Merge tag 'for-hubcap-v4.9-readahead' of git://github.com/martinbrandenburg/linux

orangefs: integrate readahead cache changes from out-of-tree

The readahead cache has long been present as a compile time option to
OrangeFS. As it had not been tested in some time, it was disabled by
default. Recently, Walt Ligon started work reviving it, which eventually
culminated in the commit below to OrangeFS SVN.

r12519 | walt | 2016-07-13 14:32:42 -0400 (Wed, 13 Jul 2016) | 1 line
reintegrating readahead cache code

This cache is implemented almost entirely in userspace. There are a few
parameters exposed via sysfs, and the cache must be flushed after an
inode is released.

25 files changed, 756 insertions, 672 deletions

diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h
index 54643d1f5af4..24563970ff7b 100644
--- a/include/asm-generic/vmlinux.lds.h
+++ b/include/asm-generic/vmlinux.lds.h
@@ -164,7 +164,7 @@
 
 #define ___OF_TABLE(cfg, name)	_OF_TABLE_##cfg(name)
 #define __OF_TABLE(cfg, name)	___OF_TABLE(cfg, name)
-#define OF_TABLE(cfg, name)	__OF_TABLE(config_enabled(cfg), name)
+#define OF_TABLE(cfg, name)	__OF_TABLE(IS_ENABLED(cfg), name)
 #define _OF_TABLE_0(name)
 #define _OF_TABLE_1(name)						\
 	. = ALIGN(8);							\
diff --git a/include/drm/drm_dp_helper.h b/include/drm/drm_dp_helper.h
index 72dee1213268..63b8bd502444 100644
--- a/include/drm/drm_dp_helper.h
+++ b/include/drm/drm_dp_helper.h
@@ -657,6 +657,8 @@ struct edp_vsc_psr {
 #define EDP_VSC_PSR_UPDATE_RFB		(1<<1)
 #define EDP_VSC_PSR_CRC_VALUES_VALID	(1<<2)
 
+int drm_dp_psr_setup_time(const u8 psr_cap[EDP_PSR_RECEIVER_CAP_SIZE]);
+
 static inline int
 drm_dp_max_link_rate(const u8 dpcd[DP_RECEIVER_CAP_SIZE])
 {
diff --git a/include/kvm/arm_vgic.h b/include/kvm/arm_vgic.h
index da0a524802cb..540da5149ba7 100644
--- a/include/kvm/arm_vgic.h
+++ b/include/kvm/arm_vgic.h
@@ -1,6 +1,5 @@
 /*
- * Copyright (C) 2012 ARM Ltd.
- * Author: Marc Zyngier <marc.zyngier@arm.com>
+ * Copyright (C) 2015, 2016 ARM Ltd.
  *
  * 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
@@ -12,16 +11,10 @@
  * GNU General Public License for more details.
  *
  * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
  */
-
-#ifndef __ASM_ARM_KVM_VGIC_H
-#define __ASM_ARM_KVM_VGIC_H
-
-#ifdef CONFIG_KVM_NEW_VGIC
-#include <kvm/vgic/vgic.h>
-#else
+#ifndef __KVM_ARM_VGIC_H
+#define __KVM_ARM_VGIC_H
 
 #include <linux/kernel.h>
 #include <linux/kvm.h>
@@ -29,248 +22,187 @@
 #include <linux/spinlock.h>
 #include <linux/types.h>
 #include <kvm/iodev.h>
-#include <linux/irqchip/arm-gic-common.h>
+#include <linux/list.h>
 
-#define VGIC_NR_IRQS_LEGACY	256
+#define VGIC_V3_MAX_CPUS	255
+#define VGIC_V2_MAX_CPUS	8
+#define VGIC_NR_IRQS_LEGACY     256
 #define VGIC_NR_SGIS		16
 #define VGIC_NR_PPIS		16
 #define VGIC_NR_PRIVATE_IRQS	(VGIC_NR_SGIS + VGIC_NR_PPIS)
+#define VGIC_MAX_PRIVATE	(VGIC_NR_PRIVATE_IRQS - 1)
+#define VGIC_MAX_SPI		1019
+#define VGIC_MAX_RESERVED	1023
+#define VGIC_MIN_LPI		8192
 
-#define VGIC_V2_MAX_LRS		(1 << 6)
-#define VGIC_V3_MAX_LRS		16
-#define VGIC_MAX_IRQS		1024
-#define VGIC_V2_MAX_CPUS	8
-#define VGIC_V3_MAX_CPUS	255
+enum vgic_type {
+	VGIC_V2,		/* Good ol' GICv2 */
+	VGIC_V3,		/* New fancy GICv3 */
+};
 
-#if (VGIC_NR_IRQS_LEGACY & 31)
-#error "VGIC_NR_IRQS must be a multiple of 32"
-#endif
+/* same for all guests, as depending only on the _host's_ GIC model */
+struct vgic_global {
+	/* type of the host GIC */
+	enum vgic_type		type;
 
-#if (VGIC_NR_IRQS_LEGACY > VGIC_MAX_IRQS)
-#error "VGIC_NR_IRQS must be <= 1024"
-#endif
+	/* Physical address of vgic virtual cpu interface */
+	phys_addr_t		vcpu_base;
 
-/*
- * The GIC distributor registers describing interrupts have two parts:
- * - 32 per-CPU interrupts (SGI + PPI)
- * - a bunch of shared interrupts (SPI)
- */
-struct vgic_bitmap {
-	/*
-	 * - One UL per VCPU for private interrupts (assumes UL is at
-	 *   least 32 bits)
-	 * - As many UL as necessary for shared interrupts.
-	 *
-	 * The private interrupts are accessed via the "private"
-	 * field, one UL per vcpu (the state for vcpu n is in
-	 * private[n]). The shared interrupts are accessed via the
-	 * "shared" pointer (IRQn state is at bit n-32 in the bitmap).
-	 */
-	unsigned long *private;
-	unsigned long *shared;
-};
+	/* virtual control interface mapping */
+	void __iomem		*vctrl_base;
 
-struct vgic_bytemap {
-	/*
-	 * - 8 u32 per VCPU for private interrupts
-	 * - As many u32 as necessary for shared interrupts.
-	 *
-	 * The private interrupts are accessed via the "private"
-	 * field, (the state for vcpu n is in private[n*8] to
-	 * private[n*8 + 7]). The shared interrupts are accessed via
-	 * the "shared" pointer (IRQn state is at byte (n-32)%4 of the
-	 * shared[(n-32)/4] word).
-	 */
-	u32 *private;
-	u32 *shared;
-};
+	/* Number of implemented list registers */
+	int			nr_lr;
 
-struct kvm_vcpu;
+	/* Maintenance IRQ number */
+	unsigned int		maint_irq;
 
-enum vgic_type {
-	VGIC_V2,		/* Good ol' GICv2 */
-	VGIC_V3,		/* New fancy GICv3 */
+	/* maximum number of VCPUs allowed (GICv2 limits us to 8) */
+	int			max_gic_vcpus;
+
+	/* Only needed for the legacy KVM_CREATE_IRQCHIP */
+	bool			can_emulate_gicv2;
 };
 
-#define LR_STATE_PENDING	(1 << 0)
-#define LR_STATE_ACTIVE		(1 << 1)
-#define LR_STATE_MASK		(3 << 0)
-#define LR_EOI_INT		(1 << 2)
-#define LR_HW			(1 << 3)
+extern struct vgic_global kvm_vgic_global_state;
 
-struct vgic_lr {
-	unsigned irq:10;
-	union {
-		unsigned hwirq:10;
-		unsigned source:3;
-	};
-	unsigned state:4;
-};
+#define VGIC_V2_MAX_LRS		(1 << 6)
+#define VGIC_V3_MAX_LRS		16
+#define VGIC_V3_LR_INDEX(lr)	(VGIC_V3_MAX_LRS - 1 - lr)
 
-struct vgic_vmcr {
-	u32	ctlr;
-	u32	abpr;
-	u32	bpr;
-	u32	pmr;
+enum vgic_irq_config {
+	VGIC_CONFIG_EDGE = 0,
+	VGIC_CONFIG_LEVEL
 };
 
-struct vgic_ops {
-	struct vgic_lr	(*get_lr)(const struct kvm_vcpu *, int);
-	void	(*set_lr)(struct kvm_vcpu *, int, struct vgic_lr);
-	u64	(*get_elrsr)(const struct kvm_vcpu *vcpu);
-	u64	(*get_eisr)(const struct kvm_vcpu *vcpu);
-	void	(*clear_eisr)(struct kvm_vcpu *vcpu);
-	u32	(*get_interrupt_status)(const struct kvm_vcpu *vcpu);
-	void	(*enable_underflow)(struct kvm_vcpu *vcpu);
-	void	(*disable_underflow)(struct kvm_vcpu *vcpu);
-	void	(*get_vmcr)(struct kvm_vcpu *vcpu, struct vgic_vmcr *vmcr);
-	void	(*set_vmcr)(struct kvm_vcpu *vcpu, struct vgic_vmcr *vmcr);
-	void	(*enable)(struct kvm_vcpu *vcpu);
+struct vgic_irq {
+	spinlock_t irq_lock;		/* Protects the content of the struct */
+	struct list_head lpi_list;	/* Used to link all LPIs together */
+	struct list_head ap_list;
+
+	struct kvm_vcpu *vcpu;		/* SGIs and PPIs: The VCPU
+					 * SPIs and LPIs: The VCPU whose ap_list
+					 * this is queued on.
+					 */
+
+	struct kvm_vcpu *target_vcpu;	/* The VCPU that this interrupt should
+					 * be sent to, as a result of the
+					 * targets reg (v2) or the
+					 * affinity reg (v3).
+					 */
+
+	u32 intid;			/* Guest visible INTID */
+	bool pending;
+	bool line_level;		/* Level only */
+	bool soft_pending;		/* Level only */
+	bool active;			/* not used for LPIs */
+	bool enabled;
+	bool hw;			/* Tied to HW IRQ */
+	struct kref refcount;		/* Used for LPIs */
+	u32 hwintid;			/* HW INTID number */
+	union {
+		u8 targets;			/* GICv2 target VCPUs mask */
+		u32 mpidr;			/* GICv3 target VCPU */
+	};
+	u8 source;			/* GICv2 SGIs only */
+	u8 priority;
+	enum vgic_irq_config config;	/* Level or edge */
 };
 
-struct vgic_params {
-	/* vgic type */
-	enum vgic_type	type;
-	/* Physical address of vgic virtual cpu interface */
-	phys_addr_t	vcpu_base;
-	/* Number of list registers */
-	u32		nr_lr;
-	/* Interrupt number */
-	unsigned int	maint_irq;
-	/* Virtual control interface base address */
-	void __iomem	*vctrl_base;
-	int		max_gic_vcpus;
-	/* Only needed for the legacy KVM_CREATE_IRQCHIP */
-	bool		can_emulate_gicv2;
-};
+struct vgic_register_region;
+struct vgic_its;
 
-struct vgic_vm_ops {
-	bool	(*queue_sgi)(struct kvm_vcpu *, int irq);
-	void	(*add_sgi_source)(struct kvm_vcpu *, int irq, int source);
-	int	(*init_model)(struct kvm *);
-	int	(*map_resources)(struct kvm *, const struct vgic_params *);
+enum iodev_type {
+	IODEV_CPUIF,
+	IODEV_DIST,
+	IODEV_REDIST,
+	IODEV_ITS
 };
 
 struct vgic_io_device {
-	gpa_t addr;
-	int len;
-	const struct vgic_io_range *reg_ranges;
-	struct kvm_vcpu *redist_vcpu;
+	gpa_t base_addr;
+	union {
+		struct kvm_vcpu *redist_vcpu;
+		struct vgic_its *its;
+	};
+	const struct vgic_register_region *regions;
+	enum iodev_type iodev_type;
+	int nr_regions;
 	struct kvm_io_device dev;
 };
 
