Merge branches 'acpi-scan', 'acpi-sysfs', 'acpi-wdat' and 'acpi-tables'

* acpi-scan:
  ACPI / scan: Prefer devices without _HID/_CID for _ADR matching
  ACPI: Drop misplaced acpi_dma_deconfigure() call from acpi_bind_one()

* acpi-sysfs:
  ACPI / sysfs: Provide quirk mechanism to prevent GPE flooding

* acpi-wdat:
  ACPI / watchdog: Print out error number when device creation fails

* acpi-tables:
  ACPI / DMAR: Avoid passing NULL to acpi_put_table()

Documentation/DocBook/Makefile

@@ -12,7 +12,7 @@ DOCBOOKS := z8530book.xml  \
 	    kernel-api.xml filesystems.xml lsm.xml kgdb.xml \
 	    gadget.xml libata.xml mtdnand.xml librs.xml rapidio.xml \
 	    genericirq.xml s390-drivers.xml uio-howto.xml scsi.xml \
-	    80211.xml sh.xml regulator.xml w1.xml \
+	    sh.xml regulator.xml w1.xml \
 	    writing_musb_glue_layer.xml iio.xml
 
 ifeq ($(DOCBOOKS),)

Documentation/admin-guide/kernel-parameters.txt

@@ -106,6 +106,16 @@
 			use by PCI
 			Format: <irq>,<irq>...
 
+	acpi_mask_gpe=  [HW,ACPI]
+			Due to the existence of _Lxx/_Exx, some GPEs triggered
+			by unsupported hardware/firmware features can result in
+                        GPE floodings that cannot be automatically disabled by
+                        the GPE dispatcher.
+			This facility can be used to prevent such uncontrolled
+			GPE floodings.
+			Format: <int>
+			Support masking of GPEs numbered from 0x00 to 0x7f.
+
 	acpi_no_auto_serialize	[HW,ACPI]
 			Disable auto-serialization of AML methods
 			AML control methods that contain the opcodes to create

Documentation/unaligned-memory-access.txt

@@ -151,7 +151,7 @@ bool ether_addr_equal(const u8 *addr1, const u8 *addr2)
 #else
 	const u16 *a = (const u16 *)addr1;
 	const u16 *b = (const u16 *)addr2;
-	return ((a[0] ^ b[0]) | (a[1] ^ b[1]) | (a[2] ^ b[2])) != 0;
+	return ((a[0] ^ b[0]) | (a[1] ^ b[1]) | (a[2] ^ b[2])) == 0;
 #endif
 }
 

Makefile

 VERSION = 4
 PATCHLEVEL = 10
 SUBLEVEL = 0
-EXTRAVERSION = -rc1
+EXTRAVERSION = -rc2
 NAME = Roaring Lionus
 
 # *DOCUMENTATION*

arch/arm64/include/asm/asm-uaccess.h

+#ifndef __ASM_ASM_UACCESS_H
+#define __ASM_ASM_UACCESS_H
+
+#include <asm/alternative.h>
+#include <asm/kernel-pgtable.h>
+#include <asm/sysreg.h>
+#include <asm/assembler.h>
+
+/*
+ * User access enabling/disabling macros.
+ */
+#ifdef CONFIG_ARM64_SW_TTBR0_PAN
+	.macro	__uaccess_ttbr0_disable, tmp1
+	mrs	\tmp1, ttbr1_el1		// swapper_pg_dir
+	add	\tmp1, \tmp1, #SWAPPER_DIR_SIZE	// reserved_ttbr0 at the end of swapper_pg_dir
+	msr	ttbr0_el1, \tmp1		// set reserved TTBR0_EL1
+	isb
+	.endm
+
+	.macro	__uaccess_ttbr0_enable, tmp1
+	get_thread_info \tmp1
+	ldr	\tmp1, [\tmp1, #TSK_TI_TTBR0]	// load saved TTBR0_EL1
+	msr	ttbr0_el1, \tmp1		// set the non-PAN TTBR0_EL1
+	isb
+	.endm
+
+	.macro	uaccess_ttbr0_disable, tmp1
+alternative_if_not ARM64_HAS_PAN
+	__uaccess_ttbr0_disable \tmp1
+alternative_else_nop_endif
+	.endm
+
+	.macro	uaccess_ttbr0_enable, tmp1, tmp2
+alternative_if_not ARM64_HAS_PAN
+	save_and_disable_irq \tmp2		// avoid preemption
+	__uaccess_ttbr0_enable \tmp1
+	restore_irq \tmp2
+alternative_else_nop_endif
+	.endm
+#else
+	.macro	uaccess_ttbr0_disable, tmp1
+	.endm
+
+	.macro	uaccess_ttbr0_enable, tmp1, tmp2
+	.endm
+#endif
+
+/*
+ * These macros are no-ops when UAO is present.
+ */
+	.macro	uaccess_disable_not_uao, tmp1
+	uaccess_ttbr0_disable \tmp1
+alternative_if ARM64_ALT_PAN_NOT_UAO
+	SET_PSTATE_PAN(1)
+alternative_else_nop_endif
+	.endm
+
+	.macro	uaccess_enable_not_uao, tmp1, tmp2
+	uaccess_ttbr0_enable \tmp1, \tmp2
+alternative_if ARM64_ALT_PAN_NOT_UAO
+	SET_PSTATE_PAN(0)
+alternative_else_nop_endif
+	.endm
+
+#endif

arch/arm64/include/asm/uaccess.h

@@ -22,8 +22,6 @@
 #include <asm/kernel-pgtable.h>
 #include <asm/sysreg.h>
 
-#ifndef __ASSEMBLY__
-
 /*
  * User space memory access functions
  */
@@ -424,66 +422,4 @@ extern long strncpy_from_user(char *dest, const char __user *src, long count);
 extern __must_check long strlen_user(const char __user *str);
 extern __must_check long strnlen_user(const char __user *str, long n);
 
-#else	/* __ASSEMBLY__ */
-
-#include <asm/assembler.h>
-
-/*
- * User access enabling/disabling macros.
- */
-#ifdef CONFIG_ARM64_SW_TTBR0_PAN
-	.macro	__uaccess_ttbr0_disable, tmp1
-	mrs	\tmp1, ttbr1_el1		// swapper_pg_dir
-	add	\tmp1, \tmp1, #SWAPPER_DIR_SIZE	// reserved_ttbr0 at the end of swapper_pg_dir
-	msr	ttbr0_el1, \tmp1		// set reserved TTBR0_EL1
-	isb
-	.endm
-
-	.macro	__uaccess_ttbr0_enable, tmp1
-	get_thread_info \tmp1
-	ldr	\tmp1, [\tmp1, #TSK_TI_TTBR0]	// load saved TTBR0_EL1
-	msr	ttbr0_el1, \tmp1		// set the non-PAN TTBR0_EL1
-	isb
-	.endm
-
-	.macro	uaccess_ttbr0_disable, tmp1
-alternative_if_not ARM64_HAS_PAN
-	__uaccess_ttbr0_disable \tmp1
-alternative_else_nop_endif
-	.endm
-
-	.macro	uaccess_ttbr0_enable, tmp1, tmp2
-alternative_if_not ARM64_HAS_PAN
-	save_and_disable_irq \tmp2		// avoid preemption
-	__uaccess_ttbr0_enable \tmp1
-	restore_irq \tmp2
-alternative_else_nop_endif
-	.endm
-#else
-	.macro	uaccess_ttbr0_disable, tmp1
-	.endm
-
-	.macro	uaccess_ttbr0_enable, tmp1, tmp2
-	.endm
-#endif
-
-/*
- * These macros are no-ops when UAO is present.
- */
-	.macro	uaccess_disable_not_uao, tmp1
-	uaccess_ttbr0_disable \tmp1
-alternative_if ARM64_ALT_PAN_NOT_UAO
-	SET_PSTATE_PAN(1)
-alternative_else_nop_endif
-	.endm
-
-	.macro	uaccess_enable_not_uao, tmp1, tmp2
-	uaccess_ttbr0_enable \tmp1, \tmp2
-alternative_if ARM64_ALT_PAN_NOT_UAO
-	SET_PSTATE_PAN(0)
-alternative_else_nop_endif
-	.endm
-
-#endif	/* __ASSEMBLY__ */
-
 #endif /* __ASM_UACCESS_H */

arch/arm64/kernel/entry.S

@@ -31,7 +31,7 @@
 #include <asm/memory.h>
 #include <asm/ptrace.h>
 #include <asm/thread_info.h>
-#include <linux/uaccess.h>
+#include <asm/asm-uaccess.h>
 #include <asm/unistd.h>
 
 /*

arch/arm64/lib/clear_user.S

@@ -17,7 +17,7 @@
  */
 #include <linux/linkage.h>
 
-#include <linux/uaccess.h>
+#include <asm/asm-uaccess.h>
 
 	.text
 

arch/arm64/lib/copy_from_user.S

@@ -17,7 +17,7 @@
 #include <linux/linkage.h>
 
 #include <asm/cache.h>
-#include <linux/uaccess.h>
+#include <asm/asm-uaccess.h>
 
 /*
  * Copy from user space to a kernel buffer (alignment handled by the hardware)

arch/arm64/lib/copy_in_user.S

@@ -19,7 +19,7 @@
 #include <linux/linkage.h>
 
 #include <asm/cache.h>
-#include <linux/uaccess.h>
+#include <asm/asm-uaccess.h>
 
 /*
  * Copy from user space to user space (alignment handled by the hardware)

arch/arm64/lib/copy_to_user.S

@@ -17,7 +17,7 @@
 #include <linux/linkage.h>
 
 #include <asm/cache.h>
-#include <linux/uaccess.h>
+#include <asm/asm-uaccess.h>
 
 /*
  * Copy to user space from a kernel buffer (alignment handled by the hardware)

arch/arm64/mm/cache.S

@@ -23,7 +23,7 @@
 #include <asm/assembler.h>
 #include <asm/cpufeature.h>
 #include <asm/alternative.h>
-#include <linux/uaccess.h>
+#include <asm/asm-uaccess.h>
 
