glue.c
index 3633ad6145c5..c18806b5db2a 100644
--- a/arch/x86/crypto/aesni-intel_glue.c
+++ b/arch/x86/crypto/aesni-intel_glue.c
@@ -965,7 +965,7 @@ static int helper_rfc4106_encrypt(struct aead_request *req)
 
 	if (sg_is_last(req->src) &&
 	    req->src->offset + req->src->length <= PAGE_SIZE &&
-	    sg_is_last(req->dst) &&
+	    sg_is_last(req->dst) && req->dst->length &&
 	    req->dst->offset + req->dst->length <= PAGE_SIZE) {
 		one_entry_in_sg = 1;
 		scatterwalk_start(&src_sg_walk, req->src);
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 9d2abb2a41d2..74fda1a453bd 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -998,7 +998,8 @@ int x86_emulate_instruction(struct kvm_vcpu *vcpu, unsigned long cr2,
 static inline int emulate_instruction(struct kvm_vcpu *vcpu,
 			int emulation_type)
 {
-	return x86_emulate_instruction(vcpu, 0, emulation_type, NULL, 0);
+	return x86_emulate_instruction(vcpu, 0,
+			emulation_type | EMULTYPE_NO_REEXECUTE, NULL, 0);
 }
 
 void kvm_enable_efer_bits(u64);
diff --git a/arch/x86/kernel/cpu/perf_event_intel_bts.c b/arch/x86/kernel/cpu/perf_event_intel_bts.c
index 2cad71d1b14c..5af11c46d0b9 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_bts.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_bts.c
@@ -22,6 +22,7 @@
 #include <linux/debugfs.h>
 #include <linux/device.h>
 #include <linux/coredump.h>
+#include <linux/kaiser.h>
 
 #include <asm-generic/sizes.h>
 #include <asm/perf_event.h>
@@ -67,6 +68,23 @@ static size_t buf_size(struct page *page)
 	return 1 << (PAGE_SHIFT + page_private(page));
 }
 
+static void bts_buffer_free_aux(void *data)
+{
+#ifdef CONFIG_PAGE_TABLE_ISOLATION
+	struct bts_buffer *buf = data;
+	int nbuf;
+
+	for (nbuf = 0; nbuf < buf->nr_bufs; nbuf++) {
+		struct page *page = buf->buf[nbuf].page;
+		void *kaddr = page_address(page);
+		size_t page_size = buf_size(page);
+
+		kaiser_remove_mapping((unsigned long)kaddr, page_size);
+	}
+#endif
+	kfree(data);
+}
+
 static void *
 bts_buffer_setup_aux(int cpu, void **pages, int nr_pages, bool overwrite)
 {
@@ -103,29 +121,33 @@ bts_buffer_setup_aux(int cpu, void **pages, int nr_pages, bool overwrite)
 	buf->real_size = size - size % BTS_RECORD_SIZE;
 
 	for (pg = 0, nbuf = 0, offset = 0, pad = 0; nbuf < buf->nr_bufs; nbuf++) {
-		unsigned int __nr_pages;
+		void *kaddr = pages[pg];
+		size_t page_size;
+
+		page = virt_to_page(kaddr);
+		page_size = buf_size(page);
+
+		if (kaiser_add_mapping((unsigned long)kaddr,
+					page_size, __PAGE_KERNEL) < 0) {
+			buf->nr_bufs = nbuf;
+			bts_buffer_free_aux(buf);
+			return NULL;
+		}
 
-		page = virt_to_page(pages[pg]);
-		__nr_pages = PagePrivate(page) ? 1 << page_private(page) : 1;
 		buf->buf[nbuf].page = page;
 		buf->buf[nbuf].offset = offset;
 		buf->buf[nbuf].displacement = (pad ? BTS_RECORD_SIZE - pad : 0);
-		buf->buf[nbuf].size = buf_size(page) - buf->buf[nbuf].displacement;
+		buf->buf[nbuf].size = page_size - buf->buf[nbuf].displacement;
 		pad = buf->buf[nbuf].size % BTS_RECORD_SIZE;
 		buf->buf[nbuf].size -= pad;
 
