Merge 5.10.155 into android12-5.10-lts

Changes in 5.10.155
	fuse: fix readdir cache race
	hwspinlock: qcom: correct MMIO max register for newer SoCs
	phy: stm32: fix an error code in probe
	wifi: cfg80211: silence a sparse RCU warning
	wifi: cfg80211: fix memory leak in query_regdb_file()
	bpf, sockmap: Fix the sk->sk_forward_alloc warning of sk_stream_kill_queues
	bpftool: Fix NULL pointer dereference when pin {PROG, MAP, LINK} without FILE
	HID: hyperv: fix possible memory leak in mousevsc_probe()
	bpf: Support for pointers beyond pkt_end.
	bpf: Add helper macro bpf_for_each_reg_in_vstate
	bpf: Fix wrong reg type conversion in release_reference()
	net: gso: fix panic on frag_list with mixed head alloc types
	macsec: delete new rxsc when offload fails
	macsec: fix secy->n_rx_sc accounting
	macsec: fix detection of RXSCs when toggling offloading
	macsec: clear encryption keys from the stack after setting up offload
	net: tun: Fix memory leaks of napi_get_frags
	bnxt_en: Fix possible crash in bnxt_hwrm_set_coal()
	bnxt_en: fix potentially incorrect return value for ndo_rx_flow_steer
	net: fman: Unregister ethernet device on removal
	capabilities: fix undefined behavior in bit shift for CAP_TO_MASK
	KVM: s390x: fix SCK locking
	KVM: s390: pv: don't allow userspace to set the clock under PV
	net: lapbether: fix issue of dev reference count leakage in lapbeth_device_event()
	hamradio: fix issue of dev reference count leakage in bpq_device_event()
	drm/vc4: Fix missing platform_unregister_drivers() call in vc4_drm_register()
	tcp: prohibit TCP_REPAIR_OPTIONS if data was already sent
	ipv6: addrlabel: fix infoleak when sending struct ifaddrlblmsg to network
	can: af_can: fix NULL pointer dereference in can_rx_register()
	net: stmmac: dwmac-meson8b: fix meson8b_devm_clk_prepare_enable()
	net: broadcom: Fix BCMGENET Kconfig
	tipc: fix the msg->req tlv len check in tipc_nl_compat_name_table_dump_header
	dmaengine: pxa_dma: use platform_get_irq_optional
	dmaengine: mv_xor_v2: Fix a resource leak in mv_xor_v2_remove()
	drivers: net: xgene: disable napi when register irq failed in xgene_enet_open()
	perf stat: Fix printing os->prefix in CSV metrics output
	net: marvell: prestera: fix memory leak in prestera_rxtx_switch_init()
	net: nixge: disable napi when enable interrupts failed in nixge_open()
	net/mlx5: Allow async trigger completion execution on single CPU systems
	net/mlx5e: E-Switch, Fix comparing termination table instance
	net: cpsw: disable napi in cpsw_ndo_open()
	net: cxgb3_main: disable napi when bind qsets failed in cxgb_up()
	cxgb4vf: shut down the adapter when t4vf_update_port_info() failed in cxgb4vf_open()
	net: phy: mscc: macsec: clear encryption keys when freeing a flow
	net: atlantic: macsec: clear encryption keys from the stack
	ethernet: s2io: disable napi when start nic failed in s2io_card_up()
	net: mv643xx_eth: disable napi when init rxq or txq failed in mv643xx_eth_open()
	ethernet: tundra: free irq when alloc ring failed in tsi108_open()
	net: macvlan: fix memory leaks of macvlan_common_newlink
	riscv: process: fix kernel info leakage
	riscv: vdso: fix build with llvm
	riscv: Enable CMA support
	riscv: Separate memory init from paging init
	riscv: fix reserved memory setup
	arm64: efi: Fix handling of misaligned runtime regions and drop warning
	MIPS: jump_label: Fix compat branch range check
	mmc: cqhci: Provide helper for resetting both SDHCI and CQHCI
	mmc: sdhci-of-arasan: Fix SDHCI_RESET_ALL for CQHCI
	mmc: sdhci_am654: Fix SDHCI_RESET_ALL for CQHCI
	mmc: sdhci-tegra: Fix SDHCI_RESET_ALL for CQHCI
	ALSA: hda/hdmi - enable runtime pm for more AMD display audio
	ALSA: hda/ca0132: add quirk for EVGA Z390 DARK
	ALSA: hda: fix potential memleak in 'add_widget_node'
	ALSA: hda/realtek: Add Positivo C6300 model quirk
	ALSA: usb-audio: Add quirk entry for M-Audio Micro
	ALSA: usb-audio: Add DSD support for Accuphase DAC-60
	vmlinux.lds.h: Fix placement of '.data..decrypted' section
	ata: libata-scsi: fix SYNCHRONIZE CACHE (16) command failure
	nilfs2: fix deadlock in nilfs_count_free_blocks()
	nilfs2: fix use-after-free bug of ns_writer on remount
	drm/i915/dmabuf: fix sg_table handling in map_dma_buf
	platform/x86: hp_wmi: Fix rfkill causing soft blocked wifi
	btrfs: selftests: fix wrong error check in btrfs_free_dummy_root()
	mms: sdhci-esdhc-imx: Fix SDHCI_RESET_ALL for CQHCI
	udf: Fix a slab-out-of-bounds write bug in udf_find_entry()
	mm/memremap.c: map FS_DAX device memory as decrypted
	can: j1939: j1939_send_one(): fix missing CAN header initialization
	cert host tools: Stop complaining about deprecated OpenSSL functions
	dmaengine: at_hdmac: Fix at_lli struct definition
	dmaengine: at_hdmac: Don't start transactions at tx_submit level
	dmaengine: at_hdmac: Start transfer for cyclic channels in issue_pending
	dmaengine: at_hdmac: Fix premature completion of desc in issue_pending
	dmaengine: at_hdmac: Do not call the complete callback on device_terminate_all
	dmaengine: at_hdmac: Protect atchan->status with the channel lock
	dmaengine: at_hdmac: Fix concurrency problems by removing atc_complete_all()
	dmaengine: at_hdmac: Fix concurrency over descriptor
	dmaengine: at_hdmac: Free the memset buf without holding the chan lock
	dmaengine: at_hdmac: Fix concurrency over the active list
	dmaengine: at_hdmac: Fix descriptor handling when issuing it to hardware
	dmaengine: at_hdmac: Fix completion of unissued descriptor in case of errors
	dmaengine: at_hdmac: Don't allow CPU to reorder channel enable
	dmaengine: at_hdmac: Fix impossible condition
	dmaengine: at_hdmac: Check return code of dma_async_device_register
	net: tun: call napi_schedule_prep() to ensure we own a napi
	mmc: sdhci-esdhc-imx: Convert the driver to DT-only
	x86/cpu: Restore AMD's DE_CFG MSR after resume
	io_uring: kill goto error handling in io_sqpoll_wait_sq()
	Linux 5.10.155

