4.4.7-stable review

@@ -4949,7 +4949,10 @@ static ssize_t tracing_splice_read_pipe(
 
 	spd.nr_pages = i;
 
-	ret = splice_to_pipe(pipe, &spd);
+	if (i)
+		ret = splice_to_pipe(pipe, &spd);
+	else
+		ret = 0;
 out:
 	splice_shrink_spd(&spd);
 	return ret;

@@ -607,7 +607,7 @@ do {							\
 
 #define do_trace_printk(fmt, args...)					\
 do {									\
-	static const char *trace_printk_fmt				\
+	static const char *trace_printk_fmt __used			\
 		__attribute__((section("__trace_printk_fmt"))) =	\
 		__builtin_constant_p(fmt) ? fmt : NULL;			\
 									\

@@ -651,7 +651,7 @@ int __trace_printk(unsigned long ip, con
  */
 
 #define trace_puts(str) ({						\
-	static const char *trace_printk_fmt				\
+	static const char *trace_printk_fmt __used			\
 		__attribute__((section("__trace_printk_fmt"))) =	\
 		__builtin_constant_p(str) ? str : NULL;			\
 									\

@@ -673,7 +673,7 @@ extern void trace_dump_stack(int skip);
 #define ftrace_vprintk(fmt, vargs)					\
 do {									\
 	if (__builtin_constant_p(fmt)) {				\
-		static const char *trace_printk_fmt			\
+		static const char *trace_printk_fmt __used		\
 		  __attribute__((section("__trace_printk_fmt"))) =	\
 			__builtin_constant_p(fmt) ? fmt : NULL;		\
 									\

@@ -296,6 +296,9 @@ static int t_show(struct seq_file *m, vo
 	const char *str = *fmt;
 	int i;
 
+	if (!*fmt)
+		return 0;
+
 	seq_printf(m, "0x%lx : \"", *(unsigned long *)fmt);
 
 	/*

@@ -29,16 +29,16 @@ do {					\
  * @nr: the bit to set
  * @addr: the address to start counting from
  *
- * This operation is like clear_bit_unlock, however it is not atomic.
- * It does provide release barrier semantics so it can be used to unlock
- * a bit lock, however it would only be used if no other CPU can modify
- * any bits in the memory until the lock is released (a good example is
- * if the bit lock itself protects access to the other bits in the word).
+ * A weaker form of clear_bit_unlock() as used by __bit_lock_unlock(). If all
+ * the bits in the word are protected by this lock some archs can use weaker
+ * ops to safely unlock.
+ *
+ * See for example x86's implementation.
  */
 #define __clear_bit_unlock(nr, addr)	\
 do {					\
-	smp_mb();			\
-	__clear_bit(nr, addr);		\
+	smp_mb__before_atomic();	\
+	clear_bit(nr, addr);		\
 } while (0)
 
 #endif /* _ASM_GENERIC_BITOPS_LOCK_H_ */

@@ -865,6 +865,20 @@ static const struct dmi_system_id no_hw_
 		},
 	},
 	{
+		.ident = "Lenovo ideapad Y700-15ISK",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
+			DMI_MATCH(DMI_PRODUCT_VERSION, "Lenovo ideapad Y700-15ISK"),
+		},
+	},
+	{
+		.ident = "Lenovo ideapad Y700 Touch-15ISK",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
+			DMI_MATCH(DMI_PRODUCT_VERSION, "Lenovo ideapad Y700 Touch-15ISK"),
+		},
+	},
+	{
 		.ident = "Lenovo ideapad Y700-17ISK",
 		.matches = {
 			DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),

@@ -596,6 +596,14 @@ static int mmc_blk_ioctl_cmd(struct bloc
 	struct mmc_card *card;
 	int err = 0, ioc_err = 0;
 
+	/*
+	 * The caller must have CAP_SYS_RAWIO, and must be calling this on the
+	 * whole block device, not on a partition.  This prevents overspray
+	 * between sibling partitions.
+	 */
+	if ((!capable(CAP_SYS_RAWIO)) || (bdev != bdev->bd_contains))
+		return -EPERM;
+
 	idata = mmc_blk_ioctl_copy_from_user(ic_ptr);
 	if (IS_ERR(idata))
 		return PTR_ERR(idata);

@@ -638,6 +646,14 @@ static int mmc_blk_ioctl_multi_cmd(struc
 	int i, err = 0, ioc_err = 0;
 	__u64 num_of_cmds;
 
+	/*
+	 * The caller must have CAP_SYS_RAWIO, and must be calling this on the
+	 * whole block device, not on a partition.  This prevents overspray
+	 * between sibling partitions.
+	 */
+	if ((!capable(CAP_SYS_RAWIO)) || (bdev != bdev->bd_contains))
+		return -EPERM;
+
 	if (copy_from_user(&num_of_cmds, &user->num_of_cmds,
 			   sizeof(num_of_cmds)))
 		return -EFAULT;

@@ -693,14 +709,6 @@ cmd_err:
 static int mmc_blk_ioctl(struct block_device *bdev, fmode_t mode,
 	unsigned int cmd, unsigned long arg)
 {
-	/*
-	 * The caller must have CAP_SYS_RAWIO, and must be calling this on the
-	 * whole block device, not on a partition.  This prevents overspray
-	 * between sibling partitions.
-	 */
-	if ((!capable(CAP_SYS_RAWIO)) || (bdev != bdev->bd_contains))
-		return -EPERM;
-
 	switch (cmd) {
 	case MMC_IOC_CMD:
 		return mmc_blk_ioctl_cmd(bdev,

@@ -1436,6 +1436,12 @@ static int mmc_spi_probe(struct spi_devi
 					     host->pdata->cd_debounce);
 		if (status != 0)
 			goto fail_add_host;
+
+		/* The platform has a CD GPIO signal that may support
+		 * interrupts, so let mmc_gpiod_request_cd_irq() decide
+		 * if polling is needed or not.
+		 */
+		mmc->caps &= ~MMC_CAP_NEEDS_POLL;
 		mmc_gpiod_request_cd_irq(mmc);
 	}
 

@@ -666,7 +666,7 @@ static u8 sdhci_calc_timeout(struct sdhc
 	if (!data)
 		target_timeout = cmd->busy_timeout * 1000;
 	else {
-		target_timeout = data->timeout_ns / 1000;
+		target_timeout = DIV_ROUND_UP(data->timeout_ns, 1000);
 		if (host->clock)
 			target_timeout += data->timeout_clks / host->clock;
 	}

@@ -667,8 +667,19 @@ static u8 sdhci_calc_timeout(struct sdhc
 		target_timeout = cmd->busy_timeout * 1000;
 	else {
 		target_timeout = DIV_ROUND_UP(data->timeout_ns, 1000);
-		if (host->clock)
-			target_timeout += data->timeout_clks / host->clock;
+		if (host->clock && data->timeout_clks) {
+			unsigned long long val;
+
+			/*
+			 * data->timeout_clks is in units of clock cycles.
+			 * host->clock is in Hz.  target_timeout is in us.
+			 * Hence, us = 1000000 * cycles / Hz.  Round up.
+			 */
+			val = 1000000 * data->timeout_clks;
+			if (do_div(val, host->clock))
+				target_timeout++;
+			target_timeout += val;
+		}
 	}
 
 	/*

@@ -3106,14 +3106,14 @@ int sdhci_add_host(struct sdhci_host *ho
 		if (caps[0] & SDHCI_TIMEOUT_CLK_UNIT)
 			host->timeout_clk *= 1000;
 
