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

Conflict resolution of af_smc.c from Stephen Rothwell.

Signed-off-by: David S. Miller <davem@davemloft.net>

.clang-format

@@ -78,6 +78,8 @@ ForEachMacros:
   - 'ata_qc_for_each_with_internal'
   - 'ax25_for_each'
   - 'ax25_uid_for_each'
+  - '__bio_for_each_bvec'
+  - 'bio_for_each_bvec'
   - 'bio_for_each_integrity_vec'
   - '__bio_for_each_segment'
   - 'bio_for_each_segment'
@@ -118,10 +120,12 @@ ForEachMacros:
   - 'drm_for_each_legacy_plane'
   - 'drm_for_each_plane'
   - 'drm_for_each_plane_mask'
+  - 'drm_for_each_privobj'
   - 'drm_mm_for_each_hole'
   - 'drm_mm_for_each_node'
   - 'drm_mm_for_each_node_in_range'
   - 'drm_mm_for_each_node_safe'
+  - 'flow_action_for_each'
   - 'for_each_active_drhd_unit'
   - 'for_each_active_iommu'
   - 'for_each_available_child_of_node'
@@ -158,6 +162,9 @@ ForEachMacros:
   - 'for_each_dss_dev'
   - 'for_each_efi_memory_desc'
   - 'for_each_efi_memory_desc_in_map'
+  - 'for_each_element'
+  - 'for_each_element_extid'
+  - 'for_each_element_id'
   - 'for_each_endpoint_of_node'
   - 'for_each_evictable_lru'
   - 'for_each_fib6_node_rt_rcu'
@@ -195,6 +202,7 @@ ForEachMacros:
   - 'for_each_net_rcu'
   - 'for_each_new_connector_in_state'
   - 'for_each_new_crtc_in_state'
+  - 'for_each_new_mst_mgr_in_state'
   - 'for_each_new_plane_in_state'
   - 'for_each_new_private_obj_in_state'
   - 'for_each_node'
@@ -210,8 +218,10 @@ ForEachMacros:
   - 'for_each_of_pci_range'
   - 'for_each_old_connector_in_state'
   - 'for_each_old_crtc_in_state'
+  - 'for_each_old_mst_mgr_in_state'
   - 'for_each_oldnew_connector_in_state'
   - 'for_each_oldnew_crtc_in_state'
+  - 'for_each_oldnew_mst_mgr_in_state'
   - 'for_each_oldnew_plane_in_state'
   - 'for_each_oldnew_plane_in_state_reverse'
   - 'for_each_oldnew_private_obj_in_state'
@@ -243,6 +253,9 @@ ForEachMacros:
   - 'for_each_sg_dma_page'
   - 'for_each_sg_page'
   - 'for_each_sibling_event'
+  - 'for_each_subelement'
+  - 'for_each_subelement_extid'
+  - 'for_each_subelement_id'
   - '__for_each_thread'
   - 'for_each_thread'
   - 'for_each_zone'
@@ -252,6 +265,8 @@ ForEachMacros:
   - 'fwnode_for_each_child_node'
   - 'fwnode_graph_for_each_endpoint'
   - 'gadget_for_each_ep'
+  - 'genradix_for_each'
+  - 'genradix_for_each_from'
   - 'hash_for_each'
   - 'hash_for_each_possible'
   - 'hash_for_each_possible_rcu'
@@ -293,7 +308,11 @@ ForEachMacros:
   - 'key_for_each'
   - 'key_for_each_safe'
   - 'klp_for_each_func'
+  - 'klp_for_each_func_safe'
+  - 'klp_for_each_func_static'
   - 'klp_for_each_object'
+  - 'klp_for_each_object_safe'
+  - 'klp_for_each_object_static'
   - 'kvm_for_each_memslot'
   - 'kvm_for_each_vcpu'
   - 'list_for_each'
@@ -324,6 +343,8 @@ ForEachMacros:
   - 'media_device_for_each_intf'
   - 'media_device_for_each_link'
   - 'media_device_for_each_pad'
+  - 'mp_bvec_for_each_page'
+  - 'mp_bvec_for_each_segment'
   - 'nanddev_io_for_each_page'
   - 'netdev_for_each_lower_dev'
   - 'netdev_for_each_lower_private'
@@ -375,6 +396,7 @@ ForEachMacros:
   - 'rht_for_each_rcu'
   - 'rht_for_each_rcu_from'
   - '__rq_for_each_bio'
+  - 'rq_for_each_bvec'
   - 'rq_for_each_segment'
   - 'scsi_for_each_prot_sg'
   - 'scsi_for_each_sg'
@@ -410,6 +432,8 @@ ForEachMacros:
   - 'v4l2_m2m_for_each_src_buf_safe'
   - 'virtio_device_for_each_vq'
   - 'xa_for_each'
+  - 'xa_for_each_marked'
+  - 'xa_for_each_start'
   - 'xas_for_each'
   - 'xas_for_each_conflict'
   - 'xas_for_each_marked'

Documentation/networking/rxrpc.txt

@@ -1009,16 +1009,18 @@ The kernel interface functions are as follows:
 
  (*) Check call still alive.
 
-	u32 rxrpc_kernel_check_life(struct socket *sock,
+	bool rxrpc_kernel_check_life(struct socket *sock,
-				    struct rxrpc_call *call);
+				     struct rxrpc_call *call,
+				     u32 *_life);
 	void rxrpc_kernel_probe_life(struct socket *sock,
 				     struct rxrpc_call *call);
 
-     The first function returns a number that is updated when ACKs are received
+     The first function passes back in *_life a number that is updated when
-     from the peer (notably including PING RESPONSE ACKs which we can elicit by
+     ACKs are received from the peer (notably including PING RESPONSE ACKs
-     sending PING ACKs to see if the call still exists on the server).  The
+     which we can elicit by sending PING ACKs to see if the call still exists
-     caller should compare the numbers of two calls to see if the call is still
+     on the server).  The caller should compare the numbers of two calls to see
-     alive after waiting for a suitable interval.
+     if the call is still alive after waiting for a suitable interval.  It also
+     returns true as long as the call hasn't yet reached the completed state.
 
      This allows the caller to work out if the server is still contactable and
      if the call is still alive on the server while waiting for the server to

MAINTAINERS

@@ -10139,7 +10139,7 @@ F:	drivers/spi/spi-at91-usart.c
 F:	Documentation/devicetree/bindings/mfd/atmel-usart.txt
 
 MICROCHIP KSZ SERIES ETHERNET SWITCH DRIVER
-M:	Woojung Huh <Woojung.Huh@microchip.com>
+M:	Woojung Huh <woojung.huh@microchip.com>
 M:	Microchip Linux Driver Support <UNGLinuxDriver@microchip.com>
 L:	netdev@vger.kernel.org
 S:	Maintained
@@ -16503,7 +16503,7 @@ F:	drivers/char/virtio_console.c
 F:	include/linux/virtio_console.h
 F:	include/uapi/linux/virtio_console.h
 
-VIRTIO CORE, NET AND BLOCK DRIVERS
+VIRTIO CORE AND NET DRIVERS
 M:	"Michael S. Tsirkin" <mst@redhat.com>
 M:	Jason Wang <jasowang@redhat.com>
 L:	virtualization@lists.linux-foundation.org
@@ -16518,6 +16518,19 @@ F:	include/uapi/linux/virtio_*.h
 F:	drivers/crypto/virtio/
 F:	mm/balloon_compaction.c
 
+VIRTIO BLOCK AND SCSI DRIVERS
+M:	"Michael S. Tsirkin" <mst@redhat.com>
+M:	Jason Wang <jasowang@redhat.com>
+R:	Paolo Bonzini <pbonzini@redhat.com>
+R:	Stefan Hajnoczi <stefanha@redhat.com>
+L:	virtualization@lists.linux-foundation.org
+S:	Maintained
+F:	drivers/block/virtio_blk.c
+F:	drivers/scsi/virtio_scsi.c
+F:	include/uapi/linux/virtio_blk.h
+F:	include/uapi/linux/virtio_scsi.h
+F:	drivers/vhost/scsi.c
+
 VIRTIO CRYPTO DRIVER
 M:	Gonglei <arei.gonglei@huawei.com>
 L:	virtualization@lists.linux-foundation.org

Makefile

@@ -2,7 +2,7 @@
 VERSION = 5
 PATCHLEVEL = 1
 SUBLEVEL = 0
-EXTRAVERSION = -rc4
+EXTRAVERSION = -rc5
 NAME = Shy Crocodile
 
 # *DOCUMENTATION*

arch/arm64/include/asm/futex.h

@@ -30,8 +30,8 @@ do {									\
 "	prfm	pstl1strm, %2\n"					\
 "1:	ldxr	%w1, %2\n"						\
 	insn "\n"							\
-"2:	stlxr	%w3, %w0, %2\n"						\
+"2:	stlxr	%w0, %w3, %2\n"						\
-"	cbnz	%w3, 1b\n"						\
+"	cbnz	%w0, 1b\n"						\
 "	dmb	ish\n"							\
 "3:\n"									\
 "	.pushsection .fixup,\"ax\"\n"					\
@@ -50,30 +50,30 @@ do {									\
 static inline int
 arch_futex_atomic_op_inuser(int op, int oparg, int *oval, u32 __user *_uaddr)
 {
-	int oldval = 0, ret, tmp;
+	int oldval, ret, tmp;
 	u32 __user *uaddr = __uaccess_mask_ptr(_uaddr);
 
 	pagefault_disable();
 
 	switch (op) {
 	case FUTEX_OP_SET:
-		__futex_atomic_op("mov	%w0, %w4",
+		__futex_atomic_op("mov	%w3, %w4",
 				  ret, oldval, uaddr, tmp, oparg);
 		break;
 	case FUTEX_OP_ADD:
-		__futex_atomic_op("add	%w0, %w1, %w4",
+		__futex_atomic_op("add	%w3, %w1, %w4",
 				  ret, oldval, uaddr, tmp, oparg);
 		break;
 	case FUTEX_OP_OR:
-		__futex_atomic_op("orr	%w0, %w1, %w4",
+		__futex_atomic_op("orr	%w3, %w1, %w4",
 				  ret, oldval, uaddr, tmp, oparg);
 		break;
 	case FUTEX_OP_ANDN:
-		__futex_atomic_op("and	%w0, %w1, %w4",
+		__futex_atomic_op("and	%w3, %w1, %w4",
 				  ret, oldval, uaddr, tmp, ~oparg);
 		break;
 	case FUTEX_OP_XOR:
-		__futex_atomic_op("eor	%w0, %w1, %w4",
+		__futex_atomic_op("eor	%w3, %w1, %w4",
 				  ret, oldval, uaddr, tmp, oparg);
 		break;
 	default:

arch/arm64/include/asm/module.h

@@ -73,4 +73,9 @@ static inline bool is_forbidden_offset_for_adrp(void *place)
 struct plt_entry get_plt_entry(u64 dst, void *pc);
 bool plt_entries_equal(const struct plt_entry *a, const struct plt_entry *b);
 
+static inline bool plt_entry_is_initialized(const struct plt_entry *e)
+{
+	return e->adrp || e->add || e->br;
+}
+
 #endif /* __ASM_MODULE_H */

arch/arm64/kernel/ftrace.c

@@ -107,8 +107,7 @@ int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
 		trampoline = get_plt_entry(addr, mod->arch.ftrace_trampoline);
 		if (!plt_entries_equal(mod->arch.ftrace_trampoline,
 				       &trampoline)) {
-			if (!plt_entries_equal(mod->arch.ftrace_trampoline,
+			if (plt_entry_is_initialized(mod->arch.ftrace_trampoline)) {
-					       &(struct plt_entry){})) {
 				pr_err("ftrace: far branches to multiple entry points unsupported inside a single module\n");
 				return -EINVAL;
 			}

arch/arm64/kernel/traps.c

@@ -102,10 +102,16 @@ static void dump_instr(const char *lvl, struct pt_regs *regs)
 void dump_backtrace(struct pt_regs *regs, struct task_struct *tsk)
 {
 	struct stackframe frame;
-	int skip;
+	int skip = 0;
 
 	pr_debug("%s(regs = %p tsk = %p)\n", __func__, regs, tsk);
 
+	if (regs) {
+		if (user_mode(regs))
+			return;
+		skip = 1;
+	}
+
 	if (!tsk)
 		tsk = current;
 
@@ -126,7 +132,6 @@ void dump_backtrace(struct pt_regs *regs, struct task_struct *tsk)
 	frame.graph = 0;
 #endif
 
-	skip = !!regs;
 	printk("Call trace:\n");
 	do {
 		/* skip until specified stack frame */
@@ -176,15 +181,13 @@ static int __die(const char *str, int err, struct pt_regs *regs)
 		return ret;
 
 	print_modules();
-	__show_regs(regs);
 	pr_emerg("Process %.*s (pid: %d, stack limit = 0x%p)\n",
 		 TASK_COMM_LEN, tsk->comm, task_pid_nr(tsk),
 		 end_of_stack(tsk));
+	show_regs(regs);
 
-	if (!user_mode(regs)) {
+	if (!user_mode(regs))
-		dump_backtrace(regs, tsk);
 		dump_instr(KERN_EMERG, regs);
-	}
 
 	return ret;
 }

arch/mips/configs/generic/board-ocelot.config

@@ -1,6 +1,10 @@
 # require CONFIG_CPU_MIPS32_R2=y
 
 CONFIG_LEGACY_BOARD_OCELOT=y
+CONFIG_FIT_IMAGE_FDT_OCELOT=y
+
+CONFIG_BRIDGE=y
+CONFIG_GENERIC_PHY=y
 
 CONFIG_MTD=y
 CONFIG_MTD_CMDLINE_PARTS=y
@@ -19,6 +23,8 @@ CONFIG_SERIAL_8250_CONSOLE=y
 CONFIG_SERIAL_OF_PLATFORM=y
 
 CONFIG_NETDEVICES=y
+CONFIG_NET_SWITCHDEV=y
+CONFIG_NET_DSA=y
 CONFIG_MSCC_OCELOT_SWITCH=y
 CONFIG_MSCC_OCELOT_SWITCH_OCELOT=y
 CONFIG_MDIO_MSCC_MIIM=y
@@ -35,6 +41,8 @@ CONFIG_SPI_DESIGNWARE=y
 CONFIG_SPI_DW_MMIO=y
 CONFIG_SPI_SPIDEV=y
 
+CONFIG_PINCTRL_OCELOT=y
+
 CONFIG_GPIO_SYSFS=y
 
 CONFIG_POWER_RESET=y

arch/mips/kernel/kgdb.c

@@ -33,6 +33,7 @@
 #include <asm/processor.h>
 #include <asm/sigcontext.h>
 #include <linux/uaccess.h>
+#include <asm/irq_regs.h>
 
 static struct hard_trap_info {
 	unsigned char tt;	/* Trap type code for MIPS R3xxx and R4xxx */
@@ -214,7 +215,7 @@ void kgdb_call_nmi_hook(void *ignored)
 	old_fs = get_fs();
 	set_fs(KERNEL_DS);
 
-	kgdb_nmicallback(raw_smp_processor_id(), NULL);
+	kgdb_nmicallback(raw_smp_processor_id(), get_irq_regs());
 
 	set_fs(old_fs);
 }

arch/mips/sgi-ip27/ip27-irq.c

@@ -118,7 +118,6 @@ static void shutdown_bridge_irq(struct irq_data *d)
 {
 	struct hub_irq_data *hd = irq_data_get_irq_chip_data(d);
 	struct bridge_controller *bc;
-	int pin = hd->pin;
 
 	if (!hd)
 		return;
@@ -126,7 +125,7 @@ static void shutdown_bridge_irq(struct irq_data *d)
 	disable_hub_irq(d);
 
 	bc = hd->bc;
-	bridge_clr(bc, b_int_enable, (1 << pin));
+	bridge_clr(bc, b_int_enable, (1 << hd->pin));
 	bridge_read(bc, b_wid_tflush);
 }
 

arch/powerpc/include/asm/mmu.h

@@ -352,7 +352,7 @@ static inline bool strict_kernel_rwx_enabled(void)
 #if defined(CONFIG_SPARSEMEM_VMEMMAP) && defined(CONFIG_SPARSEMEM_EXTREME) &&	\
 	defined (CONFIG_PPC_64K_PAGES)
 #define MAX_PHYSMEM_BITS        51
-#elif defined(CONFIG_SPARSEMEM)
+#elif defined(CONFIG_PPC64)
 #define MAX_PHYSMEM_BITS        46
 #endif
 

arch/powerpc/kernel/exceptions-64s.S

@@ -656,11 +656,17 @@ EXC_COMMON_BEGIN(data_access_slb_common)
 	ld	r4,PACA_EXSLB+EX_DAR(r13)
 	std	r4,_DAR(r1)
 	addi	r3,r1,STACK_FRAME_OVERHEAD
+BEGIN_MMU_FTR_SECTION
+	/* HPT case, do SLB fault */
 	bl	do_slb_fault
 	cmpdi	r3,0
 	bne-	1f
 	b	fast_exception_return
 1:	/* Error case */
+MMU_FTR_SECTION_ELSE
+	/* Radix case, access is outside page table range */
+	li	r3,-EFAULT
+ALT_MMU_FTR_SECTION_END_IFCLR(MMU_FTR_TYPE_RADIX)
 	std	r3,RESULT(r1)
 	bl	save_nvgprs
 	RECONCILE_IRQ_STATE(r10, r11)
@@ -705,11 +711,17 @@ EXC_COMMON_BEGIN(instruction_access_slb_common)
 	EXCEPTION_PROLOG_COMMON(0x480, PACA_EXSLB)
 	ld	r4,_NIP(r1)
 	addi	r3,r1,STACK_FRAME_OVERHEAD
+BEGIN_MMU_FTR_SECTION
+	/* HPT case, do SLB fault */
 	bl	do_slb_fault
 	cmpdi	r3,0
 	bne-	1f
 	b	fast_exception_return
 1:	/* Error case */
+MMU_FTR_SECTION_ELSE
+	/* Radix case, access is outside page table range */
+	li	r3,-EFAULT
+ALT_MMU_FTR_SECTION_END_IFCLR(MMU_FTR_TYPE_RADIX)
 	std	r3,RESULT(r1)
 	bl	save_nvgprs
 	RECONCILE_IRQ_STATE(r10, r11)

arch/powerpc/kernel/head_32.S

@@ -851,10 +851,6 @@ __secondary_start:
 	tophys(r4,r2)
 	addi	r4,r4,THREAD	/* phys address of our thread_struct */
 	mtspr	SPRN_SPRG_THREAD,r4
-#ifdef CONFIG_PPC_RTAS
-	li	r3,0
-	stw	r3, RTAS_SP(r4)		/* 0 => not in RTAS */
-#endif
 	lis	r4, (swapper_pg_dir - PAGE_OFFSET)@h
 	ori	r4, r4, (swapper_pg_dir - PAGE_OFFSET)@l
 	mtspr	SPRN_SPRG_PGDIR, r4
@@ -941,10 +937,6 @@ start_here:
 	tophys(r4,r2)
 	addi	r4,r4,THREAD	/* init task's THREAD */
 	mtspr	SPRN_SPRG_THREAD,r4
-#ifdef CONFIG_PPC_RTAS
-	li	r3,0
-	stw	r3, RTAS_SP(r4)		/* 0 => not in RTAS */
-#endif
 	lis	r4, (swapper_pg_dir - PAGE_OFFSET)@h
 	ori	r4, r4, (swapper_pg_dir - PAGE_OFFSET)@l
 	mtspr	SPRN_SPRG_PGDIR, r4

arch/powerpc/kernel/vdso32/gettimeofday.S

@@ -98,7 +98,7 @@ V_FUNCTION_BEGIN(__kernel_clock_gettime)
 	 * can be used, r7 contains NSEC_PER_SEC.
 	 */
 
-	lwz	r5,WTOM_CLOCK_SEC(r9)
+	lwz	r5,(WTOM_CLOCK_SEC+LOPART)(r9)
 	lwz	r6,WTOM_CLOCK_NSEC(r9)
 
 	/* We now have our offset in r5,r6. We create a fake dependency

arch/riscv/configs/rv32_defconfig

@@ -0,0 +1,84 @@
+CONFIG_SYSVIPC=y
+CONFIG_POSIX_MQUEUE=y
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
+CONFIG_CGROUPS=y
+CONFIG_CGROUP_SCHED=y
+CONFIG_CFS_BANDWIDTH=y
+CONFIG_CGROUP_BPF=y
+CONFIG_NAMESPACES=y
+CONFIG_USER_NS=y
+CONFIG_CHECKPOINT_RESTORE=y
+CONFIG_BLK_DEV_INITRD=y
+CONFIG_EXPERT=y
+CONFIG_BPF_SYSCALL=y
+CONFIG_ARCH_RV32I=y
+CONFIG_SMP=y
+CONFIG_MODULES=y
+CONFIG_MODULE_UNLOAD=y
+CONFIG_NET=y
+CONFIG_PACKET=y
+CONFIG_UNIX=y
+CONFIG_INET=y
+CONFIG_IP_MULTICAST=y
+CONFIG_IP_ADVANCED_ROUTER=y
+CONFIG_IP_PNP=y
+CONFIG_IP_PNP_DHCP=y
+CONFIG_IP_PNP_BOOTP=y
+CONFIG_IP_PNP_RARP=y
+CONFIG_NETLINK_DIAG=y
+CONFIG_PCI=y
+CONFIG_PCIEPORTBUS=y
+CONFIG_PCI_HOST_GENERIC=y
+CONFIG_PCIE_XILINX=y
+CONFIG_DEVTMPFS=y
+CONFIG_BLK_DEV_LOOP=y
+CONFIG_VIRTIO_BLK=y
+CONFIG_BLK_DEV_SD=y
+CONFIG_BLK_DEV_SR=y
+CONFIG_ATA=y
+CONFIG_SATA_AHCI=y
+CONFIG_SATA_AHCI_PLATFORM=y
+CONFIG_NETDEVICES=y
+CONFIG_VIRTIO_NET=y
+CONFIG_MACB=y
+CONFIG_E1000E=y
+CONFIG_R8169=y
+CONFIG_MICROSEMI_PHY=y
+CONFIG_INPUT_MOUSEDEV=y
+CONFIG_SERIAL_8250=y
+CONFIG_SERIAL_8250_CONSOLE=y
+CONFIG_SERIAL_OF_PLATFORM=y
+CONFIG_SERIAL_EARLYCON_RISCV_SBI=y
+CONFIG_HVC_RISCV_SBI=y
+# CONFIG_PTP_1588_CLOCK is not set
+CONFIG_DRM=y
+CONFIG_DRM_RADEON=y
+CONFIG_FRAMEBUFFER_CONSOLE=y
+CONFIG_USB=y
+CONFIG_USB_XHCI_HCD=y
+CONFIG_USB_XHCI_PLATFORM=y
+CONFIG_USB_EHCI_HCD=y
+CONFIG_USB_EHCI_HCD_PLATFORM=y
+CONFIG_USB_OHCI_HCD=y
+CONFIG_USB_OHCI_HCD_PLATFORM=y
+CONFIG_USB_STORAGE=y
+CONFIG_USB_UAS=y
+CONFIG_VIRTIO_MMIO=y
+CONFIG_SIFIVE_PLIC=y
+CONFIG_EXT4_FS=y
+CONFIG_EXT4_FS_POSIX_ACL=y
+CONFIG_AUTOFS4_FS=y
+CONFIG_MSDOS_FS=y
+CONFIG_VFAT_FS=y
+CONFIG_TMPFS=y
+CONFIG_TMPFS_POSIX_ACL=y
+CONFIG_NFS_FS=y
+CONFIG_NFS_V4=y
+CONFIG_NFS_V4_1=y
+CONFIG_NFS_V4_2=y
+CONFIG_ROOT_NFS=y
+CONFIG_CRYPTO_USER_API_HASH=y
+CONFIG_CRYPTO_DEV_VIRTIO=y
+CONFIG_PRINTK_TIME=y
+# CONFIG_RCU_TRACE is not set

arch/riscv/mm/init.c

@@ -121,6 +121,14 @@ void __init setup_bootmem(void)
 			 */
 			memblock_reserve(reg->base, vmlinux_end - reg->base);
 			mem_size = min(reg->size, (phys_addr_t)-PAGE_OFFSET);
+
+			/*
+			 * Remove memblock from the end of usable area to the
+			 * end of region
+			 */
+			if (reg->base + mem_size < end)
+				memblock_remove(reg->base + mem_size,
+						end - reg->base - mem_size);
 		}
 	}
 	BUG_ON(mem_size == 0);

arch/sparc/kernel/pci_sun4v.c

@@ -73,6 +73,11 @@ static inline void iommu_batch_start(struct device *dev, unsigned long prot, uns
 	p->npages	= 0;
 }
 