-struct irq_phys_map {
-	u32			virt_irq;
-	u32			phys_irq;
-};
-
-struct irq_phys_map_entry {
-	struct list_head	entry;
-	struct rcu_head		rcu;
-	struct irq_phys_map	map;
+struct vgic_its {
+	/* The base address of the ITS control register frame */
+	gpa_t			vgic_its_base;
+
+	bool			enabled;
+	bool			initialized;
+	struct vgic_io_device	iodev;
+	struct kvm_device	*dev;
+
+	/* These registers correspond to GITS_BASER{0,1} */
+	u64			baser_device_table;
+	u64			baser_coll_table;
+
+	/* Protects the command queue */
+	struct mutex		cmd_lock;
+	u64			cbaser;
+	u32			creadr;
+	u32			cwriter;
+
+	/* Protects the device and collection lists */
+	struct mutex		its_lock;
+	struct list_head	device_list;
+	struct list_head	collection_list;
 };
 
 struct vgic_dist {
-	spinlock_t		lock;
 	bool			in_kernel;
 	bool			ready;
+	bool			initialized;
 
 	/* vGIC model the kernel emulates for the guest (GICv2 or GICv3) */
 	u32			vgic_model;
 
-	int			nr_cpus;
-	int			nr_irqs;
+	/* Do injected MSIs require an additional device ID? */
+	bool			msis_require_devid;
+
+	int			nr_spis;
 
+	/* TODO: Consider moving to global state */
 	/* Virtual control interface mapping */
 	void __iomem		*vctrl_base;
 
-	/* Distributor and vcpu interface mapping in the guest */
-	phys_addr_t		vgic_dist_base;
-	/* GICv2 and GICv3 use different mapped register blocks */
+	/* base addresses in guest physical address space: */
+	gpa_t			vgic_dist_base;		/* distributor */
 	union {
-		phys_addr_t		vgic_cpu_base;
-		phys_addr_t		vgic_redist_base;
+		/* either a GICv2 CPU interface */
+		gpa_t			vgic_cpu_base;
+		/* or a number of GICv3 redistributor regions */
+		gpa_t			vgic_redist_base;
 	};
 
-	/* Distributor enabled */
-	u32			enabled;
-
-	/* Interrupt enabled (one bit per IRQ) */
-	struct vgic_bitmap	irq_enabled;
-
-	/* Level-triggered interrupt external input is asserted */
-	struct vgic_bitmap	irq_level;
-
-	/*
-	 * Interrupt state is pending on the distributor
-	 */
-	struct vgic_bitmap	irq_pending;
-
-	/*
-	 * Tracks writes to GICD_ISPENDRn and GICD_ICPENDRn for level-triggered
-	 * interrupts.  Essentially holds the state of the flip-flop in
-	 * Figure 4-10 on page 4-101 in ARM IHI 0048B.b.
-	 * Once set, it is only cleared for level-triggered interrupts on
-	 * guest ACKs (when we queue it) or writes to GICD_ICPENDRn.
-	 */
-	struct vgic_bitmap	irq_soft_pend;
-
-	/* Level-triggered interrupt queued on VCPU interface */
-	struct vgic_bitmap	irq_queued;
-
-	/* Interrupt was active when unqueue from VCPU interface */
-	struct vgic_bitmap	irq_active;
-
-	/* Interrupt priority. Not used yet. */
-	struct vgic_bytemap	irq_priority;
+	/* distributor enabled */
+	bool			enabled;
 
-	/* Level/edge triggered */
-	struct vgic_bitmap	irq_cfg;
+	struct vgic_irq		*spis;
 
-	/*
-	 * Source CPU per SGI and target CPU:
-	 *
-	 * Each byte represent a SGI observable on a VCPU, each bit of
-	 * this byte indicating if the corresponding VCPU has
-	 * generated this interrupt. This is a GICv2 feature only.
-	 *
-	 * For VCPUn (n < 8), irq_sgi_sources[n*16] to [n*16 + 15] are
-	 * the SGIs observable on VCPUn.
-	 */
-	u8			*irq_sgi_sources;
+	struct vgic_io_device	dist_iodev;
 
-	/*
-	 * Target CPU for each SPI:
-	 *
-	 * Array of available SPI, each byte indicating the target
-	 * VCPU for SPI. IRQn (n >=32) is at irq_spi_cpu[n-32].
-	 */
-	u8			*irq_spi_cpu;
+	bool			has_its;
 
 	/*
-	 * Reverse lookup of irq_spi_cpu for faster compute pending:
-	 *
-	 * Array of bitmaps, one per VCPU, describing if IRQn is
-	 * routed to a particular VCPU.
+	 * Contains the attributes and gpa of the LPI configuration table.
+	 * Since we report GICR_TYPER.CommonLPIAff as 0b00, we can share
+	 * one address across all redistributors.
+	 * GICv3 spec: 6.1.2 "LPI Configuration tables"
 	 */
-	struct vgic_bitmap	*irq_spi_target;
-
-	/* Target MPIDR for each IRQ (needed for GICv3 IROUTERn) only */
-	u32			*irq_spi_mpidr;
+	u64			propbaser;
 
-	/* Bitmap indicating which CPU has something pending */
-	unsigned long		*irq_pending_on_cpu;
-
-	/* Bitmap indicating which CPU has active IRQs */
-	unsigned long		*irq_active_on_cpu;
-
-	struct vgic_vm_ops	vm_ops;
-	struct vgic_io_device	dist_iodev;
-	struct vgic_io_device	*redist_iodevs;
-
-	/* Virtual irq to hwirq mapping */
-	spinlock_t		irq_phys_map_lock;
-	struct list_head	irq_phys_map_list;
+	/* Protects the lpi_list and the count value below. */
+	spinlock_t		lpi_list_lock;
+	struct list_head	lpi_list_head;
+	int			lpi_list_count;
 };
 
 struct vgic_v2_cpu_if {
@@ -298,78 +230,88 @@ struct vgic_v3_cpu_if {
 };
 
 struct vgic_cpu {
-	/* Pending/active/both interrupts on this VCPU */
-	DECLARE_BITMAP(pending_percpu, VGIC_NR_PRIVATE_IRQS);
-	DECLARE_BITMAP(active_percpu, VGIC_NR_PRIVATE_IRQS);
-	DECLARE_BITMAP(pend_act_percpu, VGIC_NR_PRIVATE_IRQS);
-
-	/* Pending/active/both shared interrupts, dynamically sized */
-	unsigned long	*pending_shared;
-	unsigned long   *active_shared;
-	unsigned long   *pend_act_shared;
-
 	/* CPU vif control registers for world switch */
 	union {
 		struct vgic_v2_cpu_if	vgic_v2;
 		struct vgic_v3_cpu_if	vgic_v3;
 	};
 
-	/* Protected by the distributor's irq_phys_map_lock */
-	struct list_head	irq_phys_map_list;
+	unsigned int used_lrs;
+	struct vgic_irq private_irqs[VGIC_NR_PRIVATE_IRQS];
 
-	u64		live_lrs;
-};
+	spinlock_t ap_list_lock;	/* Protects the ap_list */
+
+	/*
+	 * List of IRQs that this VCPU should consider because they are either
+	 * Active or Pending (hence the name; AP list), or because they recently
+	 * were one of the two and need to be migrated off this list to another
+	 * VCPU.
+	 */
+	struct list_head ap_list_head;
 
-#define LR_EMPTY	0xff
+	u64 live_lrs;
 
-#define INT_STATUS_EOI		(1 << 0)
-#define INT_STATUS_UNDERFLOW	(1 << 1)
+	/*
+	 * Members below are used with GICv3 emulation only and represent
+	 * parts of the redistributor.
+	 */
+	struct vgic_io_device	rd_iodev;
+	struct vgic_io_device	sgi_iodev;
 
-struct kvm;
-struct kvm_vcpu;
+	/* Contains the attributes and gpa of the LPI pending tables. */
+	u64 pendbaser;
+
+	bool lpis_enabled;
+};
 
 int kvm_vgic_addr(struct kvm *kvm, unsigned long type, u64 *addr, bool write);
-int kvm_vgic_hyp_init(void);
-int kvm_vgic_map_resources(struct kvm *kvm);
-int kvm_vgic_get_max_vcpus(void);
 void kvm_vgic_early_init(struct kvm *kvm);
 int kvm_vgic_create(struct kvm *kvm, u32 type);
 void kvm_vgic_destroy(struct kvm *kvm);
 void kvm_vgic_vcpu_early_init(struct kvm_vcpu *vcpu);
 void kvm_vgic_vcpu_destroy(struct kvm_vcpu *vcpu);
-void kvm_vgic_flush_hwstate(struct kvm_vcpu *vcpu);
-void kvm_vgic_sync_hwstate(struct kvm_vcpu *vcpu);
-int kvm_vgic_inject_irq(struct kvm *kvm, int cpuid, unsigned int irq_num,
+int kvm_vgic_map_resources(struct kvm *kvm);
+int kvm_vgic_hyp_init(void);
+
+int kvm_vgic_inject_irq(struct kvm *kvm, int cpuid, unsigned int intid,
 			bool level);
-int kvm_vgic_inject_mapped_irq(struct kvm *kvm, int cpuid,
-			       unsigned int virt_irq, bool level);
-void vgic_v3_dispatch_sgi(struct kvm_vcpu *vcpu, u64 reg);
-int kvm_vgic_vcpu_pending_irq(struct kvm_vcpu *vcpu);
-int kvm_vgic_map_phys_irq(struct kvm_vcpu *vcpu, int virt_irq, int phys_irq);
+int kvm_vgic_inject_mapped_irq(struct kvm *kvm, int cpuid, unsigned int intid,
+			       bool level);
+int kvm_vgic_map_phys_irq(struct kvm_vcpu *vcpu, u32 virt_irq, u32 phys_irq);
 int kvm_vgic_unmap_phys_irq(struct kvm_vcpu *vcpu, unsigned int virt_irq);
 bool kvm_vgic_map_is_active(struct kvm_vcpu *vcpu, unsigned int virt_irq);
 
+int kvm_vgic_vcpu_pending_irq(struct kvm_vcpu *vcpu);
+
 #define irqchip_in_kernel(k)	(!!((k)->arch.vgic.in_kernel))
-#define vgic_initialized(k)	(!!((k)->arch.vgic.nr_cpus))
+#define vgic_initialized(k)	((k)->arch.vgic.initialized)
 #define vgic_ready(k)		((k)->arch.vgic.ready)
 #define vgic_valid_spi(k, i)	(((i) >= VGIC_NR_PRIVATE_IRQS) && \
-				 ((i) < (k)->arch.vgic.nr_irqs))
+			((i) < (k)->arch.vgic.nr_spis + VGIC_NR_PRIVATE_IRQS))
+
+bool kvm_vcpu_has_pending_irqs(struct kvm_vcpu *vcpu);
+void kvm_vgic_sync_hwstate(struct kvm_vcpu *vcpu);
+void kvm_vgic_flush_hwstate(struct kvm_vcpu *vcpu);
 
-int vgic_v2_probe(const struct gic_kvm_info *gic_kvm_info,
-		  const struct vgic_ops **ops,
-		  const struct vgic_params **params);
 #ifdef CONFIG_KVM_ARM_VGIC_V3
-int vgic_v3_probe(const struct gic_kvm_info *gic_kvm_info,
-		  const struct vgic_ops **ops,
-		  const struct vgic_params **params);
+void vgic_v3_dispatch_sgi(struct kvm_vcpu *vcpu, u64 reg);
 #else
-static inline int vgic_v3_probe(const struct gic_kvm_info *gic_kvm_info,
-				const struct vgic_ops **ops,
-				const struct vgic_params **params)
+static inline void vgic_v3_dispatch_sgi(struct kvm_vcpu *vcpu, u64 reg)
 {
-	return -ENODEV;
 }
 #endif
 
