Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net

66 files changed, 594 insertions, 290 deletions

diff --git a/CREDITS b/CREDITS
index c58560701d13..c5626bf06264 100644
--- a/CREDITS
+++ b/CREDITS
@@ -2478,12 +2478,11 @@ S: D-90453 Nuernberg
 S: Germany
 
 N: Arnaldo Carvalho de Melo
-E: acme@ghostprotocols.net
+E: acme@kernel.org
 E: arnaldo.melo@gmail.com
 E: acme@redhat.com
-W: http://oops.ghostprotocols.net:81/blog/
 P: 1024D/9224DF01 D5DF E3BB E3C8 BCBB F8AD  841A B6AB 4681 9224 DF01
-D: IPX, LLC, DCCP, cyc2x, wl3501_cs, net/ hacks
+D: tools/, IPX, LLC, DCCP, cyc2x, wl3501_cs, net/ hacks
 S: Brazil
 
 N: Karsten Merker
diff --git a/Documentation/media/uapi/v4l/pixfmt-007.rst b/Documentation/media/uapi/v4l/pixfmt-007.rst
index 44bb5a7059b3..95a23a28c595 100644
--- a/Documentation/media/uapi/v4l/pixfmt-007.rst
+++ b/Documentation/media/uapi/v4l/pixfmt-007.rst
@@ -211,7 +211,13 @@ Colorspace sRGB (V4L2_COLORSPACE_SRGB)
 The :ref:`srgb` standard defines the colorspace used by most webcams
 and computer graphics. The default transfer function is
 ``V4L2_XFER_FUNC_SRGB``. The default Y'CbCr encoding is
-``V4L2_YCBCR_ENC_601``. The default Y'CbCr quantization is full range.
+``V4L2_YCBCR_ENC_601``. The default Y'CbCr quantization is limited range.
+
+Note that the :ref:`sycc` standard specifies full range quantization,
+however all current capture hardware supported by the kernel convert
+R'G'B' to limited range Y'CbCr. So choosing full range as the default
+would break how applications interpret the quantization range.
+
 The chromaticities of the primary colors and the white reference are:
 
 
@@ -276,7 +282,7 @@ the following ``V4L2_YCBCR_ENC_601`` encoding as defined by :ref:`sycc`:
 
 Y' is clamped to the range [0…1] and Cb and Cr are clamped to the range
 [-0.5…0.5]. This transform is identical to one defined in SMPTE
-170M/BT.601. The Y'CbCr quantization is full range.
+170M/BT.601. The Y'CbCr quantization is limited range.
 
 
 .. _col-adobergb:
@@ -288,10 +294,15 @@ The :ref:`adobergb` standard defines the colorspace used by computer
 graphics that use the AdobeRGB colorspace. This is also known as the
 :ref:`oprgb` standard. The default transfer function is
 ``V4L2_XFER_FUNC_ADOBERGB``. The default Y'CbCr encoding is
-``V4L2_YCBCR_ENC_601``. The default Y'CbCr quantization is full
-range. The chromaticities of the primary colors and the white reference
-are:
+``V4L2_YCBCR_ENC_601``. The default Y'CbCr quantization is limited
+range.
+
+Note that the :ref:`oprgb` standard specifies full range quantization,
+however all current capture hardware supported by the kernel convert
+R'G'B' to limited range Y'CbCr. So choosing full range as the default
+would break how applications interpret the quantization range.
 
+The chromaticities of the primary colors and the white reference are:
 
 
 .. tabularcolumns:: |p{4.4cm}|p{4.4cm}|p{8.7cm}|
@@ -344,7 +355,7 @@ the following ``V4L2_YCBCR_ENC_601`` encoding:
 
 Y' is clamped to the range [0…1] and Cb and Cr are clamped to the range
 [-0.5…0.5]. This transform is identical to one defined in SMPTE
-170M/BT.601. The Y'CbCr quantization is full range.
+170M/BT.601. The Y'CbCr quantization is limited range.
 
 
 .. _col-bt2020:
diff --git a/MAINTAINERS b/MAINTAINERS
index 62b0307a7ca4..d8f71f21fb88 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -877,8 +877,8 @@ S:	Odd fixes
 F:	drivers/hwmon/applesmc.c
 
 APPLETALK NETWORK LAYER
-M:	Arnaldo Carvalho de Melo <acme@ghostprotocols.net>
-S:	Maintained
+L:	netdev@vger.kernel.org
+S:	Odd fixes
 F:	drivers/net/appletalk/
 F:	net/appletalk/
 
@@ -6748,9 +6748,8 @@ S:	Odd Fixes
 F:	drivers/tty/ipwireless/
 
 IPX NETWORK LAYER
-M:	Arnaldo Carvalho de Melo <acme@ghostprotocols.net>
 L:	netdev@vger.kernel.org
-S:	Maintained
+S:	Odd fixes
 F:	include/net/ipx.h
 F:	include/uapi/linux/ipx.h
 F:	net/ipx/
@@ -7522,8 +7521,8 @@ S:	Maintained
 F:	drivers/misc/lkdtm*
 
 LLC (802.2)
-M:	Arnaldo Carvalho de Melo <acme@ghostprotocols.net>
-S:	Maintained
+L:	netdev@vger.kernel.org
+S:	Odd fixes
 F:	include/linux/llc.h
 F:	include/uapi/linux/llc.h
 F:	include/net/llc*
@@ -13416,10 +13415,8 @@ S:	Maintained
 F:	drivers/input/misc/wistron_btns.c
 
 WL3501 WIRELESS PCMCIA CARD DRIVER
-M:	Arnaldo Carvalho de Melo <acme@ghostprotocols.net>
 L:	linux-wireless@vger.kernel.org
-W:	http://oops.ghostprotocols.net:81/blog
-S:	Maintained
+S:	Odd fixes
 F:	drivers/net/wireless/wl3501*
 
 WOLFSON MICROELECTRONICS DRIVERS
diff --git a/Makefile b/Makefile
index 8e223e081c9d..503dae1de8ef 100644
--- a/Makefile
+++ b/Makefile
@@ -1,7 +1,7 @@
 VERSION = 4
 PATCHLEVEL = 10
 SUBLEVEL = 0
-EXTRAVERSION = -rc7
+EXTRAVERSION = -rc8
 NAME = Fearless Coyote
 
 # *DOCUMENTATION*
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index 1be64da0384e..e6cfe7ba2d65 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -104,6 +104,7 @@ struct cpuinfo_x86 {
 	__u8			x86_phys_bits;
 	/* CPUID returned core id bits: */
 	__u8			x86_coreid_bits;
+	__u8			cu_id;
 	/* Max extended CPUID function supported: */
 	__u32			extended_cpuid_level;
 	/* Maximum supported CPUID level, -1=no CPUID: */
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index 1d3167269a67..2b4cf04239b6 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -309,8 +309,22 @@ static void amd_get_topology(struct cpuinfo_x86 *c)
 
 	/* get information required for multi-node processors */
 	if (boot_cpu_has(X86_FEATURE_TOPOEXT)) {
+		u32 eax, ebx, ecx, edx;
 
-		node_id = cpuid_ecx(0x8000001e) & 7;
+		cpuid(0x8000001e, &eax, &ebx, &ecx, &edx);
+
+		node_id  = ecx & 0xff;
+		smp_num_siblings = ((ebx >> 8) & 0xff) + 1;
+
+		if (c->x86 == 0x15)
+			c->cu_id = ebx & 0xff;
+
+		if (c->x86 >= 0x17) {
+			c->cpu_core_id = ebx & 0xff;
+
+			if (smp_num_siblings > 1)
+				c->x86_max_cores /= smp_num_siblings;
+		}
 
 		/*
 		 * We may have multiple LLCs if L3 caches exist, so check if we
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 9bab7a8a4293..ede03e849a8b 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -1015,6 +1015,7 @@ static void identify_cpu(struct cpuinfo_x86 *c)
 	c->x86_model_id[0] = '\0';  /* Unset */
 	c->x86_max_cores = 1;
 	c->x86_coreid_bits = 0;
+	c->cu_id = 0xff;
 #ifdef CONFIG_X86_64
 	c->x86_clflush_size = 64;
 	c->x86_phys_bits = 36;
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 46732dc3b73c..99b920d0e516 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -433,9 +433,15 @@ static bool match_smt(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o)
 		int cpu1 = c->cpu_index, cpu2 = o->cpu_index;
 
 		if (c->phys_proc_id == o->phys_proc_id &&
-		    per_cpu(cpu_llc_id, cpu1) == per_cpu(cpu_llc_id, cpu2) &&
-		    c->cpu_core_id == o->cpu_core_id)
-			return topology_sane(c, o, "smt");
+		    per_cpu(cpu_llc_id, cpu1) == per_cpu(cpu_llc_id, cpu2)) {
+			if (c->cpu_core_id == o->cpu_core_id)
+				return topology_sane(c, o, "smt");
+
+			if ((c->cu_id != 0xff) &&
+			    (o->cu_id != 0xff) &&
+			    (c->cu_id == o->cu_id))
+				return topology_sane(c, o, "smt");
+		}
 
 	} else if (c->phys_proc_id == o->phys_proc_id &&
 		   c->cpu_core_id == o->cpu_core_id) {
diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index e41af597aed8..37e7cf544e51 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -1356,6 +1356,9 @@ void __init tsc_init(void)
 		(unsigned long)cpu_khz / 1000,
 		(unsigned long)cpu_khz % 1000);
 
+	/* Sanitize TSC ADJUST before cyc2ns gets initialized */
+	tsc_store_and_check_tsc_adjust(true);
+
 	/*
 	 * Secondary CPUs do not run through tsc_init(), so set up
 	 * all the scale factors for all CPUs, assuming the same
@@ -1386,8 +1389,6 @@ void __init tsc_init(void)
 
 	if (unsynchronized_tsc())
 		mark_tsc_unstable("TSCs unsynchronized");
-	else
-		tsc_store_and_check_tsc_adjust(true);
 
 	check_system_tsc_reliable();
 
diff --git a/arch/x86/kernel/tsc_sync.c b/arch/x86/kernel/tsc_sync.c
index d0db011051a5..728f75378475 100644
--- a/arch/x86/kernel/tsc_sync.c
+++ b/arch/x86/kernel/tsc_sync.c
@@ -286,13 +286,6 @@ void check_tsc_sync_source(int cpu)
 	if (unsynchronized_tsc())
 		return;
 
-	if (tsc_clocksource_reliable) {
-		if (cpu == (nr_cpu_ids-1) || system_state != SYSTEM_BOOTING)
-			pr_info(
-			"Skipped synchronization checks as TSC is reliable.\n");
-		return;
-	}
-
 	/*
 	 * Set the maximum number of test runs to
 	 *  1 if the CPU does not provide the TSC_ADJUST MSR
@@ -380,14 +373,19 @@ void check_tsc_sync_target(void)
 	int cpus = 2;
 
 	/* Also aborts if there is no TSC. */
-	if (unsynchronized_tsc() || tsc_clocksource_reliable)
+	if (unsynchronized_tsc())
 		return;
 
 	/*
 	 * Store, verify and sanitize the TSC adjust register. If
 	 * successful skip the test.
+	 *
+	 * The test is also skipped when the TSC is marked reliable. This
+	 * is true for SoCs which have no fallback clocksource. On these
+	 * SoCs the TSC is frequency synchronized, but still the TSC ADJUST
+	 * register might have been wreckaged by the BIOS..
 	 */
-	if (tsc_store_and_check_tsc_adjust(false)) {
+	if (tsc_store_and_check_tsc_adjust(false) || tsc_clocksource_reliable) {
 		atomic_inc(&skip_test);
 		return;
 	}
diff --git a/arch/x86/mm/dump_pagetables.c b/arch/x86/mm/dump_pagetables.c
index ea9c49adaa1f..8aa6bea1cd6c 100644
--- a/arch/x86/mm/dump_pagetables.c
+++ b/arch/x86/mm/dump_pagetables.c
@@ -15,6 +15,7 @@
 #include <linux/debugfs.h>
 #include <linux/mm.h>
 #include <linux/init.h>
+#include <linux/sched.h>
 #include <linux/seq_file.h>
 
 #include <asm/pgtable.h>
@@ -406,6 +407,7 @@ static void ptdump_walk_pgd_level_core(struct seq_file *m, pgd_t *pgd,
 		} else
 			note_page(m, &st, __pgprot(0), 1);
 
+		cond_resched();
 		start++;
 	}
 
diff --git a/drivers/irqchip/irq-keystone.c b/drivers/irqchip/irq-keystone.c
index 54a5e870a8f5..efbcf8435185 100644
--- a/drivers/irqchip/irq-keystone.c
+++ b/drivers/irqchip/irq-keystone.c
@@ -19,9 +19,9 @@
 #include <linux/bitops.h>
 #include <linux/module.h>
 #include <linux/moduleparam.h>
+#include <linux/interrupt.h>
 #include <linux/irqdomain.h>
 #include <linux/irqchip.h>
-#include <linux/irqchip/chained_irq.h>
 #include <linux/of.h>
 #include <linux/of_platform.h>
 #include <linux/mfd/syscon.h>
@@ -39,6 +39,7 @@ struct keystone_irq_device {
 	struct irq_domain	*irqd;
 	struct regmap		*devctrl_regs;
 	u32			devctrl_offset;
+	raw_spinlock_t		wa_lock;
 };
 
 static inline u32 keystone_irq_readl(struct keystone_irq_device *kirq)
@@ -83,17 +84,15 @@ static void keystone_irq_ack(struct irq_data *d)
 	/* nothing to do here */
 }
 
-static void keystone_irq_handler(struct irq_desc *desc)
+static irqreturn_t keystone_irq_handler(int irq, void *keystone_irq)
 {
-	unsigned int irq = irq_desc_get_irq(desc);
-	struct keystone_irq_device *kirq = irq_desc_get_handler_data(desc);
+	struct keystone_irq_device *kirq = keystone_irq;
+	unsigned long wa_lock_flags;
 	unsigned long pending;
 	int src, virq;
 
 	dev_dbg(kirq->dev, "start irq %d\n", irq);
 
-	chained_irq_enter(irq_desc_get_chip(desc), desc);
-
 	pending = keystone_irq_readl(kirq);
 	keystone_irq_writel(kirq, pending);
 
