Merge tag 'trace-v7.3-2' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-tracegrafted

Pull tracing fixes from Steven Rostedt:

 - Fix error output of boot instance creation failure

   Currently if a boot instance creation fails, instead of printing out
   the name of the instance that failed, it prints "(null)". That is
   because it prints "cur_str" that had already been processed by
   strsep(). Print the saved name instead.

   While at it, print the error code of the failure.

 - Fix use-after-free for same named historgrams

   Histograms can be named so that they can be used in multiple events.
   But if the named histogram has a variable attached, the second event
   that uses the named histogram which duplicates it and needs to free
   the original after duplication leaves the old variable in place and
   still visible. If another histogram uses than variable, it will use
   the stale one which will try to reference the freed duplicate
   histogram and crash the kernel.

   Free the duplicate variables along with the duplicated histogram
   data.

 - Check return value of kthread_run() in event self test

   The events self tests uses a kthread for testing but does not check
   if it succeeded in creating a kthread. If the kthread creation were
   to fail, the code will still try to call kthread_stop() on the error
   returned.

 - Fix race between reading trace_pipe and updating subbuffer size

   If a user is reading the trace_pipe file at the same time they update
   the ring buffer sub-buffer size, can cause the trace_pipe read to
   read stale data. Add trace_access_lock() around updating the ring
   buffer sub-buffer size.

 - Fix eventfs_inode on failure path in creation of the events directory

   In the creation of the "events" directory, if after allocating the
   eventfs_inode a failure is detected, it calls cleanup_ei() which
   calls free_ei(). The free_ei() will test if eventfs_inode being freed
   has no children. It is a bug if it does. But on the failure case of
   the creation of the "events" directory, the children lists have not
   yet been initialized and the free will trigger a warning because
   list_empty() on an uninitialized list returns false.

   Move the initialization into init_ei() where it makes more sense and
   makes sure that a created eventfs_inode has its lists initialized
   upon creation.

 - Check return value of kthread_run() in ftrace direct sample code

   The sample code that shows how to use the ftrace direct calls does
   not test the return of kthread_run() to see if it succeeds. Return a
   failure if the kthread_run() doesn't succeed.

 - Clear user events state on fork in case of alloc failure

   On fork, the child gets a pointer to the parent's user events state.
   It makes a copy of it then updates the child's pointer to it. But if
   the allocation fails, the duplication function leaves the child with
   a pointer to its parent's descriptor. When the child cleans up its
   data, it will free the parent's descriptor while the parent is still
   using it.

   In the duplication function, set the child's user_event_mm to NULL
   before testing if the allocation succeeded, and when it exits it will
   not free the parent's descriptor.

 - Fix retry exhaustion in simple ring buffer reader swap

   simple_ring_buffer_swap_reader_page() starts with retry set to 8 and
   post-decrements it only after a failed link replacement. On the final
   attempt, a successful replacement leaves retry at zero, while a
   failed replacement leaves it at -1.

   But the check for success expects the retry value to be non-zero and
   exits with an error on zero. This is the opposite result. Fix it.

 - Fail nicely when the remote swap_reader_page() returns an error

   Currently, if the swap_reader_page() of a remote buffer fails, it
   triggers a WARN_ON_ONCE() and continues normally. Instead, have it
   exit with an error and a pr_warn() print instead of a full WARNING.

* tag 'trace-v7.3-2' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace:
  ring-buffer: Stop remote reader update when page swap fails
  tracing: Fix retry exhaustion in simple ring buffer reader swap
  tracing/user_events: Clear copied tracing state before fork duplication
  samples/ftrace: Fix kthread_stop() on ERR_PTR in ftrace-direct-multi-modify
  samples/ftrace: Fix kthread_stop() on ERR_PTR in ftrace-direct-modify
  eventfs: Initialize ei->children and ei->list in init_ei()
  tracing: Fix use-after-free in trace_pipe read on sub-buffer order change
  tracing: Fix crash passing ERR_PTR to kthread_stop()
  tracing: Fix use-after-free with same-name named triggers
  tracing: Fix logged instance name on creation failure