 /*
  *	flush_icache_range(start,end)

arch/arm64/xen/hypercall.S

@@ -49,7 +49,7 @@
 
 #include <linux/linkage.h>
 #include <asm/assembler.h>
-#include <linux/uaccess.h>
+#include <asm/asm-uaccess.h>
 #include <xen/interface/xen.h>
 
 

arch/x86/include/asm/bitops.h

@@ -139,6 +139,19 @@ static __always_inline void __clear_bit(long nr, volatile unsigned long *addr)
 	asm volatile("btr %1,%0" : ADDR : "Ir" (nr));
 }
 
+static __always_inline bool clear_bit_unlock_is_negative_byte(long nr, volatile unsigned long *addr)
+{
+	bool negative;
+	asm volatile(LOCK_PREFIX "andb %2,%1\n\t"
+		CC_SET(s)
+		: CC_OUT(s) (negative), ADDR
+		: "ir" ((char) ~(1 << nr)) : "memory");
+	return negative;
+}
+
+// Let everybody know we have it
+#define clear_bit_unlock_is_negative_byte clear_bit_unlock_is_negative_byte
+
 /*
  * __clear_bit_unlock - Clears a bit in memory
  * @nr: Bit to clear

arch/x86/kernel/cpu/mcheck/mce_amd.c

@@ -1182,6 +1182,9 @@ static int threshold_create_bank(unsigned int cpu, unsigned int bank)
 	const char *name = get_name(bank, NULL);
 	int err = 0;
 
+	if (!dev)
+		return -ENODEV;
+
 	if (is_shared_bank(bank)) {
 		nb = node_to_amd_nb(amd_get_nb_id(cpu));
 

crypto/testmgr.c

@@ -1461,16 +1461,25 @@ static int test_acomp(struct crypto_acomp *tfm, struct comp_testvec *ctemplate,
 	for (i = 0; i < ctcount; i++) {
 		unsigned int dlen = COMP_BUF_SIZE;
 		int ilen = ctemplate[i].inlen;
+		void *input_vec;
 
+		input_vec = kmalloc(ilen, GFP_KERNEL);
+		if (!input_vec) {
+			ret = -ENOMEM;
+			goto out;
+		}
+
+		memcpy(input_vec, ctemplate[i].input, ilen);
 		memset(output, 0, dlen);
 		init_completion(&result.completion);
-		sg_init_one(&src, ctemplate[i].input, ilen);
+		sg_init_one(&src, input_vec, ilen);
 		sg_init_one(&dst, output, dlen);
 
 		req = acomp_request_alloc(tfm);
 		if (!req) {
 			pr_err("alg: acomp: request alloc failed for %s\n",
 			       algo);
+			kfree(input_vec);
 			ret = -ENOMEM;
 			goto out;
 		}
@@ -1483,6 +1492,7 @@ static int test_acomp(struct crypto_acomp *tfm, struct comp_testvec *ctemplate,
 		if (ret) {
 			pr_err("alg: acomp: compression failed on test %d for %s: ret=%d\n",
 			       i + 1, algo, -ret);
+			kfree(input_vec);
 			acomp_request_free(req);
 			goto out;
 		}
@@ -1491,6 +1501,7 @@ static int test_acomp(struct crypto_acomp *tfm, struct comp_testvec *ctemplate,
 			pr_err("alg: acomp: Compression test %d failed for %s: output len = %d\n",
 			       i + 1, algo, req->dlen);
 			ret = -EINVAL;
+			kfree(input_vec);
 			acomp_request_free(req);
 			goto out;
 		}
@@ -1500,26 +1511,37 @@ static int test_acomp(struct crypto_acomp *tfm, struct comp_testvec *ctemplate,
 			       i + 1, algo);
 			hexdump(output, req->dlen);
 			ret = -EINVAL;
+			kfree(input_vec);
 			acomp_request_free(req);
 			goto out;
 		}
 
+		kfree(input_vec);
 		acomp_request_free(req);
 	}
 
 	for (i = 0; i < dtcount; i++) {
 		unsigned int dlen = COMP_BUF_SIZE;
 		int ilen = dtemplate[i].inlen;
+		void *input_vec;
+
+		input_vec = kmalloc(ilen, GFP_KERNEL);
+		if (!input_vec) {
+			ret = -ENOMEM;
+			goto out;
+		}
 
+		memcpy(input_vec, dtemplate[i].input, ilen);
 		memset(output, 0, dlen);
 		init_completion(&result.completion);
-		sg_init_one(&src, dtemplate[i].input, ilen);
+		sg_init_one(&src, input_vec, ilen);
 		sg_init_one(&dst, output, dlen);
 
 		req = acomp_request_alloc(tfm);
 		if (!req) {
 			pr_err("alg: acomp: request alloc failed for %s\n",
 			       algo);
+			kfree(input_vec);
 			ret = -ENOMEM;
 			goto out;
 		}
@@ -1532,6 +1554,7 @@ static int test_acomp(struct crypto_acomp *tfm, struct comp_testvec *ctemplate,
 		if (ret) {
 			pr_err("alg: acomp: decompression failed on test %d for %s: ret=%d\n",
 			       i + 1, algo, -ret);
+			kfree(input_vec);
 			acomp_request_free(req);
 			goto out;
 		}
@@ -1540,6 +1563,7 @@ static int test_acomp(struct crypto_acomp *tfm, struct comp_testvec *ctemplate,
 			pr_err("alg: acomp: Decompression test %d failed for %s: output len = %d\n",
 			       i + 1, algo, req->dlen);
 			ret = -EINVAL;
+			kfree(input_vec);
 			acomp_request_free(req);
 			goto out;
 		}
@@ -1549,10 +1573,12 @@ static int test_acomp(struct crypto_acomp *tfm, struct comp_testvec *ctemplate,
 			       i + 1, algo);
 			hexdump(output, req->dlen);
 			ret = -EINVAL;
+			kfree(input_vec);
 			acomp_request_free(req);
 			goto out;
 		}
 
+		kfree(input_vec);
 		acomp_request_free(req);
 	}
 

drivers/acpi/acpi_watchdog.c

@@ -114,7 +114,7 @@ void __init acpi_watchdog_init(void)
 	pdev = platform_device_register_simple("wdat_wdt", PLATFORM_DEVID_NONE,
 					       resources, nresources);
 	if (IS_ERR(pdev))
-		pr_err("Failed to create platform device\n");
+		pr_err("Device creation failed: %ld\n", PTR_ERR(pdev));
 
 	kfree(resources);
 

drivers/acpi/internal.h

@@ -37,6 +37,7 @@ void acpi_amba_init(void);
 static inline void acpi_amba_init(void) {}
 #endif
 int acpi_sysfs_init(void);
+void acpi_gpe_apply_masked_gpes(void);
 void acpi_container_init(void);
 void acpi_memory_hotplug_init(void);
 #ifdef	CONFIG_ACPI_HOTPLUG_IOAPIC

drivers/acpi/scan.c

@@ -2074,6 +2074,7 @@ int __init acpi_scan_init(void)
 		}
 	}
 
+	acpi_gpe_apply_masked_gpes();
 	acpi_update_all_gpes();
 	acpi_ec_ecdt_start();
 

drivers/acpi/sysfs.c

@@ -708,6 +708,62 @@ static ssize_t counter_set(struct kobject *kobj,
 	return result ? result : size;
 }
 