@@ -111,13 +110,15 @@ static void keystone_irq_handler(struct irq_desc *desc)
 			if (!virq)
 				dev_warn(kirq->dev, "spurious irq detected hwirq %d, virq %d\n",
 					 src, virq);
+			raw_spin_lock_irqsave(&kirq->wa_lock, wa_lock_flags);
 			generic_handle_irq(virq);
+			raw_spin_unlock_irqrestore(&kirq->wa_lock,
+						   wa_lock_flags);
 		}
 	}
 
-	chained_irq_exit(irq_desc_get_chip(desc), desc);
-
 	dev_dbg(kirq->dev, "end irq %d\n", irq);
+	return IRQ_HANDLED;
 }
 
 static int keystone_irq_map(struct irq_domain *h, unsigned int virq,
@@ -182,9 +183,16 @@ static int keystone_irq_probe(struct platform_device *pdev)
 		return -ENODEV;
 	}
 
+	raw_spin_lock_init(&kirq->wa_lock);
+
 	platform_set_drvdata(pdev, kirq);
 
-	irq_set_chained_handler_and_data(kirq->irq, keystone_irq_handler, kirq);
+	ret = request_irq(kirq->irq, keystone_irq_handler,
+			  0, dev_name(dev), kirq);
+	if (ret) {
+		irq_domain_remove(kirq->irqd);
+		return ret;
+	}
 
 	/* clear all source bits */
 	keystone_irq_writel(kirq, ~0x0);
@@ -199,6 +207,8 @@ static int keystone_irq_remove(struct platform_device *pdev)
 	struct keystone_irq_device *kirq = platform_get_drvdata(pdev);
 	int hwirq;
 
+	free_irq(kirq->irq, kirq);
+
 	for (hwirq = 0; hwirq < KEYSTONE_N_IRQ; hwirq++)
 		irq_dispose_mapping(irq_find_mapping(kirq->irqd, hwirq));
 
diff --git a/drivers/irqchip/irq-mxs.c b/drivers/irqchip/irq-mxs.c
index 17304705f2cf..05fa9f7af53c 100644
--- a/drivers/irqchip/irq-mxs.c
+++ b/drivers/irqchip/irq-mxs.c
@@ -131,12 +131,16 @@ static struct irq_chip mxs_icoll_chip = {
 	.irq_ack = icoll_ack_irq,
 	.irq_mask = icoll_mask_irq,
 	.irq_unmask = icoll_unmask_irq,
+	.flags = IRQCHIP_MASK_ON_SUSPEND |
+		 IRQCHIP_SKIP_SET_WAKE,
 };
 
 static struct irq_chip asm9260_icoll_chip = {
 	.irq_ack = icoll_ack_irq,
 	.irq_mask = asm9260_mask_irq,
 	.irq_unmask = asm9260_unmask_irq,
+	.flags = IRQCHIP_MASK_ON_SUSPEND |
+		 IRQCHIP_SKIP_SET_WAKE,
 };
 
 asmlinkage void __exception_irq_entry icoll_handle_irq(struct pt_regs *regs)
diff --git a/drivers/media/cec/cec-adap.c b/drivers/media/cec/cec-adap.c
index 87a6b65ed3af..ccda41c2c9e4 100644
--- a/drivers/media/cec/cec-adap.c
+++ b/drivers/media/cec/cec-adap.c
@@ -612,8 +612,7 @@ int cec_transmit_msg_fh(struct cec_adapter *adap, struct cec_msg *msg,
 	}
 	memset(msg->msg + msg->len, 0, sizeof(msg->msg) - msg->len);
 	if (msg->len == 1) {
-		if (cec_msg_initiator(msg) != 0xf ||
-		    cec_msg_destination(msg) == 0xf) {
+		if (cec_msg_destination(msg) == 0xf) {
 			dprintk(1, "cec_transmit_msg: invalid poll message\n");
 			return -EINVAL;
 		}
@@ -638,7 +637,7 @@ int cec_transmit_msg_fh(struct cec_adapter *adap, struct cec_msg *msg,
 		dprintk(1, "cec_transmit_msg: destination is the adapter itself\n");
 		return -EINVAL;
 	}
-	if (cec_msg_initiator(msg) != 0xf &&
+	if (msg->len > 1 && adap->is_configured &&
 	    !cec_has_log_addr(adap, cec_msg_initiator(msg))) {
 		dprintk(1, "cec_transmit_msg: initiator has unknown logical address %d\n",
 			cec_msg_initiator(msg));
@@ -1072,7 +1071,7 @@ static int cec_config_log_addr(struct cec_adapter *adap,
 
 	/* Send poll message */
 	msg.len = 1;
-	msg.msg[0] = 0xf0 | log_addr;
+	msg.msg[0] = (log_addr << 4) | log_addr;
 	err = cec_transmit_msg_fh(adap, &msg, NULL, true);
 
 	/*
diff --git a/drivers/media/usb/siano/smsusb.c b/drivers/media/usb/siano/smsusb.c
index a4dcaec31d02..8c1f926567ec 100644
--- a/drivers/media/usb/siano/smsusb.c
+++ b/drivers/media/usb/siano/smsusb.c
@@ -218,22 +218,30 @@ static int smsusb_start_streaming(struct smsusb_device_t *dev)
 static int smsusb_sendrequest(void *context, void *buffer, size_t size)
 {
 	struct smsusb_device_t *dev = (struct smsusb_device_t *) context;
-	struct sms_msg_hdr *phdr = (struct sms_msg_hdr *) buffer;
-	int dummy;
+	struct sms_msg_hdr *phdr;
+	int dummy, ret;
 
 	if (dev->state != SMSUSB_ACTIVE) {
 		pr_debug("Device not active yet\n");
 		return -ENOENT;
 	}
 
+	phdr = kmalloc(size, GFP_KERNEL);
+	if (!phdr)
+		return -ENOMEM;
+	memcpy(phdr, buffer, size);
+
 	pr_debug("sending %s(%d) size: %d\n",
 		  smscore_translate_msg(phdr->msg_type), phdr->msg_type,
 		  phdr->msg_length);
 
 	smsendian_handle_tx_message((struct sms_msg_data *) phdr);
-	smsendian_handle_message_header((struct sms_msg_hdr *)buffer);
-	return usb_bulk_msg(dev->udev, usb_sndbulkpipe(dev->udev, 2),
-			    buffer, size, &dummy, 1000);
+	smsendian_handle_message_header((struct sms_msg_hdr *)phdr);
+	ret = usb_bulk_msg(dev->udev, usb_sndbulkpipe(dev->udev, 2),
+			    phdr, size, &dummy, 1000);
+
+	kfree(phdr);
+	return ret;
 }
 
 static char *smsusb1_fw_lkup[] = {
diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c
index 2cc552ddd8f0..91a16641e851 100644
--- a/drivers/net/ethernet/freescale/fec_main.c
+++ b/drivers/net/ethernet/freescale/fec_main.c
@@ -2910,6 +2910,7 @@ static void set_multicast_list(struct net_device *ndev)
 	struct netdev_hw_addr *ha;
 	unsigned int i, bit, data, crc, tmp;
 	unsigned char hash;
+	unsigned int hash_high = 0, hash_low = 0;
 
 	if (ndev->flags & IFF_PROMISC) {
 		tmp = readl(fep->hwp + FEC_R_CNTRL);
@@ -2932,11 +2933,7 @@ static void set_multicast_list(struct net_device *ndev)
 		return;
 	}
 
-	/* Clear filter and add the addresses in hash register
-	 */
-	writel(0, fep->hwp + FEC_GRP_HASH_TABLE_HIGH);
-	writel(0, fep->hwp + FEC_GRP_HASH_TABLE_LOW);
-
+	/* Add the addresses in hash register */
 	netdev_for_each_mc_addr(ha, ndev) {
 		/* calculate crc32 value of mac address */
 		crc = 0xffffffff;
@@ -2954,16 +2951,14 @@ static void set_multicast_list(struct net_device *ndev)
 		 */
 		hash = (crc >> (32 - FEC_HASH_BITS)) & 0x3f;
 
-		if (hash > 31) {
-			tmp = readl(fep->hwp + FEC_GRP_HASH_TABLE_HIGH);
-			tmp |= 1 << (hash - 32);
-			writel(tmp, fep->hwp + FEC_GRP_HASH_TABLE_HIGH);
-		} else {
-			tmp = readl(fep->hwp + FEC_GRP_HASH_TABLE_LOW);
-			tmp |= 1 << hash;
-			writel(tmp, fep->hwp + FEC_GRP_HASH_TABLE_LOW);
-		}
+		if (hash > 31)
+			hash_high |= 1 << (hash - 32);
+		else
+			hash_low |= 1 << hash;
 	}
+
+	writel(hash_high, fep->hwp + FEC_GRP_HASH_TABLE_HIGH);
+	writel(hash_low, fep->hwp + FEC_GRP_HASH_TABLE_LOW);
 }
 
 /* Set a MAC change in hardware. */
diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c
index c46935d4a3fe..0c94e23985be 100644
--- a/drivers/net/ethernet/ibm/ibmvnic.c
+++ b/drivers/net/ethernet/ibm/ibmvnic.c
@@ -189,9 +189,10 @@ static int alloc_long_term_buff(struct ibmvnic_adapter *adapter,
 	}
 	ltb->map_id = adapter->map_id;
 	adapter->map_id++;
+
+	init_completion(&adapter->fw_done);
 	send_request_map(adapter, ltb->addr,
 			 ltb->size, ltb->map_id);
-	init_completion(&adapter->fw_done);
 	wait_for_completion(&adapter->fw_done);
 	return 0;
 }
@@ -505,7 +506,7 @@ rx_pool_alloc_failed:
 	adapter->rx_pool = NULL;
 rx_pool_arr_alloc_failed:
 	for (i = 0; i < adapter->req_rx_queues; i++)
-		napi_enable(&adapter->napi[i]);
+		napi_disable(&adapter->napi[i]);
 alloc_napi_failed:
 	return -ENOMEM;
 }
@@ -1126,10 +1127,10 @@ static void ibmvnic_get_ethtool_stats(struct net_device *dev,
 	crq.request_statistics.ioba = cpu_to_be32(adapter->stats_token);
 	crq.request_statistics.len =
 	    cpu_to_be32(sizeof(struct ibmvnic_statistics));
-	ibmvnic_send_crq(adapter, &crq);
 
 	/* Wait for data to be written */
 	init_completion(&adapter->stats_done);
+	ibmvnic_send_crq(adapter, &crq);
 	wait_for_completion(&adapter->stats_done);
 
 	for (i = 0; i < ARRAY_SIZE(ibmvnic_stats); i++)
@@ -1501,7 +1502,7 @@ static void init_sub_crqs(struct ibmvnic_adapter *adapter, int retry)
 		adapter->req_rx_queues = adapter->opt_rx_comp_queues;
 		adapter->req_rx_add_queues = adapter->max_rx_add_queues;
 
-		adapter->req_mtu = adapter->max_mtu;
+		adapter->req_mtu = adapter->netdev->mtu + ETH_HLEN;
 	}
 
 	total_queues = adapter->req_tx_queues + adapter->req_rx_queues;
@@ -2190,12 +2191,12 @@ static void handle_error_info_rsp(union ibmvnic_crq *crq,
 
 	if (!found) {
 		dev_err(dev, "Couldn't find error id %x\n",
-			crq->request_error_rsp.error_id);
+			be32_to_cpu(crq->request_error_rsp.error_id));
 		return;
 	}
 
 	dev_err(dev, "Detailed info for error id %x:",
-		crq->request_error_rsp.error_id);
+		be32_to_cpu(crq->request_error_rsp.error_id));
 
 	for (i = 0; i < error_buff->len; i++) {
 		pr_cont("%02x", (int)error_buff->buff[i]);
@@ -2274,8 +2275,8 @@ static void handle_error_indication(union ibmvnic_crq *crq,
 	dev_err(dev, "Firmware reports %serror id %x, cause %d\n",
 		crq->error_indication.
 		    flags & IBMVNIC_FATAL_ERROR ? "FATAL " : "",
-		crq->error_indication.error_id,
-		crq->error_indication.error_cause);
+		be32_to_cpu(crq->error_indication.error_id),
+		be16_to_cpu(crq->error_indication.error_cause));
 
 	error_buff = kmalloc(sizeof(*error_buff), GFP_ATOMIC);
 	if (!error_buff)
@@ -2393,10 +2394,10 @@ static void handle_request_cap_rsp(union ibmvnic_crq *crq,
 	case PARTIALSUCCESS:
 		dev_info(dev, "req=%lld, rsp=%ld in %s queue, retrying.\n",
 			 *req_value,
-			 (long int)be32_to_cpu(crq->request_capability_rsp.
+			 (long int)be64_to_cpu(crq->request_capability_rsp.
 					       number), name);
 		release_sub_crqs_no_irqs(adapter);
-		*req_value = be32_to_cpu(crq->request_capability_rsp.number);
+		*req_value = be64_to_cpu(crq->request_capability_rsp.number);
 		init_sub_crqs(adapter, 1);
 		return;
 	default:
@@ -2631,12 +2632,12 @@ static void handle_query_cap_rsp(union ibmvnic_crq *crq,
 		break;
 	case MIN_MTU:
 		adapter->min_mtu = be64_to_cpu(crq->query_capability.number);
-		netdev->min_mtu = adapter->min_mtu;
+		netdev->min_mtu = adapter->min_mtu - ETH_HLEN;
 		netdev_dbg(netdev, "min_mtu = %lld\n", adapter->min_mtu);
 		break;
 	case MAX_MTU:
 		adapter->max_mtu = be64_to_cpu(crq->query_capability.number);
-		netdev->max_mtu = adapter->max_mtu;
+		netdev->max_mtu = adapter->max_mtu - ETH_HLEN;
 		netdev_dbg(netdev, "max_mtu = %lld\n", adapter->max_mtu);
 		break;
 	case MAX_MULTICAST_FILTERS:
@@ -2804,9 +2805,9 @@ static ssize_t trace_read(struct file *file, char __user *user_buf, size_t len,
 	crq.collect_fw_trace.correlator = adapter->ras_comps[num].correlator;
 	crq.collect_fw_trace.ioba = cpu_to_be32(trace_tok);
 	crq.collect_fw_trace.len = adapter->ras_comps[num].trace_buff_size;
-	ibmvnic_send_crq(adapter, &crq);
 
 	init_completion(&adapter->fw_done);
+	ibmvnic_send_crq(adapter, &crq);
 	wait_for_completion(&adapter->fw_done);
 
 	if (*ppos + len > be32_to_cpu(adapter->ras_comps[num].trace_buff_size))
@@ -3586,9 +3587,9 @@ static int ibmvnic_dump_show(struct seq_file *seq, void *v)
 	memset(&crq, 0, sizeof(crq));
 	crq.request_dump_size.first = IBMVNIC_CRQ_CMD;
 	crq.request_dump_size.cmd = REQUEST_DUMP_SIZE;
-	ibmvnic_send_crq(adapter, &crq);
 
 	init_completion(&adapter->fw_done);
+	ibmvnic_send_crq(adapter, &crq);
 	wait_for_completion(&adapter->fw_done);
 
 	seq_write(seq, adapter->dump_data, adapter->dump_data_size);
@@ -3634,8 +3635,8 @@ static void handle_crq_init_rsp(struct work_struct *work)
 		}
 	}
 
