Linux 4.12.2

commit 99c13b8c88 upstream.

The pat_enabled() logic is broken on CPUs which do not support PAT and
where the initialization code fails to call pat_init(). Due to that the
enabled flag stays true and pat_enabled() returns true wrongfully.

As a consequence the mappings, e.g. for Xorg, are set up with the wrong
caching mode and the required MTRR setups are omitted.

To cure this the following changes are required:

  1) Make pat_enabled() return true only if PAT initialization was
     invoked and successful.

  2) Invoke init_cache_modes() unconditionally in setup_arch() and
     remove the extra callsites in pat_disable() and the pat disabled
     code path in pat_init().

Also rename __pat_enabled to pat_disabled to reflect the real purpose of
this variable.

Fixes: 9cd25aac1f ("x86/mm/pat: Emulate PAT when it is disabled")
Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Bernhard Held <berny156@gmx.de>
Cc: Denys Vlasenko <dvlasenk@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Brian Gerst <brgerst@gmail.com>
Cc: "Luis R. Rodriguez" <mcgrof@suse.com>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Josh Poimboeuf <jpoimboe@redhat.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: http://lkml.kernel.org/r/alpine.LRH.2.02.1707041749300.3456@file01.intranet.prod.int.rdu2.redhat.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

Makefile

@@ -1,6 +1,6 @@
 VERSION = 4
 PATCHLEVEL = 12
-SUBLEVEL = 0
+SUBLEVEL = 2
 EXTRAVERSION =
 NAME = Fearless Coyote
 

arch/powerpc/platforms/powernv/idle.c

@@ -261,6 +261,7 @@ static u64 pnv_deepest_stop_psscr_val;
 static u64 pnv_deepest_stop_psscr_mask;
 static bool deepest_stop_found;
 
+#ifdef CONFIG_HOTPLUG_CPU
 /*
  * pnv_cpu_offline: A function that puts the CPU into the deepest
  * available platform idle state on a CPU-Offline.
@@ -293,6 +294,7 @@ unsigned long pnv_cpu_offline(unsigned int cpu)
 
 	return srr1;
 }
+#endif
 
 /*
  * Power ISA 3.0 idle initialization.

arch/x86/include/asm/pat.h

@@ -7,6 +7,7 @@
 bool pat_enabled(void);
 void pat_disable(const char *reason);
 extern void pat_init(void);
+extern void init_cache_modes(void);
 
 extern int reserve_memtype(u64 start, u64 end,
 		enum page_cache_mode req_pcm, enum page_cache_mode *ret_pcm);

arch/x86/kernel/setup.c

@@ -1075,6 +1075,13 @@ void __init setup_arch(char **cmdline_p)
 
 	max_possible_pfn = max_pfn;
 
+	/*
+	 * This call is required when the CPU does not support PAT. If
+	 * mtrr_bp_init() invoked it already via pat_init() the call has no
+	 * effect.
+	 */
+	init_cache_modes();
+
 	/*
 	 * Define random base addresses for memory sections after max_pfn is
 	 * defined and before each memory section base is used.

arch/x86/lib/copy_user_64.S

@@ -37,7 +37,7 @@ ENTRY(copy_user_generic_unrolled)
 	movl %edx,%ecx
 	andl $63,%edx
 	shrl $6,%ecx
-	jz 17f
+	jz .L_copy_short_string
 1:	movq (%rsi),%r8
 2:	movq 1*8(%rsi),%r9
 3:	movq 2*8(%rsi),%r10
@@ -58,7 +58,8 @@ ENTRY(copy_user_generic_unrolled)
 	leaq 64(%rdi),%rdi
 	decl %ecx
 	jnz 1b
-17:	movl %edx,%ecx
+.L_copy_short_string:
+	movl %edx,%ecx
 	andl $7,%edx
 	shrl $3,%ecx
 	jz 20f
@@ -174,6 +175,8 @@ EXPORT_SYMBOL(copy_user_generic_string)
  */
 ENTRY(copy_user_enhanced_fast_string)
 	ASM_STAC
+	cmpl $64,%edx
+	jb .L_copy_short_string	/* less then 64 bytes, avoid the costly 'rep' */
 	movl %edx,%ecx
 1:	rep
 	movsb

arch/x86/mm/pat.c

@@ -37,14 +37,14 @@
 #undef pr_fmt
 #define pr_fmt(fmt) "" fmt
 
-static bool boot_cpu_done;
-
-static int __read_mostly __pat_enabled = IS_ENABLED(CONFIG_X86_PAT);
-static void init_cache_modes(void);
+static bool __read_mostly boot_cpu_done;
+static bool __read_mostly pat_disabled = !IS_ENABLED(CONFIG_X86_PAT);
+static bool __read_mostly pat_initialized;
+static bool __read_mostly init_cm_done;
 
 void pat_disable(const char *reason)
 {
-	if (!__pat_enabled)
+	if (pat_disabled)
 		return;
 
 	if (boot_cpu_done) {
@@ -52,10 +52,8 @@ void pat_disable(const char *reason)
 		return;
 	}
 
-	__pat_enabled = 0;
+	pat_disabled = true;
 	pr_info("x86/PAT: %s\n", reason);
-
-	init_cache_modes();
 }
 
 static int __init nopat(char *str)
@@ -67,7 +65,7 @@ early_param("nopat", nopat);
 
 bool pat_enabled(void)
 {
-	return !!__pat_enabled;
+	return pat_initialized;
 }
 EXPORT_SYMBOL_GPL(pat_enabled);
 
@@ -205,6 +203,8 @@ static void __init_cache_modes(u64 pat)
 		update_cache_mode_entry(i, cache);
 	}
 	pr_info("x86/PAT: Configuration [0-7]: %s\n", pat_msg);
+
+	init_cm_done = true;
 }
 
 #define PAT(x, y)	((u64)PAT_ ## y << ((x)*8))
@@ -225,6 +225,7 @@ static void pat_bsp_init(u64 pat)
 	}
 
 	wrmsrl(MSR_IA32_CR_PAT, pat);
+	pat_initialized = true;
 
 	__init_cache_modes(pat);
 }
@@ -242,10 +243,9 @@ static void pat_ap_init(u64 pat)
 	wrmsrl(MSR_IA32_CR_PAT, pat);
 }
 
-static void init_cache_modes(void)
+void init_cache_modes(void)
 {
 	u64 pat = 0;
-	static int init_cm_done;
 
 	if (init_cm_done)
 		return;
@@ -287,8 +287,6 @@ static void init_cache_modes(void)
 	}
 
 	__init_cache_modes(pat);
-
-	init_cm_done = 1;
 }
 
 /**
@@ -306,10 +304,8 @@ void pat_init(void)
 	u64 pat;
 	struct cpuinfo_x86 *c = &boot_cpu_data;
 
