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

Build failure in drivers/net/wwan/mhi_wwan_mbim.c:
add missing parameter (0, assuming we don't want buffer pre-alloc).

Conflict in drivers/net/dsa/sja1105/sja1105_main.c between:
589918df9322 ("net: dsa: sja1105: be stateless with FDB entries on SJA1105P/Q/R/S/SJA1110 too")
0fac6aa098ed ("net: dsa: sja1105: delete the best_effort_vlan_filtering mode")

Follow the instructions from the commit message of the former commit
- removed the if conditions. When looking at commit 589918df9322 ("net:
dsa: sja1105: be stateless with FDB entries on SJA1105P/Q/R/S/SJA1110 too")
note that the mask_iotag fields get removed by the following patch.

Signed-off-by: Jakub Kicinski <[e-mail]>

Documentation/networking/netdev-FAQ.rst

···
 gets overloaded very easily and netdev@vger really doesn't need more
 traffic if we can help it.
 
+netdevsim is great, can I extend it for my out-of-tree tests?
+-------------------------------------------------------------
+
+No, `netdevsim` is a test vehicle solely for upstream tests.
+(Please add your tests under tools/testing/selftests/.)
+
+We also give no guarantees that `netdevsim` won't change in the future
+in a way which would break what would normally be considered uAPI.
+
+Is netdevsim considered a "user" of an API?
+-------------------------------------------
+
+Linux kernel has a long standing rule that no API should be added unless
+it has a real, in-tree user. Mock-ups and tests based on `netdevsim` are
+strongly encouraged when adding new APIs, but `netdevsim` in itself
+is **not** considered a use case/user.
+
 Any other tips to help ensure my net/net-next patch gets OK'd?
 --------------------------------------------------------------
 Attention to detail.  Re-read your own work as if you were the

Documentation/networking/operstates.rst

···
  state (f.e. VLAN).
 
 IF_OPER_TESTING (4):
- Unused in current kernel.
+ Interface is in testing mode, for example executing driver self-tests
+ or media (cable) test. It can't be used for normal traffic until tests
+ complete.
 
 IF_OPER_DORMANT (5):
  Interface is L1 up, but waiting for an external event, f.e. for a
···
 
 Note that for certain kind of soft-devices, which are not managing any
 real hardware, it is possible to set this bit from userspace.  One
-should use TVL IFLA_CARRIER to do so.
+should use TLV IFLA_CARRIER to do so.
 
 netif_carrier_ok() can be used to query that bit.
 

Makefile

···
 VERSION = 5
 PATCHLEVEL = 14
 SUBLEVEL = 0
-EXTRAVERSION = -rc3
+EXTRAVERSION = -rc4
 NAME = Opossums on Parade
 
 # *DOCUMENTATION*
···
 PHONY += scripts_basic
 scripts_basic:
 	$(Q)$(MAKE) $(build)=scripts/basic
-	$(Q)rm -f .tmp_quiet_recordmcount
 
 PHONY += outputmakefile
 ifdef building_out_of_srctree

arch/powerpc/kernel/vdso64/Makefile

···
 
 ccflags-y := -shared -fno-common -fno-builtin -nostdlib \
 	-Wl,-soname=linux-vdso64.so.1 -Wl,--hash-style=both
+
+# Go prior to 1.16.x assumes r30 is not clobbered by any VDSO code. That used to be true
+# by accident when the VDSO was hand-written asm code, but may not be now that the VDSO is
+# compiler generated. To avoid breaking Go tell GCC not to use r30. Impact on code
+# generation is minimal, it will just use r29 instead.
+ccflags-y += $(call cc-option, -ffixed-r30)
+
 asflags-y := -D__VDSO64__ -s
 
 targets += vdso64.lds

arch/powerpc/platforms/pseries/setup.c

···
 #include "../../../../drivers/pci/pci.h"
 
 DEFINE_STATIC_KEY_FALSE(shared_processor);
-EXPORT_SYMBOL_GPL(shared_processor);
+EXPORT_SYMBOL(shared_processor);
 
 int CMO_PrPSP = -1;
 int CMO_SecPSP = -1;

arch/s390/boot/compressed/Makefile

···
 KASAN_SANITIZE := n
 
 obj-y	:= $(if $(CONFIG_KERNEL_UNCOMPRESSED),,decompressor.o) info.o
+obj-$(CONFIG_KERNEL_ZSTD) += clz_ctz.o
 obj-all := $(obj-y) piggy.o syms.o
 targets	:= vmlinux.lds vmlinux vmlinux.bin vmlinux.bin.gz vmlinux.bin.bz2
 targets += vmlinux.bin.xz vmlinux.bin.lzma vmlinux.bin.lzo vmlinux.bin.lz4

arch/s390/boot/compressed/clz_ctz.c

···
+// SPDX-License-Identifier: GPL-2.0
+#include "../../../../lib/clz_ctz.c"

arch/s390/configs/debug_defconfig

···
 CONFIG_L2TP_V3=y
 CONFIG_L2TP_IP=m
 CONFIG_L2TP_ETH=m
-CONFIG_BRIDGE=m
+CONFIG_BRIDGE=y
 CONFIG_BRIDGE_MRP=y
 CONFIG_VLAN_8021Q=m
 CONFIG_VLAN_8021Q_GVRP=y

arch/s390/configs/defconfig

···
 CONFIG_L2TP_V3=y
 CONFIG_L2TP_IP=m
 CONFIG_L2TP_ETH=m
-CONFIG_BRIDGE=m
+CONFIG_BRIDGE=y
 CONFIG_BRIDGE_MRP=y
 CONFIG_VLAN_8021Q=m
 CONFIG_VLAN_8021Q_GVRP=y

arch/s390/kernel/vdso32/vdso32.lds.S

···
 
 	.rela.dyn ALIGN(8) : { *(.rela.dyn) }
 	.got ALIGN(8)	: { *(.got .toc) }
+	.got.plt ALIGN(8) : { *(.got.plt) }
 
 	_end = .;
 	PROVIDE(end = .);

arch/s390/kernel/vdso64/vdso64.lds.S

···
 
 	.rela.dyn ALIGN(8) : { *(.rela.dyn) }
 	.got ALIGN(8)	: { *(.got .toc) }
+	.got.plt ALIGN(8) : { *(.got.plt) }
 
 	_end = .;
 	PROVIDE(end = .);

arch/x86/kvm/hyperv.c

···
 
 static int kvm_hv_hypercall_complete(struct kvm_vcpu *vcpu, u64 result)
 {
+	trace_kvm_hv_hypercall_done(result);
 	kvm_hv_hypercall_set_result(vcpu, result);
 	++vcpu->stat.hypercalls;
 	return kvm_skip_emulated_instruction(vcpu);
···
 
 int kvm_hv_hypercall(struct kvm_vcpu *vcpu)
 {
+	struct kvm_vcpu_hv *hv_vcpu = to_hv_vcpu(vcpu);
 	struct kvm_hv_hcall hc;
 	u64 ret = HV_STATUS_SUCCESS;
 
···
 	hc.rep_idx = (hc.param >> HV_HYPERCALL_REP_START_OFFSET) & 0xfff;
 	hc.rep = !!(hc.rep_cnt || hc.rep_idx);
 
-	if (hc.fast && is_xmm_fast_hypercall(&hc))
-		kvm_hv_hypercall_read_xmm(&hc);
-
 	trace_kvm_hv_hypercall(hc.code, hc.fast, hc.rep_cnt, hc.rep_idx,
 			       hc.ingpa, hc.outgpa);
 
-	if (unlikely(!hv_check_hypercall_access(to_hv_vcpu(vcpu), hc.code))) {
+	if (unlikely(!hv_check_hypercall_access(hv_vcpu, hc.code))) {
 		ret = HV_STATUS_ACCESS_DENIED;
 		goto hypercall_complete;
+	}
+
+	if (hc.fast && is_xmm_fast_hypercall(&hc)) {
+		if (unlikely(hv_vcpu->enforce_cpuid &&
+			     !(hv_vcpu->cpuid_cache.features_edx &
+			       HV_X64_HYPERCALL_XMM_INPUT_AVAILABLE))) {
+			kvm_queue_exception(vcpu, UD_VECTOR);
+			return 1;
+		}
+
+		kvm_hv_hypercall_read_xmm(&hc);
 	}
 
 	switch (hc.code) {

arch/x86/kvm/mmu/mmu.c

···
  * aggregate version in order to make the slab shrinker
  * faster
  */
-static inline void kvm_mod_used_mmu_pages(struct kvm *kvm, unsigned long nr)
+static inline void kvm_mod_used_mmu_pages(struct kvm *kvm, long nr)
 {
 	kvm->arch.n_used_mmu_pages += nr;
 	percpu_counter_add(&kvm_total_used_mmu_pages, nr);

arch/x86/kvm/svm/sev.c

···
 unsigned int max_sev_asid;
 static unsigned int min_sev_asid;
 static unsigned long sev_me_mask;
+static unsigned int nr_asids;
 static unsigned long *sev_asid_bitmap;
 static unsigned long *sev_reclaim_asid_bitmap;
 
···
 /* Called with the sev_bitmap_lock held, or on shutdown  */
 static int sev_flush_asids(int min_asid, int max_asid)
 {
-	int ret, pos, error = 0;
+	int ret, asid, error = 0;
 
 	/* Check if there are any ASIDs to reclaim before performing a flush */
-	pos = find_next_bit(sev_reclaim_asid_bitmap, max_asid, min_asid);
-	if (pos >= max_asid)
+	asid = find_next_bit(sev_reclaim_asid_bitmap, nr_asids, min_asid);
+	if (asid > max_asid)
 		return -EBUSY;
 
 	/*
···
 
 	/* The flush process will flush all reclaimable SEV and SEV-ES ASIDs */
 	bitmap_xor(sev_asid_bitmap, sev_asid_bitmap, sev_reclaim_asid_bitmap,
-		   max_sev_asid);
-	bitmap_zero(sev_reclaim_asid_bitmap, max_sev_asid);
+		   nr_asids);
+	bitmap_zero(sev_reclaim_asid_bitmap, nr_asids);
 
 	return true;
 }
 
 static int sev_asid_new(struct kvm_sev_info *sev)
 {
-	int pos, min_asid, max_asid, ret;
+	int asid, min_asid, max_asid, ret;
 	bool retry = true;
 	enum misc_res_type type;
 
···
 	 * SEV-enabled guests must use asid from min_sev_asid to max_sev_asid.
 	 * SEV-ES-enabled guest can use from 1 to min_sev_asid - 1.
 	 */
-	min_asid = sev->es_active ? 0 : min_sev_asid - 1;
+	min_asid = sev->es_active ? 1 : min_sev_asid;
 	max_asid = sev->es_active ? min_sev_asid - 1 : max_sev_asid;
 again:
-	pos = find_next_zero_bit(sev_asid_bitmap, max_sev_asid, min_asid);
-	if (pos >= max_asid) {
+	asid = find_next_zero_bit(sev_asid_bitmap, max_asid + 1, min_asid);
+	if (asid > max_asid) {
 		if (retry && __sev_recycle_asids(min_asid, max_asid)) {
 			retry = false;
 			goto again;
···
 		goto e_uncharge;
 	}
 
-	__set_bit(pos, sev_asid_bitmap);
+	__set_bit(asid, sev_asid_bitmap);
 
 	mutex_unlock(&sev_bitmap_lock);
 
-	return pos + 1;
+	return asid;
 e_uncharge:
 	misc_cg_uncharge(type, sev->misc_cg, 1);
 	put_misc_cg(sev->misc_cg);
···
 static void sev_asid_free(struct kvm_sev_info *sev)
 {
 	struct svm_cpu_data *sd;
-	int cpu, pos;
+	int cpu;
 	enum misc_res_type type;
 
 	mutex_lock(&sev_bitmap_lock);
 
-	pos = sev->asid - 1;
-	__set_bit(pos, sev_reclaim_asid_bitmap);
+	__set_bit(sev->asid, sev_reclaim_asid_bitmap);
 
 	for_each_possible_cpu(cpu) {
 		sd = per_cpu(svm_data, cpu);
-		sd->sev_vmcbs[pos] = NULL;
+		sd->sev_vmcbs[sev->asid] = NULL;
 	}
 
 	mutex_unlock(&sev_bitmap_lock);
···
 	min_sev_asid = edx;
 	sev_me_mask = 1UL << (ebx & 0x3f);
 
-	/* Initialize SEV ASID bitmaps */
-	sev_asid_bitmap = bitmap_zalloc(max_sev_asid, GFP_KERNEL);
+	/*
+	 * Initialize SEV ASID bitmaps. Allocate space for ASID 0 in the bitmap,
+	 * even though it's never used, so that the bitmap is indexed by the
+	 * actual ASID.
+	 */
+	nr_asids = max_sev_asid + 1;
+	sev_asid_bitmap = bitmap_zalloc(nr_asids, GFP_KERNEL);
 	if (!sev_asid_bitmap)
 		goto out;
 
-	sev_reclaim_asid_bitmap = bitmap_zalloc(max_sev_asid, GFP_KERNEL);
+	sev_reclaim_asid_bitmap = bitmap_zalloc(nr_asids, GFP_KERNEL);
 	if (!sev_reclaim_asid_bitmap) {
 		bitmap_free(sev_asid_bitmap);
 		sev_asid_bitmap = NULL;
···
 		return;
 
 	/* No need to take sev_bitmap_lock, all VMs have been destroyed. */
-	sev_flush_asids(0, max_sev_asid);
+	sev_flush_asids(1, max_sev_asid);
 
 	bitmap_free(sev_asid_bitmap);
 	bitmap_free(sev_reclaim_asid_bitmap);
···
 	if (!sev_enabled)
 		return 0;
 
-	sd->sev_vmcbs = kcalloc(max_sev_asid + 1, sizeof(void *), GFP_KERNEL);
+	sd->sev_vmcbs = kcalloc(nr_asids, sizeof(void *), GFP_KERNEL);
 	if (!sd->sev_vmcbs)
 		return -ENOMEM;
 

arch/x86/kvm/trace.h

···
 		  __entry->outgpa)
 );
 
+TRACE_EVENT(kvm_hv_hypercall_done,
+	TP_PROTO(u64 result),
+	TP_ARGS(result),
+
+	TP_STRUCT__entry(
+		__field(__u64, result)
+	),
+
+	TP_fast_assign(
+		__entry->result	= result;
+	),
+
+	TP_printk("result 0x%llx", __entry->result)
+);
+
 /*
  * Tracepoint for Xen hypercall.
  */

arch/x86/kvm/x86.c

···
 
 static int kvm_vcpu_ready_for_interrupt_injection(struct kvm_vcpu *vcpu)
 {
-	return kvm_arch_interrupt_allowed(vcpu) &&
-		kvm_cpu_accept_dm_intr(vcpu);
+	/*
+	 * Do not cause an interrupt window exit if an exception
+	 * is pending or an event needs reinjection; userspace
+	 * might want to inject the interrupt manually using KVM_SET_REGS
+	 * or KVM_SET_SREGS.  For that to work, we must be at an
+	 * instruction boundary and with no events half-injected.
+	 */
+	return (kvm_arch_interrupt_allowed(vcpu) &&
+		kvm_cpu_accept_dm_intr(vcpu) &&
+		!kvm_event_needs_reinjection(vcpu) &&
+		!vcpu->arch.exception.pending);
 }
 
 static int kvm_vcpu_ioctl_interrupt(struct kvm_vcpu *vcpu,

drivers/bus/mhi/core/internal.h

···
 		      struct image_info *img_info);
 void mhi_fw_load_handler(struct mhi_controller *mhi_cntrl);
 int mhi_prepare_channel(struct mhi_controller *mhi_cntrl,
-			struct mhi_chan *mhi_chan);
+			struct mhi_chan *mhi_chan, unsigned int flags);
 int mhi_init_chan_ctxt(struct mhi_controller *mhi_cntrl,
 		       struct mhi_chan *mhi_chan);
 void mhi_deinit_chan_ctxt(struct mhi_controller *mhi_cntrl,

drivers/bus/mhi/core/main.c

···
 }
 
 int mhi_prepare_channel(struct mhi_controller *mhi_cntrl,
-			struct mhi_chan *mhi_chan)
+			struct mhi_chan *mhi_chan, unsigned int flags)
 {
 	int ret = 0;
 	struct device *dev = &mhi_chan->mhi_dev->dev;
···
 	if (ret)
 		goto error_pm_state;
 
+	if (mhi_chan->dir == DMA_FROM_DEVICE)
+		mhi_chan->pre_alloc = !!(flags & MHI_CH_INBOUND_ALLOC_BUFS);
+	
 	/* Pre-allocate buffer for xfer ring */
 	if (mhi_chan->pre_alloc) {
 		int nr_el = get_nr_avail_ring_elements(mhi_cntrl,
···
 }
 
 /* Move channel to start state */
-int mhi_prepare_for_transfer(struct mhi_device *mhi_dev)
+int mhi_prepare_for_transfer(struct mhi_device *mhi_dev, unsigned int flags)
 {
 	int ret, dir;
 	struct mhi_controller *mhi_cntrl = mhi_dev->mhi_cntrl;
···
 		if (!mhi_chan)
 			continue;
 
-		ret = mhi_prepare_channel(mhi_cntrl, mhi_chan);
+		ret = mhi_prepare_channel(mhi_cntrl, mhi_chan, flags);
 		if (ret)
 			goto error_open_chan;
 	}

drivers/clk/clk-devres.c

···
 }
 EXPORT_SYMBOL_GPL(devm_clk_bulk_get_optional);
 
+static void devm_clk_bulk_release_all(struct device *dev, void *res)
+{
+	struct clk_bulk_devres *devres = res;
+
+	clk_bulk_put_all(devres->num_clks, devres->clks);
+}
+
 int __must_check devm_clk_bulk_get_all(struct device *dev,
 				       struct clk_bulk_data **clks)
 {
 	struct clk_bulk_devres *devres;
 	int ret;
 
-	devres = devres_alloc(devm_clk_bulk_release,
+	devres = devres_alloc(devm_clk_bulk_release_all,
 			      sizeof(*devres), GFP_KERNEL);
 	if (!devres)
 		return -ENOMEM;

drivers/clk/clk-stm32f4.c

···
 
 struct stm32f4_pll_post_div_data {
 	int idx;
-	u8 pll_num;
+	int pll_idx;
 	const char *name;
 	const char *parent;
 	u8 flag;
···
 
 #define MAX_POST_DIV 3
 static const struct stm32f4_pll_post_div_data  post_div_data[MAX_POST_DIV] = {
-	{ CLK_I2SQ_PDIV, PLL_I2S, "plli2s-q-div", "plli2s-q",
+	{ CLK_I2SQ_PDIV, PLL_VCO_I2S, "plli2s-q-div", "plli2s-q",
 		CLK_SET_RATE_PARENT, STM32F4_RCC_DCKCFGR, 0, 5, 0, NULL},
 
-	{ CLK_SAIQ_PDIV, PLL_SAI, "pllsai-q-div", "pllsai-q",
+	{ CLK_SAIQ_PDIV, PLL_VCO_SAI, "pllsai-q-div", "pllsai-q",
 		CLK_SET_RATE_PARENT, STM32F4_RCC_DCKCFGR, 8, 5, 0, NULL },
 