-		pg += __nr_pages;
-		offset += __nr_pages << PAGE_SHIFT;
+		pg += page_size >> PAGE_SHIFT;
+		offset += page_size;
 	}
 
 	return buf;
 }
 
-static void bts_buffer_free_aux(void *data)
-{
-	kfree(data);
-}
-
 static unsigned long bts_buffer_offset(struct bts_buffer *buf, unsigned int idx)
 {
 	return buf->buf[idx].offset + buf->buf[idx].displacement;
diff --git a/arch/x86/kernel/tboot.c b/arch/x86/kernel/tboot.c
index 91a4496db434..c77ab1f51fbe 100644
--- a/arch/x86/kernel/tboot.c
+++ b/arch/x86/kernel/tboot.c
@@ -140,6 +140,16 @@ static int map_tboot_page(unsigned long vaddr, unsigned long pfn,
 		return -1;
 	set_pte_at(&tboot_mm, vaddr, pte, pfn_pte(pfn, prot));
 	pte_unmap(pte);
+
+	/*
+	 * PTI poisons low addresses in the kernel page tables in the
+	 * name of making them unusable for userspace.  To execute
+	 * code at such a low address, the poison must be cleared.
+	 *
+	 * Note: 'pgd' actually gets set in pud_alloc().
+	 */
+	pgd->pgd &= ~_PAGE_NX;
+
 	return 0;
 }
 
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index 00045499f6c2..e4eb1d2bf849 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -4978,6 +4978,8 @@ int x86_decode_insn(struct x86_emulate_ctxt *ctxt, void *insn, int insn_len)
 	bool op_prefix = false;
 	bool has_seg_override = false;
 	struct opcode opcode;
+	u16 dummy;
+	struct desc_struct desc;
 
 	ctxt->memop.type = OP_NONE;
 	ctxt->memopp = NULL;
@@ -4996,6 +4998,11 @@ int x86_decode_insn(struct x86_emulate_ctxt *ctxt, void *insn, int insn_len)
 	switch (mode) {
 	case X86EMUL_MODE_REAL:
 	case X86EMUL_MODE_VM86:
+		def_op_bytes = def_ad_bytes = 2;
+		ctxt->ops->get_segment(ctxt, &dummy, &desc, NULL, VCPU_SREG_CS);
+		if (desc.d)
+			def_op_bytes = def_ad_bytes = 4;
+		break;
 	case X86EMUL_MODE_PROT16:
 		def_op_bytes = def_ad_bytes = 2;
 		break;
diff --git a/arch/x86/kvm/ioapic.c b/arch/x86/kvm/ioapic.c
index 3aab53f8cad2..d380111351c0 100644
--- a/arch/x86/kvm/ioapic.c
+++ b/arch/x86/kvm/ioapic.c
@@ -247,8 +247,7 @@ void kvm_ioapic_scan_entry(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap)
 		    index == RTC_GSI) {
 			if (kvm_apic_match_dest(vcpu, NULL, 0,
 			             e->fields.dest_id, e->fields.dest_mode) ||
-			    (e->fields.trig_mode == IOAPIC_EDGE_TRIG &&
-			     kvm_apic_pending_eoi(vcpu, e->fields.vector)))
+			    kvm_apic_pending_eoi(vcpu, e->fields.vector))
 				__set_bit(e->fields.vector,
 					(unsigned long *)eoi_exit_bitmap);
 		}
@@ -269,6 +268,7 @@ static void ioapic_write_indirect(struct kvm_ioapic *ioapic, u32 val)
 {
 	unsigned index;
 	bool mask_before, mask_after;
+	int old_remote_irr, old_delivery_status;
 	union kvm_ioapic_redirect_entry *e;
 
 	switch (ioapic->ioregsel) {
@@ -291,14 +291,28 @@ static void ioapic_write_indirect(struct kvm_ioapic *ioapic, u32 val)
 			return;
 		e = &ioapic->redirtbl[index];
 		mask_before = e->fields.mask;
+		/* Preserve read-only fields */
+		old_remote_irr = e->fields.remote_irr;
+		old_delivery_status = e->fields.delivery_status;
 		if (ioapic->ioregsel & 1) {
 			e->bits &= 0xffffffff;
 			e->bits |= (u64) val << 32;
 		} else {
 			e->bits &= ~0xffffffffULL;
 			e->bits |= (u32) val;
-			e->fields.remote_irr = 0;
 		}
+		e->fields.remote_irr = old_remote_irr;
+		e->fields.delivery_status = old_delivery_status;
+
+		/*
+		 * Some OSes (Linux, Xen) assume that Remote IRR bit will
+		 * be cleared by IOAPIC hardware when the entry is configured
+		 * as edge-triggered. This behavior is used to simulate an
+		 * explicit EOI on IOAPICs that don't have the EOI register.
+		 */
+		if (e->fields.trig_mode == IOAPIC_EDGE_TRIG)
+			e->fields.remote_irr = 0;
+
 		mask_after = e->fields.mask;
 		if (mask_before != mask_after)
 			kvm_fire_mask_notifiers(ioapic->kvm, KVM_IRQCHIP_IOAPIC, index, mask_after);
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 75d60e40c389..f8d785aa2e96 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -4954,7 +4954,7 @@ static void vmx_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event)
 		vmcs_write64(GUEST_IA32_DEBUGCTL, 0);
 	}
 