-	if (!pat_enabled()) {
-		init_cache_modes();
+	if (pat_disabled)
 		return;
-	}
 
 	if ((c->x86_vendor == X86_VENDOR_INTEL) &&
 	    (((c->x86 == 0x6) && (c->x86_model <= 0xd)) ||

crypto/drbg.c

@@ -1691,6 +1691,7 @@ static int drbg_init_sym_kernel(struct drbg_state *drbg)
 		return PTR_ERR(sk_tfm);
 	}
 	drbg->ctr_handle = sk_tfm;
+	init_completion(&drbg->ctr_completion);
 
 	req = skcipher_request_alloc(sk_tfm, GFP_KERNEL);
 	if (!req) {

crypto/rsa-pkcs1pad.c

@@ -496,7 +496,7 @@ static int pkcs1pad_verify_complete(struct akcipher_request *req, int err)
 		goto done;
 	pos++;
 
-	if (memcmp(out_buf + pos, digest_info->data, digest_info->size))
+	if (crypto_memneq(out_buf + pos, digest_info->data, digest_info->size))
 		goto done;
 
 	pos += digest_info->size;

drivers/base/core.c

@@ -2667,7 +2667,11 @@ void device_shutdown(void)
 		pm_runtime_get_noresume(dev);
 		pm_runtime_barrier(dev);
 
-		if (dev->bus && dev->bus->shutdown) {
+		if (dev->class && dev->class->shutdown) {
+			if (initcall_debug)
+				dev_info(dev, "shutdown\n");
+			dev->class->shutdown(dev);
+		} else if (dev->bus && dev->bus->shutdown) {
 			if (initcall_debug)
 				dev_info(dev, "shutdown\n");
 			dev->bus->shutdown(dev);

drivers/base/platform.c

@@ -866,7 +866,7 @@ static ssize_t driver_override_store(struct device *dev,
 				     const char *buf, size_t count)
 {
 	struct platform_device *pdev = to_platform_device(dev);
-	char *driver_override, *old = pdev->driver_override, *cp;
+	char *driver_override, *old, *cp;
 
 	if (count > PATH_MAX)
 		return -EINVAL;
@@ -879,12 +879,15 @@ static ssize_t driver_override_store(struct device *dev,
 	if (cp)
 		*cp = '\0';
 
+	device_lock(dev);
+	old = pdev->driver_override;
 	if (strlen(driver_override)) {
 		pdev->driver_override = driver_override;
 	} else {
 		kfree(driver_override);
 		pdev->driver_override = NULL;
 	}
+	device_unlock(dev);
 
 	kfree(old);
 
@@ -895,8 +898,12 @@ static ssize_t driver_override_show(struct device *dev,
 				    struct device_attribute *attr, char *buf)
 {
 	struct platform_device *pdev = to_platform_device(dev);
+	ssize_t len;
 
-	return sprintf(buf, "%s\n", pdev->driver_override);
+	device_lock(dev);
+	len = sprintf(buf, "%s\n", pdev->driver_override);
+	device_unlock(dev);
+	return len;
 }
 static DEVICE_ATTR_RW(driver_override);
 

drivers/char/tpm/tpm-chip.c

@@ -142,6 +142,39 @@ static void tpm_devs_release(struct device *dev)
 	put_device(&chip->dev);
 }
 
+/**
+ * tpm_class_shutdown() - prepare the TPM device for loss of power.
+ * @dev: device to which the chip is associated.
+ *
+ * Issues a TPM2_Shutdown command prior to loss of power, as required by the
+ * TPM 2.0 spec.
+ * Then, calls bus- and device- specific shutdown code.
+ *
+ * XXX: This codepath relies on the fact that sysfs is not enabled for
+ * TPM2: sysfs uses an implicit lock on chip->ops, so this could race if TPM2
+ * has sysfs support enabled before TPM sysfs's implicit locking is fixed.
+ */
+static int tpm_class_shutdown(struct device *dev)
+{
+	struct tpm_chip *chip = container_of(dev, struct tpm_chip, dev);
+
+	if (chip->flags & TPM_CHIP_FLAG_TPM2) {
+		down_write(&chip->ops_sem);
+		tpm2_shutdown(chip, TPM2_SU_CLEAR);
+		chip->ops = NULL;
+		up_write(&chip->ops_sem);
+	}
+	/* Allow bus- and device-specific code to run. Note: since chip->ops
+	 * is NULL, more-specific shutdown code will not be able to issue TPM
+	 * commands.
+	 */
+	if (dev->bus && dev->bus->shutdown)
+		dev->bus->shutdown(dev);
+	else if (dev->driver && dev->driver->shutdown)
+		dev->driver->shutdown(dev);
+	return 0;
+}
+
 /**
  * tpm_chip_alloc() - allocate a new struct tpm_chip instance
  * @pdev: device to which the chip is associated
@@ -181,6 +214,7 @@ struct tpm_chip *tpm_chip_alloc(struct device *pdev,
 	device_initialize(&chip->devs);
 
 	chip->dev.class = tpm_class;
+	chip->dev.class->shutdown = tpm_class_shutdown;
 	chip->dev.release = tpm_dev_release;
 	chip->dev.parent = pdev;
 	chip->dev.groups = chip->groups;

drivers/char/tpm/tpm-sysfs.c

@@ -36,9 +36,10 @@ static ssize_t pubek_show(struct device *dev, struct device_attribute *attr,
 	ssize_t err;
 	int i, rc;
 	char *str = buf;
-
 	struct tpm_chip *chip = to_tpm_chip(dev);
 
+	memset(&tpm_cmd, 0, sizeof(tpm_cmd));
+
 	tpm_cmd.header.in = tpm_readpubek_header;
 	err = tpm_transmit_cmd(chip, NULL, &tpm_cmd, READ_PUBEK_RESULT_SIZE,
 			       READ_PUBEK_RESULT_MIN_BODY_SIZE, 0,
@@ -294,6 +295,9 @@ static const struct attribute_group tpm_dev_group = {
 
 void tpm_sysfs_add_device(struct tpm_chip *chip)
 {
+	/* XXX: If you wish to remove this restriction, you must first update
+	 * tpm_sysfs to explicitly lock chip->ops.
+	 */
 	if (chip->flags & TPM_CHIP_FLAG_TPM2)
 		return;
 

drivers/crypto/caam/caamalg.c

@@ -1475,8 +1475,7 @@ static struct ablkcipher_edesc *ablkcipher_edesc_alloc(struct ablkcipher_request
 	struct crypto_ablkcipher *ablkcipher = crypto_ablkcipher_reqtfm(req);
 	struct caam_ctx *ctx = crypto_ablkcipher_ctx(ablkcipher);
 	struct device *jrdev = ctx->jrdev;
-	gfp_t flags = (req->base.flags & (CRYPTO_TFM_REQ_MAY_BACKLOG |
-					  CRYPTO_TFM_REQ_MAY_SLEEP)) ?
+	gfp_t flags = (req->base.flags & CRYPTO_TFM_REQ_MAY_SLEEP) ?
 		       GFP_KERNEL : GFP_ATOMIC;
 	int src_nents, mapped_src_nents, dst_nents = 0, mapped_dst_nents = 0;
 	struct ablkcipher_edesc *edesc;

drivers/infiniband/core/uverbs_cmd.c

@@ -1931,6 +1931,11 @@ static int modify_qp(struct ib_uverbs_file *file,
 		goto out;
 	}
 
