Merge branch 'acpi-scan' into acpi-pm

Conflicts:
	drivers/acpi/scan.c

The conflict is resolved by moving the just introduced
acpi_device_is_first_physical_node() to bus.c and using
the existing acpi_companion_match() from there.

There will be an additional commit to combine the two.

Documentation/kbuild/makefiles.txt

@@ -952,6 +952,14 @@ When kbuild executes, the following steps are followed (roughly):
 	$(KBUILD_ARFLAGS) set by the top level Makefile to "D" (deterministic
 	mode) if this option is supported by $(AR).
 
+    ARCH_CPPFLAGS, ARCH_AFLAGS, ARCH_CFLAGS   Overrides the kbuild defaults
+
+	These variables are appended to the KBUILD_CPPFLAGS,
+	KBUILD_AFLAGS, and KBUILD_CFLAGS, respectively, after the
+	top-level Makefile has set any other flags. This provides a
+	means for an architecture to override the defaults.
+
+
 --- 6.2 Add prerequisites to archheaders:
 
 	The archheaders: rule is used to generate header files that

MAINTAINERS

@@ -7019,6 +7019,7 @@ F:	include/uapi/linux/netfilter/
 F:	net/*/netfilter.c
 F:	net/*/netfilter/
 F:	net/netfilter/
+F:	net/bridge/br_netfilter*.c
 
 NETLABEL
 M:	Paul Moore <paul@paul-moore.com>

Makefile

@@ -780,10 +780,11 @@ endif
 include scripts/Makefile.kasan
 include scripts/Makefile.extrawarn
 
-# Add user supplied CPPFLAGS, AFLAGS and CFLAGS as the last assignments
-KBUILD_CPPFLAGS += $(KCPPFLAGS)
-KBUILD_AFLAGS += $(KAFLAGS)
-KBUILD_CFLAGS += $(KCFLAGS)
+# Add any arch overrides and user supplied CPPFLAGS, AFLAGS and CFLAGS as the
+# last assignments
+KBUILD_CPPFLAGS += $(ARCH_CPPFLAGS) $(KCPPFLAGS)
+KBUILD_AFLAGS   += $(ARCH_AFLAGS)   $(KAFLAGS)
+KBUILD_CFLAGS   += $(ARCH_CFLAGS)   $(KCFLAGS)
 
 # Use --build-id when available.
 LDFLAGS_BUILD_ID = $(patsubst -Wl$(comma)%,%,\

arch/arc/Kconfig

@@ -115,6 +115,7 @@ if ISA_ARCOMPACT
 
 config ARC_CPU_750D
 	bool "ARC750D"
+	select ARC_CANT_LLSC
 	help
 	  Support for ARC750 core
 
@@ -362,7 +363,7 @@ config ARC_CANT_LLSC
 config ARC_HAS_LLSC
 	bool "Insn: LLOCK/SCOND (efficient atomic ops)"
 	default y
-	depends on !ARC_CPU_750D && !ARC_CANT_LLSC
+	depends on !ARC_CANT_LLSC
 
 config ARC_HAS_SWAPE
 	bool "Insn: SWAPE (endian-swap)"

arch/arc/Makefile

@@ -49,7 +49,8 @@ endif
 
 ifndef CONFIG_CC_OPTIMIZE_FOR_SIZE
 # Generic build system uses -O2, we want -O3
-cflags-y  += -O3
+# Note: No need to add to cflags-y as that happens anyways
+ARCH_CFLAGS += -O3
 endif
 
 # small data is default for elf32 tool-chain. If not usable, disable it

arch/arc/boot/dts/axc003.dtsi

@@ -12,7 +12,7 @@
 
 / {
 	compatible = "snps,arc";
-	clock-frequency = <75000000>;
+	clock-frequency = <90000000>;
 	#address-cells = <1>;
 	#size-cells = <1>;
 

arch/arc/boot/dts/axc003_idu.dtsi

@@ -12,7 +12,7 @@
 
 / {
 	compatible = "snps,arc";
-	clock-frequency = <75000000>;
+	clock-frequency = <90000000>;
 	#address-cells = <1>;
 	#size-cells = <1>;
 

arch/arc/include/asm/bitops.h

@@ -50,8 +50,7 @@ static inline void op##_bit(unsigned long nr, volatile unsigned long *m)\
 	 * done for const @nr, but no code is generated due to gcc	\
 	 * const prop.							\
 	 */								\
-	if (__builtin_constant_p(nr))					\
-		nr &= 0x1f;						\
+	nr &= 0x1f;							\
 									\
 	__asm__ __volatile__(						\
 	"1:	llock       %0, [%1]		\n"			\
@@ -82,8 +81,7 @@ static inline int test_and_##op##_bit(unsigned long nr, volatile unsigned long *
 									\
 	m += nr >> 5;							\
 									\
-	if (__builtin_constant_p(nr))					\
-		nr &= 0x1f;						\
+	nr &= 0x1f;							\
 									\
 	/*								\
 	 * Explicit full memory barrier needed before/after as		\
@@ -129,16 +127,13 @@ static inline void op##_bit(unsigned long nr, volatile unsigned long *m)\
 	unsigned long temp, flags;					\
 	m += nr >> 5;							\
 									\
-	if (__builtin_constant_p(nr))					\
-		nr &= 0x1f;						\
-									\
 	/*								\
 	 * spin lock/unlock provide the needed smp_mb() before/after	\
 	 */								\
 	bitops_lock(flags);						\
 									\
 	temp = *m;							\
-	*m = temp c_op (1UL << nr);					\
+	*m = temp c_op (1UL << (nr & 0x1f));					\
 									\
 	bitops_unlock(flags);						\
 }
@@ -149,17 +144,14 @@ static inline int test_and_##op##_bit(unsigned long nr, volatile unsigned long *
 	unsigned long old, flags;					\
 	m += nr >> 5;							\
 									\
-	if (__builtin_constant_p(nr))					\
-		nr &= 0x1f;						\
-									\
 	bitops_lock(flags);						\
 									\
 	old = *m;							\
-	*m = old c_op (1 << nr);					\
+	*m = old c_op (1UL << (nr & 0x1f));				\
 									\
 	bitops_unlock(flags);						\
 									\
-	return (old & (1 << nr)) != 0;					\
+	return (old & (1UL << (nr & 0x1f))) != 0;			\
 }
 
 #endif /* CONFIG_ARC_HAS_LLSC */
@@ -174,11 +166,8 @@ static inline void __##op##_bit(unsigned long nr, volatile unsigned long *m)	\
 	unsigned long temp;						\
 	m += nr >> 5;							\
 									\
-	if (__builtin_constant_p(nr))					\
-		nr &= 0x1f;						\
-									\
 	temp = *m;							\
-	*m = temp c_op (1UL << nr);					\
+	*m = temp c_op (1UL << (nr & 0x1f));				\
 }
 
 #define __TEST_N_BIT_OP(op, c_op, asm_op)				\
@@ -187,13 +176,10 @@ static inline int __test_and_##op##_bit(unsigned long nr, volatile unsigned long
 	unsigned long old;						\
 	m += nr >> 5;							\
 									\
-	if (__builtin_constant_p(nr))					\
-		nr &= 0x1f;						\
-									\
 	old = *m;							\
-	*m = old c_op (1 << nr);					\
+	*m = old c_op (1UL << (nr & 0x1f));				\
 									\
-	return (old & (1 << nr)) != 0;					\
+	return (old & (1UL << (nr & 0x1f))) != 0;			\
 }
 
 #define BIT_OPS(op, c_op, asm_op)					\
@@ -224,10 +210,7 @@ test_bit(unsigned int nr, const volatile unsigned long *addr)
 
 	addr += nr >> 5;
 
-	if (__builtin_constant_p(nr))
-		nr &= 0x1f;
-
-	mask = 1 << nr;
+	mask = 1UL << (nr & 0x1f);
 
 	return ((mask & *addr) != 0);
 }

arch/arc/include/asm/futex.h

@@ -16,12 +16,40 @@
 #include <linux/uaccess.h>
 #include <asm/errno.h>
 
+#ifdef CONFIG_ARC_HAS_LLSC
+
+#define __futex_atomic_op(insn, ret, oldval, uaddr, oparg)\
+							\
+	__asm__ __volatile__(				\
+	"1:	llock	%1, [%2]		\n"	\
+		insn				"\n"	\
+	"2:	scond	%0, [%2]		\n"	\
+	"	bnz	1b			\n"	\
+	"	mov %0, 0			\n"	\
+	"3:					\n"	\
+	"	.section .fixup,\"ax\"		\n"	\
+	"	.align  4			\n"	\
+	"4:	mov %0, %4			\n"	\
+	"	b   3b				\n"	\
+	"	.previous			\n"	\
+	"	.section __ex_table,\"a\"	\n"	\
+	"	.align  4			\n"	\
+	"	.word   1b, 4b			\n"	\
+	"	.word   2b, 4b			\n"	\
+	"	.previous			\n"	\
+							\
+	: "=&r" (ret), "=&r" (oldval)			\
+	: "r" (uaddr), "r" (oparg), "ir" (-EFAULT)	\
+	: "cc", "memory")
+
+#else	/* !CONFIG_ARC_HAS_LLSC */
+
 #define __futex_atomic_op(insn, ret, oldval, uaddr, oparg)\
 							\
 	__asm__ __volatile__(				\
-	"1:	ld  %1, [%2]			\n"	\
+	"1:	ld	%1, [%2]		\n"	\
 		insn				"\n"	\
-	"2:	st  %0, [%2]			\n"	\
+	"2:	st	%0, [%2]		\n"	\
 	"	mov %0, 0			\n"	\
 	"3:					\n"	\
 	"	.section .fixup,\"ax\"		\n"	\
@@ -39,6 +67,8 @@
 	: "r" (uaddr), "r" (oparg), "ir" (-EFAULT)	\
 	: "cc", "memory")
 
+#endif
+
 static inline int futex_atomic_op_inuser(int encoded_op, u32 __user *uaddr)
 {
 	int op = (encoded_op >> 28) & 7;
@@ -123,11 +153,17 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr, u32 oldval,
 
 	pagefault_disable();
 
-	/* TBD : can use llock/scond */
 	__asm__ __volatile__(
-	"1:	ld    %0, [%3]	\n"
-	"	brne  %0, %1, 3f	\n"
-	"2:	st    %2, [%3]	\n"
+#ifdef CONFIG_ARC_HAS_LLSC
+	"1:	llock	%0, [%3]		\n"
+	"	brne	%0, %1, 3f		\n"
+	"2:	scond	%2, [%3]		\n"
+	"	bnz	1b			\n"
+#else
+	"1:	ld	%0, [%3]		\n"
+	"	brne	%0, %1, 3f		\n"
+	"2:	st	%2, [%3]		\n"
+#endif
 	"3:	\n"
 	"	.section .fixup,\"ax\"	\n"
 	"4:	mov %0, %4	\n"

arch/arc/include/asm/ptrace.h

@@ -106,7 +106,7 @@ struct callee_regs {
 	long r25, r24, r23, r22, r21, r20, r19, r18, r17, r16, r15, r14, r13;
 };
 
-#define instruction_pointer(regs)	((regs)->ret)
+#define instruction_pointer(regs)	(unsigned long)((regs)->ret)
 #define profile_pc(regs)		instruction_pointer(regs)
 
 /* return 1 if user mode or 0 if kernel mode */

arch/arc/kernel/intc-arcv2.c

@@ -12,7 +12,6 @@
 #include <linux/of.h>
 #include <linux/irqdomain.h>
 #include <linux/irqchip.h>
-#include "../../drivers/irqchip/irqchip.h"
 #include <asm/irq.h>
 
 /*

arch/arc/kernel/intc-compact.c

@@ -12,7 +12,6 @@
 #include <linux/of.h>
 #include <linux/irqdomain.h>
 #include <linux/irqchip.h>
-#include "../../drivers/irqchip/irqchip.h"
 #include <asm/irq.h>
 
 /*

arch/arc/kernel/mcip.c

@@ -175,7 +175,6 @@ void mcip_init_early_smp(void)
 #include <linux/irqchip.h>
 #include <linux/of.h>
 #include <linux/of_irq.h>
-#include "../../drivers/irqchip/irqchip.h"
 
 /*
  * Set the DEST for @cmn_irq to @cpu_mask (1 bit per core)
@@ -218,11 +217,28 @@ static void idu_irq_unmask(struct irq_data *data)
 	raw_spin_unlock_irqrestore(&mcip_lock, flags);
 }
 
+#ifdef CONFIG_SMP
 static int
-idu_irq_set_affinity(struct irq_data *d, const struct cpumask *cpumask, bool f)
+idu_irq_set_affinity(struct irq_data *data, const struct cpumask *cpumask,
+		     bool force)
 {
+	unsigned long flags;
+	cpumask_t online;
+
+	/* errout if no online cpu per @cpumask */
+	if (!cpumask_and(&online, cpumask, cpu_online_mask))
+		return -EINVAL;
+
+	raw_spin_lock_irqsave(&mcip_lock, flags);
+
+	idu_set_dest(data->hwirq, cpumask_bits(&online)[0]);
+	idu_set_mode(data->hwirq, IDU_M_TRIG_LEVEL, IDU_M_DISTRI_RR);
+
+	raw_spin_unlock_irqrestore(&mcip_lock, flags);
+
 	return IRQ_SET_MASK_OK;
 }
+#endif
 
 static struct irq_chip idu_irq_chip = {
 	.name			= "MCIP IDU Intc",
@@ -330,8 +346,7 @@ idu_of_init(struct device_node *intc, struct device_node *parent)
 		if (!i)
 			idu_first_irq = irq;
 
-		irq_set_handler_data(irq, domain);
-		irq_set_chained_handler(irq, idu_cascade_isr);
+		irq_set_chained_handler_and_data(irq, idu_cascade_isr, domain);
 	}
 
 	__mcip_cmd(CMD_IDU_ENABLE, 0);

arch/arc/kernel/setup.c

@@ -142,17 +142,22 @@ static void read_arc_build_cfg_regs(void)
 }
 
 static const struct cpuinfo_data arc_cpu_tbl[] = {
+#ifdef CONFIG_ISA_ARCOMPACT
 	{ {0x20, "ARC 600"      }, 0x2F},
 	{ {0x30, "ARC 700"      }, 0x33},
 	{ {0x34, "ARC 700 R4.10"}, 0x34},
 	{ {0x35, "ARC 700 R4.11"}, 0x35},
-	{ {0x50, "ARC HS38"	}, 0x51},
+#else
+	{ {0x50, "ARC HS38 R2.0"}, 0x51},
+	{ {0x52, "ARC HS38 R2.1"}, 0x52},
+#endif
 	{ {0x00, NULL		} }
 };
 
-#define IS_AVAIL1(v, str)	((v) ? str : "")
-#define IS_USED(cfg)		(IS_ENABLED(cfg) ? "" : "(not used) ")
-#define IS_AVAIL2(v, str, cfg)  IS_AVAIL1(v, str), IS_AVAIL1(v, IS_USED(cfg))
+#define IS_AVAIL1(v, s)		((v) ? s : "")
+#define IS_USED_RUN(v)		((v) ? "" : "(not used) ")
+#define IS_USED_CFG(cfg)	IS_USED_RUN(IS_ENABLED(cfg))
+#define IS_AVAIL2(v, s, cfg)	IS_AVAIL1(v, s), IS_AVAIL1(v, IS_USED_CFG(cfg))
 
 static char *arc_cpu_mumbojumbo(int cpu_id, char *buf, int len)
 {
@@ -226,7 +231,7 @@ static char *arc_cpu_mumbojumbo(int cpu_id, char *buf, int len)
 			n += scnprintf(buf + n, len - n, "mpy[opt %d] ", opt);
 		}
 		n += scnprintf(buf + n, len - n, "%s",
-			       IS_USED(CONFIG_ARC_HAS_HW_MPY));
+			       IS_USED_CFG(CONFIG_ARC_HAS_HW_MPY));
 	}
 
 	n += scnprintf(buf + n, len - n, "%s%s%s%s%s%s%s%s\n",

arch/arc/kernel/troubleshoot.c

@@ -58,7 +58,6 @@ static void show_callee_regs(struct callee_regs *cregs)
 
 static void print_task_path_n_nm(struct task_struct *tsk, char *buf)
 {
-	struct path path;
 	char *path_nm = NULL;
 	struct mm_struct *mm;
 	struct file *exe_file;

arch/arc/mm/cache.c

@@ -468,10 +468,18 @@ static void __ic_line_inv_vaddr(unsigned long paddr, unsigned long vaddr,
 noinline void slc_op(unsigned long paddr, unsigned long sz, const int op)
 {
 #ifdef CONFIG_ISA_ARCV2
+	/*
+	 * SLC is shared between all cores and concurrent aux operations from
+	 * multiple cores need to be serialized using a spinlock
+	 * A concurrent operation can be silently ignored and/or the old/new
+	 * operation can remain incomplete forever (lockup in SLC_CTRL_BUSY loop
+	 * below)
+	 */
+	static DEFINE_SPINLOCK(lock);
 	unsigned long flags;
 	unsigned int ctrl;
 
-	local_irq_save(flags);
+	spin_lock_irqsave(&lock, flags);
 
 	/*
 	 * The Region Flush operation is specified by CTRL.RGN_OP[11..9]
@@ -504,7 +512,7 @@ noinline void slc_op(unsigned long paddr, unsigned long sz, const int op)
 
 	while (read_aux_reg(ARC_REG_SLC_CTRL) & SLC_CTRL_BUSY);
 
-	local_irq_restore(flags);
+	spin_unlock_irqrestore(&lock, flags);
 #endif
 }
 

arch/arc/mm/dma.c

@@ -60,8 +60,8 @@ void *dma_alloc_coherent(struct device *dev, size_t size,
 
 	/* This is kernel Virtual address (0x7000_0000 based) */
 	kvaddr = ioremap_nocache((unsigned long)paddr, size);
-	if (kvaddr != NULL)
-		memset(kvaddr, 0, size);
+	if (kvaddr == NULL)
+		return NULL;
 
 	/* This is bus address, platform dependent */
 	*dma_handle = (dma_addr_t)paddr;

arch/arm/boot/dts/dra7-evm.dts

@@ -686,7 +686,8 @@
 
 &dcan1 {
 	status = "ok";
-	pinctrl-names = "default", "sleep";
-	pinctrl-0 = <&dcan1_pins_default>;
+	pinctrl-names = "default", "sleep", "active";
+	pinctrl-0 = <&dcan1_pins_sleep>;
 	pinctrl-1 = <&dcan1_pins_sleep>;
+	pinctrl-2 = <&dcan1_pins_default>;
 };

arch/arm/boot/dts/dra72-evm.dts

@@ -587,9 +587,10 @@
 
 &dcan1 {
 	status = "ok";
-	pinctrl-names = "default", "sleep";
-	pinctrl-0 = <&dcan1_pins_default>;
+	pinctrl-names = "default", "sleep", "active";
+	pinctrl-0 = <&dcan1_pins_sleep>;
 	pinctrl-1 = <&dcan1_pins_sleep>;
+	pinctrl-2 = <&dcan1_pins_default>;
 };
 
 &qspi {

arch/m68k/Kconfig.cpu

@@ -125,6 +125,13 @@ endif # M68KCLASSIC
 
 if COLDFIRE
 
+choice
+	prompt "ColdFire SoC type"
+	default M520x
+	help
+	  Select the type of ColdFire System-on-Chip (SoC) that you want
+	  to build for.
+
 config M5206
 	bool "MCF5206"
 	depends on !MMU
@@ -174,9 +181,6 @@ config M525x
 	help
 	  Freescale (Motorola) Coldfire 5251/5253 processor support.
 
-config M527x
-	bool
-
 config M5271
 	bool "MCF5271"
 	depends on !MMU
@@ -223,9 +227,6 @@ config M5307
 	help
 	  Motorola ColdFire 5307 processor support.
 
-config M53xx
-	bool
-
 config M532x
 	bool "MCF532x"
 	depends on !MMU
@@ -251,9 +252,6 @@ config M5407
 	help
 	  Motorola ColdFire 5407 processor support.
 
-config M54xx
-	bool
-
 config M547x
 	bool "MCF547x"
 	select M54xx
@@ -280,6 +278,17 @@ config M5441x
 	help
 	  Freescale Coldfire 54410/54415/54416/54417/54418 processor support.
 
+endchoice
+
+config M527x
+	bool
+
+config M53xx
+	bool
+
+config M54xx
+	bool
+
 endif # COLDFIRE
 
 
@@ -416,22 +425,18 @@ config HAVE_MBAR
 config HAVE_IPSBAR
 	bool
 
-config CLOCK_SET
-	bool "Enable setting the CPU clock frequency"
-	depends on COLDFIRE
-	default n
-	help
-	  On some CPU's you do not need to know what the core CPU clock
-	  frequency is. On these you can disable clock setting. On some
-	  traditional 68K parts, and on all ColdFire parts you need to set
-	  the appropriate CPU clock frequency. On these devices many of the
-	  onboard peripherals derive their timing from the master CPU clock
-	  frequency.
-
 config CLOCK_FREQ
 	int "Set the core clock frequency"
+	default "25000000" if M5206
+	default "54000000" if M5206e
+	default "166666666" if M520x
+	default "140000000" if M5249
+	default "150000000" if M527x || M523x
+	default "90000000" if M5307
+	default "50000000" if M5407
+	default "266000000" if M54xx
 	default "66666666"
-	depends on CLOCK_SET
+	depends on COLDFIRE
 	help
 	  Define the CPU clock frequency in use. This is the core clock
 	  frequency, it may or may not be the same as the external clock

arch/m68k/configs/m5208evb_defconfig

@@ -1,10 +1,6 @@
-# CONFIG_MMU is not set
-CONFIG_EXPERIMENTAL=y
 CONFIG_LOG_BUF_SHIFT=14
-# CONFIG_CC_OPTIMIZE_FOR_SIZE is not set
 CONFIG_EXPERT=y
 # CONFIG_KALLSYMS is not set
-# CONFIG_HOTPLUG is not set
 # CONFIG_FUTEX is not set
 # CONFIG_EPOLL is not set
 # CONFIG_SIGNALFD is not set
@@ -16,17 +12,12 @@ CONFIG_EXPERT=y
 # CONFIG_BLK_DEV_BSG is not set
 # CONFIG_IOSCHED_DEADLINE is not set
 # CONFIG_IOSCHED_CFQ is not set
-CONFIG_M520x=y
-CONFIG_CLOCK_SET=y
-CONFIG_CLOCK_FREQ=166666666
-CONFIG_CLOCK_DIV=2
-CONFIG_M5208EVB=y
+# CONFIG_MMU is not set
 # CONFIG_4KSTACKS is not set
 CONFIG_RAMBASE=0x40000000
 CONFIG_RAMSIZE=0x2000000
 CONFIG_VECTORBASE=0x40000000
 CONFIG_KERNELBASE=0x40020000
-CONFIG_RAM16BIT=y
 CONFIG_BINFMT_FLAT=y
 CONFIG_NET=y
 CONFIG_PACKET=y
@@ -40,24 +31,19 @@ CONFIG_INET=y
 # CONFIG_IPV6 is not set
 # CONFIG_FW_LOADER is not set
 CONFIG_MTD=y
-CONFIG_MTD_CHAR=y
 CONFIG_MTD_BLOCK=y
 CONFIG_MTD_RAM=y
 CONFIG_MTD_UCLINUX=y
 CONFIG_BLK_DEV_RAM=y
-# CONFIG_MISC_DEVICES is not set
 CONFIG_NETDEVICES=y
-CONFIG_NET_ETHERNET=y
 CONFIG_FEC=y
-# CONFIG_NETDEV_1000 is not set
-# CONFIG_NETDEV_10000 is not set
 # CONFIG_INPUT is not set
 # CONFIG_SERIO is not set
 # CONFIG_VT is not set
+# CONFIG_UNIX98_PTYS is not set
 CONFIG_SERIAL_MCF=y
 CONFIG_SERIAL_MCF_BAUDRATE=115200
 CONFIG_SERIAL_MCF_CONSOLE=y
-# CONFIG_UNIX98_PTYS is not set
 # CONFIG_HW_RANDOM is not set
 # CONFIG_HWMON is not set
 # CONFIG_USB_SUPPORT is not set
@@ -68,8 +54,6 @@ CONFIG_EXT2_FS=y
 CONFIG_ROMFS_FS=y
 CONFIG_ROMFS_BACKED_BY_MTD=y
 # CONFIG_NETWORK_FILESYSTEMS is not set
-# CONFIG_RCU_CPU_STALL_DETECTOR is not set
-CONFIG_SYSCTL_SYSCALL_CHECK=y
-CONFIG_FULLDEBUG=y
 CONFIG_BOOTPARAM=y
 CONFIG_BOOTPARAM_STRING="root=/dev/mtdblock0"
+CONFIG_FULLDEBUG=y

arch/m68k/configs/m5249evb_defconfig

@@ -1,10 +1,6 @@
-# CONFIG_MMU is not set
-CONFIG_EXPERIMENTAL=y
 CONFIG_LOG_BUF_SHIFT=14
-# CONFIG_CC_OPTIMIZE_FOR_SIZE is not set
 CONFIG_EXPERT=y
 # CONFIG_KALLSYMS is not set
-# CONFIG_HOTPLUG is not set
 # CONFIG_FUTEX is not set
 # CONFIG_EPOLL is not set
 # CONFIG_SIGNALFD is not set
@@ -16,10 +12,8 @@ CONFIG_EXPERT=y
 # CONFIG_BLK_DEV_BSG is not set
 # CONFIG_IOSCHED_DEADLINE is not set
 # CONFIG_IOSCHED_CFQ is not set
+# CONFIG_MMU is not set
 CONFIG_M5249=y
-CONFIG_CLOCK_SET=y
-CONFIG_CLOCK_FREQ=140000000
-CONFIG_CLOCK_DIV=2
 CONFIG_M5249C3=y
 CONFIG_RAMBASE=0x00000000
 CONFIG_RAMSIZE=0x00800000
@@ -38,23 +32,18 @@ CONFIG_INET=y
 # CONFIG_IPV6 is not set
 # CONFIG_FW_LOADER is not set
 CONFIG_MTD=y
-CONFIG_MTD_CHAR=y
 CONFIG_MTD_BLOCK=y
 CONFIG_MTD_RAM=y
 CONFIG_MTD_UCLINUX=y
 CONFIG_BLK_DEV_RAM=y
-# CONFIG_MISC_DEVICES is not set
 CONFIG_NETDEVICES=y
-CONFIG_NET_ETHERNET=y
-# CONFIG_NETDEV_1000 is not set
-# CONFIG_NETDEV_10000 is not set
 CONFIG_PPP=y
 # CONFIG_INPUT is not set
 # CONFIG_SERIO is not set
 # CONFIG_VT is not set
+# CONFIG_UNIX98_PTYS is not set
 CONFIG_SERIAL_MCF=y
 CONFIG_SERIAL_MCF_CONSOLE=y
-# CONFIG_UNIX98_PTYS is not set
 # CONFIG_HWMON is not set
 # CONFIG_USB_SUPPORT is not set
 CONFIG_EXT2_FS=y
@@ -62,7 +51,5 @@ CONFIG_EXT2_FS=y
 CONFIG_ROMFS_FS=y
 CONFIG_ROMFS_BACKED_BY_MTD=y
 # CONFIG_NETWORK_FILESYSTEMS is not set
-# CONFIG_RCU_CPU_STALL_DETECTOR is not set
 CONFIG_BOOTPARAM=y
 CONFIG_BOOTPARAM_STRING="root=/dev/mtdblock0"
-# CONFIG_CRC32 is not set

arch/m68k/configs/m5272c3_defconfig

@@ -1,10 +1,6 @@
-# CONFIG_MMU is not set
-CONFIG_EXPERIMENTAL=y
 CONFIG_LOG_BUF_SHIFT=14
-# CONFIG_CC_OPTIMIZE_FOR_SIZE is not set
 CONFIG_EXPERT=y
 # CONFIG_KALLSYMS is not set
-# CONFIG_HOTPLUG is not set
 # CONFIG_FUTEX is not set
 # CONFIG_EPOLL is not set
 # CONFIG_SIGNALFD is not set
@@ -16,8 +12,8 @@ CONFIG_EXPERT=y
 # CONFIG_BLK_DEV_BSG is not set
 # CONFIG_IOSCHED_DEADLINE is not set
 # CONFIG_IOSCHED_CFQ is not set
+# CONFIG_MMU is not set
 CONFIG_M5272=y
-CONFIG_CLOCK_SET=y
 CONFIG_M5272C3=y
 CONFIG_RAMBASE=0x00000000
 CONFIG_RAMSIZE=0x00800000
@@ -36,23 +32,18 @@ CONFIG_INET=y
 # CONFIG_IPV6 is not set
 # CONFIG_FW_LOADER is not set
 CONFIG_MTD=y
-CONFIG_MTD_CHAR=y
 CONFIG_MTD_BLOCK=y
 CONFIG_MTD_RAM=y
 CONFIG_MTD_UCLINUX=y
 CONFIG_BLK_DEV_RAM=y
-# CONFIG_MISC_DEVICES is not set
 CONFIG_NETDEVICES=y
-CONFIG_NET_ETHERNET=y
 CONFIG_FEC=y
-# CONFIG_NETDEV_1000 is not set
-# CONFIG_NETDEV_10000 is not set
 # CONFIG_INPUT is not set
 # CONFIG_SERIO is not set
 # CONFIG_VT is not set
+# CONFIG_UNIX98_PTYS is not set
 CONFIG_SERIAL_MCF=y
 CONFIG_SERIAL_MCF_CONSOLE=y
-# CONFIG_UNIX98_PTYS is not set
 # CONFIG_HWMON is not set
 # CONFIG_USB_SUPPORT is not set
 CONFIG_EXT2_FS=y
@@ -61,6 +52,5 @@ CONFIG_EXT2_FS=y
 CONFIG_ROMFS_FS=y
 CONFIG_ROMFS_BACKED_BY_MTD=y
 # CONFIG_NETWORK_FILESYSTEMS is not set
-# CONFIG_RCU_CPU_STALL_DETECTOR is not set
 CONFIG_BOOTPARAM=y
 CONFIG_BOOTPARAM_STRING="root=/dev/mtdblock0"