+static inline bool iommu_use_atu(struct iommu *iommu, u64 mask)
+{
+	return iommu->atu && mask > DMA_BIT_MASK(32);
+}
+
 /* Interrupts must be disabled.  */
 static long iommu_batch_flush(struct iommu_batch *p, u64 mask)
 {
@@ -92,7 +97,7 @@ static long iommu_batch_flush(struct iommu_batch *p, u64 mask)
 		prot &= (HV_PCI_MAP_ATTR_READ | HV_PCI_MAP_ATTR_WRITE);
 
 	while (npages != 0) {
-		if (mask <= DMA_BIT_MASK(32) || !pbm->iommu->atu) {
+		if (!iommu_use_atu(pbm->iommu, mask)) {
 			num = pci_sun4v_iommu_map(devhandle,
 						  HV_PCI_TSBID(0, entry),
 						  npages,
@@ -179,7 +184,6 @@ static void *dma_4v_alloc_coherent(struct device *dev, size_t size,
 	unsigned long flags, order, first_page, npages, n;
 	unsigned long prot = 0;
 	struct iommu *iommu;
-	struct atu *atu;
 	struct iommu_map_table *tbl;
 	struct page *page;
 	void *ret;
@@ -205,13 +209,11 @@ static void *dma_4v_alloc_coherent(struct device *dev, size_t size,
 	memset((char *)first_page, 0, PAGE_SIZE << order);
 
 	iommu = dev->archdata.iommu;
-	atu = iommu->atu;
-
 	mask = dev->coherent_dma_mask;
-	if (mask <= DMA_BIT_MASK(32) || !atu)
+	if (!iommu_use_atu(iommu, mask))
 		tbl = &iommu->tbl;
 	else
-		tbl = &atu->tbl;
+		tbl = &iommu->atu->tbl;
 
 	entry = iommu_tbl_range_alloc(dev, tbl, npages, NULL,
 				      (unsigned long)(-1), 0);
@@ -333,7 +335,7 @@ static void dma_4v_free_coherent(struct device *dev, size_t size, void *cpu,
 	atu = iommu->atu;
 	devhandle = pbm->devhandle;
 
-	if (dvma <= DMA_BIT_MASK(32)) {
+	if (!iommu_use_atu(iommu, dvma)) {
 		tbl = &iommu->tbl;
 		iotsb_num = 0; /* we don't care for legacy iommu */
 	} else {
@@ -374,7 +376,7 @@ static dma_addr_t dma_4v_map_page(struct device *dev, struct page *page,
 	npages >>= IO_PAGE_SHIFT;
 
 	mask = *dev->dma_mask;
-	if (mask <= DMA_BIT_MASK(32))
+	if (!iommu_use_atu(iommu, mask))
 		tbl = &iommu->tbl;
 	else
 		tbl = &atu->tbl;
@@ -510,7 +512,7 @@ static int dma_4v_map_sg(struct device *dev, struct scatterlist *sglist,
 				  IO_PAGE_SIZE) >> IO_PAGE_SHIFT;
 
 	mask = *dev->dma_mask;
-	if (mask <= DMA_BIT_MASK(32))
+	if (!iommu_use_atu(iommu, mask))
 		tbl = &iommu->tbl;
 	else
 		tbl = &atu->tbl;

arch/x86/events/amd/core.c

@@ -3,10 +3,14 @@
 #include <linux/types.h>
 #include <linux/init.h>
 #include <linux/slab.h>
+#include <linux/delay.h>
 #include <asm/apicdef.h>
+#include <asm/nmi.h>
 
 #include "../perf_event.h"
 
+static DEFINE_PER_CPU(unsigned int, perf_nmi_counter);
+
 static __initconst const u64 amd_hw_cache_event_ids
 				[PERF_COUNT_HW_CACHE_MAX]
 				[PERF_COUNT_HW_CACHE_OP_MAX]
@@ -429,6 +433,132 @@ static void amd_pmu_cpu_dead(int cpu)
 	}
 }
 
+/*
+ * When a PMC counter overflows, an NMI is used to process the event and
+ * reset the counter. NMI latency can result in the counter being updated
+ * before the NMI can run, which can result in what appear to be spurious
+ * NMIs. This function is intended to wait for the NMI to run and reset
+ * the counter to avoid possible unhandled NMI messages.
+ */
+#define OVERFLOW_WAIT_COUNT	50
+
+static void amd_pmu_wait_on_overflow(int idx)
+{
+	unsigned int i;
+	u64 counter;
+
+	/*
+	 * Wait for the counter to be reset if it has overflowed. This loop
+	 * should exit very, very quickly, but just in case, don't wait
+	 * forever...
+	 */
+	for (i = 0; i < OVERFLOW_WAIT_COUNT; i++) {
+		rdmsrl(x86_pmu_event_addr(idx), counter);
+		if (counter & (1ULL << (x86_pmu.cntval_bits - 1)))
+			break;
+
+		/* Might be in IRQ context, so can't sleep */
+		udelay(1);
+	}
+}
+
+static void amd_pmu_disable_all(void)
+{
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+	int idx;
+
+	x86_pmu_disable_all();
+
+	/*
+	 * This shouldn't be called from NMI context, but add a safeguard here
+	 * to return, since if we're in NMI context we can't wait for an NMI
+	 * to reset an overflowed counter value.
+	 */
+	if (in_nmi())
+		return;
+
+	/*
+	 * Check each counter for overflow and wait for it to be reset by the
+	 * NMI if it has overflowed. This relies on the fact that all active
+	 * counters are always enabled when this function is caled and
+	 * ARCH_PERFMON_EVENTSEL_INT is always set.
+	 */
+	for (idx = 0; idx < x86_pmu.num_counters; idx++) {
+		if (!test_bit(idx, cpuc->active_mask))
+			continue;
+
+		amd_pmu_wait_on_overflow(idx);
+	}
+}
+
+static void amd_pmu_disable_event(struct perf_event *event)
+{
+	x86_pmu_disable_event(event);
+
+	/*
+	 * This can be called from NMI context (via x86_pmu_stop). The counter
+	 * may have overflowed, but either way, we'll never see it get reset
+	 * by the NMI if we're already in the NMI. And the NMI latency support
+	 * below will take care of any pending NMI that might have been
+	 * generated by the overflow.
+	 */
+	if (in_nmi())
+		return;
+
+	amd_pmu_wait_on_overflow(event->hw.idx);
+}
+
+/*
+ * Because of NMI latency, if multiple PMC counters are active or other sources
+ * of NMIs are received, the perf NMI handler can handle one or more overflowed
+ * PMC counters outside of the NMI associated with the PMC overflow. If the NMI
+ * doesn't arrive at the LAPIC in time to become a pending NMI, then the kernel
+ * back-to-back NMI support won't be active. This PMC handler needs to take into
+ * account that this can occur, otherwise this could result in unknown NMI
+ * messages being issued. Examples of this is PMC overflow while in the NMI
+ * handler when multiple PMCs are active or PMC overflow while handling some
+ * other source of an NMI.
+ *
+ * Attempt to mitigate this by using the number of active PMCs to determine
+ * whether to return NMI_HANDLED if the perf NMI handler did not handle/reset
+ * any PMCs. The per-CPU perf_nmi_counter variable is set to a minimum of the
+ * number of active PMCs or 2. The value of 2 is used in case an NMI does not
+ * arrive at the LAPIC in time to be collapsed into an already pending NMI.
+ */
+static int amd_pmu_handle_irq(struct pt_regs *regs)
+{
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+	int active, handled;
+
+	/*
+	 * Obtain the active count before calling x86_pmu_handle_irq() since
+	 * it is possible that x86_pmu_handle_irq() may make a counter
+	 * inactive (through x86_pmu_stop).
+	 */
+	active = __bitmap_weight(cpuc->active_mask, X86_PMC_IDX_MAX);
+
+	/* Process any counter overflows */
+	handled = x86_pmu_handle_irq(regs);
+
+	/*
+	 * If a counter was handled, record the number of possible remaining
+	 * NMIs that can occur.
+	 */
+	if (handled) {
+		this_cpu_write(perf_nmi_counter,
+			       min_t(unsigned int, 2, active));
+
+		return handled;
+	}
+
+	if (!this_cpu_read(perf_nmi_counter))
+		return NMI_DONE;
+
+	this_cpu_dec(perf_nmi_counter);
+
+	return NMI_HANDLED;
+}
+
 static struct event_constraint *
 amd_get_event_constraints(struct cpu_hw_events *cpuc, int idx,
 			  struct perf_event *event)
@@ -621,11 +751,11 @@ static ssize_t amd_event_sysfs_show(char *page, u64 config)
 
 static __initconst const struct x86_pmu amd_pmu = {
 	.name			= "AMD",
-	.handle_irq		= x86_pmu_handle_irq,
+	.handle_irq		= amd_pmu_handle_irq,
-	.disable_all		= x86_pmu_disable_all,
+	.disable_all		= amd_pmu_disable_all,
 	.enable_all		= x86_pmu_enable_all,
 	.enable			= x86_pmu_enable_event,
-	.disable		= x86_pmu_disable_event,
+	.disable		= amd_pmu_disable_event,
 	.hw_config		= amd_pmu_hw_config,
 	.schedule_events	= x86_schedule_events,
 	.eventsel		= MSR_K7_EVNTSEL0,
@@ -732,7 +862,7 @@ void amd_pmu_enable_virt(void)
 	cpuc->perf_ctr_virt_mask = 0;
 
 	/* Reload all events */
-	x86_pmu_disable_all();
+	amd_pmu_disable_all();
 	x86_pmu_enable_all(0);
 }
 EXPORT_SYMBOL_GPL(amd_pmu_enable_virt);
@@ -750,7 +880,7 @@ void amd_pmu_disable_virt(void)
 	cpuc->perf_ctr_virt_mask = AMD64_EVENTSEL_HOSTONLY;
 
 	/* Reload all events */
-	x86_pmu_disable_all();
+	amd_pmu_disable_all();
 	x86_pmu_enable_all(0);
 }
 EXPORT_SYMBOL_GPL(amd_pmu_disable_virt);

arch/x86/events/core.c

@@ -1349,8 +1349,9 @@ void x86_pmu_stop(struct perf_event *event, int flags)
 	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	struct hw_perf_event *hwc = &event->hw;
 
-	if (__test_and_clear_bit(hwc->idx, cpuc->active_mask)) {
+	if (test_bit(hwc->idx, cpuc->active_mask)) {
 		x86_pmu.disable(event);
+		__clear_bit(hwc->idx, cpuc->active_mask);
 		cpuc->events[hwc->idx] = NULL;
 		WARN_ON_ONCE(hwc->state & PERF_HES_STOPPED);
 		hwc->state |= PERF_HES_STOPPED;
@@ -1447,16 +1448,8 @@ int x86_pmu_handle_irq(struct pt_regs *regs)
 	apic_write(APIC_LVTPC, APIC_DM_NMI);
 
 	for (idx = 0; idx < x86_pmu.num_counters; idx++) {
-		if (!test_bit(idx, cpuc->active_mask)) {
+		if (!test_bit(idx, cpuc->active_mask))
-			/*
-			 * Though we deactivated the counter some cpus
-			 * might still deliver spurious interrupts still
-			 * in flight. Catch them:
-			 */
-			if (__test_and_clear_bit(idx, cpuc->running))
-				handled++;
 			continue;
-		}
 
 		event = cpuc->events[idx];
 

arch/x86/events/intel/core.c

@@ -3185,7 +3185,7 @@ static int intel_pmu_hw_config(struct perf_event *event)
 		return ret;
 
 	if (event->attr.precise_ip) {
-		if (!event->attr.freq) {
+		if (!(event->attr.freq || event->attr.wakeup_events)) {
 			event->hw.flags |= PERF_X86_EVENT_AUTO_RELOAD;
 			if (!(event->attr.sample_type &
 			      ~intel_pmu_large_pebs_flags(event)))
@@ -3575,6 +3575,12 @@ static void intel_pmu_cpu_starting(int cpu)
 
 	cpuc->lbr_sel = NULL;
 
+	if (x86_pmu.flags & PMU_FL_TFA) {
+		WARN_ON_ONCE(cpuc->tfa_shadow);
+		cpuc->tfa_shadow = ~0ULL;
+		intel_set_tfa(cpuc, false);
+	}
+
 	if (x86_pmu.version > 1)
 		flip_smm_bit(&x86_pmu.attr_freeze_on_smi);
 

arch/x86/include/asm/bitops.h

@@ -36,16 +36,17 @@
  * bit 0 is the LSB of addr; bit 32 is the LSB of (addr+1).
  */
 
-#define BITOP_ADDR(x) "+m" (*(volatile long *) (x))
+#define RLONG_ADDR(x)			 "m" (*(volatile long *) (x))
+#define WBYTE_ADDR(x)			"+m" (*(volatile char *) (x))
 
-#define ADDR				BITOP_ADDR(addr)
+#define ADDR				RLONG_ADDR(addr)
 
 /*
  * We do the locked ops that don't return the old value as
  * a mask operation on a byte.
  */
 #define IS_IMMEDIATE(nr)		(__builtin_constant_p(nr))
-#define CONST_MASK_ADDR(nr, addr)	BITOP_ADDR((void *)(addr) + ((nr)>>3))
+#define CONST_MASK_ADDR(nr, addr)	WBYTE_ADDR((void *)(addr) + ((nr)>>3))
 #define CONST_MASK(nr)			(1 << ((nr) & 7))
 
 /**
@@ -73,7 +74,7 @@ set_bit(long nr, volatile unsigned long *addr)
 			: "memory");
 	} else {
 		asm volatile(LOCK_PREFIX __ASM_SIZE(bts) " %1,%0"
-			: BITOP_ADDR(addr) : "Ir" (nr) : "memory");
+			: : RLONG_ADDR(addr), "Ir" (nr) : "memory");
 	}
 }
 
@@ -88,7 +89,7 @@ set_bit(long nr, volatile unsigned long *addr)
  */
 static __always_inline void __set_bit(long nr, volatile unsigned long *addr)
 {
-	asm volatile(__ASM_SIZE(bts) " %1,%0" : ADDR : "Ir" (nr) : "memory");
+	asm volatile(__ASM_SIZE(bts) " %1,%0" : : ADDR, "Ir" (nr) : "memory");
 }
 
 /**
@@ -110,8 +111,7 @@ clear_bit(long nr, volatile unsigned long *addr)
 			: "iq" ((u8)~CONST_MASK(nr)));
 	} else {
 		asm volatile(LOCK_PREFIX __ASM_SIZE(btr) " %1,%0"
-			: BITOP_ADDR(addr)
+			: : RLONG_ADDR(addr), "Ir" (nr) : "memory");
-			: "Ir" (nr));
 	}
 }
 
@@ -131,7 +131,7 @@ static __always_inline void clear_bit_unlock(long nr, volatile unsigned long *ad
 
 static __always_inline void __clear_bit(long nr, volatile unsigned long *addr)
 {
-	asm volatile(__ASM_SIZE(btr) " %1,%0" : ADDR : "Ir" (nr));
+	asm volatile(__ASM_SIZE(btr) " %1,%0" : : ADDR, "Ir" (nr) : "memory");
 }
 
 static __always_inline bool clear_bit_unlock_is_negative_byte(long nr, volatile unsigned long *addr)
@@ -139,7 +139,7 @@ static __always_inline bool clear_bit_unlock_is_negative_byte(long nr, volatile
 	bool negative;
 	asm volatile(LOCK_PREFIX "andb %2,%1"
 		CC_SET(s)
-		: CC_OUT(s) (negative), ADDR
+		: CC_OUT(s) (negative), WBYTE_ADDR(addr)
 		: "ir" ((char) ~(1 << nr)) : "memory");
 	return negative;
 }
@@ -155,13 +155,9 @@ static __always_inline bool clear_bit_unlock_is_negative_byte(long nr, volatile
  * __clear_bit() is non-atomic and implies release semantics before the memory
  * operation. It can be used for an unlock if no other CPUs can concurrently
  * modify other bits in the word.
- *
- * No memory barrier is required here, because x86 cannot reorder stores past
- * older loads. Same principle as spin_unlock.
  */
 static __always_inline void __clear_bit_unlock(long nr, volatile unsigned long *addr)
 {
-	barrier();
 	__clear_bit(nr, addr);
 }
 
@@ -176,7 +172,7 @@ static __always_inline void __clear_bit_unlock(long nr, volatile unsigned long *
  */
 static __always_inline void __change_bit(long nr, volatile unsigned long *addr)
 {
-	asm volatile(__ASM_SIZE(btc) " %1,%0" : ADDR : "Ir" (nr));
+	asm volatile(__ASM_SIZE(btc) " %1,%0" : : ADDR, "Ir" (nr) : "memory");
 }
 
 /**
@@ -196,8 +192,7 @@ static __always_inline void change_bit(long nr, volatile unsigned long *addr)
 			: "iq" ((u8)CONST_MASK(nr)));
 	} else {
 		asm volatile(LOCK_PREFIX __ASM_SIZE(btc) " %1,%0"
-			: BITOP_ADDR(addr)
+			: : RLONG_ADDR(addr), "Ir" (nr) : "memory");
-			: "Ir" (nr));
 	}
 }
 
@@ -242,8 +237,8 @@ static __always_inline bool __test_and_set_bit(long nr, volatile unsigned long *
 
 	asm(__ASM_SIZE(bts) " %2,%1"
 	    CC_SET(c)
-	    : CC_OUT(c) (oldbit), ADDR
+	    : CC_OUT(c) (oldbit)
-	    : "Ir" (nr));
+	    : ADDR, "Ir" (nr) : "memory");
 	return oldbit;
 }
 
@@ -282,8 +277,8 @@ static __always_inline bool __test_and_clear_bit(long nr, volatile unsigned long
 
 	asm volatile(__ASM_SIZE(btr) " %2,%1"
 		     CC_SET(c)
-		     : CC_OUT(c) (oldbit), ADDR
+		     : CC_OUT(c) (oldbit)
-		     : "Ir" (nr));
+		     : ADDR, "Ir" (nr) : "memory");
 	return oldbit;
 }
 
@@ -294,8 +289,8 @@ static __always_inline bool __test_and_change_bit(long nr, volatile unsigned lon
 
 	asm volatile(__ASM_SIZE(btc) " %2,%1"
 		     CC_SET(c)
-		     : CC_OUT(c) (oldbit), ADDR
+		     : CC_OUT(c) (oldbit)
-		     : "Ir" (nr) : "memory");
+		     : ADDR, "Ir" (nr) : "memory");
 
 	return oldbit;
 }
@@ -326,7 +321,7 @@ static __always_inline bool variable_test_bit(long nr, volatile const unsigned l
 	asm volatile(__ASM_SIZE(bt) " %2,%1"
 		     CC_SET(c)
 		     : CC_OUT(c) (oldbit)
-		     : "m" (*(unsigned long *)addr), "Ir" (nr));
+		     : "m" (*(unsigned long *)addr), "Ir" (nr) : "memory");
 
 	return oldbit;
 }

arch/x86/include/asm/kvm_emulate.h

@@ -226,7 +226,9 @@ struct x86_emulate_ops {
 
 	unsigned (*get_hflags)(struct x86_emulate_ctxt *ctxt);
 	void (*set_hflags)(struct x86_emulate_ctxt *ctxt, unsigned hflags);
-	int (*pre_leave_smm)(struct x86_emulate_ctxt *ctxt, u64 smbase);
+	int (*pre_leave_smm)(struct x86_emulate_ctxt *ctxt,
+			     const char *smstate);
+	void (*post_leave_smm)(struct x86_emulate_ctxt *ctxt);
 
 };
 

arch/x86/include/asm/kvm_host.h

@@ -126,7 +126,7 @@ static inline gfn_t gfn_to_index(gfn_t gfn, gfn_t base_gfn, int level)
 }
 
 #define KVM_PERMILLE_MMU_PAGES 20
-#define KVM_MIN_ALLOC_MMU_PAGES 64
+#define KVM_MIN_ALLOC_MMU_PAGES 64UL
 #define KVM_MMU_HASH_SHIFT 12
 #define KVM_NUM_MMU_PAGES (1 << KVM_MMU_HASH_SHIFT)
 #define KVM_MIN_FREE_MMU_PAGES 5
@@ -844,9 +844,9 @@ enum kvm_irqchip_mode {
 };
 
 struct kvm_arch {
-	unsigned int n_used_mmu_pages;
+	unsigned long n_used_mmu_pages;
-	unsigned int n_requested_mmu_pages;
+	unsigned long n_requested_mmu_pages;
-	unsigned int n_max_mmu_pages;
+	unsigned long n_max_mmu_pages;
 	unsigned int indirect_shadow_pages;
 	struct hlist_head mmu_page_hash[KVM_NUM_MMU_PAGES];
 	/*
@@ -1182,7 +1182,7 @@ struct kvm_x86_ops {
 
 	int (*smi_allowed)(struct kvm_vcpu *vcpu);
 	int (*pre_enter_smm)(struct kvm_vcpu *vcpu, char *smstate);
-	int (*pre_leave_smm)(struct kvm_vcpu *vcpu, u64 smbase);
+	int (*pre_leave_smm)(struct kvm_vcpu *vcpu, const char *smstate);
 	int (*enable_smi_window)(struct kvm_vcpu *vcpu);
 
 	int (*mem_enc_op)(struct kvm *kvm, void __user *argp);
@@ -1256,8 +1256,8 @@ void kvm_mmu_clear_dirty_pt_masked(struct kvm *kvm,
 				   gfn_t gfn_offset, unsigned long mask);
 void kvm_mmu_zap_all(struct kvm *kvm);
 void kvm_mmu_invalidate_mmio_sptes(struct kvm *kvm, u64 gen);
-unsigned int kvm_mmu_calculate_default_mmu_pages(struct kvm *kvm);
+unsigned long kvm_mmu_calculate_default_mmu_pages(struct kvm *kvm);
-void kvm_mmu_change_mmu_pages(struct kvm *kvm, unsigned int kvm_nr_mmu_pages);
+void kvm_mmu_change_mmu_pages(struct kvm *kvm, unsigned long kvm_nr_mmu_pages);
 
 int load_pdptrs(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, unsigned long cr3);
 bool pdptrs_changed(struct kvm_vcpu *vcpu);
@@ -1592,4 +1592,7 @@ static inline int kvm_cpu_get_apicid(int mps_cpu)
 #define put_smstate(type, buf, offset, val)                      \
 	*(type *)((buf) + (offset) - 0x7e00) = val
 