+	if (!rdma_is_port_valid(qp->device, cmd->base.port_num)) {
+		ret = -EINVAL;
+		goto release_qp;
+	}
+
 	attr->qp_state		  = cmd->base.qp_state;
 	attr->cur_qp_state	  = cmd->base.cur_qp_state;
 	attr->path_mtu		  = cmd->base.path_mtu;
@@ -2541,6 +2546,9 @@ ssize_t ib_uverbs_create_ah(struct ib_uverbs_file *file,
 	if (copy_from_user(&cmd, buf, sizeof cmd))
 		return -EFAULT;
 
+	if (!rdma_is_port_valid(ib_dev, cmd.attr.port_num))
+		return -EINVAL;
+
 	INIT_UDATA(&udata, buf + sizeof(cmd),
 		   (unsigned long)cmd.response + sizeof(resp),
 		   in_len - sizeof(cmd), out_len - sizeof(resp));

drivers/staging/comedi/comedi_fops.c

@@ -2915,6 +2915,7 @@ static int __init comedi_init(void)
 		dev = comedi_alloc_board_minor(NULL);
 		if (IS_ERR(dev)) {
 			comedi_cleanup_board_minors();
+			class_destroy(comedi_class);
 			cdev_del(&comedi_cdev);
 			unregister_chrdev_region(MKDEV(COMEDI_MAJOR, 0),
 						 COMEDI_NUM_MINORS);

drivers/staging/vt6656/main_usb.c

@@ -513,6 +513,9 @@ static int vnt_start(struct ieee80211_hw *hw)
 		goto free_all;
 	}
 
+	if (vnt_key_init_table(priv))
+		goto free_all;
+
 	priv->int_interval = 1;  /* bInterval is set to 1 */
 
 	vnt_int_start_interrupt(priv);

drivers/tty/serial/imx.c

@@ -1340,29 +1340,13 @@ static int imx_startup(struct uart_port *port)
 	imx_enable_ms(&sport->port);
 
 	/*
-	 * If the serial port is opened for reading start RX DMA immediately
-	 * instead of waiting for RX FIFO interrupts. In our iMX53 the average
-	 * delay for the first reception dropped from approximately 35000
-	 * microseconds to 1000 microseconds.
+	 * Start RX DMA immediately instead of waiting for RX FIFO interrupts.
+	 * In our iMX53 the average delay for the first reception dropped from
+	 * approximately 35000 microseconds to 1000 microseconds.
 	 */
 	if (sport->dma_is_enabled) {
-		struct tty_struct *tty = sport->port.state->port.tty;
-		struct tty_file_private *file_priv;
-		int readcnt = 0;
-
-		spin_lock(&tty->files_lock);
-
-		if (!list_empty(&tty->tty_files))
-			list_for_each_entry(file_priv, &tty->tty_files, list)
-				if (!(file_priv->file->f_flags & O_WRONLY))
-					readcnt++;
-
-		spin_unlock(&tty->files_lock);
-
-		if (readcnt > 0) {
-			imx_disable_rx_int(sport);
-			start_rx_dma(sport);
-		}
+		imx_disable_rx_int(sport);
+		start_rx_dma(sport);
 	}
 
 	spin_unlock_irqrestore(&sport->port.lock, flags);

drivers/usb/core/quirks.c

@@ -223,6 +223,10 @@ static const struct usb_device_id usb_quirk_list[] = {
 	/* Blackmagic Design UltraStudio SDI */
 	{ USB_DEVICE(0x1edb, 0xbd4f), .driver_info = USB_QUIRK_NO_LPM },
 
+	/* Hauppauge HVR-950q */
+	{ USB_DEVICE(0x2040, 0x7200), .driver_info =
+			USB_QUIRK_CONFIG_INTF_STRINGS },
+
 	/* INTEL VALUE SSD */
 	{ USB_DEVICE(0x8086, 0xf1a5), .driver_info = USB_QUIRK_RESET_RESUME },
 

drivers/usb/core/usb.c

@@ -416,6 +416,8 @@ static void usb_release_dev(struct device *dev)
 
 	usb_destroy_configuration(udev);
 	usb_release_bos_descriptor(udev);
+	if (udev->parent)
+		of_node_put(dev->of_node);
 	usb_put_hcd(hcd);
 	kfree(udev->product);
 	kfree(udev->manufacturer);

drivers/usb/dwc3/dwc3-st.c

@@ -230,7 +230,7 @@ static int st_dwc3_probe(struct platform_device *pdev)
 
 	dwc3_data->syscfg_reg_off = res->start;
 
-	dev_vdbg(&pdev->dev, "glue-logic addr 0x%p, syscfg-reg offset 0x%x\n",
+	dev_vdbg(&pdev->dev, "glue-logic addr 0x%pK, syscfg-reg offset 0x%x\n",
 		 dwc3_data->glue_base, dwc3_data->syscfg_reg_off);
 
 	dwc3_data->rstc_pwrdn =

drivers/usb/dwc3/gadget.c

@@ -1215,12 +1215,9 @@ static int __dwc3_gadget_ep_queue(struct dwc3_ep *dep, struct dwc3_request *req)
 		return -ESHUTDOWN;
 	}
 
-	if (WARN(req->dep != dep, "request %p belongs to '%s'\n",
-				&req->request, req->dep->name)) {
-		dev_err(dwc->dev, "%s: request %p belongs to '%s'\n",
-				dep->name, &req->request, req->dep->name);
+	if (WARN(req->dep != dep, "request %pK belongs to '%s'\n",
+				&req->request, req->dep->name))
 		return -EINVAL;
-	}
 
 	pm_runtime_get(dwc->dev);
 
@@ -1396,7 +1393,7 @@ static int dwc3_gadget_ep_dequeue(struct usb_ep *ep,
 			}
 			goto out1;
 		}
-		dev_err(dwc->dev, "request %p was not queued to %s\n",
+		dev_err(dwc->dev, "request %pK was not queued to %s\n",
 				request, ep->name);
 		ret = -EINVAL;
 		goto out0;

drivers/usb/host/xhci-hub.c

@@ -1461,6 +1461,9 @@ int xhci_bus_suspend(struct usb_hcd *hcd)
 				t2 |= PORT_WKOC_E | PORT_WKCONN_E;
 				t2 &= ~PORT_WKDISC_E;
 			}
+			if ((xhci->quirks & XHCI_U2_DISABLE_WAKE) &&
+			    (hcd->speed < HCD_USB3))
+				t2 &= ~PORT_WAKE_BITS;
 		} else
 			t2 &= ~PORT_WAKE_BITS;
 

drivers/usb/host/xhci-pci.c

@@ -54,6 +54,11 @@
 #define PCI_DEVICE_ID_INTEL_APL_XHCI			0x5aa8
 #define PCI_DEVICE_ID_INTEL_DNV_XHCI			0x19d0
 