Change-Id: Id7d803ed2db044ef465aab7e80fca8b4b07df258
Signed-off-by: Greg Kroah-Hartman <gregkh@google.com>

Documentation/virt/kvm/devices/vm.rst

@@ -215,6 +215,7 @@ KVM_S390_VM_TOD_EXT).
 :Parameters: address of a buffer in user space to store the data (u8) to
 :Returns:   -EFAULT if the given address is not accessible from kernel space;
 	    -EINVAL if setting the TOD clock extension to != 0 is not supported
+	    -EOPNOTSUPP for a PV guest (TOD managed by the ultravisor)
 
 3.2. ATTRIBUTE: KVM_S390_VM_TOD_LOW
 -----------------------------------
@@ -224,6 +225,7 @@ the POP (u64).
 
 :Parameters: address of a buffer in user space to store the data (u64) to
 :Returns:    -EFAULT if the given address is not accessible from kernel space
+	     -EOPNOTSUPP for a PV guest (TOD managed by the ultravisor)
 
 3.3. ATTRIBUTE: KVM_S390_VM_TOD_EXT
 -----------------------------------
@@ -237,6 +239,7 @@ it, it is stored as 0 and not allowed to be set to a value != 0.
 	     (kvm_s390_vm_tod_clock) to
 :Returns:   -EFAULT if the given address is not accessible from kernel space;
 	    -EINVAL if setting the TOD clock extension to != 0 is not supported
+	    -EOPNOTSUPP for a PV guest (TOD managed by the ultravisor)
 
 4. GROUP: KVM_S390_VM_CRYPTO
 ============================

Makefile

@@ -1,7 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0
 VERSION = 5
 PATCHLEVEL = 10
-SUBLEVEL = 154
+SUBLEVEL = 155
 EXTRAVERSION =
 NAME = Dare mighty things
 

arch/arm64/kernel/efi.c

@@ -12,6 +12,14 @@
 
 #include <asm/efi.h>
 
+static bool region_is_misaligned(const efi_memory_desc_t *md)
+{
+	if (PAGE_SIZE == EFI_PAGE_SIZE)
+		return false;
+	return !PAGE_ALIGNED(md->phys_addr) ||
+	       !PAGE_ALIGNED(md->num_pages << EFI_PAGE_SHIFT);
+}
+
 /*
  * Only regions of type EFI_RUNTIME_SERVICES_CODE need to be
  * executable, everything else can be mapped with the XN bits
@@ -25,14 +33,22 @@ static __init pteval_t create_mapping_protection(efi_memory_desc_t *md)
 	if (type == EFI_MEMORY_MAPPED_IO)
 		return PROT_DEVICE_nGnRE;
 
-	if (WARN_ONCE(!PAGE_ALIGNED(md->phys_addr),
-		      "UEFI Runtime regions are not aligned to 64 KB -- buggy firmware?"))
+	if (region_is_misaligned(md)) {
+		static bool __initdata code_is_misaligned;
+
 		/*
-		 * If the region is not aligned to the page size of the OS, we
-		 * can not use strict permissions, since that would also affect
-		 * the mapping attributes of the adjacent regions.
+		 * Regions that are not aligned to the OS page size cannot be
+		 * mapped with strict permissions, as those might interfere
+		 * with the permissions that are needed by the adjacent
+		 * region's mapping. However, if we haven't encountered any
+		 * misaligned runtime code regions so far, we can safely use
+		 * non-executable permissions for non-code regions.
 		 */
-		return pgprot_val(PAGE_KERNEL_EXEC);
+		code_is_misaligned |= (type == EFI_RUNTIME_SERVICES_CODE);
+
+		return code_is_misaligned ? pgprot_val(PAGE_KERNEL_EXEC)
+					  : pgprot_val(PAGE_KERNEL);
+	}
 