+/*
+ * A Quirk Mechanism for GPE Flooding Prevention:
+ *
+ * Quirks may be needed to prevent GPE flooding on a specific GPE. The
+ * flooding typically cannot be detected and automatically prevented by
+ * ACPI_GPE_DISPATCH_NONE check because there is a _Lxx/_Exx prepared in
+ * the AML tables. This normally indicates a feature gap in Linux, thus
+ * instead of providing endless quirk tables, we provide a boot parameter
+ * for those who want this quirk. For example, if the users want to prevent
+ * the GPE flooding for GPE 00, they need to specify the following boot
+ * parameter:
+ *   acpi_mask_gpe=0x00
+ * The masking status can be modified by the following runtime controlling
+ * interface:
+ *   echo unmask > /sys/firmware/acpi/interrupts/gpe00
+ */
+
+/*
+ * Currently, the GPE flooding prevention only supports to mask the GPEs
+ * numbered from 00 to 7f.
+ */
+#define ACPI_MASKABLE_GPE_MAX	0x80
+
+static u64 __initdata acpi_masked_gpes;
+
+static int __init acpi_gpe_set_masked_gpes(char *val)
+{
+	u8 gpe;
+
+	if (kstrtou8(val, 0, &gpe) || gpe > ACPI_MASKABLE_GPE_MAX)
+		return -EINVAL;
+	acpi_masked_gpes |= ((u64)1<<gpe);
+
+	return 1;
+}
+__setup("acpi_mask_gpe=", acpi_gpe_set_masked_gpes);
+
+void __init acpi_gpe_apply_masked_gpes(void)
+{
+	acpi_handle handle;
+	acpi_status status;
+	u8 gpe;
+
+	for (gpe = 0;
+	     gpe < min_t(u8, ACPI_MASKABLE_GPE_MAX, acpi_current_gpe_count);
+	     gpe++) {
+		if (acpi_masked_gpes & ((u64)1<<gpe)) {
+			status = acpi_get_gpe_device(gpe, &handle);
+			if (ACPI_SUCCESS(status)) {
+				pr_info("Masking GPE 0x%x.\n", gpe);
+				(void)acpi_mask_gpe(handle, gpe, TRUE);
+			}
+		}
+	}
+}
+
 void acpi_irq_stats_init(void)
 {
 	acpi_status status;

drivers/crypto/marvell/cesa.h

@@ -273,7 +273,8 @@ struct mv_cesa_op_ctx {
 #define CESA_TDMA_SRC_IN_SRAM			BIT(30)
 #define CESA_TDMA_END_OF_REQ			BIT(29)
 #define CESA_TDMA_BREAK_CHAIN			BIT(28)
-#define CESA_TDMA_TYPE_MSK			GENMASK(27, 0)
+#define CESA_TDMA_SET_STATE			BIT(27)
+#define CESA_TDMA_TYPE_MSK			GENMASK(26, 0)
 #define CESA_TDMA_DUMMY				0
 #define CESA_TDMA_DATA				1
 #define CESA_TDMA_OP				2

drivers/crypto/marvell/hash.c

@@ -280,13 +280,32 @@ static void mv_cesa_ahash_std_prepare(struct ahash_request *req)
 	sreq->offset = 0;
 }
 
+static void mv_cesa_ahash_dma_step(struct ahash_request *req)
+{
+	struct mv_cesa_ahash_req *creq = ahash_request_ctx(req);
+	struct mv_cesa_req *base = &creq->base;
+
+	/* We must explicitly set the digest state. */
+	if (base->chain.first->flags & CESA_TDMA_SET_STATE) {
+		struct mv_cesa_engine *engine = base->engine;
+		int i;
+
+		/* Set the hash state in the IVDIG regs. */
+		for (i = 0; i < ARRAY_SIZE(creq->state); i++)
+			writel_relaxed(creq->state[i], engine->regs +
+				       CESA_IVDIG(i));
+	}
+
+	mv_cesa_dma_step(base);
+}
+
 static void mv_cesa_ahash_step(struct crypto_async_request *req)
 {
 	struct ahash_request *ahashreq = ahash_request_cast(req);
 	struct mv_cesa_ahash_req *creq = ahash_request_ctx(ahashreq);
 
 	if (mv_cesa_req_get_type(&creq->base) == CESA_DMA_REQ)
-		mv_cesa_dma_step(&creq->base);
+		mv_cesa_ahash_dma_step(ahashreq);
 	else
 		mv_cesa_ahash_std_step(ahashreq);
 }
@@ -584,12 +603,16 @@ static int mv_cesa_ahash_dma_req_init(struct ahash_request *req)
 	struct mv_cesa_ahash_dma_iter iter;
 	struct mv_cesa_op_ctx *op = NULL;
 	unsigned int frag_len;
+	bool set_state = false;
 	int ret;
 	u32 type;
 
 	basereq->chain.first = NULL;
 	basereq->chain.last = NULL;
 
+	if (!mv_cesa_mac_op_is_first_frag(&creq->op_tmpl))
+		set_state = true;
+
 	if (creq->src_nents) {
 		ret = dma_map_sg(cesa_dev->dev, req->src, creq->src_nents,
 				 DMA_TO_DEVICE);
@@ -683,6 +706,15 @@ static int mv_cesa_ahash_dma_req_init(struct ahash_request *req)
 	if (type != CESA_TDMA_RESULT)
 		basereq->chain.last->flags |= CESA_TDMA_BREAK_CHAIN;
 
+	if (set_state) {
+		/*
+		 * Put the CESA_TDMA_SET_STATE flag on the first tdma desc to
+		 * let the step logic know that the IVDIG registers should be
+		 * explicitly set before launching a TDMA chain.
+		 */
+		basereq->chain.first->flags |= CESA_TDMA_SET_STATE;
+	}
+
 	return 0;
 
 err_free_tdma:

drivers/crypto/marvell/tdma.c

@@ -109,7 +109,14 @@ void mv_cesa_tdma_chain(struct mv_cesa_engine *engine,
 		last->next = dreq->chain.first;
 		engine->chain.last = dreq->chain.last;
 
-		if (!(last->flags & CESA_TDMA_BREAK_CHAIN))
+		/*
+		 * Break the DMA chain if the CESA_TDMA_BREAK_CHAIN is set on
+		 * the last element of the current chain, or if the request
+		 * being queued needs the IV regs to be set before lauching
+		 * the request.
+		 */
+		if (!(last->flags & CESA_TDMA_BREAK_CHAIN) &&
+		    !(dreq->chain.first->flags & CESA_TDMA_SET_STATE))
 			last->next_dma = dreq->chain.first->cur_dma;
 	}
 }

drivers/iommu/dmar.c

@@ -903,8 +903,10 @@ int __init detect_intel_iommu(void)
 		x86_init.iommu.iommu_init = intel_iommu_init;
 #endif
 
-	acpi_put_table(dmar_tbl);
-	dmar_tbl = NULL;
+	if (dmar_tbl) {
+		acpi_put_table(dmar_tbl);
+		dmar_tbl = NULL;
+	}
 	up_write(&dmar_global_lock);
 
 	return ret ? 1 : -ENODEV;

drivers/net/ethernet/korina.c

@@ -900,10 +900,10 @@ static void korina_restart_task(struct work_struct *work)
 				DMA_STAT_DONE | DMA_STAT_HALT | DMA_STAT_ERR,
 				&lp->rx_dma_regs->dmasm);
 
-	korina_free_ring(dev);
-
 	napi_disable(&lp->napi);
 
+	korina_free_ring(dev);
+
 	if (korina_init(dev) < 0) {
 		printk(KERN_ERR "%s: cannot restart device\n", dev->name);
 		return;
@@ -1064,12 +1064,12 @@ static int korina_close(struct net_device *dev)
 	tmp = tmp | DMA_STAT_DONE | DMA_STAT_HALT | DMA_STAT_ERR;
 	writel(tmp, &lp->rx_dma_regs->dmasm);
 
-	korina_free_ring(dev);
-
 	napi_disable(&lp->napi);
 
 	cancel_work_sync(&lp->restart_task);
 
+	korina_free_ring(dev);
+
 	free_irq(lp->rx_irq, dev);
 	free_irq(lp->tx_irq, dev);
 	free_irq(lp->ovr_irq, dev);

drivers/net/ethernet/mellanox/mlx4/en_netdev.c

@@ -1638,7 +1638,8 @@ int mlx4_en_start_port(struct net_device *dev)
 
 	/* Configure tx cq's and rings */
 	for (t = 0 ; t < MLX4_EN_NUM_TX_TYPES; t++) {
-		u8 num_tx_rings_p_up = t == TX ? priv->num_tx_rings_p_up : 1;
+		u8 num_tx_rings_p_up = t == TX ?
+			priv->num_tx_rings_p_up : priv->tx_ring_num[t];
 
 		for (i = 0; i < priv->tx_ring_num[t]; i++) {
 			/* Configure cq */

drivers/net/ethernet/realtek/r8169.c

@@ -326,6 +326,7 @@ enum cfg_version {
 static const struct pci_device_id rtl8169_pci_tbl[] = {
 	{ PCI_DEVICE(PCI_VENDOR_ID_REALTEK,	0x8129), 0, 0, RTL_CFG_0 },
 	{ PCI_DEVICE(PCI_VENDOR_ID_REALTEK,	0x8136), 0, 0, RTL_CFG_2 },
+	{ PCI_DEVICE(PCI_VENDOR_ID_REALTEK,	0x8161), 0, 0, RTL_CFG_1 },
 	{ PCI_DEVICE(PCI_VENDOR_ID_REALTEK,	0x8167), 0, 0, RTL_CFG_0 },
 	{ PCI_DEVICE(PCI_VENDOR_ID_REALTEK,	0x8168), 0, 0, RTL_CFG_1 },
 	{ PCI_DEVICE(PCI_VENDOR_ID_REALTEK,	0x8169), 0, 0, RTL_CFG_0 },

drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c

@@ -116,7 +116,7 @@ static int stmmac_mdio_write(struct mii_bus *bus, int phyaddr, int phyreg,
 	unsigned int mii_address = priv->hw->mii.addr;
 	unsigned int mii_data = priv->hw->mii.data;
 
-	u32 value = MII_WRITE | MII_BUSY;
+	u32 value = MII_BUSY;
 
 	value |= (phyaddr << priv->hw->mii.addr_shift)
 		& priv->hw->mii.addr_mask;
@@ -126,6 +126,8 @@ static int stmmac_mdio_write(struct mii_bus *bus, int phyaddr, int phyreg,
 		& priv->hw->mii.clk_csr_mask;
 	if (priv->plat->has_gmac4)
 		value |= MII_GMAC4_WRITE;
+	else
+		value |= MII_WRITE;
 