+#define PCI_DEVICE_ID_AMD_PROMONTORYA_4			0x43b9
+#define PCI_DEVICE_ID_AMD_PROMONTORYA_3			0x43ba
+#define PCI_DEVICE_ID_AMD_PROMONTORYA_2			0x43bb
+#define PCI_DEVICE_ID_AMD_PROMONTORYA_1			0x43bc
+
 static const char hcd_name[] = "xhci_hcd";
 
 static struct hc_driver __read_mostly xhci_pci_hc_driver;
@@ -135,6 +140,13 @@ static void xhci_pci_quirks(struct device *dev, struct xhci_hcd *xhci)
 	if (pdev->vendor == PCI_VENDOR_ID_AMD)
 		xhci->quirks |= XHCI_TRUST_TX_LENGTH;
 
+	if ((pdev->vendor == PCI_VENDOR_ID_AMD) &&
+		((pdev->device == PCI_DEVICE_ID_AMD_PROMONTORYA_4) ||
+		(pdev->device == PCI_DEVICE_ID_AMD_PROMONTORYA_3) ||
+		(pdev->device == PCI_DEVICE_ID_AMD_PROMONTORYA_2) ||
+		(pdev->device == PCI_DEVICE_ID_AMD_PROMONTORYA_1)))
+		xhci->quirks |= XHCI_U2_DISABLE_WAKE;
+
 	if (pdev->vendor == PCI_VENDOR_ID_INTEL) {
 		xhci->quirks |= XHCI_LPM_SUPPORT;
 		xhci->quirks |= XHCI_INTEL_HOST;

drivers/usb/host/xhci.h

@@ -1819,6 +1819,7 @@ struct xhci_hcd {
 /* For controller with a broken Port Disable implementation */
 #define XHCI_BROKEN_PORT_PED	(1 << 25)
 #define XHCI_LIMIT_ENDPOINT_INTERVAL_7	(1 << 26)
+#define XHCI_U2_DISABLE_WAKE	(1 << 27)
 
 	unsigned int		num_active_eps;
 	unsigned int		limit_active_eps;

drivers/usb/serial/cp210x.c

@@ -141,6 +141,7 @@ static const struct usb_device_id id_table[] = {
 	{ USB_DEVICE(0x10C4, 0x8977) },	/* CEL MeshWorks DevKit Device */
 	{ USB_DEVICE(0x10C4, 0x8998) }, /* KCF Technologies PRN */
 	{ USB_DEVICE(0x10C4, 0x8A2A) }, /* HubZ dual ZigBee and Z-Wave dongle */
+	{ USB_DEVICE(0x10C4, 0x8A5E) }, /* CEL EM3588 ZigBee USB Stick Long Range */
 	{ USB_DEVICE(0x10C4, 0xEA60) }, /* Silicon Labs factory default */
 	{ USB_DEVICE(0x10C4, 0xEA61) }, /* Silicon Labs factory default */
 	{ USB_DEVICE(0x10C4, 0xEA70) }, /* Silicon Labs factory default */

drivers/usb/serial/option.c

@@ -1877,6 +1877,10 @@ static const struct usb_device_id option_ids[] = {
 	  .driver_info = (kernel_ulong_t)&four_g_w100_blacklist
 	},
 	{ USB_DEVICE_INTERFACE_CLASS(LONGCHEER_VENDOR_ID, SPEEDUP_PRODUCT_SU9800, 0xff) },
+	{ USB_DEVICE_INTERFACE_CLASS(LONGCHEER_VENDOR_ID, 0x9801, 0xff),
+	  .driver_info = (kernel_ulong_t)&net_intf3_blacklist },
+	{ USB_DEVICE_INTERFACE_CLASS(LONGCHEER_VENDOR_ID, 0x9803, 0xff),
+	  .driver_info = (kernel_ulong_t)&net_intf4_blacklist },
 	{ USB_DEVICE(LONGCHEER_VENDOR_ID, ZOOM_PRODUCT_4597) },
 	{ USB_DEVICE(LONGCHEER_VENDOR_ID, IBALL_3_5G_CONNECT) },
 	{ USB_DEVICE(HAIER_VENDOR_ID, HAIER_PRODUCT_CE100) },

drivers/usb/serial/qcserial.c

@@ -158,6 +158,7 @@ static const struct usb_device_id id_table[] = {
 	{DEVICE_SWI(0x1199, 0x9056)},	/* Sierra Wireless Modem */
 	{DEVICE_SWI(0x1199, 0x9060)},	/* Sierra Wireless Modem */
 	{DEVICE_SWI(0x1199, 0x9061)},	/* Sierra Wireless Modem */
+	{DEVICE_SWI(0x1199, 0x9063)},	/* Sierra Wireless EM7305 */
 	{DEVICE_SWI(0x1199, 0x9070)},	/* Sierra Wireless MC74xx */
 	{DEVICE_SWI(0x1199, 0x9071)},	/* Sierra Wireless MC74xx */
 	{DEVICE_SWI(0x1199, 0x9078)},	/* Sierra Wireless EM74xx */

drivers/usb/usbip/stub_main.c

@@ -262,7 +262,11 @@ void stub_device_cleanup_urbs(struct stub_device *sdev)
 		kmem_cache_free(stub_priv_cache, priv);
 
 		kfree(urb->transfer_buffer);
+		urb->transfer_buffer = NULL;
+
 		kfree(urb->setup_packet);
+		urb->setup_packet = NULL;
+
 		usb_free_urb(urb);
 	}
 }

drivers/usb/usbip/stub_tx.c

@@ -28,7 +28,11 @@ static void stub_free_priv_and_urb(struct stub_priv *priv)
 	struct urb *urb = priv->urb;
 
 	kfree(urb->setup_packet);
+	urb->setup_packet = NULL;
+
 	kfree(urb->transfer_buffer);
+	urb->transfer_buffer = NULL;
+
 	list_del(&priv->list);
 	kmem_cache_free(stub_priv_cache, priv);
 	usb_free_urb(urb);

drivers/xen/xenbus/xenbus_comms.c

@@ -299,17 +299,7 @@ static int process_msg(void)
 		mutex_lock(&xb_write_mutex);
 		list_for_each_entry(req, &xs_reply_list, list) {
 			if (req->msg.req_id == state.msg.req_id) {
-				if (req->state == xb_req_state_wait_reply) {
-					req->msg.type = state.msg.type;
-					req->msg.len = state.msg.len;
-					req->body = state.body;
-					req->state = xb_req_state_got_reply;
-					list_del(&req->list);
-					req->cb(req);
-				} else {
-					list_del(&req->list);
-					kfree(req);
-				}
+				list_del(&req->list);
 				err = 0;
 				break;
 			}
@@ -317,6 +307,15 @@ static int process_msg(void)
 		mutex_unlock(&xb_write_mutex);
 		if (err)
 			goto out;
+
+		if (req->state == xb_req_state_wait_reply) {
+			req->msg.type = state.msg.type;
+			req->msg.len = state.msg.len;
+			req->body = state.body;
+			req->state = xb_req_state_got_reply;
+			req->cb(req);
+		} else
+			kfree(req);
 	}
 
 	mutex_unlock(&xs_response_mutex);

fs/ext4/sysfs.c

@@ -100,7 +100,7 @@ static ssize_t reserved_clusters_store(struct ext4_attr *a,
 	int ret;
 
 	ret = kstrtoull(skip_spaces(buf), 0, &val);
-	if (!ret || val >= clusters)
+	if (ret || val >= clusters)
 		return -EINVAL;
 
 	atomic64_set(&sbi->s_resv_clusters, val);

fs/gfs2/glock.c

@@ -80,9 +80,9 @@ static struct rhashtable_params ht_parms = {
 
 static struct rhashtable gl_hash_table;
 
