6.6.113-rc1 review

@@ -81,7 +81,7 @@ static struct mfd_cell chtdc_ti_dev[] =
 static const struct regmap_config chtdc_ti_regmap_config = {
 	.reg_bits = 8,
 	.val_bits = 8,
-	.max_register = 128,
+	.max_register = 0xff,
 	.cache_type = REGCACHE_NONE,
 };
 

@@ -82,7 +82,6 @@ static const struct regmap_config chtdc_
 	.reg_bits = 8,
 	.val_bits = 8,
 	.max_register = 0xff,
-	.cache_type = REGCACHE_NONE,
 };
 
 static const struct regmap_irq chtdc_ti_irqs[] = {

@@ -82,6 +82,8 @@ static const struct regmap_config chtdc_
 	.reg_bits = 8,
 	.val_bits = 8,
 	.max_register = 0xff,
+	/* The hardware does not support reading multiple registers at once */
+	.use_single_read = true,
 };
 
 static const struct regmap_irq chtdc_ti_irqs[] = {

@@ -342,12 +342,14 @@ static int fentry_dispatcher(struct fpro
 			     void *entry_data)
 {
 	struct trace_fprobe *tf = container_of(fp, struct trace_fprobe, fp);
+	unsigned int flags = trace_probe_load_flag(&tf->tp);
 	int ret = 0;
 
-	if (trace_probe_test_flag(&tf->tp, TP_FLAG_TRACE))
+	if (flags & TP_FLAG_TRACE)
 		fentry_trace_func(tf, entry_ip, regs);
+
 #ifdef CONFIG_PERF_EVENTS
-	if (trace_probe_test_flag(&tf->tp, TP_FLAG_PROFILE))
+	if (flags & TP_FLAG_PROFILE)
 		ret = fentry_perf_func(tf, entry_ip, regs);
 #endif
 	return ret;

@@ -359,11 +361,12 @@ static void fexit_dispatcher(struct fpro
 			     void *entry_data)
 {
 	struct trace_fprobe *tf = container_of(fp, struct trace_fprobe, fp);
+	unsigned int flags = trace_probe_load_flag(&tf->tp);
 
-	if (trace_probe_test_flag(&tf->tp, TP_FLAG_TRACE))
+	if (flags & TP_FLAG_TRACE)
 		fexit_trace_func(tf, entry_ip, ret_ip, regs, entry_data);
 #ifdef CONFIG_PERF_EVENTS
-	if (trace_probe_test_flag(&tf->tp, TP_FLAG_PROFILE))
+	if (flags & TP_FLAG_PROFILE)
 		fexit_perf_func(tf, entry_ip, ret_ip, regs, entry_data);
 #endif
 }

@@ -1713,14 +1713,15 @@ static int kprobe_register(struct trace_
 static int kprobe_dispatcher(struct kprobe *kp, struct pt_regs *regs)
 {
 	struct trace_kprobe *tk = container_of(kp, struct trace_kprobe, rp.kp);
+	unsigned int flags = trace_probe_load_flag(&tk->tp);
 	int ret = 0;
 
 	raw_cpu_inc(*tk->nhit);
 
-	if (trace_probe_test_flag(&tk->tp, TP_FLAG_TRACE))
+	if (flags & TP_FLAG_TRACE)
 		kprobe_trace_func(tk, regs);
 #ifdef CONFIG_PERF_EVENTS
-	if (trace_probe_test_flag(&tk->tp, TP_FLAG_PROFILE))
+	if (flags & TP_FLAG_PROFILE)
 		ret = kprobe_perf_func(tk, regs);
 #endif
 	return ret;

@@ -1732,6 +1733,7 @@ kretprobe_dispatcher(struct kretprobe_in
 {
 	struct kretprobe *rp = get_kretprobe(ri);
 	struct trace_kprobe *tk;
+	unsigned int flags;
 
 	/*
 	 * There is a small chance that get_kretprobe(ri) returns NULL when

@@ -1744,10 +1746,11 @@ kretprobe_dispatcher(struct kretprobe_in
 	tk = container_of(rp, struct trace_kprobe, rp);
 	raw_cpu_inc(*tk->nhit);
 
-	if (trace_probe_test_flag(&tk->tp, TP_FLAG_TRACE))
+	flags = trace_probe_load_flag(&tk->tp);
+	if (flags & TP_FLAG_TRACE)
 		kretprobe_trace_func(tk, ri, regs);
 #ifdef CONFIG_PERF_EVENTS
-	if (trace_probe_test_flag(&tk->tp, TP_FLAG_PROFILE))
+	if (flags & TP_FLAG_PROFILE)
 		kretprobe_perf_func(tk, ri, regs);
 #endif
 	return 0;	/* We don't tweak kernel, so just return 0 */

@@ -268,16 +268,21 @@ struct event_file_link {
 	struct list_head		list;
 };
 
+static inline unsigned int trace_probe_load_flag(struct trace_probe *tp)
+{
+	return smp_load_acquire(&tp->event->flags);
+}
+
 static inline bool trace_probe_test_flag(struct trace_probe *tp,
 					 unsigned int flag)
 {
-	return !!(tp->event->flags & flag);
+	return !!(trace_probe_load_flag(tp) & flag);
 }
 
 static inline void trace_probe_set_flag(struct trace_probe *tp,
 					unsigned int flag)
 {
-	tp->event->flags |= flag;
+	smp_store_release(&tp->event->flags, tp->event->flags | flag);
 }
 
 static inline void trace_probe_clear_flag(struct trace_probe *tp,

@@ -1514,6 +1514,7 @@ static int uprobe_dispatcher(struct upro
 	struct trace_uprobe *tu;
 	struct uprobe_dispatch_data udd;
 	struct uprobe_cpu_buffer *ucb = NULL;
+	unsigned int flags;
 	int ret = 0;
 
 	tu = container_of(con, struct trace_uprobe, consumer);

@@ -1527,11 +1528,12 @@ static int uprobe_dispatcher(struct upro
 	if (WARN_ON_ONCE(!uprobe_cpu_buffer))
 		return 0;
 
-	if (trace_probe_test_flag(&tu->tp, TP_FLAG_TRACE))
+	flags = trace_probe_load_flag(&tu->tp);
+	if (flags & TP_FLAG_TRACE)
 		ret |= uprobe_trace_func(tu, regs, &ucb);
 
 #ifdef CONFIG_PERF_EVENTS
-	if (trace_probe_test_flag(&tu->tp, TP_FLAG_PROFILE))
+	if (flags & TP_FLAG_PROFILE)
 		ret |= uprobe_perf_func(tu, regs, &ucb);
 #endif
 	uprobe_buffer_put(ucb);

@@ -1544,6 +1546,7 @@ static int uretprobe_dispatcher(struct u
 	struct trace_uprobe *tu;
 	struct uprobe_dispatch_data udd;
 	struct uprobe_cpu_buffer *ucb = NULL;
+	unsigned int flags;
 
 	tu = container_of(con, struct trace_uprobe, consumer);
 

@@ -1555,11 +1558,12 @@ static int uretprobe_dispatcher(struct u
 	if (WARN_ON_ONCE(!uprobe_cpu_buffer))
 		return 0;
 
-	if (trace_probe_test_flag(&tu->tp, TP_FLAG_TRACE))
+	flags = trace_probe_load_flag(&tu->tp);
+	if (flags & TP_FLAG_TRACE)
 		uretprobe_trace_func(tu, func, regs, &ucb);
 
 #ifdef CONFIG_PERF_EVENTS
-	if (trace_probe_test_flag(&tu->tp, TP_FLAG_PROFILE))
+	if (flags & TP_FLAG_PROFILE)
 		uretprobe_perf_func(tu, func, regs, &ucb);
 #endif
 	uprobe_buffer_put(ucb);

@@ -59,6 +59,12 @@ static inline int ksm_fork(struct mm_str
 	int ret;
 
 	if (test_bit(MMF_VM_MERGEABLE, &oldmm->flags)) {
+		long nr_ksm_zero_pages = atomic_long_read(&mm->ksm_zero_pages);
+
+		mm->ksm_merging_pages = 0;
+		mm->ksm_rmap_items = 0;
+		atomic_long_add(nr_ksm_zero_pages, &ksm_zero_pages);
+
 		ret = __ksm_enter(mm);
 		if (ret)
 			return ret;

@@ -4156,11 +4156,20 @@ static int svm_vcpu_pre_run(struct kvm_v
 
 static fastpath_t svm_exit_handlers_fastpath(struct kvm_vcpu *vcpu)
 {
+	struct vcpu_svm *svm = to_svm(vcpu);
+
+	/*
+	 * Next RIP must be provided as IRQs are disabled, and accessing guest
+	 * memory to decode the instruction might fault, i.e. might sleep.
+	 */
+	if (!nrips || !svm->vmcb->control.next_rip)
+		return EXIT_FASTPATH_NONE;
+
 	if (is_guest_mode(vcpu))
 		return EXIT_FASTPATH_NONE;
 
-	if (to_svm(vcpu)->vmcb->control.exit_code == SVM_EXIT_MSR &&
-	    to_svm(vcpu)->vmcb->control.exit_info_1)
+	if (svm->vmcb->control.exit_code == SVM_EXIT_MSR &&
+	    svm->vmcb->control.exit_info_1)
 		return handle_fastpath_set_msr_irqoff(vcpu);
 
 	return EXIT_FASTPATH_NONE;

@@ -108,10 +108,11 @@ struct ksmbd_startup_request {
 	__u32	smb2_max_credits;	/* MAX credits */
 	__u32	smbd_max_io_size;	/* smbd read write size */
 	__u32	max_connections;	/* Number of maximum simultaneous connections */
-	__u32	reserved[126];		/* Reserved room */
+	__u32	max_ip_connections;	/* Number of maximum connection per ip address */
+	__u32	reserved[125];		/* Reserved room */
 	__u32	ifc_list_sz;		/* interfaces list size */
 	__s8	____payload[];
-};
+} __packed;
 
 #define KSMBD_STARTUP_CONFIG_INTERFACES(s)	((s)->____payload)
 

@@ -43,6 +43,7 @@ struct ksmbd_server_config {
 	unsigned int		auth_mechs;
 	unsigned int		max_connections;
 	unsigned int		max_inflight_req;
+	unsigned int		max_ip_connections;
 
 	char			*conf[SERVER_CONF_WORK_GROUP + 1];
 };

@@ -321,6 +321,9 @@ static int ipc_server_config_on_startup(
 	if (req->max_connections)
 		server_conf.max_connections = req->max_connections;
 
+	if (req->max_ip_connections)
+		server_conf.max_ip_connections = req->max_ip_connections;
+
 	ret = ksmbd_set_netbios_name(req->netbios_name);
 	ret |= ksmbd_set_server_string(req->server_string);
 	ret |= ksmbd_set_work_group(req->work_group);

@@ -240,6 +240,7 @@ static int ksmbd_kthread_fn(void *p)
 	struct interface *iface = (struct interface *)p;
 	struct ksmbd_conn *conn;
 	int ret;
+	unsigned int max_ip_conns;
 
 	while (!kthread_should_stop()) {
 		mutex_lock(&iface->sock_release_lock);

@@ -257,34 +258,39 @@ static int ksmbd_kthread_fn(void *p)
 			continue;
 		}
 
+		if (!server_conf.max_ip_connections)
+			goto skip_max_ip_conns_limit;
+
 		/*
 		 * Limits repeated connections from clients with the same IP.
 		 */
+		max_ip_conns = 0;
 		down_read(&conn_list_lock);
-		list_for_each_entry(conn, &conn_list, conns_list)
+		list_for_each_entry(conn, &conn_list, conns_list) {
 #if IS_ENABLED(CONFIG_IPV6)
 			if (client_sk->sk->sk_family == AF_INET6) {
 				if (memcmp(&client_sk->sk->sk_v6_daddr,
-					   &conn->inet6_addr, 16) == 0) {
-					ret = -EAGAIN;
-					break;
-				}
+					   &conn->inet6_addr, 16) == 0)
+					max_ip_conns++;
 			} else if (inet_sk(client_sk->sk)->inet_daddr ==
-				 conn->inet_addr) {
-				ret = -EAGAIN;
-				break;
-			}
+				 conn->inet_addr)
+				max_ip_conns++;
 #else
 			if (inet_sk(client_sk->sk)->inet_daddr ==
-			    conn->inet_addr) {
+			    conn->inet_addr)
+				max_ip_conns++;
+#endif
+			if (server_conf.max_ip_connections <= max_ip_conns) {
 				ret = -EAGAIN;
 				break;
 			}
-#endif
+		}
 		up_read(&conn_list_lock);
 		if (ret == -EAGAIN)
 			continue;
 