 	/* R-- */
 	if ((attr & (EFI_MEMORY_XP | EFI_MEMORY_RO)) ==
@@ -62,19 +78,16 @@ int __init efi_create_mapping(struct mm_struct *mm, efi_memory_desc_t *md)
 	bool page_mappings_only = (md->type == EFI_RUNTIME_SERVICES_CODE ||
 				   md->type == EFI_RUNTIME_SERVICES_DATA);
 
-	if (!PAGE_ALIGNED(md->phys_addr) ||
-	    !PAGE_ALIGNED(md->num_pages << EFI_PAGE_SHIFT)) {
-		/*
-		 * If the end address of this region is not aligned to page
-		 * size, the mapping is rounded up, and may end up sharing a
-		 * page frame with the next UEFI memory region. If we create
-		 * a block entry now, we may need to split it again when mapping
-		 * the next region, and support for that is going to be removed
-		 * from the MMU routines. So avoid block mappings altogether in
-		 * that case.
-		 */
+	/*
+	 * If this region is not aligned to the page size used by the OS, the
+	 * mapping will be rounded outwards, and may end up sharing a page
+	 * frame with an adjacent runtime memory region. Given that the page
+	 * table descriptor covering the shared page will be rewritten when the
+	 * adjacent region gets mapped, we must avoid block mappings here so we
+	 * don't have to worry about splitting them when that happens.
+	 */
+	if (region_is_misaligned(md))
 		page_mappings_only = true;
-	}
 
 	create_pgd_mapping(mm, md->phys_addr, md->virt_addr,
 			   md->num_pages << EFI_PAGE_SHIFT,
@@ -101,6 +114,9 @@ int __init efi_set_mapping_permissions(struct mm_struct *mm,
 	BUG_ON(md->type != EFI_RUNTIME_SERVICES_CODE &&
 	       md->type != EFI_RUNTIME_SERVICES_DATA);
 
+	if (region_is_misaligned(md))
+		return 0;
+
 	/*
 	 * Calling apply_to_page_range() is only safe on regions that are
 	 * guaranteed to be mapped down to pages. Since we are only called

arch/mips/kernel/jump_label.c

@@ -56,7 +56,7 @@ void arch_jump_label_transform(struct jump_entry *e,
 			 * The branch offset must fit in the instruction's 26
 			 * bit field.
 			 */
-			WARN_ON((offset >= BIT(25)) ||
+			WARN_ON((offset >= (long)BIT(25)) ||
 				(offset < -(long)BIT(25)));
 
 			insn.j_format.opcode = bc6_op;

arch/riscv/include/asm/pgtable.h

@@ -470,6 +470,7 @@ extern void *dtb_early_va;
 extern uintptr_t dtb_early_pa;
 void setup_bootmem(void);
 void paging_init(void);
+void misc_mem_init(void);
 
 #define FIRST_USER_ADDRESS  0
 

arch/riscv/kernel/process.c

@@ -111,6 +111,8 @@ int copy_thread(unsigned long clone_flags, unsigned long usp, unsigned long arg,
 {
 	struct pt_regs *childregs = task_pt_regs(p);
 
+	memset(&p->thread.s, 0, sizeof(p->thread.s));
+
 	/* p->thread holds context to be restored by __switch_to() */
 	if (unlikely(p->flags & PF_KTHREAD)) {
 		/* Kernel thread */

arch/riscv/kernel/setup.c

@@ -96,6 +96,8 @@ void __init setup_arch(char **cmdline_p)
 	else
 		pr_err("No DTB found in kernel mappings\n");
 #endif
+	early_init_fdt_scan_reserved_mem();
+	misc_mem_init();
 
 #ifdef CONFIG_SWIOTLB
 	swiotlb_init(1);

arch/riscv/kernel/vdso/Makefile

@@ -30,7 +30,7 @@ obj-y += vdso.o vdso-syms.o
 CPPFLAGS_vdso.lds += -P -C -U$(ARCH)
 
 # Disable -pg to prevent insert call site
-CFLAGS_REMOVE_vgettimeofday.o = $(CC_FLAGS_FTRACE) -Os
+CFLAGS_REMOVE_vgettimeofday.o = $(CC_FLAGS_FTRACE)
 
 # Disable profiling and instrumentation for VDSO code
 GCOV_PROFILE := n

arch/riscv/mm/init.c

@@ -13,6 +13,7 @@
 #include <linux/of_fdt.h>
 #include <linux/libfdt.h>
 #include <linux/set_memory.h>
+#include <linux/dma-map-ops.h>
 
 #include <asm/fixmap.h>
 #include <asm/tlbflush.h>
@@ -41,13 +42,14 @@ struct pt_alloc_ops {
 #endif
 };
 
+static phys_addr_t dma32_phys_limit __ro_after_init;
+
 static void __init zone_sizes_init(void)
 {
 	unsigned long max_zone_pfns[MAX_NR_ZONES] = { 0, };
 
 #ifdef CONFIG_ZONE_DMA32
-	max_zone_pfns[ZONE_DMA32] = PFN_DOWN(min(4UL * SZ_1G,
-			(unsigned long) PFN_PHYS(max_low_pfn)));
+	max_zone_pfns[ZONE_DMA32] = PFN_DOWN(dma32_phys_limit);
 #endif
 	max_zone_pfns[ZONE_NORMAL] = max_low_pfn;
 