-#endif	/* old VGIC include */
-#endif
+/**
+ * kvm_vgic_get_max_vcpus - Get the maximum number of VCPUs allowed by HW
+ *
+ * The host's GIC naturally limits the maximum amount of VCPUs a guest
+ * can use.
+ */
+static inline int kvm_vgic_get_max_vcpus(void)
+{
+	return kvm_vgic_global_state.max_gic_vcpus;
+}
+
+int kvm_send_userspace_msi(struct kvm *kvm, struct kvm_msi *msi);
+
+#endif /* __KVM_ARM_VGIC_H */
diff --git a/include/kvm/vgic/vgic.h b/include/kvm/vgic/vgic.h
deleted file mode 100644
index 3fbd175265ae..000000000000
--- a/include/kvm/vgic/vgic.h
+++ /dev/null
@@ -1,246 +0,0 @@
-/*
- * Copyright (C) 2015, 2016 ARM Ltd.
- *
- * 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.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program.  If not, see <http://www.gnu.org/licenses/>.
- */
-#ifndef __ASM_ARM_KVM_VGIC_VGIC_H
-#define __ASM_ARM_KVM_VGIC_VGIC_H
-
-#include <linux/kernel.h>
-#include <linux/kvm.h>
-#include <linux/irqreturn.h>
-#include <linux/spinlock.h>
-#include <linux/types.h>
-#include <kvm/iodev.h>
-
-#define VGIC_V3_MAX_CPUS	255
-#define VGIC_V2_MAX_CPUS	8
-#define VGIC_NR_IRQS_LEGACY     256
-#define VGIC_NR_SGIS		16
-#define VGIC_NR_PPIS		16
-#define VGIC_NR_PRIVATE_IRQS	(VGIC_NR_SGIS + VGIC_NR_PPIS)
-#define VGIC_MAX_PRIVATE	(VGIC_NR_PRIVATE_IRQS - 1)
-#define VGIC_MAX_SPI		1019
-#define VGIC_MAX_RESERVED	1023
-#define VGIC_MIN_LPI		8192
-
-enum vgic_type {
-	VGIC_V2,		/* Good ol' GICv2 */
-	VGIC_V3,		/* New fancy GICv3 */
-};
-
-/* same for all guests, as depending only on the _host's_ GIC model */
-struct vgic_global {
-	/* type of the host GIC */
-	enum vgic_type		type;
-
-	/* Physical address of vgic virtual cpu interface */
-	phys_addr_t		vcpu_base;
-
-	/* virtual control interface mapping */
-	void __iomem		*vctrl_base;
-
-	/* Number of implemented list registers */
-	int			nr_lr;
-
-	/* Maintenance IRQ number */
-	unsigned int		maint_irq;
-
-	/* maximum number of VCPUs allowed (GICv2 limits us to 8) */
-	int			max_gic_vcpus;
-
-	/* Only needed for the legacy KVM_CREATE_IRQCHIP */
-	bool			can_emulate_gicv2;
-};
-
-extern struct vgic_global kvm_vgic_global_state;
-
-#define VGIC_V2_MAX_LRS		(1 << 6)
-#define VGIC_V3_MAX_LRS		16
-#define VGIC_V3_LR_INDEX(lr)	(VGIC_V3_MAX_LRS - 1 - lr)
-
-enum vgic_irq_config {
-	VGIC_CONFIG_EDGE = 0,
-	VGIC_CONFIG_LEVEL
-};
-
-struct vgic_irq {
-	spinlock_t irq_lock;		/* Protects the content of the struct */
-	struct list_head ap_list;
-
-	struct kvm_vcpu *vcpu;		/* SGIs and PPIs: The VCPU
-					 * SPIs and LPIs: The VCPU whose ap_list
-					 * this is queued on.
-					 */
-
-	struct kvm_vcpu *target_vcpu;	/* The VCPU that this interrupt should
-					 * be sent to, as a result of the
-					 * targets reg (v2) or the
-					 * affinity reg (v3).
-					 */
-
-	u32 intid;			/* Guest visible INTID */
-	bool pending;
-	bool line_level;		/* Level only */
-	bool soft_pending;		/* Level only */
-	bool active;			/* not used for LPIs */
-	bool enabled;
-	bool hw;			/* Tied to HW IRQ */
-	u32 hwintid;			/* HW INTID number */
-	union {
-		u8 targets;			/* GICv2 target VCPUs mask */
-		u32 mpidr;			/* GICv3 target VCPU */
-	};
-	u8 source;			/* GICv2 SGIs only */
-	u8 priority;
-	enum vgic_irq_config config;	/* Level or edge */
-};
-
-struct vgic_register_region;
-
-struct vgic_io_device {
-	gpa_t base_addr;
-	struct kvm_vcpu *redist_vcpu;
-	const struct vgic_register_region *regions;
-	int nr_regions;
-	struct kvm_io_device dev;
-};
-
-struct vgic_dist {
-	bool			in_kernel;
-	bool			ready;
-	bool			initialized;
-
-	/* vGIC model the kernel emulates for the guest (GICv2 or GICv3) */
-	u32			vgic_model;
-
-	int			nr_spis;
-
-	/* TODO: Consider moving to global state */
-	/* Virtual control interface mapping */
-	void __iomem		*vctrl_base;
-
-	/* base addresses in guest physical address space: */
-	gpa_t			vgic_dist_base;		/* distributor */
-	union {
-		/* either a GICv2 CPU interface */
-		gpa_t			vgic_cpu_base;
-		/* or a number of GICv3 redistributor regions */
-		gpa_t			vgic_redist_base;
-	};
-
-	/* distributor enabled */
-	bool			enabled;
-
-	struct vgic_irq		*spis;
-
-	struct vgic_io_device	dist_iodev;
-	struct vgic_io_device	*redist_iodevs;
-};
-
-struct vgic_v2_cpu_if {
-	u32		vgic_hcr;
-	u32		vgic_vmcr;
-	u32		vgic_misr;	/* Saved only */
-	u64		vgic_eisr;	/* Saved only */
-	u64		vgic_elrsr;	/* Saved only */
-	u32		vgic_apr;
-	u32		vgic_lr[VGIC_V2_MAX_LRS];
-};
-
-struct vgic_v3_cpu_if {
-#ifdef CONFIG_KVM_ARM_VGIC_V3
-	u32		vgic_hcr;
-	u32		vgic_vmcr;
-	u32		vgic_sre;	/* Restored only, change ignored */
-	u32		vgic_misr;	/* Saved only */
-	u32		vgic_eisr;	/* Saved only */
-	u32		vgic_elrsr;	/* Saved only */
-	u32		vgic_ap0r[4];
-	u32		vgic_ap1r[4];
-	u64		vgic_lr[VGIC_V3_MAX_LRS];
-#endif
-};
-
-struct vgic_cpu {
-	/* CPU vif control registers for world switch */
-	union {
-		struct vgic_v2_cpu_if	vgic_v2;
-		struct vgic_v3_cpu_if	vgic_v3;
-	};
-
-	unsigned int used_lrs;
-	struct vgic_irq private_irqs[VGIC_NR_PRIVATE_IRQS];
-
-	spinlock_t ap_list_lock;	/* Protects the ap_list */
-
-	/*
-	 * List of IRQs that this VCPU should consider because they are either
-	 * Active or Pending (hence the name; AP list), or because they recently
-	 * were one of the two and need to be migrated off this list to another
-	 * VCPU.
-	 */
-	struct list_head ap_list_head;
-
-	u64 live_lrs;
-};
-
-int kvm_vgic_addr(struct kvm *kvm, unsigned long type, u64 *addr, bool write);
-void kvm_vgic_early_init(struct kvm *kvm);
-int kvm_vgic_create(struct kvm *kvm, u32 type);
-void kvm_vgic_destroy(struct kvm *kvm);
-void kvm_vgic_vcpu_early_init(struct kvm_vcpu *vcpu);
-void kvm_vgic_vcpu_destroy(struct kvm_vcpu *vcpu);
-int kvm_vgic_map_resources(struct kvm *kvm);
-int kvm_vgic_hyp_init(void);
-
-int kvm_vgic_inject_irq(struct kvm *kvm, int cpuid, unsigned int intid,
-			bool level);
-int kvm_vgic_inject_mapped_irq(struct kvm *kvm, int cpuid, unsigned int intid,
-			       bool level);
-int kvm_vgic_map_phys_irq(struct kvm_vcpu *vcpu, u32 virt_irq, u32 phys_irq);
-int kvm_vgic_unmap_phys_irq(struct kvm_vcpu *vcpu, unsigned int virt_irq);
-bool kvm_vgic_map_is_active(struct kvm_vcpu *vcpu, unsigned int virt_irq);
-
-int kvm_vgic_vcpu_pending_irq(struct kvm_vcpu *vcpu);
-
-#define irqchip_in_kernel(k)	(!!((k)->arch.vgic.in_kernel))
-#define vgic_initialized(k)	((k)->arch.vgic.initialized)
-#define vgic_ready(k)		((k)->arch.vgic.ready)
-#define vgic_valid_spi(k, i)	(((i) >= VGIC_NR_PRIVATE_IRQS) && \
-			((i) < (k)->arch.vgic.nr_spis + VGIC_NR_PRIVATE_IRQS))
-
-bool kvm_vcpu_has_pending_irqs(struct kvm_vcpu *vcpu);
-void kvm_vgic_sync_hwstate(struct kvm_vcpu *vcpu);
-void kvm_vgic_flush_hwstate(struct kvm_vcpu *vcpu);
-
-#ifdef CONFIG_KVM_ARM_VGIC_V3
-void vgic_v3_dispatch_sgi(struct kvm_vcpu *vcpu, u64 reg);
-#else
-static inline void vgic_v3_dispatch_sgi(struct kvm_vcpu *vcpu, u64 reg)
-{
-}
-#endif
-
-/**
- * kvm_vgic_get_max_vcpus - Get the maximum number of VCPUs allowed by HW
- *
- * The host's GIC naturally limits the maximum amount of VCPUs a guest
- * can use.
- */
-static inline int kvm_vgic_get_max_vcpus(void)
-{
-	return kvm_vgic_global_state.max_gic_vcpus;
-}
-
-#endif /* __ASM_ARM_KVM_VGIC_VGIC_H */
diff --git a/include/linux/ceph/ceph_fs.h b/include/linux/ceph/ceph_fs.h
index dfce616002ad..7868d602c0a0 100644
--- a/include/linux/ceph/ceph_fs.h
+++ b/include/linux/ceph/ceph_fs.h
@@ -34,9 +34,9 @@
 #define CEPH_MAX_MON   31
 
 /*
- * ceph_file_layout - describe data layout for a file/inode
+ * legacy ceph_file_layoute
  */
-struct ceph_file_layout {
+struct ceph_file_layout_legacy {
 	/* file -> object mapping */
 	__le32 fl_stripe_unit;     /* stripe unit, in bytes.  must be multiple
 				      of page size. */
@@ -53,33 +53,27 @@ struct ceph_file_layout {
 	__le32 fl_pg_pool;      /* namespace, crush ruleset, rep level */
 } __attribute__ ((packed));
 
-#define ceph_file_layout_su(l) ((__s32)le32_to_cpu((l).fl_stripe_unit))
-#define ceph_file_layout_stripe_count(l) \
-	((__s32)le32_to_cpu((l).fl_stripe_count))
-#define ceph_file_layout_object_size(l) ((__s32)le32_to_cpu((l).fl_object_size))
-#define ceph_file_layout_cas_hash(l) ((__s32)le32_to_cpu((l).fl_cas_hash))
-#define ceph_file_layout_object_su(l) \
-	((__s32)le32_to_cpu((l).fl_object_stripe_unit))
-#define ceph_file_layout_pg_pool(l) \
-	((__s32)le32_to_cpu((l).fl_pg_pool))
-
-static inline unsigned ceph_file_layout_stripe_width(struct ceph_file_layout *l)
-{
-	return le32_to_cpu(l->fl_stripe_unit) *
-		le32_to_cpu(l->fl_stripe_count);
-}
-
-/* "period" == bytes before i start on a new set of objects */
-static inline unsigned ceph_file_layout_period(struct ceph_file_layout *l)
-{
-	return le32_to_cpu(l->fl_object_size) *
-		le32_to_cpu(l->fl_stripe_count);
-}
+struct ceph_string;
+/*
+ * ceph_file_layout - describe data layout for a file/inode
+ */
+struct ceph_file_layout {
+	/* file -> object mapping */
+	u32 stripe_unit;   /* stripe unit, in bytes */
+	u32 stripe_count;  /* over this many objects */
+	u32 object_size;   /* until objects are this big */
+	s64 pool_id;        /* rados pool id */
+	struct ceph_string __rcu *pool_ns; /* rados pool namespace */
+};
+
+extern int ceph_file_layout_is_valid(const struct ceph_file_layout *layout);
+extern void ceph_file_layout_from_legacy(struct ceph_file_layout *fl,
+				struct ceph_file_layout_legacy *legacy);
+extern void ceph_file_layout_to_legacy(struct ceph_file_layout *fl,
+				struct ceph_file_layout_legacy *legacy);
 