-	send_version_xchg(adapter);
 	reinit_completion(&adapter->init_done);
+	send_version_xchg(adapter);
 	if (!wait_for_completion_timeout(&adapter->init_done, timeout)) {
 		dev_err(dev, "Passive init timeout\n");
 		goto task_failed;
@@ -3645,9 +3646,9 @@ static void handle_crq_init_rsp(struct work_struct *work)
 		if (adapter->renegotiate) {
 			adapter->renegotiate = false;
 			release_sub_crqs_no_irqs(adapter);
-			send_cap_queries(adapter);
 
 			reinit_completion(&adapter->init_done);
+			send_cap_queries(adapter);
 			if (!wait_for_completion_timeout(&adapter->init_done,
 							 timeout)) {
 				dev_err(dev, "Passive init timeout\n");
@@ -3661,9 +3662,7 @@ static void handle_crq_init_rsp(struct work_struct *work)
 		goto task_failed;
 
 	netdev->real_num_tx_queues = adapter->req_tx_queues;
-	netdev->mtu = adapter->req_mtu;
-	netdev->min_mtu = adapter->min_mtu;
-	netdev->max_mtu = adapter->max_mtu;
+	netdev->mtu = adapter->req_mtu - ETH_HLEN;
 
 	if (adapter->failover) {
 		adapter->failover = false;
@@ -3777,9 +3776,9 @@ static int ibmvnic_probe(struct vio_dev *dev, const struct vio_device_id *id)
 			adapter->debugfs_dump = ent;
 		}
 	}
-	ibmvnic_send_crq_init(adapter);
 
 	init_completion(&adapter->init_done);
+	ibmvnic_send_crq_init(adapter);
 	if (!wait_for_completion_timeout(&adapter->init_done, timeout))
 		return 0;
 
@@ -3787,9 +3786,9 @@ static int ibmvnic_probe(struct vio_dev *dev, const struct vio_device_id *id)
 		if (adapter->renegotiate) {
 			adapter->renegotiate = false;
 			release_sub_crqs_no_irqs(adapter);
-			send_cap_queries(adapter);
 
 			reinit_completion(&adapter->init_done);
+			send_cap_queries(adapter);
 			if (!wait_for_completion_timeout(&adapter->init_done,
 							 timeout))
 				return 0;
@@ -3803,7 +3802,7 @@ static int ibmvnic_probe(struct vio_dev *dev, const struct vio_device_id *id)
 	}
 
 	netdev->real_num_tx_queues = adapter->req_tx_queues;
-	netdev->mtu = adapter->req_mtu;
+	netdev->mtu = adapter->req_mtu - ETH_HLEN;
 
 	rc = register_netdev(netdev);
 	if (rc) {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index d87a82682cb5..44406a5ec15d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -1240,10 +1240,14 @@ int mlx5e_stats_flower(struct mlx5e_priv *priv,
 
 	mlx5_fc_query_cached(counter, &bytes, &packets, &lastuse);
 
+	preempt_disable();
+
 	tcf_exts_to_list(f->exts, &actions);
 	list_for_each_entry(a, &actions, list)
 		tcf_action_stats_update(a, bytes, packets, lastuse);
 
+	preempt_enable();
+
 	return 0;
 }
 
diff --git a/drivers/net/ethernet/ti/cpsw.c b/drivers/net/ethernet/ti/cpsw.c
index e86f226b258e..10f6f7496f50 100644
--- a/drivers/net/ethernet/ti/cpsw.c
+++ b/drivers/net/ethernet/ti/cpsw.c
@@ -3207,7 +3207,7 @@ static int cpsw_resume(struct device *dev)
 {
 	struct platform_device	*pdev = to_platform_device(dev);
 	struct net_device	*ndev = platform_get_drvdata(pdev);
-	struct cpsw_common	*cpsw = netdev_priv(ndev);
+	struct cpsw_common	*cpsw = ndev_to_cpsw(ndev);
 
 	/* Select default pin state */
 	pinctrl_pm_select_default_state(dev);
diff --git a/drivers/net/ethernet/xilinx/xilinx_emaclite.c b/drivers/net/ethernet/xilinx/xilinx_emaclite.c
index e3070fd88bce..69e31ceccfae 100644
--- a/drivers/net/ethernet/xilinx/xilinx_emaclite.c
+++ b/drivers/net/ethernet/xilinx/xilinx_emaclite.c
@@ -100,6 +100,14 @@
 /* BUFFER_ALIGN(adr) calculates the number of bytes to the next alignment. */
 #define BUFFER_ALIGN(adr) ((ALIGNMENT - ((u32) adr)) % ALIGNMENT)
 
+#ifdef __BIG_ENDIAN
+#define xemaclite_readl		ioread32be
+#define xemaclite_writel	iowrite32be
+#else
+#define xemaclite_readl		ioread32
+#define xemaclite_writel	iowrite32
+#endif
+
 /**
  * struct net_local - Our private per device data
  * @ndev:		instance of the network device
@@ -156,15 +164,15 @@ static void xemaclite_enable_interrupts(struct net_local *drvdata)
 	u32 reg_data;
 
 	/* Enable the Tx interrupts for the first Buffer */
-	reg_data = __raw_readl(drvdata->base_addr + XEL_TSR_OFFSET);
-	__raw_writel(reg_data | XEL_TSR_XMIT_IE_MASK,
-		     drvdata->base_addr + XEL_TSR_OFFSET);
+	reg_data = xemaclite_readl(drvdata->base_addr + XEL_TSR_OFFSET);
+	xemaclite_writel(reg_data | XEL_TSR_XMIT_IE_MASK,
+			 drvdata->base_addr + XEL_TSR_OFFSET);
 
 	/* Enable the Rx interrupts for the first buffer */
-	__raw_writel(XEL_RSR_RECV_IE_MASK, drvdata->base_addr + XEL_RSR_OFFSET);
+	xemaclite_writel(XEL_RSR_RECV_IE_MASK, drvdata->base_addr + XEL_RSR_OFFSET);
 
 	/* Enable the Global Interrupt Enable */
-	__raw_writel(XEL_GIER_GIE_MASK, drvdata->base_addr + XEL_GIER_OFFSET);
+	xemaclite_writel(XEL_GIER_GIE_MASK, drvdata->base_addr + XEL_GIER_OFFSET);
 }
 
 /**
@@ -179,17 +187,17 @@ static void xemaclite_disable_interrupts(struct net_local *drvdata)
 	u32 reg_data;
 
 	/* Disable the Global Interrupt Enable */
-	__raw_writel(XEL_GIER_GIE_MASK, drvdata->base_addr + XEL_GIER_OFFSET);
+	xemaclite_writel(XEL_GIER_GIE_MASK, drvdata->base_addr + XEL_GIER_OFFSET);
 
 	/* Disable the Tx interrupts for the first buffer */
-	reg_data = __raw_readl(drvdata->base_addr + XEL_TSR_OFFSET);
-	__raw_writel(reg_data & (~XEL_TSR_XMIT_IE_MASK),
-		     drvdata->base_addr + XEL_TSR_OFFSET);
+	reg_data = xemaclite_readl(drvdata->base_addr + XEL_TSR_OFFSET);
+	xemaclite_writel(reg_data & (~XEL_TSR_XMIT_IE_MASK),
+			 drvdata->base_addr + XEL_TSR_OFFSET);
 
 	/* Disable the Rx interrupts for the first buffer */
-	reg_data = __raw_readl(drvdata->base_addr + XEL_RSR_OFFSET);
-	__raw_writel(reg_data & (~XEL_RSR_RECV_IE_MASK),
-		     drvdata->base_addr + XEL_RSR_OFFSET);
+	reg_data = xemaclite_readl(drvdata->base_addr + XEL_RSR_OFFSET);
+	xemaclite_writel(reg_data & (~XEL_RSR_RECV_IE_MASK),
+			 drvdata->base_addr + XEL_RSR_OFFSET);
 }
 
 /**
@@ -321,7 +329,7 @@ static int xemaclite_send_data(struct net_local *drvdata, u8 *data,
 		byte_count = ETH_FRAME_LEN;
 
 	/* Check if the expected buffer is available */
-	reg_data = __raw_readl(addr + XEL_TSR_OFFSET);
+	reg_data = xemaclite_readl(addr + XEL_TSR_OFFSET);
 	if ((reg_data & (XEL_TSR_XMIT_BUSY_MASK |
 	     XEL_TSR_XMIT_ACTIVE_MASK)) == 0) {
 
@@ -334,7 +342,7 @@ static int xemaclite_send_data(struct net_local *drvdata, u8 *data,
 
 		addr = (void __iomem __force *)((u32 __force)addr ^
 						 XEL_BUFFER_OFFSET);
-		reg_data = __raw_readl(addr + XEL_TSR_OFFSET);
+		reg_data = xemaclite_readl(addr + XEL_TSR_OFFSET);
 
 		if ((reg_data & (XEL_TSR_XMIT_BUSY_MASK |
 		     XEL_TSR_XMIT_ACTIVE_MASK)) != 0)
@@ -345,16 +353,16 @@ static int xemaclite_send_data(struct net_local *drvdata, u8 *data,
 	/* Write the frame to the buffer */
 	xemaclite_aligned_write(data, (u32 __force *) addr, byte_count);
 
-	__raw_writel((byte_count & XEL_TPLR_LENGTH_MASK),
-		     addr + XEL_TPLR_OFFSET);
+	xemaclite_writel((byte_count & XEL_TPLR_LENGTH_MASK),
+			 addr + XEL_TPLR_OFFSET);
 
 	/* Update the Tx Status Register to indicate that there is a
 	 * frame to send. Set the XEL_TSR_XMIT_ACTIVE_MASK flag which
 	 * is used by the interrupt handler to check whether a frame
 	 * has been transmitted */
-	reg_data = __raw_readl(addr + XEL_TSR_OFFSET);
+	reg_data = xemaclite_readl(addr + XEL_TSR_OFFSET);
 	reg_data |= (XEL_TSR_XMIT_BUSY_MASK | XEL_TSR_XMIT_ACTIVE_MASK);
-	__raw_writel(reg_data, addr + XEL_TSR_OFFSET);
+	xemaclite_writel(reg_data, addr + XEL_TSR_OFFSET);
 
 	return 0;
 }
@@ -369,7 +377,7 @@ static int xemaclite_send_data(struct net_local *drvdata, u8 *data,
  *
  * Return:	Total number of bytes received
  */
-static u16 xemaclite_recv_data(struct net_local *drvdata, u8 *data)
+static u16 xemaclite_recv_data(struct net_local *drvdata, u8 *data, int maxlen)
 {
 	void __iomem *addr;
 	u16 length, proto_type;
@@ -379,7 +387,7 @@ static u16 xemaclite_recv_data(struct net_local *drvdata, u8 *data)
 	addr = (drvdata->base_addr + drvdata->next_rx_buf_to_use);
 
 	/* Verify which buffer has valid data */
-	reg_data = __raw_readl(addr + XEL_RSR_OFFSET);
+	reg_data = xemaclite_readl(addr + XEL_RSR_OFFSET);
 
 	if ((reg_data & XEL_RSR_RECV_DONE_MASK) == XEL_RSR_RECV_DONE_MASK) {
 		if (drvdata->rx_ping_pong != 0)
@@ -396,27 +404,28 @@ static u16 xemaclite_recv_data(struct net_local *drvdata, u8 *data)
 			return 0;	/* No data was available */
 
 		/* Verify that buffer has valid data */
-		reg_data = __raw_readl(addr + XEL_RSR_OFFSET);
+		reg_data = xemaclite_readl(addr + XEL_RSR_OFFSET);
 		if ((reg_data & XEL_RSR_RECV_DONE_MASK) !=
 		     XEL_RSR_RECV_DONE_MASK)
 			return 0;	/* No data was available */
 	}
 
 	/* Get the protocol type of the ethernet frame that arrived */
-	proto_type = ((ntohl(__raw_readl(addr + XEL_HEADER_OFFSET +
+	proto_type = ((ntohl(xemaclite_readl(addr + XEL_HEADER_OFFSET +
 			XEL_RXBUFF_OFFSET)) >> XEL_HEADER_SHIFT) &
 			XEL_RPLR_LENGTH_MASK);
 
 	/* Check if received ethernet frame is a raw ethernet frame
 	 * or an IP packet or an ARP packet */
-	if (proto_type > (ETH_FRAME_LEN + ETH_FCS_LEN)) {
+	if (proto_type > ETH_DATA_LEN) {
 
 		if (proto_type == ETH_P_IP) {
-			length = ((ntohl(__raw_readl(addr +
+			length = ((ntohl(xemaclite_readl(addr +
 					XEL_HEADER_IP_LENGTH_OFFSET +
 					XEL_RXBUFF_OFFSET)) >>
 					XEL_HEADER_SHIFT) &
 					XEL_RPLR_LENGTH_MASK);
+			length = min_t(u16, length, ETH_DATA_LEN);
 			length += ETH_HLEN + ETH_FCS_LEN;
 
 		} else if (proto_type == ETH_P_ARP)
@@ -429,14 +438,17 @@ static u16 xemaclite_recv_data(struct net_local *drvdata, u8 *data)
 		/* Use the length in the frame, plus the header and trailer */
 		length = proto_type + ETH_HLEN + ETH_FCS_LEN;
 