@@ -193,6 +195,7 @@ void __init setup_bootmem(void)
 
 	max_pfn = PFN_DOWN(dram_end);
 	max_low_pfn = max_pfn;
+	dma32_phys_limit = min(4UL * SZ_1G, (unsigned long)PFN_PHYS(max_low_pfn));
 	set_max_mapnr(max_low_pfn);
 
 #ifdef CONFIG_BLK_DEV_INITRD
@@ -205,7 +208,7 @@ void __init setup_bootmem(void)
 	 */
 	memblock_reserve(dtb_early_pa, fdt_totalsize(dtb_early_va));
 
-	early_init_fdt_scan_reserved_mem();
+	dma_contiguous_reserve(dma32_phys_limit);
 	memblock_allow_resize();
 	memblock_dump_all();
 }
@@ -665,8 +668,12 @@ static void __init resource_init(void)
 void __init paging_init(void)
 {
 	setup_vm_final();
-	sparse_init();
 	setup_zero_page();
+}
+
+void __init misc_mem_init(void)
+{
+	sparse_init();
 	zone_sizes_init();
 	resource_init();
 }

arch/s390/kvm/kvm-s390.c

@@ -1092,6 +1092,8 @@ static int kvm_s390_vm_get_migration(struct kvm *kvm,
 	return 0;
 }
 
+static void __kvm_s390_set_tod_clock(struct kvm *kvm, const struct kvm_s390_vm_tod_clock *gtod);
+
 static int kvm_s390_set_tod_ext(struct kvm *kvm, struct kvm_device_attr *attr)
 {
 	struct kvm_s390_vm_tod_clock gtod;
@@ -1101,7 +1103,7 @@ static int kvm_s390_set_tod_ext(struct kvm *kvm, struct kvm_device_attr *attr)
 
 	if (!test_kvm_facility(kvm, 139) && gtod.epoch_idx)
 		return -EINVAL;
-	kvm_s390_set_tod_clock(kvm, &gtod);
+	__kvm_s390_set_tod_clock(kvm, &gtod);
 
 	VM_EVENT(kvm, 3, "SET: TOD extension: 0x%x, TOD base: 0x%llx",
 		gtod.epoch_idx, gtod.tod);
@@ -1132,7 +1134,7 @@ static int kvm_s390_set_tod_low(struct kvm *kvm, struct kvm_device_attr *attr)
 			   sizeof(gtod.tod)))
 		return -EFAULT;
 
-	kvm_s390_set_tod_clock(kvm, &gtod);
+	__kvm_s390_set_tod_clock(kvm, &gtod);
 	VM_EVENT(kvm, 3, "SET: TOD base: 0x%llx", gtod.tod);
 	return 0;
 }
@@ -1144,6 +1146,16 @@ static int kvm_s390_set_tod(struct kvm *kvm, struct kvm_device_attr *attr)
 	if (attr->flags)
 		return -EINVAL;
 
+	mutex_lock(&kvm->lock);
+	/*
+	 * For protected guests, the TOD is managed by the ultravisor, so trying
+	 * to change it will never bring the expected results.
+	 */
+	if (kvm_s390_pv_is_protected(kvm)) {
+		ret = -EOPNOTSUPP;
+		goto out_unlock;
+	}
+
 	switch (attr->attr) {
 	case KVM_S390_VM_TOD_EXT:
 		ret = kvm_s390_set_tod_ext(kvm, attr);
@@ -1158,6 +1170,9 @@ static int kvm_s390_set_tod(struct kvm *kvm, struct kvm_device_attr *attr)
 		ret = -ENXIO;
 		break;
 	}
+
+out_unlock:
+	mutex_unlock(&kvm->lock);
 	return ret;
 }
 
@@ -3862,14 +3877,12 @@ retry:
 	return 0;
 }
 
-void kvm_s390_set_tod_clock(struct kvm *kvm,
-			    const struct kvm_s390_vm_tod_clock *gtod)
+static void __kvm_s390_set_tod_clock(struct kvm *kvm, const struct kvm_s390_vm_tod_clock *gtod)
 {
 	struct kvm_vcpu *vcpu;
 	struct kvm_s390_tod_clock_ext htod;
 	int i;
 
-	mutex_lock(&kvm->lock);
 	preempt_disable();
 
 	get_tod_clock_ext((char *)&htod);
@@ -3890,7 +3903,15 @@ void kvm_s390_set_tod_clock(struct kvm *kvm,
 
 	kvm_s390_vcpu_unblock_all(kvm);
 	preempt_enable();
+}
+
+int kvm_s390_try_set_tod_clock(struct kvm *kvm, const struct kvm_s390_vm_tod_clock *gtod)
+{
+	if (!mutex_trylock(&kvm->lock))
+		return 0;
+	__kvm_s390_set_tod_clock(kvm, gtod);
 	mutex_unlock(&kvm->lock);
+	return 1;
 }
 
 /**

arch/s390/kvm/kvm-s390.h

@@ -326,8 +326,7 @@ int kvm_s390_handle_sigp(struct kvm_vcpu *vcpu);
 int kvm_s390_handle_sigp_pei(struct kvm_vcpu *vcpu);
 