arch/m68k/configs/m5275evb_defconfig

@@ -1,10 +1,6 @@
-# CONFIG_MMU is not set
-CONFIG_EXPERIMENTAL=y
 CONFIG_LOG_BUF_SHIFT=14
-# CONFIG_CC_OPTIMIZE_FOR_SIZE is not set
 CONFIG_EXPERT=y
 # CONFIG_KALLSYMS is not set
-# CONFIG_HOTPLUG is not set
 # CONFIG_FUTEX is not set
 # CONFIG_EPOLL is not set
 # CONFIG_SIGNALFD is not set
@@ -16,11 +12,8 @@ CONFIG_EXPERT=y
 # CONFIG_BLK_DEV_BSG is not set
 # CONFIG_IOSCHED_DEADLINE is not set
 # CONFIG_IOSCHED_CFQ is not set
+# CONFIG_MMU is not set
 CONFIG_M5275=y
-CONFIG_CLOCK_SET=y
-CONFIG_CLOCK_FREQ=150000000
-CONFIG_CLOCK_DIV=2
-CONFIG_M5275EVB=y
 # CONFIG_4KSTACKS is not set
 CONFIG_RAMBASE=0x00000000
 CONFIG_RAMSIZE=0x00000000
@@ -39,24 +32,19 @@ CONFIG_INET=y
 # CONFIG_IPV6 is not set
 # CONFIG_FW_LOADER is not set
 CONFIG_MTD=y
-CONFIG_MTD_CHAR=y
 CONFIG_MTD_BLOCK=y
 CONFIG_MTD_RAM=y
 CONFIG_MTD_UCLINUX=y
 CONFIG_BLK_DEV_RAM=y
-# CONFIG_MISC_DEVICES is not set
 CONFIG_NETDEVICES=y
-CONFIG_NET_ETHERNET=y
 CONFIG_FEC=y
-# CONFIG_NETDEV_1000 is not set
-# CONFIG_NETDEV_10000 is not set
 CONFIG_PPP=y
 # CONFIG_INPUT is not set
 # CONFIG_SERIO is not set
 # CONFIG_VT is not set
+# CONFIG_UNIX98_PTYS is not set
 CONFIG_SERIAL_MCF=y
 CONFIG_SERIAL_MCF_CONSOLE=y
-# CONFIG_UNIX98_PTYS is not set
 # CONFIG_HWMON is not set
 # CONFIG_USB_SUPPORT is not set
 CONFIG_EXT2_FS=y
@@ -65,8 +53,5 @@ CONFIG_EXT2_FS=y
 CONFIG_ROMFS_FS=y
 CONFIG_ROMFS_BACKED_BY_MTD=y
 # CONFIG_NETWORK_FILESYSTEMS is not set
-# CONFIG_RCU_CPU_STALL_DETECTOR is not set
-CONFIG_SYSCTL_SYSCALL_CHECK=y
 CONFIG_BOOTPARAM=y
 CONFIG_BOOTPARAM_STRING="root=/dev/mtdblock0"
-# CONFIG_CRC32 is not set

arch/m68k/configs/m5307c3_defconfig

@@ -1,10 +1,6 @@
-# CONFIG_MMU is not set
-CONFIG_EXPERIMENTAL=y
 CONFIG_LOG_BUF_SHIFT=14
-# CONFIG_CC_OPTIMIZE_FOR_SIZE is not set
 CONFIG_EXPERT=y
 # CONFIG_KALLSYMS is not set
-# CONFIG_HOTPLUG is not set
 # CONFIG_FUTEX is not set
 # CONFIG_EPOLL is not set
 # CONFIG_SIGNALFD is not set
@@ -16,10 +12,8 @@ CONFIG_EXPERT=y
 # CONFIG_BLK_DEV_BSG is not set
 # CONFIG_IOSCHED_DEADLINE is not set
 # CONFIG_IOSCHED_CFQ is not set
+# CONFIG_MMU is not set
 CONFIG_M5307=y
-CONFIG_CLOCK_SET=y
-CONFIG_CLOCK_FREQ=90000000
-CONFIG_CLOCK_DIV=2
 CONFIG_M5307C3=y
 CONFIG_RAMBASE=0x00000000
 CONFIG_RAMSIZE=0x00800000
@@ -38,16 +32,11 @@ CONFIG_INET=y
 # CONFIG_IPV6 is not set
 # CONFIG_FW_LOADER is not set
 CONFIG_MTD=y
-CONFIG_MTD_CHAR=y
 CONFIG_MTD_BLOCK=y
 CONFIG_MTD_RAM=y
 CONFIG_MTD_UCLINUX=y
 CONFIG_BLK_DEV_RAM=y
-# CONFIG_MISC_DEVICES is not set
 CONFIG_NETDEVICES=y
-CONFIG_NET_ETHERNET=y
-# CONFIG_NETDEV_1000 is not set
-# CONFIG_NETDEV_10000 is not set
 CONFIG_PPP=y
 CONFIG_SLIP=y
 CONFIG_SLIP_COMPRESSED=y
@@ -56,21 +45,17 @@ CONFIG_SLIP_COMPRESSED=y
 # CONFIG_INPUT_MOUSE is not set
 # CONFIG_SERIO is not set
 # CONFIG_VT is not set
+# CONFIG_LEGACY_PTYS is not set
 CONFIG_SERIAL_MCF=y
 CONFIG_SERIAL_MCF_CONSOLE=y
-# CONFIG_LEGACY_PTYS is not set
 # CONFIG_HW_RANDOM is not set
 # CONFIG_HWMON is not set
-# CONFIG_HID_SUPPORT is not set
 # CONFIG_USB_SUPPORT is not set
 CONFIG_EXT2_FS=y
 # CONFIG_DNOTIFY is not set
 CONFIG_ROMFS_FS=y
 CONFIG_ROMFS_BACKED_BY_MTD=y
 # CONFIG_NETWORK_FILESYSTEMS is not set
-# CONFIG_RCU_CPU_STALL_DETECTOR is not set
-CONFIG_SYSCTL_SYSCALL_CHECK=y
-CONFIG_FULLDEBUG=y
 CONFIG_BOOTPARAM=y
 CONFIG_BOOTPARAM_STRING="root=/dev/mtdblock0"
-# CONFIG_CRC32 is not set
+CONFIG_FULLDEBUG=y

arch/m68k/configs/m5407c3_defconfig

@@ -1,10 +1,6 @@
-# CONFIG_MMU is not set
-CONFIG_EXPERIMENTAL=y
 CONFIG_LOG_BUF_SHIFT=14
-# CONFIG_CC_OPTIMIZE_FOR_SIZE is not set
 CONFIG_EXPERT=y
 # CONFIG_KALLSYMS is not set
-# CONFIG_HOTPLUG is not set
 # CONFIG_FUTEX is not set
 # CONFIG_EPOLL is not set
 # CONFIG_SIGNALFD is not set
@@ -17,9 +13,8 @@ CONFIG_MODULE_UNLOAD=y
 # CONFIG_BLK_DEV_BSG is not set
 # CONFIG_IOSCHED_DEADLINE is not set
 # CONFIG_IOSCHED_CFQ is not set
+# CONFIG_MMU is not set
 CONFIG_M5407=y
-CONFIG_CLOCK_SET=y
-CONFIG_CLOCK_FREQ=50000000
 CONFIG_M5407C3=y
 CONFIG_RAMBASE=0x00000000
 CONFIG_RAMSIZE=0x00000000
@@ -38,22 +33,17 @@ CONFIG_INET=y
 # CONFIG_IPV6 is not set
 # CONFIG_FW_LOADER is not set
 CONFIG_MTD=y
-CONFIG_MTD_CHAR=y
 CONFIG_MTD_BLOCK=y
 CONFIG_MTD_RAM=y
 CONFIG_MTD_UCLINUX=y
 CONFIG_BLK_DEV_RAM=y
-# CONFIG_MISC_DEVICES is not set
 CONFIG_NETDEVICES=y
-CONFIG_NET_ETHERNET=y
-# CONFIG_NETDEV_1000 is not set
-# CONFIG_NETDEV_10000 is not set
 CONFIG_PPP=y
 # CONFIG_INPUT is not set
 # CONFIG_VT is not set
+# CONFIG_UNIX98_PTYS is not set
 CONFIG_SERIAL_MCF=y
 CONFIG_SERIAL_MCF_CONSOLE=y
-# CONFIG_UNIX98_PTYS is not set
 # CONFIG_HW_RANDOM is not set
 # CONFIG_HWMON is not set
 # CONFIG_USB_SUPPORT is not set
@@ -63,8 +53,5 @@ CONFIG_EXT2_FS=y
 CONFIG_ROMFS_FS=y
 CONFIG_ROMFS_BACKED_BY_MTD=y
 # CONFIG_NETWORK_FILESYSTEMS is not set
-# CONFIG_RCU_CPU_STALL_DETECTOR is not set
-CONFIG_SYSCTL_SYSCALL_CHECK=y
 CONFIG_BOOTPARAM=y
 CONFIG_BOOTPARAM_STRING="root=/dev/mtdblock0"
-# CONFIG_CRC32 is not set

arch/m68k/configs/m5475evb_defconfig

@@ -1,11 +1,7 @@
-CONFIG_EXPERIMENTAL=y
 # CONFIG_SWAP is not set
 CONFIG_LOG_BUF_SHIFT=14
-CONFIG_SYSFS_DEPRECATED=y
-CONFIG_SYSFS_DEPRECATED_V2=y
 CONFIG_SYSCTL_SYSCALL=y
 # CONFIG_KALLSYMS is not set
-# CONFIG_HOTPLUG is not set
 # CONFIG_FUTEX is not set
 # CONFIG_EPOLL is not set
 # CONFIG_SIGNALFD is not set
@@ -20,19 +16,16 @@ CONFIG_MODULES=y
 # CONFIG_IOSCHED_DEADLINE is not set
 # CONFIG_IOSCHED_CFQ is not set
 CONFIG_COLDFIRE=y
-CONFIG_M547x=y
-CONFIG_CLOCK_SET=y
-CONFIG_CLOCK_FREQ=266000000
 # CONFIG_4KSTACKS is not set
 CONFIG_RAMBASE=0x0
 CONFIG_RAMSIZE=0x2000000
 CONFIG_VECTORBASE=0x0
 CONFIG_MBAR=0xff000000
 CONFIG_KERNELBASE=0x20000
+CONFIG_PCI=y
 # CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set
 # CONFIG_FW_LOADER is not set
 CONFIG_MTD=y
-CONFIG_MTD_CHAR=y
 CONFIG_MTD_BLOCK=y
 CONFIG_MTD_CFI=y
 CONFIG_MTD_JEDECPROBE=y

arch/m68k/include/asm/coldfire.h

@@ -19,7 +19,7 @@
  *	in any case new boards come along from time to time that have yet
  *	another different clocking frequency.
  */
-#ifdef CONFIG_CLOCK_SET
+#ifdef CONFIG_CLOCK_FREQ
 #define	MCF_CLK		CONFIG_CLOCK_FREQ
 #else
 #error "Don't know what your ColdFire CPU clock frequency is??"

arch/m68k/include/asm/io_mm.h

@@ -413,7 +413,8 @@ static inline void isa_delay(void)
 #define writew(val, addr)	out_le16((addr), (val))
 #endif /* CONFIG_ATARI_ROM_ISA */
 
-#if !defined(CONFIG_ISA) && !defined(CONFIG_ATARI_ROM_ISA)
+#if !defined(CONFIG_ISA) && !defined(CONFIG_ATARI_ROM_ISA) && \
+    !(defined(CONFIG_PCI) && defined(CONFIG_COLDFIRE))
 /*
  * We need to define dummy functions for GENERIC_IOMAP support.
  */

arch/s390/include/asm/ctl_reg.h

@@ -57,7 +57,10 @@ union ctlreg0 {
 		unsigned long lap  : 1; /* Low-address-protection control */
 		unsigned long	   : 4;
 		unsigned long edat : 1; /* Enhanced-DAT-enablement control */
-		unsigned long	   : 23;
+		unsigned long	   : 4;
+		unsigned long afp  : 1; /* AFP-register control */
+		unsigned long vx   : 1; /* Vector enablement control */
+		unsigned long	   : 17;
 	};
 };
 

arch/s390/include/asm/perf_event.h

@@ -87,7 +87,15 @@ struct sf_raw_sample {
 } __packed;
 
 /* Perf hardware reserve and release functions */
+#ifdef CONFIG_PERF_EVENTS
 int perf_reserve_sampling(void);
 void perf_release_sampling(void);
+#else /* CONFIG_PERF_EVENTS */
+static inline int perf_reserve_sampling(void)
+{
+	return 0;
+}
+static inline void perf_release_sampling(void) {}
+#endif /* CONFIG_PERF_EVENTS */
 
 #endif /* _ASM_S390_PERF_EVENT_H */

arch/s390/kernel/nmi.c

@@ -21,6 +21,7 @@
 #include <asm/nmi.h>
 #include <asm/crw.h>
 #include <asm/switch_to.h>
+#include <asm/ctl_reg.h>
 
 struct mcck_struct {
 	int kill_task;
@@ -129,26 +130,30 @@ static int notrace s390_revalidate_registers(struct mci *mci)
 	} else
 		asm volatile("lfpc 0(%0)" : : "a" (fpt_creg_save_area));
 
-	asm volatile(
-		"	ld	0,0(%0)\n"
-		"	ld	1,8(%0)\n"
-		"	ld	2,16(%0)\n"
-		"	ld	3,24(%0)\n"
-		"	ld	4,32(%0)\n"
-		"	ld	5,40(%0)\n"
-		"	ld	6,48(%0)\n"
-		"	ld	7,56(%0)\n"
-		"	ld	8,64(%0)\n"
-		"	ld	9,72(%0)\n"
-		"	ld	10,80(%0)\n"
-		"	ld	11,88(%0)\n"
-		"	ld	12,96(%0)\n"
-		"	ld	13,104(%0)\n"
-		"	ld	14,112(%0)\n"
-		"	ld	15,120(%0)\n"
-		: : "a" (fpt_save_area));
-	/* Revalidate vector registers */
-	if (MACHINE_HAS_VX && current->thread.vxrs) {
+	if (!MACHINE_HAS_VX) {
+		/* Revalidate floating point registers */
+		asm volatile(
+			"	ld	0,0(%0)\n"
+			"	ld	1,8(%0)\n"
+			"	ld	2,16(%0)\n"
+			"	ld	3,24(%0)\n"
+			"	ld	4,32(%0)\n"
+			"	ld	5,40(%0)\n"
+			"	ld	6,48(%0)\n"
+			"	ld	7,56(%0)\n"
+			"	ld	8,64(%0)\n"
+			"	ld	9,72(%0)\n"
+			"	ld	10,80(%0)\n"
+			"	ld	11,88(%0)\n"
+			"	ld	12,96(%0)\n"
+			"	ld	13,104(%0)\n"
+			"	ld	14,112(%0)\n"
+			"	ld	15,120(%0)\n"
+			: : "a" (fpt_save_area));
+	} else {
+		/* Revalidate vector registers */
+		union ctlreg0 cr0;
+
 		if (!mci->vr) {
 			/*
 			 * Vector registers can't be restored and therefore
@@ -156,8 +161,12 @@ static int notrace s390_revalidate_registers(struct mci *mci)
 			 */
 			kill_task = 1;
 		}
+		cr0.val = S390_lowcore.cregs_save_area[0];
+		cr0.afp = cr0.vx = 1;
+		__ctl_load(cr0.val, 0, 0);
 		restore_vx_regs((__vector128 *)
-				S390_lowcore.vector_save_area_addr);
+				&S390_lowcore.vector_save_area);
+		__ctl_load(S390_lowcore.cregs_save_area[0], 0, 0);
 	}
 	/* Revalidate access registers */
 	asm volatile(

arch/s390/kernel/process.c

@@ -163,7 +163,7 @@ int copy_thread(unsigned long clone_flags, unsigned long new_stackp,
 asmlinkage void execve_tail(void)
 {
 	current->thread.fp_regs.fpc = 0;
-	asm volatile("sfpc %0,%0" : : "d" (0));
+	asm volatile("sfpc %0" : : "d" (0));
 }
 
 /*

arch/s390/kernel/sclp.S

@@ -270,6 +270,8 @@ ENTRY(_sclp_print_early)
 	jno	.Lesa2
 	ahi	%r15,-80
 	stmh	%r6,%r15,96(%r15)		# store upper register halves
+	basr	%r13,0
+	lmh	%r0,%r15,.Lzeroes-.(%r13)	# clear upper register halves
 .Lesa2:
 	lr	%r10,%r2			# save string pointer
 	lhi	%r2,0
@@ -291,6 +293,8 @@ ENTRY(_sclp_print_early)
 .Lesa3:
 	lm	%r6,%r15,120(%r15)		# restore registers
 	br	%r14
+.Lzeroes:
+	.fill	64,4,0
 
 .LwritedataS4:
 	.long	0x00760005			# SCLP command for write data

arch/s390/oprofile/init.c

@@ -16,6 +16,7 @@
 #include <linux/fs.h>
 #include <linux/module.h>
 #include <asm/processor.h>
+#include <asm/perf_event.h>
 
 #include "../../../drivers/oprofile/oprof.h"
 

arch/x86/include/asm/intel_pmc_ipc.h

@@ -25,36 +25,9 @@
 
 #if IS_ENABLED(CONFIG_INTEL_PMC_IPC)
 
-/*
- * intel_pmc_ipc_simple_command
- * @cmd: command
- * @sub: sub type
- */
 int intel_pmc_ipc_simple_command(int cmd, int sub);
-
-/*
- * intel_pmc_ipc_raw_cmd
- * @cmd: command
- * @sub: sub type
- * @in: input data
- * @inlen: input length in bytes
- * @out: output data
- * @outlen: output length in dwords
- * @sptr: data writing to SPTR register
- * @dptr: data writing to DPTR register
- */
 int intel_pmc_ipc_raw_cmd(u32 cmd, u32 sub, u8 *in, u32 inlen,
 		u32 *out, u32 outlen, u32 dptr, u32 sptr);
-
-/*
- * intel_pmc_ipc_command
- * @cmd: command
- * @sub: sub type
- * @in: input data
- * @inlen: input length in bytes
- * @out: output data
- * @outlen: output length in dwords
- */
 int intel_pmc_ipc_command(u32 cmd, u32 sub, u8 *in, u32 inlen,
 		u32 *out, u32 outlen);
 

arch/x86/include/asm/kvm_host.h

@@ -604,6 +604,8 @@ struct kvm_arch {
 	bool iommu_noncoherent;
 #define __KVM_HAVE_ARCH_NONCOHERENT_DMA
 	atomic_t noncoherent_dma_count;
+#define __KVM_HAVE_ARCH_ASSIGNED_DEVICE
+	atomic_t assigned_device_count;
 	struct kvm_pic *vpic;
 	struct kvm_ioapic *vioapic;
 	struct kvm_pit *vpit;

arch/x86/include/uapi/asm/hyperv.h

@@ -108,6 +108,8 @@
 #define HV_X64_HYPERCALL_PARAMS_XMM_AVAILABLE		(1 << 4)
 /* Support for a virtual guest idle state is available */
 #define HV_X64_GUEST_IDLE_STATE_AVAILABLE		(1 << 5)
+/* Guest crash data handler available */
+#define HV_X64_GUEST_CRASH_MSR_AVAILABLE		(1 << 10)
 
 /*
  * Implementation recommendations. Indicates which behaviors the hypervisor

arch/x86/kvm/cpuid.c

@@ -98,6 +98,8 @@ int kvm_update_cpuid(struct kvm_vcpu *vcpu)
 		best->ebx = xstate_required_size(vcpu->arch.xcr0, true);
 
 	vcpu->arch.eager_fpu = use_eager_fpu() || guest_cpuid_has_mpx(vcpu);
+	if (vcpu->arch.eager_fpu)
+		kvm_x86_ops->fpu_activate(vcpu);
 
 	/*
 	 * The existing code assumes virtual address is 48-bit in the canonical

arch/x86/kvm/iommu.c

@@ -200,6 +200,7 @@ int kvm_assign_device(struct kvm *kvm, struct pci_dev *pdev)
 			goto out_unmap;
 	}
 
+	kvm_arch_start_assignment(kvm);
 	pci_set_dev_assigned(pdev);
 
 	dev_info(&pdev->dev, "kvm assign device\n");
@@ -224,6 +225,7 @@ int kvm_deassign_device(struct kvm *kvm, struct pci_dev *pdev)
 	iommu_detach_device(domain, &pdev->dev);
 
 	pci_clear_dev_assigned(pdev);
+	kvm_arch_end_assignment(kvm);
 
 	dev_info(&pdev->dev, "kvm deassign device\n");
 

arch/x86/kvm/mmu.c

@@ -2479,6 +2479,14 @@ static int mmu_need_write_protect(struct kvm_vcpu *vcpu, gfn_t gfn,
 	return 0;
 }
 
+static bool kvm_is_mmio_pfn(pfn_t pfn)
+{
+	if (pfn_valid(pfn))
+		return !is_zero_pfn(pfn) && PageReserved(pfn_to_page(pfn));
+
+	return true;
+}
+
 static int set_spte(struct kvm_vcpu *vcpu, u64 *sptep,
 		    unsigned pte_access, int level,
 		    gfn_t gfn, pfn_t pfn, bool speculative,
@@ -2506,7 +2514,7 @@ static int set_spte(struct kvm_vcpu *vcpu, u64 *sptep,
 		spte |= PT_PAGE_SIZE_MASK;
 	if (tdp_enabled)
 		spte |= kvm_x86_ops->get_mt_mask(vcpu, gfn,
-			kvm_is_reserved_pfn(pfn));
+			kvm_is_mmio_pfn(pfn));
 
 	if (host_writable)
 		spte |= SPTE_HOST_WRITEABLE;

arch/x86/kvm/svm.c

@@ -865,6 +865,64 @@ static void svm_disable_lbrv(struct vcpu_svm *svm)
 	set_msr_interception(msrpm, MSR_IA32_LASTINTTOIP, 0, 0);
 }
 
+#define MTRR_TYPE_UC_MINUS	7
+#define MTRR2PROTVAL_INVALID 0xff
+
+static u8 mtrr2protval[8];
+
+static u8 fallback_mtrr_type(int mtrr)
+{
+	/*
+	 * WT and WP aren't always available in the host PAT.  Treat
+	 * them as UC and UC- respectively.  Everything else should be
+	 * there.
+	 */
+	switch (mtrr)
+	{
+	case MTRR_TYPE_WRTHROUGH:
+		return MTRR_TYPE_UNCACHABLE;
+	case MTRR_TYPE_WRPROT:
+		return MTRR_TYPE_UC_MINUS;
+	default:
+		BUG();
+	}
+}
+
+static void build_mtrr2protval(void)
+{
+	int i;
+	u64 pat;
+
+	for (i = 0; i < 8; i++)
+		mtrr2protval[i] = MTRR2PROTVAL_INVALID;
+
+	/* Ignore the invalid MTRR types.  */
+	mtrr2protval[2] = 0;
+	mtrr2protval[3] = 0;
+
+	/*
+	 * Use host PAT value to figure out the mapping from guest MTRR
+	 * values to nested page table PAT/PCD/PWT values.  We do not
+	 * want to change the host PAT value every time we enter the
+	 * guest.
+	 */
+	rdmsrl(MSR_IA32_CR_PAT, pat);
+	for (i = 0; i < 8; i++) {
+		u8 mtrr = pat >> (8 * i);
+
+		if (mtrr2protval[mtrr] == MTRR2PROTVAL_INVALID)
+			mtrr2protval[mtrr] = __cm_idx2pte(i);
+	}
+
+	for (i = 0; i < 8; i++) {
+		if (mtrr2protval[i] == MTRR2PROTVAL_INVALID) {
+			u8 fallback = fallback_mtrr_type(i);
+			mtrr2protval[i] = mtrr2protval[fallback];
+			BUG_ON(mtrr2protval[i] == MTRR2PROTVAL_INVALID);
+		}
+	}
+}
+
 static __init int svm_hardware_setup(void)
 {
 	int cpu;
@@ -931,6 +989,7 @@ static __init int svm_hardware_setup(void)
 	} else
 		kvm_disable_tdp();
 
+	build_mtrr2protval();
 	return 0;
 
 err:
@@ -1085,6 +1144,39 @@ static u64 svm_compute_tsc_offset(struct kvm_vcpu *vcpu, u64 target_tsc)
 	return target_tsc - tsc;
 }
 
+static void svm_set_guest_pat(struct vcpu_svm *svm, u64 *g_pat)
+{
+	struct kvm_vcpu *vcpu = &svm->vcpu;
+
+	/* Unlike Intel, AMD takes the guest's CR0.CD into account.
+	 *
+	 * AMD does not have IPAT.  To emulate it for the case of guests
+	 * with no assigned devices, just set everything to WB.  If guests
+	 * have assigned devices, however, we cannot force WB for RAM
+	 * pages only, so use the guest PAT directly.
+	 */
+	if (!kvm_arch_has_assigned_device(vcpu->kvm))
+		*g_pat = 0x0606060606060606;
+	else
+		*g_pat = vcpu->arch.pat;
+}
+
+static u64 svm_get_mt_mask(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio)
+{
+	u8 mtrr;
+
+	/*
+	 * 1. MMIO: trust guest MTRR, so same as item 3.
+	 * 2. No passthrough: always map as WB, and force guest PAT to WB as well
+	 * 3. Passthrough: can't guarantee the result, try to trust guest.
+	 */
+	if (!is_mmio && !kvm_arch_has_assigned_device(vcpu->kvm))
+		return 0;
+
+	mtrr = kvm_mtrr_get_guest_memory_type(vcpu, gfn);
+	return mtrr2protval[mtrr];
+}
+
 static void init_vmcb(struct vcpu_svm *svm, bool init_event)
 {
 	struct vmcb_control_area *control = &svm->vmcb->control;
@@ -1180,6 +1272,7 @@ static void init_vmcb(struct vcpu_svm *svm, bool init_event)
 		clr_cr_intercept(svm, INTERCEPT_CR3_READ);
 		clr_cr_intercept(svm, INTERCEPT_CR3_WRITE);
 		save->g_pat = svm->vcpu.arch.pat;
+		svm_set_guest_pat(svm, &save->g_pat);
 		save->cr3 = 0;
 		save->cr4 = 0;
 	}
@@ -3254,6 +3347,16 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr)
 	case MSR_VM_IGNNE:
 		vcpu_unimpl(vcpu, "unimplemented wrmsr: 0x%x data 0x%llx\n", ecx, data);
 		break;
+	case MSR_IA32_CR_PAT:
+		if (npt_enabled) {
+			if (!kvm_mtrr_valid(vcpu, MSR_IA32_CR_PAT, data))
+				return 1;
+			vcpu->arch.pat = data;
+			svm_set_guest_pat(svm, &svm->vmcb->save.g_pat);
+			mark_dirty(svm->vmcb, VMCB_NPT);
+			break;
+		}
+		/* fall through */
 	default:
 		return kvm_set_msr_common(vcpu, msr);
 	}
@@ -4088,11 +4191,6 @@ static bool svm_has_high_real_mode_segbase(void)
 	return true;
 }
 
-static u64 svm_get_mt_mask(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio)
-{
-	return 0;
-}
-
 static void svm_cpuid_update(struct kvm_vcpu *vcpu)
 {
 }

arch/x86/kvm/vmx.c

@@ -8632,22 +8632,17 @@ static u64 vmx_get_mt_mask(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio)
 	u64 ipat = 0;
 
 	/* For VT-d and EPT combination
-	 * 1. MMIO: always map as UC
+	 * 1. MMIO: guest may want to apply WC, trust it.
 	 * 2. EPT with VT-d:
 	 *   a. VT-d without snooping control feature: can't guarantee the
-	 *	result, try to trust guest.
+	 *	result, try to trust guest.  So the same as item 1.
 	 *   b. VT-d with snooping control feature: snooping control feature of
 	 *	VT-d engine can guarantee the cache correctness. Just set it
 	 *	to WB to keep consistent with host. So the same as item 3.
 	 * 3. EPT without VT-d: always map as WB and set IPAT=1 to keep
 	 *    consistent with host MTRR
 	 */
-	if (is_mmio) {
-		cache = MTRR_TYPE_UNCACHABLE;
-		goto exit;
-	}
-
-	if (!kvm_arch_has_noncoherent_dma(vcpu->kvm)) {
+	if (!is_mmio && !kvm_arch_has_noncoherent_dma(vcpu->kvm)) {
 		ipat = VMX_EPT_IPAT_BIT;
 		cache = MTRR_TYPE_WRBACK;
 		goto exit;

arch/x86/kvm/x86.c

@@ -3157,8 +3157,7 @@ static void load_xsave(struct kvm_vcpu *vcpu, u8 *src)
 			cpuid_count(XSTATE_CPUID, index,
 				    &size, &offset, &ecx, &edx);
 			memcpy(dest, src + offset, size);
-		} else
-			WARN_ON_ONCE(1);
+		}
 
 		valid -= feature;
 	}
@@ -7315,11 +7314,6 @@ struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm,
 
 	vcpu = kvm_x86_ops->vcpu_create(kvm, id);
 
-	/*
-	 * Activate fpu unconditionally in case the guest needs eager FPU.  It will be
-	 * deactivated soon if it doesn't.
-	 */
-	kvm_x86_ops->fpu_activate(vcpu);
 	return vcpu;
 }
 
