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

Makefile

@@ -1172,7 +1172,7 @@ headers_check_all: headers_install_all
 PHONY += headers_check
 headers_check: headers_install
 	$(Q)$(MAKE) $(hdr-inst)=include/uapi HDRCHECK=1
-	$(Q)$(MAKE) $(hdr-inst)=arch/$(hdr-arch)/include/uapi/ $(hdr-dst) HDRCHECK=1
+	$(Q)$(MAKE) $(hdr-inst)=arch/$(hdr-arch)/include/uapi $(hdr-dst) HDRCHECK=1
 
 # ---------------------------------------------------------------------------
 # Kernel selftest

arch/s390/include/asm/debug.h

@@ -10,6 +10,7 @@
 #include <linux/spinlock.h>
 #include <linux/kernel.h>
 #include <linux/time.h>
+#include <linux/refcount.h>
 #include <uapi/asm/debug.h>
 
 #define DEBUG_MAX_LEVEL            6  /* debug levels range from 0 to 6 */
@@ -31,7 +32,7 @@ struct debug_view;
 typedef struct debug_info {	
 	struct debug_info* next;
 	struct debug_info* prev;
-	atomic_t ref_count;
+	refcount_t ref_count;
 	spinlock_t lock;			
 	int level;
 	int nr_areas;

arch/s390/include/asm/dis.h

@@ -40,6 +40,8 @@ static inline int insn_length(unsigned char code)
 	return ((((int) code + 64) >> 7) + 1) << 1;
 }
 
+struct pt_regs;
+
 void show_code(struct pt_regs *regs);
 void print_fn_code(unsigned char *code, unsigned long len);
 int insn_to_mnemonic(unsigned char *instruction, char *buf, unsigned int len);

arch/s390/include/asm/kprobes.h

@@ -27,12 +27,21 @@
  * 2005-Dec	Used as a template for s390 by Mike Grundy
  *		<grundym@us.ibm.com>
  */
+#include <linux/types.h>
 #include <asm-generic/kprobes.h>
 
 #define BREAKPOINT_INSTRUCTION	0x0002
 
+#define FIXUP_PSW_NORMAL	0x08
+#define FIXUP_BRANCH_NOT_TAKEN	0x04
+#define FIXUP_RETURN_REGISTER	0x02
+#define FIXUP_NOT_REQUIRED	0x01
+
+int probe_is_prohibited_opcode(u16 *insn);
+int probe_get_fixup_type(u16 *insn);
+int probe_is_insn_relative_long(u16 *insn);
+
 #ifdef CONFIG_KPROBES
-#include <linux/types.h>
 #include <linux/ptrace.h>
 #include <linux/percpu.h>
 #include <linux/sched/task_stack.h>
@@ -56,11 +65,6 @@ typedef u16 kprobe_opcode_t;
 
 #define KPROBE_SWAP_INST	0x10
 
-#define FIXUP_PSW_NORMAL	0x08
-#define FIXUP_BRANCH_NOT_TAKEN	0x04
-#define FIXUP_RETURN_REGISTER	0x02
-#define FIXUP_NOT_REQUIRED	0x01
-
 /* Architecture specific copy of original instruction */
 struct arch_specific_insn {
 	/* copy of original instruction */
@@ -90,10 +94,6 @@ int kprobe_fault_handler(struct pt_regs *regs, int trapnr);
 int kprobe_exceptions_notify(struct notifier_block *self,
 	unsigned long val, void *data);
 
-int probe_is_prohibited_opcode(u16 *insn);
-int probe_get_fixup_type(u16 *insn);
-int probe_is_insn_relative_long(u16 *insn);
-
 #define flush_insn_slot(p)	do { } while (0)
 
 #endif /* CONFIG_KPROBES */

arch/s390/include/asm/sysinfo.h

@@ -146,7 +146,7 @@ extern int topology_max_mnest;
  * Returns the maximum nesting level supported by the cpu topology code.
  * The current maximum level is 4 which is the drawer level.
  */
-static inline int topology_mnest_limit(void)
+static inline unsigned char topology_mnest_limit(void)
 {
 	return min(topology_max_mnest, 4);
 }

arch/s390/kernel/debug.c

@@ -277,7 +277,7 @@ debug_info_alloc(const char *name, int pages_per_area, int nr_areas,
 	memset(rc->views, 0, DEBUG_MAX_VIEWS * sizeof(struct debug_view *));
 	memset(rc->debugfs_entries, 0 ,DEBUG_MAX_VIEWS *
 		sizeof(struct dentry*));
-	atomic_set(&(rc->ref_count), 0);
+	refcount_set(&(rc->ref_count), 0);
 
 	return rc;
 
@@ -361,7 +361,7 @@ debug_info_create(const char *name, int pages_per_area, int nr_areas,
         debug_area_last = rc;
         rc->next = NULL;
 
-	debug_info_get(rc);
+	refcount_set(&rc->ref_count, 1);
 out:
 	return rc;
 }
@@ -416,7 +416,7 @@ static void
 debug_info_get(debug_info_t * db_info)
 {
 	if (db_info)
-		atomic_inc(&db_info->ref_count);
+		refcount_inc(&db_info->ref_count);
 }
 
 /*
@@ -431,7 +431,7 @@ debug_info_put(debug_info_t *db_info)
 
 	if (!db_info)
 		return;
-	if (atomic_dec_and_test(&db_info->ref_count)) {
+	if (refcount_dec_and_test(&db_info->ref_count)) {
 		for (i = 0; i < DEBUG_MAX_VIEWS; i++) {
 			if (!db_info->views[i])
 				continue;

arch/s390/kernel/entry.S

@@ -312,6 +312,7 @@ ENTRY(system_call)
 	lg	%r14,__LC_VDSO_PER_CPU
 	lmg	%r0,%r10,__PT_R0(%r11)
 	mvc	__LC_RETURN_PSW(16),__PT_PSW(%r11)
+.Lsysc_exit_timer:
 	stpt	__LC_EXIT_TIMER
 	mvc	__VDSO_ECTG_BASE(16,%r14),__LC_EXIT_TIMER
 	lmg	%r11,%r15,__PT_R11(%r11)
@@ -623,6 +624,7 @@ ENTRY(io_int_handler)
 	lg	%r14,__LC_VDSO_PER_CPU
 	lmg	%r0,%r10,__PT_R0(%r11)
 	mvc	__LC_RETURN_PSW(16),__PT_PSW(%r11)
+.Lio_exit_timer:
 	stpt	__LC_EXIT_TIMER
 	mvc	__VDSO_ECTG_BASE(16,%r14),__LC_EXIT_TIMER
 	lmg	%r11,%r15,__PT_R11(%r11)
@@ -1174,15 +1176,23 @@ cleanup_critical:
 	br	%r14
 
 .Lcleanup_sysc_restore:
+	# check if stpt has been executed
 	clg	%r9,BASED(.Lcleanup_sysc_restore_insn)
+	jh	0f
+	mvc	__LC_EXIT_TIMER(8),__LC_ASYNC_ENTER_TIMER
+	cghi	%r11,__LC_SAVE_AREA_ASYNC
 	je	0f
+	mvc	__LC_EXIT_TIMER(8),__LC_MCCK_ENTER_TIMER
+0:	clg	%r9,BASED(.Lcleanup_sysc_restore_insn+8)
+	je	1f
 	lg	%r9,24(%r11)		# get saved pointer to pt_regs
 	mvc	__LC_RETURN_PSW(16),__PT_PSW(%r9)
 	mvc	0(64,%r11),__PT_R8(%r9)
 	lmg	%r0,%r7,__PT_R0(%r9)
-0:	lmg	%r8,%r9,__LC_RETURN_PSW
+1:	lmg	%r8,%r9,__LC_RETURN_PSW
 	br	%r14
 .Lcleanup_sysc_restore_insn:
+	.quad	.Lsysc_exit_timer
 	.quad	.Lsysc_done - 4
 
 .Lcleanup_io_tif:
@@ -1190,15 +1200,20 @@ cleanup_critical:
 	br	%r14
 
 .Lcleanup_io_restore:
+	# check if stpt has been executed
 	clg	%r9,BASED(.Lcleanup_io_restore_insn)
-	je	0f
+	jh	0f
+	mvc	__LC_EXIT_TIMER(8),__LC_MCCK_ENTER_TIMER
+0:	clg	%r9,BASED(.Lcleanup_io_restore_insn+8)
+	je	1f
 	lg	%r9,24(%r11)		# get saved r11 pointer to pt_regs
 	mvc	__LC_RETURN_PSW(16),__PT_PSW(%r9)
 	mvc	0(64,%r11),__PT_R8(%r9)
 	lmg	%r0,%r7,__PT_R0(%r9)
-0:	lmg	%r8,%r9,__LC_RETURN_PSW
+1:	lmg	%r8,%r9,__LC_RETURN_PSW
 	br	%r14
 .Lcleanup_io_restore_insn:
+	.quad	.Lio_exit_timer
 	.quad	.Lio_done - 4
 
 .Lcleanup_idle:

arch/s390/kernel/ftrace.c

@@ -173,6 +173,8 @@ int __init ftrace_dyn_arch_init(void)
 	return 0;
 }
 
+#ifdef CONFIG_MODULES
+
 static int __init ftrace_plt_init(void)
 {
 	unsigned int *ip;
@@ -191,6 +193,8 @@ static int __init ftrace_plt_init(void)
 }
 device_initcall(ftrace_plt_init);
 
+#endif /* CONFIG_MODULES */
+
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
 /*
  * Hook the return address and push it in the stack of return addresses

arch/s390/kernel/vmlinux.lds.S

@@ -31,8 +31,14 @@ SECTIONS
 {
 	. = 0x00000000;
 	.text : {
-	_text = .;		/* Text and read-only data */
+		/* Text and read-only data */
 		HEAD_TEXT
+		/*
+		 * E.g. perf doesn't like symbols starting at address zero,
+		 * therefore skip the initial PSW and channel program located
+		 * at address zero and let _text start at 0x200.
+		 */
+	_text = 0x200;
 		TEXT_TEXT
 		SCHED_TEXT
 		CPUIDLE_TEXT

arch/s390/lib/probes.c

@@ -4,6 +4,7 @@
  *    Copyright IBM Corp. 2014
  */
 
+#include <linux/errno.h>
 #include <asm/kprobes.h>
 #include <asm/dis.h>
 

arch/s390/lib/uaccess.c

@@ -337,8 +337,8 @@ long __strncpy_from_user(char *dst, const char __user *src, long size)
 		return 0;
 	done = 0;
 	do {
-		offset = (size_t)src & ~PAGE_MASK;
+		offset = (size_t)src & (L1_CACHE_BYTES - 1);
-		len = min(size - done, PAGE_SIZE - offset);
+		len = min(size - done, L1_CACHE_BYTES - offset);
 		if (copy_from_user(dst, src, len))
 			return -EFAULT;
 		len_str = strnlen(dst, len);

arch/sparc/include/asm/hugetlb.h

@@ -24,9 +24,11 @@ static inline int is_hugepage_only_range(struct mm_struct *mm,
 static inline int prepare_hugepage_range(struct file *file,
 			unsigned long addr, unsigned long len)
 {
-	if (len & ~HPAGE_MASK)
+	struct hstate *h = hstate_file(file);
+
+	if (len & ~huge_page_mask(h))
 		return -EINVAL;
-	if (addr & ~HPAGE_MASK)
+	if (addr & ~huge_page_mask(h))
 		return -EINVAL;
 	return 0;
 }

arch/sparc/include/asm/pgtable_32.h

@@ -91,9 +91,9 @@ extern unsigned long pfn_base;
  * ZERO_PAGE is a global shared page that is always zero: used
  * for zero-mapped memory areas etc..
  */
-extern unsigned long empty_zero_page;
+extern unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)];
 
-#define ZERO_PAGE(vaddr) (virt_to_page(&empty_zero_page))
+#define ZERO_PAGE(vaddr) (virt_to_page(empty_zero_page))
 
 /*
  * In general all page table modifications should use the V8 atomic

arch/sparc/include/asm/setup.h

@@ -16,7 +16,7 @@ extern char reboot_command[];
  */
 extern unsigned char boot_cpu_id;
 
-extern unsigned long empty_zero_page;
+extern unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)];
 
 extern int serial_console;
 static inline int con_is_present(void)

arch/sparc/kernel/ftrace.c

@@ -130,18 +130,17 @@ unsigned long prepare_ftrace_return(unsigned long parent,
 	if (unlikely(atomic_read(&current->tracing_graph_pause)))
 		return parent + 8UL;
 
+	trace.func = self_addr;
+	trace.depth = current->curr_ret_stack + 1;
+
+	/* Only trace if the calling function expects to */
+	if (!ftrace_graph_entry(&trace))
+		return parent + 8UL;
+
 	if (ftrace_push_return_trace(parent, self_addr, &trace.depth,
 				     frame_pointer, NULL) == -EBUSY)
 		return parent + 8UL;
 
-	trace.func = self_addr;
-
-	/* Only trace if the calling function expects to */
-	if (!ftrace_graph_entry(&trace)) {
-		current->curr_ret_stack--;
-		return parent + 8UL;
-	}
-
 	return return_hooker;
 }
 #endif /* CONFIG_FUNCTION_GRAPH_TRACER */

arch/sparc/mm/init_32.c

@@ -290,7 +290,7 @@ void __init mem_init(void)
 
 
 	/* Saves us work later. */
-	memset((void *)&empty_zero_page, 0, PAGE_SIZE);
+	memset((void *)empty_zero_page, 0, PAGE_SIZE);
 
 	i = last_valid_pfn >> ((20 - PAGE_SHIFT) + 5);
 	i += 1;

drivers/edac/amd64_edac.c

@@ -782,24 +782,26 @@ static void debug_dump_dramcfg_low(struct amd64_pvt *pvt, u32 dclr, int chan)
 
 static void debug_display_dimm_sizes_df(struct amd64_pvt *pvt, u8 ctrl)
 {
-	u32 *dcsb = ctrl ? pvt->csels[1].csbases : pvt->csels[0].csbases;
+	int dimm, size0, size1, cs0, cs1;
-	int dimm, size0, size1;
 
 	edac_printk(KERN_DEBUG, EDAC_MC, "UMC%d chip selects:\n", ctrl);
 
 	for (dimm = 0; dimm < 4; dimm++) {
 		size0 = 0;
+		cs0 = dimm * 2;
 