+	if (WARN_ON(length > maxlen))
+		length = maxlen;
+
 	/* Read from the EmacLite device */
 	xemaclite_aligned_read((u32 __force *) (addr + XEL_RXBUFF_OFFSET),
 				data, length);
 
 	/* Acknowledge the frame */
-	reg_data = __raw_readl(addr + XEL_RSR_OFFSET);
+	reg_data = xemaclite_readl(addr + XEL_RSR_OFFSET);
 	reg_data &= ~XEL_RSR_RECV_DONE_MASK;
-	__raw_writel(reg_data, addr + XEL_RSR_OFFSET);
+	xemaclite_writel(reg_data, addr + XEL_RSR_OFFSET);
 
 	return length;
 }
@@ -463,14 +475,14 @@ static void xemaclite_update_address(struct net_local *drvdata,
 
 	xemaclite_aligned_write(address_ptr, (u32 __force *) addr, ETH_ALEN);
 
-	__raw_writel(ETH_ALEN, addr + XEL_TPLR_OFFSET);
+	xemaclite_writel(ETH_ALEN, addr + XEL_TPLR_OFFSET);
 
 	/* Update the MAC address in the EmacLite */
-	reg_data = __raw_readl(addr + XEL_TSR_OFFSET);
-	__raw_writel(reg_data | XEL_TSR_PROG_MAC_ADDR, addr + XEL_TSR_OFFSET);
+	reg_data = xemaclite_readl(addr + XEL_TSR_OFFSET);
+	xemaclite_writel(reg_data | XEL_TSR_PROG_MAC_ADDR, addr + XEL_TSR_OFFSET);
 
 	/* Wait for EmacLite to finish with the MAC address update */
-	while ((__raw_readl(addr + XEL_TSR_OFFSET) &
+	while ((xemaclite_readl(addr + XEL_TSR_OFFSET) &
 		XEL_TSR_PROG_MAC_ADDR) != 0)
 		;
 }
@@ -603,7 +615,7 @@ static void xemaclite_rx_handler(struct net_device *dev)
 
 	skb_reserve(skb, 2);
 
-	len = xemaclite_recv_data(lp, (u8 *) skb->data);
+	len = xemaclite_recv_data(lp, (u8 *) skb->data, len);
 
 	if (!len) {
 		dev->stats.rx_errors++;
@@ -640,32 +652,32 @@ static irqreturn_t xemaclite_interrupt(int irq, void *dev_id)
 	u32 tx_status;
 
 	/* Check if there is Rx Data available */
-	if ((__raw_readl(base_addr + XEL_RSR_OFFSET) &
+	if ((xemaclite_readl(base_addr + XEL_RSR_OFFSET) &
 			 XEL_RSR_RECV_DONE_MASK) ||
-	    (__raw_readl(base_addr + XEL_BUFFER_OFFSET + XEL_RSR_OFFSET)
+	    (xemaclite_readl(base_addr + XEL_BUFFER_OFFSET + XEL_RSR_OFFSET)
 			 & XEL_RSR_RECV_DONE_MASK))
 
 		xemaclite_rx_handler(dev);
 
 	/* Check if the Transmission for the first buffer is completed */
-	tx_status = __raw_readl(base_addr + XEL_TSR_OFFSET);
+	tx_status = xemaclite_readl(base_addr + XEL_TSR_OFFSET);
 	if (((tx_status & XEL_TSR_XMIT_BUSY_MASK) == 0) &&
 		(tx_status & XEL_TSR_XMIT_ACTIVE_MASK) != 0) {
 
 		tx_status &= ~XEL_TSR_XMIT_ACTIVE_MASK;
-		__raw_writel(tx_status, base_addr + XEL_TSR_OFFSET);
+		xemaclite_writel(tx_status, base_addr + XEL_TSR_OFFSET);
 
 		tx_complete = true;
 	}
 
 	/* Check if the Transmission for the second buffer is completed */
-	tx_status = __raw_readl(base_addr + XEL_BUFFER_OFFSET + XEL_TSR_OFFSET);
+	tx_status = xemaclite_readl(base_addr + XEL_BUFFER_OFFSET + XEL_TSR_OFFSET);
 	if (((tx_status & XEL_TSR_XMIT_BUSY_MASK) == 0) &&
 		(tx_status & XEL_TSR_XMIT_ACTIVE_MASK) != 0) {
 
 		tx_status &= ~XEL_TSR_XMIT_ACTIVE_MASK;
-		__raw_writel(tx_status, base_addr + XEL_BUFFER_OFFSET +
-			     XEL_TSR_OFFSET);
+		xemaclite_writel(tx_status, base_addr + XEL_BUFFER_OFFSET +
+				 XEL_TSR_OFFSET);
 
 		tx_complete = true;
 	}
@@ -698,7 +710,7 @@ static int xemaclite_mdio_wait(struct net_local *lp)
 	/* wait for the MDIO interface to not be busy or timeout
 	   after some time.
 	*/
-	while (__raw_readl(lp->base_addr + XEL_MDIOCTRL_OFFSET) &
+	while (xemaclite_readl(lp->base_addr + XEL_MDIOCTRL_OFFSET) &
 			XEL_MDIOCTRL_MDIOSTS_MASK) {
 		if (time_before_eq(end, jiffies)) {
 			WARN_ON(1);
@@ -734,17 +746,17 @@ static int xemaclite_mdio_read(struct mii_bus *bus, int phy_id, int reg)
 	 * MDIO Address register. Set the Status bit in the MDIO Control
 	 * register to start a MDIO read transaction.
 	 */
-	ctrl_reg = __raw_readl(lp->base_addr + XEL_MDIOCTRL_OFFSET);
-	__raw_writel(XEL_MDIOADDR_OP_MASK |
-		     ((phy_id << XEL_MDIOADDR_PHYADR_SHIFT) | reg),
-		     lp->base_addr + XEL_MDIOADDR_OFFSET);
-	__raw_writel(ctrl_reg | XEL_MDIOCTRL_MDIOSTS_MASK,
-		     lp->base_addr + XEL_MDIOCTRL_OFFSET);
+	ctrl_reg = xemaclite_readl(lp->base_addr + XEL_MDIOCTRL_OFFSET);
+	xemaclite_writel(XEL_MDIOADDR_OP_MASK |
+			 ((phy_id << XEL_MDIOADDR_PHYADR_SHIFT) | reg),
+			 lp->base_addr + XEL_MDIOADDR_OFFSET);
+	xemaclite_writel(ctrl_reg | XEL_MDIOCTRL_MDIOSTS_MASK,
+			 lp->base_addr + XEL_MDIOCTRL_OFFSET);
 
 	if (xemaclite_mdio_wait(lp))
 		return -ETIMEDOUT;
 
-	rc = __raw_readl(lp->base_addr + XEL_MDIORD_OFFSET);
+	rc = xemaclite_readl(lp->base_addr + XEL_MDIORD_OFFSET);
 
 	dev_dbg(&lp->ndev->dev,
 		"xemaclite_mdio_read(phy_id=%i, reg=%x) == %x\n",
@@ -781,13 +793,13 @@ static int xemaclite_mdio_write(struct mii_bus *bus, int phy_id, int reg,
 	 * Data register. Finally, set the Status bit in the MDIO Control
 	 * register to start a MDIO write transaction.
 	 */
-	ctrl_reg = __raw_readl(lp->base_addr + XEL_MDIOCTRL_OFFSET);
-	__raw_writel(~XEL_MDIOADDR_OP_MASK &
-		     ((phy_id << XEL_MDIOADDR_PHYADR_SHIFT) | reg),
-		     lp->base_addr + XEL_MDIOADDR_OFFSET);
-	__raw_writel(val, lp->base_addr + XEL_MDIOWR_OFFSET);
-	__raw_writel(ctrl_reg | XEL_MDIOCTRL_MDIOSTS_MASK,
-		     lp->base_addr + XEL_MDIOCTRL_OFFSET);
+	ctrl_reg = xemaclite_readl(lp->base_addr + XEL_MDIOCTRL_OFFSET);
+	xemaclite_writel(~XEL_MDIOADDR_OP_MASK &
+			 ((phy_id << XEL_MDIOADDR_PHYADR_SHIFT) | reg),
+			 lp->base_addr + XEL_MDIOADDR_OFFSET);
+	xemaclite_writel(val, lp->base_addr + XEL_MDIOWR_OFFSET);
+	xemaclite_writel(ctrl_reg | XEL_MDIOCTRL_MDIOSTS_MASK,
+			 lp->base_addr + XEL_MDIOCTRL_OFFSET);
 
 	return 0;
 }
@@ -834,8 +846,8 @@ static int xemaclite_mdio_setup(struct net_local *lp, struct device *dev)
 	/* Enable the MDIO bus by asserting the enable bit in MDIO Control
 	 * register.
 	 */
-	__raw_writel(XEL_MDIOCTRL_MDIOEN_MASK,
-		     lp->base_addr + XEL_MDIOCTRL_OFFSET);
+	xemaclite_writel(XEL_MDIOCTRL_MDIOEN_MASK,
+			 lp->base_addr + XEL_MDIOCTRL_OFFSET);
 
 	bus = mdiobus_alloc();
 	if (!bus) {
@@ -1126,8 +1138,8 @@ static int xemaclite_of_probe(struct platform_device *ofdev)
 	}
 
 	/* Clear the Tx CSR's in case this is a restart */
-	__raw_writel(0, lp->base_addr + XEL_TSR_OFFSET);
-	__raw_writel(0, lp->base_addr + XEL_BUFFER_OFFSET + XEL_TSR_OFFSET);
+	xemaclite_writel(0, lp->base_addr + XEL_TSR_OFFSET);
+	xemaclite_writel(0, lp->base_addr + XEL_BUFFER_OFFSET + XEL_TSR_OFFSET);
 
 	/* Set the MAC address in the EmacLite device */
 	xemaclite_update_address(lp, ndev->dev_addr);
diff --git a/drivers/net/xen-netback/common.h b/drivers/net/xen-netback/common.h
index 3ce1f7da8647..530586be05b4 100644
--- a/drivers/net/xen-netback/common.h
+++ b/drivers/net/xen-netback/common.h
@@ -113,10 +113,10 @@ struct xenvif_stats {
 	 * A subset of struct net_device_stats that contains only the
 	 * fields that are updated in netback.c for each queue.
 	 */
-	unsigned int rx_bytes;
-	unsigned int rx_packets;
-	unsigned int tx_bytes;
-	unsigned int tx_packets;
+	u64 rx_bytes;
+	u64 rx_packets;
+	u64 tx_bytes;
+	u64 tx_packets;
 
 	/* Additional stats used by xenvif */
 	unsigned long rx_gso_checksum_fixup;
diff --git a/drivers/net/xen-netback/interface.c b/drivers/net/xen-netback/interface.c
index 1073b27e54aa..a2d326760a72 100644
--- a/drivers/net/xen-netback/interface.c
+++ b/drivers/net/xen-netback/interface.c
@@ -221,10 +221,10 @@ static struct net_device_stats *xenvif_get_stats(struct net_device *dev)
 {
 	struct xenvif *vif = netdev_priv(dev);
 	struct xenvif_queue *queue = NULL;
-	unsigned long rx_bytes = 0;
-	unsigned long rx_packets = 0;
-	unsigned long tx_bytes = 0;
-	unsigned long tx_packets = 0;
+	u64 rx_bytes = 0;
+	u64 rx_packets = 0;
+	u64 tx_bytes = 0;
+	u64 tx_packets = 0;
 	unsigned int index;
 
 	spin_lock(&vif->lock);
diff --git a/drivers/pci/pcie/pme.c b/drivers/pci/pcie/pme.c
index 717529331dac..2dd1c68e6de8 100644
--- a/drivers/pci/pcie/pme.c
+++ b/drivers/pci/pcie/pme.c
@@ -433,6 +433,17 @@ static int pcie_pme_resume(struct pcie_device *srv)
 	return 0;
 }
 
+/**
+ * pcie_pme_remove - Prepare PCIe PME service device for removal.
+ * @srv - PCIe service device to remove.
+ */
+static void pcie_pme_remove(struct pcie_device *srv)
+{
+	pcie_pme_suspend(srv);
+	free_irq(srv->irq, srv);
+	kfree(get_service_data(srv));
+}
+
 static struct pcie_port_service_driver pcie_pme_driver = {
 	.name		= "pcie_pme",
 	.port_type	= PCI_EXP_TYPE_ROOT_PORT,
@@ -441,6 +452,7 @@ static struct pcie_port_service_driver pcie_pme_driver = {
 	.probe		= pcie_pme_probe,
 	.suspend	= pcie_pme_suspend,
 	.resume		= pcie_pme_resume,
+	.remove		= pcie_pme_remove,
 };
 
 /**
diff --git a/drivers/s390/scsi/zfcp_fsf.c b/drivers/s390/scsi/zfcp_fsf.c
index 75f820ca17b7..27ff38f839fc 100644
--- a/drivers/s390/scsi/zfcp_fsf.c
+++ b/drivers/s390/scsi/zfcp_fsf.c
@@ -1583,7 +1583,7 @@ out:
 int zfcp_fsf_open_wka_port(struct zfcp_fc_wka_port *wka_port)
 {
 	struct zfcp_qdio *qdio = wka_port->adapter->qdio;
-	struct zfcp_fsf_req *req = NULL;
+	struct zfcp_fsf_req *req;
 	int retval = -EIO;
 
 	spin_lock_irq(&qdio->req_q_lock);
@@ -1612,7 +1612,7 @@ int zfcp_fsf_open_wka_port(struct zfcp_fc_wka_port *wka_port)
 		zfcp_fsf_req_free(req);
 out:
 	spin_unlock_irq(&qdio->req_q_lock);
-	if (req && !IS_ERR(req))
+	if (!retval)
 		zfcp_dbf_rec_run_wka("fsowp_1", wka_port, req->req_id);
 	return retval;
 }
@@ -1638,7 +1638,7 @@ static void zfcp_fsf_close_wka_port_handler(struct zfcp_fsf_req *req)
 int zfcp_fsf_close_wka_port(struct zfcp_fc_wka_port *wka_port)
 {
 	struct zfcp_qdio *qdio = wka_port->adapter->qdio;
-	struct zfcp_fsf_req *req = NULL;
+	struct zfcp_fsf_req *req;
 	int retval = -EIO;
 
 	spin_lock_irq(&qdio->req_q_lock);
@@ -1667,7 +1667,7 @@ int zfcp_fsf_close_wka_port(struct zfcp_fc_wka_port *wka_port)
 		zfcp_fsf_req_free(req);
 out:
 	spin_unlock_irq(&qdio->req_q_lock);
-	if (req && !IS_ERR(req))
+	if (!retval)
 		zfcp_dbf_rec_run_wka("fscwp_1", wka_port, req->req_id);
 	return retval;
 }
diff --git a/drivers/scsi/aacraid/comminit.c b/drivers/scsi/aacraid/comminit.c
index 4f56b1003cc7..5b48bedd7c38 100644
--- a/drivers/scsi/aacraid/comminit.c
+++ b/drivers/scsi/aacraid/comminit.c
@@ -50,9 +50,13 @@ struct aac_common aac_config = {
 
 static inline int aac_is_msix_mode(struct aac_dev *dev)
 {
-	u32 status;
+	u32 status = 0;
 