-void gfs2_glock_free(struct gfs2_glock *gl)
+static void gfs2_glock_dealloc(struct rcu_head *rcu)
 {
-	struct gfs2_sbd *sdp = gl->gl_name.ln_sbd;
+	struct gfs2_glock *gl = container_of(rcu, struct gfs2_glock, gl_rcu);
 
 	if (gl->gl_ops->go_flags & GLOF_ASPACE) {
 		kmem_cache_free(gfs2_glock_aspace_cachep, gl);
@@ -90,6 +90,13 @@ void gfs2_glock_free(struct gfs2_glock *gl)
 		kfree(gl->gl_lksb.sb_lvbptr);
 		kmem_cache_free(gfs2_glock_cachep, gl);
 	}
+}
+
+void gfs2_glock_free(struct gfs2_glock *gl)
+{
+	struct gfs2_sbd *sdp = gl->gl_name.ln_sbd;
+
+	call_rcu(&gl->gl_rcu, gfs2_glock_dealloc);
 	if (atomic_dec_and_test(&sdp->sd_glock_disposal))
 		wake_up(&sdp->sd_glock_wait);
 }

fs/gfs2/incore.h

@@ -374,6 +374,7 @@ struct gfs2_glock {
 			loff_t end;
 		} gl_vm;
 	};
+	struct rcu_head gl_rcu;
 	struct rhash_head gl_node;
 };
 

fs/proc/internal.h

@@ -67,7 +67,7 @@ struct proc_inode {
 	struct proc_dir_entry *pde;
 	struct ctl_table_header *sysctl;
 	struct ctl_table *sysctl_entry;
-	struct list_head sysctl_inodes;
+	struct hlist_node sysctl_inodes;
 	const struct proc_ns_operations *ns_ops;
 	struct inode vfs_inode;
 };

fs/proc/proc_sysctl.c

@@ -191,7 +191,7 @@ static void init_header(struct ctl_table_header *head,
 	head->set = set;
 	head->parent = NULL;
 	head->node = node;
-	INIT_LIST_HEAD(&head->inodes);
+	INIT_HLIST_HEAD(&head->inodes);
 	if (node) {
 		struct ctl_table *entry;
 		for (entry = table; entry->procname; entry++, node++)
@@ -261,25 +261,42 @@ static void unuse_table(struct ctl_table_header *p)
 			complete(p->unregistering);
 }
 
-/* called under sysctl_lock */
 static void proc_sys_prune_dcache(struct ctl_table_header *head)
 {
-	struct inode *inode, *prev = NULL;
+	struct inode *inode;
 	struct proc_inode *ei;
+	struct hlist_node *node;
+	struct super_block *sb;
 
 	rcu_read_lock();
-	list_for_each_entry_rcu(ei, &head->inodes, sysctl_inodes) {
-		inode = igrab(&ei->vfs_inode);
-		if (inode) {
-			rcu_read_unlock();
-			iput(prev);
-			prev = inode;
-			d_prune_aliases(inode);
+	for (;;) {
+		node = hlist_first_rcu(&head->inodes);
+		if (!node)
+			break;
+		ei = hlist_entry(node, struct proc_inode, sysctl_inodes);
+		spin_lock(&sysctl_lock);
+		hlist_del_init_rcu(&ei->sysctl_inodes);
+		spin_unlock(&sysctl_lock);
+
+		inode = &ei->vfs_inode;
+		sb = inode->i_sb;
+		if (!atomic_inc_not_zero(&sb->s_active))
+			continue;
+		inode = igrab(inode);
+		rcu_read_unlock();
+		if (unlikely(!inode)) {
+			deactivate_super(sb);
 			rcu_read_lock();
+			continue;
 		}
+
+		d_prune_aliases(inode);
+		iput(inode);
+		deactivate_super(sb);
+
+		rcu_read_lock();
 	}
 	rcu_read_unlock();
-	iput(prev);
 }
 
 /* called under sysctl_lock, will reacquire if has to wait */
@@ -461,7 +478,7 @@ static struct inode *proc_sys_make_inode(struct super_block *sb,
 	}
 	ei->sysctl = head;
 	ei->sysctl_entry = table;
-	list_add_rcu(&ei->sysctl_inodes, &head->inodes);
+	hlist_add_head_rcu(&ei->sysctl_inodes, &head->inodes);
 	head->count++;
 	spin_unlock(&sysctl_lock);
 
@@ -489,7 +506,7 @@ out:
 void proc_sys_evict_inode(struct inode *inode, struct ctl_table_header *head)
 {
 	spin_lock(&sysctl_lock);
-	list_del_rcu(&PROC_I(inode)->sysctl_inodes);
+	hlist_del_init_rcu(&PROC_I(inode)->sysctl_inodes);
 	if (!--head->count)
 		kfree_rcu(head, rcu);
 	spin_unlock(&sysctl_lock);

include/linux/cpumask.h

@@ -236,6 +236,23 @@ unsigned int cpumask_local_spread(unsigned int i, int node);
 		(cpu) = cpumask_next_zero((cpu), (mask)),	\
 		(cpu) < nr_cpu_ids;)
 
+extern int cpumask_next_wrap(int n, const struct cpumask *mask, int start, bool wrap);
+
+/**
+ * for_each_cpu_wrap - iterate over every cpu in a mask, starting at a specified location
+ * @cpu: the (optionally unsigned) integer iterator
+ * @mask: the cpumask poiter
+ * @start: the start location
+ *
+ * The implementation does not assume any bit in @mask is set (including @start).
+ *
+ * After the loop, cpu is >= nr_cpu_ids.
+ */
+#define for_each_cpu_wrap(cpu, mask, start)					\
+	for ((cpu) = cpumask_next_wrap((start)-1, (mask), (start), false);	\
+	     (cpu) < nr_cpumask_bits;						\
+	     (cpu) = cpumask_next_wrap((cpu), (mask), (start), true))
+
 /**
  * for_each_cpu_and - iterate over every cpu in both masks
  * @cpu: the (optionally unsigned) integer iterator

include/linux/device.h

@@ -378,6 +378,7 @@ int subsys_virtual_register(struct bus_type *subsys,
  * @suspend:	Used to put the device to sleep mode, usually to a low power
  *		state.
  * @resume:	Used to bring the device from the sleep mode.
+ * @shutdown:	Called at shut-down time to quiesce the device.
  * @ns_type:	Callbacks so sysfs can detemine namespaces.
  * @namespace:	Namespace of the device belongs to this class.
  * @pm:		The default device power management operations of this class.
@@ -407,6 +408,7 @@ struct class {
 