-		if (dcsb[dimm*2] & DCSB_CS_ENABLE)
+		if (csrow_enabled(cs0, ctrl, pvt))
-			size0 = pvt->ops->dbam_to_cs(pvt, ctrl, 0, dimm);
+			size0 = pvt->ops->dbam_to_cs(pvt, ctrl, 0, cs0);
 
 		size1 = 0;
-		if (dcsb[dimm*2 + 1] & DCSB_CS_ENABLE)
+		cs1 = dimm * 2 + 1;
-			size1 = pvt->ops->dbam_to_cs(pvt, ctrl, 0, dimm);
+
+		if (csrow_enabled(cs1, ctrl, pvt))
+			size1 = pvt->ops->dbam_to_cs(pvt, ctrl, 0, cs1);
 
 		amd64_info(EDAC_MC ": %d: %5dMB %d: %5dMB\n",
-				dimm * 2,     size0,
+				cs0,	size0,
-				dimm * 2 + 1, size1);
+				cs1,	size1);
 	}
 }
 
@@ -2756,26 +2758,22 @@ skip:
  *	encompasses
  *
  */
-static u32 get_csrow_nr_pages(struct amd64_pvt *pvt, u8 dct, int csrow_nr)
+static u32 get_csrow_nr_pages(struct amd64_pvt *pvt, u8 dct, int csrow_nr_orig)
 {
-	u32 cs_mode, nr_pages;
 	u32 dbam = dct ? pvt->dbam1 : pvt->dbam0;
+	int csrow_nr = csrow_nr_orig;
+	u32 cs_mode, nr_pages;
 
+	if (!pvt->umc)
+		csrow_nr >>= 1;
 
-	/*
+	cs_mode = DBAM_DIMM(csrow_nr, dbam);
-	 * The math on this doesn't look right on the surface because x/2*4 can
-	 * be simplified to x*2 but this expression makes use of the fact that
-	 * it is integral math where 1/2=0. This intermediate value becomes the
-	 * number of bits to shift the DBAM register to extract the proper CSROW
-	 * field.
-	 */
-	cs_mode = DBAM_DIMM(csrow_nr / 2, dbam);
 
-	nr_pages = pvt->ops->dbam_to_cs(pvt, dct, cs_mode, (csrow_nr / 2))
+	nr_pages   = pvt->ops->dbam_to_cs(pvt, dct, cs_mode, csrow_nr);
-							   << (20 - PAGE_SHIFT);
+	nr_pages <<= 20 - PAGE_SHIFT;
 
 	edac_dbg(0, "csrow: %d, channel: %d, DBAM idx: %d\n",
-		    csrow_nr, dct,  cs_mode);
+		    csrow_nr_orig, dct,  cs_mode);
 	edac_dbg(0, "nr_pages/channel: %u\n", nr_pages);
 
 	return nr_pages;

drivers/firmware/efi/efi-pstore.c

@@ -155,19 +155,14 @@ static int efi_pstore_scan_sysfs_exit(struct efivar_entry *pos,
  * efi_pstore_sysfs_entry_iter
  *
  * @record: pstore record to pass to callback
- * @pos: entry to begin iterating from
  *
  * You MUST call efivar_enter_iter_begin() before this function, and
  * efivar_entry_iter_end() afterwards.
  *
- * It is possible to begin iteration from an arbitrary entry within
- * the list by passing @pos. @pos is updated on return to point to
- * the next entry of the last one passed to efi_pstore_read_func().
- * To begin iterating from the beginning of the list @pos must be %NULL.
  */
-static int efi_pstore_sysfs_entry_iter(struct pstore_record *record,
+static int efi_pstore_sysfs_entry_iter(struct pstore_record *record)
-				       struct efivar_entry **pos)
 {
+	struct efivar_entry **pos = (struct efivar_entry **)&record->psi->data;
 	struct efivar_entry *entry, *n;
 	struct list_head *head = &efivar_sysfs_list;
 	int size = 0;
@@ -218,7 +213,6 @@ static int efi_pstore_sysfs_entry_iter(struct pstore_record *record,
  */
 static ssize_t efi_pstore_read(struct pstore_record *record)
 {
-	struct efivar_entry *entry = (struct efivar_entry *)record->psi->data;
 	ssize_t size;
 
 	record->buf = kzalloc(EFIVARS_DATA_SIZE_MAX, GFP_KERNEL);
@@ -229,7 +223,7 @@ static ssize_t efi_pstore_read(struct pstore_record *record)
 		size = -EINTR;
 		goto out;
 	}
-	size = efi_pstore_sysfs_entry_iter(record, &entry);
+	size = efi_pstore_sysfs_entry_iter(record);
 	efivar_entry_iter_end();
 
 out:

drivers/hwmon/coretemp.c

@@ -604,6 +604,13 @@ static int coretemp_cpu_online(unsigned int cpu)
 	struct cpuinfo_x86 *c = &cpu_data(cpu);
 	struct platform_data *pdata;
 
+	/*
+	 * Don't execute this on resume as the offline callback did
+	 * not get executed on suspend.
+	 */
+	if (cpuhp_tasks_frozen)
+		return 0;
+
 	/*
 	 * CPUID.06H.EAX[0] indicates whether the CPU has thermal
 	 * sensors. We check this bit only, all the early CPUs
@@ -654,6 +661,13 @@ static int coretemp_cpu_offline(unsigned int cpu)
 	struct temp_data *tdata;
 	int indx, target;
 
+	/*
+	 * Don't execute this on suspend as the device remove locks
+	 * up the machine.
+	 */
+	if (cpuhp_tasks_frozen)
+		return 0;
+
 	/* If the physical CPU device does not exist, just return */
 	if (!pdev)
 		return 0;

drivers/i2c/busses/i2c-mv64xxx.c

@@ -819,7 +819,6 @@ mv64xxx_of_config(struct mv64xxx_i2c_data *drv_data,
 		rc = -EINVAL;
 		goto out;
 	}
-	drv_data->irq = irq_of_parse_and_map(np, 0);
 
 	drv_data->rstc = devm_reset_control_get_optional(dev, NULL);
 	if (IS_ERR(drv_data->rstc)) {
@@ -902,10 +901,11 @@ mv64xxx_i2c_probe(struct platform_device *pd)
 	if (!IS_ERR(drv_data->clk))
 		clk_prepare_enable(drv_data->clk);
 
+	drv_data->irq = platform_get_irq(pd, 0);
+
 	if (pdata) {
 		drv_data->freq_m = pdata->freq_m;
 		drv_data->freq_n = pdata->freq_n;
-		drv_data->irq = platform_get_irq(pd, 0);
 		drv_data->adapter.timeout = msecs_to_jiffies(pdata->timeout);
 		drv_data->offload_enabled = false;
 		memcpy(&drv_data->reg_offsets, &mv64xxx_i2c_regs_mv64xxx, sizeof(drv_data->reg_offsets));
@@ -915,7 +915,7 @@ mv64xxx_i2c_probe(struct platform_device *pd)
 			goto exit_clk;
 	}
 	if (drv_data->irq < 0) {
-		rc = -ENXIO;
+		rc = drv_data->irq;
 		goto exit_reset;
 	}
 

drivers/i2c/busses/i2c-xgene-slimpro.c

@@ -416,6 +416,7 @@ static int xgene_slimpro_i2c_probe(struct platform_device *pdev)
 	adapter->class = I2C_CLASS_HWMON;
 	adapter->dev.parent = &pdev->dev;
 	adapter->dev.of_node = pdev->dev.of_node;
+	ACPI_COMPANION_SET(&adapter->dev, ACPI_COMPANION(&pdev->dev));
 	i2c_set_adapdata(adapter, ctx);
 	rc = i2c_add_adapter(adapter);
 	if (rc) {

drivers/i2c/i2c-mux.c

@@ -395,18 +395,20 @@ int i2c_mux_add_adapter(struct i2c_mux_core *muxc,
 	if (force_nr) {
 		priv->adap.nr = force_nr;
 		ret = i2c_add_numbered_adapter(&priv->adap);
-		dev_err(&parent->dev,
+		if (ret < 0) {
-			"failed to add mux-adapter %u as bus %u (error=%d)\n",
+			dev_err(&parent->dev,
-			chan_id, force_nr, ret);
+				"failed to add mux-adapter %u as bus %u (error=%d)\n",
+				chan_id, force_nr, ret);
+			goto err_free_priv;
+		}
 	} else {
 		ret = i2c_add_adapter(&priv->adap);
-		dev_err(&parent->dev,
+		if (ret < 0) {
-			"failed to add mux-adapter %u (error=%d)\n",
+			dev_err(&parent->dev,
-			chan_id, ret);
+				"failed to add mux-adapter %u (error=%d)\n",
-	}
+				chan_id, ret);
-	if (ret < 0) {
+			goto err_free_priv;
-		kfree(priv);
+		}
-		return ret;
 	}
 
 	WARN(sysfs_create_link(&priv->adap.dev.kobj, &muxc->dev->kobj,
@@ -422,6 +424,10 @@ int i2c_mux_add_adapter(struct i2c_mux_core *muxc,
 
 	muxc->adapter[muxc->num_adapters++] = &priv->adap;
 	return 0;
+
+err_free_priv:
+	kfree(priv);
+	return ret;
 }
 EXPORT_SYMBOL_GPL(i2c_mux_add_adapter);
 

drivers/i2c/muxes/i2c-mux-reg.c

@@ -196,20 +196,25 @@ static int i2c_mux_reg_probe(struct platform_device *pdev)
 		res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 		mux->data.reg_size = resource_size(res);
 		mux->data.reg = devm_ioremap_resource(&pdev->dev, res);
-		if (IS_ERR(mux->data.reg))
+		if (IS_ERR(mux->data.reg)) {
-			return PTR_ERR(mux->data.reg);
+			ret = PTR_ERR(mux->data.reg);
+			goto err_put_parent;
+		}
 	}
 
 	if (mux->data.reg_size != 4 && mux->data.reg_size != 2 &&
 	    mux->data.reg_size != 1) {
 		dev_err(&pdev->dev, "Invalid register size\n");
-		return -EINVAL;
+		ret = -EINVAL;
+		goto err_put_parent;
 	}
 
 	muxc = i2c_mux_alloc(parent, &pdev->dev, mux->data.n_values, 0, 0,
 			     i2c_mux_reg_select, NULL);
-	if (!muxc)
+	if (!muxc) {
-		return -ENOMEM;
+		ret = -ENOMEM;
+		goto err_put_parent;
+	}
 	muxc->priv = mux;
 
 	platform_set_drvdata(pdev, muxc);
@@ -223,7 +228,7 @@ static int i2c_mux_reg_probe(struct platform_device *pdev)
 
 		ret = i2c_mux_add_adapter(muxc, nr, mux->data.values[i], class);
 		if (ret)
-			goto add_adapter_failed;
+			goto err_del_mux_adapters;
 	}
 
 	dev_dbg(&pdev->dev, "%d port mux on %s adapter\n",
@@ -231,8 +236,10 @@ static int i2c_mux_reg_probe(struct platform_device *pdev)
 
 	return 0;
 
-add_adapter_failed:
+err_del_mux_adapters:
 	i2c_mux_del_adapters(muxc);
+err_put_parent:
+	i2c_put_adapter(parent);
 
 	return ret;
 }

drivers/md/dm-bufio.c

@@ -218,7 +218,7 @@ static DEFINE_SPINLOCK(param_spinlock);
  * Buffers are freed after this timeout
  */
 static unsigned dm_bufio_max_age = DM_BUFIO_DEFAULT_AGE_SECS;
-static unsigned dm_bufio_retain_bytes = DM_BUFIO_DEFAULT_RETAIN_BYTES;
+static unsigned long dm_bufio_retain_bytes = DM_BUFIO_DEFAULT_RETAIN_BYTES;
 
 static unsigned long dm_bufio_peak_allocated;
 static unsigned long dm_bufio_allocated_kmem_cache;
@@ -1558,10 +1558,10 @@ static bool __try_evict_buffer(struct dm_buffer *b, gfp_t gfp)
 	return true;
 }
 
-static unsigned get_retain_buffers(struct dm_bufio_client *c)
+static unsigned long get_retain_buffers(struct dm_bufio_client *c)
 {
-        unsigned retain_bytes = ACCESS_ONCE(dm_bufio_retain_bytes);
+        unsigned long retain_bytes = ACCESS_ONCE(dm_bufio_retain_bytes);
-        return retain_bytes / c->block_size;
+        return retain_bytes >> (c->sectors_per_block_bits + SECTOR_SHIFT);
 }
 
 static unsigned long __scan(struct dm_bufio_client *c, unsigned long nr_to_scan,
@@ -1571,7 +1571,7 @@ static unsigned long __scan(struct dm_bufio_client *c, unsigned long nr_to_scan,
 	struct dm_buffer *b, *tmp;
 	unsigned long freed = 0;
 	unsigned long count = nr_to_scan;
-	unsigned retain_target = get_retain_buffers(c);
+	unsigned long retain_target = get_retain_buffers(c);
 
 	for (l = 0; l < LIST_SIZE; l++) {
 		list_for_each_entry_safe_reverse(b, tmp, &c->lru[l], lru_list) {
@@ -1794,8 +1794,8 @@ static bool older_than(struct dm_buffer *b, unsigned long age_hz)
 static void __evict_old_buffers(struct dm_bufio_client *c, unsigned long age_hz)
 {
 	struct dm_buffer *b, *tmp;
-	unsigned retain_target = get_retain_buffers(c);
+	unsigned long retain_target = get_retain_buffers(c);
-	unsigned count;
+	unsigned long count;
 	LIST_HEAD(write_list);
 
 	dm_bufio_lock(c);
@@ -1955,7 +1955,7 @@ MODULE_PARM_DESC(max_cache_size_bytes, "Size of metadata cache");
 module_param_named(max_age_seconds, dm_bufio_max_age, uint, S_IRUGO | S_IWUSR);
 MODULE_PARM_DESC(max_age_seconds, "Max age of a buffer in seconds");
 