+		if (override_timeout_clk)
+			host->timeout_clk = override_timeout_clk;
+
 		mmc->max_busy_timeout = host->ops->get_max_timeout_count ?
 			host->ops->get_max_timeout_count(host) : 1 << 27;
 		mmc->max_busy_timeout /= host->timeout_clk;
 	}
 
-	if (override_timeout_clk)
-		host->timeout_clk = override_timeout_clk;
-
 	mmc->caps |= MMC_CAP_SDIO_IRQ | MMC_CAP_ERASE | MMC_CAP_CMD23;
 	mmc->caps2 |= MMC_CAP2_SDIO_IRQ_NOTHREAD;
 

@@ -165,7 +165,7 @@ static const struct rockchip_cpuclk_reg_
 	.core_reg = RK3368_CLKSEL_CON(0),
 	.div_core_shift = 0,
 	.div_core_mask = 0x1f,
-	.mux_core_shift = 15,
+	.mux_core_shift = 7,
 };
 
 static const struct rockchip_cpuclk_reg_data rk3368_cpuclkl_data = {

@@ -218,29 +218,29 @@ static const struct rockchip_cpuclk_reg_
 	}
 
 static struct rockchip_cpuclk_rate_table rk3368_cpuclkb_rates[] __initdata = {
-	RK3368_CPUCLKB_RATE(1512000000, 2, 6, 6),
-	RK3368_CPUCLKB_RATE(1488000000, 2, 5, 5),
-	RK3368_CPUCLKB_RATE(1416000000, 2, 5, 5),
-	RK3368_CPUCLKB_RATE(1200000000, 2, 4, 4),
-	RK3368_CPUCLKB_RATE(1008000000, 2, 4, 4),
-	RK3368_CPUCLKB_RATE( 816000000, 2, 3, 3),
-	RK3368_CPUCLKB_RATE( 696000000, 2, 3, 3),
-	RK3368_CPUCLKB_RATE( 600000000, 2, 2, 2),
-	RK3368_CPUCLKB_RATE( 408000000, 2, 2, 2),
-	RK3368_CPUCLKB_RATE( 312000000, 2, 2, 2),
+	RK3368_CPUCLKB_RATE(1512000000, 1, 5, 5),
+	RK3368_CPUCLKB_RATE(1488000000, 1, 4, 4),
+	RK3368_CPUCLKB_RATE(1416000000, 1, 4, 4),
+	RK3368_CPUCLKB_RATE(1200000000, 1, 3, 3),
+	RK3368_CPUCLKB_RATE(1008000000, 1, 3, 3),
+	RK3368_CPUCLKB_RATE( 816000000, 1, 2, 2),
+	RK3368_CPUCLKB_RATE( 696000000, 1, 2, 2),
+	RK3368_CPUCLKB_RATE( 600000000, 1, 1, 1),
+	RK3368_CPUCLKB_RATE( 408000000, 1, 1, 1),
+	RK3368_CPUCLKB_RATE( 312000000, 1, 1, 1),
 };
 
 static struct rockchip_cpuclk_rate_table rk3368_cpuclkl_rates[] __initdata = {
-	RK3368_CPUCLKL_RATE(1512000000, 2, 7, 7),
-	RK3368_CPUCLKL_RATE(1488000000, 2, 6, 6),
-	RK3368_CPUCLKL_RATE(1416000000, 2, 6, 6),
-	RK3368_CPUCLKL_RATE(1200000000, 2, 5, 5),
-	RK3368_CPUCLKL_RATE(1008000000, 2, 5, 5),
-	RK3368_CPUCLKL_RATE( 816000000, 2, 4, 4),
-	RK3368_CPUCLKL_RATE( 696000000, 2, 3, 3),
-	RK3368_CPUCLKL_RATE( 600000000, 2, 3, 3),
-	RK3368_CPUCLKL_RATE( 408000000, 2, 2, 2),
-	RK3368_CPUCLKL_RATE( 312000000, 2, 2, 2),
+	RK3368_CPUCLKL_RATE(1512000000, 1, 6, 6),
+	RK3368_CPUCLKL_RATE(1488000000, 1, 5, 5),
+	RK3368_CPUCLKL_RATE(1416000000, 1, 5, 5),
+	RK3368_CPUCLKL_RATE(1200000000, 1, 4, 4),
+	RK3368_CPUCLKL_RATE(1008000000, 1, 4, 4),
+	RK3368_CPUCLKL_RATE( 816000000, 1, 3, 3),
+	RK3368_CPUCLKL_RATE( 696000000, 1, 2, 2),
+	RK3368_CPUCLKL_RATE( 600000000, 1, 2, 2),
+	RK3368_CPUCLKL_RATE( 408000000, 1, 1, 1),
+	RK3368_CPUCLKL_RATE( 312000000, 1, 1, 1),
 };
 
 static struct rockchip_clk_branch rk3368_clk_branches[] __initdata = {

@@ -384,10 +384,10 @@ static struct rockchip_clk_branch rk3368
 	 * Clock-Architecture Diagram 3
 	 */
 
-	COMPOSITE(0, "aclk_vepu", mux_pll_src_cpll_gpll_usb_p, 0,
+	COMPOSITE(0, "aclk_vepu", mux_pll_src_cpll_gpll_npll_usb_p, 0,
 			RK3368_CLKSEL_CON(15), 6, 2, MFLAGS, 0, 5, DFLAGS,
 			RK3368_CLKGATE_CON(4), 6, GFLAGS),
-	COMPOSITE(0, "aclk_vdpu", mux_pll_src_cpll_gpll_usb_p, 0,
+	COMPOSITE(0, "aclk_vdpu", mux_pll_src_cpll_gpll_npll_usb_p, 0,
 			RK3368_CLKSEL_CON(15), 14, 2, MFLAGS, 8, 5, DFLAGS,
 			RK3368_CLKGATE_CON(4), 7, GFLAGS),
 

@@ -442,7 +442,7 @@ static struct rockchip_clk_branch rk3368
 	GATE(SCLK_HDMI_HDCP, "sclk_hdmi_hdcp", "xin24m", 0,
 			RK3368_CLKGATE_CON(4), 13, GFLAGS),
 	GATE(SCLK_HDMI_CEC, "sclk_hdmi_cec", "xin32k", 0,
-			RK3368_CLKGATE_CON(5), 12, GFLAGS),
+			RK3368_CLKGATE_CON(4), 12, GFLAGS),
 
 	COMPOSITE_NODIV(0, "vip_src", mux_pll_src_cpll_gpll_p, 0,
 			RK3368_CLKSEL_CON(21), 15, 1, MFLAGS,

@@ -718,6 +718,7 @@ static const char *const rk3188_critical
 	"hclk_peri",
 	"pclk_cpu",
 	"pclk_peri",
+	"hclk_cpubus"
 };
 
 static void __init rk3188_common_clk_init(struct device_node *np)

@@ -1097,13 +1097,15 @@ static int bcm2835_pll_divider_set_rate(
 	struct bcm2835_pll_divider *divider = bcm2835_pll_divider_from_hw(hw);
 	struct bcm2835_cprman *cprman = divider->cprman;
 	const struct bcm2835_pll_divider_data *data = divider->data;
-	u32 cm;
-	int ret;
+	u32 cm, div, max_div = 1 << A2W_PLL_DIV_BITS;
 
-	ret = clk_divider_ops.set_rate(hw, rate, parent_rate);
-	if (ret)
-		return ret;
+	div = DIV_ROUND_UP_ULL(parent_rate, rate);
 