 /* implemented in kvm-s390.c */
-void kvm_s390_set_tod_clock(struct kvm *kvm,
-			    const struct kvm_s390_vm_tod_clock *gtod);
+int kvm_s390_try_set_tod_clock(struct kvm *kvm, const struct kvm_s390_vm_tod_clock *gtod);
 long kvm_arch_fault_in_page(struct kvm_vcpu *vcpu, gpa_t gpa, int writable);
 int kvm_s390_store_status_unloaded(struct kvm_vcpu *vcpu, unsigned long addr);
 int kvm_s390_vcpu_store_status(struct kvm_vcpu *vcpu, unsigned long addr);

arch/s390/kvm/priv.c

@@ -102,7 +102,20 @@ static int handle_set_clock(struct kvm_vcpu *vcpu)
 		return kvm_s390_inject_prog_cond(vcpu, rc);
 
 	VCPU_EVENT(vcpu, 3, "SCK: setting guest TOD to 0x%llx", gtod.tod);
-	kvm_s390_set_tod_clock(vcpu->kvm, &gtod);
+	/*
+	 * To set the TOD clock the kvm lock must be taken, but the vcpu lock
+	 * is already held in handle_set_clock. The usual lock order is the
+	 * opposite.  As SCK is deprecated and should not be used in several
+	 * cases, for example when the multiple epoch facility or TOD clock
+	 * steering facility is installed (see Principles of Operation),  a
+	 * slow path can be used.  If the lock can not be taken via try_lock,
+	 * the instruction will be retried via -EAGAIN at a later point in
+	 * time.
+	 */
+	if (!kvm_s390_try_set_tod_clock(vcpu->kvm, &gtod)) {
+		kvm_s390_retry_instr(vcpu);
+		return -EAGAIN;
+	}
 
 	kvm_s390_set_psw_cc(vcpu, 0);
 	return 0;

arch/x86/include/asm/msr-index.h

@@ -489,6 +489,11 @@
 #define MSR_AMD64_CPUID_FN_1		0xc0011004
 #define MSR_AMD64_LS_CFG		0xc0011020
 #define MSR_AMD64_DC_CFG		0xc0011022
+
+#define MSR_AMD64_DE_CFG		0xc0011029
+#define MSR_AMD64_DE_CFG_LFENCE_SERIALIZE_BIT	 1
+#define MSR_AMD64_DE_CFG_LFENCE_SERIALIZE	BIT_ULL(MSR_AMD64_DE_CFG_LFENCE_SERIALIZE_BIT)
+
 #define MSR_AMD64_BU_CFG2		0xc001102a
 #define MSR_AMD64_IBSFETCHCTL		0xc0011030
 #define MSR_AMD64_IBSFETCHLINAD		0xc0011031
@@ -565,9 +570,6 @@
 #define FAM10H_MMIO_CONF_BASE_MASK	0xfffffffULL
 #define FAM10H_MMIO_CONF_BASE_SHIFT	20
 #define MSR_FAM10H_NODE_ID		0xc001100c
-#define MSR_F10H_DECFG			0xc0011029
-#define MSR_F10H_DECFG_LFENCE_SERIALIZE_BIT	1
-#define MSR_F10H_DECFG_LFENCE_SERIALIZE		BIT_ULL(MSR_F10H_DECFG_LFENCE_SERIALIZE_BIT)
 
 /* K8 MSRs */
 #define MSR_K8_TOP_MEM1			0xc001001a

arch/x86/kernel/cpu/amd.c

@@ -822,8 +822,6 @@ static void init_amd_gh(struct cpuinfo_x86 *c)
 		set_cpu_bug(c, X86_BUG_AMD_TLB_MMATCH);
 }
 
-#define MSR_AMD64_DE_CFG	0xC0011029
-
 static void init_amd_ln(struct cpuinfo_x86 *c)
 {
 	/*
@@ -1018,8 +1016,8 @@ static void init_amd(struct cpuinfo_x86 *c)
 		 * msr_set_bit() uses the safe accessors, too, even if the MSR
 		 * is not present.
 		 */
-		msr_set_bit(MSR_F10H_DECFG,
-			    MSR_F10H_DECFG_LFENCE_SERIALIZE_BIT);
+		msr_set_bit(MSR_AMD64_DE_CFG,
+			    MSR_AMD64_DE_CFG_LFENCE_SERIALIZE_BIT);
 
 		/* A serializing LFENCE stops RDTSC speculation */
 		set_cpu_cap(c, X86_FEATURE_LFENCE_RDTSC);

arch/x86/kernel/cpu/hygon.c

@@ -342,8 +342,8 @@ static void init_hygon(struct cpuinfo_x86 *c)
 		 * msr_set_bit() uses the safe accessors, too, even if the MSR
 		 * is not present.
 		 */
-		msr_set_bit(MSR_F10H_DECFG,
-			    MSR_F10H_DECFG_LFENCE_SERIALIZE_BIT);
+		msr_set_bit(MSR_AMD64_DE_CFG,
+			    MSR_AMD64_DE_CFG_LFENCE_SERIALIZE_BIT);
 