-module_param_named(retain_bytes, dm_bufio_retain_bytes, uint, S_IRUGO | S_IWUSR);
+module_param_named(retain_bytes, dm_bufio_retain_bytes, ulong, S_IRUGO | S_IWUSR);
 MODULE_PARM_DESC(retain_bytes, "Try to keep at least this many bytes cached in memory");
 
 module_param_named(peak_allocated_bytes, dm_bufio_peak_allocated, ulong, S_IRUGO | S_IWUSR);

drivers/md/dm-cache-background-tracker.c

@@ -33,6 +33,11 @@ struct background_tracker *btracker_create(unsigned max_work)
 {
 	struct background_tracker *b = kmalloc(sizeof(*b), GFP_KERNEL);
 
+	if (!b) {
+		DMERR("couldn't create background_tracker");
+		return NULL;
+	}
+
 	b->max_work = max_work;
 	atomic_set(&b->pending_promotes, 0);
 	atomic_set(&b->pending_writebacks, 0);

drivers/md/dm-cache-policy-smq.c

@@ -1120,8 +1120,6 @@ static bool clean_target_met(struct smq_policy *mq, bool idle)
 	 * Cache entries may not be populated.  So we cannot rely on the
 	 * size of the clean queue.
 	 */
-	unsigned nr_clean;
-
 	if (idle) {
 		/*
 		 * We'd like to clean everything.
@@ -1129,18 +1127,16 @@ static bool clean_target_met(struct smq_policy *mq, bool idle)
 		return q_size(&mq->dirty) == 0u;
 	}
 
-	nr_clean = from_cblock(mq->cache_size) - q_size(&mq->dirty);
+	/*
-	return (nr_clean + btracker_nr_writebacks_queued(mq->bg_work)) >=
+	 * If we're busy we don't worry about cleaning at all.
-		percent_to_target(mq, CLEAN_TARGET);
+	 */
+	return true;
 }
 
-static bool free_target_met(struct smq_policy *mq, bool idle)
+static bool free_target_met(struct smq_policy *mq)
 {
 	unsigned nr_free;
 
-	if (!idle)
-		return true;
-
 	nr_free = from_cblock(mq->cache_size) - mq->cache_alloc.nr_allocated;
 	return (nr_free + btracker_nr_demotions_queued(mq->bg_work)) >=
 		percent_to_target(mq, FREE_TARGET);
@@ -1190,9 +1186,9 @@ static void queue_demotion(struct smq_policy *mq)
 	if (unlikely(WARN_ON_ONCE(!mq->migrations_allowed)))
 		return;
 
-	e = q_peek(&mq->clean, mq->clean.nr_levels, true);
+	e = q_peek(&mq->clean, mq->clean.nr_levels / 2, true);
 	if (!e) {
-		if (!clean_target_met(mq, false))
+		if (!clean_target_met(mq, true))
 			queue_writeback(mq);
 		return;
 	}
@@ -1220,7 +1216,7 @@ static void queue_promotion(struct smq_policy *mq, dm_oblock_t oblock,
 		 * We always claim to be 'idle' to ensure some demotions happen
 		 * with continuous loads.
 		 */
-		if (!free_target_met(mq, true))
+		if (!free_target_met(mq))
 			queue_demotion(mq);
 		return;
 	}
@@ -1421,14 +1417,10 @@ static int smq_get_background_work(struct dm_cache_policy *p, bool idle,
 	spin_lock_irqsave(&mq->lock, flags);
 	r = btracker_issue(mq->bg_work, result);
 	if (r == -ENODATA) {
-		/* find some writeback work to do */
+		if (!clean_target_met(mq, idle)) {
-		if (mq->migrations_allowed && !free_target_met(mq, idle))
-			queue_demotion(mq);
-
-		else if (!clean_target_met(mq, idle))
 			queue_writeback(mq);
-
+			r = btracker_issue(mq->bg_work, result);
-		r = btracker_issue(mq->bg_work, result);
+		}
 	}
 	spin_unlock_irqrestore(&mq->lock, flags);
 
@@ -1452,6 +1444,7 @@ static void __complete_background_work(struct smq_policy *mq,
 		clear_pending(mq, e);
 		if (success) {
 			e->oblock = work->oblock;
+			e->level = NR_CACHE_LEVELS - 1;
 			push(mq, e);
 			// h, q, a
 		} else {

drivers/md/dm-cache-target.c

@@ -94,6 +94,9 @@ static void iot_io_begin(struct io_tracker *iot, sector_t len)
 
 static void __iot_io_end(struct io_tracker *iot, sector_t len)
 {
+	if (!len)
+		return;
+
 	iot->in_flight -= len;
 	if (!iot->in_flight)
 		iot->idle_time = jiffies;
@@ -474,7 +477,7 @@ struct cache {
 	spinlock_t invalidation_lock;
 	struct list_head invalidation_requests;
 
-	struct io_tracker origin_tracker;
+	struct io_tracker tracker;
 
 	struct work_struct commit_ws;
 	struct batcher committer;
@@ -901,8 +904,7 @@ static dm_oblock_t get_bio_block(struct cache *cache, struct bio *bio)
 
 static bool accountable_bio(struct cache *cache, struct bio *bio)
 {
-	return ((bio->bi_bdev == cache->origin_dev->bdev) &&
+	return bio_op(bio) != REQ_OP_DISCARD;
-		bio_op(bio) != REQ_OP_DISCARD);
 }
 
 static void accounted_begin(struct cache *cache, struct bio *bio)
@@ -912,7 +914,7 @@ static void accounted_begin(struct cache *cache, struct bio *bio)
 
 	if (accountable_bio(cache, bio)) {
 		pb->len = bio_sectors(bio);
-		iot_io_begin(&cache->origin_tracker, pb->len);
+		iot_io_begin(&cache->tracker, pb->len);
 	}
 }
 
@@ -921,7 +923,7 @@ static void accounted_complete(struct cache *cache, struct bio *bio)
 	size_t pb_data_size = get_per_bio_data_size(cache);
 	struct per_bio_data *pb = get_per_bio_data(bio, pb_data_size);
 
-	iot_io_end(&cache->origin_tracker, pb->len);
+	iot_io_end(&cache->tracker, pb->len);
 }
 
 static void accounted_request(struct cache *cache, struct bio *bio)
@@ -1716,20 +1718,19 @@ static int invalidate_start(struct cache *cache, dm_cblock_t cblock,
 
 enum busy {
 	IDLE,
-	MODERATE,
 	BUSY
 };
 
 static enum busy spare_migration_bandwidth(struct cache *cache)
 {
-	bool idle = iot_idle_for(&cache->origin_tracker, HZ);
+	bool idle = iot_idle_for(&cache->tracker, HZ);
 	sector_t current_volume = (atomic_read(&cache->nr_io_migrations) + 1) *
 		cache->sectors_per_block;
 
-	if (current_volume <= cache->migration_threshold)
+	if (idle && current_volume <= cache->migration_threshold)
-		return idle ? IDLE : MODERATE;
+		return IDLE;
 	else
-		return idle ? MODERATE : BUSY;
+		return BUSY;
 }
 
 static void inc_hit_counter(struct cache *cache, struct bio *bio)
@@ -2045,8 +2046,6 @@ static void check_migrations(struct work_struct *ws)
 
 	for (;;) {
 		b = spare_migration_bandwidth(cache);
-		if (b == BUSY)
-			break;
 
 		r = policy_get_background_work(cache->policy, b == IDLE, &op);
 		if (r == -ENODATA)
@@ -2717,7 +2716,7 @@ static int cache_create(struct cache_args *ca, struct cache **result)
 
 	batcher_init(&cache->committer, commit_op, cache,
 		     issue_op, cache, cache->wq);
-	iot_init(&cache->origin_tracker);
+	iot_init(&cache->tracker);
 
 	init_rwsem(&cache->background_work_lock);
 	prevent_background_work(cache);
@@ -2941,7 +2940,7 @@ static void cache_postsuspend(struct dm_target *ti)
 
 	cancel_delayed_work(&cache->waker);
 	flush_workqueue(cache->wq);
-	WARN_ON(cache->origin_tracker.in_flight);
+	WARN_ON(cache->tracker.in_flight);
 
 	/*
 	 * If it's a flush suspend there won't be any deferred bios, so this

drivers/md/dm-mpath.c

@@ -447,7 +447,7 @@ failed:
  * it has been invoked.
  */
 #define dm_report_EIO(m)						\
-({									\
+do {									\
 	struct mapped_device *md = dm_table_get_md((m)->ti->table);	\
 									\
 	pr_debug("%s: returning EIO; QIFNP = %d; SQIFNP = %d; DNFS = %d\n", \
@@ -455,8 +455,7 @@ failed:
 		 test_bit(MPATHF_QUEUE_IF_NO_PATH, &(m)->flags),	\
 		 test_bit(MPATHF_SAVED_QUEUE_IF_NO_PATH, &(m)->flags),	\
 		 dm_noflush_suspending((m)->ti));			\
-	-EIO;								\
+} while (0)
-})
 
 /*
  * Map cloned requests (request-based multipath)
@@ -481,7 +480,8 @@ static int multipath_clone_and_map(struct dm_target *ti, struct request *rq,
 	if (!pgpath) {
 		if (test_bit(MPATHF_QUEUE_IF_NO_PATH, &m->flags))
 			return DM_MAPIO_DELAY_REQUEUE;
-		return dm_report_EIO(m);	/* Failed */
+		dm_report_EIO(m);	/* Failed */
+		return DM_MAPIO_KILL;
 	} else if (test_bit(MPATHF_QUEUE_IO, &m->flags) ||
 		   test_bit(MPATHF_PG_INIT_REQUIRED, &m->flags)) {
 		if (pg_init_all_paths(m))
@@ -558,7 +558,8 @@ static int __multipath_map_bio(struct multipath *m, struct bio *bio, struct dm_m
 	if (!pgpath) {
 		if (test_bit(MPATHF_QUEUE_IF_NO_PATH, &m->flags))
 			return DM_MAPIO_REQUEUE;
-		return dm_report_EIO(m);
+		dm_report_EIO(m);
+		return -EIO;
 	}
 
 	mpio->pgpath = pgpath;
@@ -1493,7 +1494,7 @@ static int multipath_end_io(struct dm_target *ti, struct request *clone,
 		if (atomic_read(&m->nr_valid_paths) == 0 &&
 		    !test_bit(MPATHF_QUEUE_IF_NO_PATH, &m->flags)) {
 			if (error == -EIO)
-				error = dm_report_EIO(m);
+				dm_report_EIO(m);
 			/* complete with the original error */
 			r = DM_ENDIO_DONE;
 		}
@@ -1524,8 +1525,10 @@ static int do_end_io_bio(struct multipath *m, struct bio *clone,
 		fail_path(mpio->pgpath);
 
 	if (atomic_read(&m->nr_valid_paths) == 0 &&
-	    !test_bit(MPATHF_QUEUE_IF_NO_PATH, &m->flags))
+	    !test_bit(MPATHF_QUEUE_IF_NO_PATH, &m->flags)) {
-		return dm_report_EIO(m);
+		dm_report_EIO(m);
+		return -EIO;
+	}
 
 	/* Queue for the daemon to resubmit */
 	dm_bio_restore(get_bio_details_from_bio(clone), clone);

drivers/md/dm-rq.c

@@ -507,6 +507,7 @@ static int map_request(struct dm_rq_target_io *tio)
 	case DM_MAPIO_KILL:
 		/* The target wants to complete the I/O */
 		dm_kill_unmapped_request(rq, -EIO);
+		break;
 	default:
 		DMWARN("unimplemented target map return value: %d", r);
 		BUG();

drivers/md/dm-thin-metadata.c

@@ -484,11 +484,11 @@ static int __write_initial_superblock(struct dm_pool_metadata *pmd)
 	if (r < 0)
 		return r;
 
-	r = save_sm_roots(pmd);
+	r = dm_tm_pre_commit(pmd->tm);
 	if (r < 0)
 		return r;
 