+	div = min(div, max_div);
+	if (div == max_div)
+		div = 0;
+
+	cprman_write(cprman, data->a2w_reg, div);
 	cm = cprman_read(cprman, data->cm_reg);
 	cprman_write(cprman, data->cm_reg, cm | data->load_mask);
 	cprman_write(cprman, data->cm_reg, cm & ~data->load_mask);

@@ -2618,8 +2618,6 @@ void target_wait_for_sess_cmds(struct se
 
 	list_for_each_entry_safe(se_cmd, tmp_cmd,
 				&se_sess->sess_wait_list, se_cmd_list) {
-		list_del_init(&se_cmd->se_cmd_list);
-
 		pr_debug("Waiting for se_cmd: %p t_state: %d, fabric state:"
 			" %d\n", se_cmd, se_cmd->t_state,
 			se_cmd->se_tfo->get_cmd_state(se_cmd));

@@ -2035,7 +2035,8 @@ is_isert_tx_desc(struct isert_conn *iser
 	void *start = isert_conn->rx_descs;
 	int len = ISERT_QP_MAX_RECV_DTOS * sizeof(*isert_conn->rx_descs);
 
-	if (wr_id >= start && wr_id < start + len)
+	if ((wr_id >= start && wr_id < start + len) ||
+	    (wr_id == isert_conn->login_req_buf))
 		return false;
 
 	return true;

@@ -820,7 +820,7 @@ isert_put_conn(struct isert_conn *isert_
  * @isert_conn: isert connection struct
  *
  * Notes:
- * In case the connection state is FULL_FEATURE, move state
+ * In case the connection state is BOUND, move state
  * to TEMINATING and start teardown sequence (rdma_disconnect).
  * In case the connection state is UP, complete flush as well.
  *

@@ -836,6 +836,7 @@ isert_conn_terminate(struct isert_conn *
 	case ISER_CONN_TERMINATING:
 		break;
 	case ISER_CONN_UP:
+	case ISER_CONN_BOUND:
 	case ISER_CONN_FULL_FEATURE: /* FALLTHRU */
 		isert_info("Terminating conn %p state %d\n",
 			   isert_conn, isert_conn->state);

@@ -2062,7 +2063,8 @@ isert_cq_comp_err(struct isert_conn *ise
 			isert_completion_put(desc, isert_cmd, ib_dev, true);
 	} else {
 		isert_conn->post_recv_buf_count--;
-		if (!isert_conn->post_recv_buf_count)
+		if (!isert_conn->post_recv_buf_count &&
+		    isert_conn->state >= ISER_CONN_BOUND)
 			iscsit_cause_connection_reinstatement(isert_conn->conn, 0);
 	}
 }

@@ -3194,6 +3196,7 @@ accept_wait:
 
 	conn->context = isert_conn;
 	isert_conn->conn = conn;
+	isert_conn->state = ISER_CONN_BOUND;
 
 	isert_set_conn_info(np, conn, isert_conn);
 

@@ -50,6 +50,7 @@ enum iser_ib_op_code {
 enum iser_conn_state {
 	ISER_CONN_INIT,
 	ISER_CONN_UP,
+	ISER_CONN_BOUND,
 	ISER_CONN_FULL_FEATURE,
 	ISER_CONN_TERMINATING,
 	ISER_CONN_DOWN,

@@ -884,14 +884,9 @@ isert_disconnected_handler(struct rdma_c
 			   enum rdma_cm_event_type event)
 {
 	struct isert_np *isert_np = cma_id->context;
-	struct isert_conn *isert_conn;
+	struct isert_conn *isert_conn = cma_id->qp->qp_context;
 	bool terminating = false;
 
-	if (isert_np->cm_id == cma_id)
-		return isert_np_cma_handler(cma_id->context, event);
-
-	isert_conn = cma_id->qp->qp_context;
-
 	mutex_lock(&isert_conn->mutex);
 	terminating = (isert_conn->state == ISER_CONN_TERMINATING);
 	isert_conn_terminate(isert_conn);

@@ -930,12 +925,16 @@ isert_connect_error(struct rdma_cm_id *c
 static int
 isert_cma_handler(struct rdma_cm_id *cma_id, struct rdma_cm_event *event)
 {
+	struct isert_np *isert_np = cma_id->context;
 	int ret = 0;
 
 	isert_info("%s (%d): status %d id %p np %p\n",
 		   rdma_event_msg(event->event), event->event,
 		   event->status, cma_id, cma_id->context);
 
+	if (isert_np->cm_id == cma_id)
+		return isert_np_cma_handler(cma_id->context, event->event);
+
 	switch (event->event) {
 	case RDMA_CM_EVENT_CONNECT_REQUEST:
 		ret = isert_connect_request(cma_id, event);

@@ -66,6 +66,7 @@ isert_rdma_accept(struct isert_conn *ise
 struct rdma_cm_id *isert_setup_id(struct isert_np *isert_np);
 
 static void isert_release_work(struct work_struct *work);
+static void isert_wait4flush(struct isert_conn *isert_conn);
 
 static inline bool
 isert_prot_cmd(struct isert_conn *conn, struct se_cmd *cmd)

@@ -815,6 +816,25 @@ isert_put_conn(struct isert_conn *isert_
 	kref_put(&isert_conn->kref, isert_release_kref);
 }
 
+static void
+isert_handle_unbound_conn(struct isert_conn *isert_conn)
+{
+	struct isert_np *isert_np = isert_conn->cm_id->context;
+
+	mutex_lock(&isert_np->mutex);
+	if (!list_empty(&isert_conn->node)) {
+		/*
+		 * This means iscsi doesn't know this connection
+		 * so schedule a cleanup ourselves
+		 */
+		list_del_init(&isert_conn->node);
+		isert_put_conn(isert_conn);
+		complete(&isert_conn->wait);
+		queue_work(isert_release_wq, &isert_conn->release_work);
+	}
+	mutex_unlock(&isert_np->mutex);
+}
+
 /**
  * isert_conn_terminate() - Initiate connection termination
  * @isert_conn: isert connection struct

@@ -832,24 +852,19 @@ isert_conn_terminate(struct isert_conn *
 {
 	int err;
 
-	switch (isert_conn->state) {
-	case ISER_CONN_TERMINATING:
-		break;
-	case ISER_CONN_UP:
-	case ISER_CONN_BOUND:
-	case ISER_CONN_FULL_FEATURE: /* FALLTHRU */
-		isert_info("Terminating conn %p state %d\n",
-			   isert_conn, isert_conn->state);
-		isert_conn->state = ISER_CONN_TERMINATING;
-		err = rdma_disconnect(isert_conn->cm_id);
-		if (err)
-			isert_warn("Failed rdma_disconnect isert_conn %p\n",
-				   isert_conn);
-		break;
-	default:
-		isert_warn("conn %p teminating in state %d\n",
-			   isert_conn, isert_conn->state);
-	}
+	if (isert_conn->state >= ISER_CONN_TERMINATING)
+		return;
+
+	isert_info("Terminating conn %p state %d\n",
+		   isert_conn, isert_conn->state);
+	isert_conn->state = ISER_CONN_TERMINATING;
+	err = rdma_disconnect(isert_conn->cm_id);
+	if (err)
+		isert_warn("Failed rdma_disconnect isert_conn %p\n",
+			   isert_conn);
+
+	isert_info("conn %p completing wait\n", isert_conn);
+	complete(&isert_conn->wait);
 }
 