 		/* A serializing LFENCE stops RDTSC speculation */
 		set_cpu_cap(c, X86_FEATURE_LFENCE_RDTSC);

arch/x86/kvm/svm/svm.c

@@ -2475,9 +2475,9 @@ static int svm_get_msr_feature(struct kvm_msr_entry *msr)
 	msr->data = 0;
 
 	switch (msr->index) {
-	case MSR_F10H_DECFG:
-		if (boot_cpu_has(X86_FEATURE_LFENCE_RDTSC))
-			msr->data |= MSR_F10H_DECFG_LFENCE_SERIALIZE;
+	case MSR_AMD64_DE_CFG:
+		if (cpu_feature_enabled(X86_FEATURE_LFENCE_RDTSC))
+			msr->data |= MSR_AMD64_DE_CFG_LFENCE_SERIALIZE;
 		break;
 	case MSR_IA32_PERF_CAPABILITIES:
 		return 0;
@@ -2584,7 +2584,7 @@ static int svm_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 			msr_info->data = 0x1E;
 		}
 		break;
-	case MSR_F10H_DECFG:
+	case MSR_AMD64_DE_CFG:
 		msr_info->data = svm->msr_decfg;
 		break;
 	default:
@@ -2764,7 +2764,7 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr)
 	case MSR_VM_IGNNE:
 		vcpu_unimpl(vcpu, "unimplemented wrmsr: 0x%x data 0x%llx\n", ecx, data);
 		break;
-	case MSR_F10H_DECFG: {
+	case MSR_AMD64_DE_CFG: {
 		struct kvm_msr_entry msr_entry;
 
 		msr_entry.index = msr->index;

arch/x86/kvm/x86.c

@@ -1362,7 +1362,7 @@ static const u32 msr_based_features_all[] = {
 	MSR_IA32_VMX_EPT_VPID_CAP,
 	MSR_IA32_VMX_VMFUNC,
 
-	MSR_F10H_DECFG,
+	MSR_AMD64_DE_CFG,
 	MSR_IA32_UCODE_REV,
 	MSR_IA32_ARCH_CAPABILITIES,
 	MSR_IA32_PERF_CAPABILITIES,

arch/x86/power/cpu.c

@@ -535,6 +535,7 @@ static void pm_save_spec_msr(void)
 		MSR_TSX_FORCE_ABORT,
 		MSR_IA32_MCU_OPT_CTRL,
 		MSR_AMD64_LS_CFG,
+		MSR_AMD64_DE_CFG,
 	};
 
 	msr_build_context(spec_msr_id, ARRAY_SIZE(spec_msr_id));

drivers/ata/libata-scsi.c

@@ -3303,6 +3303,7 @@ static unsigned int ata_scsiop_maint_in(struct ata_scsi_args *args, u8 *rbuf)
 	case REPORT_LUNS:
 	case REQUEST_SENSE:
 	case SYNCHRONIZE_CACHE:
+	case SYNCHRONIZE_CACHE_16:
 	case REZERO_UNIT:
 	case SEEK_6:
 	case SEEK_10:
@@ -3969,6 +3970,7 @@ static inline ata_xlat_func_t ata_get_xlat_func(struct ata_device *dev, u8 cmd)
 		return ata_scsi_write_same_xlat;
 
 	case SYNCHRONIZE_CACHE:
+	case SYNCHRONIZE_CACHE_16:
 		if (ata_try_flush_cache(dev))
 			return ata_scsi_flush_xlat;
 		break;
@@ -4215,6 +4217,7 @@ void ata_scsi_simulate(struct ata_device *dev, struct scsi_cmnd *cmd)
 	 * turning this into a no-op.
 	 */
 	case SYNCHRONIZE_CACHE:
+	case SYNCHRONIZE_CACHE_16:
 		fallthrough;
 
 	/* no-op's, complete with success */

drivers/dma/at_hdmac.c

@@ -237,6 +237,8 @@ static void atc_dostart(struct at_dma_chan *atchan, struct at_desc *first)
 		       ATC_SPIP_BOUNDARY(first->boundary));
 	channel_writel(atchan, DPIP, ATC_DPIP_HOLE(first->dst_hole) |
 		       ATC_DPIP_BOUNDARY(first->boundary));
+	/* Don't allow CPU to reorder channel enable. */
+	wmb();
 	dma_writel(atdma, CHER, atchan->mask);
 
 	vdbg_dump_regs(atchan);
@@ -297,7 +299,8 @@ static int atc_get_bytes_left(struct dma_chan *chan, dma_cookie_t cookie)
 	struct at_desc *desc_first = atc_first_active(atchan);
 	struct at_desc *desc;
 	int ret;
-	u32 ctrla, dscr, trials;
+	u32 ctrla, dscr;
+	unsigned int i;
 
 	/*
 	 * If the cookie doesn't match to the currently running transfer then
@@ -367,7 +370,7 @@ static int atc_get_bytes_left(struct dma_chan *chan, dma_cookie_t cookie)
 		dscr = channel_readl(atchan, DSCR);
 		rmb(); /* ensure DSCR is read before CTRLA */
 		ctrla = channel_readl(atchan, CTRLA);
-		for (trials = 0; trials < ATC_MAX_DSCR_TRIALS; ++trials) {
+		for (i = 0; i < ATC_MAX_DSCR_TRIALS; ++i) {
 			u32 new_dscr;
 
 			rmb(); /* ensure DSCR is read after CTRLA */
@@ -393,7 +396,7 @@ static int atc_get_bytes_left(struct dma_chan *chan, dma_cookie_t cookie)
 			rmb(); /* ensure DSCR is read before CTRLA */
 			ctrla = channel_readl(atchan, CTRLA);
 		}
-		if (unlikely(trials >= ATC_MAX_DSCR_TRIALS))
+		if (unlikely(i == ATC_MAX_DSCR_TRIALS))
 			return -ETIMEDOUT;
 