-	r = dm_tm_pre_commit(pmd->tm);
+	r = save_sm_roots(pmd);
 	if (r < 0)
 		return r;
 

drivers/md/md.c

@@ -8022,18 +8022,15 @@ EXPORT_SYMBOL(md_write_end);
  * may proceed without blocking.  It is important to call this before
  * attempting a GFP_KERNEL allocation while holding the mddev lock.
  * Must be called with mddev_lock held.
- *
- * In the ->external case MD_SB_CHANGE_PENDING can not be cleared until mddev->lock
- * is dropped, so return -EAGAIN after notifying userspace.
  */
-int md_allow_write(struct mddev *mddev)
+void md_allow_write(struct mddev *mddev)
 {
 	if (!mddev->pers)
-		return 0;
+		return;
 	if (mddev->ro)
-		return 0;
+		return;
 	if (!mddev->pers->sync_request)
-		return 0;
+		return;
 
 	spin_lock(&mddev->lock);
 	if (mddev->in_sync) {
@@ -8046,13 +8043,12 @@ int md_allow_write(struct mddev *mddev)
 		spin_unlock(&mddev->lock);
 		md_update_sb(mddev, 0);
 		sysfs_notify_dirent_safe(mddev->sysfs_state);
+		/* wait for the dirty state to be recorded in the metadata */
+		wait_event(mddev->sb_wait,
+			   !test_bit(MD_SB_CHANGE_CLEAN, &mddev->sb_flags) &&
+			   !test_bit(MD_SB_CHANGE_PENDING, &mddev->sb_flags));
 	} else
 		spin_unlock(&mddev->lock);
-
-	if (test_bit(MD_SB_CHANGE_PENDING, &mddev->sb_flags))
-		return -EAGAIN;
-	else
-		return 0;
 }
 EXPORT_SYMBOL_GPL(md_allow_write);
 

drivers/md/md.h

@@ -665,7 +665,7 @@ extern int sync_page_io(struct md_rdev *rdev, sector_t sector, int size,
 			bool metadata_op);
 extern void md_do_sync(struct md_thread *thread);
 extern void md_new_event(struct mddev *mddev);
-extern int md_allow_write(struct mddev *mddev);
+extern void md_allow_write(struct mddev *mddev);
 extern void md_wait_for_blocked_rdev(struct md_rdev *rdev, struct mddev *mddev);
 extern void md_set_array_sectors(struct mddev *mddev, sector_t array_sectors);
 extern int md_check_no_bitmap(struct mddev *mddev);

drivers/md/persistent-data/dm-space-map-disk.c

@@ -142,10 +142,23 @@ static int sm_disk_inc_block(struct dm_space_map *sm, dm_block_t b)
 
 static int sm_disk_dec_block(struct dm_space_map *sm, dm_block_t b)
 {
+	int r;
+	uint32_t old_count;
 	enum allocation_event ev;
 	struct sm_disk *smd = container_of(sm, struct sm_disk, sm);
 
-	return sm_ll_dec(&smd->ll, b, &ev);
+	r = sm_ll_dec(&smd->ll, b, &ev);
+	if (!r && (ev == SM_FREE)) {
+		/*
+		 * It's only free if it's also free in the last
+		 * transaction.
+		 */
+		r = sm_ll_lookup(&smd->old_ll, b, &old_count);
+		if (!r && !old_count)
+			smd->nr_allocated_this_transaction--;
+	}
+
+	return r;
 }
 
 static int sm_disk_new_block(struct dm_space_map *sm, dm_block_t *b)

drivers/md/raid0.c

@@ -385,7 +385,7 @@ static int raid0_run(struct mddev *mddev)
 		blk_queue_max_hw_sectors(mddev->queue, mddev->chunk_sectors);
 		blk_queue_max_write_same_sectors(mddev->queue, mddev->chunk_sectors);
 		blk_queue_max_write_zeroes_sectors(mddev->queue, mddev->chunk_sectors);
-		blk_queue_max_discard_sectors(mddev->queue, mddev->chunk_sectors);
+		blk_queue_max_discard_sectors(mddev->queue, UINT_MAX);
 
 		blk_queue_io_min(mddev->queue, mddev->chunk_sectors << 9);
 		blk_queue_io_opt(mddev->queue,
@@ -459,6 +459,95 @@ static inline int is_io_in_chunk_boundary(struct mddev *mddev,
 	}
 }
 
+static void raid0_handle_discard(struct mddev *mddev, struct bio *bio)
+{
+	struct r0conf *conf = mddev->private;
+	struct strip_zone *zone;
+	sector_t start = bio->bi_iter.bi_sector;
+	sector_t end;
+	unsigned int stripe_size;
+	sector_t first_stripe_index, last_stripe_index;
+	sector_t start_disk_offset;
+	unsigned int start_disk_index;
+	sector_t end_disk_offset;
+	unsigned int end_disk_index;
+	unsigned int disk;
+
+	zone = find_zone(conf, &start);
+
+	if (bio_end_sector(bio) > zone->zone_end) {
+		struct bio *split = bio_split(bio,
+			zone->zone_end - bio->bi_iter.bi_sector, GFP_NOIO,
+			mddev->bio_set);
+		bio_chain(split, bio);
+		generic_make_request(bio);
+		bio = split;
+		end = zone->zone_end;
+	} else
+		end = bio_end_sector(bio);
+
+	if (zone != conf->strip_zone)
+		end = end - zone[-1].zone_end;
+
+	/* Now start and end is the offset in zone */
+	stripe_size = zone->nb_dev * mddev->chunk_sectors;
+
+	first_stripe_index = start;
+	sector_div(first_stripe_index, stripe_size);
+	last_stripe_index = end;
+	sector_div(last_stripe_index, stripe_size);
+
+	start_disk_index = (int)(start - first_stripe_index * stripe_size) /
+		mddev->chunk_sectors;
+	start_disk_offset = ((int)(start - first_stripe_index * stripe_size) %
+		mddev->chunk_sectors) +
+		first_stripe_index * mddev->chunk_sectors;
+	end_disk_index = (int)(end - last_stripe_index * stripe_size) /
+		mddev->chunk_sectors;
+	end_disk_offset = ((int)(end - last_stripe_index * stripe_size) %
+		mddev->chunk_sectors) +
+		last_stripe_index * mddev->chunk_sectors;
+
+	for (disk = 0; disk < zone->nb_dev; disk++) {
+		sector_t dev_start, dev_end;
+		struct bio *discard_bio = NULL;
+		struct md_rdev *rdev;
+
+		if (disk < start_disk_index)
+			dev_start = (first_stripe_index + 1) *
+				mddev->chunk_sectors;
+		else if (disk > start_disk_index)
+			dev_start = first_stripe_index * mddev->chunk_sectors;
+		else
+			dev_start = start_disk_offset;
+
+		if (disk < end_disk_index)
+			dev_end = (last_stripe_index + 1) * mddev->chunk_sectors;
+		else if (disk > end_disk_index)
+			dev_end = last_stripe_index * mddev->chunk_sectors;
+		else
+			dev_end = end_disk_offset;
+
+		if (dev_end <= dev_start)
+			continue;
+
+		rdev = conf->devlist[(zone - conf->strip_zone) *
+			conf->strip_zone[0].nb_dev + disk];
+		if (__blkdev_issue_discard(rdev->bdev,
+			dev_start + zone->dev_start + rdev->data_offset,
+			dev_end - dev_start, GFP_NOIO, 0, &discard_bio) ||
+		    !discard_bio)
+			continue;
+		bio_chain(discard_bio, bio);
+		if (mddev->gendisk)
+			trace_block_bio_remap(bdev_get_queue(rdev->bdev),
+				discard_bio, disk_devt(mddev->gendisk),
+				bio->bi_iter.bi_sector);
+		generic_make_request(discard_bio);
+	}
+	bio_endio(bio);
+}
+
 static void raid0_make_request(struct mddev *mddev, struct bio *bio)
 {
 	struct strip_zone *zone;
@@ -473,6 +562,11 @@ static void raid0_make_request(struct mddev *mddev, struct bio *bio)
 		return;
 	}
 
+	if (unlikely((bio_op(bio) == REQ_OP_DISCARD))) {
+		raid0_handle_discard(mddev, bio);
+		return;
+	}
+
 	bio_sector = bio->bi_iter.bi_sector;
 	sector = bio_sector;
 	chunk_sects = mddev->chunk_sectors;
@@ -498,19 +592,13 @@ static void raid0_make_request(struct mddev *mddev, struct bio *bio)
 	bio->bi_iter.bi_sector = sector + zone->dev_start +
 		tmp_dev->data_offset;
 
-	if (unlikely((bio_op(bio) == REQ_OP_DISCARD) &&
+	if (mddev->gendisk)
-		     !blk_queue_discard(bdev_get_queue(bio->bi_bdev)))) {
+		trace_block_bio_remap(bdev_get_queue(bio->bi_bdev),
-		/* Just ignore it */
+				      bio, disk_devt(mddev->gendisk),
-		bio_endio(bio);
+				      bio_sector);
-	} else {
+	mddev_check_writesame(mddev, bio);
-		if (mddev->gendisk)
+	mddev_check_write_zeroes(mddev, bio);
-			trace_block_bio_remap(bdev_get_queue(bio->bi_bdev),
+	generic_make_request(bio);
-					      bio, disk_devt(mddev->gendisk),
-					      bio_sector);
-		mddev_check_writesame(mddev, bio);
-		mddev_check_write_zeroes(mddev, bio);
-		generic_make_request(bio);
-	}
 }
 
 static void raid0_status(struct seq_file *seq, struct mddev *mddev)

drivers/md/raid1.c

@@ -666,8 +666,11 @@ static int read_balance(struct r1conf *conf, struct r1bio *r1_bio, int *max_sect
 					break;
 			}
 			continue;
-		} else
+		} else {
+			if ((sectors > best_good_sectors) && (best_disk >= 0))
+				best_disk = -1;
 			best_good_sectors = sectors;
+		}
 
 		if (best_disk >= 0)
 			/* At least two disks to choose from so failfast is OK */
@@ -1529,17 +1532,16 @@ static void raid1_write_request(struct mddev *mddev, struct bio *bio,
 			plug = container_of(cb, struct raid1_plug_cb, cb);
 		else
 			plug = NULL;
-		spin_lock_irqsave(&conf->device_lock, flags);
 		if (plug) {
 			bio_list_add(&plug->pending, mbio);
 			plug->pending_cnt++;
 		} else {
+			spin_lock_irqsave(&conf->device_lock, flags);
 			bio_list_add(&conf->pending_bio_list, mbio);
 			conf->pending_count++;
-		}
+			spin_unlock_irqrestore(&conf->device_lock, flags);
-		spin_unlock_irqrestore(&conf->device_lock, flags);
-		if (!plug)
 			md_wakeup_thread(mddev->thread);
+		}
 	}
 
 	r1_bio_write_done(r1_bio);
@@ -3197,7 +3199,7 @@ static int raid1_reshape(struct mddev *mddev)
 	struct r1conf *conf = mddev->private;
 	int cnt, raid_disks;
 	unsigned long flags;
-	int d, d2, err;
+	int d, d2;
 
 	/* Cannot change chunk_size, layout, or level */
 	if (mddev->chunk_sectors != mddev->new_chunk_sectors ||
@@ -3209,11 +3211,8 @@ static int raid1_reshape(struct mddev *mddev)
 		return -EINVAL;
 	}
 
-	if (!mddev_is_clustered(mddev)) {
+	if (!mddev_is_clustered(mddev))
-		err = md_allow_write(mddev);
+		md_allow_write(mddev);
-		if (err)
-			return err;
-	}
 
 	raid_disks = mddev->raid_disks + mddev->delta_disks;
 

drivers/md/raid10.c

@@ -1282,17 +1282,16 @@ static void raid10_write_one_disk(struct mddev *mddev, struct r10bio *r10_bio,
 		plug = container_of(cb, struct raid10_plug_cb, cb);
 	else
 		plug = NULL;
-	spin_lock_irqsave(&conf->device_lock, flags);
 	if (plug) {
 		bio_list_add(&plug->pending, mbio);
 		plug->pending_cnt++;
 	} else {
+		spin_lock_irqsave(&conf->device_lock, flags);
 		bio_list_add(&conf->pending_bio_list, mbio);
 		conf->pending_count++;
-	}
+		spin_unlock_irqrestore(&conf->device_lock, flags);
-	spin_unlock_irqrestore(&conf->device_lock, flags);
-	if (!plug)
 		md_wakeup_thread(mddev->thread);
+	}
 }
 
 static void raid10_write_request(struct mddev *mddev, struct bio *bio,

drivers/md/raid5-cache.c

@@ -24,6 +24,7 @@
 #include "md.h"
 #include "raid5.h"
 #include "bitmap.h"
+#include "raid5-log.h"
 
 /*
  * metadata/data stored in disk with 4k size unit (a block) regardless
@@ -622,20 +623,30 @@ static void r5l_do_submit_io(struct r5l_log *log, struct r5l_io_unit *io)
 	__r5l_set_io_unit_state(io, IO_UNIT_IO_START);
 	spin_unlock_irqrestore(&log->io_list_lock, flags);
 
+	/*
+	 * In case of journal device failures, submit_bio will get error
+	 * and calls endio, then active stripes will continue write
+	 * process. Therefore, it is not necessary to check Faulty bit
+	 * of journal device here.
+	 *
+	 * We can't check split_bio after current_bio is submitted. If
+	 * io->split_bio is null, after current_bio is submitted, current_bio
+	 * might already be completed and the io_unit is freed. We submit
+	 * split_bio first to avoid the issue.
+	 */
+	if (io->split_bio) {
+		if (io->has_flush)
+			io->split_bio->bi_opf |= REQ_PREFLUSH;
+		if (io->has_fua)
+			io->split_bio->bi_opf |= REQ_FUA;
+		submit_bio(io->split_bio);
+	}
+
 	if (io->has_flush)
 		io->current_bio->bi_opf |= REQ_PREFLUSH;
 	if (io->has_fua)
 		io->current_bio->bi_opf |= REQ_FUA;
 	submit_bio(io->current_bio);
-
-	if (!io->split_bio)
-		return;
-
-	if (io->has_flush)
-		io->split_bio->bi_opf |= REQ_PREFLUSH;
-	if (io->has_fua)
-		io->split_bio->bi_opf |= REQ_FUA;
-	submit_bio(io->split_bio);
 }
 
 /* deferred io_unit will be dispatched here */
@@ -670,6 +681,11 @@ static void r5c_disable_writeback_async(struct work_struct *work)
 		return;
 	pr_info("md/raid:%s: Disabling writeback cache for degraded array.\n",
 		mdname(mddev));
+
+	/* wait superblock change before suspend */
+	wait_event(mddev->sb_wait,
+		   !test_bit(MD_SB_CHANGE_PENDING, &mddev->sb_flags));
+
 	mddev_suspend(mddev);
 	log->r5c_journal_mode = R5C_JOURNAL_MODE_WRITE_THROUGH;
 	mddev_resume(mddev);
@@ -2621,8 +2637,11 @@ int r5c_try_caching_write(struct r5conf *conf,
 	 * When run in degraded mode, array is set to write-through mode.
 	 * This check helps drain pending write safely in the transition to
 	 * write-through mode.
+	 *
+	 * When a stripe is syncing, the write is also handled in write
+	 * through mode.
 	 */
-	if (s->failed) {
+	if (s->failed || test_bit(STRIPE_SYNCING, &sh->state)) {
 		r5c_make_stripe_write_out(sh);
 		return -EAGAIN;
 	}
@@ -2825,6 +2844,9 @@ void r5c_finish_stripe_write_out(struct r5conf *conf,
 	}
 
 	r5l_append_flush_payload(log, sh->sector);
+	/* stripe is flused to raid disks, we can do resync now */
+	if (test_bit(STRIPE_SYNC_REQUESTED, &sh->state))
+		set_bit(STRIPE_HANDLE, &sh->state);
 }
 
 int r5c_cache_data(struct r5l_log *log, struct stripe_head *sh)
@@ -2973,7 +2995,7 @@ ioerr:
 	return ret;
 }
 