 static int

@@ -883,30 +898,27 @@ static int
 isert_disconnected_handler(struct rdma_cm_id *cma_id,
 			   enum rdma_cm_event_type event)
 {
-	struct isert_np *isert_np = cma_id->context;
 	struct isert_conn *isert_conn = cma_id->qp->qp_context;
-	bool terminating = false;
 
 	mutex_lock(&isert_conn->mutex);
-	terminating = (isert_conn->state == ISER_CONN_TERMINATING);
-	isert_conn_terminate(isert_conn);
-	mutex_unlock(&isert_conn->mutex);
-
-	isert_info("conn %p completing wait\n", isert_conn);
-	complete(&isert_conn->wait);
-
-	if (terminating)
-		goto out;
-
-	mutex_lock(&isert_np->mutex);
-	if (!list_empty(&isert_conn->node)) {
-		list_del_init(&isert_conn->node);
-		isert_put_conn(isert_conn);
-		queue_work(isert_release_wq, &isert_conn->release_work);
+	switch (isert_conn->state) {
+	case ISER_CONN_TERMINATING:
+		break;
+	case ISER_CONN_UP:
+		isert_conn_terminate(isert_conn);
+		isert_wait4flush(isert_conn);
+		isert_handle_unbound_conn(isert_conn);
+		break;
+	case ISER_CONN_BOUND:
+	case ISER_CONN_FULL_FEATURE: /* FALLTHRU */
+		iscsit_cause_connection_reinstatement(isert_conn->conn, 0);
+		break;
+	default:
+		isert_warn("conn %p teminating in state %d\n",
+			   isert_conn, isert_conn->state);
 	}
-	mutex_unlock(&isert_np->mutex);
+	mutex_unlock(&isert_conn->mutex);
 
-out:
 	return 0;
 }
 

@@ -980,13 +992,10 @@ isert_post_recvm(struct isert_conn *iser
 	rx_wr--;
 	rx_wr->next = NULL; /* mark end of work requests list */
 
-	isert_conn->post_recv_buf_count += count;
 	ret = ib_post_recv(isert_conn->qp, isert_conn->rx_wr,
 			   &rx_wr_failed);
-	if (ret) {
+	if (ret)
 		isert_err("ib_post_recv() failed with ret: %d\n", ret);
-		isert_conn->post_recv_buf_count -= count;
-	}
 
 	return ret;
 }

@@ -1002,12 +1011,9 @@ isert_post_recv(struct isert_conn *isert
 	rx_wr.num_sge = 1;
 	rx_wr.next = NULL;
 
-	isert_conn->post_recv_buf_count++;
 	ret = ib_post_recv(isert_conn->qp, &rx_wr, &rx_wr_failed);
-	if (ret) {
+	if (ret)
 		isert_err("ib_post_recv() failed with ret: %d\n", ret);
-		isert_conn->post_recv_buf_count--;
-	}
 
 	return ret;
 }

@@ -1120,12 +1126,9 @@ isert_rdma_post_recvl(struct isert_conn
 	rx_wr.sg_list = &sge;
 	rx_wr.num_sge = 1;
 
-	isert_conn->post_recv_buf_count++;
 	ret = ib_post_recv(isert_conn->qp, &rx_wr, &rx_wr_fail);
-	if (ret) {
+	if (ret)
 		isert_err("ib_post_recv() failed: %d\n", ret);
-		isert_conn->post_recv_buf_count--;
-	}
 
 	return ret;
 }

@@ -1620,7 +1623,6 @@ isert_rcv_completion(struct iser_rx_desc
 	ib_dma_sync_single_for_device(ib_dev, rx_dma, rx_buflen,
 				      DMA_FROM_DEVICE);
 
-	isert_conn->post_recv_buf_count--;
 }
 
 static int

@@ -2060,11 +2062,6 @@ isert_cq_comp_err(struct isert_conn *ise
 			isert_unmap_tx_desc(desc, ib_dev);
 		else
 			isert_completion_put(desc, isert_cmd, ib_dev, true);
-	} else {
-		isert_conn->post_recv_buf_count--;
-		if (!isert_conn->post_recv_buf_count &&
-		    isert_conn->state >= ISER_CONN_BOUND)
-			iscsit_cause_connection_reinstatement(isert_conn->conn, 0);
 	}
 }
 

@@ -145,7 +145,6 @@ struct isert_device;
 
 struct isert_conn {
 	enum iser_conn_state	state;
-	int			post_recv_buf_count;
 	u32			responder_resources;
 	u32			initiator_depth;
 	bool			pi_support;

@@ -1072,8 +1072,9 @@ nfsd4_decode_rename(struct nfsd4_compoun
 
 	READ_BUF(4);
 	rename->rn_snamelen = be32_to_cpup(p++);
-	READ_BUF(rename->rn_snamelen + 4);
+	READ_BUF(rename->rn_snamelen);
 	SAVEMEM(rename->rn_sname, rename->rn_snamelen);
+	READ_BUF(4);
 	rename->rn_tnamelen = be32_to_cpup(p++);
 	READ_BUF(rename->rn_tnamelen);
 	SAVEMEM(rename->rn_tname, rename->rn_tnamelen);

@@ -1155,13 +1156,14 @@ nfsd4_decode_setclientid(struct nfsd4_co
 	READ_BUF(8);
 	setclientid->se_callback_prog = be32_to_cpup(p++);
 	setclientid->se_callback_netid_len = be32_to_cpup(p++);
-
-	READ_BUF(setclientid->se_callback_netid_len + 4);
+	READ_BUF(setclientid->se_callback_netid_len);
 	SAVEMEM(setclientid->se_callback_netid_val, setclientid->se_callback_netid_len);
+	READ_BUF(4);
 	setclientid->se_callback_addr_len = be32_to_cpup(p++);
 
-	READ_BUF(setclientid->se_callback_addr_len + 4);
+	READ_BUF(setclientid->se_callback_addr_len);
 	SAVEMEM(setclientid->se_callback_addr_val, setclientid->se_callback_addr_len);
+	READ_BUF(4);
 	setclientid->se_callback_ident = be32_to_cpup(p++);
 
 	DECODE_TAIL;

@@ -1815,8 +1817,9 @@ nfsd4_decode_compound(struct nfsd4_compo
 
 	READ_BUF(4);
 	argp->taglen = be32_to_cpup(p++);
-	READ_BUF(argp->taglen + 8);
+	READ_BUF(argp->taglen);
 	SAVEMEM(argp->tag, argp->taglen);
+	READ_BUF(8);
 	argp->minorversion = be32_to_cpup(p++);
 	argp->opcnt = be32_to_cpup(p++);
 	max_reply += 4 + (XDR_QUADLEN(argp->taglen) << 2);

@@ -877,6 +877,7 @@ nfsd4_secinfo(struct svc_rqst *rqstp, st
 				    &exp, &dentry);
 	if (err)
 		return err;
+	fh_unlock(&cstate->current_fh);
 	if (d_really_is_negative(dentry)) {
 		exp_put(exp);
 		err = nfserr_noent;

@@ -714,6 +714,7 @@ static int acpi_hibernation_enter(void)
 
 static void acpi_hibernation_leave(void)
 {
+	pm_set_resume_via_firmware();
 	/*
 	 * If ACPI is not enabled by the BIOS and the boot kernel, we need to
 	 * enable it here.

