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, 202 insertions, 0 deletions

diff --git a/include/vdso/datapage.h b/include/vdso/datapage.h
new file mode 100644
index 000000000..09897f76a
--- /dev/null
+++ b/include/vdso/datapage.h
@@ -0,0 +1,202 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __VDSO_DATAPAGE_H
+#define __VDSO_DATAPAGE_H
+
+#ifndef __ASSEMBLER__
+
+#include <linux/types.h>
+
+#include <uapi/linux/bits.h>
+#include <uapi/linux/time.h>
+
+#include <vdso/align.h>
+#include <vdso/bits.h>
+#include <vdso/cache.h>
+#include <vdso/page.h>
+#include <vdso/time.h>
+
+#ifdef CONFIG_ARCH_HAS_VDSO_TIME_DATA
+#include <asm/vdso/time_data.h>
+#else
+struct arch_vdso_time_data {};
+#endif
+
+#if defined(CONFIG_ARCH_HAS_VDSO_ARCH_DATA)
+#include <asm/vdso/arch_data.h>
+#else
+struct vdso_arch_data {
+	/* Needed for the generic code, never actually used at runtime */
+	char __unused;
+};
+#endif
+
+#define VDSO_BASES	(CLOCK_TAI + 1)
+#define VDSO_BASE_AUX	0
+#define VDSO_HRES	(BIT(CLOCK_REALTIME)		| \
+			 BIT(CLOCK_MONOTONIC)		| \
+			 BIT(CLOCK_BOOTTIME)		| \
+			 BIT(CLOCK_TAI))
+#define VDSO_COARSE	(BIT(CLOCK_REALTIME_COARSE)	| \
+			 BIT(CLOCK_MONOTONIC_COARSE))
+#define VDSO_RAW	(BIT(CLOCK_MONOTONIC_RAW))
+#define VDSO_AUX	__GENMASK(CLOCK_AUX_LAST, CLOCK_AUX)
+
+#define CS_HRES_COARSE	0
+#define CS_RAW		1
+#define CS_BASES	(CS_RAW + 1)
+
+/**
+ * struct vdso_timestamp - basetime per clock_id
+ * @sec:	seconds
+ * @nsec:	nanoseconds
+ *
+ * There is one vdso_timestamp object in vvar for each vDSO-accelerated
+ * clock_id. For high-resolution clocks, this encodes the time
+ * corresponding to vdso_time_data.cycle_last. For coarse clocks this encodes
+ * the actual time.
+ *
+ * To be noticed that for highres clocks nsec is left-shifted by
+ * vdso_time_data[x].shift.
+ */
+struct vdso_timestamp {
+	u64	sec;
+	u64	nsec;
+};
+
+/**
+ * struct vdso_clock - vdso per clocksource datapage representation
+ * @seq:		timebase sequence counter
+ * @clock_mode:		clock mode
+ * @cycle_last:		timebase at clocksource init
+ * @max_cycles:		maximum cycles which won't overflow 64bit multiplication
+ * @mask:		clocksource mask
+ * @mult:		clocksource multiplier
+ * @shift:		clocksource shift
+ * @basetime:		basetime per clock_id
+ * @offset:		time namespace offset per clock_id
+ *
+ * See also struct vdso_time_data for basic access and ordering information as
+ * struct vdso_clock is used there.
+ *
+ * @basetime is used to store the base time for the system wide time getter
+ * VVAR page.
+ *
+ * @offset is used by the special time namespace VVAR pages which are
+ * installed instead of the real VVAR page. These namespace pages must set
+ * @seq to 1 and @clock_mode to VDSO_CLOCKMODE_TIMENS to force the code into
+ * the time namespace slow path. The namespace aware functions retrieve the
+ * real system wide VVAR page, read host time and add the per clock offset.
+ * For clocks which are not affected by time namespace adjustment the
+ * offset must be zero.