 		/* for the first descriptor we can be more accurate */
@@ -443,18 +446,6 @@ atc_chain_complete(struct at_dma_chan *atchan, struct at_desc *desc)
 	if (!atc_chan_is_cyclic(atchan))
 		dma_cookie_complete(txd);
 
-	/* If the transfer was a memset, free our temporary buffer */
-	if (desc->memset_buffer) {
-		dma_pool_free(atdma->memset_pool, desc->memset_vaddr,
-			      desc->memset_paddr);
-		desc->memset_buffer = false;
-	}
-
-	/* move children to free_list */
-	list_splice_init(&desc->tx_list, &atchan->free_list);
-	/* move myself to free_list */
-	list_move(&desc->desc_node, &atchan->free_list);
-
 	spin_unlock_irqrestore(&atchan->lock, flags);
 
 	dma_descriptor_unmap(txd);
@@ -464,42 +455,20 @@ atc_chain_complete(struct at_dma_chan *atchan, struct at_desc *desc)
 		dmaengine_desc_get_callback_invoke(txd, NULL);
 
 	dma_run_dependencies(txd);
-}
-
-/**
- * atc_complete_all - finish work for all transactions
- * @atchan: channel to complete transactions for
- *
- * Eventually submit queued descriptors if any
- *
- * Assume channel is idle while calling this function
- * Called with atchan->lock held and bh disabled
- */
-static void atc_complete_all(struct at_dma_chan *atchan)
-{
-	struct at_desc *desc, *_desc;
-	LIST_HEAD(list);
-	unsigned long flags;
-
-	dev_vdbg(chan2dev(&atchan->chan_common), "complete all\n");
 
 	spin_lock_irqsave(&atchan->lock, flags);
-
-	/*
-	 * Submit queued descriptors ASAP, i.e. before we go through
-	 * the completed ones.
-	 */
-	if (!list_empty(&atchan->queue))
-		atc_dostart(atchan, atc_first_queued(atchan));
-	/* empty active_list now it is completed */
-	list_splice_init(&atchan->active_list, &list);
-	/* empty queue list by moving descriptors (if any) to active_list */
-	list_splice_init(&atchan->queue, &atchan->active_list);
-
+	/* move children to free_list */
+	list_splice_init(&desc->tx_list, &atchan->free_list);
+	/* add myself to free_list */
+	list_add(&desc->desc_node, &atchan->free_list);
 	spin_unlock_irqrestore(&atchan->lock, flags);
 
-	list_for_each_entry_safe(desc, _desc, &list, desc_node)
-		atc_chain_complete(atchan, desc);
+	/* If the transfer was a memset, free our temporary buffer */
+	if (desc->memset_buffer) {
+		dma_pool_free(atdma->memset_pool, desc->memset_vaddr,
+			      desc->memset_paddr);
+		desc->memset_buffer = false;
+	}
 }
 
 /**
@@ -508,26 +477,28 @@ static void atc_complete_all(struct at_dma_chan *atchan)
  */
 static void atc_advance_work(struct at_dma_chan *atchan)
 {
+	struct at_desc *desc;
 	unsigned long flags;
-	int ret;
 
 	dev_vdbg(chan2dev(&atchan->chan_common), "advance_work\n");
 
 	spin_lock_irqsave(&atchan->lock, flags);
-	ret = atc_chan_is_enabled(atchan);
+	if (atc_chan_is_enabled(atchan) || list_empty(&atchan->active_list))
+		return spin_unlock_irqrestore(&atchan->lock, flags);
+
+	desc = atc_first_active(atchan);
+	/* Remove the transfer node from the active list. */
+	list_del_init(&desc->desc_node);
 	spin_unlock_irqrestore(&atchan->lock, flags);
-	if (ret)
-		return;
-
-	if (list_empty(&atchan->active_list) ||
-	    list_is_singular(&atchan->active_list))
-		return atc_complete_all(atchan);
-
-	atc_chain_complete(atchan, atc_first_active(atchan));
+	atc_chain_complete(atchan, desc);
 
 	/* advance work */
 	spin_lock_irqsave(&atchan->lock, flags);
-	atc_dostart(atchan, atc_first_active(atchan));
+	if (!list_empty(&atchan->active_list)) {
+		desc = atc_first_queued(atchan);
+		list_move_tail(&desc->desc_node, &atchan->active_list);
+		atc_dostart(atchan, desc);
+	}
 	spin_unlock_irqrestore(&atchan->lock, flags);
 }
 
@@ -539,6 +510,7 @@ static void atc_advance_work(struct at_dma_chan *atchan)
 static void atc_handle_error(struct at_dma_chan *atchan)
 {
 	struct at_desc *bad_desc;
+	struct at_desc *desc;
 	struct at_desc *child;
 	unsigned long flags;
 
@@ -551,13 +523,12 @@ static void atc_handle_error(struct at_dma_chan *atchan)
 	bad_desc = atc_first_active(atchan);
 	list_del_init(&bad_desc->desc_node);
 