@@ -281,13 +281,15 @@ locked_inode_to_wb_and_lock_list(struct
 		wb_get(wb);
 		spin_unlock(&inode->i_lock);
 		spin_lock(&wb->list_lock);
-		wb_put(wb);		/* not gonna deref it anymore */
 
 		/* i_wb may have changed inbetween, can't use inode_to_wb() */
-		if (likely(wb == inode->i_wb))
-			return wb;	/* @inode already has ref */
+		if (likely(wb == inode->i_wb)) {
+			wb_put(wb);	/* @inode already has ref */
+			return wb;
+		}
 
 		spin_unlock(&wb->list_lock);
+		wb_put(wb);
 		cpu_relax();
 		spin_lock(&inode->i_lock);
 	}

@@ -1341,10 +1341,10 @@ __writeback_single_inode(struct inode *i
  * we go e.g. from filesystem. Flusher thread uses __writeback_single_inode()
  * and does more profound writeback list handling in writeback_sb_inodes().
  */
-static int
-writeback_single_inode(struct inode *inode, struct bdi_writeback *wb,
-		       struct writeback_control *wbc)
+static int writeback_single_inode(struct inode *inode,
+				  struct writeback_control *wbc)
 {
+	struct bdi_writeback *wb;
 	int ret = 0;
 
 	spin_lock(&inode->i_lock);

@@ -1382,7 +1382,8 @@ writeback_single_inode(struct inode *ino
 	ret = __writeback_single_inode(inode, wbc);
 
 	wbc_detach_inode(wbc);
-	spin_lock(&wb->list_lock);
+
+	wb = inode_to_wb_and_lock_list(inode);
 	spin_lock(&inode->i_lock);
 	/*
 	 * If inode is clean, remove it from writeback lists. Otherwise don't

@@ -1457,6 +1458,7 @@ static long writeback_sb_inodes(struct s
 
 	while (!list_empty(&wb->b_io)) {
 		struct inode *inode = wb_inode(wb->b_io.prev);
+		struct bdi_writeback *tmp_wb;
 
 		if (inode->i_sb != sb) {
 			if (work->sb) {

@@ -1547,15 +1549,23 @@ static long writeback_sb_inodes(struct s
 			cond_resched();
 		}
 
-
-		spin_lock(&wb->list_lock);
+		/*
+		 * Requeue @inode if still dirty.  Be careful as @inode may
+		 * have been switched to another wb in the meantime.
+		 */
+		tmp_wb = inode_to_wb_and_lock_list(inode);
 		spin_lock(&inode->i_lock);
 		if (!(inode->i_state & I_DIRTY_ALL))
 			wrote++;
-		requeue_inode(inode, wb, &wbc);
+		requeue_inode(inode, tmp_wb, &wbc);
 		inode_sync_complete(inode);
 		spin_unlock(&inode->i_lock);
 
+		if (unlikely(tmp_wb != wb)) {
+			spin_unlock(&tmp_wb->list_lock);
+			spin_lock(&wb->list_lock);
+		}
+
 		/*
 		 * bail out to wb_writeback() often enough to check
 		 * background threshold and other termination conditions.

@@ -2342,7 +2352,6 @@ EXPORT_SYMBOL(sync_inodes_sb);
  */
 int write_inode_now(struct inode *inode, int sync)
 {
-	struct bdi_writeback *wb = &inode_to_bdi(inode)->wb;
 	struct writeback_control wbc = {
 		.nr_to_write = LONG_MAX,
 		.sync_mode = sync ? WB_SYNC_ALL : WB_SYNC_NONE,

@@ -2354,7 +2363,7 @@ int write_inode_now(struct inode *inode,
 		wbc.nr_to_write = 0;
 
 	might_sleep();
-	return writeback_single_inode(inode, wb, &wbc);
+	return writeback_single_inode(inode, &wbc);
 }
 EXPORT_SYMBOL(write_inode_now);
 

@@ -2371,7 +2380,7 @@ EXPORT_SYMBOL(write_inode_now);
  */
 int sync_inode(struct inode *inode, struct writeback_control *wbc)
 {
-	return writeback_single_inode(inode, &inode_to_bdi(inode)->wb, wbc);
+	return writeback_single_inode(inode, wbc);
 }
 EXPORT_SYMBOL(sync_inode);
 

@@ -862,8 +862,9 @@ static void synaptics_report_ext_buttons
 	if (!SYN_CAP_MULTI_BUTTON_NO(priv->ext_cap))
 		return;
 
-	/* Bug in FW 8.1, buttons are reported only when ExtBit is 1 */
-	if (SYN_ID_FULL(priv->identity) == 0x801 &&
+	/* Bug in FW 8.1 & 8.2, buttons are reported only when ExtBit is 1 */
+	if ((SYN_ID_FULL(priv->identity) == 0x801 ||
+	     SYN_ID_FULL(priv->identity) == 0x802) &&
 	    !((psmouse->packet[0] ^ psmouse->packet[3]) & 0x02))
 		return;
 

@@ -1663,6 +1663,8 @@ static int ims_pcu_parse_cdc_data(struct
 
 	pcu->ctrl_intf = usb_ifnum_to_if(pcu->udev,
 					 union_desc->bMasterInterface0);
+	if (!pcu->ctrl_intf)
+		return -EINVAL;
 
 	alt = pcu->ctrl_intf->cur_altsetting;
 	pcu->ep_ctrl = &alt->endpoint[0].desc;

@@ -1670,6 +1672,8 @@ static int ims_pcu_parse_cdc_data(struct
 
 	pcu->data_intf = usb_ifnum_to_if(pcu->udev,
 					 union_desc->bSlaveInterface0);
+	if (!pcu->data_intf)
+		return -EINVAL;
 
 	alt = pcu->data_intf->cur_altsetting;
 	if (alt->desc.bNumEndpoints != 2) {

@@ -817,26 +817,49 @@ static int ati_remote2_probe(struct usb_
 
 	ar2->udev = udev;
 
+	/* Sanity check, first interface must have an endpoint */
+	if (alt->desc.bNumEndpoints < 1 || !alt->endpoint) {
+		dev_err(&interface->dev,
+			"%s(): interface 0 must have an endpoint\n", __func__);
+		r = -ENODEV;
+		goto fail1;
+	}
 	ar2->intf[0] = interface;
 	ar2->ep[0] = &alt->endpoint[0].desc;
 
+	/* Sanity check, the device must have two interfaces */
 	ar2->intf[1] = usb_ifnum_to_if(udev, 1);
+	if ((udev->actconfig->desc.bNumInterfaces < 2) || !ar2->intf[1]) {
+		dev_err(&interface->dev, "%s(): need 2 interfaces, found %d\n",
+			__func__, udev->actconfig->desc.bNumInterfaces);
+		r = -ENODEV;
+		goto fail1;
+	}
+
 	r = usb_driver_claim_interface(&ati_remote2_driver, ar2->intf[1], ar2);
 	if (r)
 		goto fail1;
+
+	/* Sanity check, second interface must have an endpoint */
 	alt = ar2->intf[1]->cur_altsetting;
+	if (alt->desc.bNumEndpoints < 1 || !alt->endpoint) {
+		dev_err(&interface->dev,
+			"%s(): interface 1 must have an endpoint\n", __func__);
+		r = -ENODEV;
+		goto fail2;
+	}
 	ar2->ep[1] = &alt->endpoint[0].desc;
 
 	r = ati_remote2_urb_init(ar2);
 	if (r)
-		goto fail2;
+		goto fail3;
 
 	ar2->channel_mask = channel_mask;
 	ar2->mode_mask = mode_mask;
 
 	r = ati_remote2_setup(ar2, ar2->channel_mask);
 	if (r)
-		goto fail2;
+		goto fail3;
 
 	usb_make_path(udev, ar2->phys, sizeof(ar2->phys));
 	strlcat(ar2->phys, "/input0", sizeof(ar2->phys));