-	status = src_readl(dev, MUnit.OMR);
+	if (dev->pdev->device == PMC_DEVICE_S6 ||
+		dev->pdev->device == PMC_DEVICE_S7 ||
+		dev->pdev->device == PMC_DEVICE_S8) {
+		status = src_readl(dev, MUnit.OMR);
+	}
 	return (status & AAC_INT_MODE_MSIX);
 }
 
diff --git a/drivers/scsi/mpt3sas/mpt3sas_scsih.c b/drivers/scsi/mpt3sas/mpt3sas_scsih.c
index 75f3fce1c867..0b5b423b1db0 100644
--- a/drivers/scsi/mpt3sas/mpt3sas_scsih.c
+++ b/drivers/scsi/mpt3sas/mpt3sas_scsih.c
@@ -51,6 +51,7 @@
 #include <linux/workqueue.h>
 #include <linux/delay.h>
 #include <linux/pci.h>
+#include <linux/pci-aspm.h>
 #include <linux/interrupt.h>
 #include <linux/aer.h>
 #include <linux/raid_class.h>
@@ -4657,6 +4658,7 @@ _scsih_io_done(struct MPT3SAS_ADAPTER *ioc, u16 smid, u8 msix_index, u32 reply)
 	struct MPT3SAS_DEVICE *sas_device_priv_data;
 	u32 response_code = 0;
 	unsigned long flags;
+	unsigned int sector_sz;
 
 	mpi_reply = mpt3sas_base_get_reply_virt_addr(ioc, reply);
 	scmd = _scsih_scsi_lookup_get_clear(ioc, smid);
@@ -4715,6 +4717,20 @@ _scsih_io_done(struct MPT3SAS_ADAPTER *ioc, u16 smid, u8 msix_index, u32 reply)
 	}
 
 	xfer_cnt = le32_to_cpu(mpi_reply->TransferCount);
+
+	/* In case of bogus fw or device, we could end up having
+	 * unaligned partial completion. We can force alignment here,
+	 * then scsi-ml does not need to handle this misbehavior.
+	 */
+	sector_sz = scmd->device->sector_size;
+	if (unlikely(scmd->request->cmd_type == REQ_TYPE_FS && sector_sz &&
+		     xfer_cnt % sector_sz)) {
+		sdev_printk(KERN_INFO, scmd->device,
+		    "unaligned partial completion avoided (xfer_cnt=%u, sector_sz=%u)\n",
+			    xfer_cnt, sector_sz);
+		xfer_cnt = round_down(xfer_cnt, sector_sz);
+	}
+
 	scsi_set_resid(scmd, scsi_bufflen(scmd) - xfer_cnt);
 	if (ioc_status & MPI2_IOCSTATUS_FLAG_LOG_INFO_AVAILABLE)
 		log_info =  le32_to_cpu(mpi_reply->IOCLogInfo);
@@ -8746,6 +8762,8 @@ _scsih_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 
 	switch (hba_mpi_version) {
 	case MPI2_VERSION:
+		pci_disable_link_state(pdev, PCIE_LINK_STATE_L0S |
+			PCIE_LINK_STATE_L1 | PCIE_LINK_STATE_CLKPM);
 		/* Use mpt2sas driver host template for SAS 2.0 HBA's */
 		shost = scsi_host_alloc(&mpt2sas_driver_template,
 		  sizeof(struct MPT3SAS_ADAPTER));
diff --git a/drivers/scsi/qla2xxx/qla_isr.c b/drivers/scsi/qla2xxx/qla_isr.c
index dc88a09f9043..a94b0b6bd030 100644
--- a/drivers/scsi/qla2xxx/qla_isr.c
+++ b/drivers/scsi/qla2xxx/qla_isr.c
@@ -3242,7 +3242,7 @@ qla2x00_free_irqs(scsi_qla_host_t *vha)
 	 * from a probe failure context.
 	 */
 	if (!ha->rsp_q_map || !ha->rsp_q_map[0])
-		return;
+		goto free_irqs;
 	rsp = ha->rsp_q_map[0];
 
 	if (ha->flags.msix_enabled) {
@@ -3262,6 +3262,7 @@ qla2x00_free_irqs(scsi_qla_host_t *vha)
 		free_irq(pci_irq_vector(ha->pdev, 0), rsp);
 	}
 
+free_irqs:
 	pci_free_irq_vectors(ha->pdev);
 }
 
diff --git a/drivers/scsi/qla2xxx/qla_os.c b/drivers/scsi/qla2xxx/qla_os.c
index 0a000ecf0881..40660461a4b5 100644
--- a/drivers/scsi/qla2xxx/qla_os.c
+++ b/drivers/scsi/qla2xxx/qla_os.c
@@ -1616,7 +1616,7 @@ qla2x00_abort_all_cmds(scsi_qla_host_t *vha, int res)
 				/* Don't abort commands in adapter during EEH
 				 * recovery as it's not accessible/responding.
 				 */
-				if (!ha->flags.eeh_busy) {
+				if (GET_CMD_SP(sp) && !ha->flags.eeh_busy) {
 					/* Get a reference to the sp and drop the lock.
 					 * The reference ensures this sp->done() call
 					 * - and not the call in qla2xxx_eh_abort() -
diff --git a/fs/btrfs/compression.c b/fs/btrfs/compression.c
index 7f390849343b..c4444d6f439f 100644
--- a/fs/btrfs/compression.c
+++ b/fs/btrfs/compression.c
@@ -1024,6 +1024,7 @@ int btrfs_decompress_buf2page(char *buf, unsigned long buf_start,
 	unsigned long buf_offset;
 	unsigned long current_buf_start;
 	unsigned long start_byte;
+	unsigned long prev_start_byte;
 	unsigned long working_bytes = total_out - buf_start;
 	unsigned long bytes;
 	char *kaddr;
@@ -1071,26 +1072,34 @@ int btrfs_decompress_buf2page(char *buf, unsigned long buf_start,
 		if (!bio->bi_iter.bi_size)
 			return 0;
 		bvec = bio_iter_iovec(bio, bio->bi_iter);
-
+		prev_start_byte = start_byte;
 		start_byte = page_offset(bvec.bv_page) - disk_start;
 
 		/*
-		 * make sure our new page is covered by this
-		 * working buffer
+		 * We need to make sure we're only adjusting
+		 * our offset into compression working buffer when
+		 * we're switching pages.  Otherwise we can incorrectly
+		 * keep copying when we were actually done.
 		 */
-		if (total_out <= start_byte)
-			return 1;
+		if (start_byte != prev_start_byte) {
+			/*
+			 * make sure our new page is covered by this
+			 * working buffer
+			 */
+			if (total_out <= start_byte)
+				return 1;
 
-		/*
-		 * the next page in the biovec might not be adjacent
-		 * to the last page, but it might still be found
-		 * inside this working buffer. bump our offset pointer
-		 */
-		if (total_out > start_byte &&
-		    current_buf_start < start_byte) {
-			buf_offset = start_byte - buf_start;
-			working_bytes = total_out - start_byte;
-			current_buf_start = buf_start + buf_offset;
+			/*
+			 * the next page in the biovec might not be adjacent
+			 * to the last page, but it might still be found
+			 * inside this working buffer. bump our offset pointer
+			 */
+			if (total_out > start_byte &&
+			    current_buf_start < start_byte) {
+				buf_offset = start_byte - buf_start;
+				working_bytes = total_out - start_byte;
+				current_buf_start = buf_start + buf_offset;
+			}
 		}
 	}
 
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index 33f967d30b2a..21e51b0ba188 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -5653,6 +5653,10 @@ long btrfs_ioctl(struct file *file, unsigned int
 #ifdef CONFIG_COMPAT
 long btrfs_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 {
+	/*
+	 * These all access 32-bit values anyway so no further
+	 * handling is necessary.
+	 */
 	switch (cmd) {
 	case FS_IOC32_GETFLAGS:
 		cmd = FS_IOC_GETFLAGS;
@@ -5663,8 +5667,6 @@ long btrfs_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 	case FS_IOC32_GETVERSION:
 		cmd = FS_IOC_GETVERSION;
 		break;
-	default:
-		return -ENOIOCTLCMD;
 	}
 
 	return btrfs_ioctl(file, cmd, (unsigned long) compat_ptr(arg));
diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c
index 4e06a27ed7f8..f11792672977 100644
--- a/fs/fuse/dev.c
+++ b/fs/fuse/dev.c
@@ -399,6 +399,10 @@ static void request_end(struct fuse_conn *fc, struct fuse_req *req)
 static void queue_interrupt(struct fuse_iqueue *fiq, struct fuse_req *req)
 {
 	spin_lock(&fiq->waitq.lock);
+	if (test_bit(FR_FINISHED, &req->flags)) {
+		spin_unlock(&fiq->waitq.lock);
+		return;
+	}
 	if (list_empty(&req->intr_entry)) {
 		list_add_tail(&req->intr_entry, &fiq->interrupts);
 		wake_up_locked(&fiq->waitq);
@@ -1372,6 +1376,7 @@ static ssize_t fuse_dev_splice_read(struct file *in, loff_t *ppos,
 		 * code can Oops if the buffer persists after module unload.
 		 */
 		bufs[page_nr].ops = &nosteal_pipe_buf_ops;
+		bufs[page_nr].flags = 0;
 		ret = add_to_pipe(pipe, &bufs[page_nr++]);
 		if (unlikely(ret < 0))
 			break;
diff --git a/fs/splice.c b/fs/splice.c
index 873d83104e79..4ef78aa8ef61 100644
--- a/fs/splice.c
+++ b/fs/splice.c
@@ -204,6 +204,7 @@ ssize_t splice_to_pipe(struct pipe_inode_info *pipe,
 		buf->len = spd->partial[page_nr].len;
 		buf->private = spd->partial[page_nr].private;
 		buf->ops = spd->ops;
+		buf->flags = 0;
 
 		pipe->nrbufs++;
 		page_nr++;
diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h
index 92bc89ae7e20..c970a25d2a49 100644
--- a/include/linux/bpf-cgroup.h
+++ b/include/linux/bpf-cgroup.h
@@ -21,20 +21,19 @@ struct cgroup_bpf {
 	 */
 	struct bpf_prog *prog[MAX_BPF_ATTACH_TYPE];
 	struct bpf_prog __rcu *effective[MAX_BPF_ATTACH_TYPE];
+	bool disallow_override[MAX_BPF_ATTACH_TYPE];
 };
 
 void cgroup_bpf_put(struct cgroup *cgrp);
 void cgroup_bpf_inherit(struct cgroup *cgrp, struct cgroup *parent);
 
-void __cgroup_bpf_update(struct cgroup *cgrp,
-			 struct cgroup *parent,
-			 struct bpf_prog *prog,
-			 enum bpf_attach_type type);
+int __cgroup_bpf_update(struct cgroup *cgrp, struct cgroup *parent,
+			struct bpf_prog *prog, enum bpf_attach_type type,
+			bool overridable);
 
 /* Wrapper for __cgroup_bpf_update() protected by cgroup_mutex */
-void cgroup_bpf_update(struct cgroup *cgrp,
-		       struct bpf_prog *prog,
-		       enum bpf_attach_type type);
+int cgroup_bpf_update(struct cgroup *cgrp, struct bpf_prog *prog,
+		      enum bpf_attach_type type, bool overridable);
 
 int __cgroup_bpf_run_filter_skb(struct sock *sk,
 				struct sk_buff *skb,
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index e07fd5a324e6..0539a0ceef38 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -123,6 +123,12 @@ enum bpf_attach_type {
 
 #define MAX_BPF_ATTACH_TYPE __MAX_BPF_ATTACH_TYPE
 
+/* If BPF_F_ALLOW_OVERRIDE flag is used in BPF_PROG_ATTACH command
+ * to the given target_fd cgroup the descendent cgroup will be able to
+ * override effective bpf program that was inherited from this cgroup
+ */
+#define BPF_F_ALLOW_OVERRIDE	(1U << 0)
+
 #define BPF_PSEUDO_MAP_FD	1
 
 /* flags for BPF_MAP_UPDATE_ELEM command */
@@ -178,6 +184,7 @@ union bpf_attr {
 		__u32		target_fd;	/* container object to attach to */
 		__u32		attach_bpf_fd;	/* eBPF program to attach */
 		__u32		attach_type;
+		__u32		attach_flags;
 	};
 } __attribute__((aligned(8)));
 
diff --git a/include/uapi/linux/l2tp.h b/include/uapi/linux/l2tp.h
index 85ddb74fcd1c..b23c1914a182 100644
--- a/include/uapi/linux/l2tp.h
+++ b/include/uapi/linux/l2tp.h
@@ -9,9 +9,8 @@
 
 #include <linux/types.h>
 #include <linux/socket.h>
-#ifndef __KERNEL__
-#include <netinet/in.h>
-#endif
+#include <linux/in.h>
+#include <linux/in6.h>
 
 #define IPPROTO_L2TP		115
 
@@ -31,7 +30,7 @@ struct sockaddr_l2tpip {
 	__u32		l2tp_conn_id;	/* Connection ID of tunnel */
 