 	/* Wait until any existing MII operation is complete */
 	if (stmmac_mdio_busy_wait(priv->ioaddr, mii_address))

drivers/net/ipvlan/ipvlan.h

@@ -99,6 +99,11 @@ struct ipvl_port {
 	int			count;
 };
 
+struct ipvl_skb_cb {
+	bool tx_pkt;
+};
+#define IPVL_SKB_CB(_skb) ((struct ipvl_skb_cb *)&((_skb)->cb[0]))
+
 static inline struct ipvl_port *ipvlan_port_get_rcu(const struct net_device *d)
 {
 	return rcu_dereference(d->rx_handler_data);

drivers/net/ipvlan/ipvlan_core.c

@@ -198,7 +198,7 @@ void ipvlan_process_multicast(struct work_struct *work)
 	unsigned int mac_hash;
 	int ret;
 	u8 pkt_type;
-	bool hlocal, dlocal;
+	bool tx_pkt;
 
 	__skb_queue_head_init(&list);
 
@@ -207,8 +207,11 @@ void ipvlan_process_multicast(struct work_struct *work)
 	spin_unlock_bh(&port->backlog.lock);
 
 	while ((skb = __skb_dequeue(&list)) != NULL) {
+		struct net_device *dev = skb->dev;
+		bool consumed = false;
+
 		ethh = eth_hdr(skb);
-		hlocal = ether_addr_equal(ethh->h_source, port->dev->dev_addr);
+		tx_pkt = IPVL_SKB_CB(skb)->tx_pkt;
 		mac_hash = ipvlan_mac_hash(ethh->h_dest);
 
 		if (ether_addr_equal(ethh->h_dest, port->dev->broadcast))
@@ -216,41 +219,45 @@ void ipvlan_process_multicast(struct work_struct *work)
 		else
 			pkt_type = PACKET_MULTICAST;
 
-		dlocal = false;
 		rcu_read_lock();
 		list_for_each_entry_rcu(ipvlan, &port->ipvlans, pnode) {
-			if (hlocal && (ipvlan->dev == skb->dev)) {
-				dlocal = true;
+			if (tx_pkt && (ipvlan->dev == skb->dev))
 				continue;
-			}
 			if (!test_bit(mac_hash, ipvlan->mac_filters))
 				continue;
-
+			if (!(ipvlan->dev->flags & IFF_UP))
+				continue;
 			ret = NET_RX_DROP;
 			len = skb->len + ETH_HLEN;
 			nskb = skb_clone(skb, GFP_ATOMIC);
-			if (!nskb)
-				goto acct;
-
-			nskb->pkt_type = pkt_type;
-			nskb->dev = ipvlan->dev;
-			if (hlocal)
-				ret = dev_forward_skb(ipvlan->dev, nskb);
-			else
-				ret = netif_rx(nskb);
-acct:
+			local_bh_disable();
+			if (nskb) {
+				consumed = true;
+				nskb->pkt_type = pkt_type;
+				nskb->dev = ipvlan->dev;
+				if (tx_pkt)
+					ret = dev_forward_skb(ipvlan->dev, nskb);
+				else
+					ret = netif_rx(nskb);
+			}
 			ipvlan_count_rx(ipvlan, len, ret == NET_RX_SUCCESS, true);
+			local_bh_enable();
 		}
 		rcu_read_unlock();
 
-		if (dlocal) {
+		if (tx_pkt) {
 			/* If the packet originated here, send it out. */
 			skb->dev = port->dev;
 			skb->pkt_type = pkt_type;
 			dev_queue_xmit(skb);
 		} else {
-			kfree_skb(skb);
+			if (consumed)
+				consume_skb(skb);
+			else
+				kfree_skb(skb);
 		}
+		if (dev)
+			dev_put(dev);
 	}
 }
 
@@ -470,15 +477,24 @@ static int ipvlan_process_outbound(struct sk_buff *skb)
 }
 
 static void ipvlan_multicast_enqueue(struct ipvl_port *port,
-				     struct sk_buff *skb)
+				     struct sk_buff *skb, bool tx_pkt)
 {
 	if (skb->protocol == htons(ETH_P_PAUSE)) {
 		kfree_skb(skb);
 		return;
 	}
 
+	/* Record that the deferred packet is from TX or RX path. By
+	 * looking at mac-addresses on packet will lead to erronus decisions.
+	 * (This would be true for a loopback-mode on master device or a
+	 * hair-pin mode of the switch.)
+	 */
+	IPVL_SKB_CB(skb)->tx_pkt = tx_pkt;
+
 	spin_lock(&port->backlog.lock);
 	if (skb_queue_len(&port->backlog) < IPVLAN_QBACKLOG_LIMIT) {
+		if (skb->dev)
+			dev_hold(skb->dev);
 		__skb_queue_tail(&port->backlog, skb);
 		spin_unlock(&port->backlog.lock);
 		schedule_work(&port->wq);
@@ -537,7 +553,7 @@ static int ipvlan_xmit_mode_l2(struct sk_buff *skb, struct net_device *dev)
 
 	} else if (is_multicast_ether_addr(eth->h_dest)) {
 		ipvlan_skb_crossing_ns(skb, NULL);
-		ipvlan_multicast_enqueue(ipvlan->port, skb);
+		ipvlan_multicast_enqueue(ipvlan->port, skb, true);
 		return NET_XMIT_SUCCESS;
 	}
 
@@ -634,7 +650,7 @@ static rx_handler_result_t ipvlan_handle_mode_l2(struct sk_buff **pskb,
 			 */
 			if (nskb) {
 				ipvlan_skb_crossing_ns(nskb, NULL);
-				ipvlan_multicast_enqueue(port, nskb);
+				ipvlan_multicast_enqueue(port, nskb, false);
 			}
 		}
 	} else {

drivers/net/ipvlan/ipvlan_main.c

@@ -135,6 +135,7 @@ static int ipvlan_port_create(struct net_device *dev)
 static void ipvlan_port_destroy(struct net_device *dev)
 {
 	struct ipvl_port *port = ipvlan_port_get_rtnl(dev);
+	struct sk_buff *skb;
 
 	dev->priv_flags &= ~IFF_IPVLAN_MASTER;
 	if (port->mode == IPVLAN_MODE_L3S) {
@@ -144,7 +145,11 @@ static void ipvlan_port_destroy(struct net_device *dev)
 	}
 	netdev_rx_handler_unregister(dev);
 	cancel_work_sync(&port->wq);
-	__skb_queue_purge(&port->backlog);
+	while ((skb = __skb_dequeue(&port->backlog)) != NULL) {
+		if (skb->dev)
+			dev_put(skb->dev);
+		kfree_skb(skb);
+	}
 	kfree(port);
 }
 

fs/dax.c

@@ -451,16 +451,37 @@ void dax_wake_mapping_entry_waiter(struct address_space *mapping,
 		__wake_up(wq, TASK_NORMAL, wake_all ? 0 : 1, &key);
 }
 
+static int __dax_invalidate_mapping_entry(struct address_space *mapping,
+					  pgoff_t index, bool trunc)
+{
+	int ret = 0;
+	void *entry;
+	struct radix_tree_root *page_tree = &mapping->page_tree;
+
+	spin_lock_irq(&mapping->tree_lock);
+	entry = get_unlocked_mapping_entry(mapping, index, NULL);
+	if (!entry || !radix_tree_exceptional_entry(entry))
+		goto out;
+	if (!trunc &&
+	    (radix_tree_tag_get(page_tree, index, PAGECACHE_TAG_DIRTY) ||
+	     radix_tree_tag_get(page_tree, index, PAGECACHE_TAG_TOWRITE)))
+		goto out;
+	radix_tree_delete(page_tree, index);
+	mapping->nrexceptional--;
+	ret = 1;
+out:
+	put_unlocked_mapping_entry(mapping, index, entry);
+	spin_unlock_irq(&mapping->tree_lock);
+	return ret;
+}
 /*
  * Delete exceptional DAX entry at @index from @mapping. Wait for radix tree
  * entry to get unlocked before deleting it.
  */
 int dax_delete_mapping_entry(struct address_space *mapping, pgoff_t index)
 {
-	void *entry;
+	int ret = __dax_invalidate_mapping_entry(mapping, index, true);
 
-	spin_lock_irq(&mapping->tree_lock);
-	entry = get_unlocked_mapping_entry(mapping, index, NULL);
 	/*
 	 * This gets called from truncate / punch_hole path. As such, the caller
 	 * must hold locks protecting against concurrent modifications of the
@@ -468,16 +489,46 @@ int dax_delete_mapping_entry(struct address_space *mapping, pgoff_t index)
 	 * caller has seen exceptional entry for this index, we better find it
 	 * at that index as well...
 	 */
-	if (WARN_ON_ONCE(!entry || !radix_tree_exceptional_entry(entry))) {
-		spin_unlock_irq(&mapping->tree_lock);
-		return 0;
-	}
-	radix_tree_delete(&mapping->page_tree, index);
+	WARN_ON_ONCE(!ret);
+	return ret;
+}
+
+/*
+ * Invalidate exceptional DAX entry if easily possible. This handles DAX
+ * entries for invalidate_inode_pages() so we evict the entry only if we can
+ * do so without blocking.
+ */
+int dax_invalidate_mapping_entry(struct address_space *mapping, pgoff_t index)
+{
+	int ret = 0;
+	void *entry, **slot;
+	struct radix_tree_root *page_tree = &mapping->page_tree;
+
+	spin_lock_irq(&mapping->tree_lock);
+	entry = __radix_tree_lookup(page_tree, index, NULL, &slot);
+	if (!entry || !radix_tree_exceptional_entry(entry) ||
+	    slot_locked(mapping, slot))
+		goto out;
+	if (radix_tree_tag_get(page_tree, index, PAGECACHE_TAG_DIRTY) ||
+	    radix_tree_tag_get(page_tree, index, PAGECACHE_TAG_TOWRITE))
+		goto out;
+	radix_tree_delete(page_tree, index);
 	mapping->nrexceptional--;
+	ret = 1;
+out:
 	spin_unlock_irq(&mapping->tree_lock);
-	dax_wake_mapping_entry_waiter(mapping, index, entry, true);
+	if (ret)
+		dax_wake_mapping_entry_waiter(mapping, index, entry, true);
+	return ret;
+}
 