@@ -8218,6 +8212,24 @@ bool kvm_arch_can_inject_async_page_present(struct kvm_vcpu *vcpu)
 			kvm_x86_ops->interrupt_allowed(vcpu);
 }
 
+void kvm_arch_start_assignment(struct kvm *kvm)
+{
+	atomic_inc(&kvm->arch.assigned_device_count);
+}
+EXPORT_SYMBOL_GPL(kvm_arch_start_assignment);
+
+void kvm_arch_end_assignment(struct kvm *kvm)
+{
+	atomic_dec(&kvm->arch.assigned_device_count);
+}
+EXPORT_SYMBOL_GPL(kvm_arch_end_assignment);
+
+bool kvm_arch_has_assigned_device(struct kvm *kvm)
+{
+	return atomic_read(&kvm->arch.assigned_device_count);
+}
+EXPORT_SYMBOL_GPL(kvm_arch_has_assigned_device);
+
 void kvm_arch_register_noncoherent_dma(struct kvm *kvm)
 {
 	atomic_inc(&kvm->arch.noncoherent_dma_count);

block/bio-integrity.c

@@ -51,7 +51,7 @@ struct bio_integrity_payload *bio_integrity_alloc(struct bio *bio,
 	unsigned long idx = BIO_POOL_NONE;
 	unsigned inline_vecs;
 
-	if (!bs) {
+	if (!bs || !bs->bio_integrity_pool) {
 		bip = kmalloc(sizeof(struct bio_integrity_payload) +
 			      sizeof(struct bio_vec) * nr_vecs, gfp_mask);
 		inline_vecs = nr_vecs;
@@ -104,7 +104,7 @@ void bio_integrity_free(struct bio *bio)
 		kfree(page_address(bip->bip_vec->bv_page) +
 		      bip->bip_vec->bv_offset);
 
-	if (bs) {
+	if (bs && bs->bio_integrity_pool) {
 		if (bip->bip_slab != BIO_POOL_NONE)
 			bvec_free(bs->bvec_integrity_pool, bip->bip_vec,
 				  bip->bip_slab);

block/blk-cgroup.c

@@ -29,6 +29,14 @@
 
 #define MAX_KEY_LEN 100
 
+/*
+ * blkcg_pol_mutex protects blkcg_policy[] and policy [de]activation.
+ * blkcg_pol_register_mutex nests outside of it and synchronizes entire
+ * policy [un]register operations including cgroup file additions /
+ * removals.  Putting cgroup file registration outside blkcg_pol_mutex
+ * allows grabbing it from cgroup callbacks.
+ */
+static DEFINE_MUTEX(blkcg_pol_register_mutex);
 static DEFINE_MUTEX(blkcg_pol_mutex);
 
 struct blkcg blkcg_root;
@@ -38,6 +46,8 @@ struct cgroup_subsys_state * const blkcg_root_css = &blkcg_root.css;
 
 static struct blkcg_policy *blkcg_policy[BLKCG_MAX_POLS];
 
+static LIST_HEAD(all_blkcgs);		/* protected by blkcg_pol_mutex */
+
 static bool blkcg_policy_enabled(struct request_queue *q,
 				 const struct blkcg_policy *pol)
 {
@@ -453,20 +463,7 @@ static int blkcg_reset_stats(struct cgroup_subsys_state *css,
 	struct blkcg_gq *blkg;
 	int i;
 
-	/*
-	 * XXX: We invoke cgroup_add/rm_cftypes() under blkcg_pol_mutex
-	 * which ends up putting cgroup's internal cgroup_tree_mutex under
-	 * it; however, cgroup_tree_mutex is nested above cgroup file
-	 * active protection and grabbing blkcg_pol_mutex from a cgroup
-	 * file operation creates a possible circular dependency.  cgroup
-	 * internal locking is planned to go through further simplification
-	 * and this issue should go away soon.  For now, let's trylock
-	 * blkcg_pol_mutex and restart the write on failure.
-	 *
-	 * http://lkml.kernel.org/g/5363C04B.4010400@oracle.com
-	 */
-	if (!mutex_trylock(&blkcg_pol_mutex))
-		return restart_syscall();
+	mutex_lock(&blkcg_pol_mutex);
 	spin_lock_irq(&blkcg->lock);
 
 	/*
@@ -822,8 +819,17 @@ static void blkcg_css_free(struct cgroup_subsys_state *css)
 {
 	struct blkcg *blkcg = css_to_blkcg(css);
 
-	if (blkcg != &blkcg_root)
+	mutex_lock(&blkcg_pol_mutex);
+	list_del(&blkcg->all_blkcgs_node);
+	mutex_unlock(&blkcg_pol_mutex);
+
+	if (blkcg != &blkcg_root) {
+		int i;
+
+		for (i = 0; i < BLKCG_MAX_POLS; i++)
+			kfree(blkcg->pd[i]);
 		kfree(blkcg);
+	}
 }
 
 static struct cgroup_subsys_state *
@@ -833,6 +839,8 @@ blkcg_css_alloc(struct cgroup_subsys_state *parent_css)
 	struct cgroup_subsys_state *ret;
 	int i;
 
+	mutex_lock(&blkcg_pol_mutex);
+
 	if (!parent_css) {
 		blkcg = &blkcg_root;
 		goto done;
@@ -875,14 +883,17 @@ done:
 #ifdef CONFIG_CGROUP_WRITEBACK
 	INIT_LIST_HEAD(&blkcg->cgwb_list);
 #endif
+	list_add_tail(&blkcg->all_blkcgs_node, &all_blkcgs);
+
+	mutex_unlock(&blkcg_pol_mutex);
 	return &blkcg->css;
 
 free_pd_blkcg:
 	for (i--; i >= 0; i--)
 		kfree(blkcg->pd[i]);
-
 free_blkcg:
 	kfree(blkcg);
+	mutex_unlock(&blkcg_pol_mutex);
 	return ret;
 }
 
@@ -1037,10 +1048,8 @@ int blkcg_activate_policy(struct request_queue *q,
 			  const struct blkcg_policy *pol)
 {
 	LIST_HEAD(pds);
-	LIST_HEAD(cpds);
 	struct blkcg_gq *blkg;
 	struct blkg_policy_data *pd, *nd;
-	struct blkcg_policy_data *cpd, *cnd;
 	int cnt = 0, ret;
 
 	if (blkcg_policy_enabled(q, pol))
@@ -1053,10 +1062,7 @@ int blkcg_activate_policy(struct request_queue *q,
 		cnt++;
 	spin_unlock_irq(q->queue_lock);
 
-	/*
-	 * Allocate per-blkg and per-blkcg policy data
-	 * for all existing blkgs.
-	 */
+	/* allocate per-blkg policy data for all existing blkgs */
 	while (cnt--) {
 		pd = kzalloc_node(pol->pd_size, GFP_KERNEL, q->node);
 		if (!pd) {
@@ -1064,15 +1070,6 @@ int blkcg_activate_policy(struct request_queue *q,
 			goto out_free;
 		}
 		list_add_tail(&pd->alloc_node, &pds);
-
-		if (!pol->cpd_size)
-			continue;
-		cpd = kzalloc_node(pol->cpd_size, GFP_KERNEL, q->node);
-		if (!cpd) {
-			ret = -ENOMEM;
-			goto out_free;
-		}
-		list_add_tail(&cpd->alloc_node, &cpds);
 	}
 
 	/*
@@ -1082,32 +1079,17 @@ int blkcg_activate_policy(struct request_queue *q,
 	spin_lock_irq(q->queue_lock);
 
 	list_for_each_entry(blkg, &q->blkg_list, q_node) {
-		if (WARN_ON(list_empty(&pds)) ||
-		    WARN_ON(pol->cpd_size && list_empty(&cpds))) {
+		if (WARN_ON(list_empty(&pds))) {
 			/* umm... this shouldn't happen, just abort */
 			ret = -ENOMEM;
 			goto out_unlock;
 		}
-		cpd = list_first_entry(&cpds, struct blkcg_policy_data,
-				       alloc_node);
-		list_del_init(&cpd->alloc_node);
 		pd = list_first_entry(&pds, struct blkg_policy_data, alloc_node);
 		list_del_init(&pd->alloc_node);
 
 		/* grab blkcg lock too while installing @pd on @blkg */
 		spin_lock(&blkg->blkcg->lock);
 
-		if (!pol->cpd_size)
-			goto no_cpd;
-		if (!blkg->blkcg->pd[pol->plid]) {
-			/* Per-policy per-blkcg data */
-			blkg->blkcg->pd[pol->plid] = cpd;
-			cpd->plid = pol->plid;
-			pol->cpd_init_fn(blkg->blkcg);
-		} else { /* must free it as it has already been extracted */
-			kfree(cpd);
-		}
-no_cpd:
 		blkg->pd[pol->plid] = pd;
 		pd->blkg = blkg;
 		pd->plid = pol->plid;
@@ -1124,8 +1106,6 @@ out_free:
 	blk_queue_bypass_end(q);
 	list_for_each_entry_safe(pd, nd, &pds, alloc_node)
 		kfree(pd);
-	list_for_each_entry_safe(cpd, cnd, &cpds, alloc_node)
-		kfree(cpd);
 	return ret;
 }
 EXPORT_SYMBOL_GPL(blkcg_activate_policy);
@@ -1162,8 +1142,6 @@ void blkcg_deactivate_policy(struct request_queue *q,
 
 		kfree(blkg->pd[pol->plid]);
 		blkg->pd[pol->plid] = NULL;
-		kfree(blkg->blkcg->pd[pol->plid]);
-		blkg->blkcg->pd[pol->plid] = NULL;
 
 		spin_unlock(&blkg->blkcg->lock);
 	}
@@ -1182,11 +1160,13 @@ EXPORT_SYMBOL_GPL(blkcg_deactivate_policy);
  */
 int blkcg_policy_register(struct blkcg_policy *pol)
 {
+	struct blkcg *blkcg;
 	int i, ret;
 
 	if (WARN_ON(pol->pd_size < sizeof(struct blkg_policy_data)))
 		return -EINVAL;
 
+	mutex_lock(&blkcg_pol_register_mutex);
 	mutex_lock(&blkcg_pol_mutex);
 
 	/* find an empty slot */
@@ -1195,19 +1175,49 @@ int blkcg_policy_register(struct blkcg_policy *pol)
 		if (!blkcg_policy[i])
 			break;
 	if (i >= BLKCG_MAX_POLS)
-		goto out_unlock;
+		goto err_unlock;
 
-	/* register and update blkgs */
+	/* register @pol */
 	pol->plid = i;
-	blkcg_policy[i] = pol;
+	blkcg_policy[pol->plid] = pol;
+
+	/* allocate and install cpd's */
+	if (pol->cpd_size) {
+		list_for_each_entry(blkcg, &all_blkcgs, all_blkcgs_node) {
+			struct blkcg_policy_data *cpd;
+
+			cpd = kzalloc(pol->cpd_size, GFP_KERNEL);
+			if (!cpd) {
+				mutex_unlock(&blkcg_pol_mutex);
+				goto err_free_cpds;
+			}
+
+			blkcg->pd[pol->plid] = cpd;
+			cpd->plid = pol->plid;
+			pol->cpd_init_fn(blkcg);
+		}
+	}
+
+	mutex_unlock(&blkcg_pol_mutex);
 
 	/* everything is in place, add intf files for the new policy */
 	if (pol->cftypes)
 		WARN_ON(cgroup_add_legacy_cftypes(&blkio_cgrp_subsys,
 						  pol->cftypes));
-	ret = 0;
-out_unlock:
+	mutex_unlock(&blkcg_pol_register_mutex);
+	return 0;
+
+err_free_cpds:
+	if (pol->cpd_size) {
+		list_for_each_entry(blkcg, &all_blkcgs, all_blkcgs_node) {
+			kfree(blkcg->pd[pol->plid]);
+			blkcg->pd[pol->plid] = NULL;
+		}
+	}
+	blkcg_policy[pol->plid] = NULL;
+err_unlock:
 	mutex_unlock(&blkcg_pol_mutex);
+	mutex_unlock(&blkcg_pol_register_mutex);
 	return ret;
 }
 EXPORT_SYMBOL_GPL(blkcg_policy_register);
@@ -1220,7 +1230,9 @@ EXPORT_SYMBOL_GPL(blkcg_policy_register);
  */
 void blkcg_policy_unregister(struct blkcg_policy *pol)
 {
-	mutex_lock(&blkcg_pol_mutex);
+	struct blkcg *blkcg;
+
+	mutex_lock(&blkcg_pol_register_mutex);
 
 	if (WARN_ON(blkcg_policy[pol->plid] != pol))
 		goto out_unlock;
@@ -1229,9 +1241,19 @@ void blkcg_policy_unregister(struct blkcg_policy *pol)
 	if (pol->cftypes)
 		cgroup_rm_cftypes(pol->cftypes);
 
-	/* unregister and update blkgs */
+	/* remove cpds and unregister */
+	mutex_lock(&blkcg_pol_mutex);
+
+	if (pol->cpd_size) {
+		list_for_each_entry(blkcg, &all_blkcgs, all_blkcgs_node) {
+			kfree(blkcg->pd[pol->plid]);
+			blkcg->pd[pol->plid] = NULL;
+		}
+	}
 	blkcg_policy[pol->plid] = NULL;
-out_unlock:
+
 	mutex_unlock(&blkcg_pol_mutex);
+out_unlock:
+	mutex_unlock(&blkcg_pol_register_mutex);
 }
 EXPORT_SYMBOL_GPL(blkcg_policy_unregister);

block/blk-core.c

@@ -3370,7 +3370,7 @@ EXPORT_SYMBOL(blk_post_runtime_resume);
 int __init blk_dev_init(void)
 {
 	BUILD_BUG_ON(__REQ_NR_BITS > 8 *
-			sizeof(((struct request *)0)->cmd_flags));
+			FIELD_SIZEOF(struct request, cmd_flags));
 
 	/* used for unplugging and affects IO latency/throughput - HIGHPRI */
 	kblockd_workqueue = alloc_workqueue("kblockd",

block/blk-mq.c

@@ -1998,7 +1998,7 @@ struct request_queue *blk_mq_init_allocated_queue(struct blk_mq_tag_set *set,
 		goto err_hctxs;
 
 	setup_timer(&q->timeout, blk_mq_rq_timer, (unsigned long) q);
-	blk_queue_rq_timeout(q, set->timeout ? set->timeout : 30000);
+	blk_queue_rq_timeout(q, set->timeout ? set->timeout : 30 * HZ);
 
 	q->nr_queues = nr_cpu_ids;
 	q->nr_hw_queues = set->nr_hw_queues;

drivers/acpi/Makefile

@@ -24,7 +24,7 @@ acpi-y				+= nvs.o
 # Power management related files
 acpi-y				+= wakeup.o
 acpi-$(CONFIG_ACPI_SYSTEM_POWER_STATES_SUPPORT) += sleep.o
-acpi-y				+= device_pm.o
+acpi-y				+= device_sysfs.o device_pm.o
 acpi-$(CONFIG_ACPI_SLEEP)	+= proc.o
 
 

drivers/acpi/bus.c

@@ -423,6 +423,413 @@ static void acpi_bus_notify(acpi_handle handle, u32 type, void *data)
 	acpi_evaluate_ost(handle, type, ost_code, NULL);
 }
 
+static void acpi_device_notify(acpi_handle handle, u32 event, void *data)
+{
+	struct acpi_device *device = data;
+
+	device->driver->ops.notify(device, event);
+}
+
+static void acpi_device_notify_fixed(void *data)
+{
+	struct acpi_device *device = data;
+
+	/* Fixed hardware devices have no handles */
+	acpi_device_notify(NULL, ACPI_FIXED_HARDWARE_EVENT, device);
+}
+
+static u32 acpi_device_fixed_event(void *data)
+{
+	acpi_os_execute(OSL_NOTIFY_HANDLER, acpi_device_notify_fixed, data);
+	return ACPI_INTERRUPT_HANDLED;
+}
+
+static int acpi_device_install_notify_handler(struct acpi_device *device)
+{
+	acpi_status status;
+
+	if (device->device_type == ACPI_BUS_TYPE_POWER_BUTTON)
+		status =
+		    acpi_install_fixed_event_handler(ACPI_EVENT_POWER_BUTTON,
+						     acpi_device_fixed_event,
+						     device);
+	else if (device->device_type == ACPI_BUS_TYPE_SLEEP_BUTTON)
+		status =
+		    acpi_install_fixed_event_handler(ACPI_EVENT_SLEEP_BUTTON,
+						     acpi_device_fixed_event,
+						     device);
+	else
+		status = acpi_install_notify_handler(device->handle,
+						     ACPI_DEVICE_NOTIFY,
+						     acpi_device_notify,
+						     device);
+
+	if (ACPI_FAILURE(status))
+		return -EINVAL;
+	return 0;
+}
+
+static void acpi_device_remove_notify_handler(struct acpi_device *device)
+{
+	if (device->device_type == ACPI_BUS_TYPE_POWER_BUTTON)
+		acpi_remove_fixed_event_handler(ACPI_EVENT_POWER_BUTTON,
+						acpi_device_fixed_event);
+	else if (device->device_type == ACPI_BUS_TYPE_SLEEP_BUTTON)
+		acpi_remove_fixed_event_handler(ACPI_EVENT_SLEEP_BUTTON,
+						acpi_device_fixed_event);
+	else
+		acpi_remove_notify_handler(device->handle, ACPI_DEVICE_NOTIFY,
+					   acpi_device_notify);
+}
+
+/* --------------------------------------------------------------------------
+                             Device Matching
+   -------------------------------------------------------------------------- */
+
+/**
+ * acpi_device_is_first_physical_node - Is given dev first physical node
+ * @adev: ACPI companion device
+ * @dev: Physical device to check
+ *
+ * Function checks if given @dev is the first physical devices attached to
+ * the ACPI companion device. This distinction is needed in some cases
+ * where the same companion device is shared between many physical devices.
+ *
+ * Note that the caller have to provide valid @adev pointer.
+ */
+bool acpi_device_is_first_physical_node(struct acpi_device *adev,
+					const struct device *dev)
+{
+	bool ret = false;
+
+	mutex_lock(&adev->physical_node_lock);
+	if (!list_empty(&adev->physical_node_list)) {
+		const struct acpi_device_physical_node *node;
+
+		node = list_first_entry(&adev->physical_node_list,
+					struct acpi_device_physical_node, node);
+		ret = node->dev == dev;
+	}
+	mutex_unlock(&adev->physical_node_lock);
+
+	return ret;
+}
+
+/*
+ * acpi_companion_match() - Can we match via ACPI companion device
+ * @dev: Device in question
+ *
+ * Check if the given device has an ACPI companion and if that companion has
+ * a valid list of PNP IDs, and if the device is the first (primary) physical
+ * device associated with it.  Return the companion pointer if that's the case
+ * or NULL otherwise.
+ *
+ * If multiple physical devices are attached to a single ACPI companion, we need
+ * to be careful.  The usage scenario for this kind of relationship is that all
+ * of the physical devices in question use resources provided by the ACPI
+ * companion.  A typical case is an MFD device where all the sub-devices share
+ * the parent's ACPI companion.  In such cases we can only allow the primary
+ * (first) physical device to be matched with the help of the companion's PNP
+ * IDs.
+ *
+ * Additional physical devices sharing the ACPI companion can still use
+ * resources available from it but they will be matched normally using functions
+ * provided by their bus types (and analogously for their modalias).
+ */
+struct acpi_device *acpi_companion_match(const struct device *dev)
+{
+	struct acpi_device *adev;
+	struct mutex *physical_node_lock;
+
+	adev = ACPI_COMPANION(dev);
+	if (!adev)
+		return NULL;
+
+	if (list_empty(&adev->pnp.ids))
+		return NULL;
+
+	physical_node_lock = &adev->physical_node_lock;
+	mutex_lock(physical_node_lock);
+	if (list_empty(&adev->physical_node_list)) {
+		adev = NULL;
+	} else {
+		const struct acpi_device_physical_node *node;
+
+		node = list_first_entry(&adev->physical_node_list,
+					struct acpi_device_physical_node, node);
+		if (node->dev != dev)
+			adev = NULL;
+	}
+	mutex_unlock(physical_node_lock);
+
+	return adev;
+}
+
+/**
+ * acpi_of_match_device - Match device object using the "compatible" property.
+ * @adev: ACPI device object to match.
+ * @of_match_table: List of device IDs to match against.
+ *
+ * If @dev has an ACPI companion which has ACPI_DT_NAMESPACE_HID in its list of
+ * identifiers and a _DSD object with the "compatible" property, use that
+ * property to match against the given list of identifiers.
+ */
+static bool acpi_of_match_device(struct acpi_device *adev,
+				 const struct of_device_id *of_match_table)
+{
+	const union acpi_object *of_compatible, *obj;
+	int i, nval;
+
+	if (!adev)
+		return false;
+
+	of_compatible = adev->data.of_compatible;
+	if (!of_match_table || !of_compatible)
+		return false;
+
+	if (of_compatible->type == ACPI_TYPE_PACKAGE) {
+		nval = of_compatible->package.count;
+		obj = of_compatible->package.elements;
+	} else { /* Must be ACPI_TYPE_STRING. */
+		nval = 1;
+		obj = of_compatible;
+	}
+	/* Now we can look for the driver DT compatible strings */
+	for (i = 0; i < nval; i++, obj++) {
+		const struct of_device_id *id;
+
+		for (id = of_match_table; id->compatible[0]; id++)
+			if (!strcasecmp(obj->string.pointer, id->compatible))
+				return true;
+	}
+
+	return false;
+}
+
+static bool __acpi_match_device_cls(const struct acpi_device_id *id,
+				    struct acpi_hardware_id *hwid)
+{
+	int i, msk, byte_shift;
+	char buf[3];
+
+	if (!id->cls)
+		return false;
+
+	/* Apply class-code bitmask, before checking each class-code byte */
+	for (i = 1; i <= 3; i++) {
+		byte_shift = 8 * (3 - i);
+		msk = (id->cls_msk >> byte_shift) & 0xFF;
+		if (!msk)
+			continue;
+
+		sprintf(buf, "%02x", (id->cls >> byte_shift) & msk);
+		if (strncmp(buf, &hwid->id[(i - 1) * 2], 2))
+			return false;
+	}
+	return true;
+}
+
+static const struct acpi_device_id *__acpi_match_device(
+	struct acpi_device *device,
+	const struct acpi_device_id *ids,
+	const struct of_device_id *of_ids)
+{
+	const struct acpi_device_id *id;
+	struct acpi_hardware_id *hwid;
+
+	/*
+	 * If the device is not present, it is unnecessary to load device
+	 * driver for it.
+	 */
+	if (!device || !device->status.present)
+		return NULL;
+
+	list_for_each_entry(hwid, &device->pnp.ids, list) {
+		/* First, check the ACPI/PNP IDs provided by the caller. */
+		for (id = ids; id->id[0] || id->cls; id++) {
+			if (id->id[0] && !strcmp((char *) id->id, hwid->id))
+				return id;
+			else if (id->cls && __acpi_match_device_cls(id, hwid))
+				return id;
+		}
+
+		/*
+		 * Next, check ACPI_DT_NAMESPACE_HID and try to match the
+		 * "compatible" property if found.
+		 *
+		 * The id returned by the below is not valid, but the only
+		 * caller passing non-NULL of_ids here is only interested in
+		 * whether or not the return value is NULL.
+		 */
+		if (!strcmp(ACPI_DT_NAMESPACE_HID, hwid->id)
+		    && acpi_of_match_device(device, of_ids))
+			return id;
+	}
+	return NULL;
+}
+
+/**
+ * acpi_match_device - Match a struct device against a given list of ACPI IDs
+ * @ids: Array of struct acpi_device_id object to match against.
+ * @dev: The device structure to match.
+ *
+ * Check if @dev has a valid ACPI handle and if there is a struct acpi_device
+ * object for that handle and use that object to match against a given list of
+ * device IDs.
+ *
+ * Return a pointer to the first matching ID on success or %NULL on failure.
+ */
+const struct acpi_device_id *acpi_match_device(const struct acpi_device_id *ids,
+					       const struct device *dev)
+{
+	return __acpi_match_device(acpi_companion_match(dev), ids, NULL);
+}
+EXPORT_SYMBOL_GPL(acpi_match_device);
+
+int acpi_match_device_ids(struct acpi_device *device,
+			  const struct acpi_device_id *ids)
+{
+	return __acpi_match_device(device, ids, NULL) ? 0 : -ENOENT;
+}
+EXPORT_SYMBOL(acpi_match_device_ids);
+
+bool acpi_driver_match_device(struct device *dev,
+			      const struct device_driver *drv)
+{
+	if (!drv->acpi_match_table)
+		return acpi_of_match_device(ACPI_COMPANION(dev),
+					    drv->of_match_table);
+
+	return !!__acpi_match_device(acpi_companion_match(dev),
+				     drv->acpi_match_table, drv->of_match_table);
+}
+EXPORT_SYMBOL_GPL(acpi_driver_match_device);
+
+/* --------------------------------------------------------------------------
+                              ACPI Driver Management
+   -------------------------------------------------------------------------- */
+
+/**
+ * acpi_bus_register_driver - register a driver with the ACPI bus
+ * @driver: driver being registered
+ *
+ * Registers a driver with the ACPI bus.  Searches the namespace for all
+ * devices that match the driver's criteria and binds.  Returns zero for
+ * success or a negative error status for failure.
+ */
+int acpi_bus_register_driver(struct acpi_driver *driver)
+{
+	int ret;
+
+	if (acpi_disabled)
+		return -ENODEV;
+	driver->drv.name = driver->name;
+	driver->drv.bus = &acpi_bus_type;
+	driver->drv.owner = driver->owner;
+
+	ret = driver_register(&driver->drv);
+	return ret;
+}
+
+EXPORT_SYMBOL(acpi_bus_register_driver);
+
+/**
+ * acpi_bus_unregister_driver - unregisters a driver with the ACPI bus
+ * @driver: driver to unregister
+ *
+ * Unregisters a driver with the ACPI bus.  Searches the namespace for all
+ * devices that match the driver's criteria and unbinds.
+ */
+void acpi_bus_unregister_driver(struct acpi_driver *driver)
+{
+	driver_unregister(&driver->drv);
+}
+
+EXPORT_SYMBOL(acpi_bus_unregister_driver);
+
+/* --------------------------------------------------------------------------
+                              ACPI Bus operations
+   -------------------------------------------------------------------------- */
+
+static int acpi_bus_match(struct device *dev, struct device_driver *drv)
+{
+	struct acpi_device *acpi_dev = to_acpi_device(dev);
+	struct acpi_driver *acpi_drv = to_acpi_driver(drv);
+
+	return acpi_dev->flags.match_driver
+		&& !acpi_match_device_ids(acpi_dev, acpi_drv->ids);
+}
+
+static int acpi_device_uevent(struct device *dev, struct kobj_uevent_env *env)
+{
+	return __acpi_device_uevent_modalias(to_acpi_device(dev), env);
+}
+
+static int acpi_device_probe(struct device *dev)
+{
+	struct acpi_device *acpi_dev = to_acpi_device(dev);
+	struct acpi_driver *acpi_drv = to_acpi_driver(dev->driver);
+	int ret;
+
+	if (acpi_dev->handler && !acpi_is_pnp_device(acpi_dev))
+		return -EINVAL;
+
+	if (!acpi_drv->ops.add)
+		return -ENOSYS;
+
+	ret = acpi_drv->ops.add(acpi_dev);
+	if (ret)
+		return ret;
+
+	acpi_dev->driver = acpi_drv;
+	ACPI_DEBUG_PRINT((ACPI_DB_INFO,
+			  "Driver [%s] successfully bound to device [%s]\n",
+			  acpi_drv->name, acpi_dev->pnp.bus_id));
+
+	if (acpi_drv->ops.notify) {
+		ret = acpi_device_install_notify_handler(acpi_dev);
+		if (ret) {
+			if (acpi_drv->ops.remove)
+				acpi_drv->ops.remove(acpi_dev);
+
+			acpi_dev->driver = NULL;
+			acpi_dev->driver_data = NULL;
+			return ret;
+		}
+	}
+
+	ACPI_DEBUG_PRINT((ACPI_DB_INFO, "Found driver [%s] for device [%s]\n",
+			  acpi_drv->name, acpi_dev->pnp.bus_id));
+	get_device(dev);
+	return 0;
+}
+
+static int acpi_device_remove(struct device * dev)
+{
+	struct acpi_device *acpi_dev = to_acpi_device(dev);
+	struct acpi_driver *acpi_drv = acpi_dev->driver;
+
+	if (acpi_drv) {
+		if (acpi_drv->ops.notify)
+			acpi_device_remove_notify_handler(acpi_dev);
+		if (acpi_drv->ops.remove)
+			acpi_drv->ops.remove(acpi_dev);
+	}
+	acpi_dev->driver = NULL;
+	acpi_dev->driver_data = NULL;
+
+	put_device(dev);
+	return 0;
+}
+
+struct bus_type acpi_bus_type = {
+	.name		= "acpi",
+	.match		= acpi_bus_match,
+	.probe		= acpi_device_probe,
+	.remove		= acpi_device_remove,
+	.uevent		= acpi_device_uevent,
+};
+
 /* --------------------------------------------------------------------------
                              Initialization/Cleanup
    -------------------------------------------------------------------------- */
@@ -661,7 +1068,9 @@ static int __init acpi_bus_init(void)
 	 */
 	acpi_root_dir = proc_mkdir(ACPI_BUS_FILE_ROOT, NULL);
 
-	return 0;
+	result = bus_register(&acpi_bus_type);
+	if (!result)
+		return 0;
 