+#define GET_SMSTATE(type, buf, offset)		\
+	(*(type *)((buf) + (offset) - 0x7e00))
+
 #endif /* _ASM_X86_KVM_HOST_H */

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

@@ -146,6 +146,7 @@
 
 #define VMX_ABORT_SAVE_GUEST_MSR_FAIL        1
 #define VMX_ABORT_LOAD_HOST_PDPTE_FAIL       2
+#define VMX_ABORT_VMCS_CORRUPTED             3
 #define VMX_ABORT_LOAD_HOST_MSR_FAIL         4
 
 #endif /* _UAPIVMX_H */

arch/x86/kernel/cpu/resctrl/rdtgroup.c

@@ -2039,14 +2039,14 @@ out:
 enum rdt_param {
 	Opt_cdp,
 	Opt_cdpl2,
-	Opt_mba_mpbs,
+	Opt_mba_mbps,
 	nr__rdt_params
 };
 
 static const struct fs_parameter_spec rdt_param_specs[] = {
 	fsparam_flag("cdp",		Opt_cdp),
 	fsparam_flag("cdpl2",		Opt_cdpl2),
-	fsparam_flag("mba_mpbs",	Opt_mba_mpbs),
+	fsparam_flag("mba_MBps",	Opt_mba_mbps),
 	{}
 };
 
@@ -2072,7 +2072,7 @@ static int rdt_parse_param(struct fs_context *fc, struct fs_parameter *param)
 	case Opt_cdpl2:
 		ctx->enable_cdpl2 = true;
 		return 0;
-	case Opt_mba_mpbs:
+	case Opt_mba_mbps:
 		if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL)
 			return -EINVAL;
 		ctx->enable_mba_mbps = true;

arch/x86/kvm/emulate.c

@@ -2331,24 +2331,18 @@ static int em_lseg(struct x86_emulate_ctxt *ctxt)
 
 static int emulator_has_longmode(struct x86_emulate_ctxt *ctxt)
 {
+#ifdef CONFIG_X86_64
 	u32 eax, ebx, ecx, edx;
 
 	eax = 0x80000001;
 	ecx = 0;
 	ctxt->ops->get_cpuid(ctxt, &eax, &ebx, &ecx, &edx, false);
 	return edx & bit(X86_FEATURE_LM);
+#else
+	return false;
+#endif
 }
 
-#define GET_SMSTATE(type, smbase, offset)				  \
-	({								  \
-	 type __val;							  \
-	 int r = ctxt->ops->read_phys(ctxt, smbase + offset, &__val,      \
-				      sizeof(__val));			  \
-	 if (r != X86EMUL_CONTINUE)					  \
-		 return X86EMUL_UNHANDLEABLE;				  \
-	 __val;								  \
-	})
-
 static void rsm_set_desc_flags(struct desc_struct *desc, u32 flags)
 {
 	desc->g    = (flags >> 23) & 1;
@@ -2361,27 +2355,30 @@ static void rsm_set_desc_flags(struct desc_struct *desc, u32 flags)
 	desc->type = (flags >>  8) & 15;
 }
 
-static int rsm_load_seg_32(struct x86_emulate_ctxt *ctxt, u64 smbase, int n)
+static int rsm_load_seg_32(struct x86_emulate_ctxt *ctxt, const char *smstate,
+			   int n)
 {
 	struct desc_struct desc;
 	int offset;
 	u16 selector;
 
-	selector = GET_SMSTATE(u32, smbase, 0x7fa8 + n * 4);
+	selector = GET_SMSTATE(u32, smstate, 0x7fa8 + n * 4);
 
 	if (n < 3)
 		offset = 0x7f84 + n * 12;
 	else
 		offset = 0x7f2c + (n - 3) * 12;
 
-	set_desc_base(&desc,      GET_SMSTATE(u32, smbase, offset + 8));
+	set_desc_base(&desc,      GET_SMSTATE(u32, smstate, offset + 8));
-	set_desc_limit(&desc,     GET_SMSTATE(u32, smbase, offset + 4));
+	set_desc_limit(&desc,     GET_SMSTATE(u32, smstate, offset + 4));
-	rsm_set_desc_flags(&desc, GET_SMSTATE(u32, smbase, offset));
+	rsm_set_desc_flags(&desc, GET_SMSTATE(u32, smstate, offset));
 	ctxt->ops->set_segment(ctxt, selector, &desc, 0, n);
 	return X86EMUL_CONTINUE;
 }
 
-static int rsm_load_seg_64(struct x86_emulate_ctxt *ctxt, u64 smbase, int n)
+#ifdef CONFIG_X86_64
+static int rsm_load_seg_64(struct x86_emulate_ctxt *ctxt, const char *smstate,
+			   int n)
 {
 	struct desc_struct desc;
 	int offset;
@@ -2390,15 +2387,16 @@ static int rsm_load_seg_64(struct x86_emulate_ctxt *ctxt, u64 smbase, int n)
 
 	offset = 0x7e00 + n * 16;
 
-	selector =                GET_SMSTATE(u16, smbase, offset);
+	selector =                GET_SMSTATE(u16, smstate, offset);
-	rsm_set_desc_flags(&desc, GET_SMSTATE(u16, smbase, offset + 2) << 8);
+	rsm_set_desc_flags(&desc, GET_SMSTATE(u16, smstate, offset + 2) << 8);
-	set_desc_limit(&desc,     GET_SMSTATE(u32, smbase, offset + 4));
+	set_desc_limit(&desc,     GET_SMSTATE(u32, smstate, offset + 4));
-	set_desc_base(&desc,      GET_SMSTATE(u32, smbase, offset + 8));
+	set_desc_base(&desc,      GET_SMSTATE(u32, smstate, offset + 8));
-	base3 =                   GET_SMSTATE(u32, smbase, offset + 12);
+	base3 =                   GET_SMSTATE(u32, smstate, offset + 12);
 
 	ctxt->ops->set_segment(ctxt, selector, &desc, base3, n);
 	return X86EMUL_CONTINUE;
 }
+#endif
 
 static int rsm_enter_protected_mode(struct x86_emulate_ctxt *ctxt,
 				    u64 cr0, u64 cr3, u64 cr4)
@@ -2445,7 +2443,8 @@ static int rsm_enter_protected_mode(struct x86_emulate_ctxt *ctxt,
 	return X86EMUL_CONTINUE;
 }
 
-static int rsm_load_state_32(struct x86_emulate_ctxt *ctxt, u64 smbase)
+static int rsm_load_state_32(struct x86_emulate_ctxt *ctxt,
+			     const char *smstate)
 {
 	struct desc_struct desc;
 	struct desc_ptr dt;
@@ -2453,53 +2452,55 @@ static int rsm_load_state_32(struct x86_emulate_ctxt *ctxt, u64 smbase)
 	u32 val, cr0, cr3, cr4;
 	int i;
 
-	cr0 =                      GET_SMSTATE(u32, smbase, 0x7ffc);
+	cr0 =                      GET_SMSTATE(u32, smstate, 0x7ffc);
-	cr3 =                      GET_SMSTATE(u32, smbase, 0x7ff8);
+	cr3 =                      GET_SMSTATE(u32, smstate, 0x7ff8);
-	ctxt->eflags =             GET_SMSTATE(u32, smbase, 0x7ff4) | X86_EFLAGS_FIXED;
+	ctxt->eflags =             GET_SMSTATE(u32, smstate, 0x7ff4) | X86_EFLAGS_FIXED;
-	ctxt->_eip =               GET_SMSTATE(u32, smbase, 0x7ff0);
+	ctxt->_eip =               GET_SMSTATE(u32, smstate, 0x7ff0);
 
 	for (i = 0; i < 8; i++)
-		*reg_write(ctxt, i) = GET_SMSTATE(u32, smbase, 0x7fd0 + i * 4);
+		*reg_write(ctxt, i) = GET_SMSTATE(u32, smstate, 0x7fd0 + i * 4);
 
-	val = GET_SMSTATE(u32, smbase, 0x7fcc);
+	val = GET_SMSTATE(u32, smstate, 0x7fcc);
 	ctxt->ops->set_dr(ctxt, 6, (val & DR6_VOLATILE) | DR6_FIXED_1);
-	val = GET_SMSTATE(u32, smbase, 0x7fc8);
+	val = GET_SMSTATE(u32, smstate, 0x7fc8);
 	ctxt->ops->set_dr(ctxt, 7, (val & DR7_VOLATILE) | DR7_FIXED_1);
 
-	selector =                 GET_SMSTATE(u32, smbase, 0x7fc4);
+	selector =                 GET_SMSTATE(u32, smstate, 0x7fc4);
-	set_desc_base(&desc,       GET_SMSTATE(u32, smbase, 0x7f64));
+	set_desc_base(&desc,       GET_SMSTATE(u32, smstate, 0x7f64));
-	set_desc_limit(&desc,      GET_SMSTATE(u32, smbase, 0x7f60));
+	set_desc_limit(&desc,      GET_SMSTATE(u32, smstate, 0x7f60));
-	rsm_set_desc_flags(&desc,  GET_SMSTATE(u32, smbase, 0x7f5c));
+	rsm_set_desc_flags(&desc,  GET_SMSTATE(u32, smstate, 0x7f5c));
 	ctxt->ops->set_segment(ctxt, selector, &desc, 0, VCPU_SREG_TR);
 
-	selector =                 GET_SMSTATE(u32, smbase, 0x7fc0);
+	selector =                 GET_SMSTATE(u32, smstate, 0x7fc0);
-	set_desc_base(&desc,       GET_SMSTATE(u32, smbase, 0x7f80));
+	set_desc_base(&desc,       GET_SMSTATE(u32, smstate, 0x7f80));
-	set_desc_limit(&desc,      GET_SMSTATE(u32, smbase, 0x7f7c));
+	set_desc_limit(&desc,      GET_SMSTATE(u32, smstate, 0x7f7c));
-	rsm_set_desc_flags(&desc,  GET_SMSTATE(u32, smbase, 0x7f78));
+	rsm_set_desc_flags(&desc,  GET_SMSTATE(u32, smstate, 0x7f78));
 	ctxt->ops->set_segment(ctxt, selector, &desc, 0, VCPU_SREG_LDTR);
 
-	dt.address =               GET_SMSTATE(u32, smbase, 0x7f74);
+	dt.address =               GET_SMSTATE(u32, smstate, 0x7f74);
-	dt.size =                  GET_SMSTATE(u32, smbase, 0x7f70);
+	dt.size =                  GET_SMSTATE(u32, smstate, 0x7f70);
 	ctxt->ops->set_gdt(ctxt, &dt);
 
-	dt.address =               GET_SMSTATE(u32, smbase, 0x7f58);
+	dt.address =               GET_SMSTATE(u32, smstate, 0x7f58);
-	dt.size =                  GET_SMSTATE(u32, smbase, 0x7f54);
+	dt.size =                  GET_SMSTATE(u32, smstate, 0x7f54);
 	ctxt->ops->set_idt(ctxt, &dt);
 
 	for (i = 0; i < 6; i++) {
-		int r = rsm_load_seg_32(ctxt, smbase, i);
+		int r = rsm_load_seg_32(ctxt, smstate, i);
 		if (r != X86EMUL_CONTINUE)
 			return r;
 	}
 
-	cr4 = GET_SMSTATE(u32, smbase, 0x7f14);
+	cr4 = GET_SMSTATE(u32, smstate, 0x7f14);
 
-	ctxt->ops->set_smbase(ctxt, GET_SMSTATE(u32, smbase, 0x7ef8));
+	ctxt->ops->set_smbase(ctxt, GET_SMSTATE(u32, smstate, 0x7ef8));
 
 	return rsm_enter_protected_mode(ctxt, cr0, cr3, cr4);
 }
 
-static int rsm_load_state_64(struct x86_emulate_ctxt *ctxt, u64 smbase)
+#ifdef CONFIG_X86_64
+static int rsm_load_state_64(struct x86_emulate_ctxt *ctxt,
+			     const char *smstate)
 {
 	struct desc_struct desc;
 	struct desc_ptr dt;
@@ -2509,43 +2510,43 @@ static int rsm_load_state_64(struct x86_emulate_ctxt *ctxt, u64 smbase)
 	int i, r;
 
 	for (i = 0; i < 16; i++)
-		*reg_write(ctxt, i) = GET_SMSTATE(u64, smbase, 0x7ff8 - i * 8);
+		*reg_write(ctxt, i) = GET_SMSTATE(u64, smstate, 0x7ff8 - i * 8);
 
-	ctxt->_eip   = GET_SMSTATE(u64, smbase, 0x7f78);
+	ctxt->_eip   = GET_SMSTATE(u64, smstate, 0x7f78);
-	ctxt->eflags = GET_SMSTATE(u32, smbase, 0x7f70) | X86_EFLAGS_FIXED;
+	ctxt->eflags = GET_SMSTATE(u32, smstate, 0x7f70) | X86_EFLAGS_FIXED;
 
-	val = GET_SMSTATE(u32, smbase, 0x7f68);
+	val = GET_SMSTATE(u32, smstate, 0x7f68);
 	ctxt->ops->set_dr(ctxt, 6, (val & DR6_VOLATILE) | DR6_FIXED_1);
-	val = GET_SMSTATE(u32, smbase, 0x7f60);
+	val = GET_SMSTATE(u32, smstate, 0x7f60);
 	ctxt->ops->set_dr(ctxt, 7, (val & DR7_VOLATILE) | DR7_FIXED_1);
 
-	cr0 =                       GET_SMSTATE(u64, smbase, 0x7f58);
+	cr0 =                       GET_SMSTATE(u64, smstate, 0x7f58);
-	cr3 =                       GET_SMSTATE(u64, smbase, 0x7f50);
+	cr3 =                       GET_SMSTATE(u64, smstate, 0x7f50);
-	cr4 =                       GET_SMSTATE(u64, smbase, 0x7f48);
+	cr4 =                       GET_SMSTATE(u64, smstate, 0x7f48);
-	ctxt->ops->set_smbase(ctxt, GET_SMSTATE(u32, smbase, 0x7f00));
+	ctxt->ops->set_smbase(ctxt, GET_SMSTATE(u32, smstate, 0x7f00));
-	val =                       GET_SMSTATE(u64, smbase, 0x7ed0);
+	val =                       GET_SMSTATE(u64, smstate, 0x7ed0);
 	ctxt->ops->set_msr(ctxt, MSR_EFER, val & ~EFER_LMA);
 
-	selector =                  GET_SMSTATE(u32, smbase, 0x7e90);
+	selector =                  GET_SMSTATE(u32, smstate, 0x7e90);
-	rsm_set_desc_flags(&desc,   GET_SMSTATE(u32, smbase, 0x7e92) << 8);
+	rsm_set_desc_flags(&desc,   GET_SMSTATE(u32, smstate, 0x7e92) << 8);
-	set_desc_limit(&desc,       GET_SMSTATE(u32, smbase, 0x7e94));
+	set_desc_limit(&desc,       GET_SMSTATE(u32, smstate, 0x7e94));
-	set_desc_base(&desc,        GET_SMSTATE(u32, smbase, 0x7e98));
+	set_desc_base(&desc,        GET_SMSTATE(u32, smstate, 0x7e98));
-	base3 =                     GET_SMSTATE(u32, smbase, 0x7e9c);
+	base3 =                     GET_SMSTATE(u32, smstate, 0x7e9c);
 	ctxt->ops->set_segment(ctxt, selector, &desc, base3, VCPU_SREG_TR);
 
-	dt.size =                   GET_SMSTATE(u32, smbase, 0x7e84);
+	dt.size =                   GET_SMSTATE(u32, smstate, 0x7e84);
-	dt.address =                GET_SMSTATE(u64, smbase, 0x7e88);
+	dt.address =                GET_SMSTATE(u64, smstate, 0x7e88);
 	ctxt->ops->set_idt(ctxt, &dt);
 
-	selector =                  GET_SMSTATE(u32, smbase, 0x7e70);
+	selector =                  GET_SMSTATE(u32, smstate, 0x7e70);
-	rsm_set_desc_flags(&desc,   GET_SMSTATE(u32, smbase, 0x7e72) << 8);
+	rsm_set_desc_flags(&desc,   GET_SMSTATE(u32, smstate, 0x7e72) << 8);
-	set_desc_limit(&desc,       GET_SMSTATE(u32, smbase, 0x7e74));
+	set_desc_limit(&desc,       GET_SMSTATE(u32, smstate, 0x7e74));
-	set_desc_base(&desc,        GET_SMSTATE(u32, smbase, 0x7e78));
+	set_desc_base(&desc,        GET_SMSTATE(u32, smstate, 0x7e78));
-	base3 =                     GET_SMSTATE(u32, smbase, 0x7e7c);
+	base3 =                     GET_SMSTATE(u32, smstate, 0x7e7c);
 	ctxt->ops->set_segment(ctxt, selector, &desc, base3, VCPU_SREG_LDTR);
 
-	dt.size =                   GET_SMSTATE(u32, smbase, 0x7e64);
+	dt.size =                   GET_SMSTATE(u32, smstate, 0x7e64);
-	dt.address =                GET_SMSTATE(u64, smbase, 0x7e68);
+	dt.address =                GET_SMSTATE(u64, smstate, 0x7e68);
 	ctxt->ops->set_gdt(ctxt, &dt);
 
 	r = rsm_enter_protected_mode(ctxt, cr0, cr3, cr4);
@@ -2553,37 +2554,49 @@ static int rsm_load_state_64(struct x86_emulate_ctxt *ctxt, u64 smbase)
 		return r;
 
 	for (i = 0; i < 6; i++) {
-		r = rsm_load_seg_64(ctxt, smbase, i);
+		r = rsm_load_seg_64(ctxt, smstate, i);
 		if (r != X86EMUL_CONTINUE)
 			return r;
 	}
 
 	return X86EMUL_CONTINUE;
 }
+#endif
 
 static int em_rsm(struct x86_emulate_ctxt *ctxt)
 {
 	unsigned long cr0, cr4, efer;
+	char buf[512];
 	u64 smbase;
 	int ret;
 
 	if ((ctxt->ops->get_hflags(ctxt) & X86EMUL_SMM_MASK) == 0)
 		return emulate_ud(ctxt);
 
+	smbase = ctxt->ops->get_smbase(ctxt);
+
+	ret = ctxt->ops->read_phys(ctxt, smbase + 0xfe00, buf, sizeof(buf));
+	if (ret != X86EMUL_CONTINUE)
+		return X86EMUL_UNHANDLEABLE;
+
+	if ((ctxt->ops->get_hflags(ctxt) & X86EMUL_SMM_INSIDE_NMI_MASK) == 0)
+		ctxt->ops->set_nmi_mask(ctxt, false);
+
+	ctxt->ops->set_hflags(ctxt, ctxt->ops->get_hflags(ctxt) &
+		~(X86EMUL_SMM_INSIDE_NMI_MASK | X86EMUL_SMM_MASK));
+
 	/*
 	 * Get back to real mode, to prepare a safe state in which to load
 	 * CR0/CR3/CR4/EFER.  It's all a bit more complicated if the vCPU
 	 * supports long mode.
 	 */
-	cr4 = ctxt->ops->get_cr(ctxt, 4);
 	if (emulator_has_longmode(ctxt)) {
 		struct desc_struct cs_desc;
 
 		/* Zero CR4.PCIDE before CR0.PG.  */
-		if (cr4 & X86_CR4_PCIDE) {
+		cr4 = ctxt->ops->get_cr(ctxt, 4);
+		if (cr4 & X86_CR4_PCIDE)
 			ctxt->ops->set_cr(ctxt, 4, cr4 & ~X86_CR4_PCIDE);
-			cr4 &= ~X86_CR4_PCIDE;
-		}
 
 		/* A 32-bit code segment is required to clear EFER.LMA.  */
 		memset(&cs_desc, 0, sizeof(cs_desc));
@@ -2597,39 +2610,39 @@ static int em_rsm(struct x86_emulate_ctxt *ctxt)
 	if (cr0 & X86_CR0_PE)
 		ctxt->ops->set_cr(ctxt, 0, cr0 & ~(X86_CR0_PG | X86_CR0_PE));
 
-	/* Now clear CR4.PAE (which must be done before clearing EFER.LME).  */
+	if (emulator_has_longmode(ctxt)) {
-	if (cr4 & X86_CR4_PAE)
+		/* Clear CR4.PAE before clearing EFER.LME. */
-		ctxt->ops->set_cr(ctxt, 4, cr4 & ~X86_CR4_PAE);
+		cr4 = ctxt->ops->get_cr(ctxt, 4);
+		if (cr4 & X86_CR4_PAE)
+			ctxt->ops->set_cr(ctxt, 4, cr4 & ~X86_CR4_PAE);
 
-	/* And finally go back to 32-bit mode.  */
+		/* And finally go back to 32-bit mode.  */
-	efer = 0;
+		efer = 0;
-	ctxt->ops->set_msr(ctxt, MSR_EFER, efer);
+		ctxt->ops->set_msr(ctxt, MSR_EFER, efer);
-
+	}
-	smbase = ctxt->ops->get_smbase(ctxt);
 
 	/*
 	 * Give pre_leave_smm() a chance to make ISA-specific changes to the
 	 * vCPU state (e.g. enter guest mode) before loading state from the SMM
 	 * state-save area.
 	 */
-	if (ctxt->ops->pre_leave_smm(ctxt, smbase))
+	if (ctxt->ops->pre_leave_smm(ctxt, buf))
 		return X86EMUL_UNHANDLEABLE;
 
+#ifdef CONFIG_X86_64
 	if (emulator_has_longmode(ctxt))
-		ret = rsm_load_state_64(ctxt, smbase + 0x8000);
+		ret = rsm_load_state_64(ctxt, buf);
 	else
-		ret = rsm_load_state_32(ctxt, smbase + 0x8000);
+#endif
+		ret = rsm_load_state_32(ctxt, buf);
 
 	if (ret != X86EMUL_CONTINUE) {
 		/* FIXME: should triple fault */
 		return X86EMUL_UNHANDLEABLE;
 	}
 