+skip_max_ip_conns_limit:
+
 		if (server_conf.max_connections &&
 		    atomic_inc_return(&active_num_conn) >= server_conf.max_connections) {
 			pr_info_ratelimited("Limit the maximum number of connections(%u)\n",

@@ -325,7 +325,7 @@ static void fastrpc_free_map(struct kref
 			err = qcom_scm_assign_mem(map->phys, map->size,
 				&src_perms, &perm, 1);
 			if (err) {
-				dev_err(map->fl->sctx->dev, "Failed to assign memory phys 0x%llx size 0x%llx err %d",
+				dev_err(map->fl->sctx->dev, "Failed to assign memory phys 0x%llx size 0x%llx err %d\n",
 						map->phys, map->size, err);
 				return;
 			}

@@ -808,7 +808,7 @@ static int fastrpc_map_attach(struct fas
 		map->attr = attr;
 		err = qcom_scm_assign_mem(map->phys, (u64)map->size, &src_perms, dst_perms, 2);
 		if (err) {
-			dev_err(sess->dev, "Failed to assign memory with phys 0x%llx size 0x%llx err %d",
+			dev_err(sess->dev, "Failed to assign memory with phys 0x%llx size 0x%llx err %d\n",
 					map->phys, map->size, err);
 			goto map_err;
 		}

@@ -1240,7 +1240,7 @@ static bool is_session_rejected(struct f
 		 * that does not support unsigned PD offload
 		 */
 		if (!fl->cctx->unsigned_support || !unsigned_pd_request) {
-			dev_err(&fl->cctx->rpdev->dev, "Error: Untrusted application trying to offload to signed PD");
+			dev_err(&fl->cctx->rpdev->dev, "Error: Untrusted application trying to offload to signed PD\n");
 			return true;
 		}
 	}

@@ -1304,7 +1304,7 @@ static int fastrpc_init_create_static_pr
 							&src_perms,
 							fl->cctx->vmperms, fl->cctx->vmcount);
 			if (err) {
-				dev_err(fl->sctx->dev, "Failed to assign memory with phys 0x%llx size 0x%llx err %d",
+				dev_err(fl->sctx->dev, "Failed to assign memory with phys 0x%llx size 0x%llx err %d\n",
 					fl->cctx->remote_heap->phys, fl->cctx->remote_heap->size, err);
 				goto err_map;
 			}

@@ -1358,7 +1358,7 @@ err_invoke:
 						(u64)fl->cctx->remote_heap->size,
 						&src_perms, &dst_perms, 1);
 		if (err)
-			dev_err(fl->sctx->dev, "Failed to assign memory phys 0x%llx size 0x%llx err %d",
+			dev_err(fl->sctx->dev, "Failed to assign memory phys 0x%llx size 0x%llx err %d\n",
 				fl->cctx->remote_heap->phys, fl->cctx->remote_heap->size, err);
 	}
 err_map:

@@ -322,11 +322,11 @@ static void fastrpc_free_map(struct kref
 
 			perm.vmid = QCOM_SCM_VMID_HLOS;
 			perm.perm = QCOM_SCM_PERM_RWX;
-			err = qcom_scm_assign_mem(map->phys, map->size,
+			err = qcom_scm_assign_mem(map->phys, map->len,
 				&src_perms, &perm, 1);
 			if (err) {
 				dev_err(map->fl->sctx->dev, "Failed to assign memory phys 0x%llx size 0x%llx err %d\n",
-						map->phys, map->size, err);
+						map->phys, map->len, err);
 				return;
 			}
 		}

@@ -752,7 +752,8 @@ static int fastrpc_map_attach(struct fas
 	struct fastrpc_session_ctx *sess = fl->sctx;
 	struct fastrpc_map *map = NULL;
 	struct sg_table *table;
-	int err = 0;
+	struct scatterlist *sgl = NULL;
+	int err = 0, sgl_index = 0;
 
 	map = kzalloc(sizeof(*map), GFP_KERNEL);
 	if (!map)

@@ -789,7 +790,15 @@ static int fastrpc_map_attach(struct fas
 		map->phys = sg_dma_address(map->table->sgl);
 		map->phys += ((u64)fl->sctx->sid << 32);
 	}
-	map->size = len;
+	for_each_sg(map->table->sgl, sgl, map->table->nents,
+		sgl_index)
+		map->size += sg_dma_len(sgl);
+	if (len > map->size) {
+		dev_dbg(sess->dev, "Bad size passed len 0x%llx map size 0x%llx\n",
+				len, map->size);
+		err = -EINVAL;
+		goto map_err;
+	}
 	map->va = sg_virt(map->table->sgl);
 	map->len = len;
 

@@ -806,10 +815,10 @@ static int fastrpc_map_attach(struct fas
 		dst_perms[1].vmid = fl->cctx->vmperms[0].vmid;
 		dst_perms[1].perm = QCOM_SCM_PERM_RWX;
 		map->attr = attr;
-		err = qcom_scm_assign_mem(map->phys, (u64)map->size, &src_perms, dst_perms, 2);
+		err = qcom_scm_assign_mem(map->phys, (u64)map->len, &src_perms, dst_perms, 2);
 		if (err) {
 			dev_err(sess->dev, "Failed to assign memory with phys 0x%llx size 0x%llx err %d\n",
-					map->phys, map->size, err);
+					map->phys, map->len, err);
 			goto map_err;
 		}
 	}

@@ -2063,7 +2072,7 @@ static int fastrpc_req_mem_map(struct fa
 	args[0].length = sizeof(req_msg);
 
 	pages.addr = map->phys;
-	pages.size = map->size;
+	pages.size = map->len;
 
 	args[1].ptr = (u64) (uintptr_t) &pages;
 	args[1].length = sizeof(pages);

@@ -2078,7 +2087,7 @@ static int fastrpc_req_mem_map(struct fa
 	err = fastrpc_internal_invoke(fl, true, FASTRPC_INIT_HANDLE, sc, &args[0]);
 	if (err) {
 		dev_err(dev, "mem mmap error, fd %d, vaddr %llx, size %lld\n",
-			req.fd, req.vaddrin, map->size);
+			req.fd, req.vaddrin, map->len);
 		goto err_invoke;
 	}
 

@@ -2091,7 +2100,7 @@ static int fastrpc_req_mem_map(struct fa
 	if (copy_to_user((void __user *)argp, &req, sizeof(req))) {
 		/* unmap the memory and release the buffer */
 		req_unmap.vaddr = (uintptr_t) rsp_msg.vaddr;
-		req_unmap.length = map->size;
+		req_unmap.length = map->len;
 		fastrpc_req_mem_unmap_impl(fl, &req_unmap);
 		return -EFAULT;
 	}

@@ -291,8 +291,6 @@ static void pci_epf_test_clean_dma_chan(
 
 	dma_release_channel(epf_test->dma_chan_rx);
 	epf_test->dma_chan_rx = NULL;
-
-	return;
 }
 
 static void pci_epf_test_print_rate(struct pci_epf_test *epf_test,

@@ -282,15 +282,20 @@ static void pci_epf_test_clean_dma_chan(
 	if (!epf_test->dma_supported)
 		return;
 
-	dma_release_channel(epf_test->dma_chan_tx);
-	if (epf_test->dma_chan_tx == epf_test->dma_chan_rx) {
+	if (epf_test->dma_chan_tx) {
+		dma_release_channel(epf_test->dma_chan_tx);
+		if (epf_test->dma_chan_tx == epf_test->dma_chan_rx) {
+			epf_test->dma_chan_tx = NULL;
+			epf_test->dma_chan_rx = NULL;
+			return;
+		}
 		epf_test->dma_chan_tx = NULL;
-		epf_test->dma_chan_rx = NULL;
-		return;
 	}
 
-	dma_release_channel(epf_test->dma_chan_rx);
-	epf_test->dma_chan_rx = NULL;
+	if (epf_test->dma_chan_rx) {
+		dma_release_channel(epf_test->dma_chan_rx);
+		epf_test->dma_chan_rx = NULL;
+	}
 }
 
 static void pci_epf_test_print_rate(struct pci_epf_test *epf_test,

@@ -364,6 +364,13 @@ again:
 	/* step one, find a bunch of delalloc bytes starting at start */
 	delalloc_start = *start;
 	delalloc_end = 0;
+
+	/*
+	 * If @max_bytes is smaller than a block, btrfs_find_delalloc_range() can
+	 * return early without handling any dirty ranges.
+	 */
+	ASSERT(max_bytes >= fs_info->sectorsize);
+
 	found = btrfs_find_delalloc_range(tree, &delalloc_start, &delalloc_end,
 					  max_bytes, &cached_state);
 	if (!found || delalloc_end <= *start || delalloc_start > orig_end) {

@@ -394,13 +401,14 @@ again:
 				  delalloc_start, delalloc_end);
 	ASSERT(!ret || ret == -EAGAIN);
 	if (ret == -EAGAIN) {
-		/* some of the pages are gone, lets avoid looping by
-		 * shortening the size of the delalloc range we're searching
+		/*
+		 * Some of the pages are gone, lets avoid looping by
+		 * shortening the size of the delalloc range we're searching.
 		 */
 		free_extent_state(cached_state);
 		cached_state = NULL;
 		if (!loops) {
-			max_bytes = PAGE_SIZE;
+			max_bytes = fs_info->sectorsize;
 			loops = 1;
 			goto again;
 		} else {

@@ -2343,6 +2343,12 @@ enum rseq_event_mask {
 	RSEQ_EVENT_MIGRATE	= (1U << RSEQ_EVENT_MIGRATE_BIT),
 };
 
+#ifdef CONFIG_MEMBARRIER
+# define RSEQ_EVENT_GUARD	irq
+#else
+# define RSEQ_EVENT_GUARD	preempt
+#endif
+
 static inline void rseq_set_notify_resume(struct task_struct *t)
 {
 	if (t->rseq)

@@ -2361,9 +2367,8 @@ static inline void rseq_handle_notify_re
 static inline void rseq_signal_deliver(struct ksignal *ksig,
 				       struct pt_regs *regs)
 {
-	preempt_disable();
-	__set_bit(RSEQ_EVENT_SIGNAL_BIT, &current->rseq_event_mask);
-	preempt_enable();
+	scoped_guard(RSEQ_EVENT_GUARD)
+		__set_bit(RSEQ_EVENT_SIGNAL_BIT, &current->rseq_event_mask);
 	rseq_handle_notify_resume(ksig, regs);
 }
 

@@ -255,12 +255,12 @@ static int rseq_need_restart(struct task
 
 	/*
 	 * Load and clear event mask atomically with respect to
-	 * scheduler preemption.
+	 * scheduler preemption and membarrier IPIs.
 	 */
-	preempt_disable();
-	event_mask = t->rseq_event_mask;
-	t->rseq_event_mask = 0;
-	preempt_enable();
+	scoped_guard(RSEQ_EVENT_GUARD) {
+		event_mask = t->rseq_event_mask;
+		t->rseq_event_mask = 0;
+	}
 
 	return !!event_mask;
 }

@@ -661,6 +661,7 @@
 #define MSR_AMD64_PERF_CNTR_GLOBAL_STATUS	0xc0000300
 #define MSR_AMD64_PERF_CNTR_GLOBAL_CTL		0xc0000301
 #define MSR_AMD64_PERF_CNTR_GLOBAL_STATUS_CLR	0xc0000302
+#define MSR_AMD64_PERF_CNTR_GLOBAL_STATUS_SET	0xc0000303
 