-	{ NO_IDX, PLL_SAI, "pllsai-r-div", "pllsai-r", CLK_SET_RATE_PARENT,
+	{ NO_IDX, PLL_VCO_SAI, "pllsai-r-div", "pllsai-r", CLK_SET_RATE_PARENT,
 		STM32F4_RCC_DCKCFGR, 16, 2, 0, post_divr_table },
 };
 
···
 				post_div->width,
 				post_div->flag_div,
 				post_div->div_table,
-				clks[post_div->pll_num],
+				clks[post_div->pll_idx],
 				&stm32f4_clk_lock);
 
 		if (post_div->idx != NO_IDX)

drivers/clk/hisilicon/Kconfig

···
 config COMMON_CLK_HI3559A
 	bool "Hi3559A Clock Driver"
 	depends on ARCH_HISI || COMPILE_TEST
+	select RESET_HISI
 	default ARCH_HISI
 	help
 	  Build the clock driver for hi3559a.

drivers/clk/qcom/clk-smd-rpm.c

···
 
 static struct clk_smd_rpm *msm8936_clks[] = {
 	[RPM_SMD_PCNOC_CLK]		= &msm8916_pcnoc_clk,
-	[RPM_SMD_PCNOC_A_CLK]		= &msm8916_pcnoc_clk,
+	[RPM_SMD_PCNOC_A_CLK]		= &msm8916_pcnoc_a_clk,
 	[RPM_SMD_SNOC_CLK]		= &msm8916_snoc_clk,
 	[RPM_SMD_SNOC_A_CLK]		= &msm8916_snoc_a_clk,
 	[RPM_SMD_BIMC_CLK]		= &msm8916_bimc_clk,

drivers/clk/tegra/clk-sdmmc-mux.c

···
 	gate_ops->disable(gate_hw);
 }
 
+static void clk_sdmmc_mux_disable_unused(struct clk_hw *hw)
+{
+	struct tegra_sdmmc_mux *sdmmc_mux = to_clk_sdmmc_mux(hw);
+	const struct clk_ops *gate_ops = sdmmc_mux->gate_ops;
+	struct clk_hw *gate_hw = &sdmmc_mux->gate.hw;
+
+	gate_ops->disable_unused(gate_hw);
+}
+
 static void clk_sdmmc_mux_restore_context(struct clk_hw *hw)
 {
 	struct clk_hw *parent = clk_hw_get_parent(hw);
···
 	.is_enabled = clk_sdmmc_mux_is_enabled,
 	.enable = clk_sdmmc_mux_enable,
 	.disable = clk_sdmmc_mux_disable,
+	.disable_unused = clk_sdmmc_mux_disable_unused,
 	.restore_context = clk_sdmmc_mux_restore_context,
 };
 

drivers/gpio/gpio-mpc8xxx.c

···
 
 	ret = devm_request_irq(&pdev->dev, mpc8xxx_gc->irqn,
 			       mpc8xxx_gpio_irq_cascade,
-			       IRQF_SHARED, "gpio-cascade",
+			       IRQF_NO_THREAD | IRQF_SHARED, "gpio-cascade",
 			       mpc8xxx_gc);
 	if (ret) {
 		dev_err(&pdev->dev,

drivers/gpio/gpio-tqmx86.c

···
 	struct resource *res;
 	int ret, irq;
 
-	irq = platform_get_irq(pdev, 0);
-	if (irq < 0)
+	irq = platform_get_irq_optional(pdev, 0);
+	if (irq < 0 && irq != -ENXIO)
 		return irq;
 
 	res = platform_get_resource(pdev, IORESOURCE_IO, 0);
···
 
 	pm_runtime_enable(&pdev->dev);
 
-	if (irq) {
+	if (irq > 0) {
 		struct irq_chip *irq_chip = &gpio->irq_chip;
 		u8 irq_status;
 

drivers/media/common/videobuf2/videobuf2-core.c

···
 		  struct media_request *req)
 {
 	struct vb2_buffer *vb;
+	enum vb2_buffer_state orig_state;
 	int ret;
 
 	if (q->error) {
···
 	 * Add to the queued buffers list, a buffer will stay on it until
 	 * dequeued in dqbuf.
 	 */
+	orig_state = vb->state;
 	list_add_tail(&vb->queued_entry, &q->queued_list);
 	q->queued_count++;
 	q->waiting_for_buffers = false;
···
 	if (q->streaming && !q->start_streaming_called &&
 	    q->queued_count >= q->min_buffers_needed) {
 		ret = vb2_start_streaming(q);
-		if (ret)
+		if (ret) {
+			/*
+			 * Since vb2_core_qbuf will return with an error,
+			 * we should return it to state DEQUEUED since
+			 * the error indicates that the buffer wasn't queued.
+			 */
+			list_del(&vb->queued_entry);
+			q->queued_count--;
+			vb->state = orig_state;
 			return ret;
+		}
 	}
 
 	dprintk(q, 2, "qbuf of buffer %d succeeded\n", vb->index);

drivers/media/platform/atmel/Kconfig

···
 	select VIDEOBUF2_DMA_CONTIG
 	select REGMAP_MMIO
 	select V4L2_FWNODE
+	select VIDEO_ATMEL_ISC_BASE
 	help
 	   This module makes the ATMEL Image Sensor Controller available
 	   as a v4l2 device.
···
 	select VIDEOBUF2_DMA_CONTIG
 	select REGMAP_MMIO
 	select V4L2_FWNODE
+	select VIDEO_ATMEL_ISC_BASE
 	help
 	   This module makes the ATMEL eXtended Image Sensor Controller
 	   available as a v4l2 device.
+
+config VIDEO_ATMEL_ISC_BASE
+	tristate
+	default n
+	help
+	  ATMEL ISC and XISC common code base.
 
 config VIDEO_ATMEL_ISI
 	tristate "ATMEL Image Sensor Interface (ISI) support"

drivers/media/platform/atmel/Makefile

···
 # SPDX-License-Identifier: GPL-2.0-only
-atmel-isc-objs = atmel-sama5d2-isc.o atmel-isc-base.o
-atmel-xisc-objs = atmel-sama7g5-isc.o atmel-isc-base.o
+atmel-isc-objs = atmel-sama5d2-isc.o
+atmel-xisc-objs = atmel-sama7g5-isc.o
 
 obj-$(CONFIG_VIDEO_ATMEL_ISI) += atmel-isi.o
+obj-$(CONFIG_VIDEO_ATMEL_ISC_BASE) += atmel-isc-base.o
 obj-$(CONFIG_VIDEO_ATMEL_ISC) += atmel-isc.o
 obj-$(CONFIG_VIDEO_ATMEL_XISC) += atmel-xisc.o

drivers/media/platform/atmel/atmel-isc-base.c

···
 
 	return 0;
 }
+EXPORT_SYMBOL_GPL(isc_clk_init);
 
 void isc_clk_cleanup(struct isc_device *isc)
 {
···
 			clk_unregister(isc_clk->clk);
 	}
 }
+EXPORT_SYMBOL_GPL(isc_clk_cleanup);
 
 static int isc_queue_setup(struct vb2_queue *vq,
 			    unsigned int *nbuffers, unsigned int *nplanes,
···
 
 	return ret;
 }
+EXPORT_SYMBOL_GPL(isc_interrupt);
 
 static void isc_hist_count(struct isc_device *isc, u32 *min, u32 *max)
 {
···
 	.unbind = isc_async_unbind,
 	.complete = isc_async_complete,
 };
+EXPORT_SYMBOL_GPL(isc_async_ops);
 
 void isc_subdev_cleanup(struct isc_device *isc)
 {
···
 
 	INIT_LIST_HEAD(&isc->subdev_entities);
 }
+EXPORT_SYMBOL_GPL(isc_subdev_cleanup);
 
 int isc_pipeline_init(struct isc_device *isc)
 {
···
 
 	return 0;
 }
+EXPORT_SYMBOL_GPL(isc_pipeline_init);
 
 /* regmap configuration */
 #define ATMEL_ISC_REG_MAX    0xd5c
···
 	.val_bits       = 32,
 	.max_register	= ATMEL_ISC_REG_MAX,
 };
+EXPORT_SYMBOL_GPL(isc_regmap_config);
 
+MODULE_AUTHOR("Songjun Wu");
+MODULE_AUTHOR("Eugen Hristev");
+MODULE_DESCRIPTION("Atmel ISC common code base");
+MODULE_LICENSE("GPL v2");

drivers/media/usb/dvb-usb-v2/rtl28xxu.c

···
 	} else {
 		/* read */
 		requesttype = (USB_TYPE_VENDOR | USB_DIR_IN);
-		pipe = usb_rcvctrlpipe(d->udev, 0);
+
+		/*
+		 * Zero-length transfers must use usb_sndctrlpipe() and
+		 * rtl28xxu_identify_state() uses a zero-length i2c read
+		 * command to determine the chip type.
+		 */
+		if (req->size)
+			pipe = usb_rcvctrlpipe(d->udev, 0);
+		else
+			pipe = usb_sndctrlpipe(d->udev, 0);
 	}
 
 	ret = usb_control_msg(d->udev, pipe, 0, requesttype, req->value,
···
 static int rtl28xxu_identify_state(struct dvb_usb_device *d, const char **name)
 {
 	struct rtl28xxu_dev *dev = d_to_priv(d);
-	u8 buf[1];
 	int ret;
-	struct rtl28xxu_req req_demod_i2c = {0x0020, CMD_I2C_DA_RD, 1, buf};
+	struct rtl28xxu_req req_demod_i2c = {0x0020, CMD_I2C_DA_RD, 0, NULL};
 
 	dev_dbg(&d->intf->dev, "\n");
 

drivers/net/dsa/qca/ar9331.c

···
 		return 0;
 	}
 
-	ret = __ar9331_mdio_write(sbus, AR9331_SW_MDIO_PHY_MODE_REG, reg, val);
-	if (ret < 0)
-		goto error;
-
+	/* In case of this switch we work with 32bit registers on top of 16bit
+	 * bus. Some registers (for example access to forwarding database) have
+	 * trigger bit on the first 16bit half of request, the result and
+	 * configuration of request in the second half.
+	 * To make it work properly, we should do the second part of transfer
+	 * before the first one is done.
+	 */
 	ret = __ar9331_mdio_write(sbus, AR9331_SW_MDIO_PHY_MODE_REG, reg + 2,
 				  val >> 16);
 	if (ret < 0)
 		goto error;
 
+	ret = __ar9331_mdio_write(sbus, AR9331_SW_MDIO_PHY_MODE_REG, reg, val);
+	if (ret < 0)
+		goto error;
+
 	return 0;
+
 error:
 	dev_err_ratelimited(&sbus->dev, "Bus error. Failed to write register.\n");
 	return ret;

drivers/net/dsa/sja1105/sja1105_dynamic_config.c

···
 			hostcmd = SJA1105_HOSTCMD_INVALIDATE;
 	}
 	sja1105_packing(p, &hostcmd, 25, 23, size, op);
+}
+
+static void
+sja1105pqrs_l2_lookup_cmd_packing(void *buf, struct sja1105_dyn_cmd *cmd,
+				  enum packing_op op)
+{
+	int entry_size = SJA1105PQRS_SIZE_L2_LOOKUP_ENTRY;
+
+	sja1105pqrs_common_l2_lookup_cmd_packing(buf, cmd, op, entry_size);
 
 	/* Hack - The hardware takes the 'index' field within
 	 * struct sja1105_l2_lookup_entry as the index on which this command
···
 	 * such that our API doesn't need to ask for a full-blown entry
 	 * structure when e.g. a delete is requested.
 	 */
-	sja1105_packing(buf, &cmd->index, 15, 6,
-			SJA1105PQRS_SIZE_L2_LOOKUP_ENTRY, op);
-}
-
-static void
-sja1105pqrs_l2_lookup_cmd_packing(void *buf, struct sja1105_dyn_cmd *cmd,
-				  enum packing_op op)
-{
-	int size = SJA1105PQRS_SIZE_L2_LOOKUP_ENTRY;
-
-	return sja1105pqrs_common_l2_lookup_cmd_packing(buf, cmd, op, size);
+	sja1105_packing(buf, &cmd->index, 15, 6, entry_size, op);
 }
 
 static void
 sja1110_l2_lookup_cmd_packing(void *buf, struct sja1105_dyn_cmd *cmd,
 			      enum packing_op op)
 {
-	int size = SJA1110_SIZE_L2_LOOKUP_ENTRY;
+	int entry_size = SJA1110_SIZE_L2_LOOKUP_ENTRY;
 
-	return sja1105pqrs_common_l2_lookup_cmd_packing(buf, cmd, op, size);
+	sja1105pqrs_common_l2_lookup_cmd_packing(buf, cmd, op, entry_size);
+
+	sja1105_packing(buf, &cmd->index, 10, 1, entry_size, op);
 }
 
 /* The switch is so retarded that it makes our command/entry abstraction

drivers/net/dsa/sja1105/sja1105_main.c

···
 int sja1105et_fdb_add(struct dsa_switch *ds, int port,
 		      const unsigned char *addr, u16 vid)
 {
-	struct sja1105_l2_lookup_entry l2_lookup = {0};
+	struct sja1105_l2_lookup_entry l2_lookup = {0}, tmp;
 	struct sja1105_private *priv = ds->priv;
 	struct device *dev = ds->dev;
 	int last_unused = -1;
+	int start, end, i;
 	int bin, way, rc;
 
 	bin = sja1105et_fdb_hash(priv, addr, vid);
···
 		 * mask? If yes, we need to do nothing. If not, we need
 		 * to rewrite the entry by adding this port to it.
 		 */
-		if (l2_lookup.destports & BIT(port))
+		if ((l2_lookup.destports & BIT(port)) && l2_lookup.lockeds)
 			return 0;
 		l2_lookup.destports |= BIT(port);
 	} else {
···
 						     index, NULL, false);
 		}
 	}
+	l2_lookup.lockeds = true;
 	l2_lookup.index = sja1105et_fdb_index(bin, way);
 
 	rc = sja1105_dynamic_config_write(priv, BLK_IDX_L2_LOOKUP,
···
 					  true);
 	if (rc < 0)
 		return rc;
+
+	/* Invalidate a dynamically learned entry if that exists */
+	start = sja1105et_fdb_index(bin, 0);
+	end = sja1105et_fdb_index(bin, way);
+
+	for (i = start; i < end; i++) {
+		rc = sja1105_dynamic_config_read(priv, BLK_IDX_L2_LOOKUP,
+						 i, &tmp);
+		if (rc == -ENOENT)
+			continue;
+		if (rc)
+			return rc;
+
+		if (tmp.macaddr != ether_addr_to_u64(addr) || tmp.vlanid != vid)
+			continue;
+
+		rc = sja1105_dynamic_config_write(priv, BLK_IDX_L2_LOOKUP,
+						  i, NULL, false);
+		if (rc)
+			return rc;
+
+		break;
+	}
 
 	return sja1105_static_fdb_change(priv, port, &l2_lookup, true);
 }
···
 int sja1105pqrs_fdb_add(struct dsa_switch *ds, int port,
 			const unsigned char *addr, u16 vid)
 {
-	struct sja1105_l2_lookup_entry l2_lookup = {0};
+	struct sja1105_l2_lookup_entry l2_lookup = {0}, tmp;
 	struct sja1105_private *priv = ds->priv;
 	int rc, i;
 
 	/* Search for an existing entry in the FDB table */
 	l2_lookup.macaddr = ether_addr_to_u64(addr);
 	l2_lookup.vlanid = vid;
-	l2_lookup.iotag = SJA1105_S_TAG;
 	l2_lookup.mask_macaddr = GENMASK_ULL(ETH_ALEN * 8 - 1, 0);
-	if (priv->vlan_aware) {
-		l2_lookup.mask_vlanid = VLAN_VID_MASK;
-		l2_lookup.mask_iotag = BIT(0);
-	} else {
-		l2_lookup.mask_vlanid = 0;
-		l2_lookup.mask_iotag = 0;
-	}
+	l2_lookup.mask_vlanid = VLAN_VID_MASK;
 	l2_lookup.destports = BIT(port);
 
+	tmp = l2_lookup;
+
 	rc = sja1105_dynamic_config_read(priv, BLK_IDX_L2_LOOKUP,
-					 SJA1105_SEARCH, &l2_lookup);
-	if (rc == 0) {
-		/* Found and this port is already in the entry's
+					 SJA1105_SEARCH, &tmp);
+	if (rc == 0 && tmp.index != SJA1105_MAX_L2_LOOKUP_COUNT - 1) {
+		/* Found a static entry and this port is already in the entry's
 		 * port mask => job done
 		 */
-		if (l2_lookup.destports & BIT(port))
+		if ((tmp.destports & BIT(port)) && tmp.lockeds)
 			return 0;
+
+		l2_lookup = tmp;
+
 		/* l2_lookup.index is populated by the switch in case it
 		 * found something.
 		 */
···
 		dev_err(ds->dev, "FDB is full, cannot add entry.\n");
 		return -EINVAL;
 	}
-	l2_lookup.lockeds = true;
 	l2_lookup.index = i;
 
 skip_finding_an_index:
+	l2_lookup.lockeds = true;
+
 	rc = sja1105_dynamic_config_write(priv, BLK_IDX_L2_LOOKUP,
 					  l2_lookup.index, &l2_lookup,
 					  true);
 	if (rc < 0)
 		return rc;
+
+	/* The switch learns dynamic entries and looks up the FDB left to
+	 * right. It is possible that our addition was concurrent with the
+	 * dynamic learning of the same address, so now that the static entry
+	 * has been installed, we are certain that address learning for this
+	 * particular address has been turned off, so the dynamic entry either
+	 * is in the FDB at an index smaller than the static one, or isn't (it
+	 * can also be at a larger index, but in that case it is inactive
+	 * because the static FDB entry will match first, and the dynamic one
+	 * will eventually age out). Search for a dynamically learned address
+	 * prior to our static one and invalidate it.
+	 */
+	tmp = l2_lookup;
+
+	rc = sja1105_dynamic_config_read(priv, BLK_IDX_L2_LOOKUP,
+					 SJA1105_SEARCH, &tmp);
+	if (rc < 0) {
+		dev_err(ds->dev,
+			"port %d failed to read back entry for %pM vid %d: %pe\n",
+			port, addr, vid, ERR_PTR(rc));
+		return rc;
+	}
+
+	if (tmp.index < l2_lookup.index) {
+		rc = sja1105_dynamic_config_write(priv, BLK_IDX_L2_LOOKUP,
+						  tmp.index, NULL, false);
+		if (rc < 0)
+			return rc;
+	}
 
 	return sja1105_static_fdb_change(priv, port, &l2_lookup, true);
 }
···
 
 	l2_lookup.macaddr = ether_addr_to_u64(addr);
 	l2_lookup.vlanid = vid;
-	l2_lookup.iotag = SJA1105_S_TAG;
 	l2_lookup.mask_macaddr = GENMASK_ULL(ETH_ALEN * 8 - 1, 0);
-	if (priv->vlan_aware) {
-		l2_lookup.mask_vlanid = VLAN_VID_MASK;
-		l2_lookup.mask_iotag = BIT(0);
-	} else {
-		l2_lookup.mask_vlanid = 0;
-		l2_lookup.mask_iotag = 0;
-	}
+	l2_lookup.mask_vlanid = VLAN_VID_MASK;
 	l2_lookup.destports = BIT(port);
 
 	rc = sja1105_dynamic_config_read(priv, BLK_IDX_L2_LOOKUP,

drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c

···
 	}
 
 	/* Allocated memory for FW statistics  */
-	if (bnx2x_alloc_fw_stats_mem(bp))
+	rc = bnx2x_alloc_fw_stats_mem(bp);
+	if (rc)
 		LOAD_ERROR_EXIT(bp, load_error0);
 