@@ -845,11 +868,11 @@ static int ati_remote2_probe(struct usb_
 
 	r = sysfs_create_group(&udev->dev.kobj, &ati_remote2_attr_group);
 	if (r)
-		goto fail2;
+		goto fail3;
 
 	r = ati_remote2_input_init(ar2);
 	if (r)
-		goto fail3;
+		goto fail4;
 
 	usb_set_intfdata(interface, ar2);
 

@@ -857,10 +880,11 @@ static int ati_remote2_probe(struct usb_
 
 	return 0;
 
- fail3:
+ fail4:
 	sysfs_remove_group(&udev->dev.kobj, &ati_remote2_attr_group);
- fail2:
+ fail3:
 	ati_remote2_urb_cleanup(ar2);
+ fail2:
 	usb_driver_release_interface(&ati_remote2_driver, ar2->intf[1]);
  fail1:
 	kfree(ar2);

@@ -262,6 +262,7 @@ enum dlm_status dlmconvert_remote(struct
 				  struct dlm_lock *lock, int flags, int type)
 {
 	enum dlm_status status;
+	u8 old_owner = res->owner;
 
 	mlog(0, "type=%d, convert_type=%d, busy=%d\n", lock->ml.type,
 	     lock->ml.convert_type, res->state & DLM_LOCK_RES_IN_PROGRESS);

@@ -316,11 +317,19 @@ enum dlm_status dlmconvert_remote(struct
 	spin_lock(&res->spinlock);
 	res->state &= ~DLM_LOCK_RES_IN_PROGRESS;
 	lock->convert_pending = 0;
-	/* if it failed, move it back to granted queue */
+	/* if it failed, move it back to granted queue.
+	 * if master returns DLM_NORMAL and then down before sending ast,
+	 * it may have already been moved to granted queue, reset to
+	 * DLM_RECOVERING and retry convert */
 	if (status != DLM_NORMAL) {
 		if (status != DLM_NOTQUEUED)
 			dlm_error(status);
 		dlm_revert_pending_convert(res, lock);
+	} else if ((res->state & DLM_LOCK_RES_RECOVERING) ||
+			(old_owner != res->owner)) {
+		mlog(0, "res %.*s is in recovering or has been recovered.\n",
+				res->lockname.len, res->lockname.name);
+		status = DLM_RECOVERING;
 	}
 bail:
 	spin_unlock(&res->spinlock);

@@ -288,6 +288,19 @@ enum dlm_status dlmconvert_remote(struct
 		status = DLM_DENIED;
 		goto bail;
 	}
+
+	if (lock->ml.type == type && lock->ml.convert_type == LKM_IVMODE) {
+		mlog(0, "last convert request returned DLM_RECOVERING, but "
+		     "owner has already queued and sent ast to me. res %.*s, "
+		     "(cookie=%u:%llu, type=%d, conv=%d)\n",
+		     res->lockname.len, res->lockname.name,
+		     dlm_get_lock_cookie_node(be64_to_cpu(lock->ml.cookie)),
+		     dlm_get_lock_cookie_seq(be64_to_cpu(lock->ml.cookie)),
+		     lock->ml.type, lock->ml.convert_type);
+		status = DLM_NORMAL;
+		goto bail;
+	}
+
 	res->state |= DLM_LOCK_RES_IN_PROGRESS;
 	/* move lock to local convert queue */
 	/* do not alter lock refcount.  switching lists. */

@@ -2064,7 +2064,6 @@ void dlm_move_lockres_to_recovery_list(s
 			dlm_lock_get(lock);
 			if (lock->convert_pending) {
 				/* move converting lock back to granted */
-				BUG_ON(i != DLM_CONVERTING_LIST);
 				mlog(0, "node died with convert pending "
 				     "on %.*s. move back to granted list.\n",
 				     res->lockname.len, res->lockname.name);

@@ -662,34 +662,28 @@ static inline void __free_one_page(struc
 	unsigned long combined_idx;
 	unsigned long uninitialized_var(buddy_idx);
 	struct page *buddy;
-	unsigned int max_order = MAX_ORDER;
+	unsigned int max_order;
+
+	max_order = min_t(unsigned int, MAX_ORDER, pageblock_order + 1);
 
 	VM_BUG_ON(!zone_is_initialized(zone));
 	VM_BUG_ON_PAGE(page->flags & PAGE_FLAGS_CHECK_AT_PREP, page);
 
 	VM_BUG_ON(migratetype == -1);
-	if (is_migrate_isolate(migratetype)) {
-		/*
-		 * We restrict max order of merging to prevent merge
-		 * between freepages on isolate pageblock and normal
-		 * pageblock. Without this, pageblock isolation
-		 * could cause incorrect freepage accounting.
-		 */
-		max_order = min_t(unsigned int, MAX_ORDER, pageblock_order + 1);
-	} else {
+	if (likely(!is_migrate_isolate(migratetype)))
 		__mod_zone_freepage_state(zone, 1 << order, migratetype);
-	}
 
-	page_idx = pfn & ((1 << max_order) - 1);
+	page_idx = pfn & ((1 << MAX_ORDER) - 1);
 
 	VM_BUG_ON_PAGE(page_idx & ((1 << order) - 1), page);
 	VM_BUG_ON_PAGE(bad_range(zone, page), page);
 
+continue_merging:
 	while (order < max_order - 1) {
 		buddy_idx = __find_buddy_index(page_idx, order);
 		buddy = page + (buddy_idx - page_idx);
 		if (!page_is_buddy(page, buddy, order))
-			break;
+			goto done_merging;
 		/*
 		 * Our buddy is free or it is CONFIG_DEBUG_PAGEALLOC guard page,
 		 * merge with it and move up one order.

@@ -706,6 +700,32 @@ static inline void __free_one_page(struc
 		page_idx = combined_idx;
 		order++;
 	}
+	if (max_order < MAX_ORDER) {
+		/* If we are here, it means order is >= pageblock_order.
+		 * We want to prevent merge between freepages on isolate
+		 * pageblock and normal pageblock. Without this, pageblock
+		 * isolation could cause incorrect freepage or CMA accounting.
+		 *
+		 * We don't want to hit this code for the more frequent
+		 * low-order merging.
+		 */
+		if (unlikely(has_isolate_pageblock(zone))) {
+			int buddy_mt;
+
+			buddy_idx = __find_buddy_index(page_idx, order);
+			buddy = page + (buddy_idx - page_idx);
+			buddy_mt = get_pageblock_migratetype(buddy);
+
+			if (migratetype != buddy_mt
+					&& (is_migrate_isolate(migratetype) ||
+						is_migrate_isolate(buddy_mt)))
+				goto done_merging;
+		}
+		max_order++;
+		goto continue_merging;
+	}
+
+done_merging:
 	set_page_order(page, order);
 
 	/*

@@ -593,6 +593,19 @@ void x86_pmu_disable_all(void)
 	}
 }
 
+/*
+ * There may be PMI landing after enabled=0. The PMI hitting could be before or
+ * after disable_all.
+ *
+ * If PMI hits before disable_all, the PMU will be disabled in the NMI handler.
+ * It will not be re-enabled in the NMI handler again, because enabled=0. After
+ * handling the NMI, disable_all will be called, which will not change the
+ * state either. If PMI hits after disable_all, the PMU is already disabled
+ * before entering NMI handler. The NMI handler will not change the state
+ * either.
+ *
+ * So either situation is harmless.
+ */
 static void x86_pmu_disable(struct pmu *pmu)
 {
 	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);