 	/* Pad to size of `struct sockaddr'. */
-	unsigned char	__pad[sizeof(struct sockaddr) -
+	unsigned char	__pad[__SOCK_SIZE__ -
 			      sizeof(__kernel_sa_family_t) -
 			      sizeof(__be16) - sizeof(struct in_addr) -
 			      sizeof(__u32)];
diff --git a/include/uapi/linux/videodev2.h b/include/uapi/linux/videodev2.h
index 46e8a2e369f9..45184a2ef66c 100644
--- a/include/uapi/linux/videodev2.h
+++ b/include/uapi/linux/videodev2.h
@@ -362,8 +362,8 @@ enum v4l2_quantization {
 	/*
 	 * The default for R'G'B' quantization is always full range, except
 	 * for the BT2020 colorspace. For Y'CbCr the quantization is always
-	 * limited range, except for COLORSPACE_JPEG, SRGB, ADOBERGB,
-	 * XV601 or XV709: those are full range.
+	 * limited range, except for COLORSPACE_JPEG, XV601 or XV709: those
+	 * are full range.
 	 */
 	V4L2_QUANTIZATION_DEFAULT     = 0,
 	V4L2_QUANTIZATION_FULL_RANGE  = 1,
@@ -379,8 +379,7 @@ enum v4l2_quantization {
 	(((is_rgb_or_hsv) && (colsp) == V4L2_COLORSPACE_BT2020) ? \
 	 V4L2_QUANTIZATION_LIM_RANGE : \
 	 (((is_rgb_or_hsv) || (ycbcr_enc) == V4L2_YCBCR_ENC_XV601 || \
-	  (ycbcr_enc) == V4L2_YCBCR_ENC_XV709 || (colsp) == V4L2_COLORSPACE_JPEG) || \
-	  (colsp) == V4L2_COLORSPACE_ADOBERGB || (colsp) == V4L2_COLORSPACE_SRGB ? \
+	  (ycbcr_enc) == V4L2_YCBCR_ENC_XV709 || (colsp) == V4L2_COLORSPACE_JPEG) ? \
 	 V4L2_QUANTIZATION_FULL_RANGE : V4L2_QUANTIZATION_LIM_RANGE))
 
 enum v4l2_priority {
diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c
index a515f7b007c6..da0f53690295 100644
--- a/kernel/bpf/cgroup.c
+++ b/kernel/bpf/cgroup.c
@@ -52,6 +52,7 @@ void cgroup_bpf_inherit(struct cgroup *cgrp, struct cgroup *parent)
 		e = rcu_dereference_protected(parent->bpf.effective[type],
 					      lockdep_is_held(&cgroup_mutex));
 		rcu_assign_pointer(cgrp->bpf.effective[type], e);
+		cgrp->bpf.disallow_override[type] = parent->bpf.disallow_override[type];
 	}
 }
 
@@ -82,30 +83,63 @@ void cgroup_bpf_inherit(struct cgroup *cgrp, struct cgroup *parent)
  *
  * Must be called with cgroup_mutex held.
  */
-void __cgroup_bpf_update(struct cgroup *cgrp,
-			 struct cgroup *parent,
-			 struct bpf_prog *prog,
-			 enum bpf_attach_type type)
+int __cgroup_bpf_update(struct cgroup *cgrp, struct cgroup *parent,
+			struct bpf_prog *prog, enum bpf_attach_type type,
+			bool new_overridable)
 {
-	struct bpf_prog *old_prog, *effective;
+	struct bpf_prog *old_prog, *effective = NULL;
 	struct cgroup_subsys_state *pos;
+	bool overridable = true;
 
-	old_prog = xchg(cgrp->bpf.prog + type, prog);
+	if (parent) {
+		overridable = !parent->bpf.disallow_override[type];
+		effective = rcu_dereference_protected(parent->bpf.effective[type],
+						      lockdep_is_held(&cgroup_mutex));
+	}
+
+	if (prog && effective && !overridable)
+		/* if parent has non-overridable prog attached, disallow
+		 * attaching new programs to descendent cgroup
+		 */
+		return -EPERM;
+
+	if (prog && effective && overridable != new_overridable)
+		/* if parent has overridable prog attached, only
+		 * allow overridable programs in descendent cgroup
+		 */
+		return -EPERM;
 
-	effective = (!prog && parent) ?
-		rcu_dereference_protected(parent->bpf.effective[type],
-					  lockdep_is_held(&cgroup_mutex)) :
-		prog;
+	old_prog = cgrp->bpf.prog[type];
+
+	if (prog) {
+		overridable = new_overridable;
+		effective = prog;
+		if (old_prog &&
+		    cgrp->bpf.disallow_override[type] == new_overridable)
+			/* disallow attaching non-overridable on top
+			 * of existing overridable in this cgroup
+			 * and vice versa
+			 */
+			return -EPERM;
+	}
+
+	if (!prog && !old_prog)
+		/* report error when trying to detach and nothing is attached */
+		return -ENOENT;
+
+	cgrp->bpf.prog[type] = prog;
 
 	css_for_each_descendant_pre(pos, &cgrp->self) {
 		struct cgroup *desc = container_of(pos, struct cgroup, self);
 
 		/* skip the subtree if the descendant has its own program */
-		if (desc->bpf.prog[type] && desc != cgrp)
+		if (desc->bpf.prog[type] && desc != cgrp) {
 			pos = css_rightmost_descendant(pos);
-		else
+		} else {
 			rcu_assign_pointer(desc->bpf.effective[type],
 					   effective);
+			desc->bpf.disallow_override[type] = !overridable;
+		}
 	}
 
 	if (prog)
@@ -115,6 +149,7 @@ void __cgroup_bpf_update(struct cgroup *cgrp,
 		bpf_prog_put(old_prog);
 		static_branch_dec(&cgroup_bpf_enabled_key);
 	}
+	return 0;
 }
 
 /**
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 08a4d287226b..f74ca17af64a 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -935,13 +935,14 @@ static int bpf_obj_get(const union bpf_attr *attr)
 
 #ifdef CONFIG_CGROUP_BPF
 
-#define BPF_PROG_ATTACH_LAST_FIELD attach_type
+#define BPF_PROG_ATTACH_LAST_FIELD attach_flags
 
 static int bpf_prog_attach(const union bpf_attr *attr)
 {
+	enum bpf_prog_type ptype;
 	struct bpf_prog *prog;
 	struct cgroup *cgrp;
-	enum bpf_prog_type ptype;
+	int ret;
 
 	if (!capable(CAP_NET_ADMIN))
 		return -EPERM;
@@ -949,6 +950,9 @@ static int bpf_prog_attach(const union bpf_attr *attr)
 	if (CHECK_ATTR(BPF_PROG_ATTACH))
 		return -EINVAL;
 
+	if (attr->attach_flags & ~BPF_F_ALLOW_OVERRIDE)
+		return -EINVAL;
+
 	switch (attr->attach_type) {
 	case BPF_CGROUP_INET_INGRESS:
 	case BPF_CGROUP_INET_EGRESS:
@@ -971,10 +975,13 @@ static int bpf_prog_attach(const union bpf_attr *attr)
 		return PTR_ERR(cgrp);
 	}
 
-	cgroup_bpf_update(cgrp, prog, attr->attach_type);
+	ret = cgroup_bpf_update(cgrp, prog, attr->attach_type,
+				attr->attach_flags & BPF_F_ALLOW_OVERRIDE);
+	if (ret)
+		bpf_prog_put(prog);
 	cgroup_put(cgrp);
 
-	return 0;
+	return ret;
 }
 
 #define BPF_PROG_DETACH_LAST_FIELD attach_type
@@ -982,6 +989,7 @@ static int bpf_prog_attach(const union bpf_attr *attr)
 static int bpf_prog_detach(const union bpf_attr *attr)
 {
 	struct cgroup *cgrp;
+	int ret;
 
 	if (!capable(CAP_NET_ADMIN))
 		return -EPERM;
@@ -997,7 +1005,7 @@ static int bpf_prog_detach(const union bpf_attr *attr)
 		if (IS_ERR(cgrp))
 			return PTR_ERR(cgrp);
 
-		cgroup_bpf_update(cgrp, NULL, attr->attach_type);
+		ret = cgroup_bpf_update(cgrp, NULL, attr->attach_type, false);
 		cgroup_put(cgrp);
 		break;
 
@@ -1005,7 +1013,7 @@ static int bpf_prog_detach(const union bpf_attr *attr)
 		return -EINVAL;
 	}
 
-	return 0;
+	return ret;
 }
 #endif /* CONFIG_CGROUP_BPF */
 
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index 688dd02af985..53bbca7c4859 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -6498,15 +6498,16 @@ static __init int cgroup_namespaces_init(void)
 subsys_initcall(cgroup_namespaces_init);
 
 #ifdef CONFIG_CGROUP_BPF
-void cgroup_bpf_update(struct cgroup *cgrp,
-		       struct bpf_prog *prog,
-		       enum bpf_attach_type type)
+int cgroup_bpf_update(struct cgroup *cgrp, struct bpf_prog *prog,
+		      enum bpf_attach_type type, bool overridable)
 {
 	struct cgroup *parent = cgroup_parent(cgrp);
+	int ret;
 
 	mutex_lock(&cgroup_mutex);
-	__cgroup_bpf_update(cgrp, parent, prog, type);
+	ret = __cgroup_bpf_update(cgrp, parent, prog, type, overridable);
 	mutex_unlock(&cgroup_mutex);
+	return ret;
 }
 #endif /* CONFIG_CGROUP_BPF */
 
diff --git a/kernel/events/core.c b/kernel/events/core.c
index e5aaa806702d..e235bb991bdd 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -3487,14 +3487,15 @@ struct perf_read_data {
 	int ret;
 };
 
-static int find_cpu_to_read(struct perf_event *event, int local_cpu)
+static int __perf_event_read_cpu(struct perf_event *event, int event_cpu)
 {
-	int event_cpu = event->oncpu;
 	u16 local_pkg, event_pkg;
 
 	if (event->group_caps & PERF_EV_CAP_READ_ACTIVE_PKG) {
-		event_pkg =  topology_physical_package_id(event_cpu);
-		local_pkg =  topology_physical_package_id(local_cpu);
+		int local_cpu = smp_processor_id();
+
+		event_pkg = topology_physical_package_id(event_cpu);
+		local_pkg = topology_physical_package_id(local_cpu);
 
 		if (event_pkg == local_pkg)
 			return local_cpu;
@@ -3624,7 +3625,7 @@ u64 perf_event_read_local(struct perf_event *event)
 
 static int perf_event_read(struct perf_event *event, bool group)
 {
-	int ret = 0, cpu_to_read, local_cpu;
+	int event_cpu, ret = 0;
 
 	/*
 	 * If event is enabled and currently active on a CPU, update the
@@ -3637,21 +3638,25 @@ static int perf_event_read(struct perf_event *event, bool group)
 			.ret = 0,
 		};
 
-		local_cpu = get_cpu();
-		cpu_to_read = find_cpu_to_read(event, local_cpu);
-		put_cpu();
+		event_cpu = READ_ONCE(event->oncpu);
+		if ((unsigned)event_cpu >= nr_cpu_ids)
+			return 0;
+
+		preempt_disable();
+		event_cpu = __perf_event_read_cpu(event, event_cpu);
 
 		/*
 		 * Purposely ignore the smp_call_function_single() return
 		 * value.
 		 *
-		 * If event->oncpu isn't a valid CPU it means the event got
+		 * If event_cpu isn't a valid CPU it means the event got
 		 * scheduled out and that will have updated the event count.
 		 *
 		 * Therefore, either way, we'll have an up-to-date event count
 		 * after this.
 		 */
-		(void)smp_call_function_single(cpu_to_read, __perf_event_read, &data, 1);
+		(void)smp_call_function_single(event_cpu, __perf_event_read, &data, 1);
+		preempt_enable();
 		ret = data.ret;
 	} else if (event->state == PERF_EVENT_STATE_INACTIVE) {
 		struct perf_event_context *ctx = event->ctx;
diff --git a/kernel/stacktrace.c b/kernel/stacktrace.c
index b6e4c16377c7..9c15a9124e83 100644
--- a/kernel/stacktrace.c
+++ b/kernel/stacktrace.c
@@ -18,10 +18,8 @@ void print_stack_trace(struct stack_trace *trace, int spaces)
 	if (WARN_ON(!trace->entries))
 		return;
 
-	for (i = 0; i < trace->nr_entries; i++) {
-		printk("%*c", 1 + spaces, ' ');
-		print_ip_sym(trace->entries[i]);
-	}
+	for (i = 0; i < trace->nr_entries; i++)
+		printk("%*c%pS\n", 1 + spaces, ' ', (void *)trace->entries[i]);
 }
 EXPORT_SYMBOL_GPL(print_stack_trace);
 
@@ -29,7 +27,6 @@ int snprint_stack_trace(char *buf, size_t size,
 			struct stack_trace *trace, int spaces)
 {
 	int i;
-	unsigned long ip;
 	int generated;
 	int total = 0;
 
@@ -37,9 +34,8 @@ int snprint_stack_trace(char *buf, size_t size,
 		return 0;
 
 	for (i = 0; i < trace->nr_entries; i++) {
-		ip = trace->entries[i];
-		generated = snprintf(buf, size, "%*c[<%p>] %pS\n",
-				1 + spaces, ' ', (void *) ip, (void *) ip);
+		generated = snprintf(buf, size, "%*c%pS\n", 1 + spaces, ' ',
+				     (void *)trace->entries[i]);
 
 		total += generated;
 
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index 74e0388cc88d..fc6f740d0277 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -725,6 +725,11 @@ static ktime_t tick_nohz_stop_sched_tick(struct tick_sched *ts,
 		 */
 		if (delta == 0) {
 			tick_nohz_restart(ts, now);
+			/*
+			 * Make sure next tick stop doesn't get fooled by past
+			 * clock deadline
+			 */
+			ts->next_tick = 0;
 			goto out;
 		}
 	}
diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index 7bb12e07ffef..e7c12caa20c8 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -2923,7 +2923,8 @@ static void neigh_proc_update(struct ctl_table *ctl, int write)
 		return;
 
 	set_bit(index, p->data_state);
-	call_netevent_notifiers(NETEVENT_DELAY_PROBE_TIME_UPDATE, p);
+	if (index == NEIGH_VAR_DELAY_PROBE_TIME)
+		call_netevent_notifiers(NETEVENT_DELAY_PROBE_TIME_UPDATE, p);
 	if (!dev) /* NULL dev means this is default value */
 		neigh_copy_dflt_parms(net, p, index);
 }
diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c
index 89a8cac4726a..51b27ae09fbd 100644
--- a/net/ipv4/arp.c
+++ b/net/ipv4/arp.c
@@ -1263,7 +1263,7 @@ void __init arp_init(void)
 /*
  *	ax25 -> ASCII conversion
  */
-static char *ax2asc2(ax25_address *a, char *buf)
+static void ax2asc2(ax25_address *a, char *buf)
 {
 	char c, *s;
 	int n;
@@ -1285,10 +1285,10 @@ static char *ax2asc2(ax25_address *a, char *buf)
 	*s++ = n + '0';
 	*s++ = '\0';
 