 	/* request pf to initialize status blocks */

drivers/net/ethernet/freescale/fec_main.c

···
 	if (of_phy_is_fixed_link(np))
 		of_phy_deregister_fixed_link(np);
 	of_node_put(fep->phy_node);
-	free_netdev(ndev);
 
 	clk_disable_unprepare(fep->clk_ahb);
 	clk_disable_unprepare(fep->clk_ipg);
 	pm_runtime_put_noidle(&pdev->dev);
 	pm_runtime_disable(&pdev->dev);
 
+	free_netdev(ndev);
 	return 0;
 }
 

drivers/net/ethernet/marvell/prestera/prestera_devlink.c

···
 		prestera_trap = &prestera_trap_items_arr[i];
 		devlink_traps_unregister(devlink, &prestera_trap->trap, 1);
 	}
+	devlink_trap_groups_unregister(devlink, prestera_trap_groups_arr,
+				       groups_count);
 err_groups_register:
 	kfree(trap_data->trap_items_arr);
 err_trap_items_alloc:

drivers/net/ethernet/microchip/sparx5/sparx5_netdev.c

···
  */
 #define VSTAX 73
 
-static void ifh_encode_bitfield(void *ifh, u64 value, u32 pos, u32 width)
+#define ifh_encode_bitfield(ifh, value, pos, _width)			\
+	({								\
+		u32 width = (_width);					\
+									\
+		/* Max width is 5 bytes - 40 bits. In worst case this will
+		 * spread over 6 bytes - 48 bits
+		 */							\
+		compiletime_assert(width <= 40,				\
+				   "Unsupported width, must be <= 40");	\
+		__ifh_encode_bitfield((ifh), (value), (pos), width);	\
+	})
+
+static void __ifh_encode_bitfield(void *ifh, u64 value, u32 pos, u32 width)
 {
 	u8 *ifh_hdr = ifh;
 	/* Calculate the Start IFH byte position of this IFH bit position */
 	u32 byte = (35 - (pos / 8));
 	/* Calculate the Start bit position in the Start IFH byte */
 	u32 bit  = (pos % 8);
-	u64 encode = GENMASK(bit + width - 1, bit) & (value << bit);
-
-	/* Max width is 5 bytes - 40 bits. In worst case this will
-	 * spread over 6 bytes - 48 bits
-	 */
-	compiletime_assert(width <= 40, "Unsupported width, must be <= 40");
+	u64 encode = GENMASK_ULL(bit + width - 1, bit) & (value << bit);
 
 	/* The b0-b7 goes into the start IFH byte */
 	if (encode & 0xFF)

drivers/net/ethernet/natsemi/natsemi.c

···
 		printk(version);
 #endif
 
-	i = pci_enable_device(pdev);
+	i = pcim_enable_device(pdev);
 	if (i) return i;
 
 	/* natsemi has a non-standard PM control register
···
 	ioaddr = ioremap(iostart, iosize);
 	if (!ioaddr) {
 		i = -ENOMEM;
-		goto err_ioremap;
+		goto err_pci_request_regions;
 	}
 
 	/* Work around the dropped serial bit. */
···
 
  err_register_netdev:
 	iounmap(ioaddr);
-
- err_ioremap:
-	pci_release_regions(pdev);
 
  err_pci_request_regions:
 	free_netdev(dev);
···
 
 	NATSEMI_REMOVE_FILE(pdev, dspcfg_workaround);
 	unregister_netdev (dev);
-	pci_release_regions (pdev);
 	iounmap(ioaddr);
 	free_netdev (dev);
 }

drivers/net/ethernet/neterion/vxge/vxge-main.c

···
 
 	kfree(vdev->vpaths);
 
-	/* we are safe to free it now */
-	free_netdev(dev);
-
 	vxge_debug_init(vdev->level_trace, "%s: ethernet device unregistered",
 			buf);
 	vxge_debug_entryexit(vdev->level_trace,	"%s: %s:%d  Exiting...", buf,
 			     __func__, __LINE__);
+
+	/* we are safe to free it now */
+	free_netdev(dev);
 }
 
 /*

drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c

···
 
 	/* Init to unknowns */
 	ethtool_link_ksettings_add_link_mode(cmd, supported, FIBRE);
+	ethtool_link_ksettings_add_link_mode(cmd, supported, Pause);
+	ethtool_link_ksettings_add_link_mode(cmd, advertising, Pause);
 	cmd->base.port = PORT_OTHER;
 	cmd->base.speed = SPEED_UNKNOWN;
 	cmd->base.duplex = DUPLEX_UNKNOWN;

drivers/net/ethernet/qlogic/qede/qede.h

···
 #define QEDE_SP_HW_ERR                  4
 #define QEDE_SP_ARFS_CONFIG             5
 #define QEDE_SP_AER			7
+#define QEDE_SP_DISABLE			8
 
 #ifdef CONFIG_RFS_ACCEL
 int qede_rx_flow_steer(struct net_device *dev, const struct sk_buff *skb,

drivers/net/ethernet/qlogic/qede/qede_main.c

···
 	struct qede_dev *edev = container_of(work, struct qede_dev,
 					     sp_task.work);
 
+	/* Disable execution of this deferred work once
+	 * qede removal is in progress, this stop any future
+	 * scheduling of sp_task.
+	 */
+	if (test_bit(QEDE_SP_DISABLE, &edev->sp_flags))
+		return;
+
 	/* The locking scheme depends on the specific flag:
 	 * In case of QEDE_SP_RECOVERY, acquiring the RTNL lock is required to
 	 * ensure that ongoing flows are ended and new ones are not started.
···
 	qede_rdma_dev_remove(edev, (mode == QEDE_REMOVE_RECOVERY));
 
 	if (mode != QEDE_REMOVE_RECOVERY) {
+		set_bit(QEDE_SP_DISABLE, &edev->sp_flags);
 		unregister_netdev(ndev);
 
 		cancel_delayed_work_sync(&edev->sp_task);

drivers/net/ethernet/ti/am65-cpsw-nuss.c

···
 
 	for (i = 1; i <= common->port_num; i++) {
 		struct am65_cpsw_port *port = am65_common_get_port(common, i);
-		struct am65_cpsw_ndev_priv *priv = am65_ndev_to_priv(port->ndev);
+		struct am65_cpsw_ndev_priv *priv;
 
+		if (!port->ndev)
+			continue;
+
+		priv = am65_ndev_to_priv(port->ndev);
 		priv->offload_fwd_mark = set_val;
 	}
 }

drivers/net/mhi_net.c

···
 	u64_stats_init(&mhi_netdev->stats.tx_syncp);
 
 	/* Start MHI channels */
-	err = mhi_prepare_for_transfer(mhi_dev);
+	err = mhi_prepare_for_transfer(mhi_dev, 0);
 	if (err)
 		goto out_err;
 

drivers/net/phy/micrel.c

···
 }
 
 static int ksz8051_ksz8795_match_phy_device(struct phy_device *phydev,
-					    const u32 ksz_phy_id)
+					    const bool ksz_8051)
 {
 	int ret;
 
-	if ((phydev->phy_id & MICREL_PHY_ID_MASK) != ksz_phy_id)
+	if ((phydev->phy_id & MICREL_PHY_ID_MASK) != PHY_ID_KSZ8051)
 		return 0;
 
 	ret = phy_read(phydev, MII_BMSR);
···
 	 * the switch does not.
 	 */
 	ret &= BMSR_ERCAP;
-	if (ksz_phy_id == PHY_ID_KSZ8051)
+	if (ksz_8051)
 		return ret;
 	else
 		return !ret;
···
 
 static int ksz8051_match_phy_device(struct phy_device *phydev)
 {
-	return ksz8051_ksz8795_match_phy_device(phydev, PHY_ID_KSZ8051);
+	return ksz8051_ksz8795_match_phy_device(phydev, true);
 }
 
 static int ksz8081_config_init(struct phy_device *phydev)
···
 
 static int ksz8795_match_phy_device(struct phy_device *phydev)
 {
-	return ksz8051_ksz8795_match_phy_device(phydev, PHY_ID_KSZ87XX);
+	return ksz8051_ksz8795_match_phy_device(phydev, false);
 }
 
 static int ksz9021_load_values_from_of(struct phy_device *phydev,

drivers/net/usb/lan78xx.c

···
 {
 	struct phy_device *phydev = dev->net->phydev;
 	struct ethtool_link_ksettings ecmd;
-	int ladv, radv, ret;
+	int ladv, radv, ret, link;
 	u32 buf;
 
 	/* clear LAN78xx interrupt status */
···
 	if (unlikely(ret < 0))
 		return -EIO;
 
+	mutex_lock(&phydev->lock);
 	phy_read_status(phydev);
+	link = phydev->link;
+	mutex_unlock(&phydev->lock);
 
-	if (!phydev->link && dev->link_on) {
+	if (!link && dev->link_on) {
 		dev->link_on = false;
 
 		/* reset MAC */
···
 			return -EIO;
 
 		del_timer(&dev->stat_monitor);
-	} else if (phydev->link && !dev->link_on) {
+	} else if (link && !dev->link_on) {
 		dev->link_on = true;
 
 		phy_ethtool_ksettings_get(phydev, &ecmd);
···
 
 static u32 lan78xx_get_link(struct net_device *net)
 {
-	phy_read_status(net->phydev);
+	u32 link;
 
-	return net->phydev->link;
+	mutex_lock(&net->phydev->lock);
+	phy_read_status(net->phydev);
+	link = net->phydev->link;
+	mutex_unlock(&net->phydev->lock);
+
+	return link;
 }
 
 static void lan78xx_get_drvinfo(struct net_device *net,

drivers/net/usb/pegasus.c

···
 // SPDX-License-Identifier: GPL-2.0-only
 /*
- *  Copyright (c) 1999-2013 Petko Manolov ([e-mail])
+ *  Copyright (c) 1999-2021 Petko Manolov ([e-mail])
  *
- *	ChangeLog:
- *		....	Most of the time spent on reading sources & docs.
- *		v0.2.x	First official release for the Linux kernel.
- *		v0.3.0	Beutified and structured, some bugs fixed.
- *		v0.3.x	URBifying bulk requests and bugfixing. First relatively
- *			stable release. Still can touch device's registers only
- *			from top-halves.
- *		v0.4.0	Control messages remained unurbified are now URBs.
- *			Now we can touch the HW at any time.
- *		v0.4.9	Control urbs again use process context to wait. Argh...
- *			Some long standing bugs (enable_net_traffic) fixed.
- *			Also nasty trick about resubmiting control urb from
- *			interrupt context used. Please let me know how it
- *			behaves. Pegasus II support added since this version.
- *			TODO: suppressing HCD warnings spewage on disconnect.
- *		v0.4.13	Ethernet address is now set at probe(), not at open()
- *			time as this seems to break dhcpd.
- *		v0.5.0	branch to 2.5.x kernels
- *		v0.5.1	ethtool support added
- *		v0.5.5	rx socket buffers are in a pool and the their allocation
- *			is out of the interrupt routine.
- *		...
- *		v0.9.3	simplified [get|set]_register(s), async update registers
- *			logic revisited, receive skb_pool removed.
  */
 
 #include <linux/sched.h>
···
 /*
  * Version Information
  */
-#define DRIVER_VERSION "v0.9.3 (2013/04/25)"
 #define DRIVER_AUTHOR "Petko Manolov <[e-mail]>"
 #define DRIVER_DESC "Pegasus/Pegasus II USB Ethernet driver"
 
···
 static int set_registers(pegasus_t *pegasus, __u16 indx, __u16 size,
 			 const void *data)
 {
-	return usb_control_msg_send(pegasus->usb, 0, PEGASUS_REQ_SET_REGS,
+	int ret;
+
+	ret = usb_control_msg_send(pegasus->usb, 0, PEGASUS_REQ_SET_REGS,
 				    PEGASUS_REQT_WRITE, 0, indx, data, size,
 				    1000, GFP_NOIO);
+	if (ret < 0)
+		netif_dbg(pegasus, drv, pegasus->net, "%s failed with %d\n", __func__, ret);
+
+	return ret;
 }
 
 /*
···
 static int set_register(pegasus_t *pegasus, __u16 indx, __u8 data)
 {
 	void *buf = &data;
+	int ret;
 
-	return usb_control_msg_send(pegasus->usb, 0, PEGASUS_REQ_SET_REG,
+	ret = usb_control_msg_send(pegasus->usb, 0, PEGASUS_REQ_SET_REG,
 				    PEGASUS_REQT_WRITE, data, indx, buf, 1,
 				    1000, GFP_NOIO);
+	if (ret < 0)
+		netif_dbg(pegasus, drv, pegasus->net, "%s failed with %d\n", __func__, ret);
+
+	return ret;
 }
 
 static int update_eth_regs_async(pegasus_t *pegasus)
···
 
 static int __mii_op(pegasus_t *p, __u8 phy, __u8 indx, __u16 *regd, __u8 cmd)
 {
-	int i;
-	__u8 data[4] = { phy, 0, 0, indx };
+	int i, ret;
 	__le16 regdi;
-	int ret = -ETIMEDOUT;
+	__u8 data[4] = { phy, 0, 0, indx };
 
 	if (cmd & PHY_WRITE) {
 		__le16 *t = (__le16 *) & data[1];
···
 		if (data[0] & PHY_DONE)
 			break;
 	}
-	if (i >= REG_TIMEOUT)
+	if (i >= REG_TIMEOUT) {
+		ret = -ETIMEDOUT;
 		goto fail;
+	}
 	if (cmd & PHY_READ) {
 		ret = get_registers(p, PhyData, 2, &regdi);
+		if (ret < 0)
+			goto fail;
 		*regd = le16_to_cpu(regdi);
-		return ret;
 	}
 	return 0;
 fail:
···
 static int mdio_read(struct net_device *dev, int phy_id, int loc)
 {
 	pegasus_t *pegasus = netdev_priv(dev);
+	int ret;
 	u16 res;
 
-	read_mii_word(pegasus, phy_id, loc, &res);
+	ret = read_mii_word(pegasus, phy_id, loc, &res);
+	if (ret < 0)
+		return ret;
+
 	return (int)res;
 }
 
···
 
 static int read_eprom_word(pegasus_t *pegasus, __u8 index, __u16 *retdata)
 {
-	int i;
-	__u8 tmp = 0;
+	int ret, i;
 	__le16 retdatai;
-	int ret;
+	__u8 tmp = 0;
 
 	set_register(pegasus, EpromCtrl, 0);
 	set_register(pegasus, EpromOffset, index);
···
 
 	for (i = 0; i < REG_TIMEOUT; i++) {
 		ret = get_registers(pegasus, EpromCtrl, 1, &tmp);
+		if (ret < 0)
+			goto fail;
 		if (tmp & EPROM_DONE)
 			break;
-		if (ret == -ESHUTDOWN)
-			goto fail;
 	}
-	if (i >= REG_TIMEOUT)
+	if (i >= REG_TIMEOUT) {
+		ret = -ETIMEDOUT;
 		goto fail;
+	}
 
 	ret = get_registers(pegasus, EpromData, 2, &retdatai);
+	if (ret < 0)
+		goto fail;
 	*retdata = le16_to_cpu(retdatai);
 	return ret;
 
 fail:
-	netif_warn(pegasus, drv, pegasus->net, "%s failed\n", __func__);
-	return -ETIMEDOUT;
+	netif_dbg(pegasus, drv, pegasus->net, "%s failed\n", __func__);
+	return ret;
 }
 
 #ifdef	PEGASUS_WRITE_EEPROM
···
 	return ret;
 
 fail:
-	netif_warn(pegasus, drv, pegasus->net, "%s failed\n", __func__);
+	netif_dbg(pegasus, drv, pegasus->net, "%s failed\n", __func__);
 	return -ETIMEDOUT;
 }
-#endif				/* PEGASUS_WRITE_EEPROM */
+#endif	/* PEGASUS_WRITE_EEPROM */
 
 static inline int get_node_id(pegasus_t *pegasus, u8 *id)
 {
···
 	return;
 err:
 	eth_hw_addr_random(pegasus->net);
-	dev_info(&pegasus->intf->dev, "software assigned MAC address.\n");
+	netif_dbg(pegasus, drv, pegasus->net, "software assigned MAC address.\n");
 
 	return;
 }
 
 static inline int reset_mac(pegasus_t *pegasus)
 {
+	int ret, i;
 	__u8 data = 0x8;
-	int i;
 
 	set_register(pegasus, EthCtrl1, data);
 	for (i = 0; i < REG_TIMEOUT; i++) {
-		get_registers(pegasus, EthCtrl1, 1, &data);
+		ret = get_registers(pegasus, EthCtrl1, 1, &data);
+		if (ret < 0)
+			goto fail;
 		if (~data & 0x08) {
 			if (loopback)
 				break;
···
 	}
 	if (usb_dev_id[pegasus->dev_index].vendor == VENDOR_ELCON) {
 		__u16 auxmode;
-		read_mii_word(pegasus, 3, 0x1b, &auxmode);
+		ret = read_mii_word(pegasus, 3, 0x1b, &auxmode);
+		if (ret < 0)
+			goto fail;
 		auxmode |= 4;
 		write_mii_word(pegasus, 3, 0x1b, &auxmode);
 	}
 
 	return 0;
+fail:
+	netif_dbg(pegasus, drv, pegasus->net, "%s failed\n", __func__);
+	return ret;
 }
 
 static int enable_net_traffic(struct net_device *dev, struct usb_device *usb)
 {
-	__u16 linkpart;
-	__u8 data[4];
 	pegasus_t *pegasus = netdev_priv(dev);
 	int ret;
+	__u16 linkpart;
+	__u8 data[4];
 
-	read_mii_word(pegasus, pegasus->phy, MII_LPA, &linkpart);
+	ret = read_mii_word(pegasus, pegasus->phy, MII_LPA, &linkpart);
+	if (ret < 0)
+		goto fail;
 	data[0] = 0xc8; /* TX & RX enable, append status, no CRC */
 	data[1] = 0;
 	if (linkpart & (ADVERTISE_100FULL | ADVERTISE_10FULL))
···
 	    usb_dev_id[pegasus->dev_index].vendor == VENDOR_LINKSYS2 ||
 	    usb_dev_id[pegasus->dev_index].vendor == VENDOR_DLINK) {
 		u16 auxmode;
-		read_mii_word(pegasus, 0, 0x1b, &auxmode);
+		ret = read_mii_word(pegasus, 0, 0x1b, &auxmode);
+		if (ret < 0)
+			goto fail;
 		auxmode |= 4;
 		write_mii_word(pegasus, 0, 0x1b, &auxmode);
 	}
 
+	return 0;
+fail:
+	netif_dbg(pegasus, drv, pegasus->net, "%s failed\n", __func__);
 	return ret;
 }
 