-	if ((ctxt->ops->get_hflags(ctxt) & X86EMUL_SMM_INSIDE_NMI_MASK) == 0)
+	ctxt->ops->post_leave_smm(ctxt);
-		ctxt->ops->set_nmi_mask(ctxt, false);
 
-	ctxt->ops->set_hflags(ctxt, ctxt->ops->get_hflags(ctxt) &
-		~(X86EMUL_SMM_INSIDE_NMI_MASK | X86EMUL_SMM_MASK));
 	return X86EMUL_CONTINUE;
 }
 

arch/x86/kvm/lapic.c

@@ -138,6 +138,7 @@ static inline bool kvm_apic_map_get_logical_dest(struct kvm_apic_map *map,
 		if (offset <= max_apic_id) {
 			u8 cluster_size = min(max_apic_id - offset + 1, 16U);
 
+			offset = array_index_nospec(offset, map->max_apic_id + 1);
 			*cluster = &map->phys_map[offset];
 			*mask = dest_id & (0xffff >> (16 - cluster_size));
 		} else {
@@ -901,7 +902,8 @@ static inline bool kvm_apic_map_get_dest_lapic(struct kvm *kvm,
 		if (irq->dest_id > map->max_apic_id) {
 			*bitmap = 0;
 		} else {
-			*dst = &map->phys_map[irq->dest_id];
+			u32 dest_id = array_index_nospec(irq->dest_id, map->max_apic_id + 1);
+			*dst = &map->phys_map[dest_id];
 			*bitmap = 1;
 		}
 		return true;

arch/x86/kvm/mmu.c

@@ -2007,7 +2007,7 @@ static int is_empty_shadow_page(u64 *spt)
  * aggregate version in order to make the slab shrinker
  * faster
  */
-static inline void kvm_mod_used_mmu_pages(struct kvm *kvm, int nr)
+static inline void kvm_mod_used_mmu_pages(struct kvm *kvm, unsigned long nr)
 {
 	kvm->arch.n_used_mmu_pages += nr;
 	percpu_counter_add(&kvm_total_used_mmu_pages, nr);
@@ -2238,7 +2238,7 @@ static bool kvm_mmu_remote_flush_or_zap(struct kvm *kvm,
 					struct list_head *invalid_list,
 					bool remote_flush)
 {
-	if (!remote_flush && !list_empty(invalid_list))
+	if (!remote_flush && list_empty(invalid_list))
 		return false;
 
 	if (!list_empty(invalid_list))
@@ -2763,7 +2763,7 @@ static bool prepare_zap_oldest_mmu_page(struct kvm *kvm,
  * Changing the number of mmu pages allocated to the vm
  * Note: if goal_nr_mmu_pages is too small, you will get dead lock
  */
-void kvm_mmu_change_mmu_pages(struct kvm *kvm, unsigned int goal_nr_mmu_pages)
+void kvm_mmu_change_mmu_pages(struct kvm *kvm, unsigned long goal_nr_mmu_pages)
 {
 	LIST_HEAD(invalid_list);
 
@@ -6031,10 +6031,10 @@ out:
 /*
  * Calculate mmu pages needed for kvm.
  */
-unsigned int kvm_mmu_calculate_default_mmu_pages(struct kvm *kvm)
+unsigned long kvm_mmu_calculate_default_mmu_pages(struct kvm *kvm)
 {
-	unsigned int nr_mmu_pages;
+	unsigned long nr_mmu_pages;
-	unsigned int  nr_pages = 0;
+	unsigned long nr_pages = 0;
 	struct kvm_memslots *slots;
 	struct kvm_memory_slot *memslot;
 	int i;
@@ -6047,8 +6047,7 @@ unsigned int kvm_mmu_calculate_default_mmu_pages(struct kvm *kvm)
 	}
 
 	nr_mmu_pages = nr_pages * KVM_PERMILLE_MMU_PAGES / 1000;
-	nr_mmu_pages = max(nr_mmu_pages,
+	nr_mmu_pages = max(nr_mmu_pages, KVM_MIN_ALLOC_MMU_PAGES);
-			   (unsigned int) KVM_MIN_ALLOC_MMU_PAGES);
 
 	return nr_mmu_pages;
 }

arch/x86/kvm/mmu.h

@@ -64,7 +64,7 @@ bool kvm_can_do_async_pf(struct kvm_vcpu *vcpu);
 int kvm_handle_page_fault(struct kvm_vcpu *vcpu, u64 error_code,
 				u64 fault_address, char *insn, int insn_len);
 
-static inline unsigned int kvm_mmu_available_pages(struct kvm *kvm)
+static inline unsigned long kvm_mmu_available_pages(struct kvm *kvm)
 {
 	if (kvm->arch.n_max_mmu_pages > kvm->arch.n_used_mmu_pages)
 		return kvm->arch.n_max_mmu_pages -

arch/x86/kvm/pmu.c

@@ -281,9 +281,13 @@ static int kvm_pmu_rdpmc_vmware(struct kvm_vcpu *vcpu, unsigned idx, u64 *data)
 int kvm_pmu_rdpmc(struct kvm_vcpu *vcpu, unsigned idx, u64 *data)
 {
 	bool fast_mode = idx & (1u << 31);
+	struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
 	struct kvm_pmc *pmc;
 	u64 ctr_val;
 
+	if (!pmu->version)
+		return 1;
+
 	if (is_vmware_backdoor_pmc(idx))
 		return kvm_pmu_rdpmc_vmware(vcpu, idx, data);
 

arch/x86/kvm/svm.c

@@ -262,6 +262,7 @@ struct amd_svm_iommu_ir {
 };
 
 #define AVIC_LOGICAL_ID_ENTRY_GUEST_PHYSICAL_ID_MASK	(0xFF)
+#define AVIC_LOGICAL_ID_ENTRY_VALID_BIT			31
 #define AVIC_LOGICAL_ID_ENTRY_VALID_MASK		(1 << 31)
 
 #define AVIC_PHYSICAL_ID_ENTRY_HOST_PHYSICAL_ID_MASK	(0xFFULL)
@@ -2692,6 +2693,7 @@ static int npf_interception(struct vcpu_svm *svm)
 static int db_interception(struct vcpu_svm *svm)
 {
 	struct kvm_run *kvm_run = svm->vcpu.run;
+	struct kvm_vcpu *vcpu = &svm->vcpu;
 
 	if (!(svm->vcpu.guest_debug &
 	      (KVM_GUESTDBG_SINGLESTEP | KVM_GUESTDBG_USE_HW_BP)) &&
@@ -2702,6 +2704,8 @@ static int db_interception(struct vcpu_svm *svm)
 
 	if (svm->nmi_singlestep) {
 		disable_nmi_singlestep(svm);
+		/* Make sure we check for pending NMIs upon entry */
+		kvm_make_request(KVM_REQ_EVENT, vcpu);
 	}
 
 	if (svm->vcpu.guest_debug &
@@ -4517,14 +4521,25 @@ static int avic_incomplete_ipi_interception(struct vcpu_svm *svm)
 		kvm_lapic_reg_write(apic, APIC_ICR, icrl);
 		break;
 	case AVIC_IPI_FAILURE_TARGET_NOT_RUNNING: {
+		int i;
+		struct kvm_vcpu *vcpu;
+		struct kvm *kvm = svm->vcpu.kvm;
 		struct kvm_lapic *apic = svm->vcpu.arch.apic;
 
 		/*
-		 * Update ICR high and low, then emulate sending IPI,
+		 * At this point, we expect that the AVIC HW has already
-		 * which is handled when writing APIC_ICR.
+		 * set the appropriate IRR bits on the valid target
+		 * vcpus. So, we just need to kick the appropriate vcpu.
 		 */
-		kvm_lapic_reg_write(apic, APIC_ICR2, icrh);
+		kvm_for_each_vcpu(i, vcpu, kvm) {
-		kvm_lapic_reg_write(apic, APIC_ICR, icrl);
+			bool m = kvm_apic_match_dest(vcpu, apic,
+						     icrl & KVM_APIC_SHORT_MASK,
+						     GET_APIC_DEST_FIELD(icrh),
+						     icrl & KVM_APIC_DEST_MASK);
+
+			if (m && !avic_vcpu_is_running(vcpu))
+				kvm_vcpu_wake_up(vcpu);
+		}
 		break;
 	}
 	case AVIC_IPI_FAILURE_INVALID_TARGET:
@@ -4596,7 +4611,7 @@ static void avic_invalidate_logical_id_entry(struct kvm_vcpu *vcpu)
 	u32 *entry = avic_get_logical_id_entry(vcpu, svm->ldr_reg, flat);
 
 	if (entry)
-		WRITE_ONCE(*entry, (u32) ~AVIC_LOGICAL_ID_ENTRY_VALID_MASK);
+		clear_bit(AVIC_LOGICAL_ID_ENTRY_VALID_BIT, (unsigned long *)entry);
 }
 
 static int avic_handle_ldr_update(struct kvm_vcpu *vcpu)
@@ -5621,6 +5636,7 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu)
 	svm->vmcb->save.cr2 = vcpu->arch.cr2;
 
 	clgi();
+	kvm_load_guest_xcr0(vcpu);
 
 	/*
 	 * If this vCPU has touched SPEC_CTRL, restore the guest's value if
@@ -5766,6 +5782,7 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu)
 	if (unlikely(svm->vmcb->control.exit_code == SVM_EXIT_NMI))
 		kvm_before_interrupt(&svm->vcpu);
 
+	kvm_put_guest_xcr0(vcpu);
 	stgi();
 
 	/* Any pending NMI will happen here */
@@ -6215,32 +6232,24 @@ static int svm_pre_enter_smm(struct kvm_vcpu *vcpu, char *smstate)
 	return 0;
 }
 
-static int svm_pre_leave_smm(struct kvm_vcpu *vcpu, u64 smbase)
+static int svm_pre_leave_smm(struct kvm_vcpu *vcpu, const char *smstate)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
 	struct vmcb *nested_vmcb;
 	struct page *page;
-	struct {
+	u64 guest;
-		u64 guest;
+	u64 vmcb;
-		u64 vmcb;
-	} svm_state_save;
-	int ret;
 
-	ret = kvm_vcpu_read_guest(vcpu, smbase + 0xfed8, &svm_state_save,
+	guest = GET_SMSTATE(u64, smstate, 0x7ed8);
-				  sizeof(svm_state_save));
+	vmcb = GET_SMSTATE(u64, smstate, 0x7ee0);
-	if (ret)
-		return ret;
 
-	if (svm_state_save.guest) {
+	if (guest) {
-		vcpu->arch.hflags &= ~HF_SMM_MASK;
+		nested_vmcb = nested_svm_map(svm, vmcb, &page);
-		nested_vmcb = nested_svm_map(svm, svm_state_save.vmcb, &page);
+		if (!nested_vmcb)
-		if (nested_vmcb)
+			return 1;
-			enter_svm_guest_mode(svm, svm_state_save.vmcb, nested_vmcb, page);
+		enter_svm_guest_mode(svm, vmcb, nested_vmcb, page);
-		else
-			ret = 1;
-		vcpu->arch.hflags |= HF_SMM_MASK;
 	}
-	return ret;
+	return 0;
 }
 
 static int enable_smi_window(struct kvm_vcpu *vcpu)

arch/x86/kvm/trace.h

@@ -438,13 +438,13 @@ TRACE_EVENT(kvm_apic_ipi,
 );
 
 TRACE_EVENT(kvm_apic_accept_irq,
-	    TP_PROTO(__u32 apicid, __u16 dm, __u8 tm, __u8 vec),
+	    TP_PROTO(__u32 apicid, __u16 dm, __u16 tm, __u8 vec),
 	    TP_ARGS(apicid, dm, tm, vec),
 
 	TP_STRUCT__entry(
 		__field(	__u32,		apicid		)
 		__field(	__u16,		dm		)
-		__field(	__u8,		tm		)
+		__field(	__u16,		tm		)
 		__field(	__u8,		vec		)
 	),
 

arch/x86/kvm/vmx/nested.c

@@ -2873,20 +2873,27 @@ static void nested_get_vmcs12_pages(struct kvm_vcpu *vcpu)
 		/*
 		 * If translation failed, VM entry will fail because
 		 * prepare_vmcs02 set VIRTUAL_APIC_PAGE_ADDR to -1ull.
-		 * Failing the vm entry is _not_ what the processor
-		 * does but it's basically the only possibility we
-		 * have.  We could still enter the guest if CR8 load
-		 * exits are enabled, CR8 store exits are enabled, and
-		 * virtualize APIC access is disabled; in this case
-		 * the processor would never use the TPR shadow and we
-		 * could simply clear the bit from the execution
-		 * control.  But such a configuration is useless, so
-		 * let's keep the code simple.
 		 */
 		if (!is_error_page(page)) {
 			vmx->nested.virtual_apic_page = page;
 			hpa = page_to_phys(vmx->nested.virtual_apic_page);
 			vmcs_write64(VIRTUAL_APIC_PAGE_ADDR, hpa);
+		} else if (nested_cpu_has(vmcs12, CPU_BASED_CR8_LOAD_EXITING) &&
+		           nested_cpu_has(vmcs12, CPU_BASED_CR8_STORE_EXITING) &&
+			   !nested_cpu_has2(vmcs12, SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES)) {
+			/*
+			 * The processor will never use the TPR shadow, simply
+			 * clear the bit from the execution control.  Such a
+			 * configuration is useless, but it happens in tests.
+			 * For any other configuration, failing the vm entry is
+			 * _not_ what the processor does but it's basically the
+			 * only possibility we have.
+			 */
+			vmcs_clear_bits(CPU_BASED_VM_EXEC_CONTROL,
+					CPU_BASED_TPR_SHADOW);
+		} else {
+			printk("bad virtual-APIC page address\n");
+			dump_vmcs();
 		}
 	}
 
@@ -3789,8 +3796,18 @@ static void nested_vmx_restore_host_state(struct kvm_vcpu *vcpu)
 	vmx_set_cr4(vcpu, vmcs_readl(CR4_READ_SHADOW));
 
 	nested_ept_uninit_mmu_context(vcpu);
-	vcpu->arch.cr3 = vmcs_readl(GUEST_CR3);
+
-	__set_bit(VCPU_EXREG_CR3, (ulong *)&vcpu->arch.regs_avail);
+	/*
+	 * This is only valid if EPT is in use, otherwise the vmcs01 GUEST_CR3
+	 * points to shadow pages!  Fortunately we only get here after a WARN_ON
+	 * if EPT is disabled, so a VMabort is perfectly fine.
+	 */
+	if (enable_ept) {
+		vcpu->arch.cr3 = vmcs_readl(GUEST_CR3);
+		__set_bit(VCPU_EXREG_CR3, (ulong *)&vcpu->arch.regs_avail);
+	} else {
+		nested_vmx_abort(vcpu, VMX_ABORT_VMCS_CORRUPTED);
+	}
 
 	/*
 	 * Use ept_save_pdptrs(vcpu) to load the MMU's cached PDPTRs
@@ -5738,6 +5755,14 @@ __init int nested_vmx_hardware_setup(int (*exit_handlers[])(struct kvm_vcpu *))
 {
 	int i;
 
+	/*
+	 * Without EPT it is not possible to restore L1's CR3 and PDPTR on
+	 * VMfail, because they are not available in vmcs01.  Just always
+	 * use hardware checks.
+	 */
+	if (!enable_ept)
+		nested_early_check = 1;
+
 	if (!cpu_has_vmx_shadow_vmcs())
 		enable_shadow_vmcs = 0;
 	if (enable_shadow_vmcs) {

arch/x86/kvm/vmx/vmx.c

@@ -5603,7 +5603,7 @@ static void vmx_dump_dtsel(char *name, uint32_t limit)
 	       vmcs_readl(limit + GUEST_GDTR_BASE - GUEST_GDTR_LIMIT));
 }
 
-static void dump_vmcs(void)
+void dump_vmcs(void)
 {
 	u32 vmentry_ctl = vmcs_read32(VM_ENTRY_CONTROLS);
 	u32 vmexit_ctl = vmcs_read32(VM_EXIT_CONTROLS);
@@ -6410,6 +6410,8 @@ static void vmx_vcpu_run(struct kvm_vcpu *vcpu)
 	if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP)
 		vmx_set_interrupt_shadow(vcpu, 0);
 
+	kvm_load_guest_xcr0(vcpu);
+
 	if (static_cpu_has(X86_FEATURE_PKU) &&
 	    kvm_read_cr4_bits(vcpu, X86_CR4_PKE) &&
 	    vcpu->arch.pkru != vmx->host_pkru)
@@ -6506,6 +6508,8 @@ static void vmx_vcpu_run(struct kvm_vcpu *vcpu)
 			__write_pkru(vmx->host_pkru);
 	}
 
+	kvm_put_guest_xcr0(vcpu);
+
 	vmx->nested.nested_run_pending = 0;
 	vmx->idt_vectoring_info = 0;
 
@@ -6852,6 +6856,30 @@ static void nested_vmx_entry_exit_ctls_update(struct kvm_vcpu *vcpu)
 	}
 }
 
+static bool guest_cpuid_has_pmu(struct kvm_vcpu *vcpu)
+{
+	struct kvm_cpuid_entry2 *entry;
+	union cpuid10_eax eax;
+
+	entry = kvm_find_cpuid_entry(vcpu, 0xa, 0);
+	if (!entry)
+		return false;
+
+	eax.full = entry->eax;
+	return (eax.split.version_id > 0);
+}
+
+static void nested_vmx_procbased_ctls_update(struct kvm_vcpu *vcpu)
+{
+	struct vcpu_vmx *vmx = to_vmx(vcpu);
+	bool pmu_enabled = guest_cpuid_has_pmu(vcpu);
+
+	if (pmu_enabled)
+		vmx->nested.msrs.procbased_ctls_high |= CPU_BASED_RDPMC_EXITING;
+	else
+		vmx->nested.msrs.procbased_ctls_high &= ~CPU_BASED_RDPMC_EXITING;
+}
+
 static void update_intel_pt_cfg(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
@@ -6940,6 +6968,7 @@ static void vmx_cpuid_update(struct kvm_vcpu *vcpu)
 	if (nested_vmx_allowed(vcpu)) {
 		nested_vmx_cr_fixed1_bits_update(vcpu);
 		nested_vmx_entry_exit_ctls_update(vcpu);
+		nested_vmx_procbased_ctls_update(vcpu);
 	}
 
 	if (boot_cpu_has(X86_FEATURE_INTEL_PT) &&
@@ -7369,7 +7398,7 @@ static int vmx_pre_enter_smm(struct kvm_vcpu *vcpu, char *smstate)
 	return 0;
 }
 
-static int vmx_pre_leave_smm(struct kvm_vcpu *vcpu, u64 smbase)
+static int vmx_pre_leave_smm(struct kvm_vcpu *vcpu, const char *smstate)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
 	int ret;
@@ -7380,9 +7409,7 @@ static int vmx_pre_leave_smm(struct kvm_vcpu *vcpu, u64 smbase)
 	}
 
 	if (vmx->nested.smm.guest_mode) {
-		vcpu->arch.hflags &= ~HF_SMM_MASK;
 		ret = nested_vmx_enter_non_root_mode(vcpu, false);
-		vcpu->arch.hflags |= HF_SMM_MASK;
 		if (ret)
 			return ret;
 

arch/x86/kvm/vmx/vmx.h

@@ -517,4 +517,6 @@ static inline void decache_tsc_multiplier(struct vcpu_vmx *vmx)
 	vmcs_write64(TSC_MULTIPLIER, vmx->current_tsc_ratio);
 }
 
+void dump_vmcs(void);
+
 #endif /* __KVM_X86_VMX_H */

arch/x86/kvm/x86.c

@@ -800,7 +800,7 @@ void kvm_lmsw(struct kvm_vcpu *vcpu, unsigned long msw)
 }
 EXPORT_SYMBOL_GPL(kvm_lmsw);
 
-static void kvm_load_guest_xcr0(struct kvm_vcpu *vcpu)
+void kvm_load_guest_xcr0(struct kvm_vcpu *vcpu)
 {
 	if (kvm_read_cr4_bits(vcpu, X86_CR4_OSXSAVE) &&
 			!vcpu->guest_xcr0_loaded) {
@@ -810,8 +810,9 @@ static void kvm_load_guest_xcr0(struct kvm_vcpu *vcpu)
 		vcpu->guest_xcr0_loaded = 1;
 	}
 }
+EXPORT_SYMBOL_GPL(kvm_load_guest_xcr0);
 
-static void kvm_put_guest_xcr0(struct kvm_vcpu *vcpu)
+void kvm_put_guest_xcr0(struct kvm_vcpu *vcpu)
 {
 	if (vcpu->guest_xcr0_loaded) {
 		if (vcpu->arch.xcr0 != host_xcr0)
@@ -819,6 +820,7 @@ static void kvm_put_guest_xcr0(struct kvm_vcpu *vcpu)
 		vcpu->guest_xcr0_loaded = 0;
 	}
 }
+EXPORT_SYMBOL_GPL(kvm_put_guest_xcr0);
 
 static int __kvm_set_xcr(struct kvm_vcpu *vcpu, u32 index, u64 xcr)
 {
@@ -3093,7 +3095,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 		break;
 	case KVM_CAP_NESTED_STATE:
 		r = kvm_x86_ops->get_nested_state ?
-			kvm_x86_ops->get_nested_state(NULL, 0, 0) : 0;
+			kvm_x86_ops->get_nested_state(NULL, NULL, 0) : 0;
 		break;
 	default:
 		break;
@@ -3528,7 +3530,7 @@ static void kvm_vcpu_ioctl_x86_get_vcpu_events(struct kvm_vcpu *vcpu,
 	memset(&events->reserved, 0, sizeof(events->reserved));
 }
 
-static void kvm_set_hflags(struct kvm_vcpu *vcpu, unsigned emul_flags);
+static void kvm_smm_changed(struct kvm_vcpu *vcpu);
 
 static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *vcpu,
 					      struct kvm_vcpu_events *events)
@@ -3588,12 +3590,13 @@ static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *vcpu,
 		vcpu->arch.apic->sipi_vector = events->sipi_vector;
 
 	if (events->flags & KVM_VCPUEVENT_VALID_SMM) {
-		u32 hflags = vcpu->arch.hflags;
+		if (!!(vcpu->arch.hflags & HF_SMM_MASK) != events->smi.smm) {
-		if (events->smi.smm)
+			if (events->smi.smm)
-			hflags |= HF_SMM_MASK;
+				vcpu->arch.hflags |= HF_SMM_MASK;
-		else
+			else
-			hflags &= ~HF_SMM_MASK;
+				vcpu->arch.hflags &= ~HF_SMM_MASK;
-		kvm_set_hflags(vcpu, hflags);
+			kvm_smm_changed(vcpu);
+		}
 
 		vcpu->arch.smi_pending = events->smi.pending;
 
@@ -4270,7 +4273,7 @@ static int kvm_vm_ioctl_set_identity_map_addr(struct kvm *kvm,
 }
 
 static int kvm_vm_ioctl_set_nr_mmu_pages(struct kvm *kvm,
-					  u32 kvm_nr_mmu_pages)
+					 unsigned long kvm_nr_mmu_pages)
 {
 	if (kvm_nr_mmu_pages < KVM_MIN_ALLOC_MMU_PAGES)
 		return -EINVAL;
@@ -4284,7 +4287,7 @@ static int kvm_vm_ioctl_set_nr_mmu_pages(struct kvm *kvm,
 	return 0;
 }
 