 #define CEPH_MIN_STRIPE_UNIT 65536
 
-int ceph_file_layout_is_valid(const struct ceph_file_layout *layout);
-
 struct ceph_dir_layout {
 	__u8   dl_dir_hash;   /* see ceph_hash.h for ids */
 	__u8   dl_unused1;
@@ -127,6 +121,7 @@ struct ceph_dir_layout {
 
 /* client <-> mds */
 #define CEPH_MSG_MDS_MAP                21
+#define CEPH_MSG_FS_MAP_USER            103
 
 #define CEPH_MSG_CLIENT_SESSION         22
 #define CEPH_MSG_CLIENT_RECONNECT       23
@@ -399,7 +394,7 @@ union ceph_mds_request_args {
 		__le32 flags;
 	} __attribute__ ((packed)) setxattr;
 	struct {
-		struct ceph_file_layout layout;
+		struct ceph_file_layout_legacy layout;
 	} __attribute__ ((packed)) setlayout;
 	struct {
 		__u8 rule; /* currently fcntl or flock */
@@ -478,7 +473,7 @@ struct ceph_mds_reply_inode {
 	__le64 version;                /* inode version */
 	__le64 xattr_version;          /* version for xattr blob */
 	struct ceph_mds_reply_cap cap; /* caps issued for this inode */
-	struct ceph_file_layout layout;
+	struct ceph_file_layout_legacy layout;
 	struct ceph_timespec ctime, mtime, atime;
 	__le32 time_warp_seq;
 	__le64 size, max_size, truncate_size;
@@ -531,7 +526,7 @@ struct ceph_filelock {
 #define CEPH_FILE_MODE_WR         2
 #define CEPH_FILE_MODE_RDWR       3  /* RD | WR */
 #define CEPH_FILE_MODE_LAZY       4  /* lazy io */
-#define CEPH_FILE_MODE_NUM        8  /* bc these are bit fields.. mostly */
+#define CEPH_FILE_MODE_BITS       4
 
 int ceph_flags_to_mode(int flags);
 
@@ -673,7 +668,7 @@ struct ceph_mds_caps {
 	__le64 size, max_size, truncate_size;
 	__le32 truncate_seq;
 	struct ceph_timespec mtime, atime, ctime;
-	struct ceph_file_layout layout;
+	struct ceph_file_layout_legacy layout;
 	__le32 time_warp_seq;
 } __attribute__ ((packed));
 
diff --git a/include/linux/ceph/decode.h b/include/linux/ceph/decode.h
index 19e9932f3e77..f990f2cc907a 100644
--- a/include/linux/ceph/decode.h
+++ b/include/linux/ceph/decode.h
@@ -3,6 +3,7 @@
 
 #include <linux/err.h>
 #include <linux/bug.h>
+#include <linux/slab.h>
 #include <linux/time.h>
 #include <asm/unaligned.h>
 
@@ -217,6 +218,60 @@ static inline void ceph_encode_string(void **p, void *end,
 	*p += len;
 }
 
+/*
+ * version and length starting block encoders/decoders
+ */
+
+/* current code version (u8) + compat code version (u8) + len of struct (u32) */
+#define CEPH_ENCODING_START_BLK_LEN 6
+
+/**
+ * ceph_start_encoding - start encoding block
+ * @struct_v: current (code) version of the encoding
+ * @struct_compat: oldest code version that can decode it
+ * @struct_len: length of struct encoding
+ */
+static inline void ceph_start_encoding(void **p, u8 struct_v, u8 struct_compat,
+				       u32 struct_len)
+{
+	ceph_encode_8(p, struct_v);
+	ceph_encode_8(p, struct_compat);
+	ceph_encode_32(p, struct_len);
+}
+
+/**
+ * ceph_start_decoding - start decoding block
+ * @v: current version of the encoding that the code supports
+ * @name: name of the struct (free-form)
+ * @struct_v: out param for the encoding version
+ * @struct_len: out param for the length of struct encoding
+ *
+ * Validates the length of struct encoding, so unsafe ceph_decode_*
+ * variants can be used for decoding.
+ */
+static inline int ceph_start_decoding(void **p, void *end, u8 v,
+				      const char *name, u8 *struct_v,
+				      u32 *struct_len)
+{
+	u8 struct_compat;
+
+	ceph_decode_need(p, end, CEPH_ENCODING_START_BLK_LEN, bad);
+	*struct_v = ceph_decode_8(p);
+	struct_compat = ceph_decode_8(p);
+	if (v < struct_compat) {
+		pr_warn("got struct_v %d struct_compat %d > %d of %s\n",
+			*struct_v, struct_compat, v, name);
+		return -EINVAL;
+	}
+
+	*struct_len = ceph_decode_32(p);
+	ceph_decode_need(p, end, *struct_len, bad);
+	return 0;
+
+bad:
+	return -ERANGE;
+}
+
 #define ceph_encode_need(p, end, n, bad)			\
 	do {							\
 		if (!likely(ceph_has_room(p, end, n)))		\
diff --git a/include/linux/ceph/libceph.h b/include/linux/ceph/libceph.h
index 690985daad1c..83fc1fff7061 100644
--- a/include/linux/ceph/libceph.h
+++ b/include/linux/ceph/libceph.h
@@ -21,6 +21,7 @@
 #include <linux/ceph/mon_client.h>
 #include <linux/ceph/osd_client.h>
 #include <linux/ceph/ceph_fs.h>
+#include <linux/ceph/string_table.h>
 
 /*
  * mount options
@@ -214,8 +215,9 @@ static void erase_##name(struct rb_root *root, type *t)			\
 }
 
 #define DEFINE_RB_LOOKUP_FUNC(name, type, keyfld, nodefld)		\
+extern type __lookup_##name##_key;					\
 static type *lookup_##name(struct rb_root *root,			\
-			   typeof(((type *)0)->keyfld) key)		\
+			   typeof(__lookup_##name##_key.keyfld) key)	\
 {									\
 	struct rb_node *n = root->rb_node;				\
 									\
diff --git a/include/linux/ceph/mon_client.h b/include/linux/ceph/mon_client.h
index e2a92df08b47..24d704d1ea5c 100644
--- a/include/linux/ceph/mon_client.h
+++ b/include/linux/ceph/mon_client.h
@@ -95,7 +95,7 @@ struct ceph_mon_client {
 		struct ceph_mon_subscribe_item item;
 		bool want;
 		u32 have; /* epoch */
-	} subs[3];
+	} subs[4];
 	int fs_cluster_id; /* "mdsmap.<id>" sub */
 
 #ifdef CONFIG_DEBUG_FS
@@ -111,9 +111,10 @@ extern int ceph_monc_init(struct ceph_mon_client *monc, struct ceph_client *cl);
 extern void ceph_monc_stop(struct ceph_mon_client *monc);
 
 enum {
-	CEPH_SUB_MDSMAP = 0,
-	CEPH_SUB_MONMAP,
+	CEPH_SUB_MONMAP = 0,
 	CEPH_SUB_OSDMAP,
+	CEPH_SUB_FSMAP,
+	CEPH_SUB_MDSMAP,
 };
 
 extern const char *ceph_sub_str[];
diff --git a/include/linux/ceph/msgpool.h b/include/linux/ceph/msgpool.h
index 4b0d38960726..ddd0d48d0384 100644
--- a/include/linux/ceph/msgpool.h
+++ b/include/linux/ceph/msgpool.h
@@ -2,7 +2,6 @@
 #define _FS_CEPH_MSGPOOL
 
 #include <linux/mempool.h>
-#include <linux/ceph/messenger.h>
 
 /*
  * we use memory pools for preallocating messages we may receive, to
diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h
index 1b3b6e155392..858932304260 100644
--- a/include/linux/ceph/osd_client.h
+++ b/include/linux/ceph/osd_client.h
@@ -9,6 +9,7 @@
 #include <linux/ceph/types.h>
 #include <linux/ceph/osdmap.h>
 #include <linux/ceph/messenger.h>
+#include <linux/ceph/msgpool.h>
 #include <linux/ceph/auth.h>
 #include <linux/ceph/pagelist.h>
 
diff --git a/include/linux/ceph/osdmap.h b/include/linux/ceph/osdmap.h
index 9ccf4dbe55f8..9a9041784dcf 100644
--- a/include/linux/ceph/osdmap.h
+++ b/include/linux/ceph/osdmap.h
@@ -63,11 +63,13 @@ static inline bool ceph_can_shift_osds(struct ceph_pg_pool_info *pool)
 
 struct ceph_object_locator {
 	s64 pool;
+	struct ceph_string *pool_ns;
 };
 
 static inline void ceph_oloc_init(struct ceph_object_locator *oloc)
 {
 	oloc->pool = -1;
+	oloc->pool_ns = NULL;
 }
 
 static inline bool ceph_oloc_empty(const struct ceph_object_locator *oloc)
@@ -75,11 +77,9 @@ static inline bool ceph_oloc_empty(const struct ceph_object_locator *oloc)
 	return oloc->pool == -1;
 }
 
-static inline void ceph_oloc_copy(struct ceph_object_locator *dest,
-				  const struct ceph_object_locator *src)
-{
-	dest->pool = src->pool;
-}
+void ceph_oloc_copy(struct ceph_object_locator *dest,
+		    const struct ceph_object_locator *src);
+void ceph_oloc_destroy(struct ceph_object_locator *oloc);
 
 /*
  * Maximum supported by kernel client object name length
@@ -115,6 +115,11 @@ static inline void ceph_oid_init(struct ceph_object_id *oid)
 	oid->name_len = 0;
 }
 
+#define CEPH_OID_INIT_ONSTACK(oid)					\
+    ({ ceph_oid_init(&oid); oid; })
+#define CEPH_DEFINE_OID_ONSTACK(oid)					\
+	struct ceph_object_id oid = CEPH_OID_INIT_ONSTACK(oid)
+
 static inline bool ceph_oid_empty(const struct ceph_object_id *oid)
 {
 	return oid->name == oid->inline_name && !oid->name_len;
diff --git a/include/linux/ceph/string_table.h b/include/linux/ceph/string_table.h
new file mode 100644
index 000000000000..1b02c96daf75
--- /dev/null
+++ b/include/linux/ceph/string_table.h
@@ -0,0 +1,62 @@
+#ifndef _FS_CEPH_STRING_TABLE_H
+#define _FS_CEPH_STRING_TABLE_H
+
+#include <linux/types.h>
+#include <linux/kref.h>
+#include <linux/rbtree.h>
+#include <linux/rcupdate.h>
+
+struct ceph_string {
+	struct kref kref;
+	union {
+		struct rb_node node;
+		struct rcu_head rcu;
+	};
+	size_t len;
+	char str[];
+};
+
+extern void ceph_release_string(struct kref *ref);
+extern struct ceph_string *ceph_find_or_create_string(const char *str,
+						      size_t len);
+extern bool ceph_strings_empty(void);
+
+static inline struct ceph_string *ceph_get_string(struct ceph_string *str)
+{
+	kref_get(&str->kref);
+	return str;
+}
+
+static inline void ceph_put_string(struct ceph_string *str)
+{
+	if (!str)
+		return;
+	kref_put(&str->kref, ceph_release_string);
+}
+
+static inline int ceph_compare_string(struct ceph_string *cs,
+				      const char* str, size_t len)
+{
+	size_t cs_len = cs ? cs->len : 0;
+	if (cs_len != len)
+		return cs_len - len;
+	if (len == 0)
+		return 0;
+	return strncmp(cs->str, str, len);
+}
+
+#define ceph_try_get_string(x)					\
+({								\
+	struct ceph_string *___str;				\
+	rcu_read_lock();					\
+	for (;;) {						\
+		___str = rcu_dereference(x);			\
+		if (!___str ||					\
+		    kref_get_unless_zero(&___str->kref))	\
+			break;					\
+	}							\
+	rcu_read_unlock();					\
+	(___str);						\
+})
+
+#endif
diff --git a/include/linux/context_tracking.h b/include/linux/context_tracking.h
index d9aef2a0ec8e..c78fc27418f2 100644
--- a/include/linux/context_tracking.h
+++ b/include/linux/context_tracking.h
@@ -99,7 +99,8 @@ static inline void context_tracking_init(void) { }
 