-	return 1;
+/*
+ * Invalidate exceptional DAX entry if it is clean.
+ */
+int dax_invalidate_mapping_entry_sync(struct address_space *mapping,
+				      pgoff_t index)
+{
+	return __dax_invalidate_mapping_entry(mapping, index, false);
 }
 
 /*
@@ -488,15 +539,16 @@ int dax_delete_mapping_entry(struct address_space *mapping, pgoff_t index)
  * otherwise it will simply fall out of the page cache under memory
  * pressure without ever having been dirtied.
  */
-static int dax_load_hole(struct address_space *mapping, void *entry,
+static int dax_load_hole(struct address_space *mapping, void **entry,
 			 struct vm_fault *vmf)
 {
 	struct page *page;
+	int ret;
 
 	/* Hole page already exists? Return it...  */
-	if (!radix_tree_exceptional_entry(entry)) {
-		vmf->page = entry;
-		return VM_FAULT_LOCKED;
+	if (!radix_tree_exceptional_entry(*entry)) {
+		page = *entry;
+		goto out;
 	}
 
 	/* This will replace locked radix tree entry with a hole page */
@@ -504,8 +556,17 @@ static int dax_load_hole(struct address_space *mapping, void *entry,
 				   vmf->gfp_mask | __GFP_ZERO);
 	if (!page)
 		return VM_FAULT_OOM;
+ out:
 	vmf->page = page;
-	return VM_FAULT_LOCKED;
+	ret = finish_fault(vmf);
+	vmf->page = NULL;
+	*entry = page;
+	if (!ret) {
+		/* Grab reference for PTE that is now referencing the page */
+		get_page(page);
+		return VM_FAULT_NOPAGE;
+	}
+	return ret;
 }
 
 static int copy_user_dax(struct block_device *bdev, sector_t sector, size_t size,
@@ -934,6 +995,17 @@ dax_iomap_actor(struct inode *inode, loff_t pos, loff_t length, void *data,
 	if (WARN_ON_ONCE(iomap->type != IOMAP_MAPPED))
 		return -EIO;
 
+	/*
+	 * Write can allocate block for an area which has a hole page mapped
+	 * into page tables. We have to tear down these mappings so that data
+	 * written by write(2) is visible in mmap.
+	 */
+	if ((iomap->flags & IOMAP_F_NEW) && inode->i_mapping->nrpages) {
+		invalidate_inode_pages2_range(inode->i_mapping,
+					      pos >> PAGE_SHIFT,
+					      (end - 1) >> PAGE_SHIFT);
+	}
+
 	while (pos < end) {
 		unsigned offset = pos & (PAGE_SIZE - 1);
 		struct blk_dax_ctl dax = { 0 };
@@ -992,23 +1064,6 @@ dax_iomap_rw(struct kiocb *iocb, struct iov_iter *iter,
 	if (iov_iter_rw(iter) == WRITE)
 		flags |= IOMAP_WRITE;
 
-	/*
-	 * Yes, even DAX files can have page cache attached to them:  A zeroed
-	 * page is inserted into the pagecache when we have to serve a write
-	 * fault on a hole.  It should never be dirtied and can simply be
-	 * dropped from the pagecache once we get real data for the page.
-	 *
-	 * XXX: This is racy against mmap, and there's nothing we can do about
-	 * it. We'll eventually need to shift this down even further so that
-	 * we can check if we allocated blocks over a hole first.
-	 */
-	if (mapping->nrpages) {
-		ret = invalidate_inode_pages2_range(mapping,
-				pos >> PAGE_SHIFT,
-				(pos + iov_iter_count(iter) - 1) >> PAGE_SHIFT);
-		WARN_ON_ONCE(ret);
-	}
-
 	while (iov_iter_count(iter)) {
 		ret = iomap_apply(inode, pos, iov_iter_count(iter), flags, ops,
 				iter, dax_iomap_actor);
@@ -1023,6 +1078,15 @@ dax_iomap_rw(struct kiocb *iocb, struct iov_iter *iter,
 }
 EXPORT_SYMBOL_GPL(dax_iomap_rw);
 
+static int dax_fault_return(int error)
+{
+	if (error == 0)
+		return VM_FAULT_NOPAGE;
+	if (error == -ENOMEM)
+		return VM_FAULT_OOM;
+	return VM_FAULT_SIGBUS;
+}
+
 /**
  * dax_iomap_fault - handle a page fault on a DAX file
  * @vma: The virtual memory area where the fault occurred
@@ -1055,12 +1119,6 @@ int dax_iomap_fault(struct vm_area_struct *vma, struct vm_fault *vmf,
 	if (pos >= i_size_read(inode))
 		return VM_FAULT_SIGBUS;
 
-	entry = grab_mapping_entry(mapping, vmf->pgoff, 0);
-	if (IS_ERR(entry)) {
-		error = PTR_ERR(entry);
-		goto out;
-	}
-
 	if ((vmf->flags & FAULT_FLAG_WRITE) && !vmf->cow_page)
 		flags |= IOMAP_WRITE;
 
@@ -1071,9 +1129,15 @@ int dax_iomap_fault(struct vm_area_struct *vma, struct vm_fault *vmf,
 	 */
 	error = ops->iomap_begin(inode, pos, PAGE_SIZE, flags, &iomap);
 	if (error)
-		goto unlock_entry;
+		return dax_fault_return(error);
 	if (WARN_ON_ONCE(iomap.offset + iomap.length < pos + PAGE_SIZE)) {
-		error = -EIO;		/* fs corruption? */
+		vmf_ret = dax_fault_return(-EIO);	/* fs corruption? */
+		goto finish_iomap;
+	}
+
+	entry = grab_mapping_entry(mapping, vmf->pgoff, 0);
+	if (IS_ERR(entry)) {
+		vmf_ret = dax_fault_return(PTR_ERR(entry));
 		goto finish_iomap;
 	}
 
@@ -1096,13 +1160,13 @@ int dax_iomap_fault(struct vm_area_struct *vma, struct vm_fault *vmf,
 		}
 
 		if (error)
-			goto finish_iomap;
+			goto error_unlock_entry;
 
 		__SetPageUptodate(vmf->cow_page);
 		vmf_ret = finish_fault(vmf);
 		if (!vmf_ret)
 			vmf_ret = VM_FAULT_DONE_COW;
-		goto finish_iomap;
+		goto unlock_entry;
 	}
 
 	switch (iomap.type) {
@@ -1114,12 +1178,15 @@ int dax_iomap_fault(struct vm_area_struct *vma, struct vm_fault *vmf,
 		}
 		error = dax_insert_mapping(mapping, iomap.bdev, sector,
 				PAGE_SIZE, &entry, vma, vmf);
+		/* -EBUSY is fine, somebody else faulted on the same PTE */
+		if (error == -EBUSY)
+			error = 0;
 		break;
 	case IOMAP_UNWRITTEN:
 	case IOMAP_HOLE:
 		if (!(vmf->flags & FAULT_FLAG_WRITE)) {
-			vmf_ret = dax_load_hole(mapping, entry, vmf);
-			break;
+			vmf_ret = dax_load_hole(mapping, &entry, vmf);
+			goto unlock_entry;
 		}
 		/*FALLTHRU*/
 	default:
@@ -1128,31 +1195,25 @@ int dax_iomap_fault(struct vm_area_struct *vma, struct vm_fault *vmf,
 		break;
 	}
 
+ error_unlock_entry:
+	vmf_ret = dax_fault_return(error) | major;
+ unlock_entry:
+	put_locked_mapping_entry(mapping, vmf->pgoff, entry);
  finish_iomap:
 	if (ops->iomap_end) {
-		if (error || (vmf_ret & VM_FAULT_ERROR)) {
-			/* keep previous error */
-			ops->iomap_end(inode, pos, PAGE_SIZE, 0, flags,
-					&iomap);
-		} else {
-			error = ops->iomap_end(inode, pos, PAGE_SIZE,
-					PAGE_SIZE, flags, &iomap);
-		}
-	}
- unlock_entry:
-	if (vmf_ret != VM_FAULT_LOCKED || error)
-		put_locked_mapping_entry(mapping, vmf->pgoff, entry);
- out:
-	if (error == -ENOMEM)
-		return VM_FAULT_OOM | major;
-	/* -EBUSY is fine, somebody else faulted on the same PTE */
-	if (error < 0 && error != -EBUSY)
-		return VM_FAULT_SIGBUS | major;
-	if (vmf_ret) {
-		WARN_ON_ONCE(error); /* -EBUSY from ops->iomap_end? */
-		return vmf_ret;
+		int copied = PAGE_SIZE;
+
+		if (vmf_ret & VM_FAULT_ERROR)
+			copied = 0;
+		/*
+		 * The fault is done by now and there's no way back (other
+		 * thread may be already happily using PTE we have installed).
+		 * Just ignore error from ->iomap_end since we cannot do much
+		 * with it.
+		 */
+		ops->iomap_end(inode, pos, PAGE_SIZE, copied, flags, &iomap);
 	}
-	return VM_FAULT_NOPAGE | major;
+	return vmf_ret;
 }
 EXPORT_SYMBOL_GPL(dax_iomap_fault);
 