 /* AMD Last Branch Record MSRs */
 #define MSR_AMD64_LBR_SELECT			0xc000010e

@@ -588,6 +588,7 @@ int kvm_pmu_get_msr(struct kvm_vcpu *vcp
 		msr_info->data = pmu->global_ctrl;
 		break;
 	case MSR_AMD64_PERF_CNTR_GLOBAL_STATUS_CLR:
+	case MSR_AMD64_PERF_CNTR_GLOBAL_STATUS_SET:
 	case MSR_CORE_PERF_GLOBAL_OVF_CTRL:
 		msr_info->data = 0;
 		break;

@@ -649,6 +650,10 @@ int kvm_pmu_set_msr(struct kvm_vcpu *vcp
 		if (!msr_info->host_initiated)
 			pmu->global_status &= ~data;
 		break;
+	case MSR_AMD64_PERF_CNTR_GLOBAL_STATUS_SET:
+		if (!msr_info->host_initiated)
+			pmu->global_status |= data & ~pmu->global_status_mask;
+		break;
 	default:
 		kvm_pmu_mark_pmc_in_use(vcpu, msr_info->index);
 		return static_call(kvm_x86_pmu_set_msr)(vcpu, msr_info);

@@ -117,6 +117,7 @@ static bool amd_is_valid_msr(struct kvm_
 	case MSR_AMD64_PERF_CNTR_GLOBAL_STATUS:
 	case MSR_AMD64_PERF_CNTR_GLOBAL_CTL:
 	case MSR_AMD64_PERF_CNTR_GLOBAL_STATUS_CLR:
+	case MSR_AMD64_PERF_CNTR_GLOBAL_STATUS_SET:
 		return pmu->version > 1;
 	default:
 		if (msr > MSR_F15H_PERF_CTR5 &&

@@ -1495,6 +1495,7 @@ static const u32 msrs_to_save_pmu[] = {
 	MSR_AMD64_PERF_CNTR_GLOBAL_CTL,
 	MSR_AMD64_PERF_CNTR_GLOBAL_STATUS,
 	MSR_AMD64_PERF_CNTR_GLOBAL_STATUS_CLR,
+	MSR_AMD64_PERF_CNTR_GLOBAL_STATUS_SET,
 };
 
 static u32 msrs_to_save[ARRAY_SIZE(msrs_to_save_base) +

@@ -7194,6 +7195,7 @@ static void kvm_probe_msr_to_save(u32 ms
 	case MSR_AMD64_PERF_CNTR_GLOBAL_CTL:
 	case MSR_AMD64_PERF_CNTR_GLOBAL_STATUS:
 	case MSR_AMD64_PERF_CNTR_GLOBAL_STATUS_CLR:
+	case MSR_AMD64_PERF_CNTR_GLOBAL_STATUS_SET:
 		if (!kvm_cpu_cap_has(X86_FEATURE_PERFMON_V2))
 			return;
 		break;

@@ -39,7 +39,9 @@
 
 #define IPMI_DRIVER_VERSION "39.2"
 
-static struct ipmi_recv_msg *ipmi_alloc_recv_msg(void);
+static struct ipmi_recv_msg *ipmi_alloc_recv_msg(struct ipmi_user *user);
+static void ipmi_set_recv_msg_user(struct ipmi_recv_msg *msg,
+				   struct ipmi_user *user);
 static int ipmi_init_msghandler(void);
 static void smi_recv_tasklet(struct tasklet_struct *t);
 static void handle_new_recv_msgs(struct ipmi_smi *intf);

@@ -939,13 +941,11 @@ static int deliver_response(struct ipmi_
 		 * risk.  At this moment, simply skip it in that case.
 		 */
 		ipmi_free_recv_msg(msg);
-		atomic_dec(&msg->user->nr_msgs);
 	} else {
 		int index;
 		struct ipmi_user *user = acquire_ipmi_user(msg->user, &index);
 
 		if (user) {
-			atomic_dec(&user->nr_msgs);
 			user->handler->ipmi_recv_hndl(msg, user->handler_data);
 			release_ipmi_user(user, index);
 		} else {

@@ -1634,8 +1634,7 @@ int ipmi_set_gets_events(struct ipmi_use
 		spin_unlock_irqrestore(&intf->events_lock, flags);
 
 		list_for_each_entry_safe(msg, msg2, &msgs, link) {
-			msg->user = user;
-			kref_get(&user->refcount);
+			ipmi_set_recv_msg_user(msg, user);
 			deliver_local_response(intf, msg);
 		}
 

@@ -2309,22 +2308,15 @@ static int i_ipmi_request(struct ipmi_us
 	struct ipmi_recv_msg *recv_msg;
 	int rv = 0;
 
-	if (user) {
-		if (atomic_add_return(1, &user->nr_msgs) > max_msgs_per_user) {
-			/* Decrement will happen at the end of the routine. */
-			rv = -EBUSY;
-			goto out;
-		}
-	}
-
-	if (supplied_recv)
+	if (supplied_recv) {
 		recv_msg = supplied_recv;
-	else {
-		recv_msg = ipmi_alloc_recv_msg();
-		if (recv_msg == NULL) {
-			rv = -ENOMEM;
-			goto out;
-		}
+		recv_msg->user = user;
+		if (user)
+			atomic_inc(&user->nr_msgs);
+	} else {
+		recv_msg = ipmi_alloc_recv_msg(user);
+		if (IS_ERR(recv_msg))
+			return PTR_ERR(recv_msg);
 	}
 	recv_msg->user_msg_data = user_msg_data;
 

@@ -2335,8 +2327,7 @@ static int i_ipmi_request(struct ipmi_us
 		if (smi_msg == NULL) {
 			if (!supplied_recv)
 				ipmi_free_recv_msg(recv_msg);
-			rv = -ENOMEM;
-			goto out;
+			return -ENOMEM;
 		}
 	}
 

@@ -2346,10 +2337,6 @@ static int i_ipmi_request(struct ipmi_us
 		goto out_err;
 	}
 
-	recv_msg->user = user;
-	if (user)
-		/* The put happens when the message is freed. */
-		kref_get(&user->refcount);
 	recv_msg->msgid = msgid;
 	/*
 	 * Store the message to send in the receive message so timeout

@@ -2378,8 +2365,10 @@ static int i_ipmi_request(struct ipmi_us
 
 	if (rv) {
 out_err:
-		ipmi_free_smi_msg(smi_msg);
-		ipmi_free_recv_msg(recv_msg);
+		if (!supplied_smi)
+			ipmi_free_smi_msg(smi_msg);
+		if (!supplied_recv)
+			ipmi_free_recv_msg(recv_msg);
 	} else {
 		dev_dbg(intf->si_dev, "Send: %*ph\n",
 			smi_msg->data_size, smi_msg->data);

@@ -2388,9 +2377,6 @@ out_err:
 	}
 	rcu_read_unlock();
 
-out:
-	if (rv && user)
-		atomic_dec(&user->nr_msgs);
 	return rv;
 }
 

@@ -3883,7 +3869,7 @@ static int handle_ipmb_get_msg_cmd(struc
 	unsigned char            chan;
 	struct ipmi_user         *user = NULL;
 	struct ipmi_ipmb_addr    *ipmb_addr;
-	struct ipmi_recv_msg     *recv_msg;
+	struct ipmi_recv_msg     *recv_msg = NULL;
 
 	if (msg->rsp_size < 10) {
 		/* Message not big enough, just ignore it. */

@@ -3904,9 +3890,8 @@ static int handle_ipmb_get_msg_cmd(struc
 	rcvr = find_cmd_rcvr(intf, netfn, cmd, chan);
 	if (rcvr) {
 		user = rcvr->user;
-		kref_get(&user->refcount);
-	} else
-		user = NULL;
+		recv_msg = ipmi_alloc_recv_msg(user);
+	}
 	rcu_read_unlock();
 
 	if (user == NULL) {

@@ -3941,47 +3926,41 @@ static int handle_ipmb_get_msg_cmd(struc
 			rv = -1;
 		}
 		rcu_read_unlock();
-	} else {
-		recv_msg = ipmi_alloc_recv_msg();
-		if (!recv_msg) {
-			/*
-			 * We couldn't allocate memory for the
-			 * message, so requeue it for handling
-			 * later.
-			 */
-			rv = 1;
-			kref_put(&user->refcount, free_user);
-		} else {
-			/* Extract the source address from the data. */
-			ipmb_addr = (struct ipmi_ipmb_addr *) &recv_msg->addr;
-			ipmb_addr->addr_type = IPMI_IPMB_ADDR_TYPE;
-			ipmb_addr->slave_addr = msg->rsp[6];
-			ipmb_addr->lun = msg->rsp[7] & 3;
-			ipmb_addr->channel = msg->rsp[3] & 0xf;
+	} else if (!IS_ERR(recv_msg)) {
+		/* Extract the source address from the data. */
+		ipmb_addr = (struct ipmi_ipmb_addr *) &recv_msg->addr;
+		ipmb_addr->addr_type = IPMI_IPMB_ADDR_TYPE;
+		ipmb_addr->slave_addr = msg->rsp[6];
+		ipmb_addr->lun = msg->rsp[7] & 3;
+		ipmb_addr->channel = msg->rsp[3] & 0xf;
 
-			/*
-			 * Extract the rest of the message information
-			 * from the IPMB header.
-			 */
-			recv_msg->user = user;
-			recv_msg->recv_type = IPMI_CMD_RECV_TYPE;
-			recv_msg->msgid = msg->rsp[7] >> 2;
-			recv_msg->msg.netfn = msg->rsp[4] >> 2;
-			recv_msg->msg.cmd = msg->rsp[8];
-			recv_msg->msg.data = recv_msg->msg_data;
+		/*
+		 * Extract the rest of the message information
+		 * from the IPMB header.
+		 */
+		recv_msg->recv_type = IPMI_CMD_RECV_TYPE;
+		recv_msg->msgid = msg->rsp[7] >> 2;
+		recv_msg->msg.netfn = msg->rsp[4] >> 2;
+		recv_msg->msg.cmd = msg->rsp[8];
+		recv_msg->msg.data = recv_msg->msg_data;
 
-			/*
-			 * We chop off 10, not 9 bytes because the checksum
-			 * at the end also needs to be removed.
-			 */
-			recv_msg->msg.data_len = msg->rsp_size - 10;
-			memcpy(recv_msg->msg_data, &msg->rsp[9],
-			       msg->rsp_size - 10);
-			if (deliver_response(intf, recv_msg))
-				ipmi_inc_stat(intf, unhandled_commands);
-			else
-				ipmi_inc_stat(intf, handled_commands);
-		}
+		/*
+		 * We chop off 10, not 9 bytes because the checksum
+		 * at the end also needs to be removed.
+		 */
+		recv_msg->msg.data_len = msg->rsp_size - 10;
+		memcpy(recv_msg->msg_data, &msg->rsp[9],
+		       msg->rsp_size - 10);
+		if (deliver_response(intf, recv_msg))
+			ipmi_inc_stat(intf, unhandled_commands);
+		else
+			ipmi_inc_stat(intf, handled_commands);
+	} else {
+		/*
+		 * We couldn't allocate memory for the message, so
+		 * requeue it for handling later.
+		 */
+		rv = 1;
 	}
 
 	return rv;

@@ -3994,7 +3973,7 @@ static int handle_ipmb_direct_rcv_cmd(st
 	int                      rv = 0;
 	struct ipmi_user         *user = NULL;
 	struct ipmi_ipmb_direct_addr *daddr;
-	struct ipmi_recv_msg     *recv_msg;
+	struct ipmi_recv_msg     *recv_msg = NULL;
 	unsigned char netfn = msg->rsp[0] >> 2;
 	unsigned char cmd = msg->rsp[3];
 