-	if (*buf == '\0' || *buf == '-')
-		return "*";
-
-	return buf;
+	if (*buf == '\0' || *buf == '-') {
+		buf[0] = '*';
+		buf[1] = '\0';
+	}
 }
 #endif /* CONFIG_AX25 */
 
@@ -1322,7 +1322,7 @@ static void arp_format_neigh_entry(struct seq_file *seq,
 	}
 #endif
 	sprintf(tbuf, "%pI4", n->primary_key);
-	seq_printf(seq, "%-16s 0x%-10x0x%-10x%s     *        %s\n",
+	seq_printf(seq, "%-16s 0x%-10x0x%-10x%-17s     *        %s\n",
 		   tbuf, hatype, arp_state_to_flags(n), hbuffer, dev->name);
 	read_unlock(&n->lock);
 }
diff --git a/net/ipv4/tcp_probe.c b/net/ipv4/tcp_probe.c
index f6c50af24a64..3d063eb37848 100644
--- a/net/ipv4/tcp_probe.c
+++ b/net/ipv4/tcp_probe.c
@@ -117,7 +117,7 @@ static void jtcp_rcv_established(struct sock *sk, struct sk_buff *skb,
 	     (fwmark > 0 && skb->mark == fwmark)) &&
 	    (full || tp->snd_cwnd != tcp_probe.lastcwnd)) {
 
-		spin_lock(&tcp_probe.lock);
+		spin_lock_bh(&tcp_probe.lock);
 		/* If log fills, just silently drop */
 		if (tcp_probe_avail() > 1) {
 			struct tcp_log *p = tcp_probe.log + tcp_probe.head;
@@ -157,7 +157,7 @@ static void jtcp_rcv_established(struct sock *sk, struct sk_buff *skb,
 			tcp_probe.head = (tcp_probe.head + 1) & (bufsize - 1);
 		}
 		tcp_probe.lastcwnd = tp->snd_cwnd;
-		spin_unlock(&tcp_probe.lock);
+		spin_unlock_bh(&tcp_probe.lock);
 
 		wake_up(&tcp_probe.wait);
 	}
diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c
index a3eaafd87100..eec27f87efac 100644
--- a/net/ipv6/datagram.c
+++ b/net/ipv6/datagram.c
@@ -167,18 +167,22 @@ int __ip6_datagram_connect(struct sock *sk, struct sockaddr *uaddr,
 	if (np->sndflow)
 		fl6_flowlabel = usin->sin6_flowinfo & IPV6_FLOWINFO_MASK;
 
-	addr_type = ipv6_addr_type(&usin->sin6_addr);
-
-	if (addr_type == IPV6_ADDR_ANY) {
+	if (ipv6_addr_any(&usin->sin6_addr)) {
 		/*
 		 *	connect to self
 		 */
-		usin->sin6_addr.s6_addr[15] = 0x01;
+		if (ipv6_addr_v4mapped(&sk->sk_v6_rcv_saddr))
+			ipv6_addr_set_v4mapped(htonl(INADDR_LOOPBACK),
+					       &usin->sin6_addr);
+		else
+			usin->sin6_addr = in6addr_loopback;
 	}
 
+	addr_type = ipv6_addr_type(&usin->sin6_addr);
+
 	daddr = &usin->sin6_addr;
 
-	if (addr_type == IPV6_ADDR_MAPPED) {
+	if (addr_type & IPV6_ADDR_MAPPED) {
 		struct sockaddr_in sin;
 
 		if (__ipv6_only_sock(sk)) {
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index a75871c62328..d0f51b420447 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -1022,6 +1022,9 @@ static int ip6_dst_lookup_tail(struct net *net, const struct sock *sk,
 		}
 	}
 #endif
+	if (ipv6_addr_v4mapped(&fl6->saddr) &&
+	    !(ipv6_addr_v4mapped(&fl6->daddr) || ipv6_addr_any(&fl6->daddr)))
+		return -EAFNOSUPPORT;
 
 	return 0;
 
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index b5d27212db2f..21c719965b6b 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -149,8 +149,13 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
 	 *	connect() to INADDR_ANY means loopback (BSD'ism).
 	 */
 
-	if (ipv6_addr_any(&usin->sin6_addr))
-		usin->sin6_addr.s6_addr[15] = 0x1;
+	if (ipv6_addr_any(&usin->sin6_addr)) {
+		if (ipv6_addr_v4mapped(&sk->sk_v6_rcv_saddr))
+			ipv6_addr_set_v4mapped(htonl(INADDR_LOOPBACK),
+					       &usin->sin6_addr);
+		else
+			usin->sin6_addr = in6addr_loopback;
+	}
 
 	addr_type = ipv6_addr_type(&usin->sin6_addr);
 
@@ -189,7 +194,7 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
 	 *	TCP over IPv4
 	 */
 
-	if (addr_type == IPV6_ADDR_MAPPED) {
+	if (addr_type & IPV6_ADDR_MAPPED) {
 		u32 exthdrlen = icsk->icsk_ext_hdr_len;
 		struct sockaddr_in sin;
 
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index df71ba05f41d..4e4c401e3bc6 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -1046,6 +1046,10 @@ int udpv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 			if (addr_len < SIN6_LEN_RFC2133)
 				return -EINVAL;
 			daddr = &sin6->sin6_addr;
+			if (ipv6_addr_any(daddr) &&
+			    ipv6_addr_v4mapped(&np->saddr))
+				ipv6_addr_set_v4mapped(htonl(INADDR_LOOPBACK),
+						       daddr);
 			break;
 		case AF_INET:
 			goto do_udp_sendmsg;
diff --git a/net/kcm/kcmsock.c b/net/kcm/kcmsock.c
index 64f0e8531af0..a646f3481240 100644
--- a/net/kcm/kcmsock.c
+++ b/net/kcm/kcmsock.c
@@ -1044,8 +1044,10 @@ wait_for_memory:
 	} else {
 		/* Message not complete, save state */
 partial_message:
-		kcm->seq_skb = head;
-		kcm_tx_msg(head)->last_skb = skb;
+		if (head) {
+			kcm->seq_skb = head;
+			kcm_tx_msg(head)->last_skb = skb;
+		}
 	}
 
 	KCM_STATS_ADD(kcm->stats.tx_bytes, copied);
diff --git a/net/llc/llc_conn.c b/net/llc/llc_conn.c
index 3e821daf9dd4..8bc5a1bd2d45 100644
--- a/net/llc/llc_conn.c
+++ b/net/llc/llc_conn.c
@@ -821,7 +821,10 @@ void llc_conn_handler(struct llc_sap *sap, struct sk_buff *skb)
 		 * another trick required to cope with how the PROCOM state
 		 * machine works. -acme
 		 */
+		skb_orphan(skb);
+		sock_hold(sk);
 		skb->sk = sk;
+		skb->destructor = sock_efree;
 	}
 	if (!sock_owned_by_user(sk))
 		llc_conn_rcv(sk, skb);
diff --git a/net/llc/llc_sap.c b/net/llc/llc_sap.c
index d0e1e804ebd7..5404d0d195cc 100644
--- a/net/llc/llc_sap.c
+++ b/net/llc/llc_sap.c
@@ -290,7 +290,10 @@ static void llc_sap_rcv(struct llc_sap *sap, struct sk_buff *skb,
 
 	ev->type   = LLC_SAP_EV_TYPE_PDU;
 	ev->reason = 0;
+	skb_orphan(skb);
+	sock_hold(sk);
 	skb->sk = sk;
+	skb->destructor = sock_efree;
 	llc_sap_state_process(sap, skb);
 }
 
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index a984f6f9ab4e..7098e2a457e4 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -1627,6 +1627,7 @@ static void fanout_release_data(struct packet_fanout *f)
 
 static int fanout_add(struct sock *sk, u16 id, u16 type_flags)
 {
+	struct packet_rollover *rollover = NULL;
 	struct packet_sock *po = pkt_sk(sk);
 	struct packet_fanout *f, *match;
 	u8 type = type_flags & 0xff;
@@ -1649,23 +1650,28 @@ static int fanout_add(struct sock *sk, u16 id, u16 type_flags)
 		return -EINVAL;
 	}
 
+	mutex_lock(&fanout_mutex);
+
+	err = -EINVAL;
 	if (!po->running)
-		return -EINVAL;
+		goto out;
 
+	err = -EALREADY;
 	if (po->fanout)
-		return -EALREADY;
+		goto out;
 
 	if (type == PACKET_FANOUT_ROLLOVER ||
 	    (type_flags & PACKET_FANOUT_FLAG_ROLLOVER)) {
-		po->rollover = kzalloc(sizeof(*po->rollover), GFP_KERNEL);
-		if (!po->rollover)
-			return -ENOMEM;
-		atomic_long_set(&po->rollover->num, 0);
-		atomic_long_set(&po->rollover->num_huge, 0);
-		atomic_long_set(&po->rollover->num_failed, 0);
+		err = -ENOMEM;
+		rollover = kzalloc(sizeof(*rollover), GFP_KERNEL);
+		if (!rollover)
+			goto out;
+		atomic_long_set(&rollover->num, 0);
+		atomic_long_set(&rollover->num_huge, 0);
+		atomic_long_set(&rollover->num_failed, 0);
+		po->rollover = rollover;
 	}
 
-	mutex_lock(&fanout_mutex);
 	match = NULL;
 	list_for_each_entry(f, &fanout_list, list) {
 		if (f->id == id &&
@@ -1712,11 +1718,11 @@ static int fanout_add(struct sock *sk, u16 id, u16 type_flags)
 		}
 	}
 out:
-	mutex_unlock(&fanout_mutex);
-	if (err) {
-		kfree(po->rollover);
+	if (err && rollover) {
+		kfree(rollover);
 		po->rollover = NULL;
 	}
+	mutex_unlock(&fanout_mutex);
 	return err;
 }
 
@@ -1725,23 +1731,22 @@ static void fanout_release(struct sock *sk)
 	struct packet_sock *po = pkt_sk(sk);
 	struct packet_fanout *f;
 
-	f = po->fanout;
-	if (!f)
-		return;
-
 	mutex_lock(&fanout_mutex);
-	po->fanout = NULL;
+	f = po->fanout;
+	if (f) {
+		po->fanout = NULL;
+
+		if (atomic_dec_and_test(&f->sk_ref)) {
+			list_del(&f->list);
+			dev_remove_pack(&f->prot_hook);
+			fanout_release_data(f);
+			kfree(f);
+		}
 
-	if (atomic_dec_and_test(&f->sk_ref)) {
-		list_del(&f->list);
-		dev_remove_pack(&f->prot_hook);
-		fanout_release_data(f);
-		kfree(f);
+		if (po->rollover)
+			kfree_rcu(po->rollover, rcu);
 	}
 	mutex_unlock(&fanout_mutex);
-
-	if (po->rollover)
-		kfree_rcu(po->rollover, rcu);
 }
 
 static bool packet_extra_vlan_len_allowed(const struct net_device *dev,
diff --git a/samples/bpf/test_cgrp2_attach.c b/samples/bpf/test_cgrp2_attach.c
index 504058631ffc..4bfcaf93fcf3 100644
--- a/samples/bpf/test_cgrp2_attach.c
+++ b/samples/bpf/test_cgrp2_attach.c
@@ -104,7 +104,7 @@ static int attach_filter(int cg_fd, int type, int verdict)
 		return EXIT_FAILURE;
 	}
 
-	ret = bpf_prog_attach(prog_fd, cg_fd, type);
+	ret = bpf_prog_attach(prog_fd, cg_fd, type, 0);
 	if (ret < 0) {
 		printf("Failed to attach prog to cgroup: '%s'\n",
 		       strerror(errno));
diff --git a/samples/bpf/test_cgrp2_attach2.c b/samples/bpf/test_cgrp2_attach2.c
index 6e69be37f87f..3049b1f26267 100644
--- a/samples/bpf/test_cgrp2_attach2.c
+++ b/samples/bpf/test_cgrp2_attach2.c
@@ -79,11 +79,12 @@ int main(int argc, char **argv)
 	if (join_cgroup(FOO))
 		goto err;
 
-	if (bpf_prog_attach(drop_prog, foo, BPF_CGROUP_INET_EGRESS)) {
+	if (bpf_prog_attach(drop_prog, foo, BPF_CGROUP_INET_EGRESS, 1)) {
 		log_err("Attaching prog to /foo");
 		goto err;
 	}
 
+	printf("Attached DROP prog. This ping in cgroup /foo should fail...\n");
 	assert(system(PING_CMD) != 0);
 
 	/* Create cgroup /foo/bar, get fd, and join it */
@@ -94,24 +95,27 @@ int main(int argc, char **argv)
 	if (join_cgroup(BAR))
 		goto err;
 
+	printf("Attached DROP prog. This ping in cgroup /foo/bar should fail...\n");
 	assert(system(PING_CMD) != 0);
 
-	if (bpf_prog_attach(allow_prog, bar, BPF_CGROUP_INET_EGRESS)) {
+	if (bpf_prog_attach(allow_prog, bar, BPF_CGROUP_INET_EGRESS, 1)) {
 		log_err("Attaching prog to /foo/bar");
 		goto err;
 	}
 
+	printf("Attached PASS prog. This ping in cgroup /foo/bar should pass...\n");
 	assert(system(PING_CMD) == 0);
 
-
 	if (bpf_prog_detach(bar, BPF_CGROUP_INET_EGRESS)) {
 		log_err("Detaching program from /foo/bar");
 		goto err;
 	}
 
+	printf("Detached PASS from /foo/bar while DROP is attached to /foo.\n"
+	       "This ping in cgroup /foo/bar should fail...\n");
 	assert(system(PING_CMD) != 0);
 