1 files changed, 396 insertions, 0 deletions

diff --git a/include/asm-generic/mshyperv.h b/include/asm-generic/mshyperv.h
new file mode 100644
index 000000000..bf601d67c
--- /dev/null
+++ b/include/asm-generic/mshyperv.h
@@ -0,0 +1,396 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+/*
+ * Linux-specific definitions for managing interactions with Microsoft's
+ * Hyper-V hypervisor. The definitions in this file are architecture
+ * independent. See arch/<arch>/include/asm/mshyperv.h for definitions
+ * that are specific to architecture <arch>.
+ *
+ * Definitions that are derived from Hyper-V code or headers should not go in
+ * this file, but should instead go in the relevant files in include/hyperv.
+ *
+ * Copyright (C) 2019, Microsoft, Inc.
+ *
+ * Author : Michael Kelley <mikelley@microsoft.com>
+ */
+
+#ifndef _ASM_GENERIC_MSHYPERV_H
+#define _ASM_GENERIC_MSHYPERV_H
+
+#include <linux/types.h>
+#include <linux/atomic.h>
+#include <linux/bitops.h>
+#include <acpi/acpi_numa.h>
+#include <linux/cpumask.h>
+#include <linux/nmi.h>
+#include <asm/ptrace.h>
+#include <hyperv/hvhdk.h>
+
+#define VTPM_BASE_ADDRESS 0xfed40000
+
+enum hv_partition_type {
+	HV_PARTITION_TYPE_GUEST,
+	HV_PARTITION_TYPE_ROOT,
+	HV_PARTITION_TYPE_L1VH,
+};
+
+struct ms_hyperv_info {
+	u32 features;
+	u32 priv_high;
+	u32 ext_features;
+	u32 misc_features;
+	u32 hints;
+	u32 nested_features;
+	u32 max_vp_index;
+	u32 max_lp_index;
+	u8 vtl;
+	union {
+		u32 isolation_config_a;
+		struct {
+			u32 paravisor_present : 1;
+			u32 reserved_a1 : 31;
+		};
+	};
+	union {
+		u32 isolation_config_b;
+		struct {
+			u32 cvm_type : 4;
+			u32 reserved_b1 : 1;
+			u32 shared_gpa_boundary_active : 1;
+			u32 shared_gpa_boundary_bits : 6;
+			u32 reserved_b2 : 20;
+		};
+	};
+	u64 shared_gpa_boundary;
+	bool msi_ext_dest_id;
+	bool confidential_vmbus_available;
+};
+extern struct ms_hyperv_info ms_hyperv;
+extern bool hv_nested;
+extern u64 hv_current_partition_id;
+extern enum hv_partition_type hv_curr_partition_type;
+
+extern void * __percpu *hyperv_pcpu_input_arg;
+extern void * __percpu *hyperv_pcpu_output_arg;
+
+u64 hv_do_hypercall(u64 control, void *inputaddr, void *outputaddr);
+u64 hv_do_fast_hypercall8(u16 control, u64 input8);
+u64 hv_do_fast_hypercall16(u16 control, u64 input1, u64 input2);
+
+bool hv_isolation_type_snp(void);
+bool hv_isolation_type_tdx(void);
+
+/*
+ * On architectures where Hyper-V doesn't support AEOI (e.g., ARM64),
+ * it doesn't provide a recommendation flag and AEOI must be disabled.
+ */
+static inline bool hv_recommend_using_aeoi(void)
+{
+#ifdef HV_DEPRECATING_AEOI_RECOMMENDED
+	return !(ms_hyperv.hints & HV_DEPRECATING_AEOI_RECOMMENDED);
+#else
+	return false;
+#endif
+}
+
+static inline struct hv_proximity_domain_info hv_numa_node_to_pxm_info(int node)
+{
+	struct hv_proximity_domain_info pxm_info = {};
+
+	if (node != NUMA_NO_NODE) {
+		pxm_info.domain_id = node_to_pxm(node);
+		pxm_info.flags.proximity_info_valid = 1;
+		pxm_info.flags.proximity_preferred = 1;
+	}
+
+	return pxm_info;
+}
+
+/* Helper functions that provide a consistent pattern for checking Hyper-V hypercall status. */