@@ -4003,9 +3982,8 @@ static int handle_ipmb_direct_rcv_cmd(st
 	rcvr = find_cmd_rcvr(intf, netfn, cmd, 0);
 	if (rcvr) {
 		user = rcvr->user;
-		kref_get(&user->refcount);
-	} else
-		user = NULL;
+		recv_msg = ipmi_alloc_recv_msg(user);
+	}
 	rcu_read_unlock();
 
 	if (user == NULL) {

@@ -4032,44 +4010,38 @@ static int handle_ipmb_direct_rcv_cmd(st
 			rv = -1;
 		}
 		rcu_read_unlock();
-	} else {
-		recv_msg = ipmi_alloc_recv_msg();
-		if (!recv_msg) {
-			/*
-			 * We couldn't allocate memory for the
-			 * message, so requeue it for handling
-			 * later.
-			 */
-			rv = 1;
-			kref_put(&user->refcount, free_user);
-		} else {
-			/* Extract the source address from the data. */
-			daddr = (struct ipmi_ipmb_direct_addr *)&recv_msg->addr;
-			daddr->addr_type = IPMI_IPMB_DIRECT_ADDR_TYPE;
-			daddr->channel = 0;
-			daddr->slave_addr = msg->rsp[1];
-			daddr->rs_lun = msg->rsp[0] & 3;
-			daddr->rq_lun = msg->rsp[2] & 3;
+	} else if (!IS_ERR(recv_msg)) {
+		/* Extract the source address from the data. */
+		daddr = (struct ipmi_ipmb_direct_addr *)&recv_msg->addr;
+		daddr->addr_type = IPMI_IPMB_DIRECT_ADDR_TYPE;
+		daddr->channel = 0;
+		daddr->slave_addr = msg->rsp[1];
+		daddr->rs_lun = msg->rsp[0] & 3;
+		daddr->rq_lun = msg->rsp[2] & 3;
 
-			/*
-			 * Extract the rest of the message information
-			 * from the IPMB header.
-			 */
-			recv_msg->user = user;
-			recv_msg->recv_type = IPMI_CMD_RECV_TYPE;
-			recv_msg->msgid = (msg->rsp[2] >> 2);
-			recv_msg->msg.netfn = msg->rsp[0] >> 2;
-			recv_msg->msg.cmd = msg->rsp[3];
-			recv_msg->msg.data = recv_msg->msg_data;
-
-			recv_msg->msg.data_len = msg->rsp_size - 4;
-			memcpy(recv_msg->msg_data, msg->rsp + 4,
-			       msg->rsp_size - 4);
-			if (deliver_response(intf, recv_msg))
-				ipmi_inc_stat(intf, unhandled_commands);
-			else
-				ipmi_inc_stat(intf, handled_commands);
-		}
+		/*
+		 * Extract the rest of the message information
+		 * from the IPMB header.
+		 */
+		recv_msg->recv_type = IPMI_CMD_RECV_TYPE;
+		recv_msg->msgid = (msg->rsp[2] >> 2);
+		recv_msg->msg.netfn = msg->rsp[0] >> 2;
+		recv_msg->msg.cmd = msg->rsp[3];
+		recv_msg->msg.data = recv_msg->msg_data;
+
+		recv_msg->msg.data_len = msg->rsp_size - 4;
+		memcpy(recv_msg->msg_data, msg->rsp + 4,
+		       msg->rsp_size - 4);
+		if (deliver_response(intf, recv_msg))
+			ipmi_inc_stat(intf, unhandled_commands);
+		else
+			ipmi_inc_stat(intf, handled_commands);
+	} else {
+		/*
+		 * We couldn't allocate memory for the message, so
+		 * requeue it for handling later.
+		 */
+		rv = 1;
 	}
 
 	return rv;

@@ -4183,7 +4155,7 @@ static int handle_lan_get_msg_cmd(struct
 	unsigned char            chan;
 	struct ipmi_user         *user = NULL;
 	struct ipmi_lan_addr     *lan_addr;
-	struct ipmi_recv_msg     *recv_msg;
+	struct ipmi_recv_msg     *recv_msg = NULL;
 
 	if (msg->rsp_size < 12) {
 		/* Message not big enough, just ignore it. */

@@ -4204,9 +4176,8 @@ static int handle_lan_get_msg_cmd(struct
 	rcvr = find_cmd_rcvr(intf, netfn, cmd, chan);
 	if (rcvr) {
 		user = rcvr->user;
-		kref_get(&user->refcount);
-	} else
-		user = NULL;
+		recv_msg = ipmi_alloc_recv_msg(user);
+	}
 	rcu_read_unlock();
 
 	if (user == NULL) {

@@ -4218,49 +4189,44 @@ static int handle_lan_get_msg_cmd(struct
 		 * them to be freed.
 		 */
 		rv = 0;
-	} else {
-		recv_msg = ipmi_alloc_recv_msg();
-		if (!recv_msg) {
-			/*
-			 * We couldn't allocate memory for the
-			 * message, so requeue it for handling later.
-			 */
-			rv = 1;
-			kref_put(&user->refcount, free_user);
-		} else {
-			/* Extract the source address from the data. */
-			lan_addr = (struct ipmi_lan_addr *) &recv_msg->addr;
-			lan_addr->addr_type = IPMI_LAN_ADDR_TYPE;
-			lan_addr->session_handle = msg->rsp[4];
-			lan_addr->remote_SWID = msg->rsp[8];
-			lan_addr->local_SWID = msg->rsp[5];
-			lan_addr->lun = msg->rsp[9] & 3;
-			lan_addr->channel = msg->rsp[3] & 0xf;
-			lan_addr->privilege = msg->rsp[3] >> 4;
+	} else if (!IS_ERR(recv_msg)) {
+		/* Extract the source address from the data. */
+		lan_addr = (struct ipmi_lan_addr *) &recv_msg->addr;
+		lan_addr->addr_type = IPMI_LAN_ADDR_TYPE;
+		lan_addr->session_handle = msg->rsp[4];
+		lan_addr->remote_SWID = msg->rsp[8];
+		lan_addr->local_SWID = msg->rsp[5];
+		lan_addr->lun = msg->rsp[9] & 3;
+		lan_addr->channel = msg->rsp[3] & 0xf;
+		lan_addr->privilege = msg->rsp[3] >> 4;
 
-			/*
-			 * Extract the rest of the message information
-			 * from the IPMB header.
-			 */
-			recv_msg->user = user;
-			recv_msg->recv_type = IPMI_CMD_RECV_TYPE;
-			recv_msg->msgid = msg->rsp[9] >> 2;
-			recv_msg->msg.netfn = msg->rsp[6] >> 2;
-			recv_msg->msg.cmd = msg->rsp[10];
-			recv_msg->msg.data = recv_msg->msg_data;
+		/*
+		 * Extract the rest of the message information
+		 * from the IPMB header.
+		 */
+		recv_msg->recv_type = IPMI_CMD_RECV_TYPE;
+		recv_msg->msgid = msg->rsp[9] >> 2;
+		recv_msg->msg.netfn = msg->rsp[6] >> 2;
+		recv_msg->msg.cmd = msg->rsp[10];
+		recv_msg->msg.data = recv_msg->msg_data;
 
-			/*
-			 * We chop off 12, not 11 bytes because the checksum
-			 * at the end also needs to be removed.
-			 */
-			recv_msg->msg.data_len = msg->rsp_size - 12;
-			memcpy(recv_msg->msg_data, &msg->rsp[11],
-			       msg->rsp_size - 12);
-			if (deliver_response(intf, recv_msg))
-				ipmi_inc_stat(intf, unhandled_commands);
-			else
-				ipmi_inc_stat(intf, handled_commands);
-		}
+		/*
+		 * We chop off 12, not 11 bytes because the checksum
+		 * at the end also needs to be removed.
+		 */
+		recv_msg->msg.data_len = msg->rsp_size - 12;
+		memcpy(recv_msg->msg_data, &msg->rsp[11],
+		       msg->rsp_size - 12);
+		if (deliver_response(intf, recv_msg))
+			ipmi_inc_stat(intf, unhandled_commands);
+		else
+			ipmi_inc_stat(intf, handled_commands);
+	} else {
+		/*
+		 * We couldn't allocate memory for the message, so
+		 * requeue it for handling later.
+		 */
+		rv = 1;
 	}
 
 	return rv;

@@ -4282,7 +4248,7 @@ static int handle_oem_get_msg_cmd(struct
 	unsigned char         chan;
 	struct ipmi_user *user = NULL;
 	struct ipmi_system_interface_addr *smi_addr;
-	struct ipmi_recv_msg  *recv_msg;
+	struct ipmi_recv_msg  *recv_msg = NULL;
 
 	/*
 	 * We expect the OEM SW to perform error checking

@@ -4311,9 +4277,8 @@ static int handle_oem_get_msg_cmd(struct
 	rcvr = find_cmd_rcvr(intf, netfn, cmd, chan);
 	if (rcvr) {
 		user = rcvr->user;
-		kref_get(&user->refcount);
-	} else
-		user = NULL;
+		recv_msg = ipmi_alloc_recv_msg(user);
+	}
 	rcu_read_unlock();
 
 	if (user == NULL) {

@@ -4326,48 +4291,42 @@ static int handle_oem_get_msg_cmd(struct
 		 */
 
 		rv = 0;
-	} else {
-		recv_msg = ipmi_alloc_recv_msg();
-		if (!recv_msg) {
-			/*
-			 * We couldn't allocate memory for the
-			 * message, so requeue it for handling
-			 * later.
-			 */
-			rv = 1;
-			kref_put(&user->refcount, free_user);
-		} else {
-			/*
-			 * OEM Messages are expected to be delivered via
-			 * the system interface to SMS software.  We might
-			 * need to visit this again depending on OEM
-			 * requirements
-			 */
-			smi_addr = ((struct ipmi_system_interface_addr *)
-				    &recv_msg->addr);
-			smi_addr->addr_type = IPMI_SYSTEM_INTERFACE_ADDR_TYPE;
-			smi_addr->channel = IPMI_BMC_CHANNEL;
-			smi_addr->lun = msg->rsp[0] & 3;
-
-			recv_msg->user = user;
-			recv_msg->user_msg_data = NULL;
-			recv_msg->recv_type = IPMI_OEM_RECV_TYPE;
-			recv_msg->msg.netfn = msg->rsp[0] >> 2;
-			recv_msg->msg.cmd = msg->rsp[1];
-			recv_msg->msg.data = recv_msg->msg_data;
+	} else if (!IS_ERR(recv_msg)) {
+		/*
+		 * OEM Messages are expected to be delivered via
+		 * the system interface to SMS software.  We might
+		 * need to visit this again depending on OEM
+		 * requirements
+		 */
+		smi_addr = ((struct ipmi_system_interface_addr *)
+			    &recv_msg->addr);
+		smi_addr->addr_type = IPMI_SYSTEM_INTERFACE_ADDR_TYPE;
+		smi_addr->channel = IPMI_BMC_CHANNEL;
+		smi_addr->lun = msg->rsp[0] & 3;
+
+		recv_msg->user_msg_data = NULL;
+		recv_msg->recv_type = IPMI_OEM_RECV_TYPE;
+		recv_msg->msg.netfn = msg->rsp[0] >> 2;
+		recv_msg->msg.cmd = msg->rsp[1];
+		recv_msg->msg.data = recv_msg->msg_data;
 
-			/*
-			 * The message starts at byte 4 which follows the
-			 * Channel Byte in the "GET MESSAGE" command
-			 */
-			recv_msg->msg.data_len = msg->rsp_size - 4;
-			memcpy(recv_msg->msg_data, &msg->rsp[4],
-			       msg->rsp_size - 4);
-			if (deliver_response(intf, recv_msg))
-				ipmi_inc_stat(intf, unhandled_commands);
-			else
-				ipmi_inc_stat(intf, handled_commands);
-		}
+		/*
+		 * The message starts at byte 4 which follows the
+		 * Channel Byte in the "GET MESSAGE" command
+		 */
+		recv_msg->msg.data_len = msg->rsp_size - 4;
+		memcpy(recv_msg->msg_data, &msg->rsp[4],
+		       msg->rsp_size - 4);
+		if (deliver_response(intf, recv_msg))
+			ipmi_inc_stat(intf, unhandled_commands);
+		else
+			ipmi_inc_stat(intf, handled_commands);
+	} else {
+		/*
+		 * We couldn't allocate memory for the message, so
+		 * requeue it for handling later.
+		 */
+		rv = 1;
 	}
 
 	return rv;