 	/* Mimic structured exception handling */
       error1:

drivers/acpi/device_sysfs.c

@@ -0,0 +1,521 @@
+/*
+ * drivers/acpi/device_sysfs.c - ACPI device sysfs attributes and modalias.
+ *
+ * Copyright (C) 2015, Intel Corp.
+ * Author: Mika Westerberg <mika.westerberg@linux.intel.com>
+ * Author: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
+ *
+ * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+ *
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of the GNU General Public License version 2 as published
+ *  by the Free Software Foundation.
+ *
+ *  This program is distributed in the hope that it will be useful, but
+ *  WITHOUT ANY WARRANTY; without even the implied warranty of
+ *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ *  General Public License for more details.
+ *
+ * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+ */
+
+#include <linux/acpi.h>
+#include <linux/device.h>
+#include <linux/export.h>
+#include <linux/nls.h>
+
+#include "internal.h"
+
+/**
+ * create_pnp_modalias - Create hid/cid(s) string for modalias and uevent
+ * @acpi_dev: ACPI device object.
+ * @modalias: Buffer to print into.
+ * @size: Size of the buffer.
+ *
+ * Creates hid/cid(s) string needed for modalias and uevent
+ * e.g. on a device with hid:IBM0001 and cid:ACPI0001 you get:
+ * char *modalias: "acpi:IBM0001:ACPI0001"
+ * Return: 0: no _HID and no _CID
+ *         -EINVAL: output error
+ *         -ENOMEM: output is truncated
+*/
+static int create_pnp_modalias(struct acpi_device *acpi_dev, char *modalias,
+			       int size)
+{
+	int len;
+	int count;
+	struct acpi_hardware_id *id;
+
+	/*
+	 * Since we skip ACPI_DT_NAMESPACE_HID from the modalias below, 0 should
+	 * be returned if ACPI_DT_NAMESPACE_HID is the only ACPI/PNP ID in the
+	 * device's list.
+	 */
+	count = 0;
+	list_for_each_entry(id, &acpi_dev->pnp.ids, list)
+		if (strcmp(id->id, ACPI_DT_NAMESPACE_HID))
+			count++;
+
+	if (!count)
+		return 0;
+
+	len = snprintf(modalias, size, "acpi:");
+	if (len <= 0)
+		return len;
+
+	size -= len;
+
+	list_for_each_entry(id, &acpi_dev->pnp.ids, list) {
+		if (!strcmp(id->id, ACPI_DT_NAMESPACE_HID))
+			continue;
+
+		count = snprintf(&modalias[len], size, "%s:", id->id);
+		if (count < 0)
+			return -EINVAL;
+
+		if (count >= size)
+			return -ENOMEM;
+
+		len += count;
+		size -= count;
+	}
+	modalias[len] = '\0';
+	return len;
+}
+
+/**
+ * create_of_modalias - Creates DT compatible string for modalias and uevent
+ * @acpi_dev: ACPI device object.
+ * @modalias: Buffer to print into.
+ * @size: Size of the buffer.
+ *
+ * Expose DT compatible modalias as of:NnameTCcompatible.  This function should
+ * only be called for devices having ACPI_DT_NAMESPACE_HID in their list of
+ * ACPI/PNP IDs.
+ */
+static int create_of_modalias(struct acpi_device *acpi_dev, char *modalias,
+			      int size)
+{
+	struct acpi_buffer buf = { ACPI_ALLOCATE_BUFFER };
+	const union acpi_object *of_compatible, *obj;
+	int len, count;
+	int i, nval;
+	char *c;
+
+	acpi_get_name(acpi_dev->handle, ACPI_SINGLE_NAME, &buf);
+	/* DT strings are all in lower case */
+	for (c = buf.pointer; *c != '\0'; c++)
+		*c = tolower(*c);
+
+	len = snprintf(modalias, size, "of:N%sT", (char *)buf.pointer);
+	ACPI_FREE(buf.pointer);
+
+	if (len <= 0)
+		return len;
+
+	of_compatible = acpi_dev->data.of_compatible;
+	if (of_compatible->type == ACPI_TYPE_PACKAGE) {
+		nval = of_compatible->package.count;
+		obj = of_compatible->package.elements;
+	} else { /* Must be ACPI_TYPE_STRING. */
+		nval = 1;
+		obj = of_compatible;
+	}
+	for (i = 0; i < nval; i++, obj++) {
+		count = snprintf(&modalias[len], size, "C%s",
+				 obj->string.pointer);
+		if (count < 0)
+			return -EINVAL;
+
+		if (count >= size)
+			return -ENOMEM;
+
+		len += count;
+		size -= count;
+	}
+	modalias[len] = '\0';
+	return len;
+}
+
+int __acpi_device_uevent_modalias(struct acpi_device *adev,
+				  struct kobj_uevent_env *env)
+{
+	int len;
+
+	if (!adev)
+		return -ENODEV;
+
+	if (list_empty(&adev->pnp.ids))
+		return 0;
+
+	if (add_uevent_var(env, "MODALIAS="))
+		return -ENOMEM;
+
+	len = create_pnp_modalias(adev, &env->buf[env->buflen - 1],
+				  sizeof(env->buf) - env->buflen);
+	if (len < 0)
+		return len;
+
+	env->buflen += len;
+	if (!adev->data.of_compatible)
+		return 0;
+
+	if (len > 0 && add_uevent_var(env, "MODALIAS="))
+		return -ENOMEM;
+
+	len = create_of_modalias(adev, &env->buf[env->buflen - 1],
+				 sizeof(env->buf) - env->buflen);
+	if (len < 0)
+		return len;
+
+	env->buflen += len;
+
+	return 0;
+}
+
+/**
+ * acpi_device_uevent_modalias - uevent modalias for ACPI-enumerated devices.
+ *
+ * Create the uevent modalias field for ACPI-enumerated devices.
+ *
+ * Because other buses do not support ACPI HIDs & CIDs, e.g. for a device with
+ * hid:IBM0001 and cid:ACPI0001 you get: "acpi:IBM0001:ACPI0001".
+ */
+int acpi_device_uevent_modalias(struct device *dev, struct kobj_uevent_env *env)
+{
+	return __acpi_device_uevent_modalias(acpi_companion_match(dev), env);
+}
+EXPORT_SYMBOL_GPL(acpi_device_uevent_modalias);
+
+static int __acpi_device_modalias(struct acpi_device *adev, char *buf, int size)
+{
+	int len, count;
+
+	if (!adev)
+		return -ENODEV;
+
+	if (list_empty(&adev->pnp.ids))
+		return 0;
+
+	len = create_pnp_modalias(adev, buf, size - 1);
+	if (len < 0) {
+		return len;
+	} else if (len > 0) {
+		buf[len++] = '\n';
+		size -= len;
+	}
+	if (!adev->data.of_compatible)
+		return len;
+
+	count = create_of_modalias(adev, buf + len, size - 1);
+	if (count < 0) {
+		return count;
+	} else if (count > 0) {
+		len += count;
+		buf[len++] = '\n';
+	}
+
+	return len;
+}
+
+/**
+ * acpi_device_modalias - modalias sysfs attribute for ACPI-enumerated devices.
+ *
+ * Create the modalias sysfs attribute for ACPI-enumerated devices.
+ *
+ * Because other buses do not support ACPI HIDs & CIDs, e.g. for a device with
+ * hid:IBM0001 and cid:ACPI0001 you get: "acpi:IBM0001:ACPI0001".
+ */
+int acpi_device_modalias(struct device *dev, char *buf, int size)
+{
+	return __acpi_device_modalias(acpi_companion_match(dev), buf, size);
+}
+EXPORT_SYMBOL_GPL(acpi_device_modalias);
+
+static ssize_t
+acpi_device_modalias_show(struct device *dev, struct device_attribute *attr, char *buf) {
+	return __acpi_device_modalias(to_acpi_device(dev), buf, 1024);
+}
+static DEVICE_ATTR(modalias, 0444, acpi_device_modalias_show, NULL);
+
+static ssize_t real_power_state_show(struct device *dev,
+				     struct device_attribute *attr, char *buf)
+{
+	struct acpi_device *adev = to_acpi_device(dev);
+	int state;
+	int ret;
+
+	ret = acpi_device_get_power(adev, &state);
+	if (ret)
+		return ret;
+
+	return sprintf(buf, "%s\n", acpi_power_state_string(state));
+}
+
+static DEVICE_ATTR(real_power_state, 0444, real_power_state_show, NULL);
+
+static ssize_t power_state_show(struct device *dev,
+				struct device_attribute *attr, char *buf)
+{
+	struct acpi_device *adev = to_acpi_device(dev);
+
+	return sprintf(buf, "%s\n", acpi_power_state_string(adev->power.state));
+}
+
+static DEVICE_ATTR(power_state, 0444, power_state_show, NULL);
+
+static ssize_t
+acpi_eject_store(struct device *d, struct device_attribute *attr,
+		const char *buf, size_t count)
+{
+	struct acpi_device *acpi_device = to_acpi_device(d);
+	acpi_object_type not_used;
+	acpi_status status;
+
+	if (!count || buf[0] != '1')
+		return -EINVAL;
+
+	if ((!acpi_device->handler || !acpi_device->handler->hotplug.enabled)
+	    && !acpi_device->driver)
+		return -ENODEV;
+
+	status = acpi_get_type(acpi_device->handle, &not_used);
+	if (ACPI_FAILURE(status) || !acpi_device->flags.ejectable)
+		return -ENODEV;
+
+	get_device(&acpi_device->dev);
+	status = acpi_hotplug_schedule(acpi_device, ACPI_OST_EC_OSPM_EJECT);
+	if (ACPI_SUCCESS(status))
+		return count;
+
+	put_device(&acpi_device->dev);
+	acpi_evaluate_ost(acpi_device->handle, ACPI_OST_EC_OSPM_EJECT,
+			  ACPI_OST_SC_NON_SPECIFIC_FAILURE, NULL);
+	return status == AE_NO_MEMORY ? -ENOMEM : -EAGAIN;
+}
+
+static DEVICE_ATTR(eject, 0200, NULL, acpi_eject_store);
+
+static ssize_t
+acpi_device_hid_show(struct device *dev, struct device_attribute *attr, char *buf) {
+	struct acpi_device *acpi_dev = to_acpi_device(dev);
+
+	return sprintf(buf, "%s\n", acpi_device_hid(acpi_dev));
+}
+static DEVICE_ATTR(hid, 0444, acpi_device_hid_show, NULL);
+
+static ssize_t acpi_device_uid_show(struct device *dev,
+				    struct device_attribute *attr, char *buf)
+{
+	struct acpi_device *acpi_dev = to_acpi_device(dev);
+
+	return sprintf(buf, "%s\n", acpi_dev->pnp.unique_id);
+}
+static DEVICE_ATTR(uid, 0444, acpi_device_uid_show, NULL);
+
+static ssize_t acpi_device_adr_show(struct device *dev,
+				    struct device_attribute *attr, char *buf)
+{
+	struct acpi_device *acpi_dev = to_acpi_device(dev);
+
+	return sprintf(buf, "0x%08x\n",
+		       (unsigned int)(acpi_dev->pnp.bus_address));
+}
+static DEVICE_ATTR(adr, 0444, acpi_device_adr_show, NULL);
+
+static ssize_t
+acpi_device_path_show(struct device *dev, struct device_attribute *attr, char *buf) {
+	struct acpi_device *acpi_dev = to_acpi_device(dev);
+	struct acpi_buffer path = {ACPI_ALLOCATE_BUFFER, NULL};
+	int result;
+
+	result = acpi_get_name(acpi_dev->handle, ACPI_FULL_PATHNAME, &path);
+	if (result)
+		goto end;
+
+	result = sprintf(buf, "%s\n", (char*)path.pointer);
+	kfree(path.pointer);
+end:
+	return result;
+}
+static DEVICE_ATTR(path, 0444, acpi_device_path_show, NULL);
+
+/* sysfs file that shows description text from the ACPI _STR method */
+static ssize_t description_show(struct device *dev,
+				struct device_attribute *attr,
+				char *buf) {
+	struct acpi_device *acpi_dev = to_acpi_device(dev);
+	int result;
+
+	if (acpi_dev->pnp.str_obj == NULL)
+		return 0;
+
+	/*
+	 * The _STR object contains a Unicode identifier for a device.
+	 * We need to convert to utf-8 so it can be displayed.
+	 */
+	result = utf16s_to_utf8s(
+		(wchar_t *)acpi_dev->pnp.str_obj->buffer.pointer,
+		acpi_dev->pnp.str_obj->buffer.length,
+		UTF16_LITTLE_ENDIAN, buf,
+		PAGE_SIZE);
+
+	buf[result++] = '\n';
+
+	return result;
+}
+static DEVICE_ATTR(description, 0444, description_show, NULL);
+
+static ssize_t
+acpi_device_sun_show(struct device *dev, struct device_attribute *attr,
+		     char *buf) {
+	struct acpi_device *acpi_dev = to_acpi_device(dev);
+	acpi_status status;
+	unsigned long long sun;
+
+	status = acpi_evaluate_integer(acpi_dev->handle, "_SUN", NULL, &sun);
+	if (ACPI_FAILURE(status))
+		return -ENODEV;
+
+	return sprintf(buf, "%llu\n", sun);
+}
+static DEVICE_ATTR(sun, 0444, acpi_device_sun_show, NULL);
+
+static ssize_t status_show(struct device *dev, struct device_attribute *attr,
+				char *buf) {
+	struct acpi_device *acpi_dev = to_acpi_device(dev);
+	acpi_status status;
+	unsigned long long sta;
+
+	status = acpi_evaluate_integer(acpi_dev->handle, "_STA", NULL, &sta);
+	if (ACPI_FAILURE(status))
+		return -ENODEV;
+
+	return sprintf(buf, "%llu\n", sta);
+}
+static DEVICE_ATTR_RO(status);
+
+/**
+ * acpi_device_setup_files - Create sysfs attributes of an ACPI device.
+ * @dev: ACPI device object.
+ */
+int acpi_device_setup_files(struct acpi_device *dev)
+{
+	struct acpi_buffer buffer = {ACPI_ALLOCATE_BUFFER, NULL};
+	acpi_status status;
+	int result = 0;
+
+	/*
+	 * Devices gotten from FADT don't have a "path" attribute
+	 */
+	if (dev->handle) {
+		result = device_create_file(&dev->dev, &dev_attr_path);
+		if (result)
+			goto end;
+	}
+
+	if (!list_empty(&dev->pnp.ids)) {
+		result = device_create_file(&dev->dev, &dev_attr_hid);
+		if (result)
+			goto end;
+
+		result = device_create_file(&dev->dev, &dev_attr_modalias);
+		if (result)
+			goto end;
+	}
+
+	/*
+	 * If device has _STR, 'description' file is created
+	 */
+	if (acpi_has_method(dev->handle, "_STR")) {
+		status = acpi_evaluate_object(dev->handle, "_STR",
+					NULL, &buffer);
+		if (ACPI_FAILURE(status))
+			buffer.pointer = NULL;
+		dev->pnp.str_obj = buffer.pointer;
+		result = device_create_file(&dev->dev, &dev_attr_description);
+		if (result)
+			goto end;
+	}
+
+	if (dev->pnp.type.bus_address)
+		result = device_create_file(&dev->dev, &dev_attr_adr);
+	if (dev->pnp.unique_id)
+		result = device_create_file(&dev->dev, &dev_attr_uid);
+
+	if (acpi_has_method(dev->handle, "_SUN")) {
+		result = device_create_file(&dev->dev, &dev_attr_sun);
+		if (result)
+			goto end;
+	}
+
+	if (acpi_has_method(dev->handle, "_STA")) {
+		result = device_create_file(&dev->dev, &dev_attr_status);
+		if (result)
+			goto end;
+	}
+
+        /*
+         * If device has _EJ0, 'eject' file is created that is used to trigger
+         * hot-removal function from userland.
+         */
+	if (acpi_has_method(dev->handle, "_EJ0")) {
+		result = device_create_file(&dev->dev, &dev_attr_eject);
+		if (result)
+			return result;
+	}
+
+	if (dev->flags.power_manageable) {
+		result = device_create_file(&dev->dev, &dev_attr_power_state);
+		if (result)
+			return result;
+
+		if (dev->power.flags.power_resources)
+			result = device_create_file(&dev->dev,
+						    &dev_attr_real_power_state);
+	}
+
+end:
+	return result;
+}
+
+/**
+ * acpi_device_remove_files - Remove sysfs attributes of an ACPI device.
+ * @dev: ACPI device object.
+ */
+void acpi_device_remove_files(struct acpi_device *dev)
+{
+	if (dev->flags.power_manageable) {
+		device_remove_file(&dev->dev, &dev_attr_power_state);
+		if (dev->power.flags.power_resources)
+			device_remove_file(&dev->dev,
+					   &dev_attr_real_power_state);
+	}
+
+	/*
+	 * If device has _STR, remove 'description' file
+	 */
+	if (acpi_has_method(dev->handle, "_STR")) {
+		kfree(dev->pnp.str_obj);
+		device_remove_file(&dev->dev, &dev_attr_description);
+	}
+	/*
+	 * If device has _EJ0, remove 'eject' file.
+	 */
+	if (acpi_has_method(dev->handle, "_EJ0"))
+		device_remove_file(&dev->dev, &dev_attr_eject);
+
+	if (acpi_has_method(dev->handle, "_SUN"))
+		device_remove_file(&dev->dev, &dev_attr_sun);
+
+	if (dev->pnp.unique_id)
+		device_remove_file(&dev->dev, &dev_attr_uid);
+	if (dev->pnp.type.bus_address)
+		device_remove_file(&dev->dev, &dev_attr_adr);
+	device_remove_file(&dev->dev, &dev_attr_modalias);
+	device_remove_file(&dev->dev, &dev_attr_hid);
+	if (acpi_has_method(dev->handle, "_STA"))
+		device_remove_file(&dev->dev, &dev_attr_status);
+	if (dev->handle)
+		device_remove_file(&dev->dev, &dev_attr_path);
+}

drivers/acpi/internal.h

@@ -93,6 +93,8 @@ int acpi_device_add(struct acpi_device *device,
 		    void (*release)(struct device *));
 void acpi_init_device_object(struct acpi_device *device, acpi_handle handle,
 			     int type, unsigned long long sta);
+int acpi_device_setup_files(struct acpi_device *dev);
+void acpi_device_remove_files(struct acpi_device *dev);
 void acpi_device_add_finalize(struct acpi_device *device);
 void acpi_free_pnp_ids(struct acpi_device_pnp *pnp);
 bool acpi_device_is_present(struct acpi_device *adev);
@@ -100,6 +102,13 @@ bool acpi_device_is_battery(struct acpi_device *adev);
 bool acpi_device_is_first_physical_node(struct acpi_device *adev,
 					const struct device *dev);
 
+/* --------------------------------------------------------------------------
+                     Device Matching and Notification
+   -------------------------------------------------------------------------- */
+struct acpi_device *acpi_companion_match(const struct device *dev);
+int __acpi_device_uevent_modalias(struct acpi_device *adev,
+				  struct kobj_uevent_env *env);
+
 /* --------------------------------------------------------------------------
                                   Power Resource
    -------------------------------------------------------------------------- */

drivers/acpi/resource.c

@@ -193,6 +193,7 @@ static bool acpi_decode_space(struct resource_win *win,
 	u8 iodec = attr->granularity == 0xfff ? ACPI_DECODE_10 : ACPI_DECODE_16;
 	bool wp = addr->info.mem.write_protect;
 	u64 len = attr->address_length;
+	u64 start, end, offset = 0;
 	struct resource *res = &win->res;
 
 	/*
@@ -204,9 +205,6 @@ static bool acpi_decode_space(struct resource_win *win,
 		pr_debug("ACPI: Invalid address space min_addr_fix %d, max_addr_fix %d, len %llx\n",
 			 addr->min_address_fixed, addr->max_address_fixed, len);
 
-	res->start = attr->minimum;
-	res->end = attr->maximum;
-
 	/*
 	 * For bridges that translate addresses across the bridge,
 	 * translation_offset is the offset that must be added to the
@@ -214,12 +212,22 @@ static bool acpi_decode_space(struct resource_win *win,
 	 * primary side. Non-bridge devices must list 0 for all Address
 	 * Translation offset bits.
 	 */
-	if (addr->producer_consumer == ACPI_PRODUCER) {
-		res->start += attr->translation_offset;
-		res->end += attr->translation_offset;
-	} else if (attr->translation_offset) {
+	if (addr->producer_consumer == ACPI_PRODUCER)
+		offset = attr->translation_offset;
+	else if (attr->translation_offset)
 		pr_debug("ACPI: translation_offset(%lld) is invalid for non-bridge device.\n",
 			 attr->translation_offset);
+	start = attr->minimum + offset;
+	end = attr->maximum + offset;
+
+	win->offset = offset;
+	res->start = start;
+	res->end = end;
+	if (sizeof(resource_size_t) < sizeof(u64) &&
+	    (offset != win->offset || start != res->start || end != res->end)) {
+		pr_warn("acpi resource window ([%#llx-%#llx] ignored, not CPU addressable)\n",
+			attr->minimum, attr->maximum);
+		return false;
 	}
 
 	switch (addr->resource_type) {
@@ -236,8 +244,6 @@ static bool acpi_decode_space(struct resource_win *win,
 		return false;
 	}
 
-	win->offset = attr->translation_offset;
-
 	if (addr->producer_consumer == ACPI_PRODUCER)
 		res->flags |= IORESOURCE_WINDOW;
 

drivers/acpi/scan.c

@@ -115,278 +115,6 @@ int acpi_scan_add_handler_with_hotplug(struct acpi_scan_handler *handler,
 	return 0;
 }
 
-/**
- * create_pnp_modalias - Create hid/cid(s) string for modalias and uevent
- * @acpi_dev: ACPI device object.
- * @modalias: Buffer to print into.
- * @size: Size of the buffer.
- *
- * Creates hid/cid(s) string needed for modalias and uevent
- * e.g. on a device with hid:IBM0001 and cid:ACPI0001 you get:
- * char *modalias: "acpi:IBM0001:ACPI0001"
- * Return: 0: no _HID and no _CID
- *         -EINVAL: output error
- *         -ENOMEM: output is truncated
-*/
-static int create_pnp_modalias(struct acpi_device *acpi_dev, char *modalias,
-			       int size)
-{
-	int len;
-	int count;
-	struct acpi_hardware_id *id;
-
-	/*
-	 * Since we skip ACPI_DT_NAMESPACE_HID from the modalias below, 0 should
-	 * be returned if ACPI_DT_NAMESPACE_HID is the only ACPI/PNP ID in the
-	 * device's list.
-	 */
-	count = 0;
-	list_for_each_entry(id, &acpi_dev->pnp.ids, list)
-		if (strcmp(id->id, ACPI_DT_NAMESPACE_HID))
-			count++;
-
-	if (!count)
-		return 0;
-
-	len = snprintf(modalias, size, "acpi:");
-	if (len <= 0)
-		return len;
-
-	size -= len;
-
-	list_for_each_entry(id, &acpi_dev->pnp.ids, list) {
-		if (!strcmp(id->id, ACPI_DT_NAMESPACE_HID))
-			continue;
-
-		count = snprintf(&modalias[len], size, "%s:", id->id);
-		if (count < 0)
-			return -EINVAL;
-
-		if (count >= size)
-			return -ENOMEM;
-
-		len += count;
-		size -= count;
-	}
-	modalias[len] = '\0';
-	return len;
-}
-
-/**
- * create_of_modalias - Creates DT compatible string for modalias and uevent
- * @acpi_dev: ACPI device object.
- * @modalias: Buffer to print into.
- * @size: Size of the buffer.
- *
- * Expose DT compatible modalias as of:NnameTCcompatible.  This function should
- * only be called for devices having ACPI_DT_NAMESPACE_HID in their list of
- * ACPI/PNP IDs.
- */
-static int create_of_modalias(struct acpi_device *acpi_dev, char *modalias,
-			      int size)
-{
-	struct acpi_buffer buf = { ACPI_ALLOCATE_BUFFER };
-	const union acpi_object *of_compatible, *obj;
-	int len, count;
-	int i, nval;
-	char *c;
-
-	acpi_get_name(acpi_dev->handle, ACPI_SINGLE_NAME, &buf);
-	/* DT strings are all in lower case */
-	for (c = buf.pointer; *c != '\0'; c++)
-		*c = tolower(*c);
-
-	len = snprintf(modalias, size, "of:N%sT", (char *)buf.pointer);
-	ACPI_FREE(buf.pointer);
-
-	if (len <= 0)
-		return len;
-
-	of_compatible = acpi_dev->data.of_compatible;
-	if (of_compatible->type == ACPI_TYPE_PACKAGE) {
-		nval = of_compatible->package.count;
-		obj = of_compatible->package.elements;
-	} else { /* Must be ACPI_TYPE_STRING. */
-		nval = 1;
-		obj = of_compatible;
-	}
-	for (i = 0; i < nval; i++, obj++) {
-		count = snprintf(&modalias[len], size, "C%s",
-				 obj->string.pointer);
-		if (count < 0)
-			return -EINVAL;
-
-		if (count >= size)
-			return -ENOMEM;
-
-		len += count;
-		size -= count;
-	}
-	modalias[len] = '\0';
-	return len;
-}
-
-/**
- * acpi_device_is_first_physical_node - Is given dev first physical node
- * @adev: ACPI companion device
- * @dev: Physical device to check
- *
- * Function checks if given @dev is the first physical devices attached to
- * the ACPI companion device. This distinction is needed in some cases
- * where the same companion device is shared between many physical devices.
- *
- * Note that the caller have to provide valid @adev pointer.
- */
-bool acpi_device_is_first_physical_node(struct acpi_device *adev,
-					const struct device *dev)
-{
-	bool ret = false;
-
-	mutex_lock(&adev->physical_node_lock);
-	if (!list_empty(&adev->physical_node_list)) {
-		const struct acpi_device_physical_node *node;
-
-		node = list_first_entry(&adev->physical_node_list,
-					struct acpi_device_physical_node, node);
-		ret = node->dev == dev;
-	}
-	mutex_unlock(&adev->physical_node_lock);
-
-	return ret;
-}
-
-/*
- * acpi_companion_match() - Can we match via ACPI companion device
- * @dev: Device in question
- *
- * Check if the given device has an ACPI companion and if that companion has
- * a valid list of PNP IDs, and if the device is the first (primary) physical
- * device associated with it.  Return the companion pointer if that's the case
- * or NULL otherwise.
- *
- * If multiple physical devices are attached to a single ACPI companion, we need
- * to be careful.  The usage scenario for this kind of relationship is that all
- * of the physical devices in question use resources provided by the ACPI
- * companion.  A typical case is an MFD device where all the sub-devices share
- * the parent's ACPI companion.  In such cases we can only allow the primary
- * (first) physical device to be matched with the help of the companion's PNP
- * IDs.
- *
- * Additional physical devices sharing the ACPI companion can still use
- * resources available from it but they will be matched normally using functions
- * provided by their bus types (and analogously for their modalias).
- */
-static struct acpi_device *acpi_companion_match(const struct device *dev)
-{
-	struct acpi_device *adev;
-
-	adev = ACPI_COMPANION(dev);
-	if (!adev)
-		return NULL;
-
-	if (list_empty(&adev->pnp.ids))
-		return NULL;
-
-	return acpi_device_is_first_physical_node(adev, dev) ? adev : NULL;
-}
-
-static int __acpi_device_uevent_modalias(struct acpi_device *adev,
-					 struct kobj_uevent_env *env)
-{
-	int len;
-
-	if (!adev)
-		return -ENODEV;
-
-	if (list_empty(&adev->pnp.ids))
-		return 0;
-
-	if (add_uevent_var(env, "MODALIAS="))
-		return -ENOMEM;
-
-	len = create_pnp_modalias(adev, &env->buf[env->buflen - 1],
-				  sizeof(env->buf) - env->buflen);
-	if (len < 0)
-		return len;
-
-	env->buflen += len;
-	if (!adev->data.of_compatible)
-		return 0;
-
-	if (len > 0 && add_uevent_var(env, "MODALIAS="))
-		return -ENOMEM;
-
-	len = create_of_modalias(adev, &env->buf[env->buflen - 1],
-				 sizeof(env->buf) - env->buflen);
-	if (len < 0)
-		return len;
-
-	env->buflen += len;
-
-	return 0;
-}
-
-/*
- * Creates uevent modalias field for ACPI enumerated devices.
- * Because the other buses does not support ACPI HIDs & CIDs.
- * e.g. for a device with hid:IBM0001 and cid:ACPI0001 you get:
- * "acpi:IBM0001:ACPI0001"
- */
-int acpi_device_uevent_modalias(struct device *dev, struct kobj_uevent_env *env)
-{
-	return __acpi_device_uevent_modalias(acpi_companion_match(dev), env);
-}
-EXPORT_SYMBOL_GPL(acpi_device_uevent_modalias);
-
-static int __acpi_device_modalias(struct acpi_device *adev, char *buf, int size)
-{
-	int len, count;
-
-	if (!adev)
-		return -ENODEV;
-
-	if (list_empty(&adev->pnp.ids))
-		return 0;
-
-	len = create_pnp_modalias(adev, buf, size - 1);
-	if (len < 0) {
-		return len;
-	} else if (len > 0) {
-		buf[len++] = '\n';
-		size -= len;
-	}
-	if (!adev->data.of_compatible)
-		return len;
-
-	count = create_of_modalias(adev, buf + len, size - 1);
-	if (count < 0) {
-		return count;
-	} else if (count > 0) {
-		len += count;
-		buf[len++] = '\n';
-	}
-
-	return len;
-}
-
-/*
- * Creates modalias sysfs attribute for ACPI enumerated devices.
- * Because the other buses does not support ACPI HIDs & CIDs.
- * e.g. for a device with hid:IBM0001 and cid:ACPI0001 you get:
- * "acpi:IBM0001:ACPI0001"
- */
-int acpi_device_modalias(struct device *dev, char *buf, int size)
-{
-	return __acpi_device_modalias(acpi_companion_match(dev), buf, size);
-}
-EXPORT_SYMBOL_GPL(acpi_device_modalias);
-
-static ssize_t
-acpi_device_modalias_show(struct device *dev, struct device_attribute *attr, char *buf) {
-	return __acpi_device_modalias(to_acpi_device(dev), buf, 1024);
-}
-static DEVICE_ATTR(modalias, 0444, acpi_device_modalias_show, NULL);
-
 bool acpi_scan_is_offline(struct acpi_device *adev, bool uevent)
 {
 	struct acpi_device_physical_node *pn;
@@ -715,423 +443,6 @@ void acpi_device_hotplug(struct acpi_device *adev, u32 src)
 	unlock_device_hotplug();
 }
 