 
 #ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN
-static inline void guest_enter(void)
+/* must be called with irqs disabled */
+static inline void guest_enter_irqoff(void)
 {
 	if (vtime_accounting_cpu_enabled())
 		vtime_guest_enter(current);
@@ -108,9 +109,19 @@ static inline void guest_enter(void)
 
 	if (context_tracking_is_enabled())
 		__context_tracking_enter(CONTEXT_GUEST);
+
+	/* KVM does not hold any references to rcu protected data when it
+	 * switches CPU into a guest mode. In fact switching to a guest mode
+	 * is very similar to exiting to userspace from rcu point of view. In
+	 * addition CPU may stay in a guest mode for quite a long time (up to
+	 * one time slice). Lets treat guest mode as quiescent state, just like
+	 * we do with user-mode execution.
+	 */
+	if (!context_tracking_cpu_is_enabled())
+		rcu_virt_note_context_switch(smp_processor_id());
 }
 
-static inline void guest_exit(void)
+static inline void guest_exit_irqoff(void)
 {
 	if (context_tracking_is_enabled())
 		__context_tracking_exit(CONTEXT_GUEST);
@@ -122,7 +133,7 @@ static inline void guest_exit(void)
 }
 
 #else
-static inline void guest_enter(void)
+static inline void guest_enter_irqoff(void)
 {
 	/*
 	 * This is running in ioctl context so its safe
@@ -131,9 +142,10 @@ static inline void guest_enter(void)
 	 */
 	vtime_account_system(current);
 	current->flags |= PF_VCPU;
+	rcu_virt_note_context_switch(smp_processor_id());
 }
 
-static inline void guest_exit(void)
+static inline void guest_exit_irqoff(void)
 {
 	/* Flush the guest cputime we spent on the guest */
 	vtime_account_system(current);
@@ -141,4 +153,22 @@ static inline void guest_exit(void)
 }
 #endif /* CONFIG_VIRT_CPU_ACCOUNTING_GEN */
 
+static inline void guest_enter(void)
+{
+	unsigned long flags;
+
+	local_irq_save(flags);
+	guest_enter_irqoff();
+	local_irq_restore(flags);
+}
+
+static inline void guest_exit(void)
+{
+	unsigned long flags;
+
+	local_irq_save(flags);
+	guest_exit_irqoff();
+	local_irq_restore(flags);
+}
+
 #endif
diff --git a/include/linux/export.h b/include/linux/export.h
index 2f9ccbe6a639..c565f87f005e 100644
--- a/include/linux/export.h
+++ b/include/linux/export.h
@@ -82,7 +82,7 @@ extern struct module __this_module;
 #include <generated/autoksyms.h>
 
 #define __EXPORT_SYMBOL(sym, sec)				\
-	__cond_export_sym(sym, sec, config_enabled(__KSYM_##sym))
+	__cond_export_sym(sym, sec, __is_defined(__KSYM_##sym))
 #define __cond_export_sym(sym, sec, conf)			\
 	___cond_export_sym(sym, sec, conf)
 #define ___cond_export_sym(sym, sec, enabled)			\
diff --git a/include/linux/irqchip/arm-gic-v3.h b/include/linux/irqchip/arm-gic-v3.h
index 107eed475b94..56b0b7ec66aa 100644
--- a/include/linux/irqchip/arm-gic-v3.h
+++ b/include/linux/irqchip/arm-gic-v3.h
@@ -112,34 +112,76 @@
 #define GICR_WAKER_ProcessorSleep	(1U << 1)
 #define GICR_WAKER_ChildrenAsleep	(1U << 2)
 
-#define GICR_PROPBASER_NonShareable	(0U << 10)
-#define GICR_PROPBASER_InnerShareable	(1U << 10)
-#define GICR_PROPBASER_OuterShareable	(2U << 10)
-#define GICR_PROPBASER_SHAREABILITY_MASK (3UL << 10)
-#define GICR_PROPBASER_nCnB		(0U << 7)
-#define GICR_PROPBASER_nC		(1U << 7)
-#define GICR_PROPBASER_RaWt		(2U << 7)
-#define GICR_PROPBASER_RaWb		(3U << 7)
-#define GICR_PROPBASER_WaWt		(4U << 7)
-#define GICR_PROPBASER_WaWb		(5U << 7)
-#define GICR_PROPBASER_RaWaWt		(6U << 7)
-#define GICR_PROPBASER_RaWaWb		(7U << 7)
-#define GICR_PROPBASER_CACHEABILITY_MASK (7U << 7)
-#define GICR_PROPBASER_IDBITS_MASK	(0x1f)
-
-#define GICR_PENDBASER_NonShareable	(0U << 10)
-#define GICR_PENDBASER_InnerShareable	(1U << 10)
-#define GICR_PENDBASER_OuterShareable	(2U << 10)
-#define GICR_PENDBASER_SHAREABILITY_MASK (3UL << 10)
-#define GICR_PENDBASER_nCnB		(0U << 7)
-#define GICR_PENDBASER_nC		(1U << 7)
-#define GICR_PENDBASER_RaWt		(2U << 7)
-#define GICR_PENDBASER_RaWb		(3U << 7)
-#define GICR_PENDBASER_WaWt		(4U << 7)
-#define GICR_PENDBASER_WaWb		(5U << 7)
-#define GICR_PENDBASER_RaWaWt		(6U << 7)
-#define GICR_PENDBASER_RaWaWb		(7U << 7)
-#define GICR_PENDBASER_CACHEABILITY_MASK (7U << 7)
+#define GIC_BASER_CACHE_nCnB		0ULL
+#define GIC_BASER_CACHE_SameAsInner	0ULL
+#define GIC_BASER_CACHE_nC		1ULL
+#define GIC_BASER_CACHE_RaWt		2ULL
+#define GIC_BASER_CACHE_RaWb		3ULL
+#define GIC_BASER_CACHE_WaWt		4ULL
+#define GIC_BASER_CACHE_WaWb		5ULL
+#define GIC_BASER_CACHE_RaWaWt		6ULL
+#define GIC_BASER_CACHE_RaWaWb		7ULL
+#define GIC_BASER_CACHE_MASK		7ULL
+#define GIC_BASER_NonShareable		0ULL
+#define GIC_BASER_InnerShareable	1ULL
+#define GIC_BASER_OuterShareable	2ULL
+#define GIC_BASER_SHAREABILITY_MASK	3ULL
+
+#define GIC_BASER_CACHEABILITY(reg, inner_outer, type)			\
+	(GIC_BASER_CACHE_##type << reg##_##inner_outer##_CACHEABILITY_SHIFT)
+
+#define GIC_BASER_SHAREABILITY(reg, type)				\
+	(GIC_BASER_##type << reg##_SHAREABILITY_SHIFT)
+
+#define GICR_PROPBASER_SHAREABILITY_SHIFT		(10)
+#define GICR_PROPBASER_INNER_CACHEABILITY_SHIFT		(7)
+#define GICR_PROPBASER_OUTER_CACHEABILITY_SHIFT		(56)
+#define GICR_PROPBASER_SHAREABILITY_MASK				\
+	GIC_BASER_SHAREABILITY(GICR_PROPBASER, SHAREABILITY_MASK)
+#define GICR_PROPBASER_INNER_CACHEABILITY_MASK				\
+	GIC_BASER_CACHEABILITY(GICR_PROPBASER, INNER, MASK)
+#define GICR_PROPBASER_OUTER_CACHEABILITY_MASK				\
+	GIC_BASER_CACHEABILITY(GICR_PROPBASER, OUTER, MASK)
+#define GICR_PROPBASER_CACHEABILITY_MASK GICR_PROPBASER_INNER_CACHEABILITY_MASK
+
+#define GICR_PROPBASER_InnerShareable					\
+	GIC_BASER_SHAREABILITY(GICR_PROPBASER, InnerShareable)
+
+#define GICR_PROPBASER_nCnB	GIC_BASER_CACHEABILITY(GICR_PROPBASER, INNER, nCnB)
+#define GICR_PROPBASER_nC 	GIC_BASER_CACHEABILITY(GICR_PROPBASER, INNER, nC)
+#define GICR_PROPBASER_RaWt	GIC_BASER_CACHEABILITY(GICR_PROPBASER, INNER, RaWt)
+#define GICR_PROPBASER_RaWb	GIC_BASER_CACHEABILITY(GICR_PROPBASER, INNER, RaWt)
+#define GICR_PROPBASER_WaWt	GIC_BASER_CACHEABILITY(GICR_PROPBASER, INNER, WaWt)
+#define GICR_PROPBASER_WaWb	GIC_BASER_CACHEABILITY(GICR_PROPBASER, INNER, WaWb)
+#define GICR_PROPBASER_RaWaWt	GIC_BASER_CACHEABILITY(GICR_PROPBASER, INNER, RaWaWt)
+#define GICR_PROPBASER_RaWaWb	GIC_BASER_CACHEABILITY(GICR_PROPBASER, INNER, RaWaWb)
+
+#define GICR_PROPBASER_IDBITS_MASK			(0x1f)
+
+#define GICR_PENDBASER_SHAREABILITY_SHIFT		(10)
+#define GICR_PENDBASER_INNER_CACHEABILITY_SHIFT		(7)
+#define GICR_PENDBASER_OUTER_CACHEABILITY_SHIFT		(56)
+#define GICR_PENDBASER_SHAREABILITY_MASK				\
+	GIC_BASER_SHAREABILITY(GICR_PENDBASER, SHAREABILITY_MASK)
+#define GICR_PENDBASER_INNER_CACHEABILITY_MASK				\
+	GIC_BASER_CACHEABILITY(GICR_PENDBASER, INNER, MASK)
+#define GICR_PENDBASER_OUTER_CACHEABILITY_MASK				\
+	GIC_BASER_CACHEABILITY(GICR_PENDBASER, OUTER, MASK)
+#define GICR_PENDBASER_CACHEABILITY_MASK GICR_PENDBASER_INNER_CACHEABILITY_MASK
+
+#define GICR_PENDBASER_InnerShareable					\
+	GIC_BASER_SHAREABILITY(GICR_PENDBASER, InnerShareable)
+
+#define GICR_PENDBASER_nCnB	GIC_BASER_CACHEABILITY(GICR_PENDBASER, INNER, nCnB)
+#define GICR_PENDBASER_nC 	GIC_BASER_CACHEABILITY(GICR_PENDBASER, INNER, nC)
+#define GICR_PENDBASER_RaWt	GIC_BASER_CACHEABILITY(GICR_PENDBASER, INNER, RaWt)
+#define GICR_PENDBASER_RaWb	GIC_BASER_CACHEABILITY(GICR_PENDBASER, INNER, RaWt)
+#define GICR_PENDBASER_WaWt	GIC_BASER_CACHEABILITY(GICR_PENDBASER, INNER, WaWt)
+#define GICR_PENDBASER_WaWb	GIC_BASER_CACHEABILITY(GICR_PENDBASER, INNER, WaWb)
+#define GICR_PENDBASER_RaWaWt	GIC_BASER_CACHEABILITY(GICR_PENDBASER, INNER, RaWaWt)
+#define GICR_PENDBASER_RaWaWb	GIC_BASER_CACHEABILITY(GICR_PENDBASER, INNER, RaWaWb)
+
+#define GICR_PENDBASER_PTZ				BIT_ULL(62)
 
 /*
  * Re-Distributor registers, offsets from SGI_base
@@ -175,54 +217,83 @@
 #define GITS_CWRITER			0x0088
 #define GITS_CREADR			0x0090
 #define GITS_BASER			0x0100
+#define GITS_IDREGS_BASE		0xffd0
+#define GITS_PIDR0			0xffe0
+#define GITS_PIDR1			0xffe4
 #define GITS_PIDR2			GICR_PIDR2
+#define GITS_PIDR4			0xffd0
+#define GITS_CIDR0			0xfff0
+#define GITS_CIDR1			0xfff4
+#define GITS_CIDR2			0xfff8
+#define GITS_CIDR3			0xfffc
 