-	/* As we are stopped, take advantage to push queued descriptors
-	 * in active_list */
-	list_splice_init(&atchan->queue, atchan->active_list.prev);
-
 	/* Try to restart the controller */
-	if (!list_empty(&atchan->active_list))
-		atc_dostart(atchan, atc_first_active(atchan));
+	if (!list_empty(&atchan->active_list)) {
+		desc = atc_first_queued(atchan);
+		list_move_tail(&desc->desc_node, &atchan->active_list);
+		atc_dostart(atchan, desc);
+	}
 
 	/*
 	 * KERN_CRITICAL may seem harsh, but since this only happens
@@ -672,19 +643,11 @@ static dma_cookie_t atc_tx_submit(struct dma_async_tx_descriptor *tx)
 	spin_lock_irqsave(&atchan->lock, flags);
 	cookie = dma_cookie_assign(tx);
 
-	if (list_empty(&atchan->active_list)) {
-		dev_vdbg(chan2dev(tx->chan), "tx_submit: started %u\n",
-				desc->txd.cookie);
-		atc_dostart(atchan, desc);
-		list_add_tail(&desc->desc_node, &atchan->active_list);
-	} else {
-		dev_vdbg(chan2dev(tx->chan), "tx_submit: queued %u\n",
-				desc->txd.cookie);
-		list_add_tail(&desc->desc_node, &atchan->queue);
-	}
-
+	list_add_tail(&desc->desc_node, &atchan->queue);
 	spin_unlock_irqrestore(&atchan->lock, flags);
 
+	dev_vdbg(chan2dev(tx->chan), "tx_submit: queued %u\n",
+		 desc->txd.cookie);
 	return cookie;
 }
 
@@ -1418,11 +1381,8 @@ static int atc_terminate_all(struct dma_chan *chan)
 	struct at_dma_chan	*atchan = to_at_dma_chan(chan);
 	struct at_dma		*atdma = to_at_dma(chan->device);
 	int			chan_id = atchan->chan_common.chan_id;
-	struct at_desc		*desc, *_desc;
 	unsigned long		flags;
 
-	LIST_HEAD(list);
-
 	dev_vdbg(chan2dev(chan), "%s\n", __func__);
 
 	/*
@@ -1441,19 +1401,15 @@ static int atc_terminate_all(struct dma_chan *chan)
 		cpu_relax();
 
 	/* active_list entries will end up before queued entries */
-	list_splice_init(&atchan->queue, &list);
-	list_splice_init(&atchan->active_list, &list);
-
-	spin_unlock_irqrestore(&atchan->lock, flags);
-
-	/* Flush all pending and queued descriptors */
-	list_for_each_entry_safe(desc, _desc, &list, desc_node)
-		atc_chain_complete(atchan, desc);
+	list_splice_tail_init(&atchan->queue, &atchan->free_list);
+	list_splice_tail_init(&atchan->active_list, &atchan->free_list);
 
 	clear_bit(ATC_IS_PAUSED, &atchan->status);
 	/* if channel dedicated to cyclic operations, free it */
 	clear_bit(ATC_IS_CYCLIC, &atchan->status);
 
+	spin_unlock_irqrestore(&atchan->lock, flags);
+
 	return 0;
 }
 
@@ -1508,20 +1464,26 @@ atc_tx_status(struct dma_chan *chan,
 }
 
 /**
- * atc_issue_pending - try to finish work
+ * atc_issue_pending - takes the first transaction descriptor in the pending
+ * queue and starts the transfer.
  * @chan: target DMA channel
  */
 static void atc_issue_pending(struct dma_chan *chan)
 {
-	struct at_dma_chan	*atchan = to_at_dma_chan(chan);
+	struct at_dma_chan *atchan = to_at_dma_chan(chan);
+	struct at_desc *desc;
+	unsigned long flags;
 
 	dev_vdbg(chan2dev(chan), "issue_pending\n");
 
-	/* Not needed for cyclic transfers */
-	if (atc_chan_is_cyclic(atchan))
-		return;
+	spin_lock_irqsave(&atchan->lock, flags);
+	if (atc_chan_is_enabled(atchan) || list_empty(&atchan->queue))
+		return spin_unlock_irqrestore(&atchan->lock, flags);
 
-	atc_advance_work(atchan);
+	desc = atc_first_queued(atchan);
+	list_move_tail(&desc->desc_node, &atchan->active_list);
+	atc_dostart(atchan, desc);
+	spin_unlock_irqrestore(&atchan->lock, flags);
 }
 
 /**
@@ -1939,7 +1901,11 @@ static int __init at_dma_probe(struct platform_device *pdev)
 	  dma_has_cap(DMA_SLAVE, atdma->dma_common.cap_mask)  ? "slave " : "",
 	  plat_dat->nr_channels);
 
-	dma_async_device_register(&atdma->dma_common);
+	err = dma_async_device_register(&atdma->dma_common);
+	if (err) {
+		dev_err(&pdev->dev, "Unable to register: %d.\n", err);
+		goto err_dma_async_device_register;
+	}
 
 	/*
 	 * Do not return an error if the dmac node is not present in order to
@@ -1959,6 +1925,7 @@ static int __init at_dma_probe(struct platform_device *pdev)
 
 err_of_dma_controller_register:
 	dma_async_device_unregister(&atdma->dma_common);
+err_dma_async_device_register:
 	dma_pool_destroy(atdma->memset_pool);
 err_memset_pool_create:
 	dma_pool_destroy(atdma->dma_desc_pool);