-static ssize_t real_power_state_show(struct device *dev,
-				     struct device_attribute *attr, char *buf)
-{
-	struct acpi_device *adev = to_acpi_device(dev);
-	int state;
-	int ret;
-
-	ret = acpi_device_get_power(adev, &state);
-	if (ret)
-		return ret;
-
-	return sprintf(buf, "%s\n", acpi_power_state_string(state));
-}
-
-static DEVICE_ATTR(real_power_state, 0444, real_power_state_show, NULL);
-
-static ssize_t power_state_show(struct device *dev,
-				struct device_attribute *attr, char *buf)
-{
-	struct acpi_device *adev = to_acpi_device(dev);
-
-	return sprintf(buf, "%s\n", acpi_power_state_string(adev->power.state));
-}
-
-static DEVICE_ATTR(power_state, 0444, power_state_show, NULL);
-
-static ssize_t
-acpi_eject_store(struct device *d, struct device_attribute *attr,
-		const char *buf, size_t count)
-{
-	struct acpi_device *acpi_device = to_acpi_device(d);
-	acpi_object_type not_used;
-	acpi_status status;
-
-	if (!count || buf[0] != '1')
-		return -EINVAL;
-
-	if ((!acpi_device->handler || !acpi_device->handler->hotplug.enabled)
-	    && !acpi_device->driver)
-		return -ENODEV;
-
-	status = acpi_get_type(acpi_device->handle, &not_used);
-	if (ACPI_FAILURE(status) || !acpi_device->flags.ejectable)
-		return -ENODEV;
-
-	get_device(&acpi_device->dev);
-	status = acpi_hotplug_schedule(acpi_device, ACPI_OST_EC_OSPM_EJECT);
-	if (ACPI_SUCCESS(status))
-		return count;
-
-	put_device(&acpi_device->dev);
-	acpi_evaluate_ost(acpi_device->handle, ACPI_OST_EC_OSPM_EJECT,
-			  ACPI_OST_SC_NON_SPECIFIC_FAILURE, NULL);
-	return status == AE_NO_MEMORY ? -ENOMEM : -EAGAIN;
-}
-
-static DEVICE_ATTR(eject, 0200, NULL, acpi_eject_store);
-
-static ssize_t
-acpi_device_hid_show(struct device *dev, struct device_attribute *attr, char *buf) {
-	struct acpi_device *acpi_dev = to_acpi_device(dev);
-
-	return sprintf(buf, "%s\n", acpi_device_hid(acpi_dev));
-}
-static DEVICE_ATTR(hid, 0444, acpi_device_hid_show, NULL);
-
-static ssize_t acpi_device_uid_show(struct device *dev,
-				    struct device_attribute *attr, char *buf)
-{
-	struct acpi_device *acpi_dev = to_acpi_device(dev);
-
-	return sprintf(buf, "%s\n", acpi_dev->pnp.unique_id);
-}
-static DEVICE_ATTR(uid, 0444, acpi_device_uid_show, NULL);
-
-static ssize_t acpi_device_adr_show(struct device *dev,
-				    struct device_attribute *attr, char *buf)
-{
-	struct acpi_device *acpi_dev = to_acpi_device(dev);
-
-	return sprintf(buf, "0x%08x\n",
-		       (unsigned int)(acpi_dev->pnp.bus_address));
-}
-static DEVICE_ATTR(adr, 0444, acpi_device_adr_show, NULL);
-
-static ssize_t
-acpi_device_path_show(struct device *dev, struct device_attribute *attr, char *buf) {
-	struct acpi_device *acpi_dev = to_acpi_device(dev);
-	struct acpi_buffer path = {ACPI_ALLOCATE_BUFFER, NULL};
-	int result;
-
-	result = acpi_get_name(acpi_dev->handle, ACPI_FULL_PATHNAME, &path);
-	if (result)
-		goto end;
-
-	result = sprintf(buf, "%s\n", (char*)path.pointer);
-	kfree(path.pointer);
-end:
-	return result;
-}
-static DEVICE_ATTR(path, 0444, acpi_device_path_show, NULL);
-
-/* sysfs file that shows description text from the ACPI _STR method */
-static ssize_t description_show(struct device *dev,
-				struct device_attribute *attr,
-				char *buf) {
-	struct acpi_device *acpi_dev = to_acpi_device(dev);
-	int result;
-
-	if (acpi_dev->pnp.str_obj == NULL)
-		return 0;
-
-	/*
-	 * The _STR object contains a Unicode identifier for a device.
-	 * We need to convert to utf-8 so it can be displayed.
-	 */
-	result = utf16s_to_utf8s(
-		(wchar_t *)acpi_dev->pnp.str_obj->buffer.pointer,
-		acpi_dev->pnp.str_obj->buffer.length,
-		UTF16_LITTLE_ENDIAN, buf,
-		PAGE_SIZE);
-
-	buf[result++] = '\n';
-
-	return result;
-}
-static DEVICE_ATTR(description, 0444, description_show, NULL);
-
-static ssize_t
-acpi_device_sun_show(struct device *dev, struct device_attribute *attr,
-		     char *buf) {
-	struct acpi_device *acpi_dev = to_acpi_device(dev);
-	acpi_status status;
-	unsigned long long sun;
-
-	status = acpi_evaluate_integer(acpi_dev->handle, "_SUN", NULL, &sun);
-	if (ACPI_FAILURE(status))
-		return -ENODEV;
-
-	return sprintf(buf, "%llu\n", sun);
-}
-static DEVICE_ATTR(sun, 0444, acpi_device_sun_show, NULL);
-
-static ssize_t status_show(struct device *dev, struct device_attribute *attr,
-				char *buf) {
-	struct acpi_device *acpi_dev = to_acpi_device(dev);
-	acpi_status status;
-	unsigned long long sta;
-
-	status = acpi_evaluate_integer(acpi_dev->handle, "_STA", NULL, &sta);
-	if (ACPI_FAILURE(status))
-		return -ENODEV;
-
-	return sprintf(buf, "%llu\n", sta);
-}
-static DEVICE_ATTR_RO(status);
-
-static int acpi_device_setup_files(struct acpi_device *dev)
-{
-	struct acpi_buffer buffer = {ACPI_ALLOCATE_BUFFER, NULL};
-	acpi_status status;
-	int result = 0;
-
-	/*
-	 * Devices gotten from FADT don't have a "path" attribute
-	 */
-	if (dev->handle) {
-		result = device_create_file(&dev->dev, &dev_attr_path);
-		if (result)
-			goto end;
-	}
-
-	if (!list_empty(&dev->pnp.ids)) {
-		result = device_create_file(&dev->dev, &dev_attr_hid);
-		if (result)
-			goto end;
-
-		result = device_create_file(&dev->dev, &dev_attr_modalias);
-		if (result)
-			goto end;
-	}
-
-	/*
-	 * If device has _STR, 'description' file is created
-	 */
-	if (acpi_has_method(dev->handle, "_STR")) {
-		status = acpi_evaluate_object(dev->handle, "_STR",
-					NULL, &buffer);
-		if (ACPI_FAILURE(status))
-			buffer.pointer = NULL;
-		dev->pnp.str_obj = buffer.pointer;
-		result = device_create_file(&dev->dev, &dev_attr_description);
-		if (result)
-			goto end;
-	}
-
-	if (dev->pnp.type.bus_address)
-		result = device_create_file(&dev->dev, &dev_attr_adr);
-	if (dev->pnp.unique_id)
-		result = device_create_file(&dev->dev, &dev_attr_uid);
-
-	if (acpi_has_method(dev->handle, "_SUN")) {
-		result = device_create_file(&dev->dev, &dev_attr_sun);
-		if (result)
-			goto end;
-	}
-
-	if (acpi_has_method(dev->handle, "_STA")) {
-		result = device_create_file(&dev->dev, &dev_attr_status);
-		if (result)
-			goto end;
-	}
-
-        /*
-         * If device has _EJ0, 'eject' file is created that is used to trigger
-         * hot-removal function from userland.
-         */
-	if (acpi_has_method(dev->handle, "_EJ0")) {
-		result = device_create_file(&dev->dev, &dev_attr_eject);
-		if (result)
-			return result;
-	}
-
-	if (dev->flags.power_manageable) {
-		result = device_create_file(&dev->dev, &dev_attr_power_state);
-		if (result)
-			return result;
-
-		if (dev->power.flags.power_resources)
-			result = device_create_file(&dev->dev,
-						    &dev_attr_real_power_state);
-	}
-
-end:
-	return result;
-}
-
-static void acpi_device_remove_files(struct acpi_device *dev)
-{
-	if (dev->flags.power_manageable) {
-		device_remove_file(&dev->dev, &dev_attr_power_state);
-		if (dev->power.flags.power_resources)
-			device_remove_file(&dev->dev,
-					   &dev_attr_real_power_state);
-	}
-
-	/*
-	 * If device has _STR, remove 'description' file
-	 */
-	if (acpi_has_method(dev->handle, "_STR")) {
-		kfree(dev->pnp.str_obj);
-		device_remove_file(&dev->dev, &dev_attr_description);
-	}
-	/*
-	 * If device has _EJ0, remove 'eject' file.
-	 */
-	if (acpi_has_method(dev->handle, "_EJ0"))
-		device_remove_file(&dev->dev, &dev_attr_eject);
-
-	if (acpi_has_method(dev->handle, "_SUN"))
-		device_remove_file(&dev->dev, &dev_attr_sun);
-
-	if (dev->pnp.unique_id)
-		device_remove_file(&dev->dev, &dev_attr_uid);
-	if (dev->pnp.type.bus_address)
-		device_remove_file(&dev->dev, &dev_attr_adr);
-	device_remove_file(&dev->dev, &dev_attr_modalias);
-	device_remove_file(&dev->dev, &dev_attr_hid);
-	if (acpi_has_method(dev->handle, "_STA"))
-		device_remove_file(&dev->dev, &dev_attr_status);
-	if (dev->handle)
-		device_remove_file(&dev->dev, &dev_attr_path);
-}
-/* --------------------------------------------------------------------------
-			ACPI Bus operations
-   -------------------------------------------------------------------------- */
-
-/**
- * acpi_of_match_device - Match device object using the "compatible" property.
- * @adev: ACPI device object to match.
- * @of_match_table: List of device IDs to match against.
- *
- * If @dev has an ACPI companion which has ACPI_DT_NAMESPACE_HID in its list of
- * identifiers and a _DSD object with the "compatible" property, use that
- * property to match against the given list of identifiers.
- */
-static bool acpi_of_match_device(struct acpi_device *adev,
-				 const struct of_device_id *of_match_table)
-{
-	const union acpi_object *of_compatible, *obj;
-	int i, nval;
-
-	if (!adev)
-		return false;
-
-	of_compatible = adev->data.of_compatible;
-	if (!of_match_table || !of_compatible)
-		return false;
-
-	if (of_compatible->type == ACPI_TYPE_PACKAGE) {
-		nval = of_compatible->package.count;
-		obj = of_compatible->package.elements;
-	} else { /* Must be ACPI_TYPE_STRING. */
-		nval = 1;
-		obj = of_compatible;
-	}
-	/* Now we can look for the driver DT compatible strings */
-	for (i = 0; i < nval; i++, obj++) {
-		const struct of_device_id *id;
-
-		for (id = of_match_table; id->compatible[0]; id++)
-			if (!strcasecmp(obj->string.pointer, id->compatible))
-				return true;
-	}
-
-	return false;
-}
-
-static bool __acpi_match_device_cls(const struct acpi_device_id *id,
-				    struct acpi_hardware_id *hwid)
-{
-	int i, msk, byte_shift;
-	char buf[3];
-
-	if (!id->cls)
-		return false;
-
-	/* Apply class-code bitmask, before checking each class-code byte */
-	for (i = 1; i <= 3; i++) {
-		byte_shift = 8 * (3 - i);
-		msk = (id->cls_msk >> byte_shift) & 0xFF;
-		if (!msk)
-			continue;
-
-		sprintf(buf, "%02x", (id->cls >> byte_shift) & msk);
-		if (strncmp(buf, &hwid->id[(i - 1) * 2], 2))
-			return false;
-	}
-	return true;
-}
-
-static const struct acpi_device_id *__acpi_match_device(
-	struct acpi_device *device,
-	const struct acpi_device_id *ids,
-	const struct of_device_id *of_ids)
-{
-	const struct acpi_device_id *id;
-	struct acpi_hardware_id *hwid;
-
-	/*
-	 * If the device is not present, it is unnecessary to load device
-	 * driver for it.
-	 */
-	if (!device || !device->status.present)
-		return NULL;
-
-	list_for_each_entry(hwid, &device->pnp.ids, list) {
-		/* First, check the ACPI/PNP IDs provided by the caller. */
-		for (id = ids; id->id[0] || id->cls; id++) {
-			if (id->id[0] && !strcmp((char *) id->id, hwid->id))
-				return id;
-			else if (id->cls && __acpi_match_device_cls(id, hwid))
-				return id;
-		}
-
-		/*
-		 * Next, check ACPI_DT_NAMESPACE_HID and try to match the
-		 * "compatible" property if found.
-		 *
-		 * The id returned by the below is not valid, but the only
-		 * caller passing non-NULL of_ids here is only interested in
-		 * whether or not the return value is NULL.
-		 */
-		if (!strcmp(ACPI_DT_NAMESPACE_HID, hwid->id)
-		    && acpi_of_match_device(device, of_ids))
-			return id;
-	}
-	return NULL;
-}
-
-/**
- * acpi_match_device - Match a struct device against a given list of ACPI IDs
- * @ids: Array of struct acpi_device_id object to match against.
- * @dev: The device structure to match.
- *
- * Check if @dev has a valid ACPI handle and if there is a struct acpi_device
- * object for that handle and use that object to match against a given list of
- * device IDs.
- *
- * Return a pointer to the first matching ID on success or %NULL on failure.
- */
-const struct acpi_device_id *acpi_match_device(const struct acpi_device_id *ids,
-					       const struct device *dev)
-{
-	return __acpi_match_device(acpi_companion_match(dev), ids, NULL);
-}
-EXPORT_SYMBOL_GPL(acpi_match_device);
-
-int acpi_match_device_ids(struct acpi_device *device,
-			  const struct acpi_device_id *ids)
-{
-	return __acpi_match_device(device, ids, NULL) ? 0 : -ENOENT;
-}
-EXPORT_SYMBOL(acpi_match_device_ids);
-
-bool acpi_driver_match_device(struct device *dev,
-			      const struct device_driver *drv)
-{
-	if (!drv->acpi_match_table)
-		return acpi_of_match_device(ACPI_COMPANION(dev),
-					    drv->of_match_table);
-
-	return !!__acpi_match_device(acpi_companion_match(dev),
-				     drv->acpi_match_table, drv->of_match_table);
-}
-EXPORT_SYMBOL_GPL(acpi_driver_match_device);
-
 static void acpi_free_power_resources_lists(struct acpi_device *device)
 {
 	int i;
@@ -1158,144 +469,6 @@ static void acpi_device_release(struct device *dev)
 	kfree(acpi_dev);
 }
 
-static int acpi_bus_match(struct device *dev, struct device_driver *drv)
-{
-	struct acpi_device *acpi_dev = to_acpi_device(dev);
-	struct acpi_driver *acpi_drv = to_acpi_driver(drv);
-
-	return acpi_dev->flags.match_driver
-		&& !acpi_match_device_ids(acpi_dev, acpi_drv->ids);
-}
-
-static int acpi_device_uevent(struct device *dev, struct kobj_uevent_env *env)
-{
-	return __acpi_device_uevent_modalias(to_acpi_device(dev), env);
-}
-
-static void acpi_device_notify(acpi_handle handle, u32 event, void *data)
-{
-	struct acpi_device *device = data;
-
-	device->driver->ops.notify(device, event);
-}
-
-static void acpi_device_notify_fixed(void *data)
-{
-	struct acpi_device *device = data;
-
-	/* Fixed hardware devices have no handles */
-	acpi_device_notify(NULL, ACPI_FIXED_HARDWARE_EVENT, device);
-}
-
-static u32 acpi_device_fixed_event(void *data)
-{
-	acpi_os_execute(OSL_NOTIFY_HANDLER, acpi_device_notify_fixed, data);
-	return ACPI_INTERRUPT_HANDLED;
-}
-
-static int acpi_device_install_notify_handler(struct acpi_device *device)
-{
-	acpi_status status;
-
-	if (device->device_type == ACPI_BUS_TYPE_POWER_BUTTON)
-		status =
-		    acpi_install_fixed_event_handler(ACPI_EVENT_POWER_BUTTON,
-						     acpi_device_fixed_event,
-						     device);
-	else if (device->device_type == ACPI_BUS_TYPE_SLEEP_BUTTON)
-		status =
-		    acpi_install_fixed_event_handler(ACPI_EVENT_SLEEP_BUTTON,
-						     acpi_device_fixed_event,
-						     device);
-	else
-		status = acpi_install_notify_handler(device->handle,
-						     ACPI_DEVICE_NOTIFY,
-						     acpi_device_notify,
-						     device);
-
-	if (ACPI_FAILURE(status))
-		return -EINVAL;
-	return 0;
-}
-
-static void acpi_device_remove_notify_handler(struct acpi_device *device)
-{
-	if (device->device_type == ACPI_BUS_TYPE_POWER_BUTTON)
-		acpi_remove_fixed_event_handler(ACPI_EVENT_POWER_BUTTON,
-						acpi_device_fixed_event);
-	else if (device->device_type == ACPI_BUS_TYPE_SLEEP_BUTTON)
-		acpi_remove_fixed_event_handler(ACPI_EVENT_SLEEP_BUTTON,
-						acpi_device_fixed_event);
-	else
-		acpi_remove_notify_handler(device->handle, ACPI_DEVICE_NOTIFY,
-					   acpi_device_notify);
-}
-
-static int acpi_device_probe(struct device *dev)
-{
-	struct acpi_device *acpi_dev = to_acpi_device(dev);
-	struct acpi_driver *acpi_drv = to_acpi_driver(dev->driver);
-	int ret;
-
-	if (acpi_dev->handler && !acpi_is_pnp_device(acpi_dev))
-		return -EINVAL;
-
-	if (!acpi_drv->ops.add)
-		return -ENOSYS;
-
-	ret = acpi_drv->ops.add(acpi_dev);
-	if (ret)
-		return ret;
-
-	acpi_dev->driver = acpi_drv;
-	ACPI_DEBUG_PRINT((ACPI_DB_INFO,
-			  "Driver [%s] successfully bound to device [%s]\n",
-			  acpi_drv->name, acpi_dev->pnp.bus_id));
-
-	if (acpi_drv->ops.notify) {
-		ret = acpi_device_install_notify_handler(acpi_dev);
-		if (ret) {
-			if (acpi_drv->ops.remove)
-				acpi_drv->ops.remove(acpi_dev);
-
-			acpi_dev->driver = NULL;
-			acpi_dev->driver_data = NULL;
-			return ret;
-		}
-	}
-
-	ACPI_DEBUG_PRINT((ACPI_DB_INFO, "Found driver [%s] for device [%s]\n",
-			  acpi_drv->name, acpi_dev->pnp.bus_id));
-	get_device(dev);
-	return 0;
-}
-
-static int acpi_device_remove(struct device * dev)
-{
-	struct acpi_device *acpi_dev = to_acpi_device(dev);
-	struct acpi_driver *acpi_drv = acpi_dev->driver;
-
-	if (acpi_drv) {
-		if (acpi_drv->ops.notify)
-			acpi_device_remove_notify_handler(acpi_dev);
-		if (acpi_drv->ops.remove)
-			acpi_drv->ops.remove(acpi_dev);
-	}
-	acpi_dev->driver = NULL;
-	acpi_dev->driver_data = NULL;
-
-	put_device(dev);
-	return 0;
-}
-
-struct bus_type acpi_bus_type = {
-	.name		= "acpi",
-	.match		= acpi_bus_match,
-	.probe		= acpi_device_probe,
-	.remove		= acpi_device_remove,
-	.uevent		= acpi_device_uevent,
-};
-
 static void acpi_device_del(struct acpi_device *device)
 {
 	mutex_lock(&acpi_device_lock);
@@ -1542,47 +715,6 @@ struct acpi_device *acpi_get_next_child(struct device *dev,
 	return next == head ? NULL : list_entry(next, struct acpi_device, node);
 }
 
-/* --------------------------------------------------------------------------
-                                 Driver Management
-   -------------------------------------------------------------------------- */
-/**
- * acpi_bus_register_driver - register a driver with the ACPI bus
- * @driver: driver being registered
- *
- * Registers a driver with the ACPI bus.  Searches the namespace for all
- * devices that match the driver's criteria and binds.  Returns zero for
- * success or a negative error status for failure.
- */
-int acpi_bus_register_driver(struct acpi_driver *driver)
-{
-	int ret;
-
-	if (acpi_disabled)
-		return -ENODEV;
-	driver->drv.name = driver->name;
-	driver->drv.bus = &acpi_bus_type;
-	driver->drv.owner = driver->owner;
-
-	ret = driver_register(&driver->drv);
-	return ret;
-}
-
-EXPORT_SYMBOL(acpi_bus_register_driver);
-
-/**
- * acpi_bus_unregister_driver - unregisters a driver with the ACPI bus
- * @driver: driver to unregister
- *
- * Unregisters a driver with the ACPI bus.  Searches the namespace for all
- * devices that match the driver's criteria and unbinds.
- */
-void acpi_bus_unregister_driver(struct acpi_driver *driver)
-{
-	driver_unregister(&driver->drv);
-}
-
-EXPORT_SYMBOL(acpi_bus_unregister_driver);
-
 /* --------------------------------------------------------------------------
                                  Device Enumeration
    -------------------------------------------------------------------------- */
@@ -2758,12 +1890,6 @@ int __init acpi_scan_init(void)
 {
 	int result;
 
-	result = bus_register(&acpi_bus_type);
-	if (result) {
-		/* We don't want to quit even if we failed to add suspend/resume */
-		printk(KERN_ERR PREFIX "Could not register bus type\n");
-	}
-
 	acpi_pci_root_init();
 	acpi_pci_link_init();
 	acpi_processor_init();

drivers/block/nvme-core.c

@@ -2108,8 +2108,17 @@ static void nvme_alloc_ns(struct nvme_dev *dev, unsigned nsid)
 		goto out_free_disk;
 
 	add_disk(ns->disk);
-	if (ns->ms)
-		revalidate_disk(ns->disk);
+	if (ns->ms) {
+		struct block_device *bd = bdget_disk(ns->disk, 0);
+		if (!bd)
+			return;
+		if (blkdev_get(bd, FMODE_READ, NULL)) {
+			bdput(bd);
+			return;
+		}
+		blkdev_reread_part(bd);
+		blkdev_put(bd, FMODE_READ);
+	}
 	return;
  out_free_disk:
 	kfree(disk);

drivers/char/tpm/tpm-chip.c

@@ -129,8 +129,9 @@ struct tpm_chip *tpmm_chip_alloc(struct device *dev,
 
 	device_initialize(&chip->dev);
 
-	chip->cdev.owner = chip->pdev->driver->owner;
 	cdev_init(&chip->cdev, &tpm_fops);
+	chip->cdev.owner = chip->pdev->driver->owner;
+	chip->cdev.kobj.parent = &chip->dev.kobj;
 
 	return chip;
 }

drivers/char/tpm/tpm_crb.c

@@ -233,6 +233,14 @@ static int crb_acpi_add(struct acpi_device *device)
 		return -ENODEV;
 	}
 
+	/* At least some versions of AMI BIOS have a bug that TPM2 table has
+	 * zero address for the control area and therefore we must fail.
+	*/
+	if (!buf->control_area_pa) {
+		dev_err(dev, "TPM2 ACPI table has a zero address for the control area\n");
+		return -EINVAL;
+	}
+
 	if (buf->hdr.length < sizeof(struct acpi_tpm2)) {
 		dev_err(dev, "TPM2 ACPI table has wrong size");
 		return -EINVAL;

drivers/cpufreq/cpufreq.c

@@ -169,6 +169,15 @@ struct kobject *get_governor_parent_kobj(struct cpufreq_policy *policy)
 }
 EXPORT_SYMBOL_GPL(get_governor_parent_kobj);
 
+struct cpufreq_frequency_table *cpufreq_frequency_get_table(unsigned int cpu)
+{
+	struct cpufreq_policy *policy = per_cpu(cpufreq_cpu_data, cpu);
+
+	return policy && !policy_is_inactive(policy) ?
+		policy->freq_table : NULL;
+}
+EXPORT_SYMBOL_GPL(cpufreq_frequency_get_table);
+
 static inline u64 get_cpu_idle_time_jiffy(unsigned int cpu, u64 *wall)
 {
 	u64 idle_time;
@@ -1132,6 +1141,7 @@ static struct cpufreq_policy *cpufreq_policy_restore(unsigned int cpu)
 
 		down_write(&policy->rwsem);
 		policy->cpu = cpu;
+		policy->governor = NULL;
 		up_write(&policy->rwsem);
 	}
 

drivers/cpufreq/freq_table.c

@@ -297,15 +297,6 @@ int cpufreq_table_validate_and_show(struct cpufreq_policy *policy,
 }
 EXPORT_SYMBOL_GPL(cpufreq_table_validate_and_show);
 
-struct cpufreq_policy *cpufreq_cpu_get_raw(unsigned int cpu);
-
-struct cpufreq_frequency_table *cpufreq_frequency_get_table(unsigned int cpu)
-{
-	struct cpufreq_policy *policy = cpufreq_cpu_get_raw(cpu);
-	return policy ? policy->freq_table : NULL;
-}
-EXPORT_SYMBOL_GPL(cpufreq_frequency_get_table);
-
 MODULE_AUTHOR("Dominik Brodowski <linux@brodo.de>");
 MODULE_DESCRIPTION("CPUfreq frequency table helpers");
 MODULE_LICENSE("GPL");

drivers/cpuidle/cpuidle.c

@@ -112,7 +112,12 @@ int cpuidle_find_deepest_state(struct cpuidle_driver *drv,
 static void enter_freeze_proper(struct cpuidle_driver *drv,
 				struct cpuidle_device *dev, int index)
 {
-	tick_freeze();
+	/*
+	 * trace_suspend_resume() called by tick_freeze() for the last CPU
+	 * executing it contains RCU usage regarded as invalid in the idle
+	 * context, so tell RCU about that.
+	 */
+	RCU_NONIDLE(tick_freeze());
 	/*
 	 * The state used here cannot be a "coupled" one, because the "coupled"
 	 * cpuidle mechanism enables interrupts and doing that with timekeeping
@@ -122,7 +127,7 @@ static void enter_freeze_proper(struct cpuidle_driver *drv,
 	WARN_ON(!irqs_disabled());
 	/*
 	 * timekeeping_resume() that will be called by tick_unfreeze() for the
-	 * last CPU executing it calls functions containing RCU read-side
+	 * first CPU executing it calls functions containing RCU read-side
 	 * critical sections, so tell RCU about that.
 	 */
 	RCU_NONIDLE(tick_unfreeze());

drivers/crypto/nx/nx-aes-ccm.c

@@ -494,8 +494,9 @@ out:
 static int ccm4309_aes_nx_encrypt(struct aead_request *req)
 {
 	struct nx_crypto_ctx *nx_ctx = crypto_tfm_ctx(req->base.tfm);
+	struct nx_gcm_rctx *rctx = aead_request_ctx(req);
 	struct blkcipher_desc desc;
-	u8 *iv = nx_ctx->priv.ccm.iv;
+	u8 *iv = rctx->iv;
 
 	iv[0] = 3;
 	memcpy(iv + 1, nx_ctx->priv.ccm.nonce, 3);
@@ -525,8 +526,9 @@ static int ccm_aes_nx_encrypt(struct aead_request *req)
 static int ccm4309_aes_nx_decrypt(struct aead_request *req)
 {
 	struct nx_crypto_ctx *nx_ctx = crypto_tfm_ctx(req->base.tfm);
+	struct nx_gcm_rctx *rctx = aead_request_ctx(req);
 	struct blkcipher_desc desc;
-	u8 *iv = nx_ctx->priv.ccm.iv;
+	u8 *iv = rctx->iv;
 
 	iv[0] = 3;
 	memcpy(iv + 1, nx_ctx->priv.ccm.nonce, 3);

drivers/crypto/nx/nx-aes-ctr.c

@@ -72,7 +72,7 @@ static int ctr3686_aes_nx_set_key(struct crypto_tfm *tfm,
 	if (key_len < CTR_RFC3686_NONCE_SIZE)
 		return -EINVAL;
 
-	memcpy(nx_ctx->priv.ctr.iv,
+	memcpy(nx_ctx->priv.ctr.nonce,
 	       in_key + key_len - CTR_RFC3686_NONCE_SIZE,
 	       CTR_RFC3686_NONCE_SIZE);
 
@@ -131,14 +131,15 @@ static int ctr3686_aes_nx_crypt(struct blkcipher_desc *desc,
 				unsigned int           nbytes)
 {
 	struct nx_crypto_ctx *nx_ctx = crypto_blkcipher_ctx(desc->tfm);
-	u8 *iv = nx_ctx->priv.ctr.iv;
+	u8 iv[16];
 