-static int kvm_vm_ioctl_get_nr_mmu_pages(struct kvm *kvm)
+static unsigned long kvm_vm_ioctl_get_nr_mmu_pages(struct kvm *kvm)
 {
 	return kvm->arch.n_max_mmu_pages;
 }
@@ -5958,12 +5961,18 @@ static unsigned emulator_get_hflags(struct x86_emulate_ctxt *ctxt)
 
 static void emulator_set_hflags(struct x86_emulate_ctxt *ctxt, unsigned emul_flags)
 {
-	kvm_set_hflags(emul_to_vcpu(ctxt), emul_flags);
+	emul_to_vcpu(ctxt)->arch.hflags = emul_flags;
 }
 
-static int emulator_pre_leave_smm(struct x86_emulate_ctxt *ctxt, u64 smbase)
+static int emulator_pre_leave_smm(struct x86_emulate_ctxt *ctxt,
+				  const char *smstate)
 {
-	return kvm_x86_ops->pre_leave_smm(emul_to_vcpu(ctxt), smbase);
+	return kvm_x86_ops->pre_leave_smm(emul_to_vcpu(ctxt), smstate);
+}
+
+static void emulator_post_leave_smm(struct x86_emulate_ctxt *ctxt)
+{
+	kvm_smm_changed(emul_to_vcpu(ctxt));
 }
 
 static const struct x86_emulate_ops emulate_ops = {
@@ -6006,6 +6015,7 @@ static const struct x86_emulate_ops emulate_ops = {
 	.get_hflags          = emulator_get_hflags,
 	.set_hflags          = emulator_set_hflags,
 	.pre_leave_smm       = emulator_pre_leave_smm,
+	.post_leave_smm      = emulator_post_leave_smm,
 };
 
 static void toggle_interruptibility(struct kvm_vcpu *vcpu, u32 mask)
@@ -6247,16 +6257,6 @@ static void kvm_smm_changed(struct kvm_vcpu *vcpu)
 	kvm_mmu_reset_context(vcpu);
 }
 
-static void kvm_set_hflags(struct kvm_vcpu *vcpu, unsigned emul_flags)
-{
-	unsigned changed = vcpu->arch.hflags ^ emul_flags;
-
-	vcpu->arch.hflags = emul_flags;
-
-	if (changed & HF_SMM_MASK)
-		kvm_smm_changed(vcpu);
-}
-
 static int kvm_vcpu_check_hw_bp(unsigned long addr, u32 type, u32 dr7,
 				unsigned long *db)
 {
@@ -7441,9 +7441,9 @@ static void enter_smm_save_state_32(struct kvm_vcpu *vcpu, char *buf)
 	put_smstate(u32, buf, 0x7ef8, vcpu->arch.smbase);
 }
 
+#ifdef CONFIG_X86_64
 static void enter_smm_save_state_64(struct kvm_vcpu *vcpu, char *buf)
 {
-#ifdef CONFIG_X86_64
 	struct desc_ptr dt;
 	struct kvm_segment seg;
 	unsigned long val;
@@ -7493,10 +7493,8 @@ static void enter_smm_save_state_64(struct kvm_vcpu *vcpu, char *buf)
 
 	for (i = 0; i < 6; i++)
 		enter_smm_save_seg_64(vcpu, buf, i);
-#else
-	WARN_ON_ONCE(1);
-#endif
 }
+#endif
 
 static void enter_smm(struct kvm_vcpu *vcpu)
 {
@@ -7507,9 +7505,11 @@ static void enter_smm(struct kvm_vcpu *vcpu)
 
 	trace_kvm_enter_smm(vcpu->vcpu_id, vcpu->arch.smbase, true);
 	memset(buf, 0, 512);
+#ifdef CONFIG_X86_64
 	if (guest_cpuid_has(vcpu, X86_FEATURE_LM))
 		enter_smm_save_state_64(vcpu, buf);
 	else
+#endif
 		enter_smm_save_state_32(vcpu, buf);
 
 	/*
@@ -7567,8 +7567,10 @@ static void enter_smm(struct kvm_vcpu *vcpu)
 	kvm_set_segment(vcpu, &ds, VCPU_SREG_GS);
 	kvm_set_segment(vcpu, &ds, VCPU_SREG_SS);
 
+#ifdef CONFIG_X86_64
 	if (guest_cpuid_has(vcpu, X86_FEATURE_LM))
 		kvm_x86_ops->set_efer(vcpu, 0);
+#endif
 
 	kvm_update_cpuid(vcpu);
 	kvm_mmu_reset_context(vcpu);
@@ -7865,8 +7867,6 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 		goto cancel_injection;
 	}
 
-	kvm_load_guest_xcr0(vcpu);
-
 	if (req_immediate_exit) {
 		kvm_make_request(KVM_REQ_EVENT, vcpu);
 		kvm_x86_ops->request_immediate_exit(vcpu);
@@ -7919,8 +7919,6 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 	vcpu->mode = OUTSIDE_GUEST_MODE;
 	smp_wmb();
 
-	kvm_put_guest_xcr0(vcpu);
-
 	kvm_before_interrupt(vcpu);
 	kvm_x86_ops->handle_external_intr(vcpu);
 	kvm_after_interrupt(vcpu);

arch/x86/kvm/x86.h

@@ -347,4 +347,6 @@ static inline void kvm_after_interrupt(struct kvm_vcpu *vcpu)
 	__this_cpu_write(current_vcpu, NULL);
 }
 
+void kvm_load_guest_xcr0(struct kvm_vcpu *vcpu);
+void kvm_put_guest_xcr0(struct kvm_vcpu *vcpu);
 #endif

block/bfq-iosched.c

@@ -2822,7 +2822,7 @@ static void bfq_dispatch_remove(struct request_queue *q, struct request *rq)
 	bfq_remove_request(q, rq);
 }
 
-static void __bfq_bfqq_expire(struct bfq_data *bfqd, struct bfq_queue *bfqq)
+static bool __bfq_bfqq_expire(struct bfq_data *bfqd, struct bfq_queue *bfqq)
 {
 	/*
 	 * If this bfqq is shared between multiple processes, check
@@ -2855,9 +2855,11 @@ static void __bfq_bfqq_expire(struct bfq_data *bfqd, struct bfq_queue *bfqq)
 	/*
 	 * All in-service entities must have been properly deactivated
 	 * or requeued before executing the next function, which
-	 * resets all in-service entites as no more in service.
+	 * resets all in-service entities as no more in service. This
+	 * may cause bfqq to be freed. If this happens, the next
+	 * function returns true.
 	 */
-	__bfq_bfqd_reset_in_service(bfqd);
+	return __bfq_bfqd_reset_in_service(bfqd);
 }
 
 /**
@@ -3262,7 +3264,6 @@ void bfq_bfqq_expire(struct bfq_data *bfqd,
 	bool slow;
 	unsigned long delta = 0;
 	struct bfq_entity *entity = &bfqq->entity;
-	int ref;
 
 	/*
 	 * Check whether the process is slow (see bfq_bfqq_is_slow).
@@ -3347,10 +3348,8 @@ void bfq_bfqq_expire(struct bfq_data *bfqd,
 	 * reason.
 	 */
 	__bfq_bfqq_recalc_budget(bfqd, bfqq, reason);
-	ref = bfqq->ref;
+	if (__bfq_bfqq_expire(bfqd, bfqq))
-	__bfq_bfqq_expire(bfqd, bfqq);
+		/* bfqq is gone, no more actions on it */
-
-	if (ref == 1) /* bfqq is gone, no more actions on it */
 		return;
 
 	bfqq->injected_service = 0;

block/bfq-iosched.h

@@ -995,7 +995,7 @@ bool __bfq_deactivate_entity(struct bfq_entity *entity,
 			     bool ins_into_idle_tree);
 bool next_queue_may_preempt(struct bfq_data *bfqd);
 struct bfq_queue *bfq_get_next_queue(struct bfq_data *bfqd);
-void __bfq_bfqd_reset_in_service(struct bfq_data *bfqd);
+bool __bfq_bfqd_reset_in_service(struct bfq_data *bfqd);
 void bfq_deactivate_bfqq(struct bfq_data *bfqd, struct bfq_queue *bfqq,
 			 bool ins_into_idle_tree, bool expiration);
 void bfq_activate_bfqq(struct bfq_data *bfqd, struct bfq_queue *bfqq);

block/bfq-wf2q.c

@@ -1605,7 +1605,8 @@ struct bfq_queue *bfq_get_next_queue(struct bfq_data *bfqd)
 	return bfqq;
 }
 
-void __bfq_bfqd_reset_in_service(struct bfq_data *bfqd)
+/* returns true if the in-service queue gets freed */
+bool __bfq_bfqd_reset_in_service(struct bfq_data *bfqd)
 {
 	struct bfq_queue *in_serv_bfqq = bfqd->in_service_queue;
 	struct bfq_entity *in_serv_entity = &in_serv_bfqq->entity;
@@ -1629,8 +1630,20 @@ void __bfq_bfqd_reset_in_service(struct bfq_data *bfqd)
 	 * service tree either, then release the service reference to
 	 * the queue it represents (taken with bfq_get_entity).
 	 */
-	if (!in_serv_entity->on_st)
+	if (!in_serv_entity->on_st) {
+		/*
+		 * If no process is referencing in_serv_bfqq any
+		 * longer, then the service reference may be the only
+		 * reference to the queue. If this is the case, then
+		 * bfqq gets freed here.
+		 */
+		int ref = in_serv_bfqq->ref;
 		bfq_put_queue(in_serv_bfqq);
+		if (ref == 1)
+			return true;
+	}
+
+	return false;
 }
 
 void bfq_deactivate_bfqq(struct bfq_data *bfqd, struct bfq_queue *bfqq,

block/bio.c

@@ -1298,8 +1298,11 @@ struct bio *bio_copy_user_iov(struct request_queue *q,
 			}
 		}
 
-		if (bio_add_pc_page(q, bio, page, bytes, offset) < bytes)
+		if (bio_add_pc_page(q, bio, page, bytes, offset) < bytes) {
+			if (!map_data)
+				__free_page(page);
 			break;
+		}
 
 		len -= bytes;
 		offset = 0;

block/blk-mq.c

@@ -654,6 +654,13 @@ bool blk_mq_complete_request(struct request *rq)
 }
 EXPORT_SYMBOL(blk_mq_complete_request);
 
+void blk_mq_complete_request_sync(struct request *rq)
+{
+	WRITE_ONCE(rq->state, MQ_RQ_COMPLETE);
+	rq->q->mq_ops->complete(rq);
+}
+EXPORT_SYMBOL_GPL(blk_mq_complete_request_sync);
+
 int blk_mq_request_started(struct request *rq)
 {
 	return blk_mq_rq_state(rq) != MQ_RQ_IDLE;

drivers/acpi/acpica/nsobject.c

@@ -186,6 +186,10 @@ void acpi_ns_detach_object(struct acpi_namespace_node *node)
 		}
 	}
 
+	if (obj_desc->common.type == ACPI_TYPE_REGION) {
+		acpi_ut_remove_address_range(obj_desc->region.space_id, node);
+	}
+
 	/* Clear the Node entry in all cases */
 
 	node->object = NULL;

drivers/acpi/nfit/core.c

@@ -567,6 +567,12 @@ int acpi_nfit_ctl(struct nvdimm_bus_descriptor *nd_desc, struct nvdimm *nvdimm,
 		goto out;
 	}
 
+	dev_dbg(dev, "%s cmd: %s output length: %d\n", dimm_name,
+			cmd_name, out_obj->buffer.length);
+	print_hex_dump_debug(cmd_name, DUMP_PREFIX_OFFSET, 4, 4,
+			out_obj->buffer.pointer,
+			min_t(u32, 128, out_obj->buffer.length), true);
+
 	if (call_pkg) {
 		call_pkg->nd_fw_size = out_obj->buffer.length;
 		memcpy(call_pkg->nd_payload + call_pkg->nd_size_in,
@@ -585,12 +591,6 @@ int acpi_nfit_ctl(struct nvdimm_bus_descriptor *nd_desc, struct nvdimm *nvdimm,
 		return 0;
 	}
 
-	dev_dbg(dev, "%s cmd: %s output length: %d\n", dimm_name,
-			cmd_name, out_obj->buffer.length);
-	print_hex_dump_debug(cmd_name, DUMP_PREFIX_OFFSET, 4, 4,
-			out_obj->buffer.pointer,
-			min_t(u32, 128, out_obj->buffer.length), true);
-
 	for (i = 0, offset = 0; i < desc->out_num; i++) {
 		u32 out_size = nd_cmd_out_size(nvdimm, cmd, desc, i, buf,
 				(u32 *) out_obj->buffer.pointer,

drivers/acpi/nfit/intel.c

@@ -122,9 +122,8 @@ static int intel_security_change_key(struct nvdimm *nvdimm,
 	if (!test_bit(cmd, &nfit_mem->dsm_mask))
 		return -ENOTTY;
 
-	if (old_data)
+	memcpy(nd_cmd.cmd.old_pass, old_data->data,
-		memcpy(nd_cmd.cmd.old_pass, old_data->data,
+			sizeof(nd_cmd.cmd.old_pass));
-				sizeof(nd_cmd.cmd.old_pass));
 	memcpy(nd_cmd.cmd.new_pass, new_data->data,
 			sizeof(nd_cmd.cmd.new_pass));
 	rc = nvdimm_ctl(nvdimm, ND_CMD_CALL, &nd_cmd, sizeof(nd_cmd), NULL);
@@ -336,9 +335,8 @@ static int __maybe_unused intel_security_overwrite(struct nvdimm *nvdimm,
 
 	/* flush all cache before we erase DIMM */
 	nvdimm_invalidate_cache();
-	if (nkey)
+	memcpy(nd_cmd.cmd.passphrase, nkey->data,
-		memcpy(nd_cmd.cmd.passphrase, nkey->data,
+			sizeof(nd_cmd.cmd.passphrase));
-				sizeof(nd_cmd.cmd.passphrase));
 	rc = nvdimm_ctl(nvdimm, ND_CMD_CALL, &nd_cmd, sizeof(nd_cmd), NULL);
 	if (rc < 0)
 		return rc;

drivers/block/virtio_blk.c

@@ -513,6 +513,8 @@ static int init_vq(struct virtio_blk *vblk)
 	if (err)
 		num_vqs = 1;
 
+	num_vqs = min_t(unsigned int, nr_cpu_ids, num_vqs);
+
 	vblk->vqs = kmalloc_array(num_vqs, sizeof(*vblk->vqs), GFP_KERNEL);
 	if (!vblk->vqs)
 		return -ENOMEM;

drivers/bluetooth/btusb.c

@@ -2942,6 +2942,7 @@ static int btusb_config_oob_wake(struct hci_dev *hdev)
 		return 0;
 	}
 
+	irq_set_status_flags(irq, IRQ_NOAUTOEN);
 	ret = devm_request_irq(&hdev->dev, irq, btusb_oob_wake_handler,
 			       0, "OOB Wake-on-BT", data);
 	if (ret) {
@@ -2956,7 +2957,6 @@ static int btusb_config_oob_wake(struct hci_dev *hdev)
 	}
 
 	data->oob_wake_irq = irq;
-	disable_irq(irq);
 	bt_dev_info(hdev, "OOB Wake-on-BT configured at IRQ %u", irq);
 	return 0;
 }

drivers/char/ipmi/ipmi_dmi.c

@@ -66,7 +66,6 @@ static void __init dmi_add_platform_ipmi(unsigned long base_addr,
 		return;
 	}
 
-	memset(&p, 0, sizeof(p));
 	p.addr = base_addr;
 	p.space = space;
 	p.regspacing = offset;

drivers/char/ipmi/ipmi_msghandler.c

@@ -214,6 +214,9 @@ struct ipmi_user {
 
 	/* Does this interface receive IPMI events? */
 	bool gets_events;
+
+	/* Free must run in process context for RCU cleanup. */
+	struct work_struct remove_work;
 };
 
 static struct ipmi_user *acquire_ipmi_user(struct ipmi_user *user, int *index)
@@ -1157,6 +1160,15 @@ static int intf_err_seq(struct ipmi_smi *intf,
 	return rv;
 }
 
+static void free_user_work(struct work_struct *work)
+{
+	struct ipmi_user *user = container_of(work, struct ipmi_user,
+					      remove_work);
+
+	cleanup_srcu_struct(&user->release_barrier);
+	kfree(user);
+}
+
 int ipmi_create_user(unsigned int          if_num,
 		     const struct ipmi_user_hndl *handler,
 		     void                  *handler_data,
@@ -1200,6 +1212,8 @@ int ipmi_create_user(unsigned int          if_num,
 	goto out_kfree;
 
  found:
+	INIT_WORK(&new_user->remove_work, free_user_work);
+
 	rv = init_srcu_struct(&new_user->release_barrier);
 	if (rv)
 		goto out_kfree;
@@ -1260,8 +1274,9 @@ EXPORT_SYMBOL(ipmi_get_smi_info);
 static void free_user(struct kref *ref)
 {
 	struct ipmi_user *user = container_of(ref, struct ipmi_user, refcount);
-	cleanup_srcu_struct(&user->release_barrier);
+
-	kfree(user);
+	/* SRCU cleanup must happen in task context. */
+	schedule_work(&user->remove_work);
 }
 
 static void _ipmi_destroy_user(struct ipmi_user *user)

drivers/char/ipmi/ipmi_si_hardcode.c

@@ -118,6 +118,8 @@ void __init ipmi_hardcode_init(void)
 	char *str;
 	char *si_type[SI_MAX_PARMS];
 
+	memset(si_type, 0, sizeof(si_type));
+
 	/* Parse out the si_type string into its components. */
 	str = si_type_str;
 	if (*str != '\0') {

drivers/clk/at91/clk-programmable.c

@@ -20,8 +20,7 @@
 #define PROG_ID_MAX		7
 
 #define PROG_STATUS_MASK(id)	(1 << ((id) + 8))
-#define PROG_PRES_MASK		0x7
+#define PROG_PRES(layout, pckr)	((pckr >> layout->pres_shift) & layout->pres_mask)
-#define PROG_PRES(layout, pckr)	((pckr >> layout->pres_shift) & PROG_PRES_MASK)
 #define PROG_MAX_RM9200_CSS	3
 
 struct clk_programmable {
@@ -37,20 +36,29 @@ static unsigned long clk_programmable_recalc_rate(struct clk_hw *hw,
 						  unsigned long parent_rate)
 {
 	struct clk_programmable *prog = to_clk_programmable(hw);
+	const struct clk_programmable_layout *layout = prog->layout;
 	unsigned int pckr;
+	unsigned long rate;
 
 	regmap_read(prog->regmap, AT91_PMC_PCKR(prog->id), &pckr);
 
-	return parent_rate >> PROG_PRES(prog->layout, pckr);
+	if (layout->is_pres_direct)
+		rate = parent_rate / (PROG_PRES(layout, pckr) + 1);
+	else
+		rate = parent_rate >> PROG_PRES(layout, pckr);
+
+	return rate;
 }
 
 static int clk_programmable_determine_rate(struct clk_hw *hw,
 					   struct clk_rate_request *req)
 {
+	struct clk_programmable *prog = to_clk_programmable(hw);
+	const struct clk_programmable_layout *layout = prog->layout;
 	struct clk_hw *parent;
 	long best_rate = -EINVAL;
 	unsigned long parent_rate;
-	unsigned long tmp_rate;
+	unsigned long tmp_rate = 0;
 	int shift;
 	int i;
 
@@ -60,10 +68,18 @@ static int clk_programmable_determine_rate(struct clk_hw *hw,
 			continue;
 
 		parent_rate = clk_hw_get_rate(parent);
-		for (shift = 0; shift < PROG_PRES_MASK; shift++) {
+		if (layout->is_pres_direct) {
-			tmp_rate = parent_rate >> shift;
+			for (shift = 0; shift <= layout->pres_mask; shift++) {
-			if (tmp_rate <= req->rate)
+				tmp_rate = parent_rate / (shift + 1);
-				break;
+				if (tmp_rate <= req->rate)
+					break;
+			}
+		} else {
+			for (shift = 0; shift < layout->pres_mask; shift++) {
+				tmp_rate = parent_rate >> shift;
+				if (tmp_rate <= req->rate)
+					break;
+			}
 		}
 
 		if (tmp_rate > req->rate)
@@ -137,16 +153,23 @@ static int clk_programmable_set_rate(struct clk_hw *hw, unsigned long rate,
 	if (!div)
 		return -EINVAL;
 
-	shift = fls(div) - 1;
+	if (layout->is_pres_direct) {
+		shift = div - 1;
 
-	if (div != (1 << shift))
+		if (shift > layout->pres_mask)
-		return -EINVAL;
+			return -EINVAL;
+	} else {
+		shift = fls(div) - 1;
 
-	if (shift >= PROG_PRES_MASK)
+		if (div != (1 << shift))
-		return -EINVAL;
+			return -EINVAL;
+
+		if (shift >= layout->pres_mask)
+			return -EINVAL;
+	}
 
 	regmap_update_bits(prog->regmap, AT91_PMC_PCKR(prog->id),
-			   PROG_PRES_MASK << layout->pres_shift,
+			   layout->pres_mask << layout->pres_shift,
 			   shift << layout->pres_shift);
 
 	return 0;
@@ -202,19 +225,25 @@ at91_clk_register_programmable(struct regmap *regmap,
 }
 
 const struct clk_programmable_layout at91rm9200_programmable_layout = {
+	.pres_mask = 0x7,
 	.pres_shift = 2,
 	.css_mask = 0x3,
 	.have_slck_mck = 0,
+	.is_pres_direct = 0,
 };
 
 const struct clk_programmable_layout at91sam9g45_programmable_layout = {
+	.pres_mask = 0x7,
 	.pres_shift = 2,
 	.css_mask = 0x3,
 	.have_slck_mck = 1,
+	.is_pres_direct = 0,
 };
 
 const struct clk_programmable_layout at91sam9x5_programmable_layout = {
+	.pres_mask = 0x7,
 	.pres_shift = 4,
 	.css_mask = 0x7,
 	.have_slck_mck = 0,
+	.is_pres_direct = 0,
 };

drivers/clk/at91/pmc.h

@@ -71,9 +71,11 @@ struct clk_pll_characteristics {
 };
 
 struct clk_programmable_layout {
+	u8 pres_mask;
 	u8 pres_shift;
 	u8 css_mask;
 	u8 have_slck_mck;
+	u8 is_pres_direct;
 };
 
 extern const struct clk_programmable_layout at91rm9200_programmable_layout;

drivers/clk/at91/sama5d2.c

@@ -125,6 +125,14 @@ static const struct {
 	  .pll = true },
 };
 