+ */
+struct vdso_clock {
+	u32			seq;
+
+	s32			clock_mode;
+	u64			cycle_last;
+#ifdef CONFIG_GENERIC_VDSO_OVERFLOW_PROTECT
+	u64			max_cycles;
+#endif
+	u64			mask;
+	u32			mult;
+	u32			shift;
+
+	union {
+		struct vdso_timestamp	basetime[VDSO_BASES];
+		struct timens_offset	offset[VDSO_BASES];
+	};
+};
+
+/**
+ * struct vdso_time_data - vdso datapage representation
+ * @arch_data:		architecture specific data (optional, defaults
+ *			to an empty struct)
+ * @clock_data:		clocksource related data (array)
+ * @aux_clock_data:	auxiliary clocksource related data (array)
+ * @tz_minuteswest:	minutes west of Greenwich
+ * @tz_dsttime:		type of DST correction
+ * @hrtimer_res:	hrtimer resolution
+ * @__unused:		unused
+ *
+ * vdso_time_data will be accessed by 64 bit and compat code at the same time
+ * so we should be careful before modifying this structure.
+ *
+ * The ordering of the struct members is optimized to have fast acces to the
+ * often required struct members which are related to CLOCK_REALTIME and
+ * CLOCK_MONOTONIC. This information is stored in the first cache lines.
+ */
+struct vdso_time_data {
+	struct arch_vdso_time_data	arch_data;
+
+	struct vdso_clock		clock_data[CS_BASES];
+	struct vdso_clock		aux_clock_data[MAX_AUX_CLOCKS];
+
+	s32				tz_minuteswest;
+	s32				tz_dsttime;
+	u32				hrtimer_res;
+	u32				__unused;
+} ____cacheline_aligned;
+
+/**
+ * struct vdso_rng_data - vdso RNG state information
+ * @generation:	counter representing the number of RNG reseeds
+ * @is_ready:	boolean signaling whether the RNG is initialized
+ */
+struct vdso_rng_data {
+	u64	generation;
+	u8	is_ready;
+};
+
+/*
+ * We use the hidden visibility to prevent the compiler from generating a GOT
+ * relocation. Not only is going through a GOT useless (the entry couldn't and
+ * must not be overridden by another library), it does not even work: the linker
+ * cannot generate an absolute address to the data page.
+ *
+ * With the hidden visibility, the compiler simply generates a PC-relative
+ * relocation, and this is what we need.
+ */
+extern struct vdso_time_data vdso_u_time_data __attribute__((visibility("hidden")));
+extern struct vdso_rng_data vdso_u_rng_data __attribute__((visibility("hidden")));
+extern struct vdso_arch_data vdso_u_arch_data __attribute__((visibility("hidden")));
+
+extern struct vdso_time_data *vdso_k_time_data;
+extern struct vdso_rng_data *vdso_k_rng_data;
+extern struct vdso_arch_data *vdso_k_arch_data;
+
+#define VDSO_ARCH_DATA_SIZE ALIGN(sizeof(struct vdso_arch_data), PAGE_SIZE)
+#define VDSO_ARCH_DATA_PAGES (VDSO_ARCH_DATA_SIZE >> PAGE_SHIFT)
+
+enum vdso_pages {
+	VDSO_TIME_PAGE_OFFSET,
+	VDSO_TIMENS_PAGE_OFFSET,
+	VDSO_RNG_PAGE_OFFSET,
+	VDSO_ARCH_PAGES_START,
+	VDSO_ARCH_PAGES_END = VDSO_ARCH_PAGES_START + VDSO_ARCH_DATA_PAGES - 1,
+	VDSO_NR_PAGES
+};
+
+#else /* !__ASSEMBLER__ */
+
+#ifdef CONFIG_VDSO_GETRANDOM
+#define __vdso_u_rng_data	PROVIDE(vdso_u_rng_data = vdso_u_data + 2 * PAGE_SIZE);
+#else
+#define __vdso_u_rng_data
+#endif
+
+#ifdef CONFIG_ARCH_HAS_VDSO_ARCH_DATA
+#define __vdso_u_arch_data	PROVIDE(vdso_u_arch_data = vdso_u_data + 3 * PAGE_SIZE);
+#else
+#define __vdso_u_arch_data
+#endif
+
+#define VDSO_VVAR_SYMS						\
+	PROVIDE(vdso_u_data = . - __VDSO_PAGES * PAGE_SIZE);	\
+	PROVIDE(vdso_u_time_data = vdso_u_data);		\
+	__vdso_u_rng_data					\
+	__vdso_u_arch_data					\
+
+
+#endif /* !__ASSEMBLER__ */
+
+#endif /* __VDSO_DATAPAGE_H */