+static inline int hv_result(u64 status)
+{
+	return status & HV_HYPERCALL_RESULT_MASK;
+}
+
+static inline bool hv_result_success(u64 status)
+{
+	return hv_result(status) == HV_STATUS_SUCCESS;
+}
+
+static inline unsigned int hv_repcomp(u64 status)
+{
+	/* Bits [43:32] of status have 'Reps completed' data. */
+	return (status & HV_HYPERCALL_REP_COMP_MASK) >>
+			 HV_HYPERCALL_REP_COMP_OFFSET;
+}
+
+/*
+ * Rep hypercalls. Callers of this functions are supposed to ensure that
+ * rep_count, varhead_size, and rep_start comply with Hyper-V hypercall
+ * definition.
+ */
+static inline u64 hv_do_rep_hypercall_ex(u16 code, u16 rep_count,
+					 u16 varhead_size, u16 rep_start,
+					 void *input, void *output)
+{
+	u64 control = code;
+	u64 status;
+	u16 rep_comp;
+
+	control |= (u64)varhead_size << HV_HYPERCALL_VARHEAD_OFFSET;
+	control |= (u64)rep_count << HV_HYPERCALL_REP_COMP_OFFSET;
+	control |= (u64)rep_start << HV_HYPERCALL_REP_START_OFFSET;
+
+	do {
+		status = hv_do_hypercall(control, input, output);
+		if (!hv_result_success(status))
+			return status;
+
+		rep_comp = hv_repcomp(status);
+
+		control &= ~HV_HYPERCALL_REP_START_MASK;
+		control |= (u64)rep_comp << HV_HYPERCALL_REP_START_OFFSET;
+
+		touch_nmi_watchdog();
+	} while (rep_comp < rep_count);
+
+	return status;
+}
+
+/* For the typical case where rep_start is 0 */
+static inline u64 hv_do_rep_hypercall(u16 code, u16 rep_count, u16 varhead_size,
+				      void *input, void *output)
+{
+	return hv_do_rep_hypercall_ex(code, rep_count, varhead_size, 0,
+				      input, output);
+}
+
+/* Generate the guest OS identifier as described in the Hyper-V TLFS */
+static inline u64 hv_generate_guest_id(u64 kernel_version)
+{
+	u64 guest_id;
+
+	guest_id = (((u64)HV_LINUX_VENDOR_ID) << 48);
+	guest_id |= (kernel_version << 16);
+
+	return guest_id;
+}
+
+int hv_get_hypervisor_version(union hv_hypervisor_version_info *info);
+
+void hv_setup_vmbus_handler(void (*handler)(void));
+void hv_remove_vmbus_handler(void);
+void hv_setup_stimer0_handler(void (*handler)(void));
+void hv_remove_stimer0_handler(void);
+
+void hv_setup_kexec_handler(void (*handler)(void));
+void hv_remove_kexec_handler(void);
+void hv_setup_crash_handler(void (*handler)(struct pt_regs *regs));
+void hv_remove_crash_handler(void);
+void hv_setup_mshv_handler(void (*handler)(void));
+
+#if IS_ENABLED(CONFIG_HYPERV)
+/*
+ * Hypervisor's notion of virtual processor ID is different from
+ * Linux' notion of CPU ID. This information can only be retrieved
+ * in the context of the calling CPU. Setup a map for easy access
+ * to this information.
+ */
+extern u32 *hv_vp_index;
+extern u32 hv_max_vp_index;
+
+extern u64 (*hv_read_reference_counter)(void);
+
+/* Sentinel value for an uninitialized entry in hv_vp_index array */
+#define VP_INVAL	U32_MAX
+
+int __init hv_common_init(void);
+void __init hv_get_partition_id(void);
+void __init hv_common_free(void);
+void __init ms_hyperv_late_init(void);
+int hv_common_cpu_init(unsigned int cpu);
+int hv_common_cpu_die(unsigned int cpu);
+void hv_identify_partition_type(void);