-void r5c_update_on_rdev_error(struct mddev *mddev)
+void r5c_update_on_rdev_error(struct mddev *mddev, struct md_rdev *rdev)
 {
 	struct r5conf *conf = mddev->private;
 	struct r5l_log *log = conf->log;
@@ -2981,7 +3003,8 @@ void r5c_update_on_rdev_error(struct mddev *mddev)
 	if (!log)
 		return;
 
-	if (raid5_calc_degraded(conf) > 0 &&
+	if ((raid5_calc_degraded(conf) > 0 ||
+	     test_bit(Journal, &rdev->flags)) &&
 	    conf->log->r5c_journal_mode == R5C_JOURNAL_MODE_WRITE_BACK)
 		schedule_work(&log->disable_writeback_work);
 }

drivers/md/raid5-log.h

@@ -28,7 +28,8 @@ extern void r5c_flush_cache(struct r5conf *conf, int num);
 extern void r5c_check_stripe_cache_usage(struct r5conf *conf);
 extern void r5c_check_cached_full_stripe(struct r5conf *conf);
 extern struct md_sysfs_entry r5c_journal_mode;
-extern void r5c_update_on_rdev_error(struct mddev *mddev);
+extern void r5c_update_on_rdev_error(struct mddev *mddev,
+				     struct md_rdev *rdev);
 extern bool r5c_big_stripe_cached(struct r5conf *conf, sector_t sect);
 
 extern struct dma_async_tx_descriptor *

drivers/md/raid5.c

@@ -103,8 +103,7 @@ static inline void unlock_device_hash_lock(struct r5conf *conf, int hash)
 static inline void lock_all_device_hash_locks_irq(struct r5conf *conf)
 {
 	int i;
-	local_irq_disable();
+	spin_lock_irq(conf->hash_locks);
-	spin_lock(conf->hash_locks);
 	for (i = 1; i < NR_STRIPE_HASH_LOCKS; i++)
 		spin_lock_nest_lock(conf->hash_locks + i, conf->hash_locks);
 	spin_lock(&conf->device_lock);
@@ -114,9 +113,9 @@ static inline void unlock_all_device_hash_locks_irq(struct r5conf *conf)
 {
 	int i;
 	spin_unlock(&conf->device_lock);
-	for (i = NR_STRIPE_HASH_LOCKS; i; i--)
+	for (i = NR_STRIPE_HASH_LOCKS - 1; i; i--)
-		spin_unlock(conf->hash_locks + i - 1);
+		spin_unlock(conf->hash_locks + i);
-	local_irq_enable();
+	spin_unlock_irq(conf->hash_locks);
 }
 
 /* Find first data disk in a raid6 stripe */
@@ -234,11 +233,15 @@ static void do_release_stripe(struct r5conf *conf, struct stripe_head *sh,
 			if (test_bit(R5_InJournal, &sh->dev[i].flags))
 				injournal++;
 	/*
-	 * When quiesce in r5c write back, set STRIPE_HANDLE for stripes with
+	 * In the following cases, the stripe cannot be released to cached
-	 * data in journal, so they are not released to cached lists
+	 * lists. Therefore, we make the stripe write out and set
+	 * STRIPE_HANDLE:
+	 *   1. when quiesce in r5c write back;
+	 *   2. when resync is requested fot the stripe.
 	 */
-	if (conf->quiesce && r5c_is_writeback(conf->log) &&
+	if (test_bit(STRIPE_SYNC_REQUESTED, &sh->state) ||
-	    !test_bit(STRIPE_HANDLE, &sh->state) && injournal != 0) {
+	    (conf->quiesce && r5c_is_writeback(conf->log) &&
+	     !test_bit(STRIPE_HANDLE, &sh->state) && injournal != 0)) {
 		if (test_bit(STRIPE_R5C_CACHING, &sh->state))
 			r5c_make_stripe_write_out(sh);
 		set_bit(STRIPE_HANDLE, &sh->state);
@@ -714,12 +717,11 @@ static bool is_full_stripe_write(struct stripe_head *sh)
 
 static void lock_two_stripes(struct stripe_head *sh1, struct stripe_head *sh2)
 {
-	local_irq_disable();
 	if (sh1 > sh2) {
-		spin_lock(&sh2->stripe_lock);
+		spin_lock_irq(&sh2->stripe_lock);
 		spin_lock_nested(&sh1->stripe_lock, 1);
 	} else {
-		spin_lock(&sh1->stripe_lock);
+		spin_lock_irq(&sh1->stripe_lock);
 		spin_lock_nested(&sh2->stripe_lock, 1);
 	}
 }
@@ -727,8 +729,7 @@ static void lock_two_stripes(struct stripe_head *sh1, struct stripe_head *sh2)
 static void unlock_two_stripes(struct stripe_head *sh1, struct stripe_head *sh2)
 {
 	spin_unlock(&sh1->stripe_lock);
-	spin_unlock(&sh2->stripe_lock);
+	spin_unlock_irq(&sh2->stripe_lock);
-	local_irq_enable();
 }
 
 /* Only freshly new full stripe normal write stripe can be added to a batch list */
@@ -2312,14 +2313,12 @@ static int resize_stripes(struct r5conf *conf, int newsize)
 	struct stripe_head *osh, *nsh;
 	LIST_HEAD(newstripes);
 	struct disk_info *ndisks;
-	int err;
+	int err = 0;
 	struct kmem_cache *sc;
 	int i;
 	int hash, cnt;
 
-	err = md_allow_write(conf->mddev);
+	md_allow_write(conf->mddev);
-	if (err)
-		return err;
 
 	/* Step 1 */
 	sc = kmem_cache_create(conf->cache_name[1-conf->active_name],
@@ -2694,7 +2693,7 @@ static void raid5_error(struct mddev *mddev, struct md_rdev *rdev)
 		bdevname(rdev->bdev, b),
 		mdname(mddev),
 		conf->raid_disks - mddev->degraded);
-	r5c_update_on_rdev_error(mddev);
+	r5c_update_on_rdev_error(mddev, rdev);
 }
 
 /*
@@ -3055,6 +3054,11 @@ sector_t raid5_compute_blocknr(struct stripe_head *sh, int i, int previous)
  *      When LOG_CRITICAL, stripes with injournal == 0 will be sent to
  *      no_space_stripes list.
  *
+ *   3. during journal failure
+ *      In journal failure, we try to flush all cached data to raid disks
+ *      based on data in stripe cache. The array is read-only to upper
+ *      layers, so we would skip all pending writes.
+ *
  */
 static inline bool delay_towrite(struct r5conf *conf,
 				 struct r5dev *dev,
@@ -3068,6 +3072,9 @@ static inline bool delay_towrite(struct r5conf *conf,
 	if (test_bit(R5C_LOG_CRITICAL, &conf->cache_state) &&
 	    s->injournal > 0)
 		return true;
+	/* case 3 above */
+	if (s->log_failed && s->injournal)
+		return true;
 	return false;
 }
 
@@ -4653,8 +4660,13 @@ static void handle_stripe(struct stripe_head *sh)
 
 	if (test_bit(STRIPE_SYNC_REQUESTED, &sh->state) && !sh->batch_head) {
 		spin_lock(&sh->stripe_lock);
-		/* Cannot process 'sync' concurrently with 'discard' */
+		/*
-		if (!test_bit(STRIPE_DISCARD, &sh->state) &&
+		 * Cannot process 'sync' concurrently with 'discard'.
+		 * Flush data in r5cache before 'sync'.
+		 */
+		if (!test_bit(STRIPE_R5C_PARTIAL_STRIPE, &sh->state) &&
+		    !test_bit(STRIPE_R5C_FULL_STRIPE, &sh->state) &&
+		    !test_bit(STRIPE_DISCARD, &sh->state) &&
 		    test_and_clear_bit(STRIPE_SYNC_REQUESTED, &sh->state)) {
 			set_bit(STRIPE_SYNCING, &sh->state);
 			clear_bit(STRIPE_INSYNC, &sh->state);
@@ -4701,10 +4713,15 @@ static void handle_stripe(struct stripe_head *sh)
 	       " to_write=%d failed=%d failed_num=%d,%d\n",
 	       s.locked, s.uptodate, s.to_read, s.to_write, s.failed,
 	       s.failed_num[0], s.failed_num[1]);
-	/* check if the array has lost more than max_degraded devices and,
+	/*
+	 * check if the array has lost more than max_degraded devices and,
 	 * if so, some requests might need to be failed.
+	 *
+	 * When journal device failed (log_failed), we will only process
+	 * the stripe if there is data need write to raid disks
 	 */
-	if (s.failed > conf->max_degraded || s.log_failed) {
+	if (s.failed > conf->max_degraded ||
+	    (s.log_failed && s.injournal == 0)) {
 		sh->check_state = 0;
 		sh->reconstruct_state = 0;
 		break_stripe_batch_list(sh, 0);
@@ -5277,8 +5294,10 @@ static struct stripe_head *__get_priority_stripe(struct r5conf *conf, int group)
 	struct stripe_head *sh, *tmp;
 	struct list_head *handle_list = NULL;
 	struct r5worker_group *wg;
-	bool second_try = !r5c_is_writeback(conf->log);
+	bool second_try = !r5c_is_writeback(conf->log) &&
-	bool try_loprio = test_bit(R5C_LOG_TIGHT, &conf->cache_state);
+		!r5l_log_disk_error(conf);
+	bool try_loprio = test_bit(R5C_LOG_TIGHT, &conf->cache_state) ||
+		r5l_log_disk_error(conf);
 
 again:
 	wg = NULL;
@@ -6313,7 +6332,6 @@ int
 raid5_set_cache_size(struct mddev *mddev, int size)
 {
 	struct r5conf *conf = mddev->private;
-	int err;
 
 	if (size <= 16 || size > 32768)
 		return -EINVAL;
@@ -6325,10 +6343,7 @@ raid5_set_cache_size(struct mddev *mddev, int size)
 		;
 	mutex_unlock(&conf->cache_size_mutex);
 
-
+	md_allow_write(mddev);
-	err = md_allow_write(mddev);
-	if (err)
-		return err;
 
 	mutex_lock(&conf->cache_size_mutex);
 	while (size > conf->max_nr_stripes)
@@ -7530,7 +7545,9 @@ static int raid5_remove_disk(struct mddev *mddev, struct md_rdev *rdev)
 		 * neilb: there is no locking about new writes here,
 		 * so this cannot be safe.
 		 */
-		if (atomic_read(&conf->active_stripes)) {
+		if (atomic_read(&conf->active_stripes) ||
+		    atomic_read(&conf->r5c_cached_full_stripes) ||
+		    atomic_read(&conf->r5c_cached_partial_stripes)) {
 			return -EBUSY;
 		}
 		log_exit(conf);

drivers/net/ethernet/broadcom/bnxt/bnxt.c

@@ -7642,8 +7642,6 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 	dev->min_mtu = ETH_ZLEN;
 	dev->max_mtu = BNXT_MAX_MTU;
 
-	bnxt_dcb_init(bp);
-
 #ifdef CONFIG_BNXT_SRIOV
 	init_waitqueue_head(&bp->sriov_cfg_wait);
 #endif
@@ -7681,6 +7679,7 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 	bnxt_hwrm_func_qcfg(bp);
 	bnxt_hwrm_port_led_qcaps(bp);
 	bnxt_ethtool_init(bp);
+	bnxt_dcb_init(bp);
 
 	bnxt_set_rx_skb_mode(bp, false);
 	bnxt_set_tpa_flags(bp);

drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.c

@@ -553,8 +553,10 @@ static u8 bnxt_dcbnl_setdcbx(struct net_device *dev, u8 mode)
 	if ((mode & DCB_CAP_DCBX_VER_CEE) || !(mode & DCB_CAP_DCBX_VER_IEEE))
 		return 1;
 
-	if ((mode & DCB_CAP_DCBX_HOST) && BNXT_VF(bp))
+	if (mode & DCB_CAP_DCBX_HOST) {
-		return 1;
+		if (BNXT_VF(bp) || (bp->flags & BNXT_FLAG_FW_LLDP_AGENT))
+			return 1;
+	}
 
 	if (mode == bp->dcbx_cap)
 		return 0;

drivers/net/ethernet/chelsio/cxgb4/t4fw_version.h

@@ -37,7 +37,7 @@
 
 #define T4FW_VERSION_MAJOR 0x01
 #define T4FW_VERSION_MINOR 0x10
-#define T4FW_VERSION_MICRO 0x21
+#define T4FW_VERSION_MICRO 0x2B
 #define T4FW_VERSION_BUILD 0x00
 
 #define T4FW_MIN_VERSION_MAJOR 0x01
@@ -46,7 +46,7 @@
 
 #define T5FW_VERSION_MAJOR 0x01
 #define T5FW_VERSION_MINOR 0x10
-#define T5FW_VERSION_MICRO 0x21
+#define T5FW_VERSION_MICRO 0x2B
 #define T5FW_VERSION_BUILD 0x00
 