@@ -4426,8 +4385,8 @@ static int handle_read_event_rsp(struct
 		if (!user->gets_events)
 			continue;
 
-		recv_msg = ipmi_alloc_recv_msg();
-		if (!recv_msg) {
+		recv_msg = ipmi_alloc_recv_msg(user);
+		if (IS_ERR(recv_msg)) {
 			rcu_read_unlock();
 			list_for_each_entry_safe(recv_msg, recv_msg2, &msgs,
 						 link) {

@@ -4446,8 +4405,6 @@ static int handle_read_event_rsp(struct
 		deliver_count++;
 
 		copy_event_into_recv_msg(recv_msg, msg);
-		recv_msg->user = user;
-		kref_get(&user->refcount);
 		list_add_tail(&recv_msg->link, &msgs);
 	}
 	srcu_read_unlock(&intf->users_srcu, index);

@@ -4463,8 +4420,8 @@ static int handle_read_event_rsp(struct
 		 * No one to receive the message, put it in queue if there's
 		 * not already too many things in the queue.
 		 */
-		recv_msg = ipmi_alloc_recv_msg();
-		if (!recv_msg) {
+		recv_msg = ipmi_alloc_recv_msg(NULL);
+		if (IS_ERR(recv_msg)) {
 			/*
 			 * We couldn't allocate memory for the
 			 * message, so requeue it for handling

@@ -5156,27 +5113,51 @@ static void free_recv_msg(struct ipmi_re
 		kfree(msg);
 }
 
-static struct ipmi_recv_msg *ipmi_alloc_recv_msg(void)
+static struct ipmi_recv_msg *ipmi_alloc_recv_msg(struct ipmi_user *user)
 {
 	struct ipmi_recv_msg *rv;
 
+	if (user) {
+		if (atomic_add_return(1, &user->nr_msgs) > max_msgs_per_user) {
+			atomic_dec(&user->nr_msgs);
+			return ERR_PTR(-EBUSY);
+		}
+	}
+
 	rv = kmalloc(sizeof(struct ipmi_recv_msg), GFP_ATOMIC);
-	if (rv) {
-		rv->user = NULL;
-		rv->done = free_recv_msg;
-		atomic_inc(&recv_msg_inuse_count);
+	if (!rv) {
+		if (user)
+			atomic_dec(&user->nr_msgs);
+		return ERR_PTR(-ENOMEM);
 	}
+
+	rv->user = user;
+	rv->done = free_recv_msg;
+	if (user)
+		kref_get(&user->refcount);
+	atomic_inc(&recv_msg_inuse_count);
 	return rv;
 }
 
 void ipmi_free_recv_msg(struct ipmi_recv_msg *msg)
 {
-	if (msg->user && !oops_in_progress)
+	if (msg->user && !oops_in_progress) {
+		atomic_dec(&msg->user->nr_msgs);
 		kref_put(&msg->user->refcount, free_user);
+	}
 	msg->done(msg);
 }
 EXPORT_SYMBOL(ipmi_free_recv_msg);
 
+static void ipmi_set_recv_msg_user(struct ipmi_recv_msg *msg,
+				   struct ipmi_user *user)
+{
+	WARN_ON_ONCE(msg->user); /* User should not be set. */
+	msg->user = user;
+	atomic_inc(&user->nr_msgs);
+	kref_get(&user->refcount);
+}
+
 static atomic_t panic_done_count = ATOMIC_INIT(0);
 
 static void dummy_smi_done_handler(struct ipmi_smi_msg *msg)

@@ -2311,8 +2311,11 @@ static int i_ipmi_request(struct ipmi_us
 	if (supplied_recv) {
 		recv_msg = supplied_recv;
 		recv_msg->user = user;
-		if (user)
+		if (user) {
 			atomic_inc(&user->nr_msgs);
+			/* The put happens when the message is freed. */
+			kref_get(&user->refcount);
+		}
 	} else {
 		recv_msg = ipmi_alloc_recv_msg(user);
 		if (IS_ERR(recv_msg))

@@ -131,9 +131,15 @@ int __kprobes arch_prepare_kprobe(struct
 
 void *alloc_insn_page(void)
 {
-	return __vmalloc_node_range(PAGE_SIZE, 1, VMALLOC_START, VMALLOC_END,
+	void *addr;
+
+	addr = __vmalloc_node_range(PAGE_SIZE, 1, VMALLOC_START, VMALLOC_END,
 			GFP_KERNEL, PAGE_KERNEL_ROX, VM_FLUSH_RESET_PERMS,
 			NUMA_NO_NODE, __builtin_return_address(0));
+	if (!addr)
+		return NULL;
+	set_memory_rox((unsigned long)addr, 1);
+	return addr;
 }
 
 /* arm kprobe: install breakpoint in text */

@@ -2174,17 +2174,21 @@ static void bti_enable(const struct arm6
 #ifdef CONFIG_ARM64_MTE
 static void cpu_enable_mte(struct arm64_cpu_capabilities const *cap)
 {
+	static bool cleared_zero_page = false;
+
 	sysreg_clear_set(sctlr_el1, 0, SCTLR_ELx_ATA | SCTLR_EL1_ATA0);
 
 	mte_cpu_setup();
 
 	/*
 	 * Clear the tags in the zero page. This needs to be done via the
-	 * linear map which has the Tagged attribute.
+	 * linear map which has the Tagged attribute. Since this page is
+	 * always mapped as pte_special(), set_pte_at() will not attempt to
+	 * clear the tags or set PG_mte_tagged.
 	 */
-	if (try_page_mte_tagging(ZERO_PAGE(0))) {
+	if (!cleared_zero_page) {
+		cleared_zero_page = true;
 		mte_clear_page_tags(lm_alias(empty_zero_page));
-		set_page_mte_tagged(ZERO_PAGE(0));
 	}
 
 	kasan_init_hw_tags_cpu();

@@ -428,7 +428,8 @@ static int __access_remote_tags(struct m
 			put_page(page);
 			break;
 		}
-		WARN_ON_ONCE(!page_mte_tagged(page));
+
+		WARN_ON_ONCE(!page_mte_tagged(page) && !is_zero_page(page));
 
 		/* limit access to the end of the page */
 		offset = offset_in_page(addr);

@@ -1203,7 +1203,7 @@ static int acpi_battery_add(struct acpi_
 	if (device->dep_unmet)
 		return -EPROBE_DEFER;
 
-	battery = kzalloc(sizeof(struct acpi_battery), GFP_KERNEL);
+	battery = devm_kzalloc(&device->dev, sizeof(*battery), GFP_KERNEL);
 	if (!battery)
 		return -ENOMEM;
 	battery->device = device;

@@ -1241,7 +1241,6 @@ fail:
 	sysfs_remove_battery(battery);
 	mutex_destroy(&battery->lock);
 	mutex_destroy(&battery->sysfs_lock);
-	kfree(battery);
 
 	return result;
 }

@@ -1264,7 +1263,6 @@ static void acpi_battery_remove(struct a
 
 	mutex_destroy(&battery->lock);
 	mutex_destroy(&battery->sysfs_lock);
-	kfree(battery);
 }
 
 #ifdef CONFIG_PM_SLEEP

@@ -1210,8 +1210,8 @@ static int acpi_battery_add(struct acpi_
 	strcpy(acpi_device_name(device), ACPI_BATTERY_DEVICE_NAME);
 	strcpy(acpi_device_class(device), ACPI_BATTERY_CLASS);
 	device->driver_data = battery;
-	mutex_init(&battery->lock);
-	mutex_init(&battery->sysfs_lock);
+	devm_mutex_init(&device->dev, &battery->lock);
+	devm_mutex_init(&device->dev, &battery->sysfs_lock);
 	if (acpi_has_method(battery->device->handle, "_BIX"))
 		set_bit(ACPI_BATTERY_XINFO_PRESENT, &battery->flags);
 

@@ -1239,8 +1239,6 @@ fail_pm:
 	unregister_pm_notifier(&battery->pm_nb);
 fail:
 	sysfs_remove_battery(battery);
-	mutex_destroy(&battery->lock);
-	mutex_destroy(&battery->sysfs_lock);
 
 	return result;
 }

@@ -1260,9 +1258,6 @@ static void acpi_battery_remove(struct a
 	device_init_wakeup(&device->dev, 0);
 	unregister_pm_notifier(&battery->pm_nb);
 	sysfs_remove_battery(battery);
-
-	mutex_destroy(&battery->lock);
-	mutex_destroy(&battery->sysfs_lock);
 }
 
 #ifdef CONFIG_PM_SLEEP

@@ -1210,8 +1210,14 @@ static int acpi_battery_add(struct acpi_
 	strcpy(acpi_device_name(device), ACPI_BATTERY_DEVICE_NAME);
 	strcpy(acpi_device_class(device), ACPI_BATTERY_CLASS);
 	device->driver_data = battery;
-	devm_mutex_init(&device->dev, &battery->lock);
-	devm_mutex_init(&device->dev, &battery->sysfs_lock);
+	result = devm_mutex_init(&device->dev, &battery->lock);
+	if (result)
+		return result;
+
+	result = devm_mutex_init(&device->dev, &battery->sysfs_lock);
+	if (result)
+		return result;
+
 	if (acpi_has_method(battery->device->handle, "_BIX"))
 		set_bit(ACPI_BATTERY_XINFO_PRESENT, &battery->flags);
 

@@ -94,7 +94,7 @@ enum {
 
 struct acpi_battery {
 	struct mutex lock;
-	struct mutex sysfs_lock;
+	struct mutex update_lock;
 	struct power_supply *bat;
 	struct power_supply_desc bat_desc;
 	struct acpi_device *device;

@@ -888,15 +888,12 @@ static int sysfs_add_battery(struct acpi
 
 static void sysfs_remove_battery(struct acpi_battery *battery)
 {
-	mutex_lock(&battery->sysfs_lock);
-	if (!battery->bat) {
-		mutex_unlock(&battery->sysfs_lock);
+	if (!battery->bat)
 		return;
-	}
+
 	battery_hook_remove_battery(battery);
 	power_supply_unregister(battery->bat);
 	battery->bat = NULL;
-	mutex_unlock(&battery->sysfs_lock);
 }
 
 static void find_battery(const struct dmi_header *dm, void *private)

@@ -1056,6 +1053,9 @@ static void acpi_battery_notify(acpi_han
 
 	if (!battery)
 		return;
+
+	guard(mutex)(&battery->update_lock);
+
 	old = battery->bat;
 	/*
 	 * On Acer Aspire V5-573G notifications are sometimes triggered too

@@ -1078,21 +1078,22 @@ static void acpi_battery_notify(acpi_han
 }
 
 static int battery_notify(struct notifier_block *nb,
-			       unsigned long mode, void *_unused)
+			  unsigned long mode, void *_unused)
 {
 	struct acpi_battery *battery = container_of(nb, struct acpi_battery,
 						    pm_nb);
-	int result;
 
-	switch (mode) {
-	case PM_POST_HIBERNATION:
-	case PM_POST_SUSPEND:
+	if (mode == PM_POST_SUSPEND || mode == PM_POST_HIBERNATION) {
+		guard(mutex)(&battery->update_lock);
+
 		if (!acpi_battery_present(battery))
 			return 0;
 
 		if (battery->bat) {
 			acpi_battery_refresh(battery);
 		} else {
+			int result;
+
 			result = acpi_battery_get_info(battery);
 			if (result)
 				return result;

@@ -1104,7 +1105,6 @@ static int battery_notify(struct notifie
 
 		acpi_battery_init_alarm(battery);
 		acpi_battery_get_state(battery);
-		break;
 	}
 
 	return 0;

@@ -1182,6 +1182,8 @@ static int acpi_battery_update_retry(str
 {
 	int retry, ret;
 
+	guard(mutex)(&battery->update_lock);
+
 	for (retry = 5; retry; retry--) {
 		ret = acpi_battery_update(battery, false);
 		if (!ret)