···
 {
 	pegasus_t *pegasus = urb->context;
 	struct net_device *net;
+	u8 *buf = urb->transfer_buffer;
 	int rx_status, count = urb->actual_length;
 	int status = urb->status;
-	u8 *buf = urb->transfer_buffer;
 	__u16 pkt_len;
 
 	if (!pegasus)
···
 	set_registers(pegasus, EthCtrl0, sizeof(tmp), &tmp);
 }
 
-static inline void get_interrupt_interval(pegasus_t *pegasus)
+static inline int get_interrupt_interval(pegasus_t *pegasus)
 {
 	u16 data;
 	u8 interval;
+	int ret;
 
-	read_eprom_word(pegasus, 4, &data);
+	ret = read_eprom_word(pegasus, 4, &data);
+	if (ret < 0)
+		return ret;
+
 	interval = data >> 8;
 	if (pegasus->usb->speed != USB_SPEED_HIGH) {
 		if (interval < 0x80) {
···
 		}
 	}
 	pegasus->intr_interval = interval;
+
+	return 0;
 }
 
 static void set_carrier(struct net_device *net)
···
 	pegasus_t *pegasus = netdev_priv(dev);
 
 	strlcpy(info->driver, driver_name, sizeof(info->driver));
-	strlcpy(info->version, DRIVER_VERSION, sizeof(info->version));
 	usb_make_path(pegasus->usb, info->bus_info, sizeof(info->bus_info));
 }
 
···
 		data[0] = pegasus->phy;
 		fallthrough;
 	case SIOCDEVPRIVATE + 1:
-		read_mii_word(pegasus, data[0], data[1] & 0x1f, &data[3]);
-		res = 0;
+		res = read_mii_word(pegasus, data[0], data[1] & 0x1f, &data[3]);
 		break;
 	case SIOCDEVPRIVATE + 2:
 		if (!capable(CAP_NET_ADMIN))
···
 
 static __u8 mii_phy_probe(pegasus_t *pegasus)
 {
-	int i;
+	int i, ret;
 	__u16 tmp;
 
 	for (i = 0; i < 32; i++) {
-		read_mii_word(pegasus, i, MII_BMSR, &tmp);
+		ret = read_mii_word(pegasus, i, MII_BMSR, &tmp);
+		if (ret < 0)
+			goto fail;
 		if (tmp == 0 || tmp == 0xffff || (tmp & BMSR_MEDIA) == 0)
 			continue;
 		else
 			return i;
 	}
-
+fail:
 	return 0xff;
 }
 
 static inline void setup_pegasus_II(pegasus_t *pegasus)
 {
+	int ret;
 	__u8 data = 0xa5;
 
 	set_register(pegasus, Reg1d, 0);
···
 		set_register(pegasus, Reg7b, 2);
 
 	set_register(pegasus, 0x83, data);
-	get_registers(pegasus, 0x83, 1, &data);
+	ret = get_registers(pegasus, 0x83, 1, &data);
+	if (ret < 0)
+		goto fail;
 
 	if (data == 0xa5)
 		pegasus->chip = 0x8513;
···
 		set_register(pegasus, Reg81, 6);
 	else
 		set_register(pegasus, Reg81, 2);
+
+	return;
+fail:
+	netif_dbg(pegasus, drv, pegasus->net, "%s failed\n", __func__);
 }
 
 static void check_carrier(struct work_struct *work)
···
 				| NETIF_MSG_PROBE | NETIF_MSG_LINK);
 
 	pegasus->features = usb_dev_id[dev_index].private;
-	get_interrupt_interval(pegasus);
+	res = get_interrupt_interval(pegasus);
+	if (res)
+		goto out2;
 	if (reset_mac(pegasus)) {
 		dev_err(&intf->dev, "can't reset MAC\n");
 		res = -EIO;
···
 
 static int __init pegasus_init(void)
 {
-	pr_info("%s: %s, " DRIVER_DESC "\n", driver_name, DRIVER_VERSION);
+	pr_info("%s: " DRIVER_DESC "\n", driver_name);
 	if (devid)
 		parse_id(devid);
 	return usb_register(&pegasus_driver);

drivers/net/wwan/iosm/iosm_ipc_mmio.h

···
 #define IOSM_CP_VERSION 0x0100UL
 
 /* DL dir Aggregation support mask */
-#define DL_AGGR BIT(23)
+#define DL_AGGR BIT(9)
 
 /* UL dir Aggregation support mask */
-#define UL_AGGR BIT(22)
+#define UL_AGGR BIT(8)
 
 /* UL flow credit support mask */
 #define UL_FLOW_CREDIT BIT(21)

drivers/net/wwan/iosm/iosm_ipc_mux_codec.c

···
 		return;
 	}
 
-	ul_credits = fct->vfl.nr_of_bytes;
+	ul_credits = le32_to_cpu(fct->vfl.nr_of_bytes);
 
 	dev_dbg(ipc_mux->dev, "Flow_Credit:: if_id[%d] Old: %d Grants: %d",
 		if_id, ipc_mux->session[if_id].ul_flow_credits, ul_credits);
···
 		qlt->reserved[0] = 0;
 		qlt->reserved[1] = 0;
 
-		qlt->vfl.nr_of_bytes = session->ul_list.qlen;
+		qlt->vfl.nr_of_bytes = cpu_to_le32(session->ul_list.qlen);
 
 		/* Add QLT to the transfer list. */
 		skb_queue_tail(&ipc_mux->channel->ul_list,

drivers/net/wwan/iosm/iosm_ipc_mux_codec.h

···
  * @nr_of_bytes:	Number of bytes available to transmit in the queue.
  */
 struct mux_lite_vfl {
-	u32 nr_of_bytes;
+	__le32 nr_of_bytes;
 };
 
 /**

drivers/net/wwan/iosm/iosm_ipc_protocol_ops.c

···
 	}
 
 	if (p_td->buffer.address != IPC_CB(skb)->mapping) {
-		dev_err(ipc_protocol->dev, "invalid buf=%p or skb=%p",
-			(void *)p_td->buffer.address, skb->data);
+		dev_err(ipc_protocol->dev, "invalid buf=%llx or skb=%p",
+			(unsigned long long)p_td->buffer.address, skb->data);
 		ipc_pcie_kfree_skb(ipc_protocol->pcie, skb);
 		skb = NULL;
 		goto ret;

drivers/net/wwan/iosm/iosm_ipc_wwan.c

···
 
 	RCU_INIT_POINTER(ipc_wwan->sub_netlist[if_id], NULL);
 	/* unregistering includes synchronize_net() */
-	unregister_netdevice(dev);
+	unregister_netdevice_queue(dev, head);
 
 unlock:
 	mutex_unlock(&ipc_wwan->if_mutex);

drivers/net/wwan/mhi_wwan_ctrl.c

···
 	int ret;
 
 	/* Start mhi device's channel(s) */
-	ret = mhi_prepare_for_transfer(mhiwwan->mhi_dev);
+	ret = mhi_prepare_for_transfer(mhiwwan->mhi_dev, 0);
 	if (ret)
 		return ret;
 

drivers/net/wwan/mhi_wwan_mbim.c

···
 	INIT_DELAYED_WORK(&mbim->rx_refill, mhi_net_rx_refill_work);
 
 	/* Start MHI channels */
-	err = mhi_prepare_for_transfer(mhi_dev);
+	err = mhi_prepare_for_transfer(mhi_dev, 0);
 	if (err)
 		return err;
 

drivers/pcmcia/i82092.c

···
 	for (i = 0; i < socket_count; i++) {
 		sockets[i].card_state = 1; /* 1 = present but empty */
 		sockets[i].io_base = pci_resource_start(dev, 0);
+		sockets[i].dev = dev;
 		sockets[i].socket.features |= SS_CAP_PCCARD;
 		sockets[i].socket.map_size = 0x1000;
 		sockets[i].socket.irq_mask = 0;

drivers/scsi/device_handler/scsi_dh_rdac.c

···
 		if (!h->ctlr)
 			err = SCSI_DH_RES_TEMP_UNAVAIL;
 		else {
-			list_add_rcu(&h->node, &h->ctlr->dh_list);
 			h->sdev = sdev;
+			list_add_rcu(&h->node, &h->ctlr->dh_list);
 		}
 		spin_unlock(&list_lock);
 		err = SCSI_DH_OK;
···
 	spin_lock(&list_lock);
 	if (h->ctlr) {
 		list_del_rcu(&h->node);
-		h->sdev = NULL;
 		kref_put(&h->ctlr->kref, release_controller);
 	}
 	spin_unlock(&list_lock);
 	sdev->handler_data = NULL;
+	synchronize_rcu();
 	kfree(h);
 }
 

drivers/scsi/ibmvscsi/ibmvfc.c

···
 	for (i = 0; i < size; ++i) {
 		struct ibmvfc_event *evt = &pool->events[i];
 
+		/*
+		 * evt->active states
+		 *  1 = in flight
+		 *  0 = being completed
+		 * -1 = free/freed
+		 */
+		atomic_set(&evt->active, -1);
 		atomic_set(&evt->free, 1);
 		evt->crq.valid = 0x80;
 		evt->crq.ioba = cpu_to_be64(pool->iu_token + (sizeof(*evt->xfer_iu) * i));
···
 
 	BUG_ON(!ibmvfc_valid_event(pool, evt));
 	BUG_ON(atomic_inc_return(&evt->free) != 1);
+	BUG_ON(atomic_dec_and_test(&evt->active));
 
 	spin_lock_irqsave(&evt->queue->l_lock, flags);
 	list_add_tail(&evt->queue_list, &evt->queue->free);
···
  **/
 static void ibmvfc_fail_request(struct ibmvfc_event *evt, int error_code)
 {
+	/*
+	 * Anything we are failing should still be active. Otherwise, it
+	 * implies we already got a response for the command and are doing
+	 * something bad like double completing it.
+	 */
+	BUG_ON(!atomic_dec_and_test(&evt->active));
 	if (evt->cmnd) {
 		evt->cmnd->result = (error_code << 16);
 		evt->done = ibmvfc_scsi_eh_done;
···
 
 		evt->done(evt);
 	} else {
+		atomic_set(&evt->active, 1);
 		spin_unlock_irqrestore(&evt->queue->l_lock, flags);
 		ibmvfc_trc_start(evt);
 	}
···
 		return;
 	}
 
-	if (unlikely(atomic_read(&evt->free))) {
+	if (unlikely(atomic_dec_if_positive(&evt->active))) {
 		dev_err(vhost->dev, "Received duplicate correlation_token 0x%08llx!\n",
 			crq->ioba);
 		return;
···
 		return;
 	}
 
-	if (unlikely(atomic_read(&evt->free))) {
+	if (unlikely(atomic_dec_if_positive(&evt->active))) {
 		dev_err(vhost->dev, "Received duplicate correlation_token 0x%08llx!\n",
 			crq->ioba);
 		return;

drivers/scsi/ibmvscsi/ibmvfc.h

···
 	struct ibmvfc_target *tgt;
 	struct scsi_cmnd *cmnd;
 	atomic_t free;
+	atomic_t active;
 	union ibmvfc_iu *xfer_iu;
 	void (*done)(struct ibmvfc_event *evt);
 	void (*_done)(struct ibmvfc_event *evt);

drivers/scsi/megaraid/megaraid_mm.c

···
 	mimd_t		mimd;
 	uint32_t	adapno;
 	int		iterator;
-
+	bool		is_found;
 
 	if (copy_from_user(&mimd, umimd, sizeof(mimd_t))) {
 		*rval = -EFAULT;
···
 
 	adapter = NULL;
 	iterator = 0;
+	is_found = false;
 
 	list_for_each_entry(adapter, &adapters_list_g, list) {
-		if (iterator++ == adapno) break;
+		if (iterator++ == adapno) {
+			is_found = true;
+			break;
+		}
 	}
 
-	if (!adapter) {
+	if (!is_found) {
 		*rval = -ENODEV;
 		return NULL;
 	}
···
 	uint32_t	adapno;
 	int		iterator;
 	mraid_mmadp_t*	adapter;
+	bool		is_found;
 
 	/*
 	 * When the kioc returns from driver, make sure it still doesn't
···
 		iterator	= 0;
 		adapter		= NULL;
 		adapno		= kioc->adapno;
+		is_found	= false;
 
 		con_log(CL_ANN, ( KERN_WARNING "megaraid cmm: completed "
 					"ioctl that was timedout before\n"));
 
 		list_for_each_entry(adapter, &adapters_list_g, list) {
-			if (iterator++ == adapno) break;
+			if (iterator++ == adapno) {
+				is_found = true;
+				break;
+			}
 		}
 
 		kioc->timedout = 0;
 
-		if (adapter) {
+		if (is_found)
 			mraid_mm_dealloc_kioc( adapter, kioc );
-		}
+
 	}
 	else {
 		wake_up(&wait_q);

drivers/scsi/pm8001/pm8001_sas.c

···
 
 void pm8001_task_done(struct sas_task *task)
 {
-	if (!del_timer(&task->slow_task->timer))
-		return;
+	del_timer(&task->slow_task->timer);
 	complete(&task->slow_task->completion);
 }
 
···
 {
 	struct sas_task_slow *slow = from_timer(slow, t, timer);
 	struct sas_task *task = slow->task;
+	unsigned long flags;
 
-	task->task_state_flags |= SAS_TASK_STATE_ABORTED;
-	complete(&task->slow_task->completion);
+	spin_lock_irqsave(&task->task_state_lock, flags);
+	if (!(task->task_state_flags & SAS_TASK_STATE_DONE)) {
+		task->task_state_flags |= SAS_TASK_STATE_ABORTED;
+		complete(&task->slow_task->completion);
+	}
+	spin_unlock_irqrestore(&task->task_state_lock, flags);
 }
 
 #define PM8001_TASK_TIMEOUT 20
···
 		}
 		res = -TMF_RESP_FUNC_FAILED;
 		/* Even TMF timed out, return direct. */
-		if ((task->task_state_flags & SAS_TASK_STATE_ABORTED)) {
-			if (!(task->task_state_flags & SAS_TASK_STATE_DONE)) {
-				pm8001_dbg(pm8001_ha, FAIL,
-					   "TMF task[%x]timeout.\n",
-					   tmf->tmf);
-				goto ex_err;
-			}
+		if (task->task_state_flags & SAS_TASK_STATE_ABORTED) {
+			pm8001_dbg(pm8001_ha, FAIL, "TMF task[%x]timeout.\n",
+				   tmf->tmf);
+			goto ex_err;
 		}
 
 		if (task->task_status.resp == SAS_TASK_COMPLETE &&
···
 		wait_for_completion(&task->slow_task->completion);
 		res = TMF_RESP_FUNC_FAILED;
 		/* Even TMF timed out, return direct. */
-		if ((task->task_state_flags & SAS_TASK_STATE_ABORTED)) {
-			if (!(task->task_state_flags & SAS_TASK_STATE_DONE)) {
-				pm8001_dbg(pm8001_ha, FAIL,
-					   "TMF task timeout.\n");
-				goto ex_err;
-			}
+		if (task->task_state_flags & SAS_TASK_STATE_ABORTED) {
+			pm8001_dbg(pm8001_ha, FAIL, "TMF task timeout.\n");
+			goto ex_err;
 		}
 
 		if (task->task_status.resp == SAS_TASK_COMPLETE &&

drivers/scsi/scsi_scan.c

···
 		error = shost->hostt->target_alloc(starget);
 
 		if(error) {
-			dev_printk(KERN_ERR, dev, "target allocation failed, error %d\n", error);
+			if (error != -ENXIO)
+				dev_err(dev, "target allocation failed, error %d\n", error);
 			/* don't want scsi_target_reap to do the final
 			 * put because it will be under the host lock */
 			scsi_target_destroy(starget);

drivers/scsi/scsi_sysfs.c

···
 	mutex_lock(&sdev->state_mutex);
 	ret = scsi_device_set_state(sdev, state);
 	/*
-	 * If the device state changes to SDEV_RUNNING, we need to run
-	 * the queue to avoid I/O hang.
+	 * If the device state changes to SDEV_RUNNING, we need to
+	 * rescan the device to revalidate it, and run the queue to
+	 * avoid I/O hang.
 	 */
-	if (ret == 0 && state == SDEV_RUNNING)
+	if (ret == 0 && state == SDEV_RUNNING) {
+		scsi_rescan_device(dev);
 		blk_mq_run_hw_queues(sdev->request_queue, true);
+	}
 	mutex_unlock(&sdev->state_mutex);
 
 	return ret == 0 ? count : -EINVAL;

drivers/scsi/sr.c

···
 	else if (med->media_event_code == 2)
 		return DISK_EVENT_MEDIA_CHANGE;
 	else if (med->media_event_code == 3)
-		return DISK_EVENT_EJECT_REQUEST;
+		return DISK_EVENT_MEDIA_CHANGE;
 	return 0;
 }
 

fs/cifs/file.c

···
 
 static int cifs_readpage(struct file *file, struct page *page)
 {
-	loff_t offset = (loff_t)page->index << PAGE_SHIFT;
+	loff_t offset = page_file_offset(page);
 	int rc = -EACCES;
 	unsigned int xid;
 

fs/cifs/fs_context.c

···
 		ctx->cred_uid = uid;
 		ctx->cruid_specified = true;
 		break;
+	case Opt_backupuid:
+		uid = make_kuid(current_user_ns(), result.uint_32);
+		if (!uid_valid(uid))
+			goto cifs_parse_mount_err;
+		ctx->backupuid = uid;
+		ctx->backupuid_specified = true;
+		break;
 	case Opt_backupgid:
 		gid = make_kgid(current_user_ns(), result.uint_32);
 		if (!gid_valid(gid))

fs/cifs/smb2ops.c

···
 					     char *buf)
 {
 	struct cifs_io_parms io_parms = {0};
-	int rc, nbytes;
+	int nbytes;
+	int rc = 0;
 	struct kvec iov[2];
 
 	io_parms.netfid = cfile->fid.netfid;

fs/pipe.c

···
 #include "internal.h"
 