-	vmcs_writel(GUEST_RFLAGS, 0x02);
+	kvm_set_rflags(vcpu, X86_EFLAGS_FIXED);
 	kvm_rip_write(vcpu, 0xfff0);
 
 	vmcs_writel(GUEST_GDTR_BASE, 0);
@@ -6023,7 +6023,7 @@ static int handle_invalid_guest_state(struct kvm_vcpu *vcpu)
 		if (test_bit(KVM_REQ_EVENT, &vcpu->requests))
 			return 1;
 
-		err = emulate_instruction(vcpu, EMULTYPE_NO_REEXECUTE);
+		err = emulate_instruction(vcpu, 0);
 
 		if (err == EMULATE_USER_EXIT) {
 			++vcpu->stat.mmio_exits;
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index f973cfa8ff4f..3900d34980de 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -5153,7 +5153,7 @@ static int handle_emulation_failure(struct kvm_vcpu *vcpu)
 		vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
 		vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_EMULATION;
 		vcpu->run->internal.ndata = 0;
-		r = EMULATE_FAIL;
+		r = EMULATE_USER_EXIT;
 	}
 	kvm_queue_exception(vcpu, UD_VECTOR);
 
diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index 75991979f667..33c42b826791 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -266,10 +266,10 @@ static void emit_bpf_tail_call(u8 **pprog)
 	/* if (index >= array->map.max_entries)
 	 *   goto out;
 	 */
-	EMIT4(0x48, 0x8B, 0x46,                   /* mov rax, qword ptr [rsi + 16] */
+	EMIT2(0x89, 0xD2);                        /* mov edx, edx */
+	EMIT3(0x39, 0x56,                         /* cmp dword ptr [rsi + 16], edx */
 	      offsetof(struct bpf_array, map.max_entries));
-	EMIT3(0x48, 0x39, 0xD0);                  /* cmp rax, rdx */
-#define OFFSET1 47 /* number of bytes to jump */
+#define OFFSET1 43 /* number of bytes to jump */
 	EMIT2(X86_JBE, OFFSET1);                  /* jbe out */
 	label1 = cnt;
 
@@ -278,21 +278,20 @@ static void emit_bpf_tail_call(u8 **pprog)
 	 */
 	EMIT2_off32(0x8B, 0x85, -STACKSIZE + 36); /* mov eax, dword ptr [rbp - 516] */
 	EMIT3(0x83, 0xF8, MAX_TAIL_CALL_CNT);     /* cmp eax, MAX_TAIL_CALL_CNT */
-#define OFFSET2 36
+#define OFFSET2 32
 	EMIT2(X86_JA, OFFSET2);                   /* ja out */
 	label2 = cnt;
 	EMIT3(0x83, 0xC0, 0x01);                  /* add eax, 1 */
 	EMIT2_off32(0x89, 0x85, -STACKSIZE + 36); /* mov dword ptr [rbp - 516], eax */
 
 	/* prog = array->ptrs[index]; */
-	EMIT4_off32(0x48, 0x8D, 0x84, 0xD6,       /* lea rax, [rsi + rdx * 8 + offsetof(...)] */
+	EMIT4_off32(0x48, 0x8B, 0x84, 0xD6,       /* mov rax, [rsi + rdx * 8 + offsetof(...)] */
 		    offsetof(struct bpf_array, ptrs));
-	EMIT3(0x48, 0x8B, 0x00);                  /* mov rax, qword ptr [rax] */
 
 	/* if (prog == NULL)
 	 *   goto out;
 	 */
-	EMIT4(0x48, 0x83, 0xF8, 0x00);            /* cmp rax, 0 */
+	EMIT3(0x48, 0x85, 0xC0);		  /* test rax,rax */
 #define OFFSET3 10
 	EMIT2(X86_JE, OFFSET3);                   /* je out */
 	label3 = cnt;