 #define T5FW_MIN_VERSION_MAJOR 0x00
@@ -55,7 +55,7 @@
 
 #define T6FW_VERSION_MAJOR 0x01
 #define T6FW_VERSION_MINOR 0x10
-#define T6FW_VERSION_MICRO 0x21
+#define T6FW_VERSION_MICRO 0x2B
 #define T6FW_VERSION_BUILD 0x00
 
 #define T6FW_MIN_VERSION_MAJOR 0x00

drivers/net/ethernet/faraday/ftmac100.c

@@ -1174,11 +1174,17 @@ static int ftmac100_remove(struct platform_device *pdev)
 	return 0;
 }
 
+static const struct of_device_id ftmac100_of_ids[] = {
+	{ .compatible = "andestech,atmac100" },
+	{ }
+};
+
 static struct platform_driver ftmac100_driver = {
 	.probe		= ftmac100_probe,
 	.remove		= ftmac100_remove,
 	.driver		= {
 		.name	= DRV_NAME,
+		.of_match_table = ftmac100_of_ids
 	},
 };
 
@@ -1202,3 +1208,4 @@ module_exit(ftmac100_exit);
 MODULE_AUTHOR("Po-Yu Chuang <ratbert@faraday-tech.com>");
 MODULE_DESCRIPTION("FTMAC100 driver");
 MODULE_LICENSE("GPL");
+MODULE_DEVICE_TABLE(of, ftmac100_of_ids);

drivers/net/ethernet/mellanox/mlx5/core/Kconfig

@@ -13,7 +13,7 @@ config MLX5_CORE
 
 config MLX5_CORE_EN
 	bool "Mellanox Technologies ConnectX-4 Ethernet support"
-	depends on NETDEVICES && ETHERNET && PCI && MLX5_CORE
+	depends on NETDEVICES && ETHERNET && INET && PCI && MLX5_CORE
 	depends on IPV6=y || IPV6=n || MLX5_CORE=m
 	imply PTP_1588_CLOCK
 	default n

drivers/net/ethernet/mellanox/mlxsw/spectrum_dpipe.c

@@ -199,10 +199,11 @@ static int mlxsw_sp_erif_entry_get(struct mlxsw_sp *mlxsw_sp,
 
 	entry->counter_valid = false;
 	entry->counter = 0;
+	entry->index = mlxsw_sp_rif_index(rif);
+
 	if (!counters_enabled)
 		return 0;
 
-	entry->index = mlxsw_sp_rif_index(rif);
 	err = mlxsw_sp_rif_counter_value_get(mlxsw_sp, rif,
 					     MLXSW_SP_RIF_COUNTER_EGRESS,
 					     &cnt);

drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c

@@ -231,6 +231,9 @@ void mlxsw_sp_rif_counter_free(struct mlxsw_sp *mlxsw_sp,
 {
 	unsigned int *p_counter_index;
 
+	if (!mlxsw_sp_rif_counter_valid_get(rif, dir))
+		return;
+
 	p_counter_index = mlxsw_sp_rif_p_counter_get(rif, dir);
 	if (WARN_ON(!p_counter_index))
 		return;

drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c

@@ -1369,8 +1369,7 @@ do_fdb_op:
 	err = mlxsw_sp_port_fdb_uc_op(mlxsw_sp, local_port, mac, fid,
 				      adding, true);
 	if (err) {
-		if (net_ratelimit())
+		dev_err_ratelimited(mlxsw_sp->bus_info->dev, "Failed to set FDB entry\n");
-			netdev_err(mlxsw_sp_port->dev, "Failed to set FDB entry\n");
 		return;
 	}
 
@@ -1430,8 +1429,7 @@ do_fdb_op:
 	err = mlxsw_sp_port_fdb_uc_lag_op(mlxsw_sp, lag_id, mac, fid, lag_vid,
 					  adding, true);
 	if (err) {
-		if (net_ratelimit())
+		dev_err_ratelimited(mlxsw_sp->bus_info->dev, "Failed to set FDB entry\n");
-			netdev_err(mlxsw_sp_port->dev, "Failed to set FDB entry\n");
 		return;
 	}
 

drivers/net/ethernet/renesas/sh_eth.c

@@ -3220,7 +3220,8 @@ static int sh_eth_drv_probe(struct platform_device *pdev)
 	/* MDIO bus init */
 	ret = sh_mdio_init(mdp, pd);
 	if (ret) {
-		dev_err(&ndev->dev, "failed to initialise MDIO\n");
+		if (ret != -EPROBE_DEFER)
+			dev_err(&pdev->dev, "MDIO init failed: %d\n", ret);
 		goto out_release;
 	}
 

drivers/net/usb/qmi_wwan.c

@@ -1196,6 +1196,8 @@ static const struct usb_device_id products[] = {
 	{QMI_FIXED_INTF(0x1199, 0x9071, 10)},	/* Sierra Wireless MC74xx */
 	{QMI_FIXED_INTF(0x1199, 0x9079, 8)},	/* Sierra Wireless EM74xx */
 	{QMI_FIXED_INTF(0x1199, 0x9079, 10)},	/* Sierra Wireless EM74xx */
+	{QMI_FIXED_INTF(0x1199, 0x907b, 8)},	/* Sierra Wireless EM74xx */
+	{QMI_FIXED_INTF(0x1199, 0x907b, 10)},	/* Sierra Wireless EM74xx */
 	{QMI_FIXED_INTF(0x1bbb, 0x011e, 4)},	/* Telekom Speedstick LTE II (Alcatel One Touch L100V LTE) */
 	{QMI_FIXED_INTF(0x1bbb, 0x0203, 2)},	/* Alcatel L800MA */
 	{QMI_FIXED_INTF(0x2357, 0x0201, 4)},	/* TP-LINK HSUPA Modem MA180 */

drivers/s390/cio/ccwgroup.c

@@ -35,7 +35,7 @@ static struct bus_type ccwgroup_bus_type;
 static void __ccwgroup_remove_symlinks(struct ccwgroup_device *gdev)
 {
 	int i;
-	char str[8];
+	char str[16];
 
 	for (i = 0; i < gdev->count; i++) {
 		sprintf(str, "cdev%d", i);
@@ -238,7 +238,7 @@ static void ccwgroup_release(struct device *dev)
 
 static int __ccwgroup_create_symlinks(struct ccwgroup_device *gdev)
 {
-	char str[8];
+	char str[16];
 	int i, rc;
 
 	for (i = 0; i < gdev->count; i++) {

drivers/s390/cio/qdio_debug.h

@@ -11,7 +11,7 @@
 #include "qdio.h"
 
 /* that gives us 15 characters in the text event views */
-#define QDIO_DBF_LEN	16
+#define QDIO_DBF_LEN	32
 
 extern debug_info_t *qdio_dbf_setup;
 extern debug_info_t *qdio_dbf_error;

drivers/s390/virtio/virtio_ccw.c

@@ -87,7 +87,7 @@ struct vq_info_block {
 } __packed;
 
 struct virtio_feature_desc {
-	__u32 features;
+	__le32 features;
 	__u8 index;
 } __packed;
 

include/net/x25.h

@@ -298,10 +298,10 @@ void x25_check_rbuf(struct sock *);
 
 /* sysctl_net_x25.c */
 #ifdef CONFIG_SYSCTL
-void x25_register_sysctl(void);
+int x25_register_sysctl(void);
 void x25_unregister_sysctl(void);
 #else
-static inline void x25_register_sysctl(void) {};
+static inline int x25_register_sysctl(void) { return 0; };
 static inline void x25_unregister_sysctl(void) {};
 #endif /* CONFIG_SYSCTL */
 

kernel/bpf/verifier.c

@@ -140,7 +140,7 @@ struct bpf_verifier_stack_elem {
 	struct bpf_verifier_stack_elem *next;
 };
 
-#define BPF_COMPLEXITY_LIMIT_INSNS	65536
+#define BPF_COMPLEXITY_LIMIT_INSNS	98304
 #define BPF_COMPLEXITY_LIMIT_STACK	1024
 
 #define BPF_MAP_PTR_POISON ((void *)0xeB9F + POISON_POINTER_DELTA)
@@ -2640,6 +2640,7 @@ peek_stack:
 				env->explored_states[t + 1] = STATE_LIST_MARK;
 		} else {
 			/* conditional jump with two edges */
+			env->explored_states[t] = STATE_LIST_MARK;
 			ret = push_insn(t, t + 1, FALLTHROUGH, env);
 			if (ret == 1)
 				goto peek_stack;
@@ -2798,6 +2799,12 @@ static bool states_equal(struct bpf_verifier_env *env,
 		     rcur->type != NOT_INIT))
 			continue;
 
+		/* Don't care about the reg->id in this case. */
+		if (rold->type == PTR_TO_MAP_VALUE_OR_NULL &&
+		    rcur->type == PTR_TO_MAP_VALUE_OR_NULL &&
+		    rold->map_ptr == rcur->map_ptr)
+			continue;
+
 		if (rold->type == PTR_TO_PACKET && rcur->type == PTR_TO_PACKET &&
 		    compare_ptrs_to_packet(rold, rcur))
 			continue;
@@ -2932,6 +2939,9 @@ static int do_check(struct bpf_verifier_env *env)
 			goto process_bpf_exit;
 		}
 
+		if (need_resched())
+			cond_resched();
+
 		if (log_level > 1 || (log_level && do_print_state)) {
 			if (log_level > 1)
 				verbose("%d:", insn_idx);

kernel/fork.c

@@ -1845,11 +1845,13 @@ static __latent_entropy struct task_struct *copy_process(
 	*/
 	recalc_sigpending();
 	if (signal_pending(current)) {
-		spin_unlock(&current->sighand->siglock);
-		write_unlock_irq(&tasklist_lock);
 		retval = -ERESTARTNOINTR;
 		goto bad_fork_cancel_cgroup;
 	}
+	if (unlikely(!(ns_of_pid(pid)->nr_hashed & PIDNS_HASH_ADDING))) {
+		retval = -ENOMEM;
+		goto bad_fork_cancel_cgroup;
+	}
 
 	if (likely(p->pid)) {
 		ptrace_init_task(p, (clone_flags & CLONE_PTRACE) || trace);
@@ -1907,6 +1909,8 @@ static __latent_entropy struct task_struct *copy_process(
 	return p;
 
 bad_fork_cancel_cgroup:
+	spin_unlock(&current->sighand->siglock);
+	write_unlock_irq(&tasklist_lock);
 	cgroup_cancel_fork(p);
 bad_fork_free_pid:
 	cgroup_threadgroup_change_end(current);

kernel/pid_namespace.c

@@ -277,7 +277,7 @@ void zap_pid_ns_processes(struct pid_namespace *pid_ns)
 	 * if reparented.
 	 */
 	for (;;) {
-		set_current_state(TASK_UNINTERRUPTIBLE);
+		set_current_state(TASK_INTERRUPTIBLE);
 		if (pid_ns->nr_hashed == init_pids)
 			break;
 		schedule();

net/bridge/br_netlink.c

@@ -835,6 +835,13 @@ static int br_validate(struct nlattr *tb[], struct nlattr *data[])
 			return -EPROTONOSUPPORT;
 		}
 	}
+
+	if (data[IFLA_BR_VLAN_DEFAULT_PVID]) {
+		__u16 defpvid = nla_get_u16(data[IFLA_BR_VLAN_DEFAULT_PVID]);
+
+		if (defpvid >= VLAN_VID_MASK)
+			return -EINVAL;
+	}
 #endif
 
 	return 0;

net/core/neighbour.c

@@ -1132,10 +1132,6 @@ int neigh_update(struct neighbour *neigh, const u8 *lladdr, u8 new,
 		lladdr = neigh->ha;
 	}
 
-	if (new & NUD_CONNECTED)
-		neigh->confirmed = jiffies;
-	neigh->updated = jiffies;
-
 	/* If entry was valid and address is not changed,
 	   do not change entry state, if new one is STALE.
 	 */
@@ -1157,6 +1153,16 @@ int neigh_update(struct neighbour *neigh, const u8 *lladdr, u8 new,
 		}
 	}
 
+	/* Update timestamps only once we know we will make a change to the
+	 * neighbour entry. Otherwise we risk to move the locktime window with
+	 * noop updates and ignore relevant ARP updates.
+	 */
+	if (new != old || lladdr != neigh->ha) {
+		if (new & NUD_CONNECTED)
+			neigh->confirmed = jiffies;
+		neigh->updated = jiffies;
+	}
+
 	if (new != old) {
 		neigh_del_timer(neigh);
 		if (new & NUD_PROBE)

net/core/rtnetlink.c

@@ -1627,13 +1627,13 @@ static int rtnl_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb)
 					       cb->nlh->nlmsg_seq, 0,
 					       flags,
 					       ext_filter_mask);
-			/* If we ran out of room on the first message,
-			 * we're in trouble
-			 */
-			WARN_ON((err == -EMSGSIZE) && (skb->len == 0));
 
-			if (err < 0)
+			if (err < 0) {
-				goto out;
+				if (likely(skb->len))
+					goto out;
+
+				goto out_err;
+			}
 
 			nl_dump_check_consistent(cb, nlmsg_hdr(skb));
 cont:
@@ -1641,10 +1641,12 @@ cont:
 		}
 	}
 out:
+	err = skb->len;
+out_err:
 	cb->args[1] = idx;
 	cb->args[0] = h;
 
-	return skb->len;
+	return err;
 }
 
 int rtnl_nla_parse_ifla(struct nlattr **tb, const struct nlattr *head, int len,
@@ -3453,8 +3455,12 @@ static int rtnl_bridge_getlink(struct sk_buff *skb, struct netlink_callback *cb)
 				err = br_dev->netdev_ops->ndo_bridge_getlink(
 						skb, portid, seq, dev,
 						filter_mask, NLM_F_MULTI);
-				if (err < 0 && err != -EOPNOTSUPP)
+				if (err < 0 && err != -EOPNOTSUPP) {
-					break;
+					if (likely(skb->len))
+						break;
+
+					goto out_err;
+				}
 			}
 			idx++;
 		}
@@ -3465,16 +3471,22 @@ static int rtnl_bridge_getlink(struct sk_buff *skb, struct netlink_callback *cb)
 							      seq, dev,
 							      filter_mask,
 							      NLM_F_MULTI);
-				if (err < 0 && err != -EOPNOTSUPP)
+				if (err < 0 && err != -EOPNOTSUPP) {
-					break;
+					if (likely(skb->len))
+						break;
+
+					goto out_err;
+				}
 			}
 			idx++;
 		}
 	}
+	err = skb->len;
+out_err:
 	rcu_read_unlock();
 	cb->args[0] = idx;
 