+	memcpy(iv, nx_ctx->priv.ctr.nonce, CTR_RFC3686_IV_SIZE);
 	memcpy(iv + CTR_RFC3686_NONCE_SIZE,
 	       desc->info, CTR_RFC3686_IV_SIZE);
 	iv[12] = iv[13] = iv[14] = 0;
 	iv[15] = 1;
 
-	desc->info = nx_ctx->priv.ctr.iv;
+	desc->info = iv;
 
 	return ctr_aes_nx_crypt(desc, dst, src, nbytes);
 }

drivers/crypto/nx/nx-aes-gcm.c

@@ -317,6 +317,7 @@ out:
 static int gcm_aes_nx_crypt(struct aead_request *req, int enc)
 {
 	struct nx_crypto_ctx *nx_ctx = crypto_tfm_ctx(req->base.tfm);
+	struct nx_gcm_rctx *rctx = aead_request_ctx(req);
 	struct nx_csbcpb *csbcpb = nx_ctx->csbcpb;
 	struct blkcipher_desc desc;
 	unsigned int nbytes = req->cryptlen;
@@ -326,7 +327,7 @@ static int gcm_aes_nx_crypt(struct aead_request *req, int enc)
 
 	spin_lock_irqsave(&nx_ctx->lock, irq_flags);
 
-	desc.info = nx_ctx->priv.gcm.iv;
+	desc.info = rctx->iv;
 	/* initialize the counter */
 	*(u32 *)(desc.info + NX_GCM_CTR_OFFSET) = 1;
 
@@ -424,8 +425,8 @@ out:
 
 static int gcm_aes_nx_encrypt(struct aead_request *req)
 {
-	struct nx_crypto_ctx *nx_ctx = crypto_tfm_ctx(req->base.tfm);
-	char *iv = nx_ctx->priv.gcm.iv;
+	struct nx_gcm_rctx *rctx = aead_request_ctx(req);
+	char *iv = rctx->iv;
 
 	memcpy(iv, req->iv, 12);
 
@@ -434,8 +435,8 @@ static int gcm_aes_nx_encrypt(struct aead_request *req)
 
 static int gcm_aes_nx_decrypt(struct aead_request *req)
 {
-	struct nx_crypto_ctx *nx_ctx = crypto_tfm_ctx(req->base.tfm);
-	char *iv = nx_ctx->priv.gcm.iv;
+	struct nx_gcm_rctx *rctx = aead_request_ctx(req);
+	char *iv = rctx->iv;
 
 	memcpy(iv, req->iv, 12);
 
@@ -445,7 +446,8 @@ static int gcm_aes_nx_decrypt(struct aead_request *req)
 static int gcm4106_aes_nx_encrypt(struct aead_request *req)
 {
 	struct nx_crypto_ctx *nx_ctx = crypto_tfm_ctx(req->base.tfm);
-	char *iv = nx_ctx->priv.gcm.iv;
+	struct nx_gcm_rctx *rctx = aead_request_ctx(req);
+	char *iv = rctx->iv;
 	char *nonce = nx_ctx->priv.gcm.nonce;
 
 	memcpy(iv, nonce, NX_GCM4106_NONCE_LEN);
@@ -457,7 +459,8 @@ static int gcm4106_aes_nx_encrypt(struct aead_request *req)
 static int gcm4106_aes_nx_decrypt(struct aead_request *req)
 {
 	struct nx_crypto_ctx *nx_ctx = crypto_tfm_ctx(req->base.tfm);
-	char *iv = nx_ctx->priv.gcm.iv;
+	struct nx_gcm_rctx *rctx = aead_request_ctx(req);
+	char *iv = rctx->iv;
 	char *nonce = nx_ctx->priv.gcm.nonce;
 
 	memcpy(iv, nonce, NX_GCM4106_NONCE_LEN);

drivers/crypto/nx/nx-aes-xcbc.c

@@ -42,6 +42,7 @@ static int nx_xcbc_set_key(struct crypto_shash *desc,
 			   unsigned int         key_len)
 {
 	struct nx_crypto_ctx *nx_ctx = crypto_shash_ctx(desc);
+	struct nx_csbcpb *csbcpb = nx_ctx->csbcpb;
 
 	switch (key_len) {
 	case AES_KEYSIZE_128:
@@ -51,7 +52,7 @@ static int nx_xcbc_set_key(struct crypto_shash *desc,
 		return -EINVAL;
 	}
 
-	memcpy(nx_ctx->priv.xcbc.key, in_key, key_len);
+	memcpy(csbcpb->cpb.aes_xcbc.key, in_key, key_len);
 
 	return 0;
 }
@@ -148,32 +149,29 @@ out:
 	return rc;
 }
 
-static int nx_xcbc_init(struct shash_desc *desc)
+static int nx_crypto_ctx_aes_xcbc_init2(struct crypto_tfm *tfm)
 {
-	struct xcbc_state *sctx = shash_desc_ctx(desc);
-	struct nx_crypto_ctx *nx_ctx = crypto_tfm_ctx(&desc->tfm->base);
+	struct nx_crypto_ctx *nx_ctx = crypto_tfm_ctx(tfm);
 	struct nx_csbcpb *csbcpb = nx_ctx->csbcpb;
-	struct nx_sg *out_sg;
-	int len;
+	int err;
 
-	nx_ctx_init(nx_ctx, HCOP_FC_AES);
+	err = nx_crypto_ctx_aes_xcbc_init(tfm);
+	if (err)
+		return err;
 
-	memset(sctx, 0, sizeof *sctx);
+	nx_ctx_init(nx_ctx, HCOP_FC_AES);
 
 	NX_CPB_SET_KEY_SIZE(csbcpb, NX_KS_AES_128);
 	csbcpb->cpb.hdr.mode = NX_MODE_AES_XCBC_MAC;
 
-	memcpy(csbcpb->cpb.aes_xcbc.key, nx_ctx->priv.xcbc.key, AES_BLOCK_SIZE);
-	memset(nx_ctx->priv.xcbc.key, 0, sizeof *nx_ctx->priv.xcbc.key);
-
-	len = AES_BLOCK_SIZE;
-	out_sg = nx_build_sg_list(nx_ctx->out_sg, (u8 *)sctx->state,
-				  &len, nx_ctx->ap->sglen);
+	return 0;
+}
 
-	if (len != AES_BLOCK_SIZE)
-		return -EINVAL;
+static int nx_xcbc_init(struct shash_desc *desc)
+{
+	struct xcbc_state *sctx = shash_desc_ctx(desc);
 
-	nx_ctx->op.outlen = (nx_ctx->out_sg - out_sg) * sizeof(struct nx_sg);
+	memset(sctx, 0, sizeof *sctx);
 
 	return 0;
 }
@@ -186,6 +184,7 @@ static int nx_xcbc_update(struct shash_desc *desc,
 	struct nx_crypto_ctx *nx_ctx = crypto_tfm_ctx(&desc->tfm->base);
 	struct nx_csbcpb *csbcpb = nx_ctx->csbcpb;
 	struct nx_sg *in_sg;
+	struct nx_sg *out_sg;
 	u32 to_process = 0, leftover, total;
 	unsigned int max_sg_len;
 	unsigned long irq_flags;
@@ -213,6 +212,17 @@ static int nx_xcbc_update(struct shash_desc *desc,
 	max_sg_len = min_t(u64, max_sg_len,
 				nx_ctx->ap->databytelen/NX_PAGE_SIZE);
 
+	data_len = AES_BLOCK_SIZE;
+	out_sg = nx_build_sg_list(nx_ctx->out_sg, (u8 *)sctx->state,
+				  &len, nx_ctx->ap->sglen);
+
+	if (data_len != AES_BLOCK_SIZE) {
+		rc = -EINVAL;
+		goto out;
+	}
+
+	nx_ctx->op.outlen = (nx_ctx->out_sg - out_sg) * sizeof(struct nx_sg);
+
 	do {
 		to_process = total - to_process;
 		to_process = to_process & ~(AES_BLOCK_SIZE - 1);
@@ -235,8 +245,10 @@ static int nx_xcbc_update(struct shash_desc *desc,
 						(u8 *) sctx->buffer,
 						&data_len,
 						max_sg_len);
-			if (data_len != sctx->count)
-				return -EINVAL;
+			if (data_len != sctx->count) {
+				rc = -EINVAL;
+				goto out;
+			}
 		}
 
 		data_len = to_process - sctx->count;
@@ -245,8 +257,10 @@ static int nx_xcbc_update(struct shash_desc *desc,
 					&data_len,
 					max_sg_len);
 
-		if (data_len != to_process - sctx->count)
-			return -EINVAL;
+		if (data_len != to_process - sctx->count) {
+			rc = -EINVAL;
+			goto out;
+		}
 
 		nx_ctx->op.inlen = (nx_ctx->in_sg - in_sg) *
 					sizeof(struct nx_sg);
@@ -325,15 +339,19 @@ static int nx_xcbc_final(struct shash_desc *desc, u8 *out)
 	in_sg = nx_build_sg_list(nx_ctx->in_sg, (u8 *)sctx->buffer,
 				 &len, nx_ctx->ap->sglen);
 
-	if (len != sctx->count)
-		return -EINVAL;
+	if (len != sctx->count) {
+		rc = -EINVAL;
+		goto out;
+	}
 
 	len = AES_BLOCK_SIZE;
 	out_sg = nx_build_sg_list(nx_ctx->out_sg, out, &len,
 				  nx_ctx->ap->sglen);
 
-	if (len != AES_BLOCK_SIZE)
-		return -EINVAL;
+	if (len != AES_BLOCK_SIZE) {
+		rc = -EINVAL;
+		goto out;
+	}
 
 	nx_ctx->op.inlen = (nx_ctx->in_sg - in_sg) * sizeof(struct nx_sg);
 	nx_ctx->op.outlen = (nx_ctx->out_sg - out_sg) * sizeof(struct nx_sg);
@@ -372,7 +390,7 @@ struct shash_alg nx_shash_aes_xcbc_alg = {
 		.cra_blocksize   = AES_BLOCK_SIZE,
 		.cra_module      = THIS_MODULE,
 		.cra_ctxsize     = sizeof(struct nx_crypto_ctx),
-		.cra_init        = nx_crypto_ctx_aes_xcbc_init,
+		.cra_init        = nx_crypto_ctx_aes_xcbc_init2,
 		.cra_exit        = nx_crypto_ctx_exit,
 	}
 };

drivers/crypto/nx/nx-sha256.c

@@ -29,34 +29,28 @@
 #include "nx.h"
 
 
-static int nx_sha256_init(struct shash_desc *desc)
+static int nx_crypto_ctx_sha256_init(struct crypto_tfm *tfm)
 {
-	struct sha256_state *sctx = shash_desc_ctx(desc);
-	struct nx_crypto_ctx *nx_ctx = crypto_tfm_ctx(&desc->tfm->base);
-	struct nx_sg *out_sg;
-	int len;
-	u32 max_sg_len;
+	struct nx_crypto_ctx *nx_ctx = crypto_tfm_ctx(tfm);
+	int err;
 
-	nx_ctx_init(nx_ctx, HCOP_FC_SHA);
+	err = nx_crypto_ctx_sha_init(tfm);
+	if (err)
+		return err;
 
-	memset(sctx, 0, sizeof *sctx);
+	nx_ctx_init(nx_ctx, HCOP_FC_SHA);
 
 	nx_ctx->ap = &nx_ctx->props[NX_PROPS_SHA256];
 
 	NX_CPB_SET_DIGEST_SIZE(nx_ctx->csbcpb, NX_DS_SHA256);
 
-	max_sg_len = min_t(u64, nx_ctx->ap->sglen,
-			nx_driver.of.max_sg_len/sizeof(struct nx_sg));
-	max_sg_len = min_t(u64, max_sg_len,
-			nx_ctx->ap->databytelen/NX_PAGE_SIZE);
+	return 0;
+}
 
-	len = SHA256_DIGEST_SIZE;
-	out_sg = nx_build_sg_list(nx_ctx->out_sg, (u8 *)sctx->state,
-				  &len, max_sg_len);
-	nx_ctx->op.outlen = (nx_ctx->out_sg - out_sg) * sizeof(struct nx_sg);
+static int nx_sha256_init(struct shash_desc *desc) {
+	struct sha256_state *sctx = shash_desc_ctx(desc);
 
-	if (len != SHA256_DIGEST_SIZE)
-		return -EINVAL;
+	memset(sctx, 0, sizeof *sctx);
 
 	sctx->state[0] = __cpu_to_be32(SHA256_H0);
 	sctx->state[1] = __cpu_to_be32(SHA256_H1);
@@ -78,6 +72,7 @@ static int nx_sha256_update(struct shash_desc *desc, const u8 *data,
 	struct nx_crypto_ctx *nx_ctx = crypto_tfm_ctx(&desc->tfm->base);
 	struct nx_csbcpb *csbcpb = (struct nx_csbcpb *)nx_ctx->csbcpb;
 	struct nx_sg *in_sg;
+	struct nx_sg *out_sg;
 	u64 to_process = 0, leftover, total;
 	unsigned long irq_flags;
 	int rc = 0;
@@ -108,6 +103,16 @@ static int nx_sha256_update(struct shash_desc *desc, const u8 *data,
 	max_sg_len = min_t(u64, max_sg_len,
 			nx_ctx->ap->databytelen/NX_PAGE_SIZE);
 
+	data_len = SHA256_DIGEST_SIZE;
+	out_sg = nx_build_sg_list(nx_ctx->out_sg, (u8 *)sctx->state,
+				  &data_len, max_sg_len);
+	nx_ctx->op.outlen = (nx_ctx->out_sg - out_sg) * sizeof(struct nx_sg);
+
+	if (data_len != SHA256_DIGEST_SIZE) {
+		rc = -EINVAL;
+		goto out;
+	}
+
 	do {
 		/*
 		 * to_process: the SHA256_BLOCK_SIZE data chunk to process in
@@ -282,7 +287,7 @@ struct shash_alg nx_shash_sha256_alg = {
 		.cra_blocksize   = SHA256_BLOCK_SIZE,
 		.cra_module      = THIS_MODULE,
 		.cra_ctxsize     = sizeof(struct nx_crypto_ctx),
-		.cra_init        = nx_crypto_ctx_sha_init,
+		.cra_init        = nx_crypto_ctx_sha256_init,
 		.cra_exit        = nx_crypto_ctx_exit,
 	}
 };

drivers/crypto/nx/nx-sha512.c

@@ -28,34 +28,29 @@
 #include "nx.h"
 
 
-static int nx_sha512_init(struct shash_desc *desc)
+static int nx_crypto_ctx_sha512_init(struct crypto_tfm *tfm)
 {
-	struct sha512_state *sctx = shash_desc_ctx(desc);
-	struct nx_crypto_ctx *nx_ctx = crypto_tfm_ctx(&desc->tfm->base);
-	struct nx_sg *out_sg;
-	int len;
-	u32 max_sg_len;
+	struct nx_crypto_ctx *nx_ctx = crypto_tfm_ctx(tfm);
+	int err;
 
-	nx_ctx_init(nx_ctx, HCOP_FC_SHA);
+	err = nx_crypto_ctx_sha_init(tfm);
+	if (err)
+		return err;
 
-	memset(sctx, 0, sizeof *sctx);
+	nx_ctx_init(nx_ctx, HCOP_FC_SHA);
 
 	nx_ctx->ap = &nx_ctx->props[NX_PROPS_SHA512];
 
 	NX_CPB_SET_DIGEST_SIZE(nx_ctx->csbcpb, NX_DS_SHA512);
 
-	max_sg_len = min_t(u64, nx_ctx->ap->sglen,
-			nx_driver.of.max_sg_len/sizeof(struct nx_sg));
-	max_sg_len = min_t(u64, max_sg_len,
-			nx_ctx->ap->databytelen/NX_PAGE_SIZE);
+	return 0;
+}
 
-	len = SHA512_DIGEST_SIZE;
-	out_sg = nx_build_sg_list(nx_ctx->out_sg, (u8 *)sctx->state,
-				  &len, max_sg_len);
-	nx_ctx->op.outlen = (nx_ctx->out_sg - out_sg) * sizeof(struct nx_sg);
+static int nx_sha512_init(struct shash_desc *desc)
+{
+	struct sha512_state *sctx = shash_desc_ctx(desc);
 
-	if (len != SHA512_DIGEST_SIZE)
-		return -EINVAL;
+	memset(sctx, 0, sizeof *sctx);
 
 	sctx->state[0] = __cpu_to_be64(SHA512_H0);
 	sctx->state[1] = __cpu_to_be64(SHA512_H1);
@@ -77,6 +72,7 @@ static int nx_sha512_update(struct shash_desc *desc, const u8 *data,
 	struct nx_crypto_ctx *nx_ctx = crypto_tfm_ctx(&desc->tfm->base);
 	struct nx_csbcpb *csbcpb = (struct nx_csbcpb *)nx_ctx->csbcpb;
 	struct nx_sg *in_sg;
+	struct nx_sg *out_sg;
 	u64 to_process, leftover = 0, total;
 	unsigned long irq_flags;
 	int rc = 0;
@@ -107,6 +103,16 @@ static int nx_sha512_update(struct shash_desc *desc, const u8 *data,
 	max_sg_len = min_t(u64, max_sg_len,
 			nx_ctx->ap->databytelen/NX_PAGE_SIZE);
 
+	data_len = SHA512_DIGEST_SIZE;
+	out_sg = nx_build_sg_list(nx_ctx->out_sg, (u8 *)sctx->state,
+				  &data_len, max_sg_len);
+	nx_ctx->op.outlen = (nx_ctx->out_sg - out_sg) * sizeof(struct nx_sg);
+
+	if (data_len != SHA512_DIGEST_SIZE) {
+		rc = -EINVAL;
+		goto out;
+	}
+
 	do {
 		/*
 		 * to_process: the SHA512_BLOCK_SIZE data chunk to process in
@@ -288,7 +294,7 @@ struct shash_alg nx_shash_sha512_alg = {
 		.cra_blocksize   = SHA512_BLOCK_SIZE,
 		.cra_module      = THIS_MODULE,
 		.cra_ctxsize     = sizeof(struct nx_crypto_ctx),
-		.cra_init        = nx_crypto_ctx_sha_init,
+		.cra_init        = nx_crypto_ctx_sha512_init,
 		.cra_exit        = nx_crypto_ctx_exit,
 	}
 };

drivers/crypto/nx/nx.c

@@ -713,12 +713,15 @@ static int nx_crypto_ctx_init(struct nx_crypto_ctx *nx_ctx, u32 fc, u32 mode)
 /* entry points from the crypto tfm initializers */
 int nx_crypto_ctx_aes_ccm_init(struct crypto_tfm *tfm)
 {
+	crypto_aead_set_reqsize(__crypto_aead_cast(tfm),
+				sizeof(struct nx_ccm_rctx));
 	return nx_crypto_ctx_init(crypto_tfm_ctx(tfm), NX_FC_AES,
 				  NX_MODE_AES_CCM);
 }
 
 int nx_crypto_ctx_aes_gcm_init(struct crypto_aead *tfm)
 {
+	crypto_aead_set_reqsize(tfm, sizeof(struct nx_gcm_rctx));
 	return nx_crypto_ctx_init(crypto_aead_ctx(tfm), NX_FC_AES,
 				  NX_MODE_AES_GCM);
 }

drivers/crypto/nx/nx.h

@@ -2,6 +2,8 @@
 #ifndef __NX_H__
 #define __NX_H__
 
+#include <crypto/ctr.h>
+
 #define NX_NAME		"nx-crypto"
 #define NX_STRING	"IBM Power7+ Nest Accelerator Crypto Driver"
 #define NX_VERSION	"1.0"
@@ -91,8 +93,11 @@ struct nx_crypto_driver {
 
 #define NX_GCM4106_NONCE_LEN		(4)
 #define NX_GCM_CTR_OFFSET		(12)
-struct nx_gcm_priv {
+struct nx_gcm_rctx {
 	u8 iv[16];
+};
+
+struct nx_gcm_priv {
 	u8 iauth_tag[16];
 	u8 nonce[NX_GCM4106_NONCE_LEN];
 };
@@ -100,8 +105,11 @@ struct nx_gcm_priv {
 #define NX_CCM_AES_KEY_LEN		(16)
 #define NX_CCM4309_AES_KEY_LEN		(19)
 #define NX_CCM4309_NONCE_LEN		(3)
-struct nx_ccm_priv {
+struct nx_ccm_rctx {
 	u8 iv[16];
+};
+
+struct nx_ccm_priv {
 	u8 b0[16];
 	u8 iauth_tag[16];
 	u8 oauth_tag[16];
@@ -113,7 +121,7 @@ struct nx_xcbc_priv {
 };
 
 struct nx_ctr_priv {
-	u8 iv[16];
+	u8 nonce[CTR_RFC3686_NONCE_SIZE];
 };
 
 struct nx_crypto_ctx {

drivers/crypto/omap-des.c

@@ -536,9 +536,6 @@ static int omap_des_crypt_dma_stop(struct omap_des_dev *dd)
 	dmaengine_terminate_all(dd->dma_lch_in);
 	dmaengine_terminate_all(dd->dma_lch_out);
 
-	dma_unmap_sg(dd->dev, dd->in_sg, dd->in_sg_len, DMA_TO_DEVICE);
-	dma_unmap_sg(dd->dev, dd->out_sg, dd->out_sg_len, DMA_FROM_DEVICE);
-
 	return err;
 }
 

drivers/infiniband/core/agent.c

@@ -88,7 +88,7 @@ void agent_send_response(const struct ib_mad_hdr *mad_hdr, const struct ib_grh *
 	struct ib_ah *ah;
 	struct ib_mad_send_wr_private *mad_send_wr;
 
-	if (device->node_type == RDMA_NODE_IB_SWITCH)
+	if (rdma_cap_ib_switch(device))
 		port_priv = ib_get_agent_port(device, 0);
 	else
 		port_priv = ib_get_agent_port(device, port_num);
@@ -122,7 +122,7 @@ void agent_send_response(const struct ib_mad_hdr *mad_hdr, const struct ib_grh *
 	memcpy(send_buf->mad, mad_hdr, resp_mad_len);
 	send_buf->ah = ah;
 
-	if (device->node_type == RDMA_NODE_IB_SWITCH) {
+	if (rdma_cap_ib_switch(device)) {
 		mad_send_wr = container_of(send_buf,
 					   struct ib_mad_send_wr_private,
 					   send_buf);

drivers/infiniband/core/cm.c

@@ -169,6 +169,7 @@ struct cm_device {
 	struct ib_device *ib_device;
 	struct device *device;
 	u8 ack_delay;
+	int going_down;
 	struct cm_port *port[0];
 };
 
@@ -805,6 +806,11 @@ static void cm_enter_timewait(struct cm_id_private *cm_id_priv)
 {
 	int wait_time;
 	unsigned long flags;
+	struct cm_device *cm_dev;
+
+	cm_dev = ib_get_client_data(cm_id_priv->id.device, &cm_client);
+	if (!cm_dev)
+		return;
 
 	spin_lock_irqsave(&cm.lock, flags);
 	cm_cleanup_timewait(cm_id_priv->timewait_info);
@@ -818,8 +824,14 @@ static void cm_enter_timewait(struct cm_id_private *cm_id_priv)
 	 */
 	cm_id_priv->id.state = IB_CM_TIMEWAIT;
 	wait_time = cm_convert_to_ms(cm_id_priv->av.timeout);
-	queue_delayed_work(cm.wq, &cm_id_priv->timewait_info->work.work,
-			   msecs_to_jiffies(wait_time));
+
+	/* Check if the device started its remove_one */
+	spin_lock_irq(&cm.lock);
+	if (!cm_dev->going_down)
+		queue_delayed_work(cm.wq, &cm_id_priv->timewait_info->work.work,
+				   msecs_to_jiffies(wait_time));
+	spin_unlock_irq(&cm.lock);
+
 	cm_id_priv->timewait_info = NULL;
 }
 
@@ -3305,6 +3317,11 @@ static int cm_establish(struct ib_cm_id *cm_id)
 	struct cm_work *work;
 	unsigned long flags;
 	int ret = 0;
+	struct cm_device *cm_dev;
+
+	cm_dev = ib_get_client_data(cm_id->device, &cm_client);
+	if (!cm_dev)
+		return -ENODEV;
 
 	work = kmalloc(sizeof *work, GFP_ATOMIC);
 	if (!work)
@@ -3343,7 +3360,17 @@ static int cm_establish(struct ib_cm_id *cm_id)
 	work->remote_id = cm_id->remote_id;
 	work->mad_recv_wc = NULL;
 	work->cm_event.event = IB_CM_USER_ESTABLISHED;
-	queue_delayed_work(cm.wq, &work->work, 0);
+
+	/* Check if the device started its remove_one */
+	spin_lock_irq(&cm.lock);
+	if (!cm_dev->going_down) {
+		queue_delayed_work(cm.wq, &work->work, 0);
+	} else {
+		kfree(work);
+		ret = -ENODEV;
+	}
+	spin_unlock_irq(&cm.lock);
+
 out:
 	return ret;
 }
@@ -3394,6 +3421,7 @@ static void cm_recv_handler(struct ib_mad_agent *mad_agent,
 	enum ib_cm_event_type event;
 	u16 attr_id;
 	int paths = 0;
+	int going_down = 0;
 
 	switch (mad_recv_wc->recv_buf.mad->mad_hdr.attr_id) {
 	case CM_REQ_ATTR_ID:
@@ -3452,7 +3480,19 @@ static void cm_recv_handler(struct ib_mad_agent *mad_agent,
 	work->cm_event.event = event;
 	work->mad_recv_wc = mad_recv_wc;
 	work->port = port;
-	queue_delayed_work(cm.wq, &work->work, 0);
+
+	/* Check if the device started its remove_one */
+	spin_lock_irq(&cm.lock);
+	if (!port->cm_dev->going_down)
+		queue_delayed_work(cm.wq, &work->work, 0);
+	else
+		going_down = 1;
+	spin_unlock_irq(&cm.lock);
+
+	if (going_down) {
+		kfree(work);
+		ib_free_recv_mad(mad_recv_wc);
+	}
 }
 
 static int cm_init_qp_init_attr(struct cm_id_private *cm_id_priv,
@@ -3771,7 +3811,7 @@ static void cm_add_one(struct ib_device *ib_device)
 
 	cm_dev->ib_device = ib_device;
 	cm_get_ack_delay(cm_dev);
-
+	cm_dev->going_down = 0;
 	cm_dev->device = device_create(&cm_class, &ib_device->dev,
 				       MKDEV(0, 0), NULL,
 				       "%s", ib_device->name);
@@ -3864,14 +3904,23 @@ static void cm_remove_one(struct ib_device *ib_device)
 	list_del(&cm_dev->list);
 	write_unlock_irqrestore(&cm.device_lock, flags);
 