 #define GITS_TRANSLATER			0x10040
 
 #define GITS_CTLR_ENABLE		(1U << 0)
 #define GITS_CTLR_QUIESCENT		(1U << 31)
 
+#define GITS_TYPER_PLPIS		(1UL << 0)
+#define GITS_TYPER_IDBITS_SHIFT		8
 #define GITS_TYPER_DEVBITS_SHIFT	13
 #define GITS_TYPER_DEVBITS(r)		((((r) >> GITS_TYPER_DEVBITS_SHIFT) & 0x1f) + 1)
 #define GITS_TYPER_PTA			(1UL << 19)
-
-#define GITS_CBASER_VALID		(1UL << 63)
-#define GITS_CBASER_nCnB		(0UL << 59)
-#define GITS_CBASER_nC			(1UL << 59)
-#define GITS_CBASER_RaWt		(2UL << 59)
-#define GITS_CBASER_RaWb		(3UL << 59)
-#define GITS_CBASER_WaWt		(4UL << 59)
-#define GITS_CBASER_WaWb		(5UL << 59)
-#define GITS_CBASER_RaWaWt		(6UL << 59)
-#define GITS_CBASER_RaWaWb		(7UL << 59)
-#define GITS_CBASER_CACHEABILITY_MASK	(7UL << 59)
-#define GITS_CBASER_NonShareable	(0UL << 10)
-#define GITS_CBASER_InnerShareable	(1UL << 10)
-#define GITS_CBASER_OuterShareable	(2UL << 10)
-#define GITS_CBASER_SHAREABILITY_MASK	(3UL << 10)
+#define GITS_TYPER_HWCOLLCNT_SHIFT	24
+
+#define GITS_CBASER_VALID			(1UL << 63)
+#define GITS_CBASER_SHAREABILITY_SHIFT		(10)
+#define GITS_CBASER_INNER_CACHEABILITY_SHIFT	(59)
+#define GITS_CBASER_OUTER_CACHEABILITY_SHIFT	(53)
+#define GITS_CBASER_SHAREABILITY_MASK					\
+	GIC_BASER_SHAREABILITY(GITS_CBASER, SHAREABILITY_MASK)
+#define GITS_CBASER_INNER_CACHEABILITY_MASK				\
+	GIC_BASER_CACHEABILITY(GITS_CBASER, INNER, MASK)
+#define GITS_CBASER_OUTER_CACHEABILITY_MASK				\
+	GIC_BASER_CACHEABILITY(GITS_CBASER, OUTER, MASK)
+#define GITS_CBASER_CACHEABILITY_MASK GITS_CBASER_INNER_CACHEABILITY_MASK
+
+#define GITS_CBASER_InnerShareable					\
+	GIC_BASER_SHAREABILITY(GITS_CBASER, InnerShareable)
+
+#define GITS_CBASER_nCnB	GIC_BASER_CACHEABILITY(GITS_CBASER, INNER, nCnB)
+#define GITS_CBASER_nC		GIC_BASER_CACHEABILITY(GITS_CBASER, INNER, nC)
+#define GITS_CBASER_RaWt	GIC_BASER_CACHEABILITY(GITS_CBASER, INNER, RaWt)
+#define GITS_CBASER_RaWb	GIC_BASER_CACHEABILITY(GITS_CBASER, INNER, RaWt)
+#define GITS_CBASER_WaWt	GIC_BASER_CACHEABILITY(GITS_CBASER, INNER, WaWt)
+#define GITS_CBASER_WaWb	GIC_BASER_CACHEABILITY(GITS_CBASER, INNER, WaWb)
+#define GITS_CBASER_RaWaWt	GIC_BASER_CACHEABILITY(GITS_CBASER, INNER, RaWaWt)
+#define GITS_CBASER_RaWaWb	GIC_BASER_CACHEABILITY(GITS_CBASER, INNER, RaWaWb)
 
 #define GITS_BASER_NR_REGS		8
 
-#define GITS_BASER_VALID		(1UL << 63)
-#define GITS_BASER_INDIRECT		(1UL << 62)
-#define GITS_BASER_nCnB			(0UL << 59)
-#define GITS_BASER_nC			(1UL << 59)
-#define GITS_BASER_RaWt			(2UL << 59)
-#define GITS_BASER_RaWb			(3UL << 59)
-#define GITS_BASER_WaWt			(4UL << 59)
-#define GITS_BASER_WaWb			(5UL << 59)
-#define GITS_BASER_RaWaWt		(6UL << 59)
-#define GITS_BASER_RaWaWb		(7UL << 59)
-#define GITS_BASER_CACHEABILITY_MASK	(7UL << 59)
-#define GITS_BASER_TYPE_SHIFT		(56)
+#define GITS_BASER_VALID			(1UL << 63)
+#define GITS_BASER_INDIRECT			(1ULL << 62)
+
+#define GITS_BASER_INNER_CACHEABILITY_SHIFT	(59)
+#define GITS_BASER_OUTER_CACHEABILITY_SHIFT	(53)
+#define GITS_BASER_INNER_CACHEABILITY_MASK				\
+	GIC_BASER_CACHEABILITY(GITS_BASER, INNER, MASK)
+#define GITS_BASER_CACHEABILITY_MASK		GITS_BASER_INNER_CACHEABILITY_MASK
+#define GITS_BASER_OUTER_CACHEABILITY_MASK				\
+	GIC_BASER_CACHEABILITY(GITS_BASER, OUTER, MASK)
+#define GITS_BASER_SHAREABILITY_MASK					\
+	GIC_BASER_SHAREABILITY(GITS_BASER, SHAREABILITY_MASK)
+
+#define GITS_BASER_nCnB		GIC_BASER_CACHEABILITY(GITS_BASER, INNER, nCnB)
+#define GITS_BASER_nC		GIC_BASER_CACHEABILITY(GITS_BASER, INNER, nC)
+#define GITS_BASER_RaWt		GIC_BASER_CACHEABILITY(GITS_BASER, INNER, RaWt)
+#define GITS_BASER_RaWb		GIC_BASER_CACHEABILITY(GITS_BASER, INNER, RaWt)
+#define GITS_BASER_WaWt		GIC_BASER_CACHEABILITY(GITS_BASER, INNER, WaWt)
+#define GITS_BASER_WaWb		GIC_BASER_CACHEABILITY(GITS_BASER, INNER, WaWb)
+#define GITS_BASER_RaWaWt	GIC_BASER_CACHEABILITY(GITS_BASER, INNER, RaWaWt)
+#define GITS_BASER_RaWaWb	GIC_BASER_CACHEABILITY(GITS_BASER, INNER, RaWaWb)
+
+#define GITS_BASER_TYPE_SHIFT			(56)
 #define GITS_BASER_TYPE(r)		(((r) >> GITS_BASER_TYPE_SHIFT) & 7)
-#define GITS_BASER_ENTRY_SIZE_SHIFT	(48)
+#define GITS_BASER_ENTRY_SIZE_SHIFT		(48)
 #define GITS_BASER_ENTRY_SIZE(r)	((((r) >> GITS_BASER_ENTRY_SIZE_SHIFT) & 0xff) + 1)
-#define GITS_BASER_NonShareable		(0UL << 10)
-#define GITS_BASER_InnerShareable	(1UL << 10)
-#define GITS_BASER_OuterShareable	(2UL << 10)
 #define GITS_BASER_SHAREABILITY_SHIFT	(10)
-#define GITS_BASER_SHAREABILITY_MASK	(3UL << GITS_BASER_SHAREABILITY_SHIFT)
+#define GITS_BASER_InnerShareable					\
+	GIC_BASER_SHAREABILITY(GITS_BASER, InnerShareable)
 #define GITS_BASER_PAGE_SIZE_SHIFT	(8)
 #define GITS_BASER_PAGE_SIZE_4K		(0UL << GITS_BASER_PAGE_SIZE_SHIFT)
 #define GITS_BASER_PAGE_SIZE_16K	(1UL << GITS_BASER_PAGE_SIZE_SHIFT)
@@ -230,6 +301,7 @@
 #define GITS_BASER_PAGE_SIZE_MASK	(3UL << GITS_BASER_PAGE_SIZE_SHIFT)
 #define GITS_BASER_PAGES_MAX		256
 #define GITS_BASER_PAGES_SHIFT		(0)
+#define GITS_BASER_NR_PAGES(r)		(((r) & 0xff) + 1)
 
 #define GITS_BASER_TYPE_NONE		0
 #define GITS_BASER_TYPE_DEVICE		1
@@ -247,7 +319,10 @@
  */
 #define GITS_CMD_MAPD			0x08
 #define GITS_CMD_MAPC			0x09
-#define GITS_CMD_MAPVI			0x0a
+#define GITS_CMD_MAPTI			0x0a
+/* older GIC documentation used MAPVI for this command */
+#define GITS_CMD_MAPVI			GITS_CMD_MAPTI
+#define GITS_CMD_MAPI			0x0b
 #define GITS_CMD_MOVI			0x01
 #define GITS_CMD_DISCARD		0x0f
 #define GITS_CMD_INV			0x0c
@@ -258,6 +333,22 @@
 #define GITS_CMD_SYNC			0x05
 
 /*
+ * ITS error numbers
+ */
+#define E_ITS_MOVI_UNMAPPED_INTERRUPT		0x010107
+#define E_ITS_MOVI_UNMAPPED_COLLECTION		0x010109
+#define E_ITS_CLEAR_UNMAPPED_INTERRUPT		0x010507
+#define E_ITS_MAPD_DEVICE_OOR			0x010801
+#define E_ITS_MAPC_PROCNUM_OOR			0x010902
+#define E_ITS_MAPC_COLLECTION_OOR		0x010903
+#define E_ITS_MAPTI_UNMAPPED_DEVICE		0x010a04
+#define E_ITS_MAPTI_PHYSICALID_OOR		0x010a06
+#define E_ITS_INV_UNMAPPED_INTERRUPT		0x010c07
+#define E_ITS_INVALL_UNMAPPED_COLLECTION	0x010d09
+#define E_ITS_MOVALL_PROCNUM_OOR		0x010e01
+#define E_ITS_DISCARD_UNMAPPED_INTERRUPT	0x010f07
+
+/*
  * CPU interface registers
  */
 #define ICC_CTLR_EL1_EOImode_drop_dir	(0U << 1)
diff --git a/include/linux/kconfig.h b/include/linux/kconfig.h
index b33c7797eb57..15ec117ec537 100644
--- a/include/linux/kconfig.h
+++ b/include/linux/kconfig.h
@@ -3,6 +3,21 @@
 
 #include <generated/autoconf.h>
 
+#define __ARG_PLACEHOLDER_1 0,
+#define __take_second_arg(__ignored, val, ...) val
+
+/*
+ * The use of "&&" / "||" is limited in certain expressions.
+ * The followings enable to calculate "and" / "or" with macro expansion only.
+ */
+#define __and(x, y)			___and(x, y)
+#define ___and(x, y)			____and(__ARG_PLACEHOLDER_##x, y)
+#define ____and(arg1_or_junk, y)	__take_second_arg(arg1_or_junk y, 0)
+
+#define __or(x, y)			___or(x, y)
+#define ___or(x, y)			____or(__ARG_PLACEHOLDER_##x, y)
+#define ____or(arg1_or_junk, y)		__take_second_arg(arg1_or_junk 1, y)
+
 /*
  * Helper macros to use CONFIG_ options in C/CPP expressions. Note that
  * these only work with boolean and tristate options.
@@ -16,11 +31,10 @@
  * When CONFIG_BOOGER is not defined, we generate a (... 1, 0) pair, and when
  * the last step cherry picks the 2nd arg, we get a zero.
  */
-#define __ARG_PLACEHOLDER_1 0,
-#define config_enabled(cfg) _config_enabled(cfg)
-#define _config_enabled(value) __config_enabled(__ARG_PLACEHOLDER_##value)
-#define __config_enabled(arg1_or_junk) ___config_enabled(arg1_or_junk 1, 0)
-#define ___config_enabled(__ignored, val, ...) val
+#define config_enabled(cfg)		___is_defined(cfg)
+#define __is_defined(x)			___is_defined(x)
+#define ___is_defined(val)		____is_defined(__ARG_PLACEHOLDER_##val)
+#define ____is_defined(arg1_or_junk)	__take_second_arg(arg1_or_junk 1, 0)
 