 /*
+ * New pipe buffers will be restricted to this size while the user is exceeding
+ * their pipe buffer quota. The general pipe use case needs at least two
+ * buffers: one for data yet to be read, and one for new data. If this is less
+ * than two, then a write to a non-empty pipe may block even if the pipe is not
+ * full. This can occur with GNU make jobserver or similar uses of pipes as
+ * semaphores: multiple processes may be waiting to write tokens back to the
+ * pipe before reading tokens: https://lore.kernel.org/lkml/1628086770.5rn8p04n6j.none@localhost/.
+ *
+ * Users can reduce their pipe buffers with F_SETPIPE_SZ below this at their
+ * own risk, namely: pipe writes to non-full pipes may block until the pipe is
+ * emptied.
+ */
+#define PIPE_MIN_DEF_BUFFERS 2
+
+/*
  * The max size that a non-root user is allowed to grow the pipe. Can
  * be set by root in /proc/sys/fs/pipe-max-size
  */
···
 	user_bufs = account_pipe_buffers(user, 0, pipe_bufs);
 
 	if (too_many_pipe_buffers_soft(user_bufs) && pipe_is_unprivileged_user()) {
-		user_bufs = account_pipe_buffers(user, pipe_bufs, 1);
-		pipe_bufs = 1;
+		user_bufs = account_pipe_buffers(user, pipe_bufs, PIPE_MIN_DEF_BUFFERS);
+		pipe_bufs = PIPE_MIN_DEF_BUFFERS;
 	}
 
 	if (too_many_pipe_buffers_hard(user_bufs) && pipe_is_unprivileged_user())

fs/xfs/libxfs/xfs_log_format.h

···
 	/* start of the extended dinode, writable fields */
 	uint32_t	di_crc;		/* CRC of the inode */
 	uint64_t	di_changecount;	/* number of attribute changes */
-	xfs_lsn_t	di_lsn;		/* flush sequence */
+
+	/*
+	 * The LSN we write to this field during formatting is not a reflection
+	 * of the current on-disk LSN. It should never be used for recovery
+	 * sequencing, nor should it be recovered into the on-disk inode at all.
+	 * See xlog_recover_inode_commit_pass2() and xfs_log_dinode_to_disk()
+	 * for details.
+	 */
+	xfs_lsn_t	di_lsn;
+
 	uint64_t	di_flags2;	/* more random flags */
 	uint32_t	di_cowextsize;	/* basic cow extent size for file */
 	uint8_t		di_pad2[12];	/* more padding for future expansion */

fs/xfs/xfs_buf_item_recover.c

···
 static xfs_lsn_t
 xlog_recover_get_buf_lsn(
 	struct xfs_mount	*mp,
-	struct xfs_buf		*bp)
+	struct xfs_buf		*bp,
+	struct xfs_buf_log_format *buf_f)
 {
 	uint32_t		magic32;
 	uint16_t		magic16;
···
 	void			*blk = bp->b_addr;
 	uuid_t			*uuid;
 	xfs_lsn_t		lsn = -1;
+	uint16_t		blft;
 
 	/* v4 filesystems always recover immediately */
 	if (!xfs_sb_version_hascrc(&mp->m_sb))
+		goto recover_immediately;
+
+	/*
+	 * realtime bitmap and summary file blocks do not have magic numbers or
+	 * UUIDs, so we must recover them immediately.
+	 */
+	blft = xfs_blft_from_flags(buf_f);
+	if (blft == XFS_BLFT_RTBITMAP_BUF || blft == XFS_BLFT_RTSUMMARY_BUF)
 		goto recover_immediately;
 
 	magic32 = be32_to_cpu(*(__be32 *)blk);
···
 	switch (magicda) {
 	case XFS_DIR3_LEAF1_MAGIC:
 	case XFS_DIR3_LEAFN_MAGIC:
+	case XFS_ATTR3_LEAF_MAGIC:
 	case XFS_DA3_NODE_MAGIC:
 		lsn = be64_to_cpu(((struct xfs_da3_blkinfo *)blk)->lsn);
 		uuid = &((struct xfs_da3_blkinfo *)blk)->uuid;
···
 	 * the verifier will be reset to match whatever recover turns that
 	 * buffer into.
 	 */
-	lsn = xlog_recover_get_buf_lsn(mp, bp);
+	lsn = xlog_recover_get_buf_lsn(mp, bp, buf_f);
 	if (lsn && lsn != -1 && XFS_LSN_CMP(lsn, current_lsn) >= 0) {
 		trace_xfs_log_recover_buf_skip(log, buf_f);
 		xlog_recover_validate_buf_type(mp, bp, buf_f, NULLCOMMITLSN);

fs/xfs/xfs_inode_item_recover.c

···
 STATIC void
 xfs_log_dinode_to_disk(
 	struct xfs_log_dinode	*from,
-	struct xfs_dinode	*to)
+	struct xfs_dinode	*to,
+	xfs_lsn_t		lsn)
 {
 	to->di_magic = cpu_to_be16(from->di_magic);
 	to->di_mode = cpu_to_be16(from->di_mode);
···
 		to->di_flags2 = cpu_to_be64(from->di_flags2);
 		to->di_cowextsize = cpu_to_be32(from->di_cowextsize);
 		to->di_ino = cpu_to_be64(from->di_ino);
-		to->di_lsn = cpu_to_be64(from->di_lsn);
+		to->di_lsn = cpu_to_be64(lsn);
 		memcpy(to->di_pad2, from->di_pad2, sizeof(to->di_pad2));
 		uuid_copy(&to->di_uuid, &from->di_uuid);
 		to->di_flushiter = 0;
···
 	}
 
 	/*
-	 * If the inode has an LSN in it, recover the inode only if it's less
-	 * than the lsn of the transaction we are replaying. Note: we still
-	 * need to replay an owner change even though the inode is more recent
-	 * than the transaction as there is no guarantee that all the btree
-	 * blocks are more recent than this transaction, too.
+	 * If the inode has an LSN in it, recover the inode only if the on-disk
+	 * inode's LSN is older than the lsn of the transaction we are
+	 * replaying. We can have multiple checkpoints with the same start LSN,
+	 * so the current LSN being equal to the on-disk LSN doesn't necessarily
+	 * mean that the on-disk inode is more recent than the change being
+	 * replayed.
+	 *
+	 * We must check the current_lsn against the on-disk inode
+	 * here because the we can't trust the log dinode to contain a valid LSN
+	 * (see comment below before replaying the log dinode for details).
+	 *
+	 * Note: we still need to replay an owner change even though the inode
+	 * is more recent than the transaction as there is no guarantee that all
+	 * the btree blocks are more recent than this transaction, too.
 	 */
 	if (dip->di_version >= 3) {
 		xfs_lsn_t	lsn = be64_to_cpu(dip->di_lsn);
 
-		if (lsn && lsn != -1 && XFS_LSN_CMP(lsn, current_lsn) >= 0) {
+		if (lsn && lsn != -1 && XFS_LSN_CMP(lsn, current_lsn) > 0) {
 			trace_xfs_log_recover_inode_skip(log, in_f);
 			error = 0;
 			goto out_owner_change;
···
 		goto out_release;
 	}
 
-	/* recover the log dinode inode into the on disk inode */
-	xfs_log_dinode_to_disk(ldip, dip);
+	/*
+	 * Recover the log dinode inode into the on disk inode.
+	 *
+	 * The LSN in the log dinode is garbage - it can be zero or reflect
+	 * stale in-memory runtime state that isn't coherent with the changes
+	 * logged in this transaction or the changes written to the on-disk
+	 * inode.  Hence we write the current lSN into the inode because that
+	 * matches what xfs_iflush() would write inode the inode when flushing
+	 * the changes in this transaction.
+	 */
+	xfs_log_dinode_to_disk(ldip, dip, current_lsn);
 
 	fields = in_f->ilf_fields;
 	if (fields & XFS_ILOG_DEV)

fs/xfs/xfs_log.c

···
 STATIC void
 xlog_verify_tail_lsn(
 	struct xlog		*log,
-	struct xlog_in_core	*iclog,
-	xfs_lsn_t		tail_lsn);
+	struct xlog_in_core	*iclog);
 #else
 #define xlog_verify_dest_ptr(a,b)
 #define xlog_verify_grant_tail(a)
 #define xlog_verify_iclog(a,b,c)
-#define xlog_verify_tail_lsn(a,b,c)
+#define xlog_verify_tail_lsn(a,b)
 #endif
 
 STATIC int
···
 	return error;
 }
 
-static bool
-__xlog_state_release_iclog(
-	struct xlog		*log,
-	struct xlog_in_core	*iclog)
-{
-	lockdep_assert_held(&log->l_icloglock);
-
-	if (iclog->ic_state == XLOG_STATE_WANT_SYNC) {
-		/* update tail before writing to iclog */
-		xfs_lsn_t tail_lsn = xlog_assign_tail_lsn(log->l_mp);
-
-		iclog->ic_state = XLOG_STATE_SYNCING;
-		iclog->ic_header.h_tail_lsn = cpu_to_be64(tail_lsn);
-		xlog_verify_tail_lsn(log, iclog, tail_lsn);
-		/* cycle incremented when incrementing curr_block */
-		trace_xlog_iclog_syncing(iclog, _RET_IP_);
-		return true;
-	}
-
-	ASSERT(iclog->ic_state == XLOG_STATE_ACTIVE);
-	return false;
-}
-
 /*
  * Flush iclog to disk if this is the last reference to the given iclog and the
  * it is in the WANT_SYNC state.
+ *
+ * If the caller passes in a non-zero @old_tail_lsn and the current log tail
+ * does not match, there may be metadata on disk that must be persisted before
+ * this iclog is written.  To satisfy that requirement, set the
+ * XLOG_ICL_NEED_FLUSH flag as a condition for writing this iclog with the new
+ * log tail value.
+ *
+ * If XLOG_ICL_NEED_FUA is already set on the iclog, we need to ensure that the
+ * log tail is updated correctly. NEED_FUA indicates that the iclog will be
+ * written to stable storage, and implies that a commit record is contained
+ * within the iclog. We need to ensure that the log tail does not move beyond
+ * the tail that the first commit record in the iclog ordered against, otherwise
+ * correct recovery of that checkpoint becomes dependent on future operations
+ * performed on this iclog.
+ *
+ * Hence if NEED_FUA is set and the current iclog tail lsn is empty, write the
+ * current tail into iclog. Once the iclog tail is set, future operations must
+ * not modify it, otherwise they potentially violate ordering constraints for
+ * the checkpoint commit that wrote the initial tail lsn value. The tail lsn in
+ * the iclog will get zeroed on activation of the iclog after sync, so we
+ * always capture the tail lsn on the iclog on the first NEED_FUA release
+ * regardless of the number of active reference counts on this iclog.
  */
+
 int
 xlog_state_release_iclog(
 	struct xlog		*log,
-	struct xlog_in_core	*iclog)
+	struct xlog_in_core	*iclog,
+	xfs_lsn_t		old_tail_lsn)
 {
+	xfs_lsn_t		tail_lsn;
 	lockdep_assert_held(&log->l_icloglock);
 
 	trace_xlog_iclog_release(iclog, _RET_IP_);
 	if (iclog->ic_state == XLOG_STATE_IOERROR)
 		return -EIO;
 
-	if (atomic_dec_and_test(&iclog->ic_refcnt) &&
-	    __xlog_state_release_iclog(log, iclog)) {
-		spin_unlock(&log->l_icloglock);
-		xlog_sync(log, iclog);
-		spin_lock(&log->l_icloglock);
+	/*
+	 * Grabbing the current log tail needs to be atomic w.r.t. the writing
+	 * of the tail LSN into the iclog so we guarantee that the log tail does
+	 * not move between deciding if a cache flush is required and writing
+	 * the LSN into the iclog below.
+	 */
+	if (old_tail_lsn || iclog->ic_state == XLOG_STATE_WANT_SYNC) {
+		tail_lsn = xlog_assign_tail_lsn(log->l_mp);
+
+		if (old_tail_lsn && tail_lsn != old_tail_lsn)
+			iclog->ic_flags |= XLOG_ICL_NEED_FLUSH;
+
+		if ((iclog->ic_flags & XLOG_ICL_NEED_FUA) &&
+		    !iclog->ic_header.h_tail_lsn)
+			iclog->ic_header.h_tail_lsn = cpu_to_be64(tail_lsn);
 	}
 
+	if (!atomic_dec_and_test(&iclog->ic_refcnt))
+		return 0;
+
+	if (iclog->ic_state != XLOG_STATE_WANT_SYNC) {
+		ASSERT(iclog->ic_state == XLOG_STATE_ACTIVE);
+		return 0;
+	}
+
+	iclog->ic_state = XLOG_STATE_SYNCING;
+	if (!iclog->ic_header.h_tail_lsn)
+		iclog->ic_header.h_tail_lsn = cpu_to_be64(tail_lsn);
+	xlog_verify_tail_lsn(log, iclog);
+	trace_xlog_iclog_syncing(iclog, _RET_IP_);
+
+	spin_unlock(&log->l_icloglock);
+	xlog_sync(log, iclog);
+	spin_lock(&log->l_icloglock);
 	return 0;
 }
 
···
 }
 
 /*
+ * Flush out the iclog to disk ensuring that device caches are flushed and
+ * the iclog hits stable storage before any completion waiters are woken.
+ */
+static inline int
+xlog_force_iclog(
+	struct xlog_in_core	*iclog)
+{
+	atomic_inc(&iclog->ic_refcnt);
+	iclog->ic_flags |= XLOG_ICL_NEED_FLUSH | XLOG_ICL_NEED_FUA;
+	if (iclog->ic_state == XLOG_STATE_ACTIVE)
+		xlog_state_switch_iclogs(iclog->ic_log, iclog, 0);
+	return xlog_state_release_iclog(iclog->ic_log, iclog, 0);
+}
+
+/*
  * Wait for the iclog and all prior iclogs to be written disk as required by the
  * log force state machine. Waiting on ic_force_wait ensures iclog completions
  * have been ordered and callbacks run before we are woken here, hence
···
 	/* account for space used by record data */
 	ticket->t_curr_res -= sizeof(ulf);
 
-	/*
-	 * For external log devices, we need to flush the data device cache
-	 * first to ensure all metadata writeback is on stable storage before we
-	 * stamp the tail LSN into the unmount record.
-	 */
-	if (log->l_targ != log->l_mp->m_ddev_targp)
-		blkdev_issue_flush(log->l_targ->bt_bdev);
 	return xlog_write(log, &vec, ticket, NULL, NULL, XLOG_UNMOUNT_TRANS);
 }
 
···
 
 	spin_lock(&log->l_icloglock);
 	iclog = log->l_iclog;
-	atomic_inc(&iclog->ic_refcnt);
-	if (iclog->ic_state == XLOG_STATE_ACTIVE)
-		xlog_state_switch_iclogs(log, iclog, 0);
-	else
-		ASSERT(iclog->ic_state == XLOG_STATE_WANT_SYNC ||
-		       iclog->ic_state == XLOG_STATE_IOERROR);
-	/*
-	 * Ensure the journal is fully flushed and on stable storage once the
-	 * iclog containing the unmount record is written.
-	 */
-	iclog->ic_flags |= (XLOG_ICL_NEED_FLUSH | XLOG_ICL_NEED_FUA);
-	error = xlog_state_release_iclog(log, iclog);
+	error = xlog_force_iclog(iclog);
 	xlog_wait_on_iclog(iclog);
 
 	if (tic) {
···
 	 * metadata writeback and causing priority inversions.
 	 */
 	iclog->ic_bio.bi_opf = REQ_OP_WRITE | REQ_META | REQ_SYNC | REQ_IDLE;
-	if (iclog->ic_flags & XLOG_ICL_NEED_FLUSH)
+	if (iclog->ic_flags & XLOG_ICL_NEED_FLUSH) {
 		iclog->ic_bio.bi_opf |= REQ_PREFLUSH;
+		/*
+		 * For external log devices, we also need to flush the data
+		 * device cache first to ensure all metadata writeback covered
+		 * by the LSN in this iclog is on stable storage. This is slow,
+		 * but it *must* complete before we issue the external log IO.
+		 */
+		if (log->l_targ != log->l_mp->m_ddev_targp)
+			blkdev_issue_flush(log->l_mp->m_ddev_targp->bt_bdev);
+	}
 	if (iclog->ic_flags & XLOG_ICL_NEED_FUA)
 		iclog->ic_bio.bi_opf |= REQ_FUA;
+
 	iclog->ic_flags &= ~(XLOG_ICL_NEED_FLUSH | XLOG_ICL_NEED_FUA);
 
 	if (xlog_map_iclog_data(&iclog->ic_bio, iclog->ic_data, count)) {
···
 	return 0;
 
 release_iclog:
-	error = xlog_state_release_iclog(log, iclog);
+	error = xlog_state_release_iclog(log, iclog, 0);
 	spin_unlock(&log->l_icloglock);
 	return error;
 }
···
 		ASSERT(optype & XLOG_COMMIT_TRANS);
 		*commit_iclog = iclog;
 	} else {
-		error = xlog_state_release_iclog(log, iclog);
+		error = xlog_state_release_iclog(log, iclog, 0);
 	}
 	spin_unlock(&log->l_icloglock);
 
···
 	memset(iclog->ic_header.h_cycle_data, 0,
 		sizeof(iclog->ic_header.h_cycle_data));
 	iclog->ic_header.h_lsn = 0;
+	iclog->ic_header.h_tail_lsn = 0;
 }
 
 /*
···
 		 * reference to the iclog.
 		 */
 		if (!atomic_add_unless(&iclog->ic_refcnt, -1, 1))
-			error = xlog_state_release_iclog(log, iclog);
+			error = xlog_state_release_iclog(log, iclog, 0);
 		spin_unlock(&log->l_icloglock);
 		if (error)
 			return error;
···
 }
 
 /*
+ * Force the iclog to disk and check if the iclog has been completed before
+ * xlog_force_iclog() returns. This can happen on synchronous (e.g.
+ * pmem) or fast async storage because we drop the icloglock to issue the IO.
+ * If completion has already occurred, tell the caller so that it can avoid an
+ * unnecessary wait on the iclog.
+ */
+static int
+xlog_force_and_check_iclog(
+	struct xlog_in_core	*iclog,
+	bool			*completed)
+{
+	xfs_lsn_t		lsn = be64_to_cpu(iclog->ic_header.h_lsn);
+	int			error;
+
+	*completed = false;
+	error = xlog_force_iclog(iclog);
+	if (error)
+		return error;
+
+	/*
+	 * If the iclog has already been completed and reused the header LSN
+	 * will have been rewritten by completion
+	 */
+	if (be64_to_cpu(iclog->ic_header.h_lsn) != lsn)
+		*completed = true;
+	return 0;
+}
+
+/*
  * Write out all data in the in-core log as of this exact moment in time.
  *
  * Data may be written to the in-core log during this call.  However,
···
 {
 	struct xlog		*log = mp->m_log;
 	struct xlog_in_core	*iclog;
-	xfs_lsn_t		lsn;
 
 	XFS_STATS_INC(mp, xs_log_force);
 	trace_xfs_log_force(mp, 0, _RET_IP_);
···
 		iclog = iclog->ic_prev;
 	} else if (iclog->ic_state == XLOG_STATE_ACTIVE) {
 		if (atomic_read(&iclog->ic_refcnt) == 0) {
-			/*
-			 * We are the only one with access to this iclog.
-			 *
-			 * Flush it out now.  There should be a roundoff of zero
-			 * to show that someone has already taken care of the
-			 * roundoff from the previous sync.
-			 */
-			atomic_inc(&iclog->ic_refcnt);
-			lsn = be64_to_cpu(iclog->ic_header.h_lsn);
-			xlog_state_switch_iclogs(log, iclog, 0);
-			if (xlog_state_release_iclog(log, iclog))
+			/* We have exclusive access to this iclog. */
+			bool	completed;
+
+			if (xlog_force_and_check_iclog(iclog, &completed))
 				goto out_error;
 