-	return skb->len;
+	return err;
 }
 
 static inline size_t bridge_nlmsg_size(void)

net/core/sock.c

@@ -139,10 +139,7 @@
 
 #include <trace/events/sock.h>
 
-#ifdef CONFIG_INET
 #include <net/tcp.h>
-#endif
-
 #include <net/busy_poll.h>
 
 static DEFINE_MUTEX(proto_list_mutex);

net/ipv4/arp.c

@@ -653,6 +653,7 @@ static int arp_process(struct net *net, struct sock *sk, struct sk_buff *skb)
 	unsigned char *arp_ptr;
 	struct rtable *rt;
 	unsigned char *sha;
+	unsigned char *tha = NULL;
 	__be32 sip, tip;
 	u16 dev_type = dev->type;
 	int addr_type;
@@ -724,6 +725,7 @@ static int arp_process(struct net *net, struct sock *sk, struct sk_buff *skb)
 		break;
 #endif
 	default:
+		tha = arp_ptr;
 		arp_ptr += dev->addr_len;
 	}
 	memcpy(&tip, arp_ptr, 4);
@@ -842,8 +844,18 @@ static int arp_process(struct net *net, struct sock *sk, struct sk_buff *skb)
 		   It is possible, that this option should be enabled for some
 		   devices (strip is candidate)
 		 */
-		is_garp = arp->ar_op == htons(ARPOP_REQUEST) && tip == sip &&
+		is_garp = tip == sip && addr_type == RTN_UNICAST;
-			  addr_type == RTN_UNICAST;
+
+		/* Unsolicited ARP _replies_ also require target hwaddr to be
+		 * the same as source.
+		 */
+		if (is_garp && arp->ar_op == htons(ARPOP_REPLY))
+			is_garp =
+				/* IPv4 over IEEE 1394 doesn't provide target
+				 * hardware address field in its ARP payload.
+				 */
+				tha &&
+				!memcmp(tha, sha, dev->addr_len);
 
 		if (!n &&
 		    ((arp->ar_op == htons(ARPOP_REPLY)  &&

net/ipv4/fib_frontend.c

@@ -763,7 +763,7 @@ static int inet_dump_fib(struct sk_buff *skb, struct netlink_callback *cb)
 	unsigned int e = 0, s_e;
 	struct fib_table *tb;
 	struct hlist_head *head;
-	int dumped = 0;
+	int dumped = 0, err;
 
 	if (nlmsg_len(cb->nlh) >= sizeof(struct rtmsg) &&
 	    ((struct rtmsg *) nlmsg_data(cb->nlh))->rtm_flags & RTM_F_CLONED)
@@ -783,20 +783,27 @@ static int inet_dump_fib(struct sk_buff *skb, struct netlink_callback *cb)
 			if (dumped)
 				memset(&cb->args[2], 0, sizeof(cb->args) -
 						 2 * sizeof(cb->args[0]));
-			if (fib_table_dump(tb, skb, cb) < 0)
+			err = fib_table_dump(tb, skb, cb);
-				goto out;
+			if (err < 0) {
+				if (likely(skb->len))
+					goto out;
+
+				goto out_err;
+			}
 			dumped = 1;
 next:
 			e++;
 		}
 	}
 out:
+	err = skb->len;
+out_err:
 	rcu_read_unlock();
 
 	cb->args[1] = e;
 	cb->args[0] = h;
 
-	return skb->len;
+	return err;
 }
 
 /* Prepare and feed intra-kernel routing request.

net/ipv4/fib_trie.c

@@ -1983,6 +1983,8 @@ static int fn_trie_dump_leaf(struct key_vector *l, struct fib_table *tb,
 
 	/* rcu_read_lock is hold by caller */
 	hlist_for_each_entry_rcu(fa, &l->leaf, fa_list) {
+		int err;
+
 		if (i < s_i) {
 			i++;
 			continue;
@@ -1993,17 +1995,14 @@ static int fn_trie_dump_leaf(struct key_vector *l, struct fib_table *tb,
 			continue;
 		}
 
-		if (fib_dump_info(skb, NETLINK_CB(cb->skb).portid,
+		err = fib_dump_info(skb, NETLINK_CB(cb->skb).portid,
-				  cb->nlh->nlmsg_seq,
+				    cb->nlh->nlmsg_seq, RTM_NEWROUTE,
-				  RTM_NEWROUTE,
+				    tb->tb_id, fa->fa_type,
-				  tb->tb_id,
+				    xkey, KEYLENGTH - fa->fa_slen,
-				  fa->fa_type,
+				    fa->fa_tos, fa->fa_info, NLM_F_MULTI);
-				  xkey,
+		if (err < 0) {
-				  KEYLENGTH - fa->fa_slen,
-				  fa->fa_tos,
-				  fa->fa_info, NLM_F_MULTI) < 0) {
 			cb->args[4] = i;
-			return -1;
+			return err;
 		}
 		i++;
 	}
@@ -2025,10 +2024,13 @@ int fib_table_dump(struct fib_table *tb, struct sk_buff *skb,
 	t_key key = cb->args[3];
 
 	while ((l = leaf_walk_rcu(&tp, key)) != NULL) {
-		if (fn_trie_dump_leaf(l, tb, skb, cb) < 0) {
+		int err;
+
+		err = fn_trie_dump_leaf(l, tb, skb, cb);
+		if (err < 0) {
 			cb->args[3] = key;
 			cb->args[2] = count;
-			return -1;
+			return err;
 		}
 
 		++count;

net/ipv4/ipmr.c

@@ -1980,6 +1980,20 @@ int ip_mr_input(struct sk_buff *skb)
 	struct net *net = dev_net(skb->dev);
 	int local = skb_rtable(skb)->rt_flags & RTCF_LOCAL;
 	struct mr_table *mrt;
+	struct net_device *dev;
+
+	/* skb->dev passed in is the loX master dev for vrfs.
+	 * As there are no vifs associated with loopback devices,
+	 * get the proper interface that does have a vif associated with it.
+	 */
+	dev = skb->dev;
+	if (netif_is_l3_master(skb->dev)) {
+		dev = dev_get_by_index_rcu(net, IPCB(skb)->iif);
+		if (!dev) {
+			kfree_skb(skb);
+			return -ENODEV;
+		}
+	}
 
 	/* Packet is looped back after forward, it should not be
 	 * forwarded second time, but still can be delivered locally.
@@ -2017,7 +2031,7 @@ int ip_mr_input(struct sk_buff *skb)
 	/* already under rcu_read_lock() */
 	cache = ipmr_cache_find(mrt, ip_hdr(skb)->saddr, ip_hdr(skb)->daddr);
 	if (!cache) {
-		int vif = ipmr_find_vif(mrt, skb->dev);
+		int vif = ipmr_find_vif(mrt, dev);
 
 		if (vif >= 0)
 			cache = ipmr_cache_find_any(mrt, ip_hdr(skb)->daddr,
@@ -2037,7 +2051,7 @@ int ip_mr_input(struct sk_buff *skb)
 		}
 
 		read_lock(&mrt_lock);
-		vif = ipmr_find_vif(mrt, skb->dev);
+		vif = ipmr_find_vif(mrt, dev);
 		if (vif >= 0) {
 			int err2 = ipmr_cache_unresolved(mrt, vif, skb);
 			read_unlock(&mrt_lock);

net/ipv4/tcp_input.c

@@ -3190,7 +3190,7 @@ static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets,
 			int delta;
 
 			/* Non-retransmitted hole got filled? That's reordering */
-			if (reord < prior_fackets)
+			if (reord < prior_fackets && reord <= tp->fackets_out)
 				tcp_update_reordering(sk, tp->fackets_out - reord, 0);
 
 			delta = tcp_is_fack(tp) ? pkts_acked :

net/ipv4/udp.c

@@ -1727,7 +1727,7 @@ static void udp_v4_rehash(struct sock *sk)
 	udp_lib_rehash(sk, new_hash);
 }
 
-int __udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
+static int __udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
 {
 	int rc;
 
@@ -1772,7 +1772,7 @@ EXPORT_SYMBOL(udp_encap_enable);
  * Note that in the success and error cases, the skb is assumed to
  * have either been requeued or freed.
  */
-int udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
+static int udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
 {
 	struct udp_sock *up = udp_sk(sk);
 	int is_udplite = IS_UDPLITE(sk);

net/ipv4/udp_impl.h

@@ -25,7 +25,6 @@ int udp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int noblock,
 		int flags, int *addr_len);
 int udp_sendpage(struct sock *sk, struct page *page, int offset, size_t size,
 		 int flags);
-int __udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb);
 void udp_destroy_sock(struct sock *sk);
 
 #ifdef CONFIG_PROC_FS

net/ipv6/ip6_offload.c

@@ -63,7 +63,6 @@ static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb,
 	const struct net_offload *ops;
 	int proto;
 	struct frag_hdr *fptr;
-	unsigned int unfrag_ip6hlen;
 	unsigned int payload_len;
 	u8 *prevhdr;
 	int offset = 0;
@@ -116,8 +115,10 @@ static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb,
 		skb->network_header = (u8 *)ipv6h - skb->head;
 
 		if (udpfrag) {
-			unfrag_ip6hlen = ip6_find_1stfragopt(skb, &prevhdr);
+			int err = ip6_find_1stfragopt(skb, &prevhdr);
-			fptr = (struct frag_hdr *)((u8 *)ipv6h + unfrag_ip6hlen);
+			if (err < 0)
+				return ERR_PTR(err);
+			fptr = (struct frag_hdr *)((u8 *)ipv6h + err);
 			fptr->frag_off = htons(offset);
 			if (skb->next)
 				fptr->frag_off |= htons(IP6_MF);

net/ipv6/ip6_output.c

@@ -597,7 +597,10 @@ int ip6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb,
 	int ptr, offset = 0, err = 0;
 	u8 *prevhdr, nexthdr = 0;
 
-	hlen = ip6_find_1stfragopt(skb, &prevhdr);
+	err = ip6_find_1stfragopt(skb, &prevhdr);
+	if (err < 0)
+		goto fail;
+	hlen = err;
 	nexthdr = *prevhdr;
 
 	mtu = ip6_skb_dst_mtu(skb);

net/ipv6/output_core.c

@@ -79,14 +79,13 @@ EXPORT_SYMBOL(ipv6_select_ident);
 int ip6_find_1stfragopt(struct sk_buff *skb, u8 **nexthdr)
 {
 	u16 offset = sizeof(struct ipv6hdr);
-	struct ipv6_opt_hdr *exthdr =
-				(struct ipv6_opt_hdr *)(ipv6_hdr(skb) + 1);
 	unsigned int packet_len = skb_tail_pointer(skb) -
 		skb_network_header(skb);
 	int found_rhdr = 0;
 	*nexthdr = &ipv6_hdr(skb)->nexthdr;
 
-	while (offset + 1 <= packet_len) {
+	while (offset <= packet_len) {
+		struct ipv6_opt_hdr *exthdr;
 
 		switch (**nexthdr) {
 
@@ -107,13 +106,16 @@ int ip6_find_1stfragopt(struct sk_buff *skb, u8 **nexthdr)
 			return offset;
 		}
 
-		offset += ipv6_optlen(exthdr);
+		if (offset + sizeof(struct ipv6_opt_hdr) > packet_len)
-		*nexthdr = &exthdr->nexthdr;
+			return -EINVAL;
+
 		exthdr = (struct ipv6_opt_hdr *)(skb_network_header(skb) +
 						 offset);
+		offset += ipv6_optlen(exthdr);
+		*nexthdr = &exthdr->nexthdr;
 	}
 
-	return offset;
+	return -EINVAL;
 }
 EXPORT_SYMBOL(ip6_find_1stfragopt);
 

net/ipv6/udp.c

@@ -527,7 +527,7 @@ out:
 	return;
 }
 
-int __udpv6_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
+static int __udpv6_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
 {
 	int rc;
 
@@ -570,7 +570,7 @@ void udpv6_encap_enable(void)
 }
 EXPORT_SYMBOL(udpv6_encap_enable);
 
-int udpv6_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
+static int udpv6_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
 {
 	struct udp_sock *up = udp_sk(sk);
 	int is_udplite = IS_UDPLITE(sk);

net/ipv6/udp_impl.h

@@ -26,7 +26,6 @@ int compat_udpv6_getsockopt(struct sock *sk, int level, int optname,
 int udpv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len);
 int udpv6_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int noblock,
 		  int flags, int *addr_len);
-int __udpv6_queue_rcv_skb(struct sock *sk, struct sk_buff *skb);
 void udpv6_destroy_sock(struct sock *sk);
 
 #ifdef CONFIG_PROC_FS

net/ipv6/udp_offload.c

@@ -29,6 +29,7 @@ static struct sk_buff *udp6_ufo_fragment(struct sk_buff *skb,
 	u8 frag_hdr_sz = sizeof(struct frag_hdr);
 	__wsum csum;
 	int tnl_hlen;
+	int err;
 
 	mss = skb_shinfo(skb)->gso_size;
 	if (unlikely(skb->len <= mss))
@@ -90,7 +91,10 @@ static struct sk_buff *udp6_ufo_fragment(struct sk_buff *skb,
 		/* Find the unfragmentable header and shift it left by frag_hdr_sz
 		 * bytes to insert fragment header.
 		 */
-		unfrag_ip6hlen = ip6_find_1stfragopt(skb, &prevhdr);
+		err = ip6_find_1stfragopt(skb, &prevhdr);
+		if (err < 0)
+			return ERR_PTR(err);
+		unfrag_ip6hlen = err;
 		nexthdr = *prevhdr;
 		*prevhdr = NEXTHDR_FRAGMENT;
 		unfrag_len = (skb_network_header(skb) - skb_mac_header(skb)) +

net/sctp/ipv6.c

@@ -677,6 +677,9 @@ static struct sock *sctp_v6_create_accept_sk(struct sock *sk,
 	newnp = inet6_sk(newsk);
 
 	memcpy(newnp, np, sizeof(struct ipv6_pinfo));
+	newnp->ipv6_mc_list = NULL;
+	newnp->ipv6_ac_list = NULL;
+	newnp->ipv6_fl_list = NULL;
 
 	rcu_read_lock();
 	opt = rcu_dereference(np->opt);

net/smc/Kconfig

@@ -8,6 +8,10 @@ config SMC
 	  The Linux implementation of the SMC-R solution is designed as
 	  a separate socket family SMC.
 