 	int (*suspend)(struct device *dev, pm_message_t state);
 	int (*resume)(struct device *dev);
+	int (*shutdown)(struct device *dev);
 
 	const struct kobj_ns_type_operations *ns_type;
 	const void *(*namespace)(struct device *dev);

include/linux/sysctl.h

@@ -143,7 +143,7 @@ struct ctl_table_header
 	struct ctl_table_set *set;
 	struct ctl_dir *parent;
 	struct ctl_node *node;
-	struct list_head inodes; /* head for proc_inode->sysctl_inodes */
+	struct hlist_head inodes; /* head for proc_inode->sysctl_inodes */
 };
 
 struct ctl_dir {

include/linux/usb/hcd.h

@@ -565,9 +565,9 @@ extern void usb_ep0_reinit(struct usb_device *);
 	((USB_DIR_IN|USB_TYPE_STANDARD|USB_RECIP_INTERFACE)<<8)
 
 #define EndpointRequest \
-	((USB_DIR_IN|USB_TYPE_STANDARD|USB_RECIP_INTERFACE)<<8)
+	((USB_DIR_IN|USB_TYPE_STANDARD|USB_RECIP_ENDPOINT)<<8)
 #define EndpointOutRequest \
-	((USB_DIR_OUT|USB_TYPE_STANDARD|USB_RECIP_INTERFACE)<<8)
+	((USB_DIR_OUT|USB_TYPE_STANDARD|USB_RECIP_ENDPOINT)<<8)
 
 /* class requests from the USB 2.0 hub spec, table 11-15 */
 #define HUB_CLASS_REQ(dir, type, request) ((((dir) | (type)) << 8) | (request))

ipc/mqueue.c

@@ -1253,8 +1253,10 @@ retry:
 
 			timeo = MAX_SCHEDULE_TIMEOUT;
 			ret = netlink_attachskb(sock, nc, &timeo, NULL);
-			if (ret == 1)
+			if (ret == 1) {
+				sock = NULL;
 				goto retry;
+			}
 			if (ret) {
 				sock = NULL;
 				nc = NULL;

kernel/locking/rwsem-spinlock.c

@@ -231,8 +231,8 @@ int __sched __down_write_common(struct rw_semaphore *sem, int state)
 
 out_nolock:
 	list_del(&waiter.list);
-	if (!list_empty(&sem->wait_list))
-		__rwsem_do_wake(sem, 1);
+	if (!list_empty(&sem->wait_list) && sem->count >= 0)
+		__rwsem_do_wake(sem, 0);
 	raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
 
 	return -EINTR;

kernel/sched/fair.c

@@ -1381,7 +1381,6 @@ static unsigned long weighted_cpuload(const int cpu);
 static unsigned long source_load(int cpu, int type);
 static unsigned long target_load(int cpu, int type);
 static unsigned long capacity_of(int cpu);
-static long effective_load(struct task_group *tg, int cpu, long wl, long wg);
 
 /* Cached statistics for all CPUs within a node */
 struct numa_stats {
@@ -2469,7 +2468,8 @@ void task_numa_work(struct callback_head *work)
 		return;
 
 
-	down_read(&mm->mmap_sem);
+	if (!down_read_trylock(&mm->mmap_sem))
+		return;
 	vma = find_vma(mm, start);
 	if (!vma) {
 		reset_ptenuma_scan(p);
@@ -2584,6 +2584,60 @@ void task_tick_numa(struct rq *rq, struct task_struct *curr)
 		}
 	}
 }
+
+/*
+ * Can a task be moved from prev_cpu to this_cpu without causing a load
+ * imbalance that would trigger the load balancer?
+ */
+static inline bool numa_wake_affine(struct sched_domain *sd,
+				    struct task_struct *p, int this_cpu,
+				    int prev_cpu, int sync)
+{
+	struct numa_stats prev_load, this_load;
+	s64 this_eff_load, prev_eff_load;
+
+	update_numa_stats(&prev_load, cpu_to_node(prev_cpu));
+	update_numa_stats(&this_load, cpu_to_node(this_cpu));
+
+	/*
+	 * If sync wakeup then subtract the (maximum possible)
+	 * effect of the currently running task from the load
+	 * of the current CPU:
+	 */
+	if (sync) {
+		unsigned long current_load = task_h_load(current);
+
+		if (this_load.load > current_load)
+			this_load.load -= current_load;
+		else
+			this_load.load = 0;
+	}
+
+	/*
+	 * In low-load situations, where this_cpu's node is idle due to the
+	 * sync cause above having dropped this_load.load to 0, move the task.
+	 * Moving to an idle socket will not create a bad imbalance.
+	 *
+	 * Otherwise check if the nodes are near enough in load to allow this
+	 * task to be woken on this_cpu's node.
+	 */
+	if (this_load.load > 0) {
+		unsigned long task_load = task_h_load(p);
+
+		this_eff_load = 100;
+		this_eff_load *= prev_load.compute_capacity;
+
+		prev_eff_load = 100 + (sd->imbalance_pct - 100) / 2;
+		prev_eff_load *= this_load.compute_capacity;
+
+		this_eff_load *= this_load.load + task_load;
+		prev_eff_load *= prev_load.load - task_load;
+
+		return this_eff_load <= prev_eff_load;
+	}
+
+	return true;
+}
 #else
 static void task_tick_numa(struct rq *rq, struct task_struct *curr)
 {
@@ -2596,6 +2650,15 @@ static inline void account_numa_enqueue(struct rq *rq, struct task_struct *p)
 static inline void account_numa_dequeue(struct rq *rq, struct task_struct *p)
 {
 }
+
+#ifdef CONFIG_SMP
+static inline bool numa_wake_affine(struct sched_domain *sd,
+				    struct task_struct *p, int this_cpu,
+				    int prev_cpu, int sync)
+{
+	return true;
+}
+#endif /* !SMP */
 #endif /* CONFIG_NUMA_BALANCING */
 
 static void
@@ -2982,8 +3045,7 @@ __update_load_avg_cfs_rq(u64 now, int cpu, struct cfs_rq *cfs_rq)
  * differential update where we store the last value we propagated. This in
  * turn allows skipping updates if the differential is 'small'.
  *
- * Updating tg's load_avg is necessary before update_cfs_share() (which is
- * done) and effective_load() (which is not done because it is too costly).
+ * Updating tg's load_avg is necessary before update_cfs_share().
  */
 static inline void update_tg_load_avg(struct cfs_rq *cfs_rq, int force)
 {
@@ -5215,126 +5277,6 @@ static unsigned long cpu_avg_load_per_task(int cpu)
 	return 0;
 }
 