+static const struct clk_programmable_layout sama5d2_programmable_layout = {
+	.pres_mask = 0xff,
+	.pres_shift = 4,
+	.css_mask = 0x7,
+	.have_slck_mck = 0,
+	.is_pres_direct = 1,
+};
+
 static void __init sama5d2_pmc_setup(struct device_node *np)
 {
 	struct clk_range range = CLK_RANGE(0, 0);
@@ -249,7 +257,7 @@ static void __init sama5d2_pmc_setup(struct device_node *np)
 
 		hw = at91_clk_register_programmable(regmap, name,
 						    parent_names, 6, i,
-						    &at91sam9x5_programmable_layout);
+						    &sama5d2_programmable_layout);
 		if (IS_ERR(hw))
 			goto err_free;
 	}

drivers/clk/imx/clk-pll14xx.c

@@ -362,7 +362,7 @@ struct clk *imx_clk_pll14xx(const char *name, const char *parent_name,
 
 	switch (pll_clk->type) {
 	case PLL_1416X:
-		if (!pll->rate_table)
+		if (!pll_clk->rate_table)
 			init.ops = &clk_pll1416x_min_ops;
 		else
 			init.ops = &clk_pll1416x_ops;

drivers/clk/mediatek/clk-gate.c

@@ -169,11 +169,10 @@ struct clk *mtk_clk_register_gate(
 		return ERR_PTR(-ENOMEM);
 
 	init.name = name;
-	init.flags = CLK_SET_RATE_PARENT;
+	init.flags = flags | CLK_SET_RATE_PARENT;
 	init.parent_names = parent_name ? &parent_name : NULL;
 	init.num_parents = parent_name ? 1 : 0;
 	init.ops = ops;
-	init.flags = flags;
 
 	cg->regmap = regmap;
 	cg->set_ofs = set_ofs;

drivers/clk/meson/clk-pll.c

@@ -120,7 +120,7 @@ static bool meson_clk_pll_is_better(unsigned long rate,
 			return true;
 	} else {
 		/* Round down */
-		if (now < rate && best < now)
+		if (now <= rate && best < now)
 			return true;
 	}
 

drivers/clk/meson/g12a.c

@@ -960,14 +960,14 @@ static struct clk_regmap g12a_sd_emmc_c_clk0 = {
 /* VPU Clock */
 
 static const char * const g12a_vpu_parent_names[] = {
-	"fclk_div4", "fclk_div3", "fclk_div5", "fclk_div7",
+	"fclk_div3", "fclk_div4", "fclk_div5", "fclk_div7",
 	"mpll1", "vid_pll", "hifi_pll", "gp0_pll",
 };
 
 static struct clk_regmap g12a_vpu_0_sel = {
 	.data = &(struct clk_regmap_mux_data){
 		.offset = HHI_VPU_CLK_CNTL,
-		.mask = 0x3,
+		.mask = 0x7,
 		.shift = 9,
 	},
 	.hw.init = &(struct clk_init_data){
@@ -1011,7 +1011,7 @@ static struct clk_regmap g12a_vpu_0 = {
 static struct clk_regmap g12a_vpu_1_sel = {
 	.data = &(struct clk_regmap_mux_data){
 		.offset = HHI_VPU_CLK_CNTL,
-		.mask = 0x3,
+		.mask = 0x7,
 		.shift = 25,
 	},
 	.hw.init = &(struct clk_init_data){

drivers/clk/meson/gxbb.c

@@ -2216,6 +2216,7 @@ static struct clk_regmap gxbb_vdec_1_div = {
 		.offset = HHI_VDEC_CLK_CNTL,
 		.shift = 0,
 		.width = 7,
+		.flags = CLK_DIVIDER_ROUND_CLOSEST,
 	},
 	.hw.init = &(struct clk_init_data){
 		.name = "vdec_1_div",
@@ -2261,6 +2262,7 @@ static struct clk_regmap gxbb_vdec_hevc_div = {
 		.offset = HHI_VDEC2_CLK_CNTL,
 		.shift = 16,
 		.width = 7,
+		.flags = CLK_DIVIDER_ROUND_CLOSEST,
 	},
 	.hw.init = &(struct clk_init_data){
 		.name = "vdec_hevc_div",

drivers/clk/meson/vid-pll-div.c

@@ -82,8 +82,8 @@ static unsigned long meson_vid_pll_div_recalc_rate(struct clk_hw *hw,
 	div = _get_table_val(meson_parm_read(clk->map, &pll_div->val),
 			     meson_parm_read(clk->map, &pll_div->sel));
 	if (!div || !div->divider) {
-		pr_info("%s: Invalid config value for vid_pll_div\n", __func__);
+		pr_debug("%s: Invalid config value for vid_pll_div\n", __func__);
-		return parent_rate;
+		return 0;
 	}
 
 	return DIV_ROUND_UP_ULL(parent_rate * div->multiplier, div->divider);

drivers/clk/x86/clk-pmc-atom.c

@@ -165,7 +165,7 @@ static const struct clk_ops plt_clk_ops = {
 };
 
 static struct clk_plt *plt_clk_register(struct platform_device *pdev, int id,
-					void __iomem *base,
+					const struct pmc_clk_data *pmc_data,
 					const char **parent_names,
 					int num_parents)
 {
@@ -184,9 +184,17 @@ static struct clk_plt *plt_clk_register(struct platform_device *pdev, int id,
 	init.num_parents = num_parents;
 
 	pclk->hw.init = &init;
-	pclk->reg = base + PMC_CLK_CTL_OFFSET + id * PMC_CLK_CTL_SIZE;
+	pclk->reg = pmc_data->base + PMC_CLK_CTL_OFFSET + id * PMC_CLK_CTL_SIZE;
 	spin_lock_init(&pclk->lock);
 
+	/*
+	 * On some systems, the pmc_plt_clocks already enabled by the
+	 * firmware are being marked as critical to avoid them being
+	 * gated by the clock framework.
+	 */
+	if (pmc_data->critical && plt_clk_is_enabled(&pclk->hw))
+		init.flags |= CLK_IS_CRITICAL;
+
 	ret = devm_clk_hw_register(&pdev->dev, &pclk->hw);
 	if (ret) {
 		pclk = ERR_PTR(ret);
@@ -332,7 +340,7 @@ static int plt_clk_probe(struct platform_device *pdev)
 		return PTR_ERR(parent_names);
 
 	for (i = 0; i < PMC_CLK_NUM; i++) {
-		data->clks[i] = plt_clk_register(pdev, i, pmc_data->base,
+		data->clks[i] = plt_clk_register(pdev, i, pmc_data,
 						 parent_names, data->nparents);
 		if (IS_ERR(data->clks[i])) {
 			err = PTR_ERR(data->clks[i]);

drivers/gpu/drm/amd/amdgpu/amdgpu_device.c

@@ -3173,11 +3173,16 @@ static int amdgpu_device_recover_vram(struct amdgpu_device *adev)
 			break;
 
 		if (fence) {
-			r = dma_fence_wait_timeout(fence, false, tmo);
+			tmo = dma_fence_wait_timeout(fence, false, tmo);
 			dma_fence_put(fence);
 			fence = next;
-			if (r <= 0)
+			if (tmo == 0) {
+				r = -ETIMEDOUT;
 				break;
+			} else if (tmo < 0) {
+				r = tmo;
+				break;
+			}
 		} else {
 			fence = next;
 		}
@@ -3188,8 +3193,8 @@ static int amdgpu_device_recover_vram(struct amdgpu_device *adev)
 		tmo = dma_fence_wait_timeout(fence, false, tmo);
 	dma_fence_put(fence);
 
-	if (r <= 0 || tmo <= 0) {
+	if (r < 0 || tmo <= 0) {
-		DRM_ERROR("recover vram bo from shadow failed\n");
+		DRM_ERROR("recover vram bo from shadow failed, r is %ld, tmo is %ld\n", r, tmo);
 		return -EIO;
 	}
 

drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c

@@ -35,6 +35,7 @@
 #include "amdgpu_trace.h"
 
 #define AMDGPU_IB_TEST_TIMEOUT	msecs_to_jiffies(1000)
+#define AMDGPU_IB_TEST_GFX_XGMI_TIMEOUT	msecs_to_jiffies(2000)
 
 /*
  * IB
@@ -344,6 +345,8 @@ int amdgpu_ib_ring_tests(struct amdgpu_device *adev)
 		 * cost waiting for it coming back under RUNTIME only
 		*/
 		tmo_gfx = 8 * AMDGPU_IB_TEST_TIMEOUT;
+	} else if (adev->gmc.xgmi.hive_id) {
+		tmo_gfx = AMDGPU_IB_TEST_GFX_XGMI_TIMEOUT;
 	}
 
 	for (i = 0; i < adev->num_rings; ++i) {

drivers/gpu/drm/amd/amdkfd/kfd_device.c

@@ -320,6 +320,7 @@ static const struct kfd_deviceid supported_devices[] = {
 	{ 0x9876, &carrizo_device_info },	/* Carrizo */
 	{ 0x9877, &carrizo_device_info },	/* Carrizo */
 	{ 0x15DD, &raven_device_info },		/* Raven */
+	{ 0x15D8, &raven_device_info },		/* Raven */
 #endif
 	{ 0x67A0, &hawaii_device_info },	/* Hawaii */
 	{ 0x67A1, &hawaii_device_info },	/* Hawaii */

drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c

@@ -4533,6 +4533,7 @@ static void handle_cursor_update(struct drm_plane *plane,
 	amdgpu_crtc->cursor_width = plane->state->crtc_w;
 	amdgpu_crtc->cursor_height = plane->state->crtc_h;
 
+	memset(&attributes, 0, sizeof(attributes));
 	attributes.address.high_part = upper_32_bits(address);
 	attributes.address.low_part  = lower_32_bits(address);
 	attributes.width             = plane->state->crtc_w;

drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubp.c

@@ -1150,28 +1150,9 @@ void hubp1_cursor_set_position(
 	REG_UPDATE(CURSOR_CONTROL,
 			CURSOR_ENABLE, cur_en);
 
-	//account for cases where we see negative offset relative to overlay plane
+	REG_SET_2(CURSOR_POSITION, 0,
-	if (src_x_offset < 0 && src_y_offset < 0) {
-		REG_SET_2(CURSOR_POSITION, 0,
-			CURSOR_X_POSITION, 0,
-			CURSOR_Y_POSITION, 0);
-		x_hotspot -= src_x_offset;
-		y_hotspot -= src_y_offset;
-	} else if (src_x_offset < 0) {
-		REG_SET_2(CURSOR_POSITION, 0,
-			CURSOR_X_POSITION, 0,
-			CURSOR_Y_POSITION, pos->y);
-		x_hotspot -= src_x_offset;
-	} else if (src_y_offset < 0) {
-		REG_SET_2(CURSOR_POSITION, 0,
 			CURSOR_X_POSITION, pos->x,
-			CURSOR_Y_POSITION, 0);
+			CURSOR_Y_POSITION, pos->y);
-		y_hotspot -= src_y_offset;
-	} else {
-		REG_SET_2(CURSOR_POSITION, 0,
-				CURSOR_X_POSITION, pos->x,
-				CURSOR_Y_POSITION, pos->y);
-	}
 
 	REG_SET_2(CURSOR_HOT_SPOT, 0,
 			CURSOR_HOT_SPOT_X, x_hotspot,

drivers/gpu/drm/bridge/synopsys/dw-hdmi.c

@@ -1037,6 +1037,31 @@ void dw_hdmi_phy_i2c_write(struct dw_hdmi *hdmi, unsigned short data,
 }
 EXPORT_SYMBOL_GPL(dw_hdmi_phy_i2c_write);
 
+/* Filter out invalid setups to avoid configuring SCDC and scrambling */
+static bool dw_hdmi_support_scdc(struct dw_hdmi *hdmi)
+{
+	struct drm_display_info *display = &hdmi->connector.display_info;
+
+	/* Completely disable SCDC support for older controllers */
+	if (hdmi->version < 0x200a)
+		return false;
+
+	/* Disable if SCDC is not supported, or if an HF-VSDB block is absent */
+	if (!display->hdmi.scdc.supported ||
+	    !display->hdmi.scdc.scrambling.supported)
+		return false;
+
+	/*
+	 * Disable if display only support low TMDS rates and scrambling
+	 * for low rates is not supported either
+	 */
+	if (!display->hdmi.scdc.scrambling.low_rates &&
+	    display->max_tmds_clock <= 340000)
+		return false;
+
+	return true;
+}
+
 /*
  * HDMI2.0 Specifies the following procedure for High TMDS Bit Rates:
  * - The Source shall suspend transmission of the TMDS clock and data
@@ -1055,7 +1080,7 @@ void dw_hdmi_set_high_tmds_clock_ratio(struct dw_hdmi *hdmi)
 	unsigned long mtmdsclock = hdmi->hdmi_data.video_mode.mtmdsclock;
 
 	/* Control for TMDS Bit Period/TMDS Clock-Period Ratio */
-	if (hdmi->connector.display_info.hdmi.scdc.supported) {
+	if (dw_hdmi_support_scdc(hdmi)) {
 		if (mtmdsclock > HDMI14_MAX_TMDSCLK)
 			drm_scdc_set_high_tmds_clock_ratio(hdmi->ddc, 1);
 		else
@@ -1579,8 +1604,9 @@ static void hdmi_av_composer(struct dw_hdmi *hdmi,
 
 	/* Set up HDMI_FC_INVIDCONF */
 	inv_val = (hdmi->hdmi_data.hdcp_enable ||
-		   vmode->mtmdsclock > HDMI14_MAX_TMDSCLK ||
+		   (dw_hdmi_support_scdc(hdmi) &&
-		   hdmi_info->scdc.scrambling.low_rates ?
+		    (vmode->mtmdsclock > HDMI14_MAX_TMDSCLK ||
+		     hdmi_info->scdc.scrambling.low_rates)) ?
 		HDMI_FC_INVIDCONF_HDCP_KEEPOUT_ACTIVE :
 		HDMI_FC_INVIDCONF_HDCP_KEEPOUT_INACTIVE);
 
@@ -1646,7 +1672,7 @@ static void hdmi_av_composer(struct dw_hdmi *hdmi,
 	}
 
 	/* Scrambling Control */
-	if (hdmi_info->scdc.supported) {
+	if (dw_hdmi_support_scdc(hdmi)) {
 		if (vmode->mtmdsclock > HDMI14_MAX_TMDSCLK ||
 		    hdmi_info->scdc.scrambling.low_rates) {
 			/*

drivers/gpu/drm/drm_atomic_helper.c

@@ -1034,7 +1034,7 @@ disable_outputs(struct drm_device *dev, struct drm_atomic_state *old_state)
 			funcs->atomic_disable(crtc, old_crtc_state);
 		else if (funcs->disable)
 			funcs->disable(crtc);
-		else
+		else if (funcs->dpms)
 			funcs->dpms(crtc, DRM_MODE_DPMS_OFF);
 
 		if (!(dev->irq_enabled && dev->num_crtcs))
@@ -1277,10 +1277,9 @@ void drm_atomic_helper_commit_modeset_enables(struct drm_device *dev,
 		if (new_crtc_state->enable) {
 			DRM_DEBUG_ATOMIC("enabling [CRTC:%d:%s]\n",
 					 crtc->base.id, crtc->name);
-
 			if (funcs->atomic_enable)
 				funcs->atomic_enable(crtc, old_crtc_state);
-			else
+			else if (funcs->commit)
 				funcs->commit(crtc);
 		}
 	}

drivers/gpu/drm/i915/gvt/dmabuf.c

@@ -209,7 +209,7 @@ static int vgpu_get_plane_info(struct drm_device *dev,
 	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct intel_vgpu_primary_plane_format p;
 	struct intel_vgpu_cursor_plane_format c;
-	int ret;
+	int ret, tile_height = 1;
 
 	if (plane_id == DRM_PLANE_TYPE_PRIMARY) {
 		ret = intel_vgpu_decode_primary_plane(vgpu, &p);
@@ -228,12 +228,15 @@ static int vgpu_get_plane_info(struct drm_device *dev,
 			break;
 		case PLANE_CTL_TILED_X:
 			info->drm_format_mod = I915_FORMAT_MOD_X_TILED;
+			tile_height = 8;
 			break;
 		case PLANE_CTL_TILED_Y:
 			info->drm_format_mod = I915_FORMAT_MOD_Y_TILED;
+			tile_height = 32;
 			break;
 		case PLANE_CTL_TILED_YF:
 			info->drm_format_mod = I915_FORMAT_MOD_Yf_TILED;
+			tile_height = 32;
 			break;
 		default:
 			gvt_vgpu_err("invalid tiling mode: %x\n", p.tiled);
@@ -264,8 +267,8 @@ static int vgpu_get_plane_info(struct drm_device *dev,
 		return -EINVAL;
 	}
 
-	info->size = (info->stride * info->height + PAGE_SIZE - 1)
+	info->size = (info->stride * roundup(info->height, tile_height)
-		      >> PAGE_SHIFT;
+		      + PAGE_SIZE - 1) >> PAGE_SHIFT;
 	if (info->size == 0) {
 		gvt_vgpu_err("fb size is zero\n");
 		return -EINVAL;

drivers/gpu/drm/i915/gvt/gtt.c

@@ -750,14 +750,20 @@ static void ppgtt_free_spt(struct intel_vgpu_ppgtt_spt *spt)
 
 static void ppgtt_free_all_spt(struct intel_vgpu *vgpu)
 {
-	struct intel_vgpu_ppgtt_spt *spt;
+	struct intel_vgpu_ppgtt_spt *spt, *spn;
 	struct radix_tree_iter iter;
-	void **slot;
+	LIST_HEAD(all_spt);
+	void __rcu **slot;
 
+	rcu_read_lock();
 	radix_tree_for_each_slot(slot, &vgpu->gtt.spt_tree, &iter, 0) {
 		spt = radix_tree_deref_slot(slot);
-		ppgtt_free_spt(spt);
+		list_move(&spt->post_shadow_list, &all_spt);
 	}
+	rcu_read_unlock();
+
+	list_for_each_entry_safe(spt, spn, &all_spt, post_shadow_list)
+		ppgtt_free_spt(spt);
 }
 
 static int ppgtt_handle_guest_write_page_table_bytes(

drivers/gpu/drm/i915/gvt/kvmgt.c

@@ -905,7 +905,7 @@ static inline bool intel_vgpu_in_aperture(struct intel_vgpu *vgpu, u64 off)
 static int intel_vgpu_aperture_rw(struct intel_vgpu *vgpu, u64 off,
 		void *buf, unsigned long count, bool is_write)
 {
-	void *aperture_va;
+	void __iomem *aperture_va;
 
 	if (!intel_vgpu_in_aperture(vgpu, off) ||
 	    !intel_vgpu_in_aperture(vgpu, off + count)) {
@@ -920,9 +920,9 @@ static int intel_vgpu_aperture_rw(struct intel_vgpu *vgpu, u64 off,
 		return -EIO;
 
 	if (is_write)
-		memcpy(aperture_va + offset_in_page(off), buf, count);
+		memcpy_toio(aperture_va + offset_in_page(off), buf, count);
 	else
-		memcpy(buf, aperture_va + offset_in_page(off), count);
+		memcpy_fromio(buf, aperture_va + offset_in_page(off), count);
 
 	io_mapping_unmap(aperture_va);
 

drivers/gpu/drm/i915/icl_dsi.c

@@ -323,6 +323,21 @@ static void gen11_dsi_program_esc_clk_div(struct intel_encoder *encoder)
 	}
 }
 
+static void get_dsi_io_power_domains(struct drm_i915_private *dev_priv,
+				     struct intel_dsi *intel_dsi)
+{
+	enum port port;
+
+	for_each_dsi_port(port, intel_dsi->ports) {
+		WARN_ON(intel_dsi->io_wakeref[port]);
+		intel_dsi->io_wakeref[port] =
+			intel_display_power_get(dev_priv,
+						port == PORT_A ?
+						POWER_DOMAIN_PORT_DDI_A_IO :
+						POWER_DOMAIN_PORT_DDI_B_IO);
+	}
+}
+
 static void gen11_dsi_enable_io_power(struct intel_encoder *encoder)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
@@ -336,13 +351,7 @@ static void gen11_dsi_enable_io_power(struct intel_encoder *encoder)
 		I915_WRITE(ICL_DSI_IO_MODECTL(port), tmp);
 	}
 
-	for_each_dsi_port(port, intel_dsi->ports) {
+	get_dsi_io_power_domains(dev_priv, intel_dsi);
-		intel_dsi->io_wakeref[port] =
-			intel_display_power_get(dev_priv,
-						port == PORT_A ?
-						POWER_DOMAIN_PORT_DDI_A_IO :
-						POWER_DOMAIN_PORT_DDI_B_IO);
-	}
 }
 
 static void gen11_dsi_power_up_lanes(struct intel_encoder *encoder)
@@ -589,6 +598,12 @@ static void gen11_dsi_map_pll(struct intel_encoder *encoder,
 		val |= DPCLKA_CFGCR0_DDI_CLK_SEL(pll->info->id, port);
 	}
 	I915_WRITE(DPCLKA_CFGCR0_ICL, val);
+
+	for_each_dsi_port(port, intel_dsi->ports) {
+		val &= ~DPCLKA_CFGCR0_DDI_CLK_OFF(port);
+	}
+	I915_WRITE(DPCLKA_CFGCR0_ICL, val);
+
 	POSTING_READ(DPCLKA_CFGCR0_ICL);
 
 	mutex_unlock(&dev_priv->dpll_lock);
@@ -1117,7 +1132,7 @@ static void gen11_dsi_disable_port(struct intel_encoder *encoder)
 			DRM_ERROR("DDI port:%c buffer not idle\n",
 				  port_name(port));
 	}
-	gen11_dsi_ungate_clocks(encoder);
+	gen11_dsi_gate_clocks(encoder);
 }
 
 static void gen11_dsi_disable_io_power(struct intel_encoder *encoder)
@@ -1218,20 +1233,11 @@ static int gen11_dsi_compute_config(struct intel_encoder *encoder,
 	return 0;
 }
 
-static u64 gen11_dsi_get_power_domains(struct intel_encoder *encoder,
+static void gen11_dsi_get_power_domains(struct intel_encoder *encoder,
-				       struct intel_crtc_state *crtc_state)
+					struct intel_crtc_state *crtc_state)
 {
-	struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base);
+	get_dsi_io_power_domains(to_i915(encoder->base.dev),
-	u64 domains = 0;
+				 enc_to_intel_dsi(&encoder->base));
-	enum port port;
-
-	for_each_dsi_port(port, intel_dsi->ports)
-		if (port == PORT_A)
-			domains |= BIT_ULL(POWER_DOMAIN_PORT_DDI_A_IO);
-		else
-			domains |= BIT_ULL(POWER_DOMAIN_PORT_DDI_B_IO);
-
-	return domains;
 }
 
 static bool gen11_dsi_get_hw_state(struct intel_encoder *encoder,

drivers/gpu/drm/i915/intel_ddi.c

@@ -2075,12 +2075,11 @@ intel_ddi_main_link_aux_domain(struct intel_digital_port *dig_port)
 					      intel_aux_power_domain(dig_port);
 }
 