-			if (be64_to_cpu(iclog->ic_header.h_lsn) != lsn)
+			if (completed)
 				goto out_unlock;
 		} else {
 			/*
-			 * Someone else is writing to this iclog.
-			 *
-			 * Use its call to flush out the data.  However, the
-			 * other thread may not force out this LR, so we mark
-			 * it WANT_SYNC.
+			 * Someone else is still writing to this iclog, so we
+			 * need to ensure that when they release the iclog it
+			 * gets synced immediately as we may be waiting on it.
 			 */
 			xlog_state_switch_iclogs(log, iclog, 0);
 		}
-	} else {
-		/*
-		 * If the head iclog is not active nor dirty, we just attach
-		 * ourselves to the head and go to sleep if necessary.
-		 */
-		;
 	}
+
+	/*
+	 * The iclog we are about to wait on may contain the checkpoint pushed
+	 * by the above xlog_cil_force() call, but it may not have been pushed
+	 * to disk yet. Like the ACTIVE case above, we need to make sure caches
+	 * are flushed when this iclog is written.
+	 */
+	if (iclog->ic_state == XLOG_STATE_WANT_SYNC)
+		iclog->ic_flags |= XLOG_ICL_NEED_FLUSH | XLOG_ICL_NEED_FUA;
 
 	if (flags & XFS_LOG_SYNC)
 		return xlog_wait_on_iclog(iclog);
···
 	bool			already_slept)
 {
 	struct xlog_in_core	*iclog;
+	bool			completed;
 
 	spin_lock(&log->l_icloglock);
 	iclog = log->l_iclog;
···
 			goto out_unlock;
 	}
 
-	if (iclog->ic_state == XLOG_STATE_ACTIVE) {
+	switch (iclog->ic_state) {
+	case XLOG_STATE_ACTIVE:
 		/*
 		 * We sleep here if we haven't already slept (e.g. this is the
 		 * first time we've looked at the correct iclog buf) and the
···
 					&log->l_icloglock);
 			return -EAGAIN;
 		}
-		atomic_inc(&iclog->ic_refcnt);
-		xlog_state_switch_iclogs(log, iclog, 0);
-		if (xlog_state_release_iclog(log, iclog))
+		if (xlog_force_and_check_iclog(iclog, &completed))
 			goto out_error;
 		if (log_flushed)
 			*log_flushed = 1;
+		if (completed)
+			goto out_unlock;
+		break;
+	case XLOG_STATE_WANT_SYNC:
+		/*
+		 * This iclog may contain the checkpoint pushed by the
+		 * xlog_cil_force_seq() call, but there are other writers still
+		 * accessing it so it hasn't been pushed to disk yet. Like the
+		 * ACTIVE case above, we need to make sure caches are flushed
+		 * when this iclog is written.
+		 */
+		iclog->ic_flags |= XLOG_ICL_NEED_FLUSH | XLOG_ICL_NEED_FUA;
+		break;
+	default:
+		/*
+		 * The entire checkpoint was written by the CIL force and is on
+		 * its way to disk already. It will be stable when it
+		 * completes, so we don't need to manipulate caches here at all.
+		 * We just need to wait for completion if necessary.
+		 */
+		break;
 	}
 
 	if (flags & XFS_LOG_SYNC)
···
 STATIC void
 xlog_verify_tail_lsn(
 	struct xlog		*log,
-	struct xlog_in_core	*iclog,
-	xfs_lsn_t		tail_lsn)
+	struct xlog_in_core	*iclog)
 {
-    int blocks;
+	xfs_lsn_t	tail_lsn = be64_to_cpu(iclog->ic_header.h_tail_lsn);
+	int		blocks;
 
     if (CYCLE_LSN(tail_lsn) == log->l_prev_cycle) {
 	blocks =

fs/xfs/xfs_log_cil.c

···
 	struct xfs_trans_header thdr;
 	struct xfs_log_iovec	lhdr;
 	struct xfs_log_vec	lvhdr = { NULL };
+	xfs_lsn_t		preflush_tail_lsn;
 	xfs_lsn_t		commit_lsn;
-	xfs_lsn_t		push_seq;
+	xfs_csn_t		push_seq;
 	struct bio		bio;
 	DECLARE_COMPLETION_ONSTACK(bdev_flush);
 
···
 	 * because we hold the flush lock exclusively. Hence we can now issue
 	 * a cache flush to ensure all the completed metadata in the journal we
 	 * are about to overwrite is on stable storage.
+	 *
+	 * Because we are issuing this cache flush before we've written the
+	 * tail lsn to the iclog, we can have metadata IO completions move the
+	 * tail forwards between the completion of this flush and the iclog
+	 * being written. In this case, we need to re-issue the cache flush
+	 * before the iclog write. To detect whether the log tail moves, sample
+	 * the tail LSN *before* we issue the flush.
 	 */
+	preflush_tail_lsn = atomic64_read(&log->l_tail_lsn);
 	xfs_flush_bdev_async(&bio, log->l_mp->m_ddev_targp->bt_bdev,
 				&bdev_flush);
 
···
 	 * storage.
 	 */
 	commit_iclog->ic_flags |= XLOG_ICL_NEED_FUA;
-	xlog_state_release_iclog(log, commit_iclog);
+	xlog_state_release_iclog(log, commit_iclog, preflush_tail_lsn);
 	spin_unlock(&log->l_icloglock);
 	return;
 

fs/xfs/xfs_log_priv.h

···
 	{ XLOG_STATE_DIRTY,	"XLOG_STATE_DIRTY" }, \
 	{ XLOG_STATE_IOERROR,	"XLOG_STATE_IOERROR" }
 
+/*
+ * In core log flags
+ */
+#define XLOG_ICL_NEED_FLUSH	(1 << 0)	/* iclog needs REQ_PREFLUSH */
+#define XLOG_ICL_NEED_FUA	(1 << 1)	/* iclog needs REQ_FUA */
+
+#define XLOG_ICL_STRINGS \
+	{ XLOG_ICL_NEED_FLUSH,	"XLOG_ICL_NEED_FLUSH" }, \
+	{ XLOG_ICL_NEED_FUA,	"XLOG_ICL_NEED_FUA" }
+
 
 /*
  * Log ticket flags
···
 #define XLOG_STATE_COVER_DONE2	4
 
 #define XLOG_COVER_OPS		5
-
-#define XLOG_ICL_NEED_FLUSH	(1 << 0)	/* iclog needs REQ_PREFLUSH */
-#define XLOG_ICL_NEED_FUA	(1 << 1)	/* iclog needs REQ_FUA */
 
 /* Ticket reservation region accounting */ 
 #define XLOG_TIC_LEN_MAX	15
···
 void	xfs_log_ticket_ungrant(struct xlog *log, struct xlog_ticket *ticket);
 void	xfs_log_ticket_regrant(struct xlog *log, struct xlog_ticket *ticket);
 
-int xlog_state_release_iclog(struct xlog *log, struct xlog_in_core *iclog);
+int xlog_state_release_iclog(struct xlog *log, struct xlog_in_core *iclog,
+		xfs_lsn_t log_tail_lsn);
 
 /*
  * When we crack an atomic LSN, we sample it first so that the value will not

fs/xfs/xfs_trace.h

···
 		__field(uint32_t, state)
 		__field(int32_t, refcount)
 		__field(uint32_t, offset)
+		__field(uint32_t, flags)
 		__field(unsigned long long, lsn)
 		__field(unsigned long, caller_ip)
 	),
···
 		__entry->state = iclog->ic_state;
 		__entry->refcount = atomic_read(&iclog->ic_refcnt);
 		__entry->offset = iclog->ic_offset;
+		__entry->flags = iclog->ic_flags;
 		__entry->lsn = be64_to_cpu(iclog->ic_header.h_lsn);
 		__entry->caller_ip = caller_ip;
 	),
-	TP_printk("dev %d:%d state %s refcnt %d offset %u lsn 0x%llx caller %pS",
+	TP_printk("dev %d:%d state %s refcnt %d offset %u lsn 0x%llx flags %s caller %pS",
 		  MAJOR(__entry->dev), MINOR(__entry->dev),
 		  __print_symbolic(__entry->state, XLOG_STATE_STRINGS),
 		  __entry->refcount,
 		  __entry->offset,
 		  __entry->lsn,
+		  __print_flags(__entry->flags, "|", XLOG_ICL_STRINGS),
 		  (char *)__entry->caller_ip)
 
 );

include/linux/mhi.h

···
  *                            host and device execution environments match and
  *                            channels are in a DISABLED state.
  * @mhi_dev: Device associated with the channels
+ * @flags: MHI channel flags
  */
-int mhi_prepare_for_transfer(struct mhi_device *mhi_dev);
+int mhi_prepare_for_transfer(struct mhi_device *mhi_dev,
+			     unsigned int flags);
+
+/* Automatically allocate and queue inbound buffers */
+#define MHI_CH_INBOUND_ALLOC_BUFS BIT(0)
 
 /**
  * mhi_unprepare_from_transfer - Reset UL and DL channels for data transfer.

include/net/bluetooth/hci_core.h

···
 void hci_free_dev(struct hci_dev *hdev);
 int hci_register_dev(struct hci_dev *hdev);
 void hci_unregister_dev(struct hci_dev *hdev);
+void hci_cleanup_dev(struct hci_dev *hdev);
 int hci_suspend_dev(struct hci_dev *hdev);
 int hci_resume_dev(struct hci_dev *hdev);
 int hci_reset_dev(struct hci_dev *hdev);

include/net/flow_offload.h

···
 }
 
 /**
- * flow_action_has_one_action() - check if exactly one action is present
+ * flow_offload_has_one_action() - check if exactly one action is present
  * @action: tc filter flow offload action
  *
  * Returns true if exactly one action is present.

include/net/ip6_route.h

···
 
 static inline unsigned int ip6_skb_dst_mtu(struct sk_buff *skb)
 {
-	int mtu;
+	unsigned int mtu;
 
 	struct ipv6_pinfo *np = skb->sk && !dev_recursion_level() ?
 				inet6_sk(skb->sk) : NULL;

include/net/netns/xfrm.h

···
 #endif
 	spinlock_t		xfrm_state_lock;
 	seqcount_spinlock_t	xfrm_state_hash_generation;
+	seqcount_spinlock_t	xfrm_policy_hash_generation;
 
 	spinlock_t xfrm_policy_lock;
 	struct mutex xfrm_cfg_mutex;

include/net/pkt_cls.h

···
 
 /**
  * struct tcf_pkt_info - packet information
+ *
+ * @ptr: start of the pkt data
+ * @nexthdr: offset of the next header
  */
 struct tcf_pkt_info {
 	unsigned char *		ptr;
···
  * @ops: the operations lookup table of the corresponding ematch module
  * @datalen: length of the ematch specific configuration data
  * @data: ematch specific data
+ * @net: the network namespace
  */
 struct tcf_ematch {
 	struct tcf_ematch_ops * ops;

kernel/trace/trace.c

···
 		return -EINVAL;
 
 	ret = event_trace_add_tracer(tr->dir, tr);
-	if (ret)
+	if (ret) {
 		tracefs_remove(tr->dir);
+		return ret;
+	}
 
 	init_tracer_tracefs(tr, tr->dir);
 	__update_tracer_options(tr);

kernel/trace/trace_events_hist.c

···
 	C(INVALID_SORT_MODIFIER,"Invalid sort modifier"),		\
 	C(EMPTY_SORT_FIELD,	"Empty sort field"),			\
 	C(TOO_MANY_SORT_FIELDS,	"Too many sort fields (Max = 2)"),	\
-	C(INVALID_SORT_FIELD,	"Sort field must be a key or a val"),
+	C(INVALID_SORT_FIELD,	"Sort field must be a key or a val"),	\
+	C(INVALID_STR_OPERAND,	"String type can not be an operand in expression"),
 
 #undef C
 #define C(a, b)		HIST_ERR_##a
···
 		ret = PTR_ERR(operand1);
 		goto free;
 	}
+	if (operand1->flags & HIST_FIELD_FL_STRING) {
+		/* String type can not be the operand of unary operator. */
+		hist_err(file->tr, HIST_ERR_INVALID_STR_OPERAND, errpos(str));
+		destroy_hist_field(operand1, 0);
+		ret = -EINVAL;
+		goto free;
+	}
 
 	expr->flags |= operand1->flags &
 		(HIST_FIELD_FL_TIMESTAMP | HIST_FIELD_FL_TIMESTAMP_USECS);
···
 		operand1 = NULL;
 		goto free;
 	}
+	if (operand1->flags & HIST_FIELD_FL_STRING) {
+		hist_err(file->tr, HIST_ERR_INVALID_STR_OPERAND, errpos(operand1_str));
+		ret = -EINVAL;
+		goto free;
+	}
 
 	/* rest of string could be another expression e.g. b+c in a+b+c */
 	operand_flags = 0;
···
 	if (IS_ERR(operand2)) {
 		ret = PTR_ERR(operand2);
 		operand2 = NULL;
+		goto free;
+	}
+	if (operand2->flags & HIST_FIELD_FL_STRING) {
+		hist_err(file->tr, HIST_ERR_INVALID_STR_OPERAND, errpos(str));
+		ret = -EINVAL;
 		goto free;
 	}
 
···
 
 	expr->operands[0] = operand1;
 	expr->operands[1] = operand2;
+
+	/* The operand sizes should be the same, so just pick one */
+	expr->size = operand1->size;
+
 	expr->operator = field_op;
 	expr->name = expr_str(expr, 0);
 	expr->type = kstrdup(operand1->type, GFP_KERNEL);

kernel/trace/trace_hwlat.c

···
 
 	get_online_cpus();
 	cpumask_and(current_mask, cpu_online_mask, tr->tracing_cpumask);
-	next_cpu = cpumask_next(smp_processor_id(), current_mask);
+	next_cpu = cpumask_next(raw_smp_processor_id(), current_mask);
 	put_online_cpus();
 
 	if (next_cpu >= nr_cpu_ids)

kernel/ucount.c

···
 {
 	struct hlist_head *hashent = ucounts_hashentry(ns, uid);
 	struct ucounts *ucounts, *new;
+	long overflow;
 
 	spin_lock_irq(&ucounts_lock);
 	ucounts = find_ucounts(ns, uid, hashent);
···
 			return new;
 		}
 	}
+	overflow = atomic_add_negative(1, &ucounts->count);
 	spin_unlock_irq(&ucounts_lock);
-	ucounts = get_ucounts(ucounts);
+	if (overflow) {
+		put_ucounts(ucounts);
+		return NULL;
+	}
 	return ucounts;
 }
 
···
 {
 	unsigned long flags;
 
-	if (atomic_dec_and_test(&ucounts->count)) {
-		spin_lock_irqsave(&ucounts_lock, flags);
+	if (atomic_dec_and_lock_irqsave(&ucounts->count, &ucounts_lock, flags)) {
 		hlist_del_init(&ucounts->node);
 		spin_unlock_irqrestore(&ucounts_lock, flags);
 		kfree(ucounts);

net/bluetooth/hci_core.c

···
 /* Unregister HCI device */
 void hci_unregister_dev(struct hci_dev *hdev)
 {
-	int id;
-
 	BT_DBG("%p name %s bus %d", hdev, hdev->name, hdev->bus);
 
 	hci_dev_set_flag(hdev, HCI_UNREGISTER);
-
-	id = hdev->id;
 
 	write_lock(&hci_dev_list_lock);
 	list_del(&hdev->list);
···
 	}
 
 	device_del(&hdev->dev);
+	/* Actual cleanup is deferred until hci_cleanup_dev(). */
+	hci_dev_put(hdev);
+}
+EXPORT_SYMBOL(hci_unregister_dev);
 
+/* Cleanup HCI device */
+void hci_cleanup_dev(struct hci_dev *hdev)
+{
 	debugfs_remove_recursive(hdev->debugfs);
 	kfree_const(hdev->hw_info);
 	kfree_const(hdev->fw_info);
···
 	hci_blocked_keys_clear(hdev);
 	hci_dev_unlock(hdev);
 
-	hci_dev_put(hdev);
-
-	ida_simple_remove(&hci_index_ida, id);
+	ida_simple_remove(&hci_index_ida, hdev->id);
 }
-EXPORT_SYMBOL(hci_unregister_dev);
 
 /* Suspend HCI device */
 int hci_suspend_dev(struct hci_dev *hdev)

net/bluetooth/hci_sock.c

···
 	char              comm[TASK_COMM_LEN];
 };
 
+static struct hci_dev *hci_hdev_from_sock(struct sock *sk)
+{
+	struct hci_dev *hdev = hci_pi(sk)->hdev;
+
+	if (!hdev)
+		return ERR_PTR(-EBADFD);
+	if (hci_dev_test_flag(hdev, HCI_UNREGISTER))
+		return ERR_PTR(-EPIPE);
+	return hdev;
+}
+
 void hci_sock_set_flag(struct sock *sk, int nr)
 {
 	set_bit(nr, &hci_pi(sk)->flags);
···
 	if (event == HCI_DEV_UNREG) {
 		struct sock *sk;
 
-		/* Detach sockets from device */
+		/* Wake up sockets using this dead device */
 		read_lock(&hci_sk_list.lock);
 		sk_for_each(sk, &hci_sk_list.head) {
-			lock_sock(sk);
 			if (hci_pi(sk)->hdev == hdev) {
-				hci_pi(sk)->hdev = NULL;
 				sk->sk_err = EPIPE;
-				sk->sk_state = BT_OPEN;
 				sk->sk_state_change(sk);
-
-				hci_dev_put(hdev);
 			}
-			release_sock(sk);
 		}
 		read_unlock(&hci_sk_list.lock);
 	}
···
 static int hci_sock_bound_ioctl(struct sock *sk, unsigned int cmd,
 				unsigned long arg)
 {
-	struct hci_dev *hdev = hci_pi(sk)->hdev;
+	struct hci_dev *hdev = hci_hdev_from_sock(sk);
 
-	if (!hdev)
-		return -EBADFD;
+	if (IS_ERR(hdev))
+		return PTR_ERR(hdev);
 
 	if (hci_dev_test_flag(hdev, HCI_USER_CHANNEL))
 		return -EBUSY;
···
 		return -EINVAL;
 
 	lock_sock(sk);
+
+	/* Allow detaching from dead device and attaching to alive device, if
+	 * the caller wants to re-bind (instead of close) this socket in
+	 * response to hci_sock_dev_event(HCI_DEV_UNREG) notification.
+	 */
+	hdev = hci_pi(sk)->hdev;
+	if (hdev && hci_dev_test_flag(hdev, HCI_UNREGISTER)) {
+		hci_pi(sk)->hdev = NULL;
+		sk->sk_state = BT_OPEN;
+		hci_dev_put(hdev);
+	}
+	hdev = NULL;
 
 	if (sk->sk_state == BT_BOUND) {
 		err = -EALREADY;
···
 
 	lock_sock(sk);
 
-	hdev = hci_pi(sk)->hdev;
-	if (!hdev) {
-		err = -EBADFD;
+	hdev = hci_hdev_from_sock(sk);
+	if (IS_ERR(hdev)) {
+		err = PTR_ERR(hdev);
 		goto done;
 	}
 