+	spin_lock_irq(&cm.lock);
+	cm_dev->going_down = 1;
+	spin_unlock_irq(&cm.lock);
+
 	for (i = 1; i <= ib_device->phys_port_cnt; i++) {
 		if (!rdma_cap_ib_cm(ib_device, i))
 			continue;
 
 		port = cm_dev->port[i-1];
 		ib_modify_port(ib_device, port->port_num, 0, &port_modify);
-		ib_unregister_mad_agent(port->mad_agent);
+		/*
+		 * We flush the queue here after the going_down set, this
+		 * verify that no new works will be queued in the recv handler,
+		 * after that we can call the unregister_mad_agent
+		 */
 		flush_workqueue(cm.wq);
+		ib_unregister_mad_agent(port->mad_agent);
 		cm_remove_port_fs(port);
 	}
 	device_unregister(cm_dev->device);

drivers/infiniband/core/iwpm_msg.c

@@ -67,7 +67,8 @@ int iwpm_register_pid(struct iwpm_dev_data *pm_msg, u8 nl_client)
 		err_str = "Invalid port mapper client";
 		goto pid_query_error;
 	}
-	if (iwpm_registered_client(nl_client))
+	if (iwpm_check_registration(nl_client, IWPM_REG_VALID) ||
+			iwpm_user_pid == IWPM_PID_UNAVAILABLE)
 		return 0;
 	skb = iwpm_create_nlmsg(RDMA_NL_IWPM_REG_PID, &nlh, nl_client);
 	if (!skb) {
@@ -106,7 +107,6 @@ int iwpm_register_pid(struct iwpm_dev_data *pm_msg, u8 nl_client)
 	ret = ibnl_multicast(skb, nlh, RDMA_NL_GROUP_IWPM, GFP_KERNEL);
 	if (ret) {
 		skb = NULL; /* skb is freed in the netlink send-op handling */
-		iwpm_set_registered(nl_client, 1);
 		iwpm_user_pid = IWPM_PID_UNAVAILABLE;
 		err_str = "Unable to send a nlmsg";
 		goto pid_query_error;
@@ -144,12 +144,12 @@ int iwpm_add_mapping(struct iwpm_sa_data *pm_msg, u8 nl_client)
 		err_str = "Invalid port mapper client";
 		goto add_mapping_error;
 	}
-	if (!iwpm_registered_client(nl_client)) {
+	if (!iwpm_valid_pid())
+		return 0;
+	if (!iwpm_check_registration(nl_client, IWPM_REG_VALID)) {
 		err_str = "Unregistered port mapper client";
 		goto add_mapping_error;
 	}
-	if (!iwpm_valid_pid())
-		return 0;
 	skb = iwpm_create_nlmsg(RDMA_NL_IWPM_ADD_MAPPING, &nlh, nl_client);
 	if (!skb) {
 		err_str = "Unable to create a nlmsg";
@@ -214,12 +214,12 @@ int iwpm_add_and_query_mapping(struct iwpm_sa_data *pm_msg, u8 nl_client)
 		err_str = "Invalid port mapper client";
 		goto query_mapping_error;
 	}
-	if (!iwpm_registered_client(nl_client)) {
+	if (!iwpm_valid_pid())
+		return 0;
+	if (!iwpm_check_registration(nl_client, IWPM_REG_VALID)) {
 		err_str = "Unregistered port mapper client";
 		goto query_mapping_error;
 	}
-	if (!iwpm_valid_pid())
-		return 0;
 	ret = -ENOMEM;
 	skb = iwpm_create_nlmsg(RDMA_NL_IWPM_QUERY_MAPPING, &nlh, nl_client);
 	if (!skb) {
@@ -288,12 +288,12 @@ int iwpm_remove_mapping(struct sockaddr_storage *local_addr, u8 nl_client)
 		err_str = "Invalid port mapper client";
 		goto remove_mapping_error;
 	}
-	if (!iwpm_registered_client(nl_client)) {
+	if (!iwpm_valid_pid())
+		return 0;
+	if (iwpm_check_registration(nl_client, IWPM_REG_UNDEF)) {
 		err_str = "Unregistered port mapper client";
 		goto remove_mapping_error;
 	}
-	if (!iwpm_valid_pid())
-		return 0;
 	skb = iwpm_create_nlmsg(RDMA_NL_IWPM_REMOVE_MAPPING, &nlh, nl_client);
 	if (!skb) {
 		ret = -ENOMEM;
@@ -388,7 +388,7 @@ int iwpm_register_pid_cb(struct sk_buff *skb, struct netlink_callback *cb)
 	pr_debug("%s: iWarp Port Mapper (pid = %d) is available!\n",
 			__func__, iwpm_user_pid);
 	if (iwpm_valid_client(nl_client))
-		iwpm_set_registered(nl_client, 1);
+		iwpm_set_registration(nl_client, IWPM_REG_VALID);
 register_pid_response_exit:
 	nlmsg_request->request_done = 1;
 	/* always for found nlmsg_request */
@@ -644,7 +644,6 @@ int iwpm_mapping_info_cb(struct sk_buff *skb, struct netlink_callback *cb)
 {
 	struct nlattr *nltb[IWPM_NLA_MAPINFO_REQ_MAX];
 	const char *msg_type = "Mapping Info response";
-	int iwpm_pid;
 	u8 nl_client;
 	char *iwpm_name;
 	u16 iwpm_version;
@@ -669,14 +668,14 @@ int iwpm_mapping_info_cb(struct sk_buff *skb, struct netlink_callback *cb)
 				__func__, nl_client);
 		return ret;
 	}
-	iwpm_set_registered(nl_client, 0);
+	iwpm_set_registration(nl_client, IWPM_REG_INCOMPL);
 	atomic_set(&echo_nlmsg_seq, cb->nlh->nlmsg_seq);
+	iwpm_user_pid = cb->nlh->nlmsg_pid;
 	if (!iwpm_mapinfo_available())
 		return 0;
-	iwpm_pid = cb->nlh->nlmsg_pid;
 	pr_debug("%s: iWarp Port Mapper (pid = %d) is available!\n",
-		 __func__, iwpm_pid);
-	ret = iwpm_send_mapinfo(nl_client, iwpm_pid);
+		 __func__, iwpm_user_pid);
+	ret = iwpm_send_mapinfo(nl_client, iwpm_user_pid);
 	return ret;
 }
 EXPORT_SYMBOL(iwpm_mapping_info_cb);

drivers/infiniband/core/iwpm_util.c

@@ -78,6 +78,7 @@ init_exit:
 	mutex_unlock(&iwpm_admin_lock);
 	if (!ret) {
 		iwpm_set_valid(nl_client, 1);
+		iwpm_set_registration(nl_client, IWPM_REG_UNDEF);
 		pr_debug("%s: Mapinfo and reminfo tables are created\n",
 				__func__);
 	}
@@ -106,6 +107,7 @@ int iwpm_exit(u8 nl_client)
 	}
 	mutex_unlock(&iwpm_admin_lock);
 	iwpm_set_valid(nl_client, 0);
+	iwpm_set_registration(nl_client, IWPM_REG_UNDEF);
 	return 0;
 }
 EXPORT_SYMBOL(iwpm_exit);
@@ -397,17 +399,23 @@ void iwpm_set_valid(u8 nl_client, int valid)
 }
 
 /* valid client */
-int iwpm_registered_client(u8 nl_client)
+u32 iwpm_get_registration(u8 nl_client)
 {
 	return iwpm_admin.reg_list[nl_client];
 }
 
 /* valid client */
-void iwpm_set_registered(u8 nl_client, int reg)
+void iwpm_set_registration(u8 nl_client, u32 reg)
 {
 	iwpm_admin.reg_list[nl_client] = reg;
 }
 
+/* valid client */
+u32 iwpm_check_registration(u8 nl_client, u32 reg)
+{
+	return (iwpm_get_registration(nl_client) & reg);
+}
+
 int iwpm_compare_sockaddr(struct sockaddr_storage *a_sockaddr,
 				struct sockaddr_storage *b_sockaddr)
 {

drivers/infiniband/core/iwpm_util.h

@@ -58,6 +58,10 @@
 #define IWPM_PID_UNDEFINED     -1
 #define IWPM_PID_UNAVAILABLE   -2
 
+#define IWPM_REG_UNDEF          0x01
+#define IWPM_REG_VALID          0x02
+#define IWPM_REG_INCOMPL        0x04
+
 struct iwpm_nlmsg_request {
 	struct list_head    inprocess_list;
 	__u32               nlmsg_seq;
@@ -88,7 +92,7 @@ struct iwpm_admin_data {
 	atomic_t refcount;
 	atomic_t nlmsg_seq;
 	int      client_list[RDMA_NL_NUM_CLIENTS];
-	int      reg_list[RDMA_NL_NUM_CLIENTS];
+	u32      reg_list[RDMA_NL_NUM_CLIENTS];
 };
 
 /**
@@ -159,19 +163,31 @@ int iwpm_valid_client(u8 nl_client);
 void iwpm_set_valid(u8 nl_client, int valid);
 
 /**
- * iwpm_registered_client - Check if the port mapper client is registered
+ * iwpm_check_registration - Check if the client registration
+ *			      matches the given one
  * @nl_client: The index of the netlink client
+ * @reg: The given registration type to compare with
  *
  * Call iwpm_register_pid() to register a client
+ * Returns true if the client registration matches reg,
+ * otherwise returns false
+ */
+u32 iwpm_check_registration(u8 nl_client, u32 reg);
+
+/**
+ * iwpm_set_registration - Set the client registration
+ * @nl_client: The index of the netlink client
+ * @reg: Registration type to set
  */
-int iwpm_registered_client(u8 nl_client);
+void iwpm_set_registration(u8 nl_client, u32 reg);
 
 /**
- * iwpm_set_registered - Set the port mapper client to registered or not
+ * iwpm_get_registration
  * @nl_client: The index of the netlink client
- * @reg: 1 if registered or 0 if not
+ *
+ * Returns the client registration type
  */
-void iwpm_set_registered(u8 nl_client, int reg);
+u32 iwpm_get_registration(u8 nl_client);
 
 /**
  * iwpm_send_mapinfo - Send local and mapped IPv4/IPv6 address info of

drivers/infiniband/core/mad.c

@@ -769,7 +769,7 @@ static int handle_outgoing_dr_smp(struct ib_mad_agent_private *mad_agent_priv,
 	bool opa = rdma_cap_opa_mad(mad_agent_priv->qp_info->port_priv->device,
 				    mad_agent_priv->qp_info->port_priv->port_num);
 
-	if (device->node_type == RDMA_NODE_IB_SWITCH &&
+	if (rdma_cap_ib_switch(device) &&
 	    smp->mgmt_class == IB_MGMT_CLASS_SUBN_DIRECTED_ROUTE)
 		port_num = send_wr->wr.ud.port_num;
 	else
@@ -787,14 +787,15 @@ static int handle_outgoing_dr_smp(struct ib_mad_agent_private *mad_agent_priv,
 		if ((opa_get_smp_direction(opa_smp)
 		     ? opa_smp->route.dr.dr_dlid : opa_smp->route.dr.dr_slid) ==
 		     OPA_LID_PERMISSIVE &&
-		     opa_smi_handle_dr_smp_send(opa_smp, device->node_type,
+		     opa_smi_handle_dr_smp_send(opa_smp,
+						rdma_cap_ib_switch(device),
 						port_num) == IB_SMI_DISCARD) {
 			ret = -EINVAL;
 			dev_err(&device->dev, "OPA Invalid directed route\n");
 			goto out;
 		}
 		opa_drslid = be32_to_cpu(opa_smp->route.dr.dr_slid);
-		if (opa_drslid != OPA_LID_PERMISSIVE &&
+		if (opa_drslid != be32_to_cpu(OPA_LID_PERMISSIVE) &&
 		    opa_drslid & 0xffff0000) {
 			ret = -EINVAL;
 			dev_err(&device->dev, "OPA Invalid dr_slid 0x%x\n",
@@ -810,7 +811,7 @@ static int handle_outgoing_dr_smp(struct ib_mad_agent_private *mad_agent_priv,
 	} else {
 		if ((ib_get_smp_direction(smp) ? smp->dr_dlid : smp->dr_slid) ==
 		     IB_LID_PERMISSIVE &&
-		     smi_handle_dr_smp_send(smp, device->node_type, port_num) ==
+		     smi_handle_dr_smp_send(smp, rdma_cap_ib_switch(device), port_num) ==
 		     IB_SMI_DISCARD) {
 			ret = -EINVAL;
 			dev_err(&device->dev, "Invalid directed route\n");
@@ -2030,7 +2031,7 @@ static enum smi_action handle_ib_smi(const struct ib_mad_port_private *port_priv
 	struct ib_smp *smp = (struct ib_smp *)recv->mad;
 
 	if (smi_handle_dr_smp_recv(smp,
-				   port_priv->device->node_type,
+				   rdma_cap_ib_switch(port_priv->device),
 				   port_num,
 				   port_priv->device->phys_port_cnt) ==
 				   IB_SMI_DISCARD)
@@ -2042,13 +2043,13 @@ static enum smi_action handle_ib_smi(const struct ib_mad_port_private *port_priv
 
 	if (retsmi == IB_SMI_SEND) { /* don't forward */
 		if (smi_handle_dr_smp_send(smp,
-					   port_priv->device->node_type,
+					   rdma_cap_ib_switch(port_priv->device),
 					   port_num) == IB_SMI_DISCARD)
 			return IB_SMI_DISCARD;
 
 		if (smi_check_local_smp(smp, port_priv->device) == IB_SMI_DISCARD)
 			return IB_SMI_DISCARD;
-	} else if (port_priv->device->node_type == RDMA_NODE_IB_SWITCH) {
+	} else if (rdma_cap_ib_switch(port_priv->device)) {
 		/* forward case for switches */
 		memcpy(response, recv, mad_priv_size(response));
 		response->header.recv_wc.wc = &response->header.wc;
@@ -2115,7 +2116,7 @@ handle_opa_smi(struct ib_mad_port_private *port_priv,
 	struct opa_smp *smp = (struct opa_smp *)recv->mad;
 
 	if (opa_smi_handle_dr_smp_recv(smp,
-				   port_priv->device->node_type,
+				   rdma_cap_ib_switch(port_priv->device),
 				   port_num,
 				   port_priv->device->phys_port_cnt) ==
 				   IB_SMI_DISCARD)
@@ -2127,7 +2128,7 @@ handle_opa_smi(struct ib_mad_port_private *port_priv,
 
 	if (retsmi == IB_SMI_SEND) { /* don't forward */
 		if (opa_smi_handle_dr_smp_send(smp,
-					   port_priv->device->node_type,
+					   rdma_cap_ib_switch(port_priv->device),
 					   port_num) == IB_SMI_DISCARD)
 			return IB_SMI_DISCARD;
 
@@ -2135,7 +2136,7 @@ handle_opa_smi(struct ib_mad_port_private *port_priv,
 		    IB_SMI_DISCARD)
 			return IB_SMI_DISCARD;
 
-	} else if (port_priv->device->node_type == RDMA_NODE_IB_SWITCH) {
+	} else if (rdma_cap_ib_switch(port_priv->device)) {
 		/* forward case for switches */
 		memcpy(response, recv, mad_priv_size(response));
 		response->header.recv_wc.wc = &response->header.wc;
@@ -2235,7 +2236,7 @@ static void ib_mad_recv_done_handler(struct ib_mad_port_private *port_priv,
 		goto out;
 	}
 
-	if (port_priv->device->node_type == RDMA_NODE_IB_SWITCH)
+	if (rdma_cap_ib_switch(port_priv->device))
 		port_num = wc->port_num;
 	else
 		port_num = port_priv->port_num;
@@ -3297,17 +3298,11 @@ static int ib_mad_port_close(struct ib_device *device, int port_num)
 
 static void ib_mad_init_device(struct ib_device *device)
 {
-	int start, end, i;
+	int start, i;
 
-	if (device->node_type == RDMA_NODE_IB_SWITCH) {
-		start = 0;
-		end   = 0;
-	} else {
-		start = 1;
-		end   = device->phys_port_cnt;
-	}
+	start = rdma_start_port(device);
 
-	for (i = start; i <= end; i++) {
+	for (i = start; i <= rdma_end_port(device); i++) {
 		if (!rdma_cap_ib_mad(device, i))
 			continue;
 
@@ -3342,17 +3337,9 @@ error:
 
 static void ib_mad_remove_device(struct ib_device *device)
 {
-	int start, end, i;
-
-	if (device->node_type == RDMA_NODE_IB_SWITCH) {
-		start = 0;
-		end   = 0;
-	} else {
-		start = 1;
-		end   = device->phys_port_cnt;
-	}
+	int i;
 
-	for (i = start; i <= end; i++) {
+	for (i = rdma_start_port(device); i <= rdma_end_port(device); i++) {
 		if (!rdma_cap_ib_mad(device, i))
 			continue;
 

drivers/infiniband/core/multicast.c

@@ -812,12 +812,8 @@ static void mcast_add_one(struct ib_device *device)
 	if (!dev)
 		return;
 
-	if (device->node_type == RDMA_NODE_IB_SWITCH)
-		dev->start_port = dev->end_port = 0;
-	else {
-		dev->start_port = 1;
-		dev->end_port = device->phys_port_cnt;
-	}
+	dev->start_port = rdma_start_port(device);
+	dev->end_port = rdma_end_port(device);
 
 	for (i = 0; i <= dev->end_port - dev->start_port; i++) {
 		if (!rdma_cap_ib_mcast(device, dev->start_port + i))

drivers/infiniband/core/opa_smi.h

@@ -39,12 +39,12 @@
 
 #include "smi.h"
 
-enum smi_action opa_smi_handle_dr_smp_recv(struct opa_smp *smp, u8 node_type,
+enum smi_action opa_smi_handle_dr_smp_recv(struct opa_smp *smp, bool is_switch,
 				       int port_num, int phys_port_cnt);
 int opa_smi_get_fwd_port(struct opa_smp *smp);
 extern enum smi_forward_action opa_smi_check_forward_dr_smp(struct opa_smp *smp);
 extern enum smi_action opa_smi_handle_dr_smp_send(struct opa_smp *smp,
-					      u8 node_type, int port_num);
+					      bool is_switch, int port_num);
 
 /*
  * Return IB_SMI_HANDLE if the SMP should be handled by the local SMA/SM

drivers/infiniband/core/sa_query.c

@@ -1156,12 +1156,8 @@ static void ib_sa_add_one(struct ib_device *device)
 	int s, e, i;
 	int count = 0;
 
-	if (device->node_type == RDMA_NODE_IB_SWITCH)
-		s = e = 0;
-	else {
-		s = 1;
-		e = device->phys_port_cnt;
-	}
+	s = rdma_start_port(device);
+	e = rdma_end_port(device);
 
 	sa_dev = kzalloc(sizeof *sa_dev +
 			 (e - s + 1) * sizeof (struct ib_sa_port),

drivers/infiniband/core/smi.c

@@ -41,7 +41,7 @@
 #include "smi.h"
 #include "opa_smi.h"
 
-static enum smi_action __smi_handle_dr_smp_send(u8 node_type, int port_num,
+static enum smi_action __smi_handle_dr_smp_send(bool is_switch, int port_num,
 						u8 *hop_ptr, u8 hop_cnt,
 						const u8 *initial_path,
 						const u8 *return_path,
@@ -64,7 +64,7 @@ static enum smi_action __smi_handle_dr_smp_send(u8 node_type, int port_num,
 
 		/* C14-9:2 */
 		if (*hop_ptr && *hop_ptr < hop_cnt) {
-			if (node_type != RDMA_NODE_IB_SWITCH)
+			if (!is_switch)
 				return IB_SMI_DISCARD;
 
 			/* return_path set when received */
@@ -77,7 +77,7 @@ static enum smi_action __smi_handle_dr_smp_send(u8 node_type, int port_num,
 		if (*hop_ptr == hop_cnt) {
 			/* return_path set when received */
 			(*hop_ptr)++;
-			return (node_type == RDMA_NODE_IB_SWITCH ||
+			return (is_switch ||
 				dr_dlid_is_permissive ?
 				IB_SMI_HANDLE : IB_SMI_DISCARD);
 		}
@@ -96,7 +96,7 @@ static enum smi_action __smi_handle_dr_smp_send(u8 node_type, int port_num,
 
 		/* C14-13:2 */
 		if (2 <= *hop_ptr && *hop_ptr <= hop_cnt) {
-			if (node_type != RDMA_NODE_IB_SWITCH)
+			if (!is_switch)
 				return IB_SMI_DISCARD;
 
 			(*hop_ptr)--;
@@ -108,7 +108,7 @@ static enum smi_action __smi_handle_dr_smp_send(u8 node_type, int port_num,
 		if (*hop_ptr == 1) {
 			(*hop_ptr)--;
 			/* C14-13:3 -- SMPs destined for SM shouldn't be here */
-			return (node_type == RDMA_NODE_IB_SWITCH ||
+			return (is_switch ||
 				dr_slid_is_permissive ?
 				IB_SMI_HANDLE : IB_SMI_DISCARD);
 		}
@@ -127,9 +127,9 @@ static enum smi_action __smi_handle_dr_smp_send(u8 node_type, int port_num,
  * Return IB_SMI_DISCARD if the SMP should be discarded
  */
 enum smi_action smi_handle_dr_smp_send(struct ib_smp *smp,
-				       u8 node_type, int port_num)
+				       bool is_switch, int port_num)
 {
-	return __smi_handle_dr_smp_send(node_type, port_num,
+	return __smi_handle_dr_smp_send(is_switch, port_num,
 					&smp->hop_ptr, smp->hop_cnt,
 					smp->initial_path,
 					smp->return_path,
@@ -139,9 +139,9 @@ enum smi_action smi_handle_dr_smp_send(struct ib_smp *smp,
 }
 
 enum smi_action opa_smi_handle_dr_smp_send(struct opa_smp *smp,
-				       u8 node_type, int port_num)
+				       bool is_switch, int port_num)
 {
-	return __smi_handle_dr_smp_send(node_type, port_num,
+	return __smi_handle_dr_smp_send(is_switch, port_num,
 					&smp->hop_ptr, smp->hop_cnt,
 					smp->route.dr.initial_path,
 					smp->route.dr.return_path,
@@ -152,7 +152,7 @@ enum smi_action opa_smi_handle_dr_smp_send(struct opa_smp *smp,
 					OPA_LID_PERMISSIVE);
 }
 
-static enum smi_action __smi_handle_dr_smp_recv(u8 node_type, int port_num,
+static enum smi_action __smi_handle_dr_smp_recv(bool is_switch, int port_num,
 						int phys_port_cnt,
 						u8 *hop_ptr, u8 hop_cnt,
 						const u8 *initial_path,
@@ -173,7 +173,7 @@ static enum smi_action __smi_handle_dr_smp_recv(u8 node_type, int port_num,
 
 		/* C14-9:2 -- intermediate hop */
 		if (*hop_ptr && *hop_ptr < hop_cnt) {
-			if (node_type != RDMA_NODE_IB_SWITCH)
+			if (!is_switch)
 				return IB_SMI_DISCARD;
 
 			return_path[*hop_ptr] = port_num;
@@ -188,7 +188,7 @@ static enum smi_action __smi_handle_dr_smp_recv(u8 node_type, int port_num,
 				return_path[*hop_ptr] = port_num;
 			/* hop_ptr updated when sending */
 
-			return (node_type == RDMA_NODE_IB_SWITCH ||
+			return (is_switch ||
 				dr_dlid_is_permissive ?
 				IB_SMI_HANDLE : IB_SMI_DISCARD);
 		}
@@ -208,7 +208,7 @@ static enum smi_action __smi_handle_dr_smp_recv(u8 node_type, int port_num,
 
 		/* C14-13:2 */
 		if (2 <= *hop_ptr && *hop_ptr <= hop_cnt) {
-			if (node_type != RDMA_NODE_IB_SWITCH)
+			if (!is_switch)
 				return IB_SMI_DISCARD;
 
 			/* hop_ptr updated when sending */
@@ -224,8 +224,7 @@ static enum smi_action __smi_handle_dr_smp_recv(u8 node_type, int port_num,
 				return IB_SMI_HANDLE;
 			}
 			/* hop_ptr updated when sending */
-			return (node_type == RDMA_NODE_IB_SWITCH ?
-				IB_SMI_HANDLE : IB_SMI_DISCARD);
+			return (is_switch ? IB_SMI_HANDLE : IB_SMI_DISCARD);
 		}
 
 		/* C14-13:4 -- hop_ptr = 0 -> give to SM */
@@ -238,10 +237,10 @@ static enum smi_action __smi_handle_dr_smp_recv(u8 node_type, int port_num,
  * Adjust information for a received SMP
  * Return IB_SMI_DISCARD if the SMP should be dropped
  */
-enum smi_action smi_handle_dr_smp_recv(struct ib_smp *smp, u8 node_type,
+enum smi_action smi_handle_dr_smp_recv(struct ib_smp *smp, bool is_switch,
 				       int port_num, int phys_port_cnt)
 {
-	return __smi_handle_dr_smp_recv(node_type, port_num, phys_port_cnt,
+	return __smi_handle_dr_smp_recv(is_switch, port_num, phys_port_cnt,
 					&smp->hop_ptr, smp->hop_cnt,
 					smp->initial_path,
 					smp->return_path,
@@ -254,10 +253,10 @@ enum smi_action smi_handle_dr_smp_recv(struct ib_smp *smp, u8 node_type,
  * Adjust information for a received SMP
  * Return IB_SMI_DISCARD if the SMP should be dropped
  */
-enum smi_action opa_smi_handle_dr_smp_recv(struct opa_smp *smp, u8 node_type,
+enum smi_action opa_smi_handle_dr_smp_recv(struct opa_smp *smp, bool is_switch,
 					   int port_num, int phys_port_cnt)
 {
-	return __smi_handle_dr_smp_recv(node_type, port_num, phys_port_cnt,
+	return __smi_handle_dr_smp_recv(is_switch, port_num, phys_port_cnt,
 					&smp->hop_ptr, smp->hop_cnt,
 					smp->route.dr.initial_path,
 					smp->route.dr.return_path,

drivers/infiniband/core/smi.h

@@ -51,12 +51,12 @@ enum smi_forward_action {
 	IB_SMI_FORWARD	/* SMP should be forwarded (for switches only) */
 };
 
-enum smi_action smi_handle_dr_smp_recv(struct ib_smp *smp, u8 node_type,
+enum smi_action smi_handle_dr_smp_recv(struct ib_smp *smp, bool is_switch,
 				       int port_num, int phys_port_cnt);
 int smi_get_fwd_port(struct ib_smp *smp);
 extern enum smi_forward_action smi_check_forward_dr_smp(struct ib_smp *smp);
 extern enum smi_action smi_handle_dr_smp_send(struct ib_smp *smp,
-					      u8 node_type, int port_num);
+					      bool is_switch, int port_num);
 
 /*
  * Return IB_SMI_HANDLE if the SMP should be handled by the local SMA/SM

drivers/infiniband/core/sysfs.c

@@ -870,7 +870,7 @@ int ib_device_register_sysfs(struct ib_device *device,
 		goto err_put;
 	}
 
-	if (device->node_type == RDMA_NODE_IB_SWITCH) {
+	if (rdma_cap_ib_switch(device)) {
 		ret = add_port(device, 0, port_callback);
 		if (ret)
 			goto err_put;

drivers/infiniband/core/ucm.c

@@ -1193,6 +1193,7 @@ static int ib_ucm_close(struct inode *inode, struct file *filp)
 	return 0;
 }
 
+static DECLARE_BITMAP(overflow_map, IB_UCM_MAX_DEVICES);
 static void ib_ucm_release_dev(struct device *dev)
 {
 	struct ib_ucm_device *ucm_dev;
@@ -1202,7 +1203,7 @@ static void ib_ucm_release_dev(struct device *dev)
 	if (ucm_dev->devnum < IB_UCM_MAX_DEVICES)
 		clear_bit(ucm_dev->devnum, dev_map);
 	else
-		clear_bit(ucm_dev->devnum - IB_UCM_MAX_DEVICES, dev_map);
+		clear_bit(ucm_dev->devnum - IB_UCM_MAX_DEVICES, overflow_map);
 	kfree(ucm_dev);
 }
 
@@ -1226,7 +1227,6 @@ static ssize_t show_ibdev(struct device *dev, struct device_attribute *attr,
 static DEVICE_ATTR(ibdev, S_IRUGO, show_ibdev, NULL);
 
 static dev_t overflow_maj;
-static DECLARE_BITMAP(overflow_map, IB_UCM_MAX_DEVICES);
 static int find_overflow_devnum(void)
 {
 	int ret;

drivers/infiniband/core/ucma.c

@@ -1354,10 +1354,10 @@ static void ucma_lock_files(struct ucma_file *file1, struct ucma_file *file2)
 	/* Acquire mutex's based on pointer comparison to prevent deadlock. */
 	if (file1 < file2) {
 		mutex_lock(&file1->mut);
-		mutex_lock(&file2->mut);
+		mutex_lock_nested(&file2->mut, SINGLE_DEPTH_NESTING);
 	} else {
 		mutex_lock(&file2->mut);
-		mutex_lock(&file1->mut);
+		mutex_lock_nested(&file1->mut, SINGLE_DEPTH_NESTING);
 	}
 }
 
@@ -1616,6 +1616,7 @@ static void __exit ucma_cleanup(void)
 	device_remove_file(ucma_misc.this_device, &dev_attr_abi_version);
 	misc_deregister(&ucma_misc);
 	idr_destroy(&ctx_idr);
+	idr_destroy(&multicast_idr);
 }
 
 module_init(ucma_init);

drivers/infiniband/hw/ehca/ehca_sqp.c

@@ -226,8 +226,9 @@ int ehca_process_mad(struct ib_device *ibdev, int mad_flags, u8 port_num,
 	const struct ib_mad *in_mad = (const struct ib_mad *)in;
 	struct ib_mad *out_mad = (struct ib_mad *)out;
 
-	BUG_ON(in_mad_size != sizeof(*in_mad) ||
-	       *out_mad_size != sizeof(*out_mad));
+	if (WARN_ON_ONCE(in_mad_size != sizeof(*in_mad) ||
+			 *out_mad_size != sizeof(*out_mad)))
+		return IB_MAD_RESULT_FAILURE;
 
 	if (!port_num || port_num > ibdev->phys_port_cnt || !in_wc)
 		return IB_MAD_RESULT_FAILURE;

drivers/infiniband/hw/ipath/ipath_mad.c

@@ -1499,8 +1499,9 @@ int ipath_process_mad(struct ib_device *ibdev, int mad_flags, u8 port_num,
 	const struct ib_mad *in_mad = (const struct ib_mad *)in;
 	struct ib_mad *out_mad = (struct ib_mad *)out;
 
-	BUG_ON(in_mad_size != sizeof(*in_mad) ||
-	       *out_mad_size != sizeof(*out_mad));
+	if (WARN_ON_ONCE(in_mad_size != sizeof(*in_mad) ||
+			 *out_mad_size != sizeof(*out_mad)))
+		return IB_MAD_RESULT_FAILURE;
 
 	switch (in_mad->mad_hdr.mgmt_class) {
 	case IB_MGMT_CLASS_SUBN_DIRECTED_ROUTE:

drivers/infiniband/hw/ipath/ipath_verbs.c

@@ -2044,9 +2044,9 @@ int ipath_register_ib_device(struct ipath_devdata *dd)
 
 	spin_lock_init(&idev->qp_table.lock);
 	spin_lock_init(&idev->lk_table.lock);
-	idev->sm_lid = __constant_be16_to_cpu(IB_LID_PERMISSIVE);
+	idev->sm_lid = be16_to_cpu(IB_LID_PERMISSIVE);
 	/* Set the prefix to the default value (see ch. 4.1.1) */
-	idev->gid_prefix = __constant_cpu_to_be64(0xfe80000000000000ULL);
+	idev->gid_prefix = cpu_to_be64(0xfe80000000000000ULL);
 
 	ret = ipath_init_qp_table(idev, ib_ipath_qp_table_size);
 	if (ret)

drivers/infiniband/hw/mlx4/mad.c

@@ -860,21 +860,31 @@ int mlx4_ib_process_mad(struct ib_device *ibdev, int mad_flags, u8 port_num,
 	struct mlx4_ib_dev *dev = to_mdev(ibdev);
 	const struct ib_mad *in_mad = (const struct ib_mad *)in;
 	struct ib_mad *out_mad = (struct ib_mad *)out;
+	enum rdma_link_layer link = rdma_port_get_link_layer(ibdev, port_num);
 
-	BUG_ON(in_mad_size != sizeof(*in_mad) ||
-	       *out_mad_size != sizeof(*out_mad));
+	if (WARN_ON_ONCE(in_mad_size != sizeof(*in_mad) ||
+			 *out_mad_size != sizeof(*out_mad)))
+		return IB_MAD_RESULT_FAILURE;
 