@@ -1192,6 +1194,13 @@ static int acpi_battery_update_retry(str
 	return ret;
 }
 
+static void sysfs_battery_cleanup(struct acpi_battery *battery)
+{
+	guard(mutex)(&battery->update_lock);
+
+	sysfs_remove_battery(battery);
+}
+
 static int acpi_battery_add(struct acpi_device *device)
 {
 	int result = 0;

@@ -1214,7 +1223,7 @@ static int acpi_battery_add(struct acpi_
 	if (result)
 		return result;
 
-	result = devm_mutex_init(&device->dev, &battery->sysfs_lock);
+	result = devm_mutex_init(&device->dev, &battery->update_lock);
 	if (result)
 		return result;
 

@@ -1244,7 +1253,7 @@ fail_pm:
 	device_init_wakeup(&device->dev, 0);
 	unregister_pm_notifier(&battery->pm_nb);
 fail:
-	sysfs_remove_battery(battery);
+	sysfs_battery_cleanup(battery);
 
 	return result;
 }

@@ -1263,6 +1272,9 @@ static void acpi_battery_remove(struct a
 
 	device_init_wakeup(&device->dev, 0);
 	unregister_pm_notifier(&battery->pm_nb);
+
+	guard(mutex)(&battery->update_lock);
+
 	sysfs_remove_battery(battery);
 }
 

@@ -1280,6 +1292,9 @@ static int acpi_battery_resume(struct de
 		return -EINVAL;
 
 	battery->update_time = 0;
+
+	guard(mutex)(&battery->update_lock);
+
 	acpi_battery_update(battery, true);
 	return 0;
 }

@@ -112,32 +112,12 @@ static bool acpi_nondev_subnode_extract(
 	return false;
 }
 
-static bool acpi_nondev_subnode_data_ok(acpi_handle handle,
-					const union acpi_object *link,
-					struct list_head *list,
-					struct fwnode_handle *parent)
-{
-	struct acpi_buffer buf = { ACPI_ALLOCATE_BUFFER };
-	acpi_status status;
-
-	status = acpi_evaluate_object_typed(handle, NULL, NULL, &buf,
-					    ACPI_TYPE_PACKAGE);
-	if (ACPI_FAILURE(status))
-		return false;
-
-	if (acpi_nondev_subnode_extract(buf.pointer, handle, link, list,
-					parent))
-		return true;
-
-	ACPI_FREE(buf.pointer);
-	return false;
-}
-
 static bool acpi_nondev_subnode_ok(acpi_handle scope,
 				   const union acpi_object *link,
 				   struct list_head *list,
 				   struct fwnode_handle *parent)
 {
+	struct acpi_buffer buf = { ACPI_ALLOCATE_BUFFER };
 	acpi_handle handle;
 	acpi_status status;
 

@@ -149,7 +129,17 @@ static bool acpi_nondev_subnode_ok(acpi_
 	if (ACPI_FAILURE(status))
 		return false;
 
-	return acpi_nondev_subnode_data_ok(handle, link, list, parent);
+	status = acpi_evaluate_object_typed(handle, NULL, NULL, &buf,
+					    ACPI_TYPE_PACKAGE);
+	if (ACPI_FAILURE(status))
+		return false;
+
+	if (acpi_nondev_subnode_extract(buf.pointer, handle, link, list,
+					parent))
+		return true;
+
+	ACPI_FREE(buf.pointer);
+	return false;
 }
 
 static bool acpi_add_nondev_subnodes(acpi_handle scope,

@@ -162,7 +152,6 @@ static bool acpi_add_nondev_subnodes(acp
 
 	for (i = 0; i < links->package.count; i++) {
 		union acpi_object *link, *desc;
-		acpi_handle handle;
 		bool result;
 
 		link = &links->package.elements[i];

@@ -174,22 +163,26 @@ static bool acpi_add_nondev_subnodes(acp
 		if (link->package.elements[0].type != ACPI_TYPE_STRING)
 			continue;
 
-		/* The second one may be a string, a reference or a package. */
+		/* The second one may be a string or a package. */
 		switch (link->package.elements[1].type) {
 		case ACPI_TYPE_STRING:
 			result = acpi_nondev_subnode_ok(scope, link, list,
 							 parent);
 			break;
-		case ACPI_TYPE_LOCAL_REFERENCE:
-			handle = link->package.elements[1].reference.handle;
-			result = acpi_nondev_subnode_data_ok(handle, link, list,
-							     parent);
-			break;
 		case ACPI_TYPE_PACKAGE:
 			desc = &link->package.elements[1];
 			result = acpi_nondev_subnode_extract(desc, NULL, link,
 							     list, parent);
 			break;
+		case ACPI_TYPE_LOCAL_REFERENCE:
+			/*
+			 * It is not expected to see any local references in
+			 * the links package because referencing a named object
+			 * should cause it to be evaluated in place.
+			 */
+			acpi_handle_info(scope, "subnode %s: Unexpected reference\n",
+					 link->package.elements[0].string.pointer);
+			fallthrough;
 		default:
 			result = false;
 			break;

@@ -96,7 +96,18 @@ static bool acpi_nondev_subnode_extract(
 	if (handle)
 		acpi_get_parent(handle, &scope);
 
+	/*
+	 * Extract properties from the _DSD-equivalent package pointed to by
+	 * desc and use scope (if not NULL) for the completion of relative
+	 * pathname segments.
+	 *
+	 * The extracted properties will be held in the new data node dn.
+	 */
 	result = acpi_extract_properties(scope, desc, &dn->data);
+	/*
+	 * Look for subnodes in the _DSD-equivalent package pointed to by desc
+	 * and create child nodes of dn if there are any.
+	 */
 	if (acpi_enumerate_nondev_subnodes(scope, desc, &dn->data, &dn->fwnode))
 		result = true;
 

@@ -121,6 +132,12 @@ static bool acpi_nondev_subnode_ok(acpi_
 	acpi_handle handle;
 	acpi_status status;
 
+	/*
+	 * If the scope is unknown, the _DSD-equivalent package being parsed
+	 * was embedded in an outer _DSD-equivalent package as a result of
+	 * direct evaluation of an object pointed to by a reference.  In that
+	 * case, using a pathname as the target object pointer is invalid.
+	 */
 	if (!scope)
 		return false;
 

@@ -150,6 +167,10 @@ static bool acpi_add_nondev_subnodes(acp
 	bool ret = false;
 	int i;
 
+	/*
+	 * Every element in the links package is expected to represent a link
+	 * to a non-device node in a tree containing device-specific data.
+	 */
 	for (i = 0; i < links->package.count; i++) {
 		union acpi_object *link, *desc;
 		bool result;

@@ -159,17 +180,38 @@ static bool acpi_add_nondev_subnodes(acp
 		if (link->package.count != 2)
 			continue;
 
-		/* The first one must be a string. */
+		/* The first one (the key) must be a string. */
 		if (link->package.elements[0].type != ACPI_TYPE_STRING)
 			continue;
 
-		/* The second one may be a string or a package. */
+		/* The second one (the target) may be a string or a package. */
 		switch (link->package.elements[1].type) {
 		case ACPI_TYPE_STRING:
+			/*
+			 * The string is expected to be a full pathname or a
+			 * pathname segment relative to the given scope.  That
+			 * pathname is expected to point to an object returning
+			 * a package that contains _DSD-equivalent information.
+			 */
 			result = acpi_nondev_subnode_ok(scope, link, list,
 							 parent);
 			break;
 		case ACPI_TYPE_PACKAGE:
+			/*
+			 * This happens when a reference is used in AML to
+			 * point to the target.  Since the target is expected
+			 * to be a named object, a reference to it will cause it
+			 * to be avaluated in place and its return package will
+			 * be embedded in the links package at the location of
+			 * the reference.
+			 *
+			 * The target package is expected to contain _DSD-
+			 * equivalent information, but the scope in which it
+			 * is located in the original AML is unknown.  Thus
+			 * it cannot contain pathname segments represented as
+			 * strings because there is no way to build full
+			 * pathnames out of them.
+			 */
 			desc = &link->package.elements[1];
 			result = acpi_nondev_subnode_extract(desc, NULL, link,
 							     list, parent);

@@ -112,6 +112,10 @@ static bool acpi_nondev_subnode_extract(
 		result = true;
 
 	if (result) {
+		/*
+		 * This will be NULL if the desc package is embedded in an outer
+		 * _DSD-equivalent package and its scope cannot be determined.
+		 */
 		dn->handle = handle;
 		dn->data.pointer = desc;
 		list_add_tail(&dn->sibling, list);

@@ -212,6 +216,8 @@ static bool acpi_add_nondev_subnodes(acp
 			 * strings because there is no way to build full
 			 * pathnames out of them.
 			 */
+			acpi_handle_debug(scope, "subnode %s: Unknown scope\n",
+					  link->package.elements[0].string.pointer);
 			desc = &link->package.elements[1];
 			result = acpi_nondev_subnode_extract(desc, NULL, link,
 							     list, parent);

@@ -384,6 +390,9 @@ static void acpi_untie_nondev_subnodes(s
 	struct acpi_data_node *dn;
 
 	list_for_each_entry(dn, &data->subnodes, sibling) {
+		if (!dn->handle)
+			continue;
+
 		acpi_detach_data(dn->handle, acpi_nondev_subnode_tag);
 
 		acpi_untie_nondev_subnodes(&dn->data);

@@ -398,6 +407,9 @@ static bool acpi_tie_nondev_subnodes(str
 		acpi_status status;
 		bool ret;
 
+		if (!dn->handle)
+			continue;
+
 		status = acpi_attach_data(dn->handle, acpi_nondev_subnode_tag, dn);
 		if (ACPI_FAILURE(status) && status != AE_ALREADY_EXISTS) {
 			acpi_handle_err(dn->handle, "Can't tag data node\n");

@@ -35,7 +35,7 @@
 
 struct bpf_jit {
 	u32 seen;		/* Flags to remember seen eBPF instructions */
-	u32 seen_reg[16];	/* Array to remember which registers are used */
+	u16 seen_regs;		/* Mask to remember which registers are used */
 	u32 *addrs;		/* Array with relative instruction addresses */
 	u8 *prg_buf;		/* Start of program */
 	int size;		/* Size of program and literal pool */

@@ -118,8 +118,8 @@ static inline void reg_set_seen(struct b
 {
 	u32 r1 = reg2hex[b1];
 
-	if (r1 >= 6 && r1 <= 15 && !jit->seen_reg[r1])
-		jit->seen_reg[r1] = 1;
+	if (r1 >= 6 && r1 <= 15)
+		jit->seen_regs |= (1 << r1);
 }
 
 #define REG_SET_SEEN(b1)					\

@@ -127,8 +127,6 @@ static inline void reg_set_seen(struct b
 	reg_set_seen(jit, b1);					\
 })
 
-#define REG_SEEN(b1) jit->seen_reg[reg2hex[(b1)]]
-
 /*
  * EMIT macros for code generation
  */

@@ -436,12 +434,12 @@ static void restore_regs(struct bpf_jit
 /*
  * Return first seen register (from start)
  */
-static int get_start(struct bpf_jit *jit, int start)
+static int get_start(u16 seen_regs, int start)
 {
 	int i;
 
 	for (i = start; i <= 15; i++) {
-		if (jit->seen_reg[i])
+		if (seen_regs & (1 << i))
 			return i;
 	}
 	return 0;

@@ -450,15 +448,15 @@ static int get_start(struct bpf_jit *jit
 /*
  * Return last seen register (from start) (gap >= 2)
  */
-static int get_end(struct bpf_jit *jit, int start)
+static int get_end(u16 seen_regs, int start)
 {
 	int i;
 
 	for (i = start; i < 15; i++) {
-		if (!jit->seen_reg[i] && !jit->seen_reg[i + 1])
+		if (!(seen_regs & (3 << i)))
 			return i - 1;
 	}
-	return jit->seen_reg[15] ? 15 : 14;
+	return (seen_regs & (1 << 15)) ? 15 : 14;
 }
 