···
 		goto done;
 	}
 
-	hdev = hci_pi(sk)->hdev;
-	if (!hdev) {
-		err = -EBADFD;
+	hdev = hci_hdev_from_sock(sk);
+	if (IS_ERR(hdev)) {
+		err = PTR_ERR(hdev);
 		goto done;
 	}
 

net/bluetooth/hci_sysfs.c

···
 static void bt_host_release(struct device *dev)
 {
 	struct hci_dev *hdev = to_hci_dev(dev);
+
+	if (hci_dev_test_flag(hdev, HCI_UNREGISTER))
+		hci_cleanup_dev(hdev);
 	kfree(hdev);
 	module_put(THIS_MODULE);
 }

net/bridge/br.c

···
 	case SWITCHDEV_FDB_ADD_TO_BRIDGE:
 		fdb_info = ptr;
 		err = br_fdb_external_learn_add(br, p, fdb_info->addr,
-						fdb_info->vid, false);
+						fdb_info->vid,
+						fdb_info->is_local, false);
 		if (err) {
 			err = notifier_from_errno(err);
 			break;

net/bridge/br_fdb.c

···
 
 static int __br_fdb_add(struct ndmsg *ndm, struct net_bridge *br,
 			struct net_bridge_port *p, const unsigned char *addr,
-			u16 nlh_flags, u16 vid, struct nlattr *nfea_tb[])
+			u16 nlh_flags, u16 vid, struct nlattr *nfea_tb[],
+			struct netlink_ext_ack *extack)
 {
 	int err = 0;
 
···
 		rcu_read_unlock();
 		local_bh_enable();
 	} else if (ndm->ndm_flags & NTF_EXT_LEARNED) {
-		err = br_fdb_external_learn_add(br, p, addr, vid, true);
+		if (!p && !(ndm->ndm_state & NUD_PERMANENT)) {
+			NL_SET_ERR_MSG_MOD(extack,
+					   "FDB entry towards bridge must be permanent");
+			return -EINVAL;
+		}
+
+		err = br_fdb_external_learn_add(br, p, addr, vid,
+						ndm->ndm_state & NUD_PERMANENT,
+						true);
 	} else {
 		spin_lock_bh(&br->hash_lock);
 		err = fdb_add_entry(br, p, addr, ndm, nlh_flags, vid, nfea_tb);
···
 		}
 
 		/* VID was specified, so use it. */
-		err = __br_fdb_add(ndm, br, p, addr, nlh_flags, vid, nfea_tb);
+		err = __br_fdb_add(ndm, br, p, addr, nlh_flags, vid, nfea_tb,
+				   extack);
 	} else {
-		err = __br_fdb_add(ndm, br, p, addr, nlh_flags, 0, nfea_tb);
+		err = __br_fdb_add(ndm, br, p, addr, nlh_flags, 0, nfea_tb,
+				   extack);
 		if (err || !vg || !vg->num_vlans)
 			goto out;
 
···
 			if (!br_vlan_should_use(v))
 				continue;
 			err = __br_fdb_add(ndm, br, p, addr, nlh_flags, v->vid,
-					   nfea_tb);
+					   nfea_tb, extack);
 			if (err)
 				goto out;
 		}
···
 }
 
 int br_fdb_external_learn_add(struct net_bridge *br, struct net_bridge_port *p,
-			      const unsigned char *addr, u16 vid,
+			      const unsigned char *addr, u16 vid, bool is_local,
 			      bool swdev_notify)
 {
 	struct net_bridge_fdb_entry *fdb;
···
 
 		if (swdev_notify)
 			flags |= BIT(BR_FDB_ADDED_BY_USER);
+
+		if (is_local)
+			flags |= BIT(BR_FDB_LOCAL);
+
 		fdb = fdb_create(br, p, addr, vid, flags);
 		if (!fdb) {
 			err = -ENOMEM;
···
 
 		if (swdev_notify)
 			set_bit(BR_FDB_ADDED_BY_USER, &fdb->flags);
+
+		if (is_local)
+			set_bit(BR_FDB_LOCAL, &fdb->flags);
 
 		if (modified)
 			fdb_notify(br, fdb, RTM_NEWNEIGH, swdev_notify);

net/bridge/br_private.h

···
 int br_fdb_sync_static(struct net_bridge *br, struct net_bridge_port *p);
 void br_fdb_unsync_static(struct net_bridge *br, struct net_bridge_port *p);
 int br_fdb_external_learn_add(struct net_bridge *br, struct net_bridge_port *p,
-			      const unsigned char *addr, u16 vid,
+			      const unsigned char *addr, u16 vid, bool is_local,
 			      bool swdev_notify);
 int br_fdb_external_learn_del(struct net_bridge *br, struct net_bridge_port *p,
 			      const unsigned char *addr, u16 vid,

net/ipv4/tcp_offload.c

···
 	if (th->cwr)
 		skb_shinfo(skb)->gso_type |= SKB_GSO_TCP_ECN;
 
+	if (skb->encapsulation)
+		skb->inner_transport_header = skb->transport_header;
+
 	return 0;
 }
 EXPORT_SYMBOL(tcp_gro_complete);

net/ipv4/udp_offload.c

···
 
 	skb_shinfo(skb)->gso_segs = NAPI_GRO_CB(skb)->count;
 	skb_shinfo(skb)->gso_type |= SKB_GSO_UDP_L4;
+
+	if (skb->encapsulation)
+		skb->inner_transport_header = skb->transport_header;
+
 	return 0;
 }
 

net/mptcp/pm_netlink.c

···
 	struct mptcp_addr_info	addr;
 	u8			flags;
 	int			ifindex;
-	struct rcu_head		rcu;
 	struct socket		*lsk;
 };
 

net/qrtr/mhi.c

···
 	struct qrtr_endpoint ep;
 	struct mhi_device *mhi_dev;
 	struct device *dev;
+	struct completion ready;
 };
 
 /* From MHI to QRTR */
···
 	struct qrtr_mhi_dev *qdev = container_of(ep, struct qrtr_mhi_dev, ep);
 	int rc;
 
+	rc = wait_for_completion_interruptible(&qdev->ready);
+	if (rc)
+		goto free_skb;
+
 	if (skb->sk)
 		sock_hold(skb->sk);
 
···
 	int rc;
 
 	/* start channels */
-	rc = mhi_prepare_for_transfer(mhi_dev);
+	rc = mhi_prepare_for_transfer(mhi_dev, 0);
 	if (rc)
 		return rc;
 
···
 	if (rc)
 		return rc;
 
+	/* start channels */
+	rc = mhi_prepare_for_transfer(mhi_dev, MHI_CH_INBOUND_ALLOC_BUFS);
+	if (rc) {
+		qrtr_endpoint_unregister(&qdev->ep);
+		dev_set_drvdata(&mhi_dev->dev, NULL);
+		return rc;
+	}
+
+	complete_all(&qdev->ready);
 	dev_dbg(qdev->dev, "Qualcomm MHI QRTR driver probed\n");
 
 	return 0;

net/sched/sch_generic.c

···
 
 	/* seqlock has the same scope of busylock, for NOLOCK qdisc */
 	spin_lock_init(&sch->seqlock);
-	lockdep_set_class(&sch->busylock,
+	lockdep_set_class(&sch->seqlock,
 			  dev->qdisc_tx_busylock ?: &qdisc_tx_busylock);
 
 	seqcount_init(&sch->running);

net/sched/sch_taprio.c

···
 		if (FULL_OFFLOAD_IS_ENABLED(q->flags)) {
 			qdisc->flags |= TCQ_F_ONETXQUEUE | TCQ_F_NOPARENT;
 			old = dev_graft_qdisc(qdisc->dev_queue, qdisc);
-			if (ntx < dev->real_num_tx_queues)
-				qdisc_hash_add(qdisc, false);
 		} else {
 			old = dev_graft_qdisc(qdisc->dev_queue, sch);
 			qdisc_refcount_inc(sch);

net/sctp/auth.c

···
 	memcpy(key->data, &auth_key->sca_key[0], auth_key->sca_keylength);
 	cur_key->key = key;
 
-	if (replace) {
-		list_del_init(&shkey->key_list);
-		sctp_auth_shkey_release(shkey);
-		if (asoc && asoc->active_key_id == auth_key->sca_keynumber)
-			sctp_auth_asoc_init_active_key(asoc, GFP_KERNEL);
+	if (!replace) {
+		list_add(&cur_key->key_list, sh_keys);
+		return 0;
 	}
+
+	list_del_init(&shkey->key_list);
+	sctp_auth_shkey_release(shkey);
 	list_add(&cur_key->key_list, sh_keys);
+
+	if (asoc && asoc->active_key_id == auth_key->sca_keynumber)
+		sctp_auth_asoc_init_active_key(asoc, GFP_KERNEL);
 
 	return 0;
 }

net/vmw_vsock/virtio_transport_common.c

···
 		virtio_transport_recv_enqueue(vsk, pkt);
 		sk->sk_data_ready(sk);
 		return err;
+	case VIRTIO_VSOCK_OP_CREDIT_REQUEST:
+		virtio_transport_send_credit_update(vsk);
+		break;
 	case VIRTIO_VSOCK_OP_CREDIT_UPDATE:
 		sk->sk_write_space(sk);
 		break;

net/xfrm/xfrm_compat.c

···
 	len = nlmsg_attrlen(nlh_src, xfrm_msg_min[type]);
 
 	nla_for_each_attr(nla, attrs, len, remaining) {
-		int err = xfrm_xlate64_attr(dst, nla);
+		int err;
 
+		switch (type) {
+		case XFRM_MSG_NEWSPDINFO:
+			err = xfrm_nla_cpy(dst, nla, nla_len(nla));
+			break;
+		default:
+			err = xfrm_xlate64_attr(dst, nla);
+			break;
+		}
 		if (err)
 			return err;
 	}
···
 
 /* Calculates len of translated 64-bit message. */
 static size_t xfrm_user_rcv_calculate_len64(const struct nlmsghdr *src,
-					    struct nlattr *attrs[XFRMA_MAX+1])
+					    struct nlattr *attrs[XFRMA_MAX + 1],
+					    int maxtype)
 {
 	size_t len = nlmsg_len(src);
 
···
 	case XFRM_MSG_POLEXPIRE:
 		len += 8;
 		break;
+	case XFRM_MSG_NEWSPDINFO:
+		/* attirbutes are xfrm_spdattr_type_t, not xfrm_attr_type_t */
+		return len;
 	default:
 		break;
 	}
+
+	/* Unexpected for anything, but XFRM_MSG_NEWSPDINFO, please
+	 * correct both 64=>32-bit and 32=>64-bit translators to copy
+	 * new attributes.
+	 */
+	if (WARN_ON_ONCE(maxtype))
+		return len;
 
 	if (attrs[XFRMA_SA])
 		len += 4;
···
 
 static int xfrm_xlate32(struct nlmsghdr *dst, const struct nlmsghdr *src,
 			struct nlattr *attrs[XFRMA_MAX+1],
-			size_t size, u8 type, struct netlink_ext_ack *extack)
+			size_t size, u8 type, int maxtype,
+			struct netlink_ext_ack *extack)
 {
 	size_t pos;
 	int i;
···
 	}
 	pos = dst->nlmsg_len;
 
+	if (maxtype) {
+		/* attirbutes are xfrm_spdattr_type_t, not xfrm_attr_type_t */
+		WARN_ON_ONCE(src->nlmsg_type != XFRM_MSG_NEWSPDINFO);
+
+		for (i = 1; i <= maxtype; i++) {
+			int err;
+
+			if (!attrs[i])
+				continue;
+
+			/* just copy - no need for translation */
+			err = xfrm_attr_cpy32(dst, &pos, attrs[i], size,
+					nla_len(attrs[i]), nla_len(attrs[i]));
+			if (err)
+				return err;
+		}
+		return 0;
+	}
+
 	for (i = 1; i < XFRMA_MAX + 1; i++) {
 		int err;
 
···
 	if (err < 0)
 		return ERR_PTR(err);
 
-	len = xfrm_user_rcv_calculate_len64(h32, attrs);
+	len = xfrm_user_rcv_calculate_len64(h32, attrs, maxtype);
 	/* The message doesn't need translation */
 	if (len == nlmsg_len(h32))
 		return NULL;
···
 	if (!h64)
 		return ERR_PTR(-ENOMEM);
 
-	err = xfrm_xlate32(h64, h32, attrs, len, type, extack);
+	err = xfrm_xlate32(h64, h32, attrs, len, type, maxtype, extack);
 	if (err < 0) {
 		kvfree(h64);
 		return ERR_PTR(err);

net/xfrm/xfrm_ipcomp.c

···
 			break;
 	}
 
-	WARN_ON(!pos);
+	WARN_ON(list_entry_is_head(pos, &ipcomp_tfms_list, list));
 
 	if (--pos->users)
 		return;

net/xfrm/xfrm_policy.c

···
 						__read_mostly;
 
 static struct kmem_cache *xfrm_dst_cache __ro_after_init;
-static __read_mostly seqcount_mutex_t xfrm_policy_hash_generation;
 
 static struct rhashtable xfrm_policy_inexact_table;
 static const struct rhashtable_params xfrm_pol_inexact_params;
···
 		return;
 
 	spin_lock_bh(&net->xfrm.xfrm_policy_lock);
-	write_seqcount_begin(&xfrm_policy_hash_generation);
+	write_seqcount_begin(&net->xfrm.xfrm_policy_hash_generation);
 
 	odst = rcu_dereference_protected(net->xfrm.policy_bydst[dir].table,
 				lockdep_is_held(&net->xfrm.xfrm_policy_lock));
···
 	rcu_assign_pointer(net->xfrm.policy_bydst[dir].table, ndst);
 	net->xfrm.policy_bydst[dir].hmask = nhashmask;
 
-	write_seqcount_end(&xfrm_policy_hash_generation);
+	write_seqcount_end(&net->xfrm.xfrm_policy_hash_generation);
 	spin_unlock_bh(&net->xfrm.xfrm_policy_lock);
 
 	synchronize_rcu();
···
 	} while (read_seqretry(&net->xfrm.policy_hthresh.lock, seq));
 
 	spin_lock_bh(&net->xfrm.xfrm_policy_lock);
-	write_seqcount_begin(&xfrm_policy_hash_generation);
+	write_seqcount_begin(&net->xfrm.xfrm_policy_hash_generation);
 
 	/* make sure that we can insert the indirect policies again before
 	 * we start with destructive action.
···
 
 out_unlock:
 	__xfrm_policy_inexact_flush(net);
-	write_seqcount_end(&xfrm_policy_hash_generation);
+	write_seqcount_end(&net->xfrm.xfrm_policy_hash_generation);
 	spin_unlock_bh(&net->xfrm.xfrm_policy_lock);
 
 	mutex_unlock(&hash_resize_mutex);
···
 	if (unlikely(!daddr || !saddr))
 		return NULL;
 
- retry:
-	sequence = read_seqcount_begin(&xfrm_policy_hash_generation);
 	rcu_read_lock();
-
-	chain = policy_hash_direct(net, daddr, saddr, family, dir);
-	if (read_seqcount_retry(&xfrm_policy_hash_generation, sequence)) {
-		rcu_read_unlock();
-		goto retry;
-	}
+ retry:
+	do {
+		sequence = read_seqcount_begin(&net->xfrm.xfrm_policy_hash_generation);
+		chain = policy_hash_direct(net, daddr, saddr, family, dir);
+	} while (read_seqcount_retry(&net->xfrm.xfrm_policy_hash_generation, sequence));
 
 	ret = NULL;
 	hlist_for_each_entry_rcu(pol, chain, bydst) {
···
 	}
 
 skip_inexact:
-	if (read_seqcount_retry(&xfrm_policy_hash_generation, sequence)) {
-		rcu_read_unlock();
+	if (read_seqcount_retry(&net->xfrm.xfrm_policy_hash_generation, sequence))
 		goto retry;
-	}
 
-	if (ret && !xfrm_pol_hold_rcu(ret)) {
-		rcu_read_unlock();
+	if (ret && !xfrm_pol_hold_rcu(ret))
 		goto retry;
-	}
 fail:
 	rcu_read_unlock();
 
···
 	/* Initialize the per-net locks here */
 	spin_lock_init(&net->xfrm.xfrm_state_lock);
 	spin_lock_init(&net->xfrm.xfrm_policy_lock);
+	seqcount_spinlock_init(&net->xfrm.xfrm_policy_hash_generation, &net->xfrm.xfrm_policy_lock);
 	mutex_init(&net->xfrm.xfrm_cfg_mutex);
 
 	rv = xfrm_statistics_init(net);
···
 {
 	register_pernet_subsys(&xfrm_net_ops);
 	xfrm_dev_init();
-	seqcount_mutex_init(&xfrm_policy_hash_generation, &hash_resize_mutex);
 	xfrm_input_init();
 
 #ifdef CONFIG_XFRM_ESPINTCP

net/xfrm/xfrm_user.c

···
 
 	err = link->doit(skb, nlh, attrs);
 
+	/* We need to free skb allocated in xfrm_alloc_compat() before
+	 * returning from this function, because consume_skb() won't take
+	 * care of frag_list since netlink destructor sets
+	 * sbk->head to NULL. (see netlink_skb_destructor())
+	 */
+	if (skb_has_frag_list(skb)) {
+		kfree_skb(skb_shinfo(skb)->frag_list);
+		skb_shinfo(skb)->frag_list = NULL;
+	}
+
 err:
 	kvfree(nlh64);
 	return err;

scripts/recordmcount.pl

···
 my $mcount_adjust;	# Address adjustment to mcount offset
 my $alignment;		# The .align value to use for $mcount_section
 my $section_type;	# Section header plus possible alignment command
-my $can_use_local = 0; 	# If we can use local function references
-
-# Shut up recordmcount if user has older objcopy
-my $quiet_recordmcount = ".tmp_quiet_recordmcount";
-my $print_warning = 1;
-$print_warning = 0 if ( -f $quiet_recordmcount);
-
-##
-# check_objcopy - whether objcopy supports --globalize-symbols
-#
-#  --globalize-symbols came out in 2.17, we must test the version
-#  of objcopy, and if it is less than 2.17, then we can not
-#  record local functions.
-sub check_objcopy
-{
-    open (IN, "$objcopy --version |") or die "error running $objcopy";
-    while (<IN>) {
-	if (/objcopy.*\s(\d+)\.(\d+)/) {
-	    $can_use_local = 1 if ($1 > 2 || ($1 == 2 && $2 >= 17));
-	    last;
-	}
-    }
-    close (IN);
-
-    if (!$can_use_local && $print_warning) {
-	print STDERR "WARNING: could not find objcopy version or version " .
-	    "is less than 2.17.\n" .
-	    "\tLocal function references are disabled.\n";
-	open (QUIET, ">$quiet_recordmcount");
-	printf QUIET "Disables the warning from recordmcount.pl\n";
-	close QUIET;
-    }
-}
 
 if ($arch =~ /(x86(_64)?)|(i386)/) {
     if ($bits == 64) {
···
 my $mcount_s = $dirname . "/.tmp_mc_" . $prefix . ".s";
 my $mcount_o = $dirname . "/.tmp_mc_" . $prefix . ".o";
 
-check_objcopy();
-
 #
 # Step 1: find all the local (static functions) and weak symbols.
 #         't' is local, 'w/W' is weak
···
 
     # is this function static? If so, note this fact.
     if (defined $locals{$ref_func}) {
-
-	# only use locals if objcopy supports globalize-symbols
-	if (!$can_use_local) {
-	    return;
-	}
 	$convert{$ref_func} = 1;
     }
 

scripts/tracing/draw_functrace.py

···
 	$ cat /sys/kernel/debug/tracing/trace_pipe > ~/raw_trace_func
 	Wait some times but not too much, the script is a bit slow.
 	Break the pipe (Ctrl + Z)
-	$ scripts/draw_functrace.py < raw_trace_func > draw_functrace
+	$ scripts/tracing/draw_functrace.py < ~/raw_trace_func > draw_functrace
 	Then you have your drawn trace in draw_functrace
 """
 