-#ifdef CONFIG_FAIR_GROUP_SCHED
-/*
- * effective_load() calculates the load change as seen from the root_task_group
- *
- * Adding load to a group doesn't make a group heavier, but can cause movement
- * of group shares between cpus. Assuming the shares were perfectly aligned one
- * can calculate the shift in shares.
- *
- * Calculate the effective load difference if @wl is added (subtracted) to @tg
- * on this @cpu and results in a total addition (subtraction) of @wg to the
- * total group weight.
- *
- * Given a runqueue weight distribution (rw_i) we can compute a shares
- * distribution (s_i) using:
- *
- *   s_i = rw_i / \Sum rw_j						(1)
- *
- * Suppose we have 4 CPUs and our @tg is a direct child of the root group and
- * has 7 equal weight tasks, distributed as below (rw_i), with the resulting
- * shares distribution (s_i):
- *
- *   rw_i = {   2,   4,   1,   0 }
- *   s_i  = { 2/7, 4/7, 1/7,   0 }
- *
- * As per wake_affine() we're interested in the load of two CPUs (the CPU the
- * task used to run on and the CPU the waker is running on), we need to
- * compute the effect of waking a task on either CPU and, in case of a sync
- * wakeup, compute the effect of the current task going to sleep.
- *
- * So for a change of @wl to the local @cpu with an overall group weight change
- * of @wl we can compute the new shares distribution (s'_i) using:
- *
- *   s'_i = (rw_i + @wl) / (@wg + \Sum rw_j)				(2)
- *
- * Suppose we're interested in CPUs 0 and 1, and want to compute the load
- * differences in waking a task to CPU 0. The additional task changes the
- * weight and shares distributions like:
- *
- *   rw'_i = {   3,   4,   1,   0 }
- *   s'_i  = { 3/8, 4/8, 1/8,   0 }
- *
- * We can then compute the difference in effective weight by using:
- *
- *   dw_i = S * (s'_i - s_i)						(3)
- *
- * Where 'S' is the group weight as seen by its parent.
- *
- * Therefore the effective change in loads on CPU 0 would be 5/56 (3/8 - 2/7)
- * times the weight of the group. The effect on CPU 1 would be -4/56 (4/8 -
- * 4/7) times the weight of the group.
- */
-static long effective_load(struct task_group *tg, int cpu, long wl, long wg)
-{
-	struct sched_entity *se = tg->se[cpu];
-
-	if (!tg->parent)	/* the trivial, non-cgroup case */
-		return wl;
-
-	for_each_sched_entity(se) {
-		struct cfs_rq *cfs_rq = se->my_q;
-		long W, w = cfs_rq_load_avg(cfs_rq);
-
-		tg = cfs_rq->tg;
-
-		/*
-		 * W = @wg + \Sum rw_j
-		 */
-		W = wg + atomic_long_read(&tg->load_avg);
-
-		/* Ensure \Sum rw_j >= rw_i */
-		W -= cfs_rq->tg_load_avg_contrib;
-		W += w;
-
-		/*
-		 * w = rw_i + @wl
-		 */
-		w += wl;
-
-		/*
-		 * wl = S * s'_i; see (2)
-		 */
-		if (W > 0 && w < W)
-			wl = (w * (long)scale_load_down(tg->shares)) / W;
-		else
-			wl = scale_load_down(tg->shares);
-
-		/*
-		 * Per the above, wl is the new se->load.weight value; since
-		 * those are clipped to [MIN_SHARES, ...) do so now. See
-		 * calc_cfs_shares().
-		 */
-		if (wl < MIN_SHARES)
-			wl = MIN_SHARES;
-
-		/*
-		 * wl = dw_i = S * (s'_i - s_i); see (3)
-		 */
-		wl -= se->avg.load_avg;
-
-		/*
-		 * Recursively apply this logic to all parent groups to compute
-		 * the final effective load change on the root group. Since
-		 * only the @tg group gets extra weight, all parent groups can
-		 * only redistribute existing shares. @wl is the shift in shares
-		 * resulting from this level per the above.
-		 */
-		wg = 0;
-	}
-
-	return wl;
-}
-#else
-
-static long effective_load(struct task_group *tg, int cpu, long wl, long wg)
-{
-	return wl;
-}
-
-#endif
-
 static void record_wakee(struct task_struct *p)
 {
 	/*
@@ -5385,67 +5327,25 @@ static int wake_wide(struct task_struct *p)
 static int wake_affine(struct sched_domain *sd, struct task_struct *p,
 		       int prev_cpu, int sync)
 {
-	s64 this_load, load;
-	s64 this_eff_load, prev_eff_load;
-	int idx, this_cpu;
-	struct task_group *tg;
-	unsigned long weight;
-	int balanced;
-
-	idx	  = sd->wake_idx;
-	this_cpu  = smp_processor_id();
-	load	  = source_load(prev_cpu, idx);
-	this_load = target_load(this_cpu, idx);
+	int this_cpu = smp_processor_id();
+	bool affine = false;
 
 	/*
-	 * If sync wakeup then subtract the (maximum possible)
-	 * effect of the currently running task from the load
-	 * of the current CPU:
+	 * Common case: CPUs are in the same socket, and select_idle_sibling()
+	 * will do its thing regardless of what we return:
 	 */
-	if (sync) {
-		tg = task_group(current);
-		weight = current->se.avg.load_avg;
-
-		this_load += effective_load(tg, this_cpu, -weight, -weight);
-		load += effective_load(tg, prev_cpu, 0, -weight);
-	}
-
-	tg = task_group(p);
-	weight = p->se.avg.load_avg;
-
-	/*
-	 * In low-load situations, where prev_cpu is idle and this_cpu is idle
-	 * due to the sync cause above having dropped this_load to 0, we'll
-	 * always have an imbalance, but there's really nothing you can do
-	 * about that, so that's good too.
-	 *
-	 * Otherwise check if either cpus are near enough in load to allow this
-	 * task to be woken on this_cpu.
-	 */
-	this_eff_load = 100;
-	this_eff_load *= capacity_of(prev_cpu);
-
-	prev_eff_load = 100 + (sd->imbalance_pct - 100) / 2;
-	prev_eff_load *= capacity_of(this_cpu);
-
-	if (this_load > 0) {
-		this_eff_load *= this_load +
-			effective_load(tg, this_cpu, weight, weight);
-
-		prev_eff_load *= load + effective_load(tg, prev_cpu, 0, weight);
-	}
-
-	balanced = this_eff_load <= prev_eff_load;
+	if (cpus_share_cache(prev_cpu, this_cpu))
+		affine = true;
+	else
+		affine = numa_wake_affine(sd, p, this_cpu, prev_cpu, sync);
 
 	schedstat_inc(p->se.statistics.nr_wakeups_affine_attempts);
+	if (affine) {
+		schedstat_inc(sd->ttwu_move_affine);
+		schedstat_inc(p->se.statistics.nr_wakeups_affine);
+	}
 
-	if (!balanced)
-		return 0;
-
-	schedstat_inc(sd->ttwu_move_affine);
-	schedstat_inc(p->se.statistics.nr_wakeups_affine);
-
-	return 1;
+	return affine;
 }
 
 static inline int task_util(struct task_struct *p);
@@ -5640,43 +5540,6 @@ find_idlest_cpu(struct sched_group *group, struct task_struct *p, int this_cpu)
 	return shallowest_idle_cpu != -1 ? shallowest_idle_cpu : least_loaded_cpu;
 }
 