 #define REGS_SAVE	1

@@ -467,8 +465,10 @@ static int get_end(struct bpf_jit *jit,
  * Save and restore clobbered registers (6-15) on stack.
  * We save/restore registers in chunks with gap >= 2 registers.
  */
-static void save_restore_regs(struct bpf_jit *jit, int op, u32 stack_depth)
+static void save_restore_regs(struct bpf_jit *jit, int op, u32 stack_depth,
+			      u16 extra_regs)
 {
+	u16 seen_regs = jit->seen_regs | extra_regs;
 	const int last = 15, save_restore_size = 6;
 	int re = 6, rs;
 

@@ -482,10 +482,10 @@ static void save_restore_regs(struct bpf
 	}
 
 	do {
-		rs = get_start(jit, re);
+		rs = get_start(seen_regs, re);
 		if (!rs)
 			break;
-		re = get_end(jit, rs + 1);
+		re = get_end(seen_regs, rs + 1);
 		if (op == REGS_SAVE)
 			save_regs(jit, rs, re);
 		else

@@ -579,7 +579,7 @@ static void bpf_jit_prologue(struct bpf_
 	/* Tail calls have to skip above initialization */
 	jit->tail_call_start = jit->prg;
 	/* Save registers */
-	save_restore_regs(jit, REGS_SAVE, stack_depth);
+	save_restore_regs(jit, REGS_SAVE, stack_depth, 0);
 	/* Setup literal pool */
 	if (is_first_pass(jit) || (jit->seen & SEEN_LITERAL)) {
 		if (!is_first_pass(jit) &&

@@ -653,7 +653,7 @@ static void bpf_jit_epilogue(struct bpf_
 	/* Load exit code: lgr %r2,%b0 */
 	EMIT4(0xb9040000, REG_2, BPF_REG_0);
 	/* Restore registers */
-	save_restore_regs(jit, REGS_RESTORE, stack_depth);
+	save_restore_regs(jit, REGS_RESTORE, stack_depth, 0);
 	if (nospec_uses_trampoline()) {
 		jit->r14_thunk_ip = jit->prg;
 		/* Generate __s390_indirect_jump_r14 thunk */

@@ -1519,7 +1519,7 @@ static noinline int bpf_jit_insn(struct
 		/*
 		 * Restore registers before calling function
 		 */
-		save_restore_regs(jit, REGS_RESTORE, stack_depth);
+		save_restore_regs(jit, REGS_RESTORE, stack_depth, 0);
 
 		/*
 		 * goto *(prog->bpf_func + tail_call_start);

@@ -53,6 +53,7 @@ struct bpf_jit {
 	int excnt;		/* Number of exception table entries */
 	int prologue_plt_ret;	/* Return address for prologue hotpatch PLT */
 	int prologue_plt;	/* Start of prologue hotpatch PLT */
+	u32 frame_off;		/* Offset of frame from %r15 */
 };
 
 #define SEEN_MEM	BIT(0)		/* use mem[] for temporary storage */

@@ -416,12 +417,9 @@ static void save_regs(struct bpf_jit *ji
 /*
  * Restore registers from "rs" (register start) to "re" (register end) on stack
  */
-static void restore_regs(struct bpf_jit *jit, u32 rs, u32 re, u32 stack_depth)
+static void restore_regs(struct bpf_jit *jit, u32 rs, u32 re)
 {
-	u32 off = STK_OFF_R6 + (rs - 6) * 8;
-
-	if (jit->seen & SEEN_STACK)
-		off += STK_OFF + stack_depth;
+	u32 off = jit->frame_off + STK_OFF_R6 + (rs - 6) * 8;
 
 	if (rs == re)
 		/* lg %rs,off(%r15) */

@@ -465,8 +463,7 @@ static int get_end(u16 seen_regs, int st
  * Save and restore clobbered registers (6-15) on stack.
  * We save/restore registers in chunks with gap >= 2 registers.
  */
-static void save_restore_regs(struct bpf_jit *jit, int op, u32 stack_depth,
-			      u16 extra_regs)
+static void save_restore_regs(struct bpf_jit *jit, int op, u16 extra_regs)
 {
 	u16 seen_regs = jit->seen_regs | extra_regs;
 	const int last = 15, save_restore_size = 6;

@@ -489,7 +486,7 @@ static void save_restore_regs(struct bpf
 		if (op == REGS_SAVE)
 			save_regs(jit, rs, re);
 		else
-			restore_regs(jit, rs, re, stack_depth);
+			restore_regs(jit, rs, re);
 		re++;
 	} while (re <= last);
 }

@@ -556,8 +553,7 @@ static void bpf_jit_plt(struct bpf_plt *
  * Save registers and create stack frame if necessary.
  * See stack frame layout description in "bpf_jit.h"!
  */
-static void bpf_jit_prologue(struct bpf_jit *jit, struct bpf_prog *fp,
-			     u32 stack_depth)
+static void bpf_jit_prologue(struct bpf_jit *jit, struct bpf_prog *fp)
 {
 	/* No-op for hotpatching */
 	/* brcl 0,prologue_plt */

@@ -579,7 +575,7 @@ static void bpf_jit_prologue(struct bpf_
 	/* Tail calls have to skip above initialization */
 	jit->tail_call_start = jit->prg;
 	/* Save registers */
-	save_restore_regs(jit, REGS_SAVE, stack_depth, 0);
+	save_restore_regs(jit, REGS_SAVE, 0);
 	/* Setup literal pool */
 	if (is_first_pass(jit) || (jit->seen & SEEN_LITERAL)) {
 		if (!is_first_pass(jit) &&

@@ -599,8 +595,8 @@ static void bpf_jit_prologue(struct bpf_
 		EMIT4(0xb9040000, REG_W1, REG_15);
 		/* la %bfp,STK_160_UNUSED(%r15) (BPF frame pointer) */
 		EMIT4_DISP(0x41000000, BPF_REG_FP, REG_15, STK_160_UNUSED);
-		/* aghi %r15,-STK_OFF */
-		EMIT4_IMM(0xa70b0000, REG_15, -(STK_OFF + stack_depth));
+		/* aghi %r15,-frame_off */
+		EMIT4_IMM(0xa70b0000, REG_15, -jit->frame_off);
 		/* stg %w1,152(%r15) (backchain) */
 		EMIT6_DISP_LH(0xe3000000, 0x0024, REG_W1, REG_0,
 			      REG_15, 152);

@@ -647,13 +643,13 @@ static void call_r1(struct bpf_jit *jit)
 /*
  * Function epilogue
  */
-static void bpf_jit_epilogue(struct bpf_jit *jit, u32 stack_depth)
+static void bpf_jit_epilogue(struct bpf_jit *jit)
 {
 	jit->exit_ip = jit->prg;
 	/* Load exit code: lgr %r2,%b0 */
 	EMIT4(0xb9040000, REG_2, BPF_REG_0);
 	/* Restore registers */
-	save_restore_regs(jit, REGS_RESTORE, stack_depth, 0);
+	save_restore_regs(jit, REGS_RESTORE, 0);
 	if (nospec_uses_trampoline()) {
 		jit->r14_thunk_ip = jit->prg;
 		/* Generate __s390_indirect_jump_r14 thunk */

@@ -779,7 +775,7 @@ static int sign_extend(struct bpf_jit *j
  * stack space for the large switch statement.
  */
 static noinline int bpf_jit_insn(struct bpf_jit *jit, struct bpf_prog *fp,
-				 int i, bool extra_pass, u32 stack_depth)
+				 int i, bool extra_pass)
 {
 	struct bpf_insn *insn = &fp->insnsi[i];
 	u32 dst_reg = insn->dst_reg;

@@ -1433,9 +1429,9 @@ static noinline int bpf_jit_insn(struct
 		 * Note 2: We assume that the verifier does not let us call the
 		 * main program, which clears the tail call counter on entry.
 		 */
-		/* mvc STK_OFF_TCCNT(4,%r15),N(%r15) */
+		/* mvc STK_OFF_TCCNT(4,%r15),frame_off+STK_OFF_TCCNT(%r15) */
 		_EMIT6(0xd203f000 | STK_OFF_TCCNT,
-		       0xf000 | (STK_OFF_TCCNT + STK_OFF + stack_depth));
+		       0xf000 | (jit->frame_off + STK_OFF_TCCNT));
 
 		/* Sign-extend the kfunc arguments. */
 		if (insn->src_reg == BPF_PSEUDO_KFUNC_CALL) {

@@ -1486,10 +1482,7 @@ static noinline int bpf_jit_insn(struct
 		 *         goto out;
 		 */
 
-		if (jit->seen & SEEN_STACK)
-			off = STK_OFF_TCCNT + STK_OFF + stack_depth;
-		else
-			off = STK_OFF_TCCNT;
+		off = jit->frame_off + STK_OFF_TCCNT;
 		/* lhi %w0,1 */
 		EMIT4_IMM(0xa7080000, REG_W0, 1);
 		/* laal %w1,%w0,off(%r15) */

@@ -1519,7 +1512,7 @@ static noinline int bpf_jit_insn(struct
 		/*
 		 * Restore registers before calling function
 		 */
-		save_restore_regs(jit, REGS_RESTORE, stack_depth, 0);
+		save_restore_regs(jit, REGS_RESTORE, 0);
 
 		/*
 		 * goto *(prog->bpf_func + tail_call_start);

@@ -1822,7 +1815,7 @@ static int bpf_set_addr(struct bpf_jit *
  * Compile eBPF program into s390x code
  */
 static int bpf_jit_prog(struct bpf_jit *jit, struct bpf_prog *fp,
-			bool extra_pass, u32 stack_depth)
+			bool extra_pass)
 {
 	int i, insn_count, lit32_size, lit64_size;
 

@@ -1830,19 +1823,23 @@ static int bpf_jit_prog(struct bpf_jit *
 	jit->lit64 = jit->lit64_start;
 	jit->prg = 0;
 	jit->excnt = 0;
+	if (is_first_pass(jit) || (jit->seen & SEEN_STACK))
+		jit->frame_off = STK_OFF + round_up(fp->aux->stack_depth, 8);
+	else
+		jit->frame_off = 0;
 
-	bpf_jit_prologue(jit, fp, stack_depth);
+	bpf_jit_prologue(jit, fp);
 	if (bpf_set_addr(jit, 0) < 0)
 		return -1;
 	for (i = 0; i < fp->len; i += insn_count) {
-		insn_count = bpf_jit_insn(jit, fp, i, extra_pass, stack_depth);
+		insn_count = bpf_jit_insn(jit, fp, i, extra_pass);
 		if (insn_count < 0)
 			return -1;
 		/* Next instruction address */
 		if (bpf_set_addr(jit, i + insn_count) < 0)
 			return -1;
 	}
-	bpf_jit_epilogue(jit, stack_depth);
+	bpf_jit_epilogue(jit);
 
 	lit32_size = jit->lit32 - jit->lit32_start;
 	lit64_size = jit->lit64 - jit->lit64_start;

@@ -1902,7 +1899,6 @@ static struct bpf_binary_header *bpf_jit
  */
 struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *fp)
 {
-	u32 stack_depth = round_up(fp->aux->stack_depth, 8);
 	struct bpf_prog *tmp, *orig_fp = fp;
 	struct bpf_binary_header *header;
 	struct s390_jit_data *jit_data;

@@ -1955,7 +1951,7 @@ struct bpf_prog *bpf_int_jit_compile(str
 	 *   - 3:   Calculate program size and addrs array
 	 */
 	for (pass = 1; pass <= 3; pass++) {
-		if (bpf_jit_prog(&jit, fp, extra_pass, stack_depth)) {
+		if (bpf_jit_prog(&jit, fp, extra_pass)) {
 			fp = orig_fp;
 			goto free_addrs;
 		}

@@ -1969,7 +1965,7 @@ struct bpf_prog *bpf_int_jit_compile(str
 		goto free_addrs;
 	}
 skip_init_ctx:
-	if (bpf_jit_prog(&jit, fp, extra_pass, stack_depth)) {
+	if (bpf_jit_prog(&jit, fp, extra_pass)) {
 		bpf_jit_binary_free(header);
 		fp = orig_fp;
 		goto free_addrs;