···
 	line = line.strip()
 	if line.startswith("#"):
 		raise CommentLineException
-	m = re.match("[^]]+?\\] +([0-9.]+): (\\w+) <-(\\w+)", line)
+	m = re.match("[^]]+?\\] +([a-z.]+) +([0-9.]+): (\\w+) <-(\\w+)", line)
 	if m is None:
 		raise BrokenLineException
-	return (m.group(1), m.group(2), m.group(3))
+	return (m.group(2), m.group(3), m.group(4))
 
 
 def main():

security/selinux/ss/policydb.c

···
 	rc = sidtab_init(s);
 	if (rc) {
 		pr_err("SELinux:  out of memory on SID table init\n");
-		goto out;
+		return rc;
 	}
 
 	head = p->ocontexts[OCON_ISID];
···
 		if (sid == SECSID_NULL) {
 			pr_err("SELinux:  SID 0 was assigned a context.\n");
 			sidtab_destroy(s);
-			goto out;
+			return -EINVAL;
 		}
 
 		/* Ignore initial SIDs unused by this kernel. */
···
 			pr_err("SELinux:  unable to load initial SID %s.\n",
 			       name);
 			sidtab_destroy(s);
-			goto out;
+			return rc;
 		}
 	}
-	rc = 0;
-out:
-	return rc;
+	return 0;
 }
 
 int policydb_class_isvalid(struct policydb *p, unsigned int class)

tools/perf/util/cs-etm.c

···
 	return 0;
 }
 
+static void dump_queued_data(struct cs_etm_auxtrace *etm,
+			     struct perf_record_auxtrace *event)
+{
+	struct auxtrace_buffer *buf;
+	unsigned int i;
+	/*
+	 * Find all buffers with same reference in the queues and dump them.
+	 * This is because the queues can contain multiple entries of the same
+	 * buffer that were split on aux records.
+	 */
+	for (i = 0; i < etm->queues.nr_queues; ++i)
+		list_for_each_entry(buf, &etm->queues.queue_array[i].head, list)
+			if (buf->reference == event->reference)
+				cs_etm__dump_event(etm, buf);
+}
+
 static int cs_etm__process_auxtrace_event(struct perf_session *session,
 					  union perf_event *event,
 					  struct perf_tool *tool __maybe_unused)
···
 				cs_etm__dump_event(etm, buffer);
 				auxtrace_buffer__put_data(buffer);
 			}
-	}
+	} else if (dump_trace)
+		dump_queued_data(etm, &event->auxtrace);
 
 	return 0;
 }
···
 
 	if (dump_trace) {
 		cs_etm__print_auxtrace_info(auxtrace_info->priv, num_cpu);
-		return 0;
 	}
 
 	err = cs_etm__synth_events(etm, session);

tools/perf/util/map.c

···
 			if (!(prot & PROT_EXEC))
 				dso__set_loaded(dso);
 		}
-
-		nsinfo__put(dso->nsinfo);
 		dso->nsinfo = nsi;
 
 		if (build_id__is_defined(bid))

tools/perf/util/pmu.c

···
 	return perf_pmu__find_map(NULL);
 }
 
-static bool perf_pmu__valid_suffix(char *pmu_name, char *tok)
+/*
+ * Suffix must be in form tok_{digits}, or tok{digits}, or same as pmu_name
+ * to be valid.
+ */
+static bool perf_pmu__valid_suffix(const char *pmu_name, char *tok)
 {
-	char *p;
+	const char *p;
 
 	if (strncmp(pmu_name, tok, strlen(tok)))
 		return false;
···
 	if (*p == 0)
 		return true;
 
-	if (*p != '_')
-		return false;
+	if (*p == '_')
+		++p;
 
-	++p;
-	if (*p == 0 || !isdigit(*p))
-		return false;
+	/* Ensure we end in a number */
+	while (1) {
+		if (!isdigit(*p))
+			return false;
+		if (*(++p) == 0)
+			break;
+	}
 
 	return true;
 }
···
 	 *	    match "socket" in "socketX_pmunameY" and then "pmuname" in
 	 *	    "pmunameY".
 	 */
-	for (; tok; name += strlen(tok), tok = strtok_r(NULL, ",", &tmp)) {
+	while (1) {
+		char *next_tok = strtok_r(NULL, ",", &tmp);
+
 		name = strstr(name, tok);
-		if (!name || !perf_pmu__valid_suffix((char *)name, tok)) {
+		if (!name ||
+		    (!next_tok && !perf_pmu__valid_suffix(name, tok))) {
 			res = false;
 			goto out;
 		}
+		if (!next_tok)
+			break;
+		tok = next_tok;
+		name += strlen(tok);
 	}
 
 	res = true;

tools/testing/selftests/kvm/include/x86_64/hyperv.h

···
 #define HV_X64_GUEST_DEBUGGING_AVAILABLE		BIT(1)
 #define HV_X64_PERF_MONITOR_AVAILABLE			BIT(2)
 #define HV_X64_CPU_DYNAMIC_PARTITIONING_AVAILABLE	BIT(3)
-#define HV_X64_HYPERCALL_PARAMS_XMM_AVAILABLE		BIT(4)
+#define HV_X64_HYPERCALL_XMM_INPUT_AVAILABLE		BIT(4)
 #define HV_X64_GUEST_IDLE_STATE_AVAILABLE		BIT(5)
 #define HV_FEATURE_FREQUENCY_MSRS_AVAILABLE		BIT(8)
 #define HV_FEATURE_GUEST_CRASH_MSR_AVAILABLE		BIT(10)
···
 #define HV_STATUS_INVALID_PORT_ID		17
 #define HV_STATUS_INVALID_CONNECTION_ID		18
 #define HV_STATUS_INSUFFICIENT_BUFFERS		19
+
+/* hypercall options */
+#define HV_HYPERCALL_FAST_BIT		BIT(16)
 
 #endif /* !SELFTEST_KVM_HYPERV_H */

tools/testing/selftests/kvm/x86_64/hyperv_clock.c

···
 	vcpu_set_hv_cpuid(vm, VCPU_ID);
 
 	tsc_page_gva = vm_vaddr_alloc_page(vm);
-	memset(addr_gpa2hva(vm, tsc_page_gva), 0x0, getpagesize());
+	memset(addr_gva2hva(vm, tsc_page_gva), 0x0, getpagesize());
 	TEST_ASSERT((addr_gva2gpa(vm, tsc_page_gva) & (getpagesize() - 1)) == 0,
 		"TSC page has to be page aligned\n");
 	vcpu_args_set(vm, VCPU_ID, 2, tsc_page_gva, addr_gva2gpa(vm, tsc_page_gva));

tools/testing/selftests/kvm/x86_64/hyperv_features.c

···
 }
 
 static int nr_gp;
+static int nr_ud;
 
 static inline u64 hypercall(u64 control, vm_vaddr_t input_address,
 			    vm_vaddr_t output_address)
···
 		regs->rip = (uint64_t)&wrmsr_end;
 }
 
+static void guest_ud_handler(struct ex_regs *regs)
+{
+	nr_ud++;
+	regs->rip += 3;
+}
+
 struct msr_data {
 	uint32_t idx;
 	bool available;
···
 struct hcall_data {
 	uint64_t control;
 	uint64_t expect;
+	bool ud_expected;
 };
 
 static void guest_msr(struct msr_data *msr)
···
 static void guest_hcall(vm_vaddr_t pgs_gpa, struct hcall_data *hcall)
 {
 	int i = 0;
+	u64 res, input, output;
 
 	wrmsr(HV_X64_MSR_GUEST_OS_ID, LINUX_OS_ID);
 	wrmsr(HV_X64_MSR_HYPERCALL, pgs_gpa);
 
 	while (hcall->control) {
-		GUEST_ASSERT(hypercall(hcall->control, pgs_gpa,
-				       pgs_gpa + 4096) == hcall->expect);
+		nr_ud = 0;
+		if (!(hcall->control & HV_HYPERCALL_FAST_BIT)) {
+			input = pgs_gpa;
+			output = pgs_gpa + 4096;
+		} else {
+			input = output = 0;
+		}
+
+		res = hypercall(hcall->control, input, output);
+		if (hcall->ud_expected)
+			GUEST_ASSERT(nr_ud == 1);
+		else
+			GUEST_ASSERT(res == hcall->expect);
+
 		GUEST_SYNC(i++);
 	}
 
···
 			recomm.ebx = 0xfff;
 			hcall->expect = HV_STATUS_SUCCESS;
 			break;
-
 		case 17:
+			/* XMM fast hypercall */
+			hcall->control = HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE | HV_HYPERCALL_FAST_BIT;
+			hcall->ud_expected = true;
+			break;
+		case 18:
+			feat.edx |= HV_X64_HYPERCALL_XMM_INPUT_AVAILABLE;
+			hcall->ud_expected = false;
+			hcall->expect = HV_STATUS_SUCCESS;
+			break;
+
+		case 19:
 			/* END */
 			hcall->control = 0;
 			break;
···
 
 	/* Test hypercalls */
 	vm = vm_create_default(VCPU_ID, 0, guest_hcall);
+
+	vm_init_descriptor_tables(vm);
+	vcpu_init_descriptor_tables(vm, VCPU_ID);
+	vm_install_exception_handler(vm, UD_VECTOR, guest_ud_handler);
 
 	/* Hypercall input/output */
 	hcall_page = vm_vaddr_alloc_pages(vm, 2);

tools/testing/selftests/net/ipsec.c

···
 	MONITOR_ACQUIRE,
 	EXPIRE_STATE,
 	EXPIRE_POLICY,
+	SPDINFO_ATTRS,
 };
 const char *desc_name[] = {
 	"create tunnel",
 	"alloc spi",
 	"monitor acquire",
 	"expire state",
-	"expire policy"
+	"expire policy",
+	"spdinfo attributes",
+	""
 };
 struct xfrm_desc {
 	enum desc_type	type;
···
 	return ret;
 }
 
+static int xfrm_spdinfo_set_thresh(int xfrm_sock, uint32_t *seq,
+		unsigned thresh4_l, unsigned thresh4_r,
+		unsigned thresh6_l, unsigned thresh6_r,
+		bool add_bad_attr)
+
+{
+	struct {
+		struct nlmsghdr		nh;
+		union {
+			uint32_t	unused;
+			int		error;
+		};
+		char			attrbuf[MAX_PAYLOAD];
+	} req;
+	struct xfrmu_spdhthresh thresh;
+
+	memset(&req, 0, sizeof(req));
+	req.nh.nlmsg_len	= NLMSG_LENGTH(sizeof(req.unused));
+	req.nh.nlmsg_type	= XFRM_MSG_NEWSPDINFO;
+	req.nh.nlmsg_flags	= NLM_F_REQUEST | NLM_F_ACK;
+	req.nh.nlmsg_seq	= (*seq)++;
+
+	thresh.lbits = thresh4_l;
+	thresh.rbits = thresh4_r;
+	if (rtattr_pack(&req.nh, sizeof(req), XFRMA_SPD_IPV4_HTHRESH, &thresh, sizeof(thresh)))
+		return -1;
+
+	thresh.lbits = thresh6_l;
+	thresh.rbits = thresh6_r;
+	if (rtattr_pack(&req.nh, sizeof(req), XFRMA_SPD_IPV6_HTHRESH, &thresh, sizeof(thresh)))
+		return -1;
+
+	if (add_bad_attr) {
+		BUILD_BUG_ON(XFRMA_IF_ID <= XFRMA_SPD_MAX + 1);
+		if (rtattr_pack(&req.nh, sizeof(req), XFRMA_IF_ID, NULL, 0)) {
+			pr_err("adding attribute failed: no space");
+			return -1;
+		}
+	}
+
+	if (send(xfrm_sock, &req, req.nh.nlmsg_len, 0) < 0) {
+		pr_err("send()");
+		return -1;
+	}
+
+	if (recv(xfrm_sock, &req, sizeof(req), 0) < 0) {
+		pr_err("recv()");
+		return -1;
+	} else if (req.nh.nlmsg_type != NLMSG_ERROR) {
+		printk("expected NLMSG_ERROR, got %d", (int)req.nh.nlmsg_type);
+		return -1;
+	}
+
+	if (req.error) {
+		printk("NLMSG_ERROR: %d: %s", req.error, strerror(-req.error));
+		return -1;
+	}
+
+	return 0;
+}
+
+static int xfrm_spdinfo_attrs(int xfrm_sock, uint32_t *seq)
+{
+	struct {
+		struct nlmsghdr			nh;
+		union {
+			uint32_t	unused;
+			int		error;
+		};
+		char			attrbuf[MAX_PAYLOAD];
+	} req;
+
+	if (xfrm_spdinfo_set_thresh(xfrm_sock, seq, 32, 31, 120, 16, false)) {
+		pr_err("Can't set SPD HTHRESH");
+		return KSFT_FAIL;
+	}
+
+	memset(&req, 0, sizeof(req));
+
+	req.nh.nlmsg_len	= NLMSG_LENGTH(sizeof(req.unused));
+	req.nh.nlmsg_type	= XFRM_MSG_GETSPDINFO;
+	req.nh.nlmsg_flags	= NLM_F_REQUEST;
+	req.nh.nlmsg_seq	= (*seq)++;
+	if (send(xfrm_sock, &req, req.nh.nlmsg_len, 0) < 0) {
+		pr_err("send()");
+		return KSFT_FAIL;
+	}
+
+	if (recv(xfrm_sock, &req, sizeof(req), 0) < 0) {
+		pr_err("recv()");
+		return KSFT_FAIL;
+	} else if (req.nh.nlmsg_type == XFRM_MSG_NEWSPDINFO) {
+		size_t len = NLMSG_PAYLOAD(&req.nh, sizeof(req.unused));
+		struct rtattr *attr = (void *)req.attrbuf;
+		int got_thresh = 0;
+
+		for (; RTA_OK(attr, len); attr = RTA_NEXT(attr, len)) {
+			if (attr->rta_type == XFRMA_SPD_IPV4_HTHRESH) {
+				struct xfrmu_spdhthresh *t = RTA_DATA(attr);
+
+				got_thresh++;
+				if (t->lbits != 32 || t->rbits != 31) {
+					pr_err("thresh differ: %u, %u",
+							t->lbits, t->rbits);
+					return KSFT_FAIL;
+				}
+			}
+			if (attr->rta_type == XFRMA_SPD_IPV6_HTHRESH) {
+				struct xfrmu_spdhthresh *t = RTA_DATA(attr);
+
+				got_thresh++;
+				if (t->lbits != 120 || t->rbits != 16) {
+					pr_err("thresh differ: %u, %u",
+							t->lbits, t->rbits);
+					return KSFT_FAIL;
+				}
+			}
+		}
+		if (got_thresh != 2) {
+			pr_err("only %d thresh returned by XFRM_MSG_GETSPDINFO", got_thresh);
+			return KSFT_FAIL;
+		}
+	} else if (req.nh.nlmsg_type != NLMSG_ERROR) {
+		printk("expected NLMSG_ERROR, got %d", (int)req.nh.nlmsg_type);
+		return KSFT_FAIL;
+	} else {
+		printk("NLMSG_ERROR: %d: %s", req.error, strerror(-req.error));
+		return -1;
+	}
+
+	/* Restore the default */
+	if (xfrm_spdinfo_set_thresh(xfrm_sock, seq, 32, 32, 128, 128, false)) {
+		pr_err("Can't restore SPD HTHRESH");
+		return KSFT_FAIL;
+	}
+
+	/*
+	 * At this moment xfrm uses nlmsg_parse_deprecated(), which
+	 * implies NL_VALIDATE_LIBERAL - ignoring attributes with
+	 * (type > maxtype). nla_parse_depricated_strict() would enforce
+	 * it. Or even stricter nla_parse().
+	 * Right now it's not expected to fail, but to be ignored.
+	 */
+	if (xfrm_spdinfo_set_thresh(xfrm_sock, seq, 32, 32, 128, 128, true))
+		return KSFT_PASS;
+
+	return KSFT_PASS;
+}
+
 static int child_serv(int xfrm_sock, uint32_t *seq,
 		unsigned int nr, int cmd_fd, void *buf, struct xfrm_desc *desc)
 {
···
 			break;
 		case EXPIRE_POLICY:
 			ret = xfrm_expire_policy(xfrm_sock, &seq, nr, &desc);
+			break;
+		case SPDINFO_ATTRS:
+			ret = xfrm_spdinfo_attrs(xfrm_sock, &seq);
 			break;
 		default:
 			printk("Unknown desc type %d", desc.type);
···
  *   sizeof(xfrm_user_polexpire)  = 168  |  sizeof(xfrm_user_polexpire)  = 176
  *
  * Check the affected by the UABI difference structures.
+ * Also, check translation for xfrm_set_spdinfo: it has it's own attributes
+ * which needs to be correctly copied, but not translated.
  */
-const unsigned int compat_plan = 4;
+const unsigned int compat_plan = 5;
 static int write_compat_struct_tests(int test_desc_fd)
 {
 	struct xfrm_desc desc = {};
···
 		return -1;
 
 	desc.type = EXPIRE_POLICY;
+	if (__write_desc(test_desc_fd, &desc))
+		return -1;
+
+	desc.type = SPDINFO_ATTRS;
 	if (__write_desc(test_desc_fd, &desc))
 		return -1;
 

virt/kvm/kvm_main.c

···
 
 static int kvm_create_vm_debugfs(struct kvm *kvm, int fd)
 {
+	static DEFINE_MUTEX(kvm_debugfs_lock);
+	struct dentry *dent;
 	char dir_name[ITOA_MAX_LEN * 2];
 	struct kvm_stat_data *stat_data;
 	const struct _kvm_stats_desc *pdesc;
···
 		return 0;
 
 	snprintf(dir_name, sizeof(dir_name), "%d-%d", task_pid_nr(current), fd);
-	kvm->debugfs_dentry = debugfs_create_dir(dir_name, kvm_debugfs_dir);
+	mutex_lock(&kvm_debugfs_lock);
+	dent = debugfs_lookup(dir_name, kvm_debugfs_dir);
+	if (dent) {
+		pr_warn_ratelimited("KVM: debugfs: duplicate directory %s\n", dir_name);
+		dput(dent);
+		mutex_unlock(&kvm_debugfs_lock);
+		return 0;
+	}
+	dent = debugfs_create_dir(dir_name, kvm_debugfs_dir);
+	mutex_unlock(&kvm_debugfs_lock);
+	if (IS_ERR(dent))
+		return 0;
 
+	kvm->debugfs_dentry = dent;
 	kvm->debugfs_stat_data = kcalloc(kvm_debugfs_num_entries,
 					 sizeof(*kvm->debugfs_stat_data),
 					 GFP_KERNEL_ACCOUNT);
···
 	}
 	add_uevent_var(env, "PID=%d", kvm->userspace_pid);
 
-	if (!IS_ERR_OR_NULL(kvm->debugfs_dentry)) {
+	if (kvm->debugfs_dentry) {
 		char *tmp, *p = kmalloc(PATH_MAX, GFP_KERNEL_ACCOUNT);
 
 		if (p) {