-static u64 intel_ddi_get_power_domains(struct intel_encoder *encoder,
+static void intel_ddi_get_power_domains(struct intel_encoder *encoder,
-				       struct intel_crtc_state *crtc_state)
+					struct intel_crtc_state *crtc_state)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
 	struct intel_digital_port *dig_port;
-	u64 domains;
 
 	/*
 	 * TODO: Add support for MST encoders. Atm, the following should never
@@ -2088,10 +2087,10 @@ static u64 intel_ddi_get_power_domains(struct intel_encoder *encoder,
 	 * hook.
 	 */
 	if (WARN_ON(intel_crtc_has_type(crtc_state, INTEL_OUTPUT_DP_MST)))
-		return 0;
+		return;
 
 	dig_port = enc_to_dig_port(&encoder->base);
-	domains = BIT_ULL(dig_port->ddi_io_power_domain);
+	intel_display_power_get(dev_priv, dig_port->ddi_io_power_domain);
 
 	/*
 	 * AUX power is only needed for (e)DP mode, and for HDMI mode on TC
@@ -2099,15 +2098,15 @@ static u64 intel_ddi_get_power_domains(struct intel_encoder *encoder,
 	 */
 	if (intel_crtc_has_dp_encoder(crtc_state) ||
 	    intel_port_is_tc(dev_priv, encoder->port))
-		domains |= BIT_ULL(intel_ddi_main_link_aux_domain(dig_port));
+		intel_display_power_get(dev_priv,
+					intel_ddi_main_link_aux_domain(dig_port));
 
 	/*
 	 * VDSC power is needed when DSC is enabled
 	 */
 	if (crtc_state->dsc_params.compression_enable)
-		domains |= BIT_ULL(intel_dsc_power_domain(crtc_state));
+		intel_display_power_get(dev_priv,
-
+					intel_dsc_power_domain(crtc_state));
-	return domains;
 }
 
 void intel_ddi_enable_pipe_clock(const struct intel_crtc_state *crtc_state)
@@ -2825,10 +2824,10 @@ void icl_sanitize_encoder_pll_mapping(struct intel_encoder *encoder)
 				return;
 		}
 		/*
-		 * DSI ports should have their DDI clock ungated when disabled
+		 * For DSI we keep the ddi clocks gated
-		 * and gated when enabled.
+		 * except during enable/disable sequence.
 		 */
-		ddi_clk_needed = !encoder->base.crtc;
+		ddi_clk_needed = false;
 	}
 
 	val = I915_READ(DPCLKA_CFGCR0_ICL);

drivers/gpu/drm/i915/intel_display.c

@@ -15986,8 +15986,6 @@ get_encoder_power_domains(struct drm_i915_private *dev_priv)
 	struct intel_encoder *encoder;
 
 	for_each_intel_encoder(&dev_priv->drm, encoder) {
-		u64 get_domains;
-		enum intel_display_power_domain domain;
 		struct intel_crtc_state *crtc_state;
 
 		if (!encoder->get_power_domains)
@@ -16001,9 +15999,7 @@ get_encoder_power_domains(struct drm_i915_private *dev_priv)
 			continue;
 
 		crtc_state = to_intel_crtc_state(encoder->base.crtc->state);
-		get_domains = encoder->get_power_domains(encoder, crtc_state);
+		encoder->get_power_domains(encoder, crtc_state);
-		for_each_power_domain(domain, get_domains)
-			intel_display_power_get(dev_priv, domain);
 	}
 }
 

drivers/gpu/drm/i915/intel_dp.c

@@ -1859,42 +1859,6 @@ intel_dp_compute_link_config_wide(struct intel_dp *intel_dp,
 	return -EINVAL;
 }
 
-/* Optimize link config in order: max bpp, min lanes, min clock */
-static int
-intel_dp_compute_link_config_fast(struct intel_dp *intel_dp,
-				  struct intel_crtc_state *pipe_config,
-				  const struct link_config_limits *limits)
-{
-	struct drm_display_mode *adjusted_mode = &pipe_config->base.adjusted_mode;
-	int bpp, clock, lane_count;
-	int mode_rate, link_clock, link_avail;
-
-	for (bpp = limits->max_bpp; bpp >= limits->min_bpp; bpp -= 2 * 3) {
-		mode_rate = intel_dp_link_required(adjusted_mode->crtc_clock,
-						   bpp);
-
-		for (lane_count = limits->min_lane_count;
-		     lane_count <= limits->max_lane_count;
-		     lane_count <<= 1) {
-			for (clock = limits->min_clock; clock <= limits->max_clock; clock++) {
-				link_clock = intel_dp->common_rates[clock];
-				link_avail = intel_dp_max_data_rate(link_clock,
-								    lane_count);
-
-				if (mode_rate <= link_avail) {
-					pipe_config->lane_count = lane_count;
-					pipe_config->pipe_bpp = bpp;
-					pipe_config->port_clock = link_clock;
-
-					return 0;
-				}
-			}
-		}
-	}
-
-	return -EINVAL;
-}
-
 static int intel_dp_dsc_compute_bpp(struct intel_dp *intel_dp, u8 dsc_max_bpc)
 {
 	int i, num_bpc;
@@ -2031,15 +1995,13 @@ intel_dp_compute_link_config(struct intel_encoder *encoder,
 	limits.min_bpp = 6 * 3;
 	limits.max_bpp = intel_dp_compute_bpp(intel_dp, pipe_config);
 
-	if (intel_dp_is_edp(intel_dp) && intel_dp->edp_dpcd[0] < DP_EDP_14) {
+	if (intel_dp_is_edp(intel_dp)) {
 		/*
 		 * Use the maximum clock and number of lanes the eDP panel
-		 * advertizes being capable of. The eDP 1.3 and earlier panels
+		 * advertizes being capable of. The panels are generally
-		 * are generally designed to support only a single clock and
+		 * designed to support only a single clock and lane
-		 * lane configuration, and typically these values correspond to
+		 * configuration, and typically these values correspond to the
-		 * the native resolution of the panel. With eDP 1.4 rate select
+		 * native resolution of the panel.
-		 * and DSC, this is decreasingly the case, and we need to be
-		 * able to select less than maximum link config.
 		 */
 		limits.min_lane_count = limits.max_lane_count;
 		limits.min_clock = limits.max_clock;
@@ -2053,22 +2015,11 @@ intel_dp_compute_link_config(struct intel_encoder *encoder,
 		      intel_dp->common_rates[limits.max_clock],
 		      limits.max_bpp, adjusted_mode->crtc_clock);
 
-	if (intel_dp_is_edp(intel_dp))
+	/*
-		/*
+	 * Optimize for slow and wide. This is the place to add alternative
-		 * Optimize for fast and narrow. eDP 1.3 section 3.3 and eDP 1.4
+	 * optimization policy.
-		 * section A.1: "It is recommended that the minimum number of
+	 */
-		 * lanes be used, using the minimum link rate allowed for that
+	ret = intel_dp_compute_link_config_wide(intel_dp, pipe_config, &limits);
-		 * lane configuration."
-		 *
-		 * Note that we use the max clock and lane count for eDP 1.3 and
-		 * earlier, and fast vs. wide is irrelevant.
-		 */
-		ret = intel_dp_compute_link_config_fast(intel_dp, pipe_config,
-							&limits);
-	else
-		/* Optimize for slow and wide. */
-		ret = intel_dp_compute_link_config_wide(intel_dp, pipe_config,
-							&limits);
 
 	/* enable compression if the mode doesn't fit available BW */
 	DRM_DEBUG_KMS("Force DSC en = %d\n", intel_dp->force_dsc_en);

drivers/gpu/drm/i915/intel_drv.h

@@ -270,10 +270,12 @@ struct intel_encoder {
 	 * be set correctly before calling this function. */
 	void (*get_config)(struct intel_encoder *,
 			   struct intel_crtc_state *pipe_config);
-	/* Returns a mask of power domains that need to be referenced as part
+	/*
-	 * of the hardware state readout code. */
+	 * Acquires the power domains needed for an active encoder during
-	u64 (*get_power_domains)(struct intel_encoder *encoder,
+	 * hardware state readout.
-				 struct intel_crtc_state *crtc_state);
+	 */
+	void (*get_power_domains)(struct intel_encoder *encoder,
+				  struct intel_crtc_state *crtc_state);
 	/*
 	 * Called during system suspend after all pending requests for the
 	 * encoder are flushed (for example for DP AUX transactions) and

drivers/gpu/drm/i915/vlv_dsi.c

@@ -256,6 +256,28 @@ static void band_gap_reset(struct drm_i915_private *dev_priv)
 	mutex_unlock(&dev_priv->sb_lock);
 }
 
+static int bdw_get_pipemisc_bpp(struct intel_crtc *crtc)
+{
+	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
+	u32 tmp;
+
+	tmp = I915_READ(PIPEMISC(crtc->pipe));
+
+	switch (tmp & PIPEMISC_DITHER_BPC_MASK) {
+	case PIPEMISC_DITHER_6_BPC:
+		return 18;
+	case PIPEMISC_DITHER_8_BPC:
+		return 24;
+	case PIPEMISC_DITHER_10_BPC:
+		return 30;
+	case PIPEMISC_DITHER_12_BPC:
+		return 36;
+	default:
+		MISSING_CASE(tmp);
+		return 0;
+	}
+}
+
 static int intel_dsi_compute_config(struct intel_encoder *encoder,
 				    struct intel_crtc_state *pipe_config,
 				    struct drm_connector_state *conn_state)
@@ -1071,6 +1093,8 @@ static void bxt_dsi_get_pipe_config(struct intel_encoder *encoder,
 	bpp = mipi_dsi_pixel_format_to_bpp(
 			pixel_format_from_register_bits(fmt));
 
+	pipe_config->pipe_bpp = bdw_get_pipemisc_bpp(crtc);
+
 	/* Enable Frame time stamo based scanline reporting */
 	adjusted_mode->private_flags |=
 			I915_MODE_FLAG_GET_SCANLINE_FROM_TIMESTAMP;

drivers/gpu/drm/mediatek/mtk_dpi.c

@@ -662,13 +662,11 @@ static unsigned int mt8173_calculate_factor(int clock)
 static unsigned int mt2701_calculate_factor(int clock)
 {
 	if (clock <= 64000)
-		return 16;
-	else if (clock <= 128000)
-		return 8;
-	else if (clock <= 256000)
 		return 4;
-	else
+	else if (clock <= 128000)
 		return 2;
+	else
+		return 1;
 }
 
 static const struct mtk_dpi_conf mt8173_conf = {

drivers/gpu/drm/mediatek/mtk_drm_drv.c

@@ -15,6 +15,7 @@
 #include <drm/drmP.h>
 #include <drm/drm_atomic.h>
 #include <drm/drm_atomic_helper.h>
+#include <drm/drm_fb_helper.h>
 #include <drm/drm_gem.h>
 #include <drm/drm_gem_cma_helper.h>
 #include <drm/drm_of.h>
@@ -341,6 +342,8 @@ static struct drm_driver mtk_drm_driver = {
 	.gem_prime_get_sg_table = mtk_gem_prime_get_sg_table,
 	.gem_prime_import_sg_table = mtk_gem_prime_import_sg_table,
 	.gem_prime_mmap = mtk_drm_gem_mmap_buf,
+	.gem_prime_vmap = mtk_drm_gem_prime_vmap,
+	.gem_prime_vunmap = mtk_drm_gem_prime_vunmap,
 	.fops = &mtk_drm_fops,
 
 	.name = DRIVER_NAME,
@@ -376,6 +379,10 @@ static int mtk_drm_bind(struct device *dev)
 	if (ret < 0)
 		goto err_deinit;
 
+	ret = drm_fbdev_generic_setup(drm, 32);
+	if (ret)
+		DRM_ERROR("Failed to initialize fbdev: %d\n", ret);
+
 	return 0;
 
 err_deinit:

drivers/gpu/drm/mediatek/mtk_drm_gem.c

@@ -241,3 +241,49 @@ err_gem_free:
 	kfree(mtk_gem);
 	return ERR_PTR(ret);
 }
+
+void *mtk_drm_gem_prime_vmap(struct drm_gem_object *obj)
+{
+	struct mtk_drm_gem_obj *mtk_gem = to_mtk_gem_obj(obj);
+	struct sg_table *sgt;
+	struct sg_page_iter iter;
+	unsigned int npages;
+	unsigned int i = 0;
+
+	if (mtk_gem->kvaddr)
+		return mtk_gem->kvaddr;
+
+	sgt = mtk_gem_prime_get_sg_table(obj);
+	if (IS_ERR(sgt))
+		return NULL;
+
+	npages = obj->size >> PAGE_SHIFT;
+	mtk_gem->pages = kcalloc(npages, sizeof(*mtk_gem->pages), GFP_KERNEL);
+	if (!mtk_gem->pages)
+		goto out;
+
+	for_each_sg_page(sgt->sgl, &iter, sgt->orig_nents, 0) {
+		mtk_gem->pages[i++] = sg_page_iter_page(&iter);
+		if (i > npages)
+			break;
+	}
+	mtk_gem->kvaddr = vmap(mtk_gem->pages, npages, VM_MAP,
+			       pgprot_writecombine(PAGE_KERNEL));
+
+out:
+	kfree((void *)sgt);
+
+	return mtk_gem->kvaddr;
+}
+
+void mtk_drm_gem_prime_vunmap(struct drm_gem_object *obj, void *vaddr)
+{
+	struct mtk_drm_gem_obj *mtk_gem = to_mtk_gem_obj(obj);
+
+	if (!mtk_gem->pages)
+		return;
+
+	vunmap(vaddr);
+	mtk_gem->kvaddr = 0;
+	kfree((void *)mtk_gem->pages);
+}

drivers/gpu/drm/mediatek/mtk_drm_gem.h

@@ -37,6 +37,7 @@ struct mtk_drm_gem_obj {
 	dma_addr_t		dma_addr;
 	unsigned long		dma_attrs;
 	struct sg_table		*sg;
+	struct page		**pages;
 };
 
 #define to_mtk_gem_obj(x)	container_of(x, struct mtk_drm_gem_obj, base)
@@ -52,5 +53,7 @@ int mtk_drm_gem_mmap_buf(struct drm_gem_object *obj,
 struct sg_table *mtk_gem_prime_get_sg_table(struct drm_gem_object *obj);
 struct drm_gem_object *mtk_gem_prime_import_sg_table(struct drm_device *dev,
 			struct dma_buf_attachment *attach, struct sg_table *sg);
+void *mtk_drm_gem_prime_vmap(struct drm_gem_object *obj);
+void mtk_drm_gem_prime_vunmap(struct drm_gem_object *obj, void *vaddr);
 
 #endif

drivers/gpu/drm/mediatek/mtk_hdmi.c

@@ -1480,7 +1480,6 @@ static int mtk_hdmi_dt_parse_pdata(struct mtk_hdmi *hdmi,
 	if (IS_ERR(regmap))
 		ret = PTR_ERR(regmap);
 	if (ret) {
-		ret = PTR_ERR(regmap);
 		dev_err(dev,
 			"Failed to get system configuration registers: %d\n",
 			ret);
@@ -1516,6 +1515,7 @@ static int mtk_hdmi_dt_parse_pdata(struct mtk_hdmi *hdmi,
 	of_node_put(remote);
 
 	hdmi->ddc_adpt = of_find_i2c_adapter_by_node(i2c_np);
+	of_node_put(i2c_np);
 	if (!hdmi->ddc_adpt) {
 		dev_err(dev, "Failed to get ddc i2c adapter by node\n");
 		return -EINVAL;

drivers/gpu/drm/mediatek/mtk_hdmi_phy.c

@@ -15,28 +15,6 @@ static const struct phy_ops mtk_hdmi_phy_dev_ops = {
 	.owner = THIS_MODULE,
 };
 
-long mtk_hdmi_pll_round_rate(struct clk_hw *hw, unsigned long rate,
-			     unsigned long *parent_rate)
-{
-	struct mtk_hdmi_phy *hdmi_phy = to_mtk_hdmi_phy(hw);
-
-	hdmi_phy->pll_rate = rate;
-	if (rate <= 74250000)
-		*parent_rate = rate;
-	else
-		*parent_rate = rate / 2;
-
-	return rate;
-}
-
-unsigned long mtk_hdmi_pll_recalc_rate(struct clk_hw *hw,
-				       unsigned long parent_rate)
-{
-	struct mtk_hdmi_phy *hdmi_phy = to_mtk_hdmi_phy(hw);
-
-	return hdmi_phy->pll_rate;
-}
-
 void mtk_hdmi_phy_clear_bits(struct mtk_hdmi_phy *hdmi_phy, u32 offset,
 			     u32 bits)
 {
@@ -110,13 +88,11 @@ mtk_hdmi_phy_dev_get_ops(const struct mtk_hdmi_phy *hdmi_phy)
 		return NULL;
 }
 
-static void mtk_hdmi_phy_clk_get_ops(struct mtk_hdmi_phy *hdmi_phy,
+static void mtk_hdmi_phy_clk_get_data(struct mtk_hdmi_phy *hdmi_phy,
-				     const struct clk_ops **ops)
+				      struct clk_init_data *clk_init)
 {
-	if (hdmi_phy && hdmi_phy->conf && hdmi_phy->conf->hdmi_phy_clk_ops)
+	clk_init->flags = hdmi_phy->conf->flags;
-		*ops = hdmi_phy->conf->hdmi_phy_clk_ops;
+	clk_init->ops = hdmi_phy->conf->hdmi_phy_clk_ops;
-	else
-		dev_err(hdmi_phy->dev, "Failed to get clk ops of phy\n");
 }
 
 static int mtk_hdmi_phy_probe(struct platform_device *pdev)
@@ -129,7 +105,6 @@ static int mtk_hdmi_phy_probe(struct platform_device *pdev)
 	struct clk_init_data clk_init = {
 		.num_parents = 1,
 		.parent_names = (const char * const *)&ref_clk_name,
-		.flags = CLK_SET_RATE_PARENT | CLK_SET_RATE_GATE,
 	};
 
 	struct phy *phy;
@@ -167,7 +142,7 @@ static int mtk_hdmi_phy_probe(struct platform_device *pdev)
 	hdmi_phy->dev = dev;
 	hdmi_phy->conf =
 		(struct mtk_hdmi_phy_conf *)of_device_get_match_data(dev);
-	mtk_hdmi_phy_clk_get_ops(hdmi_phy, &clk_init.ops);
+	mtk_hdmi_phy_clk_get_data(hdmi_phy, &clk_init);
 	hdmi_phy->pll_hw.init = &clk_init;
 	hdmi_phy->pll = devm_clk_register(dev, &hdmi_phy->pll_hw);
 	if (IS_ERR(hdmi_phy->pll)) {

drivers/gpu/drm/mediatek/mtk_hdmi_phy.h

@@ -21,6 +21,7 @@ struct mtk_hdmi_phy;
 
 struct mtk_hdmi_phy_conf {
 	bool tz_disabled;
+	unsigned long flags;
 	const struct clk_ops *hdmi_phy_clk_ops;
 	void (*hdmi_phy_enable_tmds)(struct mtk_hdmi_phy *hdmi_phy);
 	void (*hdmi_phy_disable_tmds)(struct mtk_hdmi_phy *hdmi_phy);
@@ -48,10 +49,6 @@ void mtk_hdmi_phy_set_bits(struct mtk_hdmi_phy *hdmi_phy, u32 offset,
 void mtk_hdmi_phy_mask(struct mtk_hdmi_phy *hdmi_phy, u32 offset,
 		       u32 val, u32 mask);
 struct mtk_hdmi_phy *to_mtk_hdmi_phy(struct clk_hw *hw);
-long mtk_hdmi_pll_round_rate(struct clk_hw *hw, unsigned long rate,
-			     unsigned long *parent_rate);
-unsigned long mtk_hdmi_pll_recalc_rate(struct clk_hw *hw,
-				       unsigned long parent_rate);
 
 extern struct platform_driver mtk_hdmi_phy_driver;
 extern struct mtk_hdmi_phy_conf mtk_hdmi_phy_8173_conf;

drivers/gpu/drm/mediatek/mtk_mt2701_hdmi_phy.c

@@ -79,7 +79,6 @@ static int mtk_hdmi_pll_prepare(struct clk_hw *hw)
 	mtk_hdmi_phy_set_bits(hdmi_phy, HDMI_CON0, RG_HDMITX_EN_SLDO_MASK);
 	usleep_range(80, 100);
 	mtk_hdmi_phy_set_bits(hdmi_phy, HDMI_CON2, RG_HDMITX_MBIAS_LPF_EN);
-	mtk_hdmi_phy_set_bits(hdmi_phy, HDMI_CON2, RG_HDMITX_EN_TX_POSDIV);
 	mtk_hdmi_phy_set_bits(hdmi_phy, HDMI_CON0, RG_HDMITX_EN_SER_MASK);
 	mtk_hdmi_phy_set_bits(hdmi_phy, HDMI_CON0, RG_HDMITX_EN_PRED_MASK);
 	mtk_hdmi_phy_set_bits(hdmi_phy, HDMI_CON0, RG_HDMITX_EN_DRV_MASK);
@@ -94,7 +93,6 @@ static void mtk_hdmi_pll_unprepare(struct clk_hw *hw)
 	mtk_hdmi_phy_clear_bits(hdmi_phy, HDMI_CON0, RG_HDMITX_EN_DRV_MASK);
 	mtk_hdmi_phy_clear_bits(hdmi_phy, HDMI_CON0, RG_HDMITX_EN_PRED_MASK);
 	mtk_hdmi_phy_clear_bits(hdmi_phy, HDMI_CON0, RG_HDMITX_EN_SER_MASK);
-	mtk_hdmi_phy_clear_bits(hdmi_phy, HDMI_CON2, RG_HDMITX_EN_TX_POSDIV);
 	mtk_hdmi_phy_clear_bits(hdmi_phy, HDMI_CON2, RG_HDMITX_MBIAS_LPF_EN);
 	usleep_range(80, 100);
 	mtk_hdmi_phy_clear_bits(hdmi_phy, HDMI_CON0, RG_HDMITX_EN_SLDO_MASK);
@@ -108,6 +106,12 @@ static void mtk_hdmi_pll_unprepare(struct clk_hw *hw)
 	usleep_range(80, 100);
 }
 
+static long mtk_hdmi_pll_round_rate(struct clk_hw *hw, unsigned long rate,
+				    unsigned long *parent_rate)
+{
+	return rate;
+}
+
 static int mtk_hdmi_pll_set_rate(struct clk_hw *hw, unsigned long rate,
 				 unsigned long parent_rate)
 {
@@ -116,13 +120,14 @@ static int mtk_hdmi_pll_set_rate(struct clk_hw *hw, unsigned long rate,
 
 	if (rate <= 64000000)
 		pos_div = 3;
-	else if (rate <= 12800000)
+	else if (rate <= 128000000)
-		pos_div = 1;
+		pos_div = 2;
 	else
 		pos_div = 1;
 
 	mtk_hdmi_phy_set_bits(hdmi_phy, HDMI_CON6, RG_HTPLL_PREDIV_MASK);
 	mtk_hdmi_phy_set_bits(hdmi_phy, HDMI_CON6, RG_HTPLL_POSDIV_MASK);
+	mtk_hdmi_phy_set_bits(hdmi_phy, HDMI_CON2, RG_HDMITX_EN_TX_POSDIV);
 	mtk_hdmi_phy_mask(hdmi_phy, HDMI_CON6, (0x1 << RG_HTPLL_IC),
 			  RG_HTPLL_IC_MASK);
 	mtk_hdmi_phy_mask(hdmi_phy, HDMI_CON6, (0x1 << RG_HTPLL_IR),
@@ -154,6 +159,39 @@ static int mtk_hdmi_pll_set_rate(struct clk_hw *hw, unsigned long rate,
 	return 0;
 }
 