@@ -1,55 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-/*
- * BPF Jit compiler defines
- *
- * Copyright IBM Corp. 2012,2015
- *
- * Author(s): Martin Schwidefsky <[email protected]>
- *	      Michael Holzheu <[email protected]>
- */
-
-#ifndef __ARCH_S390_NET_BPF_JIT_H
-#define __ARCH_S390_NET_BPF_JIT_H
-
-#ifndef __ASSEMBLY__
-
-#include <linux/filter.h>
-#include <linux/types.h>
-
-#endif /* __ASSEMBLY__ */
-
-/*
- * Stackframe layout (packed stack):
- *
- *				    ^ high
- *	      +---------------+     |
- *	      | old backchain |     |
- *	      +---------------+     |
- *	      |   r15 - r6    |     |
- *	      +---------------+     |
- *	      | 4 byte align  |     |
- *	      | tail_call_cnt |     |
- * BFP	   -> +===============+     |
- *	      |		      |     |
- *	      |   BPF stack   |     |
- *	      |		      |     |
- * R15+160 -> +---------------+     |
- *	      | new backchain |     |
- * R15+152 -> +---------------+     |
- *	      | + 152 byte SA |     |
- * R15	   -> +---------------+     + low
- *
- * We get 160 bytes stack space from calling function, but only use
- * 12 * 8 byte for old backchain, r15..r6, and tail_call_cnt.
- *
- * The stack size used by the BPF program ("BPF stack" above) is passed
- * via "aux->stack_depth".
- */
-#define STK_SPACE_ADD	(160)
-#define STK_160_UNUSED	(160 - 12 * 8)
-#define STK_OFF		(STK_SPACE_ADD - STK_160_UNUSED)
-
-#define STK_OFF_R6	(160 - 11 * 8)	/* Offset of r6 on stack */
-#define STK_OFF_TCCNT	(160 - 12 * 8)	/* Offset of tail_call_cnt on stack */
-
-#endif /* __ARCH_S390_NET_BPF_JIT_H */

158 lines not on this page · raw message

@@ -1439,13 +1439,6 @@ static noinline int bpf_jit_insn(struct
 		jit->seen |= SEEN_FUNC;
 		/*
 		 * Copy the tail call counter to where the callee expects it.
-		 *
-		 * Note 1: The callee can increment the tail call counter, but
-		 * we do not load it back, since the x86 JIT does not do this
-		 * either.
-		 *
-		 * Note 2: We assume that the verifier does not let us call the
-		 * main program, which clears the tail call counter on entry.
 		 */
 		/* mvc tail_call_cnt(4,%r15),frame_off+tail_call_cnt(%r15) */
 		_EMIT6(0xd203f000 | offsetof(struct prog_frame, tail_call_cnt),

@@ -1472,6 +1465,22 @@ static noinline int bpf_jit_insn(struct
 		call_r1(jit);
 		/* lgr %b0,%r2: load return value into %b0 */
 		EMIT4(0xb9040000, BPF_REG_0, REG_2);
+
+		/*
+		 * Copy the potentially updated tail call counter back.
+		 */
+
+		if (insn->src_reg == BPF_PSEUDO_CALL)
+			/*
+			 * mvc frame_off+tail_call_cnt(%r15),
+			 *     tail_call_cnt(4,%r15)
+			 */
+			_EMIT6(0xd203f000 | (jit->frame_off +
+					     offsetof(struct prog_frame,
+						      tail_call_cnt)),
+			       0xf000 | offsetof(struct prog_frame,
+						 tail_call_cnt));
+
 		break;
 	}
 	case BPF_JMP | BPF_TAIL_CALL: {

@@ -2462,6 +2462,9 @@ static int __arch_prepare_bpf_trampoline
 		/* stg %r2,retval_off(%r15) */
 		EMIT6_DISP_LH(0xe3000000, 0x0024, REG_2, REG_0, REG_15,
 			      tjit->retval_off);
+		/* mvc tccnt_off(%r15),tail_call_cnt(4,%r15) */
+		_EMIT6(0xd203f000 | tjit->tccnt_off,
+		       0xf000 | offsetof(struct prog_frame, tail_call_cnt));
 
 		im->ip_after_call = jit->prg_buf + jit->prg;
 

@@ -264,23 +264,6 @@ static void test_softdirty(void)
 	munmap(addr, SIZE);
 }
 
-static int system_has_softdirty(void)
-{
-	/*
-	 * There is no way to check if the kernel supports soft-dirty, other
-	 * than by writing to a page and seeing if the bit was set. But the
-	 * tests are intended to check that the bit gets set when it should, so
-	 * doing that check would turn a potentially legitimate fail into a
-	 * skip. Fortunately, we know for sure that arm64 does not support
-	 * soft-dirty. So for now, let's just use the arch as a corse guide.
-	 */
-#if defined(__aarch64__)
-	return 0;
-#else
-	return 1;
-#endif
-}
-
 int main(int argc, char **argv)
 {
 	int nr_tests = 16;

@@ -288,7 +271,7 @@ int main(int argc, char **argv)
 
 	pagesize = getpagesize();
 
-	if (system_has_softdirty())
+	if (softdirty_supported())
 		nr_tests += 5;
 
 	ksft_print_header();

@@ -300,7 +283,7 @@ int main(int argc, char **argv)
 	test_holes();
 	test_populate_read();
 	test_populate_write();
-	if (system_has_softdirty())
+	if (softdirty_supported())
 		test_softdirty();
 
 	err = ksft_get_fail_cnt();

@@ -193,8 +193,11 @@ int main(int argc, char **argv)
 	int pagesize;
 
 	ksft_print_header();
-	ksft_set_plan(15);
 
+	if (!softdirty_supported())
+		ksft_exit_skip("soft-dirty is not support\n");
+
+	ksft_set_plan(15);
 	pagemap_fd = open(PAGEMAP_FILE_PATH, O_RDONLY);
 	if (pagemap_fd < 0)
 		ksft_exit_fail_msg("Failed to open %s\n", PAGEMAP_FILE_PATH);

86 lines not on this page · raw message

@@ -51,6 +51,7 @@ int uffd_register(int uffd, void *addr,
 int uffd_unregister(int uffd, void *addr, uint64_t len);
 int uffd_register_with_ioctls(int uffd, void *addr, uint64_t len,
 			      bool miss, bool wp, bool minor, uint64_t *ioctls);
+bool softdirty_supported(void);
 
 /*
  * On ppc64 this will only work with radix 2M hugepage size

@@ -227,9 +227,12 @@ void mptcp_pm_add_addr_received(const st
 		} else {
 			__MPTCP_INC_STATS(sock_net((struct sock *)msk), MPTCP_MIB_ADDADDRDROP);
 		}
-	/* id0 should not have a different address */
+	/* - id0 should not have a different address
+	 * - special case for C-flag: linked to fill_local_addresses_vec()
+	 */
 	} else if ((addr->id == 0 && !mptcp_pm_nl_is_init_remote_addr(msk, addr)) ||
-		   (addr->id > 0 && !READ_ONCE(pm->accept_addr))) {
+		   (addr->id > 0 && !READ_ONCE(pm->accept_addr) &&
+		    !mptcp_pm_add_addr_c_flag_case(msk))) {
 		mptcp_pm_announce_addr(msk, addr, true);
 		mptcp_pm_add_addr_send_ack(msk);
 	} else if (mptcp_pm_schedule_work(msk, MPTCP_PM_ADD_ADDR_RECEIVED)) {

78 lines not on this page · raw message

@@ -1080,6 +1080,14 @@ static inline void mptcp_pm_close_subflo
 	spin_unlock_bh(&msk->pm.lock);
 }
 
+static inline bool mptcp_pm_add_addr_c_flag_case(struct mptcp_sock *msk)
+{
+	return READ_ONCE(msk->pm.remote_deny_join_id0) &&
+	       msk->pm.local_addr_used == 0 &&
+	       mptcp_pm_get_add_addr_accept_max(msk) == 0 &&
+	       msk->pm.subflows < mptcp_pm_get_subflows_max(msk);
+}
+
 void mptcp_sockopt_sync(struct mptcp_sock *msk, struct sock *ssk);
 void mptcp_sockopt_sync_locked(struct mptcp_sock *msk, struct sock *ssk);
 

index 5728996691549..0fcd37108b67e 100644
@@ -248,11 +248,10 @@ static int plic_irq_suspend(void)
 
 	priv = per_cpu_ptr(&plic_handlers, smp_processor_id())->priv;
 
-	for (i = 0; i < priv->nr_irqs; i++)
-		if (readl(priv->regs + PRIORITY_BASE + i * PRIORITY_PER_ID))
-			__set_bit(i, priv->prio_save);
-		else
-			__clear_bit(i, priv->prio_save);
+	for (i = 0; i < priv->nr_irqs; i++) {
+		__assign_bit(i, priv->prio_save,
+			     readl(priv->regs + PRIORITY_BASE + i * PRIORITY_PER_ID));
+	}
 
 	for_each_cpu(cpu, cpu_present_mask) {
 		struct plic_handler *handler = per_cpu_ptr(&plic_handlers, cpu);

index 0fcd37108b67e..2d20cf9d84cea 100644
@@ -248,7 +248,8 @@ static int plic_irq_suspend(void)
 
 	priv = per_cpu_ptr(&plic_handlers, smp_processor_id())->priv;
 
-	for (i = 0; i < priv->nr_irqs; i++) {
+	/* irq ID 0 is reserved */
+	for (i = 1; i < priv->nr_irqs; i++) {
 		__assign_bit(i, priv->prio_save,
 			     readl(priv->regs + PRIORITY_BASE + i * PRIORITY_PER_ID));
 	}

@@ -278,7 +279,8 @@ static void plic_irq_resume(void)
 
 	priv = per_cpu_ptr(&plic_handlers, smp_processor_id())->priv;
 
-	for (i = 0; i < priv->nr_irqs; i++) {
+	/* irq ID 0 is reserved */
+	for (i = 1; i < priv->nr_irqs; i++) {
 		index = BIT_WORD(i);
 		writel((priv->prio_save[index] & BIT_MASK(i)) ? 1 : 0,
 		       priv->regs + PRIORITY_BASE + i * PRIORITY_PER_ID);

index df575473c1cc0..ee8a6fe360e72 100644
@@ -470,8 +470,14 @@ void minix_set_inode(struct inode *inode, dev_t rdev)
 		inode->i_op = &minix_symlink_inode_operations;
 		inode_nohighmem(inode);
 		inode->i_mapping->a_ops = &minix_aops;
-	} else
+	} else if (S_ISCHR(inode->i_mode) || S_ISBLK(inode->i_mode) ||
+		   S_ISFIFO(inode->i_mode) || S_ISSOCK(inode->i_mode)) {
 		init_special_inode(inode, inode->i_mode, rdev);
+	} else {
+		printk(KERN_DEBUG "MINIX-fs: Invalid file type 0%04o for inode %lu.\n",
+		       inode->i_mode, inode->i_ino);
+		make_bad_inode(inode);
+	}
 }
 
 /*

index 6500ef956f2f8..e57adc00cb779 100644
@@ -477,7 +477,7 @@ pid_t pid_nr_ns(struct pid *pid, struct pid_namespace *ns)
 	struct upid *upid;
 	pid_t nr = 0;
 
-	if (pid && ns->level <= pid->level) {
+	if (pid && ns && ns->level <= pid->level) {
 		upid = &pid->numbers[ns->level];
 		if (upid->ns == ns)
 			nr = upid->nr;

index e57adc00cb779..69922b2e7ed15 100644
@@ -500,7 +500,8 @@ pid_t __task_pid_nr_ns(struct task_struct *task, enum pid_type type,
 	rcu_read_lock();
 	if (!ns)
 		ns = task_active_pid_ns(current);
-	nr = pid_nr_ns(rcu_dereference(*task_pid_ptr(task, type)), ns);
+	if (ns)
+		nr = pid_nr_ns(rcu_dereference(*task_pid_ptr(task, type)), ns);
 	rcu_read_unlock();
 
 	return nr;