 /*
  * IS_BUILTIN(CONFIG_FOO) evaluates to 1 if CONFIG_FOO is set to 'y', 0
@@ -41,14 +55,13 @@
  * This is similar to IS_ENABLED(), but returns false when invoked from
  * built-in code when CONFIG_FOO is set to 'm'.
  */
-#define IS_REACHABLE(option) (config_enabled(option) || \
-		 (config_enabled(option##_MODULE) && config_enabled(MODULE)))
+#define IS_REACHABLE(option) __or(IS_BUILTIN(option), \
+				__and(IS_MODULE(option), __is_defined(MODULE)))
 
 /*
  * IS_ENABLED(CONFIG_FOO) evaluates to 1 if CONFIG_FOO is set to 'y' or 'm',
  * 0 otherwise.
  */
-#define IS_ENABLED(option) \
-	(IS_BUILTIN(option) || IS_MODULE(option))
+#define IS_ENABLED(option) __or(IS_BUILTIN(option), IS_MODULE(option))
 
 #endif /* __LINUX_KCONFIG_H */
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 1c9c973a7dd9..aafd702f3e21 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -164,6 +164,8 @@ int kvm_io_bus_register_dev(struct kvm *kvm, enum kvm_bus bus_idx, gpa_t addr,
 			    int len, struct kvm_io_device *dev);
 int kvm_io_bus_unregister_dev(struct kvm *kvm, enum kvm_bus bus_idx,
 			      struct kvm_io_device *dev);
+struct kvm_io_device *kvm_io_bus_get_dev(struct kvm *kvm, enum kvm_bus bus_idx,
+					 gpa_t addr);
 
 #ifdef CONFIG_KVM_ASYNC_PF
 struct kvm_async_pf {
@@ -371,7 +373,15 @@ struct kvm {
 	struct srcu_struct srcu;
 	struct srcu_struct irq_srcu;
 	struct kvm_vcpu *vcpus[KVM_MAX_VCPUS];
+
+	/*
+	 * created_vcpus is protected by kvm->lock, and is incremented
+	 * at the beginning of KVM_CREATE_VCPU.  online_vcpus is only
+	 * incremented after storing the kvm_vcpu pointer in vcpus,
+	 * and is accessed atomically.
+	 */
 	atomic_t online_vcpus;
+	int created_vcpus;
 	int last_boosted_vcpu;
 	struct list_head vm_list;
 	struct mutex lock;
@@ -867,45 +877,6 @@ static inline void kvm_iommu_unmap_pages(struct kvm *kvm,
 }
 #endif
 
-/* must be called with irqs disabled */
-static inline void __kvm_guest_enter(void)
-{
-	guest_enter();
-	/* KVM does not hold any references to rcu protected data when it
-	 * switches CPU into a guest mode. In fact switching to a guest mode
-	 * is very similar to exiting to userspace from rcu point of view. In
-	 * addition CPU may stay in a guest mode for quite a long time (up to
-	 * one time slice). Lets treat guest mode as quiescent state, just like
-	 * we do with user-mode execution.
-	 */
-	if (!context_tracking_cpu_is_enabled())
-		rcu_virt_note_context_switch(smp_processor_id());
-}
-
-/* must be called with irqs disabled */
-static inline void __kvm_guest_exit(void)
-{
-	guest_exit();
-}
-
-static inline void kvm_guest_enter(void)
-{
-	unsigned long flags;
-
-	local_irq_save(flags);
-	__kvm_guest_enter();
-	local_irq_restore(flags);
-}
-
-static inline void kvm_guest_exit(void)
-{
-	unsigned long flags;
-
-	local_irq_save(flags);
-	__kvm_guest_exit();
-	local_irq_restore(flags);
-}
-
 /*
  * search_memslots() and __gfn_to_memslot() are here because they are
  * used in non-modular code in arch/powerpc/kvm/book3s_hv_rm_mmu.c.
@@ -1042,7 +1013,8 @@ int kvm_set_irq_routing(struct kvm *kvm,
 			const struct kvm_irq_routing_entry *entries,
 			unsigned nr,
 			unsigned flags);
-int kvm_set_routing_entry(struct kvm_kernel_irq_routing_entry *e,
+int kvm_set_routing_entry(struct kvm *kvm,
+			  struct kvm_kernel_irq_routing_entry *e,
 			  const struct kvm_irq_routing_entry *ue);
 void kvm_free_irq_routing(struct kvm *kvm);
 
@@ -1097,12 +1069,6 @@ static inline int kvm_ioeventfd(struct kvm *kvm, struct kvm_ioeventfd *args)
 
 #endif /* CONFIG_HAVE_KVM_EVENTFD */
 
-#ifdef CONFIG_KVM_APIC_ARCHITECTURE
-bool kvm_vcpu_compatible(struct kvm_vcpu *vcpu);
-#else
-static inline bool kvm_vcpu_compatible(struct kvm_vcpu *vcpu) { return true; }
-#endif
-
 static inline void kvm_make_request(int req, struct kvm_vcpu *vcpu)
 {
 	/*
diff --git a/include/linux/mtd/nand.h b/include/linux/mtd/nand.h
index fbe8e164a4ee..8dd6e01f45c0 100644
--- a/include/linux/mtd/nand.h
+++ b/include/linux/mtd/nand.h
@@ -783,6 +783,7 @@ static inline void nand_set_controller_data(struct nand_chip *chip, void *priv)
  * NAND Flash Manufacturer ID Codes
  */
 #define NAND_MFR_TOSHIBA	0x98
+#define NAND_MFR_ESMT		0xc8
 #define NAND_MFR_SAMSUNG	0xec
 #define NAND_MFR_FUJITSU	0x04
 #define NAND_MFR_NATIONAL	0x8f
diff --git a/include/linux/mtd/spi-nor.h b/include/linux/mtd/spi-nor.h
index 7f041bd88b82..c425c7b4c2a0 100644
--- a/include/linux/mtd/spi-nor.h
+++ b/include/linux/mtd/spi-nor.h
@@ -173,10 +173,10 @@ struct spi_nor {
 	int (*read_reg)(struct spi_nor *nor, u8 opcode, u8 *buf, int len);
 	int (*write_reg)(struct spi_nor *nor, u8 opcode, u8 *buf, int len);
 
-	int (*read)(struct spi_nor *nor, loff_t from,
-			size_t len, size_t *retlen, u_char *read_buf);
-	void (*write)(struct spi_nor *nor, loff_t to,
-			size_t len, size_t *retlen, const u_char *write_buf);
+	ssize_t (*read)(struct spi_nor *nor, loff_t from,
+			size_t len, u_char *read_buf);
+	ssize_t (*write)(struct spi_nor *nor, loff_t to,
+			size_t len, const u_char *write_buf);
 	int (*erase)(struct spi_nor *nor, loff_t offs);
 
 	int (*flash_lock)(struct spi_nor *nor, loff_t ofs, uint64_t len);
diff --git a/include/linux/page_ref.h b/include/linux/page_ref.h
index 8b5e0a9f2431..610e13271918 100644
--- a/include/linux/page_ref.h
+++ b/include/linux/page_ref.h
@@ -124,6 +124,15 @@ static inline int page_ref_sub_and_test(struct page *page, int nr)
 	return ret;
 }
 
+static inline int page_ref_inc_return(struct page *page)
+{
+	int ret = atomic_inc_return(&page->_refcount);
+
+	if (page_ref_tracepoint_active(__tracepoint_page_ref_mod_and_return))
+		__page_ref_mod_and_return(page, 1, ret);
+	return ret;
+}
+
 static inline int page_ref_dec_and_test(struct page *page)
 {
 	int ret = atomic_dec_and_test(&page->_refcount);
diff --git a/include/linux/pci-acpi.h b/include/linux/pci-acpi.h
index 89ab0572dbc6..7d63a66e8ed4 100644
--- a/include/linux/pci-acpi.h
+++ b/include/linux/pci-acpi.h
@@ -24,6 +24,8 @@ static inline acpi_status pci_acpi_remove_pm_notifier(struct acpi_device *dev)
 }
 extern phys_addr_t acpi_pci_root_get_mcfg_addr(acpi_handle handle);
 
+extern phys_addr_t pci_mcfg_lookup(u16 domain, struct resource *bus_res);
+
 static inline acpi_handle acpi_find_root_bridge_handle(struct pci_dev *pdev)
 {
 	struct pci_bus *pbus = pdev->bus;
diff --git a/include/linux/pci-ecam.h b/include/linux/pci-ecam.h
new file mode 100644
index 000000000000..7adad206b1f4
--- /dev/null
+++ b/include/linux/pci-ecam.h
@@ -0,0 +1,67 @@
+/*
+ * Copyright 2016 Broadcom
+ *
+ * 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 (the "GPL").
+ *
+ * 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 version 2 (GPLv2) for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * version 2 (GPLv2) along with this source code.
+ */
+#ifndef DRIVERS_PCI_ECAM_H
+#define DRIVERS_PCI_ECAM_H
+
+#include <linux/kernel.h>
+#include <linux/platform_device.h>
+
+/*
+ * struct to hold pci ops and bus shift of the config window
+ * for a PCI controller.
+ */
+struct pci_config_window;
+struct pci_ecam_ops {
+	unsigned int			bus_shift;
+	struct pci_ops			pci_ops;
+	int				(*init)(struct pci_config_window *);
+};
+
+/*
+ * struct to hold the mappings of a config space window. This
+ * is expected to be used as sysdata for PCI controllers that
+ * use ECAM.
+ */
+struct pci_config_window {
+	struct resource			res;
+	struct resource			busr;
+	void				*priv;
+	struct pci_ecam_ops		*ops;
+	union {
+		void __iomem		*win;	/* 64-bit single mapping */
+		void __iomem		**winp; /* 32-bit per-bus mapping */
+	};
+	struct device			*parent;/* ECAM res was from this dev */
+};
+
+/* create and free pci_config_window */
+struct pci_config_window *pci_ecam_create(struct device *dev,
+		struct resource *cfgres, struct resource *busr,
+		struct pci_ecam_ops *ops);
+void pci_ecam_free(struct pci_config_window *cfg);
+
+/* map_bus when ->sysdata is an instance of pci_config_window */
+void __iomem *pci_ecam_map_bus(struct pci_bus *bus, unsigned int devfn,
+			       int where);
+/* default ECAM ops */
+extern struct pci_ecam_ops pci_generic_ecam_ops;
+
+#ifdef CONFIG_PCI_HOST_GENERIC
+/* for DT-based PCI controllers that support ECAM */
+int pci_host_common_probe(struct platform_device *pdev,
+			  struct pci_ecam_ops *ops);
+#endif
+#endif
diff --git a/include/linux/pci.h b/include/linux/pci.h
index c40ac910cce4..2599a980340f 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -101,6 +101,10 @@ enum {
 	DEVICE_COUNT_RESOURCE = PCI_NUM_RESOURCES,
 };
 
+/*
+ * pci_power_t values must match the bits in the Capabilities PME_Support
+ * and Control/Status PowerState fields in the Power Management capability.
+ */
 typedef int __bitwise pci_power_t;
 
 #define PCI_D0		((pci_power_t __force) 0)
@@ -116,7 +120,7 @@ extern const char *pci_power_names[];
 
 static inline const char *pci_power_name(pci_power_t state)
 {
-	return pci_power_names[1 + (int) state];
+	return pci_power_names[1 + (__force int) state];
 }
 