+static unsigned long mtk_hdmi_pll_recalc_rate(struct clk_hw *hw,
+					      unsigned long parent_rate)
+{
+	struct mtk_hdmi_phy *hdmi_phy = to_mtk_hdmi_phy(hw);
+	unsigned long out_rate, val;
+
+	val = (readl(hdmi_phy->regs + HDMI_CON6)
+	       & RG_HTPLL_PREDIV_MASK) >> RG_HTPLL_PREDIV;
+	switch (val) {
+	case 0x00:
+		out_rate = parent_rate;
+		break;
+	case 0x01:
+		out_rate = parent_rate / 2;
+		break;
+	default:
+		out_rate = parent_rate / 4;
+		break;
+	}
+
+	val = (readl(hdmi_phy->regs + HDMI_CON6)
+	       & RG_HTPLL_FBKDIV_MASK) >> RG_HTPLL_FBKDIV;
+	out_rate *= (val + 1) * 2;
+	val = (readl(hdmi_phy->regs + HDMI_CON2)
+	       & RG_HDMITX_TX_POSDIV_MASK);
+	out_rate >>= (val >> RG_HDMITX_TX_POSDIV);
+
+	if (readl(hdmi_phy->regs + HDMI_CON2) & RG_HDMITX_EN_TX_POSDIV)
+		out_rate /= 5;
+
+	return out_rate;
+}
+
 static const struct clk_ops mtk_hdmi_phy_pll_ops = {
 	.prepare = mtk_hdmi_pll_prepare,
 	.unprepare = mtk_hdmi_pll_unprepare,
@@ -174,7 +212,6 @@ static void mtk_hdmi_phy_enable_tmds(struct mtk_hdmi_phy *hdmi_phy)
 	mtk_hdmi_phy_set_bits(hdmi_phy, HDMI_CON0, RG_HDMITX_EN_SLDO_MASK);
 	usleep_range(80, 100);
 	mtk_hdmi_phy_set_bits(hdmi_phy, HDMI_CON2, RG_HDMITX_MBIAS_LPF_EN);
-	mtk_hdmi_phy_set_bits(hdmi_phy, HDMI_CON2, RG_HDMITX_EN_TX_POSDIV);
 	mtk_hdmi_phy_set_bits(hdmi_phy, HDMI_CON0, RG_HDMITX_EN_SER_MASK);
 	mtk_hdmi_phy_set_bits(hdmi_phy, HDMI_CON0, RG_HDMITX_EN_PRED_MASK);
 	mtk_hdmi_phy_set_bits(hdmi_phy, HDMI_CON0, RG_HDMITX_EN_DRV_MASK);
@@ -186,7 +223,6 @@ static void mtk_hdmi_phy_disable_tmds(struct mtk_hdmi_phy *hdmi_phy)
 	mtk_hdmi_phy_clear_bits(hdmi_phy, HDMI_CON0, RG_HDMITX_EN_DRV_MASK);
 	mtk_hdmi_phy_clear_bits(hdmi_phy, HDMI_CON0, RG_HDMITX_EN_PRED_MASK);
 	mtk_hdmi_phy_clear_bits(hdmi_phy, HDMI_CON0, RG_HDMITX_EN_SER_MASK);
-	mtk_hdmi_phy_clear_bits(hdmi_phy, HDMI_CON2, RG_HDMITX_EN_TX_POSDIV);
 	mtk_hdmi_phy_clear_bits(hdmi_phy, HDMI_CON2, RG_HDMITX_MBIAS_LPF_EN);
 	usleep_range(80, 100);
 	mtk_hdmi_phy_clear_bits(hdmi_phy, HDMI_CON0, RG_HDMITX_EN_SLDO_MASK);
@@ -202,6 +238,7 @@ static void mtk_hdmi_phy_disable_tmds(struct mtk_hdmi_phy *hdmi_phy)
 
 struct mtk_hdmi_phy_conf mtk_hdmi_phy_2701_conf = {
 	.tz_disabled = true,
+	.flags = CLK_SET_RATE_GATE,
 	.hdmi_phy_clk_ops = &mtk_hdmi_phy_pll_ops,
 	.hdmi_phy_enable_tmds = mtk_hdmi_phy_enable_tmds,
 	.hdmi_phy_disable_tmds = mtk_hdmi_phy_disable_tmds,

drivers/gpu/drm/mediatek/mtk_mt8173_hdmi_phy.c

@@ -199,6 +199,20 @@ static void mtk_hdmi_pll_unprepare(struct clk_hw *hw)
 	usleep_range(100, 150);
 }
 
+static long mtk_hdmi_pll_round_rate(struct clk_hw *hw, unsigned long rate,
+				    unsigned long *parent_rate)
+{
+	struct mtk_hdmi_phy *hdmi_phy = to_mtk_hdmi_phy(hw);
+
+	hdmi_phy->pll_rate = rate;
+	if (rate <= 74250000)
+		*parent_rate = rate;
+	else
+		*parent_rate = rate / 2;
+
+	return rate;
+}
+
 static int mtk_hdmi_pll_set_rate(struct clk_hw *hw, unsigned long rate,
 				 unsigned long parent_rate)
 {
@@ -285,6 +299,14 @@ static int mtk_hdmi_pll_set_rate(struct clk_hw *hw, unsigned long rate,
 	return 0;
 }
 
+static unsigned long mtk_hdmi_pll_recalc_rate(struct clk_hw *hw,
+					      unsigned long parent_rate)
+{
+	struct mtk_hdmi_phy *hdmi_phy = to_mtk_hdmi_phy(hw);
+
+	return hdmi_phy->pll_rate;
+}
+
 static const struct clk_ops mtk_hdmi_phy_pll_ops = {
 	.prepare = mtk_hdmi_pll_prepare,
 	.unprepare = mtk_hdmi_pll_unprepare,
@@ -309,6 +331,7 @@ static void mtk_hdmi_phy_disable_tmds(struct mtk_hdmi_phy *hdmi_phy)
 }
 
 struct mtk_hdmi_phy_conf mtk_hdmi_phy_8173_conf = {
+	.flags = CLK_SET_RATE_PARENT | CLK_SET_RATE_GATE,
 	.hdmi_phy_clk_ops = &mtk_hdmi_phy_pll_ops,
 	.hdmi_phy_enable_tmds = mtk_hdmi_phy_enable_tmds,
 	.hdmi_phy_disable_tmds = mtk_hdmi_phy_disable_tmds,

drivers/gpu/drm/omapdrm/dss/hdmi4_cec.c

@@ -175,6 +175,7 @@ static int hdmi_cec_adap_enable(struct cec_adapter *adap, bool enable)
 		REG_FLD_MOD(core->base, HDMI_CORE_SYS_INTR_UNMASK4, 0, 3, 3);
 		hdmi_wp_clear_irqenable(core->wp, HDMI_IRQ_CORE);
 		hdmi_wp_set_irqstatus(core->wp, HDMI_IRQ_CORE);
+		REG_FLD_MOD(core->wp->base, HDMI_WP_CLK, 0, 5, 0);
 		hdmi4_core_disable(core);
 		return 0;
 	}
@@ -182,16 +183,24 @@ static int hdmi_cec_adap_enable(struct cec_adapter *adap, bool enable)
 	if (err)
 		return err;
 
+	/*
+	 * Initialize CEC clock divider: CEC needs 2MHz clock hence
+	 * set the divider to 24 to get 48/24=2MHz clock
+	 */
+	REG_FLD_MOD(core->wp->base, HDMI_WP_CLK, 0x18, 5, 0);
+
 	/* Clear TX FIFO */
 	if (!hdmi_cec_clear_tx_fifo(adap)) {
 		pr_err("cec-%s: could not clear TX FIFO\n", adap->name);
-		return -EIO;
+		err = -EIO;
+		goto err_disable_clk;
 	}
 
 	/* Clear RX FIFO */
 	if (!hdmi_cec_clear_rx_fifo(adap)) {
 		pr_err("cec-%s: could not clear RX FIFO\n", adap->name);
-		return -EIO;
+		err = -EIO;
+		goto err_disable_clk;
 	}
 
 	/* Clear CEC interrupts */
@@ -236,6 +245,12 @@ static int hdmi_cec_adap_enable(struct cec_adapter *adap, bool enable)
 		hdmi_write_reg(core->base, HDMI_CEC_INT_STATUS_1, temp);
 	}
 	return 0;
+
+err_disable_clk:
+	REG_FLD_MOD(core->wp->base, HDMI_WP_CLK, 0, 5, 0);
+	hdmi4_core_disable(core);
+
+	return err;
 }
 
 static int hdmi_cec_adap_log_addr(struct cec_adapter *adap, u8 log_addr)
@@ -333,11 +348,8 @@ int hdmi4_cec_init(struct platform_device *pdev, struct hdmi_core_data *core,
 		return ret;
 	core->wp = wp;
 
-	/*
+	/* Disable clock initially, hdmi_cec_adap_enable() manages it */
-	 * Initialize CEC clock divider: CEC needs 2MHz clock hence
+	REG_FLD_MOD(core->wp->base, HDMI_WP_CLK, 0, 5, 0);
-	 * set the devider to 24 to get 48/24=2MHz clock
-	 */
-	REG_FLD_MOD(core->wp->base, HDMI_WP_CLK, 0x18, 5, 0);
 
 	ret = cec_register_adapter(core->adap, &pdev->dev);
 	if (ret < 0) {

drivers/gpu/drm/omapdrm/dss/hdmi4_core.c

@@ -708,7 +708,7 @@ int hdmi4_audio_config(struct hdmi_core_data *core, struct hdmi_wp_data *wp,
 	else
 		acore.i2s_cfg.justification = HDMI_AUDIO_JUSTIFY_RIGHT;
 	/*
-	 * The I2S input word length is twice the lenght given in the IEC-60958
+	 * The I2S input word length is twice the length given in the IEC-60958
 	 * status word. If the word size is greater than
 	 * 20 bits, increment by one.
 	 */

drivers/gpu/drm/sun4i/sun8i_dw_hdmi.c

@@ -48,8 +48,13 @@ static enum drm_mode_status
 sun8i_dw_hdmi_mode_valid_h6(struct drm_connector *connector,
 			    const struct drm_display_mode *mode)
 {
-	/* This is max for HDMI 2.0b (4K@60Hz) */
+	/*
-	if (mode->clock > 594000)
+	 * Controller support maximum of 594 MHz, which correlates to
+	 * 4K@60Hz 4:4:4 or RGB. However, for frequencies greater than
+	 * 340 MHz scrambling has to be enabled. Because scrambling is
+	 * not yet implemented, just limit to 340 MHz for now.
+	 */
+	if (mode->clock > 340000)
 		return MODE_CLOCK_HIGH;
 
 	return MODE_OK;

drivers/gpu/drm/sun4i/sun8i_tcon_top.c

@@ -227,7 +227,7 @@ static int sun8i_tcon_top_bind(struct device *dev, struct device *master,
 
 err_unregister_gates:
 	for (i = 0; i < CLK_NUM; i++)
-		if (clk_data->hws[i])
+		if (!IS_ERR_OR_NULL(clk_data->hws[i]))
 			clk_hw_unregister_gate(clk_data->hws[i]);
 	clk_disable_unprepare(tcon_top->bus);
 err_assert_reset:
@@ -245,7 +245,8 @@ static void sun8i_tcon_top_unbind(struct device *dev, struct device *master,
 
 	of_clk_del_provider(dev->of_node);
 	for (i = 0; i < CLK_NUM; i++)
-		clk_hw_unregister_gate(clk_data->hws[i]);
+		if (clk_data->hws[i])
+			clk_hw_unregister_gate(clk_data->hws[i]);
 
 	clk_disable_unprepare(tcon_top->bus);
 	reset_control_assert(tcon_top->rst);

drivers/gpu/drm/udl/udl_drv.c

@@ -52,6 +52,7 @@ static struct drm_driver driver = {
 	.driver_features = DRIVER_MODESET | DRIVER_GEM | DRIVER_PRIME,
 	.load = udl_driver_load,
 	.unload = udl_driver_unload,
+	.release = udl_driver_release,
 
 	/* gem hooks */
 	.gem_free_object_unlocked = udl_gem_free_object,

drivers/gpu/drm/udl/udl_drv.h

@@ -104,6 +104,7 @@ void udl_urb_completion(struct urb *urb);
 
 int udl_driver_load(struct drm_device *dev, unsigned long flags);
 void udl_driver_unload(struct drm_device *dev);
+void udl_driver_release(struct drm_device *dev);
 
 int udl_fbdev_init(struct drm_device *dev);
 void udl_fbdev_cleanup(struct drm_device *dev);

drivers/gpu/drm/udl/udl_main.c

@@ -379,6 +379,12 @@ void udl_driver_unload(struct drm_device *dev)
 		udl_free_urb_list(dev);
 
 	udl_fbdev_cleanup(dev);
-	udl_modeset_cleanup(dev);
 	kfree(udl);
 }
+
+void udl_driver_release(struct drm_device *dev)
+{
+	udl_modeset_cleanup(dev);
+	drm_dev_fini(dev);
+	kfree(dev);
+}

drivers/gpu/host1x/hw/channel_hw.c

@@ -114,7 +114,7 @@ static inline void synchronize_syncpt_base(struct host1x_job *job)
 
 static void host1x_channel_set_streamid(struct host1x_channel *channel)
 {
-#if HOST1X_HW >= 6
+#if IS_ENABLED(CONFIG_IOMMU_API) &&  HOST1X_HW >= 6
 	struct iommu_fwspec *spec = dev_iommu_fwspec_get(channel->dev->parent);
 	u32 sid = spec ? spec->ids[0] & 0xffff : 0x7f;
 

drivers/infiniband/hw/hfi1/chip.c

@@ -13232,7 +13232,7 @@ static int set_up_context_variables(struct hfi1_devdata *dd)
 	int total_contexts;
 	int ret;
 	unsigned ngroups;
-	int qos_rmt_count;
+	int rmt_count;
 	int user_rmt_reduced;
 	u32 n_usr_ctxts;
 	u32 send_contexts = chip_send_contexts(dd);
@@ -13294,10 +13294,20 @@ static int set_up_context_variables(struct hfi1_devdata *dd)
 		n_usr_ctxts = rcv_contexts - total_contexts;
 	}
 
-	/* each user context requires an entry in the RMT */
+	/*
-	qos_rmt_count = qos_rmt_entries(dd, NULL, NULL);
+	 * The RMT entries are currently allocated as shown below:
-	if (qos_rmt_count + n_usr_ctxts > NUM_MAP_ENTRIES) {
+	 * 1. QOS (0 to 128 entries);
-		user_rmt_reduced = NUM_MAP_ENTRIES - qos_rmt_count;
+	 * 2. FECN for PSM (num_user_contexts + num_vnic_contexts);
+	 * 3. VNIC (num_vnic_contexts).
+	 * It should be noted that PSM FECN oversubscribe num_vnic_contexts
+	 * entries of RMT because both VNIC and PSM could allocate any receive
+	 * context between dd->first_dyn_alloc_text and dd->num_rcv_contexts,
+	 * and PSM FECN must reserve an RMT entry for each possible PSM receive
+	 * context.
+	 */
+	rmt_count = qos_rmt_entries(dd, NULL, NULL) + (num_vnic_contexts * 2);
+	if (rmt_count + n_usr_ctxts > NUM_MAP_ENTRIES) {
+		user_rmt_reduced = NUM_MAP_ENTRIES - rmt_count;
 		dd_dev_err(dd,
 			   "RMT size is reducing the number of user receive contexts from %u to %d\n",
 			   n_usr_ctxts,
@@ -14285,9 +14295,11 @@ static void init_user_fecn_handling(struct hfi1_devdata *dd,
 	u64 reg;
 	int i, idx, regoff, regidx;
 	u8 offset;
+	u32 total_cnt;
 
 	/* there needs to be enough room in the map table */
-	if (rmt->used + dd->num_user_contexts >= NUM_MAP_ENTRIES) {
+	total_cnt = dd->num_rcv_contexts - dd->first_dyn_alloc_ctxt;
+	if (rmt->used + total_cnt >= NUM_MAP_ENTRIES) {
 		dd_dev_err(dd, "User FECN handling disabled - too many user contexts allocated\n");
 		return;
 	}
@@ -14341,7 +14353,7 @@ static void init_user_fecn_handling(struct hfi1_devdata *dd,
 	/* add rule 1 */
 	add_rsm_rule(dd, RSM_INS_FECN, &rrd);
 
-	rmt->used += dd->num_user_contexts;
+	rmt->used += total_cnt;
 }
 
 /* Initialize RSM for VNIC */

drivers/infiniband/hw/hfi1/qp.c

@@ -898,7 +898,9 @@ void notify_error_qp(struct rvt_qp *qp)
 		if (!list_empty(&priv->s_iowait.list) &&
 		    !(qp->s_flags & RVT_S_BUSY) &&
 		    !(priv->s_flags & RVT_S_BUSY)) {
-			qp->s_flags &= ~RVT_S_ANY_WAIT_IO;
+			qp->s_flags &= ~HFI1_S_ANY_WAIT_IO;
+			iowait_clear_flag(&priv->s_iowait, IOWAIT_PENDING_IB);
+			iowait_clear_flag(&priv->s_iowait, IOWAIT_PENDING_TID);
 			list_del_init(&priv->s_iowait.list);
 			priv->s_iowait.lock = NULL;
 			rvt_put_qp(qp);

drivers/infiniband/hw/hfi1/rc.c

@@ -3088,7 +3088,7 @@ send_last:
 			update_ack_queue(qp, next);
 		}
 		e = &qp->s_ack_queue[qp->r_head_ack_queue];
-		if (e->opcode == OP(RDMA_READ_REQUEST) && e->rdma_sge.mr) {
+		if (e->rdma_sge.mr) {
 			rvt_put_mr(e->rdma_sge.mr);
 			e->rdma_sge.mr = NULL;
 		}
@@ -3166,7 +3166,7 @@ send_last:
 			update_ack_queue(qp, next);
 		}
 		e = &qp->s_ack_queue[qp->r_head_ack_queue];
-		if (e->opcode == OP(RDMA_READ_REQUEST) && e->rdma_sge.mr) {
+		if (e->rdma_sge.mr) {
 			rvt_put_mr(e->rdma_sge.mr);
 			e->rdma_sge.mr = NULL;
 		}

drivers/infiniband/hw/hfi1/tid_rdma.c

@@ -5017,24 +5017,14 @@ int hfi1_make_tid_rdma_pkt(struct rvt_qp *qp, struct hfi1_pkt_state *ps)
 	    make_tid_rdma_ack(qp, ohdr, ps))
 		return 1;
 
-	if (!(ib_rvt_state_ops[qp->state] & RVT_PROCESS_SEND_OK)) {
+	/*
-		if (!(ib_rvt_state_ops[qp->state] & RVT_FLUSH_SEND))
+	 * Bail out if we can't send data.
-			goto bail;
+	 * Be reminded that this check must been done after the call to
-		/* We are in the error state, flush the work request. */
+	 * make_tid_rdma_ack() because the responding QP could be in
-		if (qp->s_last == READ_ONCE(qp->s_head))
+	 * RTR state where it can send TID RDMA ACK, not TID RDMA WRITE DATA.
-			goto bail;
+	 */
-		/* If DMAs are in progress, we can't flush immediately. */
+	if (!(ib_rvt_state_ops[qp->state] & RVT_PROCESS_SEND_OK))
-		if (iowait_sdma_pending(&priv->s_iowait)) {
+		goto bail;
-			qp->s_flags |= RVT_S_WAIT_DMA;
-			goto bail;
-		}
-		clear_ahg(qp);
-		wqe = rvt_get_swqe_ptr(qp, qp->s_last);
-		hfi1_trdma_send_complete(qp, wqe, qp->s_last != qp->s_acked ?
-					 IB_WC_SUCCESS : IB_WC_WR_FLUSH_ERR);
-		/* will get called again */
-		goto done_free_tx;
-	}
 
 	if (priv->s_flags & RVT_S_WAIT_ACK)
 		goto bail;
@@ -5144,11 +5134,6 @@ int hfi1_make_tid_rdma_pkt(struct rvt_qp *qp, struct hfi1_pkt_state *ps)
 	hfi1_make_ruc_header(qp, ohdr, (opcode << 24), bth1, bth2,
 			     middle, ps);
 	return 1;
-done_free_tx:
-	hfi1_put_txreq(ps->s_txreq);
-	ps->s_txreq = NULL;
-	return 1;
-
 bail:
 	hfi1_put_txreq(ps->s_txreq);
 bail_no_tx:

drivers/infiniband/hw/hns/hns_roce_hem.c

@@ -792,6 +792,8 @@ void *hns_roce_table_find(struct hns_roce_dev *hr_dev,
 		idx_offset = (obj & (table->num_obj - 1)) % obj_per_chunk;
 		dma_offset = offset = idx_offset * table->obj_size;
 	} else {
+		u32 seg_size = 64; /* 8 bytes per BA and 8 BA per segment */
+
 		hns_roce_calc_hem_mhop(hr_dev, table, &mhop_obj, &mhop);
 		/* mtt mhop */
 		i = mhop.l0_idx;
@@ -803,8 +805,8 @@ void *hns_roce_table_find(struct hns_roce_dev *hr_dev,
 			hem_idx = i;
 
 		hem = table->hem[hem_idx];
-		dma_offset = offset = (obj & (table->num_obj - 1)) *
+		dma_offset = offset = (obj & (table->num_obj - 1)) * seg_size %
-				       table->obj_size % mhop.bt_chunk_size;
+				       mhop.bt_chunk_size;
 		if (mhop.hop_num == 2)
 			dma_offset = offset = 0;
 	}

drivers/infiniband/hw/hns/hns_roce_mr.c

@@ -746,7 +746,6 @@ static int hns_roce_write_mtt_chunk(struct hns_roce_dev *hr_dev,
 	struct hns_roce_hem_table *table;
 	dma_addr_t dma_handle;
 	__le64 *mtts;
-	u32 s = start_index * sizeof(u64);
 	u32 bt_page_size;
 	u32 i;
 
@@ -780,7 +779,8 @@ static int hns_roce_write_mtt_chunk(struct hns_roce_dev *hr_dev,
 		return -EINVAL;
 
 	mtts = hns_roce_table_find(hr_dev, table,
-				mtt->first_seg + s / hr_dev->caps.mtt_entry_sz,
+				mtt->first_seg +
+				start_index / HNS_ROCE_MTT_ENTRY_PER_SEG,
 				&dma_handle);
 	if (!mtts)
 		return -ENOMEM;