@@ -1276,16 +1337,6 @@ int dax_iomap_pmd_fault(struct vm_area_struct *vma, unsigned long address,
 	if ((pgoff | PG_PMD_COLOUR) > max_pgoff)
 		goto fallback;
 
-	/*
-	 * grab_mapping_entry() will make sure we get a 2M empty entry, a DAX
-	 * PMD or a HZP entry.  If it can't (because a 4k page is already in
-	 * the tree, for instance), it will return -EEXIST and we just fall
-	 * back to 4k entries.
-	 */
-	entry = grab_mapping_entry(mapping, pgoff, RADIX_DAX_PMD);
-	if (IS_ERR(entry))
-		goto fallback;
-
 	/*
 	 * Note that we don't use iomap_apply here.  We aren't doing I/O, only
 	 * setting up a mapping, so really we're using iomap_begin() as a way
@@ -1294,10 +1345,21 @@ int dax_iomap_pmd_fault(struct vm_area_struct *vma, unsigned long address,
 	pos = (loff_t)pgoff << PAGE_SHIFT;
 	error = ops->iomap_begin(inode, pos, PMD_SIZE, iomap_flags, &iomap);
 	if (error)
-		goto unlock_entry;
+		goto fallback;
+
 	if (iomap.offset + iomap.length < pos + PMD_SIZE)
 		goto finish_iomap;
 
+	/*
+	 * grab_mapping_entry() will make sure we get a 2M empty entry, a DAX
+	 * PMD or a HZP entry.  If it can't (because a 4k page is already in
+	 * the tree, for instance), it will return -EEXIST and we just fall
+	 * back to 4k entries.
+	 */
+	entry = grab_mapping_entry(mapping, pgoff, RADIX_DAX_PMD);
+	if (IS_ERR(entry))
+		goto finish_iomap;
+
 	vmf.pgoff = pgoff;
 	vmf.flags = flags;
 	vmf.gfp_mask = mapping_gfp_mask(mapping) | __GFP_IO;
@@ -1310,7 +1372,7 @@ int dax_iomap_pmd_fault(struct vm_area_struct *vma, unsigned long address,
 	case IOMAP_UNWRITTEN:
 	case IOMAP_HOLE:
 		if (WARN_ON_ONCE(write))
-			goto finish_iomap;
+			goto unlock_entry;
 		result = dax_pmd_load_hole(vma, pmd, &vmf, address, &iomap,
 				&entry);
 		break;
@@ -1319,20 +1381,23 @@ int dax_iomap_pmd_fault(struct vm_area_struct *vma, unsigned long address,
 		break;
 	}
 
+ unlock_entry:
+	put_locked_mapping_entry(mapping, pgoff, entry);
  finish_iomap:
 	if (ops->iomap_end) {
-		if (result == VM_FAULT_FALLBACK) {
-			ops->iomap_end(inode, pos, PMD_SIZE, 0, iomap_flags,
-					&iomap);
-		} else {
-			error = ops->iomap_end(inode, pos, PMD_SIZE, PMD_SIZE,
-					iomap_flags, &iomap);
-			if (error)
-				result = VM_FAULT_FALLBACK;
-		}
+		int copied = PMD_SIZE;
+
+		if (result == VM_FAULT_FALLBACK)
+			copied = 0;
+		/*
+		 * The fault is done by now and there's no way back (other
+		 * thread may be already happily using PMD we have installed).
+		 * Just ignore error from ->iomap_end since we cannot do much
+		 * with it.
+		 */
+		ops->iomap_end(inode, pos, PMD_SIZE, copied, iomap_flags,
+				&iomap);
 	}
- unlock_entry:
-	put_locked_mapping_entry(mapping, pgoff, entry);
  fallback:
 	if (result == VM_FAULT_FALLBACK) {
 		split_huge_pmd(vma, pmd, address);

fs/ext2/inode.c

@@ -751,9 +751,8 @@ static int ext2_get_blocks(struct inode *inode,
 			mutex_unlock(&ei->truncate_mutex);
 			goto cleanup;
 		}
-	} else {
-		*new = true;
 	}
+	*new = true;
 
 	ext2_splice_branch(inode, iblock, partial, indirect_blks, count);
 	mutex_unlock(&ei->truncate_mutex);

fs/ext4/file.c

@@ -258,7 +258,6 @@ ext4_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
 static int ext4_dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 {
 	int result;
-	handle_t *handle = NULL;
 	struct inode *inode = file_inode(vma->vm_file);
 	struct super_block *sb = inode->i_sb;
 	bool write = vmf->flags & FAULT_FLAG_WRITE;
@@ -266,24 +265,12 @@ static int ext4_dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 	if (write) {
 		sb_start_pagefault(sb);
 		file_update_time(vma->vm_file);
-		down_read(&EXT4_I(inode)->i_mmap_sem);
-		handle = ext4_journal_start_sb(sb, EXT4_HT_WRITE_PAGE,
-						EXT4_DATA_TRANS_BLOCKS(sb));
-	} else
-		down_read(&EXT4_I(inode)->i_mmap_sem);
-
-	if (IS_ERR(handle))
-		result = VM_FAULT_SIGBUS;
-	else
-		result = dax_iomap_fault(vma, vmf, &ext4_iomap_ops);
-
-	if (write) {
-		if (!IS_ERR(handle))
-			ext4_journal_stop(handle);
-		up_read(&EXT4_I(inode)->i_mmap_sem);
+	}
+	down_read(&EXT4_I(inode)->i_mmap_sem);
+	result = dax_iomap_fault(vma, vmf, &ext4_iomap_ops);
+	up_read(&EXT4_I(inode)->i_mmap_sem);
+	if (write)
 		sb_end_pagefault(sb);
-	} else
-		up_read(&EXT4_I(inode)->i_mmap_sem);
 
 	return result;
 }
@@ -292,7 +279,6 @@ static int ext4_dax_pmd_fault(struct vm_area_struct *vma, unsigned long addr,
 						pmd_t *pmd, unsigned int flags)
 {
 	int result;
-	handle_t *handle = NULL;
 	struct inode *inode = file_inode(vma->vm_file);
 	struct super_block *sb = inode->i_sb;
 	bool write = flags & FAULT_FLAG_WRITE;
@@ -300,27 +286,13 @@ static int ext4_dax_pmd_fault(struct vm_area_struct *vma, unsigned long addr,
 	if (write) {
 		sb_start_pagefault(sb);
 		file_update_time(vma->vm_file);
-		down_read(&EXT4_I(inode)->i_mmap_sem);
-		handle = ext4_journal_start_sb(sb, EXT4_HT_WRITE_PAGE,
-				ext4_chunk_trans_blocks(inode,
-							PMD_SIZE / PAGE_SIZE));
-	} else
-		down_read(&EXT4_I(inode)->i_mmap_sem);
-
-	if (IS_ERR(handle))
-		result = VM_FAULT_SIGBUS;
-	else {
-		result = dax_iomap_pmd_fault(vma, addr, pmd, flags,
-					     &ext4_iomap_ops);
 	}
-
-	if (write) {
-		if (!IS_ERR(handle))
-			ext4_journal_stop(handle);
-		up_read(&EXT4_I(inode)->i_mmap_sem);
+	down_read(&EXT4_I(inode)->i_mmap_sem);
+	result = dax_iomap_pmd_fault(vma, addr, pmd, flags,
+				     &ext4_iomap_ops);
+	up_read(&EXT4_I(inode)->i_mmap_sem);
+	if (write)
 		sb_end_pagefault(sb);
-	} else
-		up_read(&EXT4_I(inode)->i_mmap_sem);
 
 	return result;
 }

include/linux/dax.h

@@ -41,6 +41,9 @@ ssize_t dax_iomap_rw(struct kiocb *iocb, struct iov_iter *iter,
 int dax_iomap_fault(struct vm_area_struct *vma, struct vm_fault *vmf,
 			struct iomap_ops *ops);
 int dax_delete_mapping_entry(struct address_space *mapping, pgoff_t index);
+int dax_invalidate_mapping_entry(struct address_space *mapping, pgoff_t index);
+int dax_invalidate_mapping_entry_sync(struct address_space *mapping,
+				      pgoff_t index);
 void dax_wake_mapping_entry_waiter(struct address_space *mapping,
 		pgoff_t index, void *entry, bool wake_all);
 

include/linux/filter.h

@@ -610,7 +610,6 @@ bool bpf_helper_changes_pkt_data(void *func);
 struct bpf_prog *bpf_patch_insn_single(struct bpf_prog *prog, u32 off,
 				       const struct bpf_insn *patch, u32 len);
 void bpf_warn_invalid_xdp_action(u32 act);
-void bpf_warn_invalid_xdp_buffer(void);
 