@@ -1458,7 +1458,15 @@ static __initconst const u64 slm_hw_cach
 };
 
 /*
- * Use from PMIs where the LBRs are already disabled.
+ * Used from PMIs where the LBRs are already disabled.
+ *
+ * This function could be called consecutively. It is required to remain in
+ * disabled state if called consecutively.
+ *
+ * During consecutive calls, the same disable value will be written to related
+ * registers, so the PMU state remains unchanged. hw.state in
+ * intel_bts_disable_local will remain PERF_HES_STOPPED too in consecutive
+ * calls.
  */
 static void __intel_pmu_disable_all(void)
 {

@@ -1895,7 +1903,10 @@ again:
 		goto again;
 
 done:
-	__intel_pmu_enable_all(0, true);
+	/* Only restore PMU state when it's active. See x86_pmu_disable(). */
+	if (cpuc->enabled)
+		__intel_pmu_enable_all(0, true);
+
 	/*
 	 * Only unmask the NMI after the overflow counters
 	 * have been reset. This avoids spurious NMIs on

@@ -263,7 +263,9 @@ again:
 		goto again;
 
 done:
-	knc_pmu_enable_all(0);
+	/* Only restore PMU state when it's active. See x86_pmu_disable(). */
+	if (cpuc->enabled)
+		knc_pmu_enable_all(0);
 
 	return handled;
 }

@@ -2599,6 +2599,7 @@ static int onenand_default_block_markbad
  */
 static int onenand_block_markbad(struct mtd_info *mtd, loff_t ofs)
 {
+	struct onenand_chip *this = mtd->priv;
 	int ret;
 
 	ret = onenand_block_isbad(mtd, ofs);

@@ -2610,7 +2611,7 @@ static int onenand_block_markbad(struct
 	}
 
 	onenand_get_device(mtd, FL_WRITING);
-	ret = mtd_block_markbad(mtd, ofs);
+	ret = this->block_markbad(mtd, ofs);
 	onenand_release_device(mtd);
 	return ret;
 }

@@ -65,7 +65,7 @@
 #include <asm/mwait.h>
 #include <asm/msr.h>
 
-#define INTEL_IDLE_VERSION "0.4"
+#define INTEL_IDLE_VERSION "0.4.1"
 #define PREFIX "intel_idle: "
 
 static struct cpuidle_driver intel_idle_driver = {

@@ -994,36 +994,92 @@ static void intel_idle_cpuidle_devices_u
 }
 
 /*
- * intel_idle_state_table_update()
- *
- * Update the default state_table for this CPU-id
+ * ivt_idle_state_table_update(void)
  *
- * Currently used to access tuned IVT multi-socket targets
+ * Tune IVT multi-socket targets
  * Assumption: num_sockets == (max_package_num + 1)
  */
-void intel_idle_state_table_update(void)
+static void ivt_idle_state_table_update(void)
 {
 	/* IVT uses a different table for 1-2, 3-4, and > 4 sockets */
-	if (boot_cpu_data.x86_model == 0x3e) { /* IVT */
-		int cpu, package_num, num_sockets = 1;
+	int cpu, package_num, num_sockets = 1;
 
-		for_each_online_cpu(cpu) {
-			package_num = topology_physical_package_id(cpu);
-			if (package_num + 1 > num_sockets) {
-				num_sockets = package_num + 1;
-
-				if (num_sockets > 4) {
-					cpuidle_state_table = ivt_cstates_8s;
-					return;
-				}
+	for_each_online_cpu(cpu) {
+		package_num = topology_physical_package_id(cpu);
+		if (package_num + 1 > num_sockets) {
+			num_sockets = package_num + 1;
+
+			if (num_sockets > 4) {
+				cpuidle_state_table = ivt_cstates_8s;
+				return;
 			}
 		}
+	}
+
+	if (num_sockets > 2)
+		cpuidle_state_table = ivt_cstates_4s;
+
+	/* else, 1 and 2 socket systems use default ivt_cstates */
+}
+/*
+ * sklh_idle_state_table_update(void)
+ *
+ * On SKL-H (model 0x5e) disable C8 and C9 if:
+ * C10 is enabled and SGX disabled
+ */
+static void sklh_idle_state_table_update(void)
+{
+	unsigned long long msr;
+	unsigned int eax, ebx, ecx, edx;
+
+
+	/* if PC10 disabled via cmdline intel_idle.max_cstate=7 or shallower */
+	if (max_cstate <= 7)
+		return;
+
+	/* if PC10 not present in CPUID.MWAIT.EDX */
+	if ((mwait_substates & (0xF << 28)) == 0)
+		return;
+
+	rdmsrl(MSR_NHM_SNB_PKG_CST_CFG_CTL, msr);
+
+	/* PC10 is not enabled in PKG C-state limit */
+	if ((msr & 0xF) != 8)
+		return;
+
+	ecx = 0;
+	cpuid(7, &eax, &ebx, &ecx, &edx);
+
+	/* if SGX is present */
+	if (ebx & (1 << 2)) {
+
+		rdmsrl(MSR_IA32_FEATURE_CONTROL, msr);
 
-		if (num_sockets > 2)
-			cpuidle_state_table = ivt_cstates_4s;
-		/* else, 1 and 2 socket systems use default ivt_cstates */
+		/* if SGX is enabled */
+		if (msr & (1 << 18))
+			return;
+	}
+
+	skl_cstates[5].disabled = 1;	/* C8-SKL */
+	skl_cstates[6].disabled = 1;	/* C9-SKL */
+}
+/*
+ * intel_idle_state_table_update()
+ *
+ * Update the default state_table for this CPU-id
+ */
+
+static void intel_idle_state_table_update(void)
+{
+	switch (boot_cpu_data.x86_model) {
+
+	case 0x3e: /* IVT */
+		ivt_idle_state_table_update();
+		break;
+	case 0x5e: /* SKL-H */
+		sklh_idle_state_table_update();
+		break;
 	}
-	return;
 }
 
 /*

@@ -1063,6 +1119,14 @@ static int __init intel_idle_cpuidle_dri
 		if (num_substates == 0)
 			continue;
 
+		/* if state marked as disabled, skip it */
+		if (cpuidle_state_table[cstate].disabled != 0) {
+			pr_debug(PREFIX "state %s is disabled",
+				cpuidle_state_table[cstate].name);
+			continue;
+		}
+
+
 		if (((mwait_cstate + 1) > 2) &&
 			!boot_cpu_has(X86_FEATURE_NONSTOP_TSC))
 			mark_tsc_unstable("TSC halts in idle"

@@ -339,6 +339,7 @@ int hibernation_snapshot(int platform_mo
 	pm_message_t msg;
 	int error;
 
+	pm_suspend_clear_flags();
 	error = platform_begin(platform_mode);
 	if (error)
 		goto Close;