-	if (bpf_prog_attach(allow_prog, bar, BPF_CGROUP_INET_EGRESS)) {
+	if (bpf_prog_attach(allow_prog, bar, BPF_CGROUP_INET_EGRESS, 1)) {
 		log_err("Attaching prog to /foo/bar");
 		goto err;
 	}
@@ -121,8 +125,60 @@ int main(int argc, char **argv)
 		goto err;
 	}
 
+	printf("Attached PASS from /foo/bar and detached DROP from /foo.\n"
+	       "This ping in cgroup /foo/bar should pass...\n");
 	assert(system(PING_CMD) == 0);
 
+	if (bpf_prog_attach(allow_prog, bar, BPF_CGROUP_INET_EGRESS, 1)) {
+		log_err("Attaching prog to /foo/bar");
+		goto err;
+	}
+
+	if (!bpf_prog_attach(allow_prog, bar, BPF_CGROUP_INET_EGRESS, 0)) {
+		errno = 0;
+		log_err("Unexpected success attaching prog to /foo/bar");
+		goto err;
+	}
+
+	if (bpf_prog_detach(bar, BPF_CGROUP_INET_EGRESS)) {
+		log_err("Detaching program from /foo/bar");
+		goto err;
+	}
+
+	if (!bpf_prog_detach(foo, BPF_CGROUP_INET_EGRESS)) {
+		errno = 0;
+		log_err("Unexpected success in double detach from /foo");
+		goto err;
+	}
+
+	if (bpf_prog_attach(allow_prog, foo, BPF_CGROUP_INET_EGRESS, 0)) {
+		log_err("Attaching non-overridable prog to /foo");
+		goto err;
+	}
+
+	if (!bpf_prog_attach(allow_prog, bar, BPF_CGROUP_INET_EGRESS, 0)) {
+		errno = 0;
+		log_err("Unexpected success attaching non-overridable prog to /foo/bar");
+		goto err;
+	}
+
+	if (!bpf_prog_attach(allow_prog, bar, BPF_CGROUP_INET_EGRESS, 1)) {
+		errno = 0;
+		log_err("Unexpected success attaching overridable prog to /foo/bar");
+		goto err;
+	}
+
+	if (!bpf_prog_attach(allow_prog, foo, BPF_CGROUP_INET_EGRESS, 1)) {
+		errno = 0;
+		log_err("Unexpected success attaching overridable prog to /foo");
+		goto err;
+	}
+
+	if (bpf_prog_attach(drop_prog, foo, BPF_CGROUP_INET_EGRESS, 0)) {
+		log_err("Attaching different non-overridable prog to /foo");
+		goto err;
+	}
+
 	goto out;
 
 err:
@@ -132,5 +188,9 @@ out:
 	close(foo);
 	close(bar);
 	cleanup_cgroup_environment();
+	if (!rc)
+		printf("PASS\n");
+	else
+		printf("FAIL\n");
 	return rc;
 }
diff --git a/samples/bpf/test_cgrp2_sock.c b/samples/bpf/test_cgrp2_sock.c
index 0791b949cbe4..c3cfb23e23b5 100644
--- a/samples/bpf/test_cgrp2_sock.c
+++ b/samples/bpf/test_cgrp2_sock.c
@@ -75,7 +75,7 @@ int main(int argc, char **argv)
 		return EXIT_FAILURE;
 	}
 
-	ret = bpf_prog_attach(prog_fd, cg_fd, BPF_CGROUP_INET_SOCK_CREATE);
+	ret = bpf_prog_attach(prog_fd, cg_fd, BPF_CGROUP_INET_SOCK_CREATE, 0);
 	if (ret < 0) {
 		printf("Failed to attach prog to cgroup: '%s'\n",
 		       strerror(errno));
diff --git a/samples/bpf/test_cgrp2_sock2.c b/samples/bpf/test_cgrp2_sock2.c
index 455ef0d06e93..db036077b644 100644
--- a/samples/bpf/test_cgrp2_sock2.c
+++ b/samples/bpf/test_cgrp2_sock2.c
@@ -55,7 +55,7 @@ int main(int argc, char **argv)
 	}
 
 	ret = bpf_prog_attach(prog_fd[filter_id], cg_fd,
-			      BPF_CGROUP_INET_SOCK_CREATE);
+			      BPF_CGROUP_INET_SOCK_CREATE, 0);
 	if (ret < 0) {
 		printf("Failed to attach prog to cgroup: '%s'\n",
 		       strerror(errno));
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index e07fd5a324e6..0539a0ceef38 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -123,6 +123,12 @@ enum bpf_attach_type {
 
 #define MAX_BPF_ATTACH_TYPE __MAX_BPF_ATTACH_TYPE
 
+/* If BPF_F_ALLOW_OVERRIDE flag is used in BPF_PROG_ATTACH command
+ * to the given target_fd cgroup the descendent cgroup will be able to
+ * override effective bpf program that was inherited from this cgroup
+ */
+#define BPF_F_ALLOW_OVERRIDE	(1U << 0)
+
 #define BPF_PSEUDO_MAP_FD	1
 
 /* flags for BPF_MAP_UPDATE_ELEM command */
@@ -178,6 +184,7 @@ union bpf_attr {
 		__u32		target_fd;	/* container object to attach to */
 		__u32		attach_bpf_fd;	/* eBPF program to attach */
 		__u32		attach_type;
+		__u32		attach_flags;
 	};
 } __attribute__((aligned(8)));
 
diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c
index 2de9c386989a..d48b70ceb25a 100644
--- a/tools/lib/bpf/bpf.c
+++ b/tools/lib/bpf/bpf.c
@@ -168,7 +168,8 @@ int bpf_obj_get(const char *pathname)
 	return sys_bpf(BPF_OBJ_GET, &attr, sizeof(attr));
 }
 
-int bpf_prog_attach(int prog_fd, int target_fd, enum bpf_attach_type type)
+int bpf_prog_attach(int prog_fd, int target_fd, enum bpf_attach_type type,
+		    unsigned int flags)
 {
 	union bpf_attr attr;
 
@@ -176,6 +177,7 @@ int bpf_prog_attach(int prog_fd, int target_fd, enum bpf_attach_type type)
 	attr.target_fd	   = target_fd;
 	attr.attach_bpf_fd = prog_fd;
 	attr.attach_type   = type;
+	attr.attach_flags  = flags;
 
 	return sys_bpf(BPF_PROG_ATTACH, &attr, sizeof(attr));
 }
diff --git a/tools/lib/bpf/bpf.h b/tools/lib/bpf/bpf.h
index 88f07c15423a..9f838aa6d26e 100644
--- a/tools/lib/bpf/bpf.h
+++ b/tools/lib/bpf/bpf.h
@@ -41,7 +41,8 @@ int bpf_map_delete_elem(int fd, const void *key);
 int bpf_map_get_next_key(int fd, const void *key, void *next_key);
 int bpf_obj_pin(int fd, const char *pathname);
 int bpf_obj_get(const char *pathname);
-int bpf_prog_attach(int prog_fd, int attachable_fd, enum bpf_attach_type type);
+int bpf_prog_attach(int prog_fd, int attachable_fd, enum bpf_attach_type type,
+		    unsigned int flags);
 int bpf_prog_detach(int attachable_fd, enum bpf_attach_type type);
 
 
diff --git a/tools/perf/builtin-diff.c b/tools/perf/builtin-diff.c
index 9ff0db4e2d0c..933aeec46f4a 100644
--- a/tools/perf/builtin-diff.c
+++ b/tools/perf/builtin-diff.c
@@ -1199,7 +1199,7 @@ static int ui_init(void)
 		BUG_ON(1);
 	}
 
-	perf_hpp__register_sort_field(fmt);
+	perf_hpp__prepend_sort_field(fmt);
 	return 0;
 }
 
diff --git a/tools/perf/ui/hist.c b/tools/perf/ui/hist.c
index 37388397b5bc..18cfcdc90356 100644
--- a/tools/perf/ui/hist.c
+++ b/tools/perf/ui/hist.c
@@ -521,6 +521,12 @@ void perf_hpp_list__register_sort_field(struct perf_hpp_list *list,
 	list_add_tail(&format->sort_list, &list->sorts);
 }
 
+void perf_hpp_list__prepend_sort_field(struct perf_hpp_list *list,
+				       struct perf_hpp_fmt *format)
+{
+	list_add(&format->sort_list, &list->sorts);
+}
+
 void perf_hpp__column_unregister(struct perf_hpp_fmt *format)
 {
 	list_del(&format->list);
@@ -560,6 +566,10 @@ void perf_hpp__setup_output_field(struct perf_hpp_list *list)
 	perf_hpp_list__for_each_sort_list(list, fmt) {
 		struct perf_hpp_fmt *pos;
 
+		/* skip sort-only fields ("sort_compute" in perf diff) */
+		if (!fmt->entry && !fmt->color)
+			continue;
+
 		perf_hpp_list__for_each_format(list, pos) {
 			if (fmt_equal(fmt, pos))
 				goto next;
diff --git a/tools/perf/util/callchain.c b/tools/perf/util/callchain.c
index 42922512c1c6..8b610dd9e2f6 100644
--- a/tools/perf/util/callchain.c
+++ b/tools/perf/util/callchain.c
@@ -437,7 +437,7 @@ fill_node(struct callchain_node *node, struct callchain_cursor *cursor)
 		}
 		call->ip = cursor_node->ip;
 		call->ms.sym = cursor_node->sym;
-		call->ms.map = cursor_node->map;
+		call->ms.map = map__get(cursor_node->map);
 
 		if (cursor_node->branch) {
 			call->branch_count = 1;
@@ -477,6 +477,7 @@ add_child(struct callchain_node *parent,
 
 		list_for_each_entry_safe(call, tmp, &new->val, list) {
 			list_del(&call->list);
+			map__zput(call->ms.map);
 			free(call);
 		}
 		free(new);
@@ -761,6 +762,7 @@ merge_chain_branch(struct callchain_cursor *cursor,
 					list->ms.map, list->ms.sym,
 					false, NULL, 0, 0);
 		list_del(&list->list);
+		map__zput(list->ms.map);
 		free(list);
 	}
 
@@ -811,7 +813,8 @@ int callchain_cursor_append(struct callchain_cursor *cursor,
 	}
 
 	node->ip = ip;
-	node->map = map;
+	map__zput(node->map);
+	node->map = map__get(map);
 	node->sym = sym;
 	node->branch = branch;
 	node->nr_loop_iter = nr_loop_iter;
@@ -1142,11 +1145,13 @@ static void free_callchain_node(struct callchain_node *node)
 
 	list_for_each_entry_safe(list, tmp, &node->parent_val, list) {
 		list_del(&list->list);
+		map__zput(list->ms.map);
 		free(list);
 	}
 
 	list_for_each_entry_safe(list, tmp, &node->val, list) {
 		list_del(&list->list);
+		map__zput(list->ms.map);
 		free(list);
 	}
 
@@ -1210,6 +1215,7 @@ int callchain_node__make_parent_list(struct callchain_node *node)
 				goto out;
 			*new = *chain;
 			new->has_children = false;
+			map__get(new->ms.map);
 			list_add_tail(&new->list, &head);
 		}
 		parent = parent->parent;
@@ -1230,6 +1236,7 @@ int callchain_node__make_parent_list(struct callchain_node *node)
 out:
 	list_for_each_entry_safe(chain, new, &head, list) {
 		list_del(&chain->list);
+		map__zput(chain->ms.map);
 		free(chain);
 	}
 	return -ENOMEM;
diff --git a/tools/perf/util/callchain.h b/tools/perf/util/callchain.h
index 35c8e379530f..4f4b60f1558a 100644
--- a/tools/perf/util/callchain.h
+++ b/tools/perf/util/callchain.h
@@ -5,6 +5,7 @@
 #include <linux/list.h>
 #include <linux/rbtree.h>
 #include "event.h"
+#include "map.h"
 #include "symbol.h"
 
 #define HELP_PAD "\t\t\t\t"
@@ -184,8 +185,13 @@ int callchain_merge(struct callchain_cursor *cursor,
  */
 static inline void callchain_cursor_reset(struct callchain_cursor *cursor)
 {
+	struct callchain_cursor_node *node;
+
 	cursor->nr = 0;
 	cursor->last = &cursor->first;
+
+	for (node = cursor->first; node != NULL; node = node->next)
+		map__zput(node->map);
 }
 
 int callchain_cursor_append(struct callchain_cursor *cursor, u64 ip,
diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index 6770a9645609..7d1b7d33e644 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -1,6 +1,7 @@
 #include "util.h"
 #include "build-id.h"
 #include "hist.h"
+#include "map.h"
 #include "session.h"
 #include "sort.h"
 #include "evlist.h"
@@ -1019,6 +1020,10 @@ int hist_entry_iter__add(struct hist_entry_iter *iter, struct addr_location *al,
 			 int max_stack_depth, void *arg)
 {
 	int err, err2;
+	struct map *alm = NULL;
+
+	if (al && al->map)
+		alm = map__get(al->map);
 
 	err = sample__resolve_callchain(iter->sample, &callchain_cursor, &iter->parent,
 					iter->evsel, al, max_stack_depth);
@@ -1058,6 +1063,8 @@ out:
 	if (!err)
 		err = err2;
 
+	map__put(alm);
+
 	return err;
 }
 
diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h
index d4b6514eeef5..28c216e3d5b7 100644
--- a/tools/perf/util/hist.h
+++ b/tools/perf/util/hist.h
@@ -283,6 +283,8 @@ void perf_hpp_list__column_register(struct perf_hpp_list *list,
 				    struct perf_hpp_fmt *format);
 void perf_hpp_list__register_sort_field(struct perf_hpp_list *list,
 					struct perf_hpp_fmt *format);
+void perf_hpp_list__prepend_sort_field(struct perf_hpp_list *list,
+				       struct perf_hpp_fmt *format);
 
 static inline void perf_hpp__column_register(struct perf_hpp_fmt *format)
 {
@@ -294,6 +296,11 @@ static inline void perf_hpp__register_sort_field(struct perf_hpp_fmt *format)
 	perf_hpp_list__register_sort_field(&perf_hpp_list, format);
 }
 
+static inline void perf_hpp__prepend_sort_field(struct perf_hpp_fmt *format)
+{
+	perf_hpp_list__prepend_sort_field(&perf_hpp_list, format);
+}
+
 #define perf_hpp_list__for_each_format(_list, format) \
 	list_for_each_entry(format, &(_list)->fields, list)