-	switch (rdma_port_get_link_layer(ibdev, port_num)) {
-	case IB_LINK_LAYER_INFINIBAND:
-		if (!mlx4_is_slave(dev->dev))
-			return ib_process_mad(ibdev, mad_flags, port_num, in_wc,
-					      in_grh, in_mad, out_mad);
-	case IB_LINK_LAYER_ETHERNET:
-		return iboe_process_mad(ibdev, mad_flags, port_num, in_wc,
-					  in_grh, in_mad, out_mad);
-	default:
-		return -EINVAL;
+	/* iboe_process_mad() which uses the HCA flow-counters to implement IB PMA
+	 * queries, should be called only by VFs and for that specific purpose
+	 */
+	if (link == IB_LINK_LAYER_INFINIBAND) {
+		if (mlx4_is_slave(dev->dev) &&
+		    in_mad->mad_hdr.mgmt_class == IB_MGMT_CLASS_PERF_MGMT &&
+		    in_mad->mad_hdr.attr_id == IB_PMA_PORT_COUNTERS)
+			return iboe_process_mad(ibdev, mad_flags, port_num, in_wc,
+						in_grh, in_mad, out_mad);
+
+		return ib_process_mad(ibdev, mad_flags, port_num, in_wc,
+				      in_grh, in_mad, out_mad);
 	}
+
+	if (link == IB_LINK_LAYER_ETHERNET)
+		return iboe_process_mad(ibdev, mad_flags, port_num, in_wc,
+					in_grh, in_mad, out_mad);
+
+	return -EINVAL;
 }
 
 static void send_handler(struct ib_mad_agent *agent,

drivers/infiniband/hw/mlx4/main.c

@@ -253,14 +253,15 @@ static int mlx4_ib_query_device(struct ib_device *ibdev,
 	props->hca_core_clock = dev->dev->caps.hca_core_clock * 1000UL;
 	props->timestamp_mask = 0xFFFFFFFFFFFFULL;
 
-	err = mlx4_get_internal_clock_params(dev->dev, &clock_params);
-	if (err)
-		goto out;
+	if (!mlx4_is_slave(dev->dev))
+		err = mlx4_get_internal_clock_params(dev->dev, &clock_params);
 
 	if (uhw->outlen >= resp.response_length + sizeof(resp.hca_core_clock_offset)) {
-		resp.hca_core_clock_offset = clock_params.offset % PAGE_SIZE;
 		resp.response_length += sizeof(resp.hca_core_clock_offset);
-		resp.comp_mask |= QUERY_DEVICE_RESP_MASK_TIMESTAMP;
+		if (!err && !mlx4_is_slave(dev->dev)) {
+			resp.comp_mask |= QUERY_DEVICE_RESP_MASK_TIMESTAMP;
+			resp.hca_core_clock_offset = clock_params.offset % PAGE_SIZE;
+		}
 	}
 
 	if (uhw->outlen) {
@@ -2669,31 +2670,33 @@ static void do_slave_init(struct mlx4_ib_dev *ibdev, int slave, int do_init)
 	dm = kcalloc(ports, sizeof(*dm), GFP_ATOMIC);
 	if (!dm) {
 		pr_err("failed to allocate memory for tunneling qp update\n");
-		goto out;
+		return;
 	}
 
 	for (i = 0; i < ports; i++) {
 		dm[i] = kmalloc(sizeof (struct mlx4_ib_demux_work), GFP_ATOMIC);
 		if (!dm[i]) {
 			pr_err("failed to allocate memory for tunneling qp update work struct\n");
-			for (i = 0; i < dev->caps.num_ports; i++) {
-				if (dm[i])
-					kfree(dm[i]);
-			}
+			while (--i >= 0)
+				kfree(dm[i]);
 			goto out;
 		}
-	}
-	/* initialize or tear down tunnel QPs for the slave */
-	for (i = 0; i < ports; i++) {
 		INIT_WORK(&dm[i]->work, mlx4_ib_tunnels_update_work);
 		dm[i]->port = first_port + i + 1;
 		dm[i]->slave = slave;
 		dm[i]->do_init = do_init;
 		dm[i]->dev = ibdev;
-		spin_lock_irqsave(&ibdev->sriov.going_down_lock, flags);
-		if (!ibdev->sriov.is_going_down)
+	}
+	/* initialize or tear down tunnel QPs for the slave */
+	spin_lock_irqsave(&ibdev->sriov.going_down_lock, flags);
+	if (!ibdev->sriov.is_going_down) {
+		for (i = 0; i < ports; i++)
 			queue_work(ibdev->sriov.demux[i].ud_wq, &dm[i]->work);
 		spin_unlock_irqrestore(&ibdev->sriov.going_down_lock, flags);
+	} else {
+		spin_unlock_irqrestore(&ibdev->sriov.going_down_lock, flags);
+		for (i = 0; i < ports; i++)
+			kfree(dm[i]);
 	}
 out:
 	kfree(dm);

drivers/infiniband/hw/mlx5/mad.c

@@ -68,8 +68,9 @@ int mlx5_ib_process_mad(struct ib_device *ibdev, int mad_flags, u8 port_num,
 	const struct ib_mad *in_mad = (const struct ib_mad *)in;
 	struct ib_mad *out_mad = (struct ib_mad *)out;
 
-	BUG_ON(in_mad_size != sizeof(*in_mad) ||
-	       *out_mad_size != sizeof(*out_mad));
+	if (WARN_ON_ONCE(in_mad_size != sizeof(*in_mad) ||
+			 *out_mad_size != sizeof(*out_mad)))
+		return IB_MAD_RESULT_FAILURE;
 
 	slid = in_wc ? in_wc->slid : be16_to_cpu(IB_LID_PERMISSIVE);
 

drivers/infiniband/hw/mthca/mthca_mad.c

@@ -209,8 +209,9 @@ int mthca_process_mad(struct ib_device *ibdev,
 	const struct ib_mad *in_mad = (const struct ib_mad *)in;
 	struct ib_mad *out_mad = (struct ib_mad *)out;
 
-	BUG_ON(in_mad_size != sizeof(*in_mad) ||
-	       *out_mad_size != sizeof(*out_mad));
+	if (WARN_ON_ONCE(in_mad_size != sizeof(*in_mad) ||
+			 *out_mad_size != sizeof(*out_mad)))
+		return IB_MAD_RESULT_FAILURE;
 
 	/* Forward locally generated traps to the SM */
 	if (in_mad->mad_hdr.method == IB_MGMT_METHOD_TRAP &&

drivers/infiniband/hw/nes/nes_cm.c

@@ -1520,8 +1520,9 @@ static int nes_addr_resolve_neigh(struct nes_vnic *nesvnic, u32 dst_ip, int arpi
 	int rc = arpindex;
 	struct net_device *netdev;
 	struct nes_adapter *nesadapter = nesvnic->nesdev->nesadapter;
+	__be32 dst_ipaddr = htonl(dst_ip);
 
-	rt = ip_route_output(&init_net, htonl(dst_ip), 0, 0, 0);
+	rt = ip_route_output(&init_net, dst_ipaddr, nesvnic->local_ipaddr, 0, 0);
 	if (IS_ERR(rt)) {
 		printk(KERN_ERR "%s: ip_route_output_key failed for 0x%08X\n",
 		       __func__, dst_ip);
@@ -1533,7 +1534,7 @@ static int nes_addr_resolve_neigh(struct nes_vnic *nesvnic, u32 dst_ip, int arpi
 	else
 		netdev = nesvnic->netdev;
 
-	neigh = neigh_lookup(&arp_tbl, &rt->rt_gateway, netdev);
+	neigh = dst_neigh_lookup(&rt->dst, &dst_ipaddr);
 
 	rcu_read_lock();
 	if (neigh) {

drivers/infiniband/hw/nes/nes_hw.c

@@ -3861,7 +3861,7 @@ void nes_manage_arp_cache(struct net_device *netdev, unsigned char *mac_addr,
 				(((u32)mac_addr[2]) << 24) | (((u32)mac_addr[3]) << 16) |
 				(((u32)mac_addr[4]) << 8)  | (u32)mac_addr[5]);
 		cqp_wqe->wqe_words[NES_CQP_ARP_WQE_MAC_HIGH_IDX] = cpu_to_le32(
-				(((u32)mac_addr[0]) << 16) | (u32)mac_addr[1]);
+				(((u32)mac_addr[0]) << 8) | (u32)mac_addr[1]);
 	} else {
 		cqp_wqe->wqe_words[NES_CQP_ARP_WQE_MAC_ADDR_LOW_IDX] = 0;
 		cqp_wqe->wqe_words[NES_CQP_ARP_WQE_MAC_HIGH_IDX] = 0;

drivers/infiniband/hw/ocrdma/ocrdma_ah.c

@@ -215,8 +215,9 @@ int ocrdma_process_mad(struct ib_device *ibdev,
 	const struct ib_mad *in_mad = (const struct ib_mad *)in;
 	struct ib_mad *out_mad = (struct ib_mad *)out;
 
-	BUG_ON(in_mad_size != sizeof(*in_mad) ||
-	       *out_mad_size != sizeof(*out_mad));
+	if (WARN_ON_ONCE(in_mad_size != sizeof(*in_mad) ||
+			 *out_mad_size != sizeof(*out_mad)))
+		return IB_MAD_RESULT_FAILURE;
 
 	switch (in_mad->mad_hdr.mgmt_class) {
 	case IB_MGMT_CLASS_PERF_MGMT:

drivers/infiniband/hw/ocrdma/ocrdma_main.c

@@ -696,6 +696,7 @@ static void __exit ocrdma_exit_module(void)
 	ocrdma_unregister_inet6addr_notifier();
 	ocrdma_unregister_inetaddr_notifier();
 	ocrdma_rem_debugfs();
+	idr_destroy(&ocrdma_dev_id);
 }
 
 module_init(ocrdma_init_module);

drivers/infiniband/hw/qib/qib_mad.c

@@ -2412,8 +2412,9 @@ int qib_process_mad(struct ib_device *ibdev, int mad_flags, u8 port,
 	const struct ib_mad *in_mad = (const struct ib_mad *)in;
 	struct ib_mad *out_mad = (struct ib_mad *)out;
 
-	BUG_ON(in_mad_size != sizeof(*in_mad) ||
-	       *out_mad_size != sizeof(*out_mad));
+	if (WARN_ON_ONCE(in_mad_size != sizeof(*in_mad) ||
+			 *out_mad_size != sizeof(*out_mad)))
+		return IB_MAD_RESULT_FAILURE;
 
 	switch (in_mad->mad_hdr.mgmt_class) {
 	case IB_MGMT_CLASS_SUBN_DIRECTED_ROUTE:

drivers/infiniband/ulp/ipoib/ipoib.h

@@ -239,7 +239,7 @@ struct ipoib_cm_tx {
 	struct net_device   *dev;
 	struct ipoib_neigh  *neigh;
 	struct ipoib_path   *path;
-	struct ipoib_cm_tx_buf *tx_ring;
+	struct ipoib_tx_buf *tx_ring;
 	unsigned	     tx_head;
 	unsigned	     tx_tail;
 	unsigned long	     flags;
@@ -504,6 +504,33 @@ int ipoib_mcast_stop_thread(struct net_device *dev);
 void ipoib_mcast_dev_down(struct net_device *dev);
 void ipoib_mcast_dev_flush(struct net_device *dev);
 
+int ipoib_dma_map_tx(struct ib_device *ca, struct ipoib_tx_buf *tx_req);
+void ipoib_dma_unmap_tx(struct ipoib_dev_priv *priv,
+			struct ipoib_tx_buf *tx_req);
+
+static inline void ipoib_build_sge(struct ipoib_dev_priv *priv,
+				   struct ipoib_tx_buf *tx_req)
+{
+	int i, off;
+	struct sk_buff *skb = tx_req->skb;
+	skb_frag_t *frags = skb_shinfo(skb)->frags;
+	int nr_frags = skb_shinfo(skb)->nr_frags;
+	u64 *mapping = tx_req->mapping;
+
+	if (skb_headlen(skb)) {
+		priv->tx_sge[0].addr         = mapping[0];
+		priv->tx_sge[0].length       = skb_headlen(skb);
+		off = 1;
+	} else
+		off = 0;
+
+	for (i = 0; i < nr_frags; ++i) {
+		priv->tx_sge[i + off].addr = mapping[i + off];
+		priv->tx_sge[i + off].length = skb_frag_size(&frags[i]);
+	}
+	priv->tx_wr.num_sge	     = nr_frags + off;
+}
+
 #ifdef CONFIG_INFINIBAND_IPOIB_DEBUG
 struct ipoib_mcast_iter *ipoib_mcast_iter_init(struct net_device *dev);
 int ipoib_mcast_iter_next(struct ipoib_mcast_iter *iter);

drivers/infiniband/ulp/ipoib/ipoib_cm.c

@@ -694,14 +694,12 @@ repost:
 static inline int post_send(struct ipoib_dev_priv *priv,
 			    struct ipoib_cm_tx *tx,
 			    unsigned int wr_id,
-			    u64 addr, int len)
+			    struct ipoib_tx_buf *tx_req)
 {
 	struct ib_send_wr *bad_wr;
 
-	priv->tx_sge[0].addr          = addr;
-	priv->tx_sge[0].length        = len;
+	ipoib_build_sge(priv, tx_req);
 
-	priv->tx_wr.num_sge	= 1;
 	priv->tx_wr.wr_id	= wr_id | IPOIB_OP_CM;
 
 	return ib_post_send(tx->qp, &priv->tx_wr, &bad_wr);
@@ -710,8 +708,7 @@ static inline int post_send(struct ipoib_dev_priv *priv,
 void ipoib_cm_send(struct net_device *dev, struct sk_buff *skb, struct ipoib_cm_tx *tx)
 {
 	struct ipoib_dev_priv *priv = netdev_priv(dev);
-	struct ipoib_cm_tx_buf *tx_req;
-	u64 addr;
+	struct ipoib_tx_buf *tx_req;
 	int rc;
 
 	if (unlikely(skb->len > tx->mtu)) {
@@ -735,24 +732,21 @@ void ipoib_cm_send(struct net_device *dev, struct sk_buff *skb, struct ipoib_cm_
 	 */
 	tx_req = &tx->tx_ring[tx->tx_head & (ipoib_sendq_size - 1)];
 	tx_req->skb = skb;
-	addr = ib_dma_map_single(priv->ca, skb->data, skb->len, DMA_TO_DEVICE);
-	if (unlikely(ib_dma_mapping_error(priv->ca, addr))) {
+
+	if (unlikely(ipoib_dma_map_tx(priv->ca, tx_req))) {
 		++dev->stats.tx_errors;
 		dev_kfree_skb_any(skb);
 		return;
 	}
 
-	tx_req->mapping = addr;
-
 	skb_orphan(skb);
 	skb_dst_drop(skb);
 
-	rc = post_send(priv, tx, tx->tx_head & (ipoib_sendq_size - 1),
-		       addr, skb->len);
+	rc = post_send(priv, tx, tx->tx_head & (ipoib_sendq_size - 1), tx_req);
 	if (unlikely(rc)) {
 		ipoib_warn(priv, "post_send failed, error %d\n", rc);
 		++dev->stats.tx_errors;
-		ib_dma_unmap_single(priv->ca, addr, skb->len, DMA_TO_DEVICE);
+		ipoib_dma_unmap_tx(priv, tx_req);
 		dev_kfree_skb_any(skb);
 	} else {
 		dev->trans_start = jiffies;
@@ -777,7 +771,7 @@ void ipoib_cm_handle_tx_wc(struct net_device *dev, struct ib_wc *wc)
 	struct ipoib_dev_priv *priv = netdev_priv(dev);
 	struct ipoib_cm_tx *tx = wc->qp->qp_context;
 	unsigned int wr_id = wc->wr_id & ~IPOIB_OP_CM;
-	struct ipoib_cm_tx_buf *tx_req;
+	struct ipoib_tx_buf *tx_req;
 	unsigned long flags;
 
 	ipoib_dbg_data(priv, "cm send completion: id %d, status: %d\n",
@@ -791,7 +785,7 @@ void ipoib_cm_handle_tx_wc(struct net_device *dev, struct ib_wc *wc)
 
 	tx_req = &tx->tx_ring[wr_id];
 
-	ib_dma_unmap_single(priv->ca, tx_req->mapping, tx_req->skb->len, DMA_TO_DEVICE);
+	ipoib_dma_unmap_tx(priv, tx_req);
 
 	/* FIXME: is this right? Shouldn't we only increment on success? */
 	++dev->stats.tx_packets;
@@ -1036,6 +1030,9 @@ static struct ib_qp *ipoib_cm_create_tx_qp(struct net_device *dev, struct ipoib_
 
 	struct ib_qp *tx_qp;
 
+	if (dev->features & NETIF_F_SG)
+		attr.cap.max_send_sge = MAX_SKB_FRAGS + 1;
+
 	tx_qp = ib_create_qp(priv->pd, &attr);
 	if (PTR_ERR(tx_qp) == -EINVAL) {
 		ipoib_warn(priv, "can't use GFP_NOIO for QPs on device %s, using GFP_KERNEL\n",
@@ -1170,7 +1167,7 @@ err_tx:
 static void ipoib_cm_tx_destroy(struct ipoib_cm_tx *p)
 {
 	struct ipoib_dev_priv *priv = netdev_priv(p->dev);
-	struct ipoib_cm_tx_buf *tx_req;
+	struct ipoib_tx_buf *tx_req;
 	unsigned long begin;
 
 	ipoib_dbg(priv, "Destroy active connection 0x%x head 0x%x tail 0x%x\n",
@@ -1197,8 +1194,7 @@ timeout:
 
 	while ((int) p->tx_tail - (int) p->tx_head < 0) {
 		tx_req = &p->tx_ring[p->tx_tail & (ipoib_sendq_size - 1)];
-		ib_dma_unmap_single(priv->ca, tx_req->mapping, tx_req->skb->len,
-				    DMA_TO_DEVICE);
+		ipoib_dma_unmap_tx(priv, tx_req);
 		dev_kfree_skb_any(tx_req->skb);
 		++p->tx_tail;
 		netif_tx_lock_bh(p->dev);
@@ -1455,7 +1451,6 @@ static void ipoib_cm_stale_task(struct work_struct *work)
 	spin_unlock_irq(&priv->lock);
 }
 
-
 static ssize_t show_mode(struct device *d, struct device_attribute *attr,
 			 char *buf)
 {

drivers/infiniband/ulp/ipoib/ipoib_ib.c

@@ -263,8 +263,7 @@ repost:
 			   "for buf %d\n", wr_id);
 }
 
-static int ipoib_dma_map_tx(struct ib_device *ca,
-			    struct ipoib_tx_buf *tx_req)
+int ipoib_dma_map_tx(struct ib_device *ca, struct ipoib_tx_buf *tx_req)
 {
 	struct sk_buff *skb = tx_req->skb;
 	u64 *mapping = tx_req->mapping;
@@ -305,8 +304,8 @@ partial_error:
 	return -EIO;
 }
 
-static void ipoib_dma_unmap_tx(struct ib_device *ca,
-			       struct ipoib_tx_buf *tx_req)
+void ipoib_dma_unmap_tx(struct ipoib_dev_priv *priv,
+			struct ipoib_tx_buf *tx_req)
 {
 	struct sk_buff *skb = tx_req->skb;
 	u64 *mapping = tx_req->mapping;
@@ -314,7 +313,8 @@ static void ipoib_dma_unmap_tx(struct ib_device *ca,
 	int off;
 
 	if (skb_headlen(skb)) {
-		ib_dma_unmap_single(ca, mapping[0], skb_headlen(skb), DMA_TO_DEVICE);
+		ib_dma_unmap_single(priv->ca, mapping[0], skb_headlen(skb),
+				    DMA_TO_DEVICE);
 		off = 1;
 	} else
 		off = 0;
@@ -322,8 +322,8 @@ static void ipoib_dma_unmap_tx(struct ib_device *ca,
 	for (i = 0; i < skb_shinfo(skb)->nr_frags; ++i) {
 		const skb_frag_t *frag = &skb_shinfo(skb)->frags[i];
 
-		ib_dma_unmap_page(ca, mapping[i + off], skb_frag_size(frag),
-				  DMA_TO_DEVICE);
+		ib_dma_unmap_page(priv->ca, mapping[i + off],
+				  skb_frag_size(frag), DMA_TO_DEVICE);
 	}
 }
 
@@ -389,7 +389,7 @@ static void ipoib_ib_handle_tx_wc(struct net_device *dev, struct ib_wc *wc)
 
 	tx_req = &priv->tx_ring[wr_id];
 
-	ipoib_dma_unmap_tx(priv->ca, tx_req);
+	ipoib_dma_unmap_tx(priv, tx_req);
 
 	++dev->stats.tx_packets;
 	dev->stats.tx_bytes += tx_req->skb->len;
@@ -514,24 +514,10 @@ static inline int post_send(struct ipoib_dev_priv *priv,
 			    void *head, int hlen)
 {
 	struct ib_send_wr *bad_wr;
-	int i, off;
 	struct sk_buff *skb = tx_req->skb;
-	skb_frag_t *frags = skb_shinfo(skb)->frags;
-	int nr_frags = skb_shinfo(skb)->nr_frags;
-	u64 *mapping = tx_req->mapping;
 
-	if (skb_headlen(skb)) {
-		priv->tx_sge[0].addr         = mapping[0];
-		priv->tx_sge[0].length       = skb_headlen(skb);
-		off = 1;
-	} else
-		off = 0;
+	ipoib_build_sge(priv, tx_req);
 
-	for (i = 0; i < nr_frags; ++i) {
-		priv->tx_sge[i + off].addr = mapping[i + off];
-		priv->tx_sge[i + off].length = skb_frag_size(&frags[i]);
-	}
-	priv->tx_wr.num_sge	     = nr_frags + off;
 	priv->tx_wr.wr_id 	     = wr_id;
 	priv->tx_wr.wr.ud.remote_qpn = qpn;
 	priv->tx_wr.wr.ud.ah 	     = address;
@@ -617,7 +603,7 @@ void ipoib_send(struct net_device *dev, struct sk_buff *skb,
 		ipoib_warn(priv, "post_send failed, error %d\n", rc);
 		++dev->stats.tx_errors;
 		--priv->tx_outstanding;
-		ipoib_dma_unmap_tx(priv->ca, tx_req);
+		ipoib_dma_unmap_tx(priv, tx_req);
 		dev_kfree_skb_any(skb);
 		if (netif_queue_stopped(dev))
 			netif_wake_queue(dev);
@@ -868,7 +854,7 @@ int ipoib_ib_dev_stop(struct net_device *dev)
 			while ((int) priv->tx_tail - (int) priv->tx_head < 0) {
 				tx_req = &priv->tx_ring[priv->tx_tail &
 							(ipoib_sendq_size - 1)];
-				ipoib_dma_unmap_tx(priv->ca, tx_req);
+				ipoib_dma_unmap_tx(priv, tx_req);
 				dev_kfree_skb_any(tx_req->skb);
 				++priv->tx_tail;
 				--priv->tx_outstanding;
@@ -985,20 +971,21 @@ static inline int update_child_pkey(struct ipoib_dev_priv *priv)
 }
 
 static void __ipoib_ib_dev_flush(struct ipoib_dev_priv *priv,
-				enum ipoib_flush_level level)
+				enum ipoib_flush_level level,
+				int nesting)
 {
 	struct ipoib_dev_priv *cpriv;
 	struct net_device *dev = priv->dev;
 	int result;
 
-	down_read(&priv->vlan_rwsem);
+	down_read_nested(&priv->vlan_rwsem, nesting);
 
 	/*
 	 * Flush any child interfaces too -- they might be up even if
 	 * the parent is down.
 	 */
 	list_for_each_entry(cpriv, &priv->child_intfs, list)
-		__ipoib_ib_dev_flush(cpriv, level);
+		__ipoib_ib_dev_flush(cpriv, level, nesting + 1);
 
 	up_read(&priv->vlan_rwsem);
 
@@ -1076,7 +1063,7 @@ void ipoib_ib_dev_flush_light(struct work_struct *work)
 	struct ipoib_dev_priv *priv =
 		container_of(work, struct ipoib_dev_priv, flush_light);
 
-	__ipoib_ib_dev_flush(priv, IPOIB_FLUSH_LIGHT);
+	__ipoib_ib_dev_flush(priv, IPOIB_FLUSH_LIGHT, 0);
 }
 
 void ipoib_ib_dev_flush_normal(struct work_struct *work)
@@ -1084,7 +1071,7 @@ void ipoib_ib_dev_flush_normal(struct work_struct *work)
 	struct ipoib_dev_priv *priv =
 		container_of(work, struct ipoib_dev_priv, flush_normal);
 
-	__ipoib_ib_dev_flush(priv, IPOIB_FLUSH_NORMAL);
+	__ipoib_ib_dev_flush(priv, IPOIB_FLUSH_NORMAL, 0);
 }
 
 void ipoib_ib_dev_flush_heavy(struct work_struct *work)
@@ -1092,7 +1079,7 @@ void ipoib_ib_dev_flush_heavy(struct work_struct *work)
 	struct ipoib_dev_priv *priv =
 		container_of(work, struct ipoib_dev_priv, flush_heavy);
 
-	__ipoib_ib_dev_flush(priv, IPOIB_FLUSH_HEAVY);
+	__ipoib_ib_dev_flush(priv, IPOIB_FLUSH_HEAVY, 0);
 }
 
 void ipoib_ib_dev_cleanup(struct net_device *dev)

drivers/infiniband/ulp/ipoib/ipoib_main.c

@@ -190,7 +190,7 @@ static netdev_features_t ipoib_fix_features(struct net_device *dev, netdev_featu
 	struct ipoib_dev_priv *priv = netdev_priv(dev);
 
 	if (test_bit(IPOIB_FLAG_ADMIN_CM, &priv->flags))
-		features &= ~(NETIF_F_SG | NETIF_F_IP_CSUM | NETIF_F_TSO);
+		features &= ~(NETIF_F_IP_CSUM | NETIF_F_TSO);
 
 	return features;
 }
@@ -232,6 +232,7 @@ int ipoib_set_mode(struct net_device *dev, const char *buf)
 		ipoib_warn(priv, "enabling connected mode "
 			   "will cause multicast packet drops\n");
 		netdev_update_features(dev);
+		dev_set_mtu(dev, ipoib_cm_max_mtu(dev));
 		rtnl_unlock();
 		priv->tx_wr.send_flags &= ~IB_SEND_IP_CSUM;
 
@@ -1577,7 +1578,8 @@ static struct net_device *ipoib_add_port(const char *format,
 	SET_NETDEV_DEV(priv->dev, hca->dma_device);
 	priv->dev->dev_id = port - 1;
 
-	if (!ib_query_port(hca, port, &attr))
+	result = ib_query_port(hca, port, &attr);
+	if (!result)
 		priv->max_ib_mtu = ib_mtu_enum_to_int(attr.max_mtu);
 	else {
 		printk(KERN_WARNING "%s: ib_query_port %d failed\n",
@@ -1598,7 +1600,8 @@ static struct net_device *ipoib_add_port(const char *format,
 		goto device_init_failed;
 	}
 
-	if (ipoib_set_dev_features(priv, hca))
+	result = ipoib_set_dev_features(priv, hca);
+	if (result)
 		goto device_init_failed;
 
 	/*
@@ -1684,7 +1687,7 @@ static void ipoib_add_one(struct ib_device *device)
 	struct list_head *dev_list;
 	struct net_device *dev;
 	struct ipoib_dev_priv *priv;
-	int s, e, p;
+	int p;
 	int count = 0;
 
 	dev_list = kmalloc(sizeof *dev_list, GFP_KERNEL);
@@ -1693,15 +1696,7 @@ static void ipoib_add_one(struct ib_device *device)
 
 	INIT_LIST_HEAD(dev_list);
 
-	if (device->node_type == RDMA_NODE_IB_SWITCH) {
-		s = 0;
-		e = 0;
-	} else {
-		s = 1;
-		e = device->phys_port_cnt;
-	}
-
-	for (p = s; p <= e; ++p) {
+	for (p = rdma_start_port(device); p <= rdma_end_port(device); ++p) {
 		if (!rdma_protocol_ib(device, p))
 			continue;
 		dev = ipoib_add_port("ib%d", device, p);

drivers/infiniband/ulp/srp/ib_srp.c

@@ -161,13 +161,10 @@ static int srp_tmo_set(const char *val, const struct kernel_param *kp)
 {
 	int tmo, res;
 
-	if (strncmp(val, "off", 3) != 0) {
-		res = kstrtoint(val, 0, &tmo);
-		if (res)
-			goto out;
-	} else {
-		tmo = -1;
-	}
+	res = srp_parse_tmo(&tmo, val);
+	if (res)
+		goto out;
+
 	if (kp->arg == &srp_reconnect_delay)
 		res = srp_tmo_valid(tmo, srp_fast_io_fail_tmo,
 				    srp_dev_loss_tmo);
@@ -3379,7 +3376,7 @@ static void srp_add_one(struct ib_device *device)
 	struct srp_device *srp_dev;
 	struct ib_device_attr *dev_attr;
 	struct srp_host *host;
-	int mr_page_shift, s, e, p;
+	int mr_page_shift, p;
 	u64 max_pages_per_mr;
 
 	dev_attr = kmalloc(sizeof *dev_attr, GFP_KERNEL);
@@ -3443,15 +3440,7 @@ static void srp_add_one(struct ib_device *device)
 	if (IS_ERR(srp_dev->mr))
 		goto err_pd;
 
-	if (device->node_type == RDMA_NODE_IB_SWITCH) {
-		s = 0;
-		e = 0;
-	} else {
-		s = 1;
-		e = device->phys_port_cnt;
-	}
-
-	for (p = s; p <= e; ++p) {
+	for (p = rdma_start_port(device); p <= rdma_end_port(device); ++p) {
 		host = srp_add_port(srp_dev, p);
 		if (host)
 			list_add_tail(&host->list, &srp_dev->dev_list);