 #ifdef CONFIG_BPF_JIT
 extern int bpf_jit_enable;

include/linux/page-flags.h

@@ -73,13 +73,13 @@
  */
 enum pageflags {
 	PG_locked,		/* Page is locked. Don't touch. */
-	PG_waiters,		/* Page has waiters, check its waitqueue */
 	PG_error,
 	PG_referenced,
 	PG_uptodate,
 	PG_dirty,
 	PG_lru,
 	PG_active,
+	PG_waiters,		/* Page has waiters, check its waitqueue. Must be bit #7 and in the same byte as "PG_locked" */
 	PG_slab,
 	PG_owner_priv_1,	/* Owner use. If pagecache, fs may use*/
 	PG_arch_1,

include/net/netns/ipv4.h

@@ -110,6 +110,7 @@ struct netns_ipv4 {
 	int sysctl_tcp_orphan_retries;
 	int sysctl_tcp_fin_timeout;
 	unsigned int sysctl_tcp_notsent_lowat;
+	int sysctl_tcp_tw_reuse;
 
 	int sysctl_igmp_max_memberships;
 	int sysctl_igmp_max_msf;

include/net/tcp.h

@@ -252,7 +252,6 @@ extern int sysctl_tcp_wmem[3];
 extern int sysctl_tcp_rmem[3];
 extern int sysctl_tcp_app_win;
 extern int sysctl_tcp_adv_win_scale;
-extern int sysctl_tcp_tw_reuse;
 extern int sysctl_tcp_frto;
 extern int sysctl_tcp_low_latency;
 extern int sysctl_tcp_nometrics_save;

kernel/cpu.c

@@ -1471,6 +1471,7 @@ int __cpuhp_setup_state(enum cpuhp_state state,
 			bool multi_instance)
 {
 	int cpu, ret = 0;
+	bool dynstate;
 
 	if (cpuhp_cb_check(state) || !name)
 		return -EINVAL;
@@ -1480,6 +1481,12 @@ int __cpuhp_setup_state(enum cpuhp_state state,
 	ret = cpuhp_store_callbacks(state, name, startup, teardown,
 				    multi_instance);
 
+	dynstate = state == CPUHP_AP_ONLINE_DYN;
+	if (ret > 0 && dynstate) {
+		state = ret;
+		ret = 0;
+	}
+
 	if (ret || !invoke || !startup)
 		goto out;
 
@@ -1508,7 +1515,7 @@ int __cpuhp_setup_state(enum cpuhp_state state,
 	 * If the requested state is CPUHP_AP_ONLINE_DYN, return the
 	 * dynamically allocated state in case of success.
 	 */
-	if (!ret && state == CPUHP_AP_ONLINE_DYN)
+	if (!ret && dynstate)
 		return state;
 	return ret;
 }

mm/filemap.c

@@ -912,6 +912,29 @@ void add_page_wait_queue(struct page *page, wait_queue_t *waiter)
 }
 EXPORT_SYMBOL_GPL(add_page_wait_queue);
 
+#ifndef clear_bit_unlock_is_negative_byte
+
+/*
+ * PG_waiters is the high bit in the same byte as PG_lock.
+ *
+ * On x86 (and on many other architectures), we can clear PG_lock and
+ * test the sign bit at the same time. But if the architecture does
+ * not support that special operation, we just do this all by hand
+ * instead.
+ *
+ * The read of PG_waiters has to be after (or concurrently with) PG_locked
+ * being cleared, but a memory barrier should be unneccssary since it is
+ * in the same byte as PG_locked.
+ */
+static inline bool clear_bit_unlock_is_negative_byte(long nr, volatile void *mem)
+{
+	clear_bit_unlock(nr, mem);
+	/* smp_mb__after_atomic(); */
+	return test_bit(PG_waiters, mem);
+}
+
+#endif
+
 /**
  * unlock_page - unlock a locked page
  * @page: the page
@@ -921,16 +944,19 @@ EXPORT_SYMBOL_GPL(add_page_wait_queue);
  * mechanism between PageLocked pages and PageWriteback pages is shared.
  * But that's OK - sleepers in wait_on_page_writeback() just go back to sleep.
  *
- * The mb is necessary to enforce ordering between the clear_bit and the read
- * of the waitqueue (to avoid SMP races with a parallel wait_on_page_locked()).
+ * Note that this depends on PG_waiters being the sign bit in the byte
+ * that contains PG_locked - thus the BUILD_BUG_ON(). That allows us to
+ * clear the PG_locked bit and test PG_waiters at the same time fairly
+ * portably (architectures that do LL/SC can test any bit, while x86 can
+ * test the sign bit).
  */
 void unlock_page(struct page *page)
 {
+	BUILD_BUG_ON(PG_waiters != 7);
 	page = compound_head(page);
 	VM_BUG_ON_PAGE(!PageLocked(page), page);
-	clear_bit_unlock(PG_locked, &page->flags);
-	smp_mb__after_atomic();
-	wake_up_page(page, PG_locked);
+	if (clear_bit_unlock_is_negative_byte(PG_locked, &page->flags))
+		wake_up_page_bit(page, PG_locked);
 }
 EXPORT_SYMBOL(unlock_page);
 

mm/truncate.c

@@ -24,20 +24,12 @@
 #include <linux/rmap.h>
 #include "internal.h"
 
-static void clear_exceptional_entry(struct address_space *mapping,
-				    pgoff_t index, void *entry)
+static void clear_shadow_entry(struct address_space *mapping, pgoff_t index,
+			       void *entry)
 {
 	struct radix_tree_node *node;
 	void **slot;
 
-	/* Handled by shmem itself */
-	if (shmem_mapping(mapping))
-		return;
-
-	if (dax_mapping(mapping)) {
-		dax_delete_mapping_entry(mapping, index);
-		return;
-	}
 	spin_lock_irq(&mapping->tree_lock);
 	/*
 	 * Regular page slots are stabilized by the page lock even
@@ -55,6 +47,56 @@ static void clear_exceptional_entry(struct address_space *mapping,
 	spin_unlock_irq(&mapping->tree_lock);
 }
 
+/*
+ * Unconditionally remove exceptional entry. Usually called from truncate path.
+ */
+static void truncate_exceptional_entry(struct address_space *mapping,
+				       pgoff_t index, void *entry)
+{
+	/* Handled by shmem itself */
+	if (shmem_mapping(mapping))
+		return;
+
+	if (dax_mapping(mapping)) {
+		dax_delete_mapping_entry(mapping, index);
+		return;
+	}
+	clear_shadow_entry(mapping, index, entry);
+}
+
+/*
+ * Invalidate exceptional entry if easily possible. This handles exceptional
+ * entries for invalidate_inode_pages() so for DAX it evicts only unlocked and
+ * clean entries.
+ */
+static int invalidate_exceptional_entry(struct address_space *mapping,
+					pgoff_t index, void *entry)
+{
+	/* Handled by shmem itself */
+	if (shmem_mapping(mapping))
+		return 1;
+	if (dax_mapping(mapping))
+		return dax_invalidate_mapping_entry(mapping, index);
+	clear_shadow_entry(mapping, index, entry);
+	return 1;
+}
+
+/*
+ * Invalidate exceptional entry if clean. This handles exceptional entries for
+ * invalidate_inode_pages2() so for DAX it evicts only clean entries.
+ */
+static int invalidate_exceptional_entry2(struct address_space *mapping,
+					 pgoff_t index, void *entry)
+{
+	/* Handled by shmem itself */
+	if (shmem_mapping(mapping))
+		return 1;
+	if (dax_mapping(mapping))
+		return dax_invalidate_mapping_entry_sync(mapping, index);
+	clear_shadow_entry(mapping, index, entry);
+	return 1;
+}
+
 /**
  * do_invalidatepage - invalidate part or all of a page
  * @page: the page which is affected
@@ -262,7 +304,8 @@ void truncate_inode_pages_range(struct address_space *mapping,
 				break;
 
 			if (radix_tree_exceptional_entry(page)) {
-				clear_exceptional_entry(mapping, index, page);
+				truncate_exceptional_entry(mapping, index,
+							   page);
 				continue;
 			}
 
@@ -351,7 +394,8 @@ void truncate_inode_pages_range(struct address_space *mapping,
 			}
 
 			if (radix_tree_exceptional_entry(page)) {
-				clear_exceptional_entry(mapping, index, page);
+				truncate_exceptional_entry(mapping, index,
+							   page);
 				continue;
 			}
 
@@ -470,7 +514,8 @@ unsigned long invalidate_mapping_pages(struct address_space *mapping,
 				break;
 
 			if (radix_tree_exceptional_entry(page)) {
-				clear_exceptional_entry(mapping, index, page);
+				invalidate_exceptional_entry(mapping, index,
+							     page);
 				continue;
 			}
 
@@ -592,7 +637,9 @@ int invalidate_inode_pages2_range(struct address_space *mapping,
 				break;
 
 			if (radix_tree_exceptional_entry(page)) {
-				clear_exceptional_entry(mapping, index, page);
+				if (!invalidate_exceptional_entry2(mapping,
+								   index, page))
+					ret = -EBUSY;
 				continue;
 			}
 

net/core/filter.c

@@ -2972,12 +2972,6 @@ void bpf_warn_invalid_xdp_action(u32 act)
 }
 EXPORT_SYMBOL_GPL(bpf_warn_invalid_xdp_action);
 