+
+/**
+ * hv_cpu_number_to_vp_number() - Map CPU to VP.
+ * @cpu_number: CPU number in Linux terms
+ *
+ * This function returns the mapping between the Linux processor
+ * number and the hypervisor's virtual processor number, useful
+ * in making hypercalls and such that talk about specific
+ * processors.
+ *
+ * Return: Virtual processor number in Hyper-V terms
+ */
+static inline int hv_cpu_number_to_vp_number(int cpu_number)
+{
+	return hv_vp_index[cpu_number];
+}
+
+static inline int __cpumask_to_vpset(struct hv_vpset *vpset,
+				    const struct cpumask *cpus,
+				    bool (*func)(int cpu))
+{
+	int cpu, vcpu, vcpu_bank, vcpu_offset, nr_bank = 1;
+	int max_vcpu_bank = hv_max_vp_index / HV_VCPUS_PER_SPARSE_BANK;
+
+	/* vpset.valid_bank_mask can represent up to HV_MAX_SPARSE_VCPU_BANKS banks */
+	if (max_vcpu_bank >= HV_MAX_SPARSE_VCPU_BANKS)
+		return 0;
+
+	/*
+	 * Clear all banks up to the maximum possible bank as hv_tlb_flush_ex
+	 * structs are not cleared between calls, we risk flushing unneeded
+	 * vCPUs otherwise.
+	 */
+	for (vcpu_bank = 0; vcpu_bank <= max_vcpu_bank; vcpu_bank++)
+		vpset->bank_contents[vcpu_bank] = 0;
+
+	/*
+	 * Some banks may end up being empty but this is acceptable.
+	 */
+	for_each_cpu(cpu, cpus) {
+		if (func && func(cpu))
+			continue;
+		vcpu = hv_cpu_number_to_vp_number(cpu);
+		if (vcpu == VP_INVAL)
+			return -1;
+		vcpu_bank = vcpu / HV_VCPUS_PER_SPARSE_BANK;
+		vcpu_offset = vcpu % HV_VCPUS_PER_SPARSE_BANK;
+		__set_bit(vcpu_offset, (unsigned long *)
+			  &vpset->bank_contents[vcpu_bank]);
+		if (vcpu_bank >= nr_bank)
+			nr_bank = vcpu_bank + 1;
+	}
+	vpset->valid_bank_mask = GENMASK_ULL(nr_bank - 1, 0);
+	return nr_bank;
+}
+
+/*
+ * Convert a Linux cpumask into a Hyper-V VPset. In the _skip variant,
+ * 'func' is called for each CPU present in cpumask.  If 'func' returns
+ * true, that CPU is skipped -- i.e., that CPU from cpumask is *not*
+ * added to the Hyper-V VPset. If 'func' is NULL, no CPUs are
+ * skipped.
+ */
+static inline int cpumask_to_vpset(struct hv_vpset *vpset,
+				    const struct cpumask *cpus)
+{
+	return __cpumask_to_vpset(vpset, cpus, NULL);
+}
+
+static inline int cpumask_to_vpset_skip(struct hv_vpset *vpset,
+				    const struct cpumask *cpus,
+				    bool (*func)(int cpu))
+{
+	return __cpumask_to_vpset(vpset, cpus, func);
+}
+
+#define _hv_status_fmt(fmt) "%s: Hyper-V status: %#x = %s: " fmt
+#define hv_status_printk(level, status, fmt, ...) \
+do { \
+	u64 __status = (status); \
+	pr_##level(_hv_status_fmt(fmt), __func__, hv_result(__status), \
+		   hv_result_to_string(__status), ##__VA_ARGS__); \
+} while (0)
+#define hv_status_err(status, fmt, ...) \
+	hv_status_printk(err, status, fmt, ##__VA_ARGS__)
+#define hv_status_debug(status, fmt, ...) \
+	hv_status_printk(debug, status, fmt, ##__VA_ARGS__)
+
+const char *hv_result_to_string(u64 hv_status);
+int hv_result_to_errno(u64 status);
+void hyperv_report_panic(struct pt_regs *regs, long err, bool in_die);
+bool hv_is_hyperv_initialized(void);
+bool hv_is_hibernation_supported(void);