-/*
- * Implement a for_each_cpu() variant that starts the scan at a given cpu
- * (@start), and wraps around.
- *
- * This is used to scan for idle CPUs; such that not all CPUs looking for an
- * idle CPU find the same CPU. The down-side is that tasks tend to cycle
- * through the LLC domain.
- *
- * Especially tbench is found sensitive to this.
- */
-
-static int cpumask_next_wrap(int n, const struct cpumask *mask, int start, int *wrapped)
-{
-	int next;
-
-again:
-	next = find_next_bit(cpumask_bits(mask), nr_cpumask_bits, n+1);
-
-	if (*wrapped) {
-		if (next >= start)
-			return nr_cpumask_bits;
-	} else {
-		if (next >= nr_cpumask_bits) {
-			*wrapped = 1;
-			n = -1;
-			goto again;
-		}
-	}
-
-	return next;
-}
-
-#define for_each_cpu_wrap(cpu, mask, start, wrap)				\
-	for ((wrap) = 0, (cpu) = (start)-1;					\
-		(cpu) = cpumask_next_wrap((cpu), (mask), (start), &(wrap)),	\
-		(cpu) < nr_cpumask_bits; )
-
 #ifdef CONFIG_SCHED_SMT
 
 static inline void set_idle_cores(int cpu, int val)
@@ -5736,7 +5599,7 @@ unlock:
 static int select_idle_core(struct task_struct *p, struct sched_domain *sd, int target)
 {
 	struct cpumask *cpus = this_cpu_cpumask_var_ptr(select_idle_mask);
-	int core, cpu, wrap;
+	int core, cpu;
 
 	if (!static_branch_likely(&sched_smt_present))
 		return -1;
@@ -5746,7 +5609,7 @@ static int select_idle_core(struct task_struct *p, struct sched_domain *sd, int
 
 	cpumask_and(cpus, sched_domain_span(sd), &p->cpus_allowed);
 
-	for_each_cpu_wrap(core, cpus, target, wrap) {
+	for_each_cpu_wrap(core, cpus, target) {
 		bool idle = true;
 
 		for_each_cpu(cpu, cpu_smt_mask(core)) {
@@ -5809,27 +5672,38 @@ static inline int select_idle_smt(struct task_struct *p, struct sched_domain *sd
 static int select_idle_cpu(struct task_struct *p, struct sched_domain *sd, int target)
 {
 	struct sched_domain *this_sd;
-	u64 avg_cost, avg_idle = this_rq()->avg_idle;
+	u64 avg_cost, avg_idle;
 	u64 time, cost;
 	s64 delta;
-	int cpu, wrap;
+	int cpu, nr = INT_MAX;
 
 	this_sd = rcu_dereference(*this_cpu_ptr(&sd_llc));
 	if (!this_sd)
 		return -1;
 
-	avg_cost = this_sd->avg_scan_cost;
-
 	/*
 	 * Due to large variance we need a large fuzz factor; hackbench in
 	 * particularly is sensitive here.
 	 */
-	if (sched_feat(SIS_AVG_CPU) && (avg_idle / 512) < avg_cost)
+	avg_idle = this_rq()->avg_idle / 512;
+	avg_cost = this_sd->avg_scan_cost + 1;
+
+	if (sched_feat(SIS_AVG_CPU) && avg_idle < avg_cost)
 		return -1;
 
+	if (sched_feat(SIS_PROP)) {
+		u64 span_avg = sd->span_weight * avg_idle;
+		if (span_avg > 4*avg_cost)
+			nr = div_u64(span_avg, avg_cost);
+		else
+			nr = 4;
+	}
+
 	time = local_clock();
 
-	for_each_cpu_wrap(cpu, sched_domain_span(sd), target, wrap) {
+	for_each_cpu_wrap(cpu, sched_domain_span(sd), target) {
+		if (!--nr)
+			return -1;
 		if (!cpumask_test_cpu(cpu, &p->cpus_allowed))
 			continue;
 		if (idle_cpu(cpu))
@@ -6011,11 +5885,15 @@ select_task_rq_fair(struct task_struct *p, int prev_cpu, int sd_flag, int wake_f
 
 	if (affine_sd) {
 		sd = NULL; /* Prefer wake_affine over balance flags */
-		if (cpu != prev_cpu && wake_affine(affine_sd, p, prev_cpu, sync))
+		if (cpu == prev_cpu)
+			goto pick_cpu;
+
+		if (wake_affine(affine_sd, p, prev_cpu, sync))
 			new_cpu = cpu;
 	}
 
 	if (!sd) {
+ pick_cpu:
 		if (sd_flag & SD_BALANCE_WAKE) /* XXX always ? */
 			new_cpu = select_idle_sibling(p, prev_cpu, new_cpu);
 
@@ -6686,6 +6564,10 @@ static int migrate_degrades_locality(struct task_struct *p, struct lb_env *env)
 	if (dst_nid == p->numa_preferred_nid)
 		return 0;
 
+	/* Leaving a core idle is often worse than degrading locality. */
+	if (env->idle != CPU_NOT_IDLE)
+		return -1;
+
 	if (numa_group) {
 		src_faults = group_faults(p, src_nid);
 		dst_faults = group_faults(p, dst_nid);

kernel/sched/features.h

@@ -55,6 +55,7 @@ SCHED_FEAT(TTWU_QUEUE, true)
  * When doing wakeups, attempt to limit superfluous scans of the LLC domain.
  */
 SCHED_FEAT(SIS_AVG_CPU, false)
+SCHED_FEAT(SIS_PROP, true)
 
 /*
  * Issue a WARN when we do multiple update_rq_clock() calls

lib/cpumask.c

@@ -43,6 +43,38 @@ int cpumask_any_but(const struct cpumask *mask, unsigned int cpu)
 }
 EXPORT_SYMBOL(cpumask_any_but);
 
+/**
+ * cpumask_next_wrap - helper to implement for_each_cpu_wrap
+ * @n: the cpu prior to the place to search
+ * @mask: the cpumask pointer
+ * @start: the start point of the iteration
+ * @wrap: assume @n crossing @start terminates the iteration
+ *
+ * Returns >= nr_cpu_ids on completion
+ *
+ * Note: the @wrap argument is required for the start condition when
+ * we cannot assume @start is set in @mask.
+ */
+int cpumask_next_wrap(int n, const struct cpumask *mask, int start, bool wrap)
+{
+	int next;
+
+again:
+	next = cpumask_next(n, mask);
+
+	if (wrap && n < start && next >= start) {
+		return nr_cpumask_bits;
+
+	} else if (next >= nr_cpumask_bits) {
+		wrap = true;
+		n = -1;
+		goto again;
+	}
+
+	return next;
+}
+EXPORT_SYMBOL(cpumask_next_wrap);
+
 /* These are not inline because of header tangles. */
 #ifdef CONFIG_CPUMASK_OFFSTACK
 /**