-void bpf_warn_invalid_xdp_buffer(void)
-{
-	WARN_ONCE(1, "Illegal XDP buffer encountered, expect throughput degradation\n");
-}
-EXPORT_SYMBOL_GPL(bpf_warn_invalid_xdp_buffer);
-
 static u32 sk_filter_convert_ctx_access(enum bpf_access_type type, int dst_reg,
 					int src_reg, int ctx_off,
 					struct bpf_insn *insn_buf,

net/ipv4/sysctl_net_ipv4.c

@@ -432,13 +432,6 @@ static struct ctl_table ipv4_table[] = {
 		.extra1		= &tcp_adv_win_scale_min,
 		.extra2		= &tcp_adv_win_scale_max,
 	},
-	{
-		.procname	= "tcp_tw_reuse",
-		.data		= &sysctl_tcp_tw_reuse,
-		.maxlen		= sizeof(int),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec
-	},
 	{
 		.procname	= "tcp_frto",
 		.data		= &sysctl_tcp_frto,
@@ -960,6 +953,13 @@ static struct ctl_table ipv4_net_table[] = {
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec,
 	},
+	{
+		.procname	= "tcp_tw_reuse",
+		.data		= &init_net.ipv4.sysctl_tcp_tw_reuse,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec
+	},
 #ifdef CONFIG_IP_ROUTE_MULTIPATH
 	{
 		.procname	= "fib_multipath_use_neigh",

net/ipv4/tcp_ipv4.c

@@ -84,7 +84,6 @@
 #include <crypto/hash.h>
 #include <linux/scatterlist.h>
 
-int sysctl_tcp_tw_reuse __read_mostly;
 int sysctl_tcp_low_latency __read_mostly;
 
 #ifdef CONFIG_TCP_MD5SIG
@@ -120,7 +119,7 @@ int tcp_twsk_unique(struct sock *sk, struct sock *sktw, void *twp)
 	   and use initial timestamp retrieved from peer table.
 	 */
 	if (tcptw->tw_ts_recent_stamp &&
-	    (!twp || (sysctl_tcp_tw_reuse &&
+	    (!twp || (sock_net(sk)->ipv4.sysctl_tcp_tw_reuse &&
 			     get_seconds() - tcptw->tw_ts_recent_stamp > 1))) {
 		tp->write_seq = tcptw->tw_snd_nxt + 65535 + 2;
 		if (tp->write_seq == 0)
@@ -2456,6 +2455,7 @@ static int __net_init tcp_sk_init(struct net *net)
 	net->ipv4.sysctl_tcp_orphan_retries = 0;
 	net->ipv4.sysctl_tcp_fin_timeout = TCP_FIN_TIMEOUT;
 	net->ipv4.sysctl_tcp_notsent_lowat = UINT_MAX;
+	net->ipv4.sysctl_tcp_tw_reuse = 0;
 
 	return 0;
 fail:

net/openvswitch/datapath.c

@@ -606,7 +606,6 @@ static int ovs_packet_cmd_execute(struct sk_buff *skb, struct genl_info *info)
 	rcu_assign_pointer(flow->sf_acts, acts);
 	packet->priority = flow->key.phy.priority;
 	packet->mark = flow->key.phy.skb_mark;
-	packet->protocol = flow->key.eth.type;
 
 	rcu_read_lock();
 	dp = get_dp_rcu(net, ovs_header->dp_ifindex);

net/openvswitch/flow.c

@@ -312,7 +312,8 @@ static bool icmp6hdr_ok(struct sk_buff *skb)
  * Returns 0 if it encounters a non-vlan or incomplete packet.
  * Returns 1 after successfully parsing vlan tag.
  */
-static int parse_vlan_tag(struct sk_buff *skb, struct vlan_head *key_vh)
+static int parse_vlan_tag(struct sk_buff *skb, struct vlan_head *key_vh,
+			  bool untag_vlan)
 {
 	struct vlan_head *vh = (struct vlan_head *)skb->data;
 
@@ -330,7 +331,20 @@ static int parse_vlan_tag(struct sk_buff *skb, struct vlan_head *key_vh)
 	key_vh->tci = vh->tci | htons(VLAN_TAG_PRESENT);
 	key_vh->tpid = vh->tpid;
 
-	__skb_pull(skb, sizeof(struct vlan_head));
+	if (unlikely(untag_vlan)) {
+		int offset = skb->data - skb_mac_header(skb);
+		u16 tci;
+		int err;
+
+		__skb_push(skb, offset);
+		err = __skb_vlan_pop(skb, &tci);
+		__skb_pull(skb, offset);
+		if (err)
+			return err;
+		__vlan_hwaccel_put_tag(skb, key_vh->tpid, tci);
+	} else {
+		__skb_pull(skb, sizeof(struct vlan_head));
+	}
 	return 1;
 }
 
@@ -351,13 +365,13 @@ static int parse_vlan(struct sk_buff *skb, struct sw_flow_key *key)
 		key->eth.vlan.tpid = skb->vlan_proto;
 	} else {
 		/* Parse outer vlan tag in the non-accelerated case. */
-		res = parse_vlan_tag(skb, &key->eth.vlan);
+		res = parse_vlan_tag(skb, &key->eth.vlan, true);
 		if (res <= 0)
 			return res;
 	}
 
 	/* Parse inner vlan tag. */
-	res = parse_vlan_tag(skb, &key->eth.cvlan);
+	res = parse_vlan_tag(skb, &key->eth.cvlan, false);
 	if (res <= 0)
 		return res;
 
@@ -800,29 +814,15 @@ int ovs_flow_key_extract_userspace(struct net *net, const struct nlattr *attr,
 	if (err)
 		return err;
 
-	if (ovs_key_mac_proto(key) == MAC_PROTO_NONE) {
-		/* key_extract assumes that skb->protocol is set-up for
-		 * layer 3 packets which is the case for other callers,
-		 * in particular packets recieved from the network stack.
-		 * Here the correct value can be set from the metadata
-		 * extracted above.
-		 */
-		skb->protocol = key->eth.type;
-	} else {
-		struct ethhdr *eth;
-
-		skb_reset_mac_header(skb);
-		eth = eth_hdr(skb);
-
-		/* Normally, setting the skb 'protocol' field would be
-		 * handled by a call to eth_type_trans(), but it assumes
-		 * there's a sending device, which we may not have.
-		 */
-		if (eth_proto_is_802_3(eth->h_proto))
-			skb->protocol = eth->h_proto;
-		else
-			skb->protocol = htons(ETH_P_802_2);
-	}
+	/* key_extract assumes that skb->protocol is set-up for
+	 * layer 3 packets which is the case for other callers,
+	 * in particular packets received from the network stack.
+	 * Here the correct value can be set from the metadata
+	 * extracted above.
+	 * For L2 packet key eth type would be zero. skb protocol
+	 * would be set to correct value later during key-extact.
+	 */
 
+	skb->protocol = key->eth.type;
 	return key_extract(skb, key);
 }

net/sched/cls_api.c

@@ -148,13 +148,15 @@ static int tc_ctl_tfilter(struct sk_buff *skb, struct nlmsghdr *n)
 	unsigned long cl;
 	unsigned long fh;
 	int err;
-	int tp_created = 0;
+	int tp_created;
 
 	if ((n->nlmsg_type != RTM_GETTFILTER) &&
 	    !netlink_ns_capable(skb, net->user_ns, CAP_NET_ADMIN))
 		return -EPERM;
 
 replay:
+	tp_created = 0;
+
 	err = nlmsg_parse(n, sizeof(*t), tca, TCA_MAX, NULL);
 	if (err < 0)
 		return err;

net/tipc/socket.c

@@ -441,15 +441,19 @@ static void __tipc_shutdown(struct socket *sock, int error)
 	while ((skb = __skb_dequeue(&sk->sk_receive_queue)) != NULL) {
 		if (TIPC_SKB_CB(skb)->bytes_read) {
 			kfree_skb(skb);
-		} else {
-			if (!tipc_sk_type_connectionless(sk) &&
-			    sk->sk_state != TIPC_DISCONNECTING) {
-				tipc_set_sk_state(sk, TIPC_DISCONNECTING);
-				tipc_node_remove_conn(net, dnode, tsk->portid);
-			}
-			tipc_sk_respond(sk, skb, error);
+			continue;
+		}
+		if (!tipc_sk_type_connectionless(sk) &&
+		    sk->sk_state != TIPC_DISCONNECTING) {
+			tipc_set_sk_state(sk, TIPC_DISCONNECTING);
+			tipc_node_remove_conn(net, dnode, tsk->portid);
 		}
+		tipc_sk_respond(sk, skb, error);
 	}
+
+	if (tipc_sk_type_connectionless(sk))
+		return;
+
 	if (sk->sk_state != TIPC_DISCONNECTING) {
 		skb = tipc_msg_create(TIPC_CRITICAL_IMPORTANCE,
 				      TIPC_CONN_MSG, SHORT_H_SIZE, 0, dnode,
@@ -457,10 +461,8 @@ static void __tipc_shutdown(struct socket *sock, int error)
 				      tsk->portid, error);
 		if (skb)
 			tipc_node_xmit_skb(net, skb, dnode, tsk->portid);
-		if (!tipc_sk_type_connectionless(sk)) {
-			tipc_node_remove_conn(net, dnode, tsk->portid);
-			tipc_set_sk_state(sk, TIPC_DISCONNECTING);
-		}
+		tipc_node_remove_conn(net, dnode, tsk->portid);
+		tipc_set_sk_state(sk, TIPC_DISCONNECTING);
 	}
 }