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, 191 insertions, 0 deletions

diff --git a/include/net/checksum.h b/include/net/checksum.h
new file mode 100644
index 000000000..3cbab35de
--- /dev/null
+++ b/include/net/checksum.h
@@ -0,0 +1,191 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * INET		An implementation of the TCP/IP protocol suite for the LINUX
+ *		operating system.  INET is implemented using the  BSD Socket
+ *		interface as the means of communication with the user level.
+ *
+ *		Checksumming functions for IP, TCP, UDP and so on
+ *
+ * Authors:	Jorge Cwik, <jorge@laser.satlink.net>
+ *		Arnt Gulbrandsen, <agulbra@nvg.unit.no>
+ *		Borrows very liberally from tcp.c and ip.c, see those
+ *		files for more names.
+ */
+
+#ifndef _CHECKSUM_H
+#define _CHECKSUM_H
+
+#include <linux/errno.h>
+#include <asm/types.h>
+#include <asm/byteorder.h>
+#include <asm/checksum.h>
+#if !defined(_HAVE_ARCH_COPY_AND_CSUM_FROM_USER) || !defined(HAVE_CSUM_COPY_USER)
+#include <linux/uaccess.h>
+#endif
+
+#ifndef _HAVE_ARCH_COPY_AND_CSUM_FROM_USER
+static __always_inline
+__wsum csum_and_copy_from_user (const void __user *src, void *dst,
+				      int len)
+{
+	if (copy_from_user(dst, src, len))
+		return 0;
+	return csum_partial(dst, len, ~0U);
+}
+#endif
+
+#ifndef HAVE_CSUM_COPY_USER
+static __always_inline __wsum csum_and_copy_to_user
+(const void *src, void __user *dst, int len)
+{
+	__wsum sum = csum_partial(src, len, ~0U);
+
+	if (copy_to_user(dst, src, len) == 0)
+		return sum;
+	return 0;
+}
+#endif
+
+#ifndef _HAVE_ARCH_CSUM_AND_COPY
+static __always_inline __wsum
+csum_partial_copy_nocheck(const void *src, void *dst, int len)
+{
+	memcpy(dst, src, len);
+	return csum_partial(dst, len, 0);
+}
+#endif
+
+#ifndef HAVE_ARCH_CSUM_ADD
+static __always_inline __wsum csum_add(__wsum csum, __wsum addend)
+{
+	u32 res = (__force u32)csum;
+	res += (__force u32)addend;
+	return (__force __wsum)(res + (res < (__force u32)addend));
+}
+#endif
+
+static __always_inline __wsum csum_sub(__wsum csum, __wsum addend)
+{
+	return csum_add(csum, ~addend);
+}
+
+static __always_inline __sum16 csum16_add(__sum16 csum, __be16 addend)
+{
+	u16 res = (__force u16)csum;
+
+	res += (__force u16)addend;
+	return (__force __sum16)(res + (res < (__force u16)addend));
+}
+
+static __always_inline __sum16 csum16_sub(__sum16 csum, __be16 addend)
+{
+	return csum16_add(csum, ~addend);
+}
+
+#ifndef HAVE_ARCH_CSUM_SHIFT
+static __always_inline __wsum csum_shift(__wsum sum, int offset)
+{
+	/* rotate sum to align it with a 16b boundary */
+	if (offset & 1)
+		return (__force __wsum)ror32((__force u32)sum, 8);
+	return sum;
+}
+#endif
+
+static __always_inline __wsum
+csum_block_add(__wsum csum, __wsum csum2, int offset)
+{
+	return csum_add(csum, csum_shift(csum2, offset));
+}
+
+static __always_inline __wsum
+csum_block_sub(__wsum csum, __wsum csum2, int offset)
+{
+	return csum_block_add(csum, ~csum2, offset);
+}
+
+static __always_inline __wsum csum_unfold(__sum16 n)
+{
+	return (__force __wsum)n;
+}
+
+#define CSUM_MANGLED_0 ((__force __sum16)0xffff)
+
+static __always_inline void csum_replace_by_diff(__sum16 *sum, __wsum diff)
+{
+	*sum = csum_fold(csum_add(diff, ~csum_unfold(*sum)));
+}
+
+static __always_inline void csum_replace4(__sum16 *sum, __be32 from, __be32 to)
+{
+	__wsum tmp = csum_sub(~csum_unfold(*sum), (__force __wsum)from);
+
+	*sum = csum_fold(csum_add(tmp, (__force __wsum)to));
+}
+
+/* Implements RFC 1624 (Incremental Internet Checksum)
+ * 3. Discussion states :
+ *     HC' = ~(~HC + ~m + m')
+ *  m : old value of a 16bit field
+ *  m' : new value of a 16bit field
+ */
+static __always_inline void csum_replace2(__sum16 *sum, __be16 old, __be16 new)
+{
+	*sum = ~csum16_add(csum16_sub(~(*sum), old), new);
+}
+
+static inline void csum_replace(__wsum *csum, __wsum old, __wsum new)
+{
+	*csum = csum_add(csum_sub(*csum, old), new);
+}
+
+static inline unsigned short csum_from32to16(unsigned int sum)
+{
+	sum += (sum >> 16) | (sum << 16);
+	return (unsigned short)(sum >> 16);
+}
+
+struct sk_buff;
+void inet_proto_csum_replace4(__sum16 *sum, struct sk_buff *skb,
+			      __be32 from, __be32 to, bool pseudohdr);
+void inet_proto_csum_replace16(__sum16 *sum, struct sk_buff *skb,
+			       const __be32 *from, const __be32 *to,
+			       bool pseudohdr);
+void inet_proto_csum_replace_by_diff(__sum16 *sum, struct sk_buff *skb,
+				     __wsum diff, bool pseudohdr, bool ipv6);
+
+static __always_inline
+void inet_proto_csum_replace2(__sum16 *sum, struct sk_buff *skb,
+			      __be16 from, __be16 to, bool pseudohdr)
+{
+	inet_proto_csum_replace4(sum, skb, (__force __be32)from,
+				 (__force __be32)to, pseudohdr);
+}
+
+static __always_inline __wsum remcsum_adjust(void *ptr, __wsum csum,
+					     int start, int offset)
+{
+	__sum16 *psum = (__sum16 *)(ptr + offset);
+	__wsum delta;
+
+	/* Subtract out checksum up to start */
+	csum = csum_sub(csum, csum_partial(ptr, start, 0));
+
+	/* Set derived checksum in packet */
+	delta = csum_sub((__force __wsum)csum_fold(csum),
+			 (__force __wsum)*psum);
+	*psum = csum_fold(csum);
+
+	return delta;
+}
+
+static __always_inline void remcsum_unadjust(__sum16 *psum, __wsum delta)
+{
+	*psum = csum_fold(csum_sub(delta, (__force __wsum)*psum));
+}
+
+static __always_inline __wsum wsum_negate(__wsum val)
+{
+	return (__force __wsum)-((__force u32)val);
+}
+#endif