@@ -278,8 +278,16 @@ int scsi_set_sense_information(u8 *buf,
 		ucp[3] = 0;
 		put_unaligned_be64(info, &ucp[4]);
 	} else if ((buf[0] & 0x7f) == 0x70) {
-		buf[0] |= 0x80;
-		put_unaligned_be64(info, &buf[3]);
+		/*
+		 * Only set the 'VALID' bit if we can represent the value
+		 * correctly; otherwise just fill out the lower bytes and
+		 * clear the 'VALID' flag.
+		 */
+		if (info <= 0xffffffffUL)
+			buf[0] |= 0x80;
+		else
+			buf[0] &= 0x7f;
+		put_unaligned_be32((u32)info, &buf[3]);
 	}
 
 	return 0;

@@ -5525,6 +5525,7 @@ migration_call(struct notifier_block *nf
 
 	case CPU_UP_PREPARE:
 		rq->calc_load_update = calc_load_update;
+		account_reset_rq(rq);
 		break;
 
 	case CPU_ONLINE:

@@ -1770,3 +1770,16 @@ static inline u64 irq_time_read(int cpu)
 }
 #endif /* CONFIG_64BIT */
 #endif /* CONFIG_IRQ_TIME_ACCOUNTING */
+
+static inline void account_reset_rq(struct rq *rq)
+{
+#ifdef CONFIG_IRQ_TIME_ACCOUNTING
+	rq->prev_irq_time = 0;
+#endif
+#ifdef CONFIG_PARAVIRT
+	rq->prev_steal_time = 0;
+#endif
+#ifdef CONFIG_PARAVIRT_TIME_ACCOUNTING
+	rq->prev_steal_time_rq = 0;
+#endif
+}

@@ -1840,6 +1840,16 @@ again:
 	if (__test_and_clear_bit(62, (unsigned long *)&status)) {
 		handled++;
 		x86_pmu.drain_pebs(regs);
+		/*
+		 * There are cases where, even though, the PEBS ovfl bit is set
+		 * in GLOBAL_OVF_STATUS, the PEBS events may also have their
+		 * overflow bits set for their counters. We must clear them
+		 * here because they have been processed as exact samples in
+		 * the drain_pebs() routine. They must not be processed again
+		 * in the for_each_bit_set() loop for regular samples below.
+		 */
+		status &= ~cpuc->pebs_enabled;
+		status &= x86_pmu.intel_ctrl | GLOBAL_STATUS_TRACE_TOPAPMI;
 	}
 
 	/*

@@ -591,6 +591,7 @@ struct x86_pmu {
 			pebs_active	:1,
 			pebs_broken	:1;
 	int		pebs_record_size;
+	int		pebs_buffer_size;
 	void		(*drain_pebs)(struct pt_regs *regs);
 	struct event_constraint *pebs_constraints;
 	void		(*pebs_aliases)(struct perf_event *event);

@@ -269,7 +269,7 @@ static int alloc_pebs_buffer(int cpu)
 	if (!x86_pmu.pebs)
 		return 0;
 
-	buffer = kzalloc_node(PEBS_BUFFER_SIZE, GFP_KERNEL, node);
+	buffer = kzalloc_node(x86_pmu.pebs_buffer_size, GFP_KERNEL, node);
 	if (unlikely(!buffer))
 		return -ENOMEM;
 

@@ -286,7 +286,7 @@ static int alloc_pebs_buffer(int cpu)
 		per_cpu(insn_buffer, cpu) = ibuffer;
 	}
 
-	max = PEBS_BUFFER_SIZE / x86_pmu.pebs_record_size;
+	max = x86_pmu.pebs_buffer_size / x86_pmu.pebs_record_size;
 
 	ds->pebs_buffer_base = (u64)(unsigned long)buffer;
 	ds->pebs_index = ds->pebs_buffer_base;

@@ -1296,6 +1296,7 @@ void __init intel_ds_init(void)
 
 	x86_pmu.bts  = boot_cpu_has(X86_FEATURE_BTS);
 	x86_pmu.pebs = boot_cpu_has(X86_FEATURE_PEBS);
+	x86_pmu.pebs_buffer_size = PEBS_BUFFER_SIZE;
 	if (x86_pmu.pebs) {
 		char pebs_type = x86_pmu.intel_cap.pebs_trap ?  '+' : '-';
 		int format = x86_pmu.intel_cap.pebs_format;

@@ -1304,6 +1305,14 @@ void __init intel_ds_init(void)
 		case 0:
 			printk(KERN_CONT "PEBS fmt0%c, ", pebs_type);
 			x86_pmu.pebs_record_size = sizeof(struct pebs_record_core);
+			/*
+			 * Using >PAGE_SIZE buffers makes the WRMSR to
+			 * PERF_GLOBAL_CTRL in intel_pmu_enable_all()
+			 * mysteriously hang on Core2.
+			 *
+			 * As a workaround, we don't do this.
+			 */
+			x86_pmu.pebs_buffer_size = PAGE_SIZE;
 			x86_pmu.drain_pebs = intel_pmu_drain_pebs_core;
 			break;
 

@@ -908,6 +908,8 @@ void intel_pmu_lbr_init_hsw(void);
 
 void intel_pmu_lbr_init_skl(void);
 
+void intel_pmu_pebs_data_source_nhm(void);
+
 int intel_pmu_setup_lbr_filter(struct perf_event *event);
 
 void intel_pt_interrupt(void);

@@ -3336,6 +3336,7 @@ __init int intel_pmu_init(void)
 		intel_perfmon_event_map[PERF_COUNT_HW_STALLED_CYCLES_BACKEND] =
 			X86_CONFIG(.event=0xb1, .umask=0x3f, .inv=1, .cmask=1);
 
+		intel_pmu_pebs_data_source_nhm();
 		x86_add_quirk(intel_nehalem_quirk);
 
 		pr_cont("Nehalem events, ");

@@ -3398,6 +3399,7 @@ __init int intel_pmu_init(void)
 		intel_perfmon_event_map[PERF_COUNT_HW_STALLED_CYCLES_BACKEND] =
 			X86_CONFIG(.event=0xb1, .umask=0x3f, .inv=1, .cmask=1);
 
+		intel_pmu_pebs_data_source_nhm();
 		pr_cont("Westmere events, ");
 		break;
 

@@ -51,7 +51,8 @@ union intel_x86_pebs_dse {
 #define OP_LH (P(OP, LOAD) | P(LVL, HIT))
 #define SNOOP_NONE_MISS (P(SNOOP, NONE) | P(SNOOP, MISS))
 
-static const u64 pebs_data_source[] = {
+/* Version for Sandy Bridge and later */
+static u64 pebs_data_source[] = {
 	P(OP, LOAD) | P(LVL, MISS) | P(LVL, L3) | P(SNOOP, NA),/* 0x00:ukn L3 */
 	OP_LH | P(LVL, L1)  | P(SNOOP, NONE),	/* 0x01: L1 local */
 	OP_LH | P(LVL, LFB) | P(SNOOP, NONE),	/* 0x02: LFB hit */

@@ -70,6 +71,14 @@ static const u64 pebs_data_source[] = {
 	OP_LH | P(LVL, UNC) | P(SNOOP, NONE), /* 0x0f: uncached */
 };
 
+/* Patch up minor differences in the bits */
+void __init intel_pmu_pebs_data_source_nhm(void)
+{
+	pebs_data_source[0x05] = OP_LH | P(LVL, L3)  | P(SNOOP, HIT);
+	pebs_data_source[0x06] = OP_LH | P(LVL, L3)  | P(SNOOP, HITM);
+	pebs_data_source[0x07] = OP_LH | P(LVL, L3)  | P(SNOOP, HITM);
+}
+
 static u64 precise_store_data(u64 status)
 {
 	union intel_x86_pebs_dse dse;