 #define PCI_PM_D2_DELAY		200
@@ -294,6 +298,7 @@ struct pci_dev {
 	unsigned int	d2_support:1;	/* Low power state D2 is supported */
 	unsigned int	no_d1d2:1;	/* D1 and D2 are forbidden */
 	unsigned int	no_d3cold:1;	/* D3cold is forbidden */
+	unsigned int	bridge_d3:1;	/* Allow D3 for bridge */
 	unsigned int	d3cold_allowed:1;	/* D3cold is allowed by user */
 	unsigned int	mmio_always_on:1;	/* disallow turning off io/mem
 						   decoding during bar sizing */
@@ -320,6 +325,7 @@ struct pci_dev {
 	 * directly, use the values stored here. They might be different!
 	 */
 	unsigned int	irq;
+	struct cpumask	*irq_affinity;
 	struct resource resource[DEVICE_COUNT_RESOURCE]; /* I/O and memory regions + expansion ROMs */
 
 	bool match_driver;		/* Skip attaching driver */
@@ -1084,6 +1090,8 @@ int pci_back_from_sleep(struct pci_dev *dev);
 bool pci_dev_run_wake(struct pci_dev *dev);
 bool pci_check_pme_status(struct pci_dev *dev);
 void pci_pme_wakeup_bus(struct pci_bus *bus);
+void pci_d3cold_enable(struct pci_dev *dev);
+void pci_d3cold_disable(struct pci_dev *dev);
 
 static inline int pci_enable_wake(struct pci_dev *dev, pci_power_t state,
 				  bool enable)
@@ -1115,6 +1123,7 @@ int pci_set_vpd_size(struct pci_dev *dev, size_t len);
 /* Helper functions for low-level code (drivers/pci/setup-[bus,res].c) */
 resource_size_t pcibios_retrieve_fw_addr(struct pci_dev *dev, int idx);
 void pci_bus_assign_resources(const struct pci_bus *bus);
+void pci_bus_claim_resources(struct pci_bus *bus);
 void pci_bus_size_bridges(struct pci_bus *bus);
 int pci_claim_resource(struct pci_dev *, int);
 int pci_claim_bridge_resource(struct pci_dev *bridge, int i);
@@ -1144,9 +1153,12 @@ void pci_add_resource(struct list_head *resources, struct resource *res);
 void pci_add_resource_offset(struct list_head *resources, struct resource *res,
 			     resource_size_t offset);
 void pci_free_resource_list(struct list_head *resources);
-void pci_bus_add_resource(struct pci_bus *bus, struct resource *res, unsigned int flags);
+void pci_bus_add_resource(struct pci_bus *bus, struct resource *res,
+			  unsigned int flags);
 struct resource *pci_bus_resource_n(const struct pci_bus *bus, int n);
 void pci_bus_remove_resources(struct pci_bus *bus);
+int devm_request_pci_bus_resources(struct device *dev,
+				   struct list_head *resources);
 
 #define pci_bus_for_each_resource(bus, res, i)				\
 	for (i = 0;							\
@@ -1168,6 +1180,7 @@ int pci_register_io_range(phys_addr_t addr, resource_size_t size);
 unsigned long pci_address_to_pio(phys_addr_t addr);
 phys_addr_t pci_pio_to_address(unsigned long pio);
 int pci_remap_iospace(const struct resource *res, phys_addr_t phys_addr);
+void pci_unmap_iospace(struct resource *res);
 
 static inline pci_bus_addr_t pci_bus_address(struct pci_dev *pdev, int bar)
 {
@@ -1238,6 +1251,11 @@ resource_size_t pcibios_iov_resource_alignment(struct pci_dev *dev, int resno);
 int pci_set_vga_state(struct pci_dev *pdev, bool decode,
 		      unsigned int command_bits, u32 flags);
 
+#define PCI_IRQ_NOLEGACY	(1 << 0) /* don't use legacy interrupts */
+#define PCI_IRQ_NOMSI		(1 << 1) /* don't use MSI interrupts */
+#define PCI_IRQ_NOMSIX		(1 << 2) /* don't use MSI-X interrupts */
+#define PCI_IRQ_NOAFFINITY	(1 << 3) /* don't auto-assign affinity */
+
 /* kmem_cache style wrapper around pci_alloc_consistent() */
 
 #include <linux/pci-dma.h>
@@ -1285,6 +1303,11 @@ static inline int pci_enable_msix_exact(struct pci_dev *dev,
 		return rc;
 	return 0;
 }
+int pci_alloc_irq_vectors(struct pci_dev *dev, unsigned int min_vecs,
+		unsigned int max_vecs, unsigned int flags);
+void pci_free_irq_vectors(struct pci_dev *dev);
+int pci_irq_vector(struct pci_dev *dev, unsigned int nr);
+
 #else
 static inline int pci_msi_vec_count(struct pci_dev *dev) { return -ENOSYS; }
 static inline void pci_msi_shutdown(struct pci_dev *dev) { }
@@ -1308,6 +1331,24 @@ static inline int pci_enable_msix_range(struct pci_dev *dev,
 static inline int pci_enable_msix_exact(struct pci_dev *dev,
 		      struct msix_entry *entries, int nvec)
 { return -ENOSYS; }
+static inline int pci_alloc_irq_vectors(struct pci_dev *dev,
+		unsigned int min_vecs, unsigned int max_vecs,
+		unsigned int flags)
+{
+	if (min_vecs > 1)
+		return -EINVAL;
+	return 1;
+}
+static inline void pci_free_irq_vectors(struct pci_dev *dev)
+{
+}
+
+static inline int pci_irq_vector(struct pci_dev *dev, unsigned int nr)
+{
+	if (WARN_ON_ONCE(nr > 0))
+		return -EINVAL;
+	return dev->irq;
+}
 #endif
 
 #ifdef CONFIG_PCIEPORTBUS
@@ -1390,12 +1431,13 @@ static inline int pci_domain_nr(struct pci_bus *bus)
 {
 	return bus->domain_nr;
 }
-void pci_bus_assign_domain_nr(struct pci_bus *bus, struct device *parent);
+#ifdef CONFIG_ACPI
+int acpi_pci_bus_find_domain_nr(struct pci_bus *bus);
 #else
-static inline void pci_bus_assign_domain_nr(struct pci_bus *bus,
-					struct device *parent)
-{
-}
+static inline int acpi_pci_bus_find_domain_nr(struct pci_bus *bus)
+{ return 0; }
+#endif
+int pci_bus_find_domain_nr(struct pci_bus *bus, struct device *parent);
 #endif
 
 /* some architectures require additional setup to direct VGA traffic */
@@ -1403,6 +1445,34 @@ typedef int (*arch_set_vga_state_t)(struct pci_dev *pdev, bool decode,
 		      unsigned int command_bits, u32 flags);
 void pci_register_set_vga_state(arch_set_vga_state_t func);
 
+static inline int
+pci_request_io_regions(struct pci_dev *pdev, const char *name)
+{
+	return pci_request_selected_regions(pdev,
+			    pci_select_bars(pdev, IORESOURCE_IO), name);
+}
+
+static inline void
+pci_release_io_regions(struct pci_dev *pdev)
+{
+	return pci_release_selected_regions(pdev,
+			    pci_select_bars(pdev, IORESOURCE_IO));
+}
+
+static inline int
+pci_request_mem_regions(struct pci_dev *pdev, const char *name)
+{
+	return pci_request_selected_regions(pdev,
+			    pci_select_bars(pdev, IORESOURCE_MEM), name);
+}
+
+static inline void
+pci_release_mem_regions(struct pci_dev *pdev)
+{
+	return pci_release_selected_regions(pdev,
+			    pci_select_bars(pdev, IORESOURCE_MEM));
+}
+
 #else /* CONFIG_PCI is not enabled */
 
 static inline void pci_set_flags(int flags) { }
@@ -1555,7 +1625,11 @@ static inline const char *pci_name(const struct pci_dev *pdev)
 /* Some archs don't want to expose struct resource to userland as-is
  * in sysfs and /proc
  */
-#ifndef HAVE_ARCH_PCI_RESOURCE_TO_USER
+#ifdef HAVE_ARCH_PCI_RESOURCE_TO_USER
+void pci_resource_to_user(const struct pci_dev *dev, int bar,
+			  const struct resource *rsrc,
+			  resource_size_t *start, resource_size_t *end);
+#else
 static inline void pci_resource_to_user(const struct pci_dev *dev, int bar,
 		const struct resource *rsrc, resource_size_t *start,
 		resource_size_t *end)
@@ -1707,6 +1781,7 @@ extern u8 pci_cache_line_size;
 
 extern unsigned long pci_hotplug_io_size;
 extern unsigned long pci_hotplug_mem_size;
+extern unsigned long pci_hotplug_bus_size;
 
 /* Architecture-specific versions may override these (weak) */
 void pcibios_disable_device(struct pci_dev *dev);
@@ -1723,7 +1798,7 @@ void pcibios_free_irq(struct pci_dev *dev);
 extern struct dev_pm_ops pcibios_pm_ops;
 #endif
 
-#ifdef CONFIG_PCI_MMCONFIG
+#if defined(CONFIG_PCI_MMCONFIG) || defined(CONFIG_ACPI_MCFG)
 void __init pci_mmcfg_early_init(void);
 void __init pci_mmcfg_late_init(void);
 #else
diff --git a/include/trace/events/kvm.h b/include/trace/events/kvm.h
index f28292d73ddb..8ade3eb6c640 100644
--- a/include/trace/events/kvm.h
+++ b/include/trace/events/kvm.h
@@ -151,8 +151,9 @@ TRACE_EVENT(kvm_msi_set_irq,
 		__entry->data		= data;
 	),
 
-	TP_printk("dst %u vec %u (%s|%s|%s%s)",
-		  (u8)(__entry->address >> 12), (u8)__entry->data,
+	TP_printk("dst %llx vec %u (%s|%s|%s%s)",
+		  (u8)(__entry->address >> 12) | ((__entry->address >> 32) & 0xffffff00),
+		  (u8)__entry->data,
 		  __print_symbolic((__entry->data >> 8 & 0x7), kvm_deliver_mode),
 		  (__entry->address & (1<<2)) ? "logical" : "physical",
 		  (__entry->data & (1<<15)) ? "level" : "edge",
diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
index 05ebf475104c..e98bb4cce639 100644
--- a/include/uapi/linux/kvm.h
+++ b/include/uapi/linux/kvm.h
@@ -866,6 +866,10 @@ struct kvm_ppc_smmu_info {
 #define KVM_CAP_ARM_PMU_V3 126
 #define KVM_CAP_VCPU_ATTRIBUTES 127
 #define KVM_CAP_MAX_VCPU_ID 128
+#define KVM_CAP_X2APIC_API 129
+#define KVM_CAP_S390_USER_INSTR0 130
+#define KVM_CAP_MSI_DEVID 131
+#define KVM_CAP_PPC_HTM 132
 
 #ifdef KVM_CAP_IRQ_ROUTING
 
@@ -1024,12 +1028,14 @@ struct kvm_one_reg {
 	__u64 addr;
 };
 
+#define KVM_MSI_VALID_DEVID	(1U << 0)
 struct kvm_msi {
 	__u32 address_lo;
 	__u32 address_hi;
 	__u32 data;
 	__u32 flags;
-	__u8  pad[16];
+	__u32 devid;
+	__u8  pad[12];
 };
 
 struct kvm_arm_device_addr {
@@ -1074,6 +1080,8 @@ enum kvm_device_type {
 #define KVM_DEV_TYPE_FLIC		KVM_DEV_TYPE_FLIC
 	KVM_DEV_TYPE_ARM_VGIC_V3,
 #define KVM_DEV_TYPE_ARM_VGIC_V3	KVM_DEV_TYPE_ARM_VGIC_V3
+	KVM_DEV_TYPE_ARM_VGIC_ITS,
+#define KVM_DEV_TYPE_ARM_VGIC_ITS	KVM_DEV_TYPE_ARM_VGIC_ITS
 	KVM_DEV_TYPE_MAX,
 };
 
@@ -1313,4 +1321,7 @@ struct kvm_assigned_msix_entry {
 	__u16 padding[3];
 };
 
+#define KVM_X2APIC_API_USE_32BIT_IDS            (1ULL << 0)
+#define KVM_X2APIC_API_DISABLE_BROADCAST_QUIRK  (1ULL << 1)
+
 #endif /* __LINUX_KVM_H */