+	  Warning: SMC will expose all memory for remote reads and writes
+	  once a connection is established.  Don't enable this option except
+	  for tightly controlled lab environment.
+
 	  Select this option if you want to run SMC socket applications
 
 config SMC_DIAG

net/smc/smc_clc.c

@@ -204,7 +204,7 @@ int smc_clc_send_confirm(struct smc_sock *smc)
 	memcpy(&cclc.lcl.mac, &link->smcibdev->mac[link->ibport - 1], ETH_ALEN);
 	hton24(cclc.qpn, link->roce_qp->qp_num);
 	cclc.rmb_rkey =
-		htonl(conn->rmb_desc->mr_rx[SMC_SINGLE_LINK]->rkey);
+		htonl(conn->rmb_desc->rkey[SMC_SINGLE_LINK]);
 	cclc.conn_idx = 1; /* for now: 1 RMB = 1 RMBE */
 	cclc.rmbe_alert_token = htonl(conn->alert_token_local);
 	cclc.qp_mtu = min(link->path_mtu, link->peer_mtu);
@@ -256,7 +256,7 @@ int smc_clc_send_accept(struct smc_sock *new_smc, int srv_first_contact)
 	memcpy(&aclc.lcl.mac, link->smcibdev->mac[link->ibport - 1], ETH_ALEN);
 	hton24(aclc.qpn, link->roce_qp->qp_num);
 	aclc.rmb_rkey =
-		htonl(conn->rmb_desc->mr_rx[SMC_SINGLE_LINK]->rkey);
+		htonl(conn->rmb_desc->rkey[SMC_SINGLE_LINK]);
 	aclc.conn_idx = 1;			/* as long as 1 RMB = 1 RMBE */
 	aclc.rmbe_alert_token = htonl(conn->alert_token_local);
 	aclc.qp_mtu = link->path_mtu;

net/smc/smc_core.c

@@ -613,19 +613,8 @@ int smc_rmb_create(struct smc_sock *smc)
 			rmb_desc = NULL;
 			continue; /* if mapping failed, try smaller one */
 		}
-		rc = smc_ib_get_memory_region(lgr->lnk[SMC_SINGLE_LINK].roce_pd,
+		rmb_desc->rkey[SMC_SINGLE_LINK] =
-					      IB_ACCESS_REMOTE_WRITE |
+			lgr->lnk[SMC_SINGLE_LINK].roce_pd->unsafe_global_rkey;
-					      IB_ACCESS_LOCAL_WRITE,
-					     &rmb_desc->mr_rx[SMC_SINGLE_LINK]);
-		if (rc) {
-			smc_ib_buf_unmap(lgr->lnk[SMC_SINGLE_LINK].smcibdev,
-					 tmp_bufsize, rmb_desc,
-					 DMA_FROM_DEVICE);
-			kfree(rmb_desc->cpu_addr);
-			kfree(rmb_desc);
-			rmb_desc = NULL;
-			continue;
-		}
 		rmb_desc->used = 1;
 		write_lock_bh(&lgr->rmbs_lock);
 		list_add(&rmb_desc->list,
@@ -668,6 +657,7 @@ int smc_rmb_rtoken_handling(struct smc_connection *conn,
 
 	for (i = 0; i < SMC_RMBS_PER_LGR_MAX; i++) {
 		if ((lgr->rtokens[i][SMC_SINGLE_LINK].rkey == rkey) &&
+		    (lgr->rtokens[i][SMC_SINGLE_LINK].dma_addr == dma_addr) &&
 		    test_bit(i, lgr->rtokens_used_mask)) {
 			conn->rtoken_idx = i;
 			return 0;

net/smc/smc_core.h

@@ -93,7 +93,7 @@ struct smc_buf_desc {
 	u64			dma_addr[SMC_LINKS_PER_LGR_MAX];
 						/* mapped address of buffer */
 	void			*cpu_addr;	/* virtual address of buffer */
-	struct ib_mr		*mr_rx[SMC_LINKS_PER_LGR_MAX];
+	u32			rkey[SMC_LINKS_PER_LGR_MAX];
 						/* for rmb only:
 						 * rkey provided to peer
 						 */

net/smc/smc_ib.c

@@ -37,24 +37,6 @@ u8 local_systemid[SMC_SYSTEMID_LEN] = SMC_LOCAL_SYSTEMID_RESET;	/* unique system
 								 * identifier
 								 */
 
-int smc_ib_get_memory_region(struct ib_pd *pd, int access_flags,
-			     struct ib_mr **mr)
-{
-	int rc;
-
-	if (*mr)
-		return 0; /* already done */
-
-	/* obtain unique key -
-	 * next invocation of get_dma_mr returns a different key!
-	 */
-	*mr = pd->device->get_dma_mr(pd, access_flags);
-	rc = PTR_ERR_OR_ZERO(*mr);
-	if (IS_ERR(*mr))
-		*mr = NULL;
-	return rc;
-}
-
 static int smc_ib_modify_qp_init(struct smc_link *lnk)
 {
 	struct ib_qp_attr qp_attr;
@@ -210,7 +192,8 @@ int smc_ib_create_protection_domain(struct smc_link *lnk)
 {
 	int rc;
 
-	lnk->roce_pd = ib_alloc_pd(lnk->smcibdev->ibdev, 0);
+	lnk->roce_pd = ib_alloc_pd(lnk->smcibdev->ibdev,
+				   IB_PD_UNSAFE_GLOBAL_RKEY);
 	rc = PTR_ERR_OR_ZERO(lnk->roce_pd);
 	if (IS_ERR(lnk->roce_pd))
 		lnk->roce_pd = NULL;

net/smc/smc_ib.h

@@ -61,8 +61,6 @@ void smc_ib_dealloc_protection_domain(struct smc_link *lnk);
 int smc_ib_create_protection_domain(struct smc_link *lnk);
 void smc_ib_destroy_queue_pair(struct smc_link *lnk);
 int smc_ib_create_queue_pair(struct smc_link *lnk);
-int smc_ib_get_memory_region(struct ib_pd *pd, int access_flags,
-			     struct ib_mr **mr);
 int smc_ib_ready_link(struct smc_link *lnk);
 int smc_ib_modify_qp_rts(struct smc_link *lnk);
 int smc_ib_modify_qp_reset(struct smc_link *lnk);

net/x25/af_x25.c

@@ -1791,32 +1791,40 @@ void x25_kill_by_neigh(struct x25_neigh *nb)
 
 static int __init x25_init(void)
 {
-	int rc = proto_register(&x25_proto, 0);
+	int rc;
 
-	if (rc != 0)
+	rc = proto_register(&x25_proto, 0);
+	if (rc)
 		goto out;
 
 	rc = sock_register(&x25_family_ops);
-	if (rc != 0)
+	if (rc)
 		goto out_proto;
 
 	dev_add_pack(&x25_packet_type);
 
 	rc = register_netdevice_notifier(&x25_dev_notifier);
-	if (rc != 0)
+	if (rc)
 		goto out_sock;
 
+	rc = x25_register_sysctl();
+	if (rc)
+		goto out_dev;
+
+	rc = x25_proc_init();
+	if (rc)
+		goto out_sysctl;
+
 	pr_info("Linux Version 0.2\n");
 
-	x25_register_sysctl();
-	rc = x25_proc_init();
-	if (rc != 0)
-		goto out_dev;
 out:
 	return rc;
+out_sysctl:
+	x25_unregister_sysctl();
 out_dev:
 	unregister_netdevice_notifier(&x25_dev_notifier);
 out_sock:
+	dev_remove_pack(&x25_packet_type);
 	sock_unregister(AF_X25);
 out_proto:
 	proto_unregister(&x25_proto);

net/x25/sysctl_net_x25.c

@@ -73,9 +73,12 @@ static struct ctl_table x25_table[] = {
 	{ },
 };
 
-void __init x25_register_sysctl(void)
+int __init x25_register_sysctl(void)
 {
 	x25_table_header = register_net_sysctl(&init_net, "net/x25", x25_table);
+	if (!x25_table_header)
+		return -ENOMEM;
+	return 0;
 }
 
 void x25_unregister_sysctl(void)

scripts/Makefile.headersinst

@@ -8,6 +8,29 @@
 #
 # ==========================================================================
 
+PHONY := __headers
+__headers:
+
+include scripts/Kbuild.include
+
+srcdir        := $(srctree)/$(obj)
+subdirs       := $(patsubst $(srcdir)/%/.,%,$(wildcard $(srcdir)/*/.))
+# caller may set destination dir (when installing to asm/)
+_dst          := $(if $(dst),$(dst),$(obj))
+
+# Recursion
+__headers: $(subdirs)
+
+.PHONY: $(subdirs)
+$(subdirs):
+	$(Q)$(MAKE) $(hdr-inst)=$(obj)/$@ dst=$(_dst)/$@
+
+# Skip header install/check for include/uapi and arch/$(hdr-arch)/include/uapi.
+# We have only sub-directories there.
+skip-inst := $(if $(filter %/uapi,$(obj)),1)
+
+ifeq ($(skip-inst),)
+
 # generated header directory
 gen := $(if $(gen),$(gen),$(subst include/,include/generated/,$(obj)))
 
@@ -15,21 +38,14 @@ gen := $(if $(gen),$(gen),$(subst include/,include/generated/,$(obj)))
 kbuild-file := $(srctree)/$(obj)/Kbuild
 -include $(kbuild-file)
 
-# called may set destination dir (when installing to asm/)
-_dst := $(if $(dst),$(dst),$(obj))
-
 old-kbuild-file := $(srctree)/$(subst uapi/,,$(obj))/Kbuild
 ifneq ($(wildcard $(old-kbuild-file)),)
 include $(old-kbuild-file)
 endif
 
-include scripts/Kbuild.include
-
 installdir    := $(INSTALL_HDR_PATH)/$(subst uapi/,,$(_dst))
 
-srcdir        := $(srctree)/$(obj)
 gendir        := $(objtree)/$(gen)
-subdirs       := $(patsubst $(srcdir)/%/.,%,$(wildcard $(srcdir)/*/.))
 header-files  := $(notdir $(wildcard $(srcdir)/*.h))
 header-files  += $(notdir $(wildcard $(srcdir)/*.agh))
 header-files  := $(filter-out $(no-export-headers), $(header-files))
@@ -88,11 +104,9 @@ quiet_cmd_check = CHECK   $(printdir) ($(words $(all-files)) files)
                   $(PERL) $< $(INSTALL_HDR_PATH)/include $(SRCARCH); \
 	          touch $@
 
-PHONY += __headersinst __headerscheck
-
 ifndef HDRCHECK
 # Rules for installing headers
-__headersinst: $(subdirs) $(install-file)
+__headers: $(install-file)
 	@:
 
 targets += $(install-file)
@@ -104,7 +118,7 @@ $(install-file): scripts/headers_install.sh \
 	$(call if_changed,install)
 
 else
-__headerscheck: $(subdirs) $(check-file)
+__headers: $(check-file)
 	@:
 
 targets += $(check-file)
@@ -113,11 +127,6 @@ $(check-file): scripts/headers_check.pl $(output-files) FORCE
 
 endif
 
-# Recursion
-.PHONY: $(subdirs)
-$(subdirs):
-	$(Q)$(MAKE) $(hdr-inst)=$(obj)/$@ dst=$(_dst)/$@
-
 targets := $(wildcard $(sort $(targets)))
 cmd_files := $(wildcard \
              $(foreach f,$(targets),$(dir $(f)).$(notdir $(f)).cmd))
@@ -126,6 +135,8 @@ ifneq ($(cmd_files),)
 	include $(cmd_files)
 endif
 
+endif # skip-inst
+
 .PHONY: $(PHONY)
 PHONY += FORCE
 FORCE: ;

tools/testing/selftests/bpf/include/uapi/linux/types.h

@@ -3,4 +3,20 @@
 
 #include <asm-generic/int-ll64.h>
 
+/* copied from linux:include/uapi/linux/types.h */
+#define __bitwise
+typedef __u16 __bitwise __le16;
+typedef __u16 __bitwise __be16;
+typedef __u32 __bitwise __le32;
+typedef __u32 __bitwise __be32;
+typedef __u64 __bitwise __le64;
+typedef __u64 __bitwise __be64;
+
+typedef __u16 __bitwise __sum16;
+typedef __u32 __bitwise __wsum;
+
+#define __aligned_u64 __u64 __attribute__((aligned(8)))
+#define __aligned_be64 __be64 __attribute__((aligned(8)))
+#define __aligned_le64 __le64 __attribute__((aligned(8)))
+
 #endif /* _UAPI_LINUX_TYPES_H */

tools/testing/selftests/bpf/test_pkt_access.c

@@ -5,6 +5,7 @@
  * License as published by the Free Software Foundation.
  */
 #include <stddef.h>
+#include <string.h>
 #include <linux/bpf.h>
 #include <linux/if_ether.h>
 #include <linux/if_packet.h>