+enum hv_isolation_type hv_get_isolation_type(void);
+bool hv_is_isolation_supported(void);
+bool hv_isolation_type_snp(void);
+u64 hv_ghcb_hypercall(u64 control, void *input, void *output, u32 input_size);
+u64 hv_tdx_hypercall(u64 control, u64 param1, u64 param2);
+void hv_enable_coco_interrupt(unsigned int cpu, unsigned int vector, bool set);
+void hv_para_set_sint_proxy(bool enable);
+u64 hv_para_get_synic_register(unsigned int reg);
+void hv_para_set_synic_register(unsigned int reg, u64 val);
+void hyperv_cleanup(void);
+bool hv_query_ext_cap(u64 cap_query);
+void hv_setup_dma_ops(struct device *dev, bool coherent);
+#else /* CONFIG_HYPERV */
+static inline void hv_identify_partition_type(void) {}
+static inline bool hv_is_hyperv_initialized(void) { return false; }
+static inline bool hv_is_hibernation_supported(void) { return false; }
+static inline void hyperv_cleanup(void) {}
+static inline void ms_hyperv_late_init(void) {}
+static inline bool hv_is_isolation_supported(void) { return false; }
+static inline enum hv_isolation_type hv_get_isolation_type(void)
+{
+	return HV_ISOLATION_TYPE_NONE;
+}
+#endif /* CONFIG_HYPERV */
+
+#if IS_ENABLED(CONFIG_MSHV_ROOT)
+static inline bool hv_root_partition(void)
+{
+	return hv_curr_partition_type == HV_PARTITION_TYPE_ROOT;
+}
+static inline bool hv_l1vh_partition(void)
+{
+	return hv_curr_partition_type == HV_PARTITION_TYPE_L1VH;
+}
+static inline bool hv_parent_partition(void)
+{
+	return hv_root_partition() || hv_l1vh_partition();
+}
+
+bool hv_result_needs_memory(u64 status);
+int hv_deposit_memory_node(int node, u64 partition_id, u64 status);
+int hv_call_deposit_pages(int node, u64 partition_id, u32 num_pages);
+int hv_call_add_logical_proc(int node, u32 lp_index, u32 acpi_id);
+int hv_call_notify_all_processors_started(void);
+bool hv_lp_exists(u32 lp_index);
+int hv_call_create_vp(int node, u64 partition_id, u32 vp_index, u32 flags);
+
+#else /* CONFIG_MSHV_ROOT */
+static inline bool hv_root_partition(void) { return false; }
+static inline bool hv_l1vh_partition(void) { return false; }
+static inline bool hv_parent_partition(void) { return false; }
+static inline bool hv_result_needs_memory(u64 status) { return false; }
+static inline int hv_deposit_memory_node(int node, u64 partition_id, u64 status)
+{
+	return -EOPNOTSUPP;
+}
+static inline int hv_call_deposit_pages(int node, u64 partition_id, u32 num_pages)
+{
+	return -EOPNOTSUPP;
+}
+static inline int hv_call_add_logical_proc(int node, u32 lp_index, u32 acpi_id)
+{
+	return -EOPNOTSUPP;
+}
+static inline int hv_call_notify_all_processors_started(void)
+{
+	return -EOPNOTSUPP;
+}
+static inline bool hv_lp_exists(u32 lp_index)
+{
+	return false;
+}
+static inline int hv_call_create_vp(int node, u64 partition_id, u32 vp_index, u32 flags)
+{
+	return -EOPNOTSUPP;
+}
+#endif /* CONFIG_MSHV_ROOT */
+
+static inline int hv_deposit_memory(u64 partition_id, u64 status)
+{
+	return hv_deposit_memory_node(NUMA_NO_NODE, partition_id, status);
+}
+
+#if IS_ENABLED(CONFIG_HYPERV_VTL_MODE)
+u8 __init get_vtl(void);
+#else
+static inline u8 get_vtl(void) { return 0; }
+#endif
+
+#endif