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, 274 insertions, 0 deletions

diff --git a/include/crypto/if_alg.h b/include/crypto/if_alg.h
new file mode 100644
index 000000000..0d51428c1
--- /dev/null
+++ b/include/crypto/if_alg.h
@@ -0,0 +1,274 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * if_alg: User-space algorithm interface
+ *
+ * Copyright (c) 2010 Herbert Xu <herbert@gondor.apana.org.au>
+ */
+
+#ifndef _CRYPTO_IF_ALG_H
+#define _CRYPTO_IF_ALG_H
+
+#include <linux/bits.h>
+#include <linux/compiler.h>
+#include <linux/completion.h>
+#include <linux/if_alg.h>
+#include <linux/scatterlist.h>
+#include <linux/types.h>
+#include <linux/atomic.h>
+#include <net/sock.h>
+
+#include <crypto/aead.h>
+#include <crypto/skcipher.h>
+
+#define ALG_MAX_PAGES			16
+
+struct alg_sock {
+	/* struct sock must be the first member of struct alg_sock */
+	struct sock sk;
+
+	struct sock *parent;
+
+	atomic_t refcnt;
+	atomic_t nokey_refcnt;
+
+	const struct af_alg_type *type;
+	void *private;
+};
+
+struct af_alg_control {
+	struct af_alg_iv *iv;
+	int op;
+	unsigned int aead_assoclen;
+};
+
+struct af_alg_type {
+	void *(*bind)(const char *name);
+	void (*release)(void *private);
+	int (*setkey)(void *private, const u8 *key, unsigned int keylen);
+	int (*setentropy)(void *private, sockptr_t entropy, unsigned int len);
+	int (*accept)(void *private, struct sock *sk);
+	int (*accept_nokey)(void *private, struct sock *sk);
+	int (*setauthsize)(void *private, unsigned int authsize);
+
+	struct proto_ops *ops;
+	struct proto_ops *ops_nokey;
+	struct module *owner;
+	char name[14];
+};
+
+struct af_alg_sgl {
+	struct sg_table sgt;
+	struct scatterlist sgl[ALG_MAX_PAGES + 1];
+	bool need_unpin;
+};
+
+/* TX SGL entry */
+struct af_alg_tsgl {
+	struct list_head list;
+	unsigned int cur;		/* Last processed SG entry */
+	struct scatterlist sg[];	/* Array of SGs forming the SGL */
+};
+
+#define MAX_SGL_ENTS ((4096 - sizeof(struct af_alg_tsgl)) / \
+		      sizeof(struct scatterlist) - 1)
+
+/* RX SGL entry */
+struct af_alg_rsgl {
+	struct af_alg_sgl sgl;
+	struct list_head list;
+	size_t sg_num_bytes;		/* Bytes of data in that SGL */
+};
+
+/**
+ * struct af_alg_async_req - definition of crypto request
+ * @sk:			Socket the request is associated with
+ * @first_rsgl:		First RX SG
+ * @last_rsgl:		Pointer to last RX SG
+ * @rsgl_list:		Track RX SGs
+ * @tsgl:		Private, per request TX SGL of buffers to process
+ * @tsgl_entries:	Number of entries in priv. TX SGL
+ * @outlen:		Number of output bytes generated by crypto op
+ * @areqlen:		Length of this data structure
+ * @cra_u:		Cipher request
+ */
+struct af_alg_async_req {
+	struct sock *sk;
+
+	struct af_alg_rsgl first_rsgl;
+	struct af_alg_rsgl *last_rsgl;
+	struct list_head rsgl_list;
+
+	struct scatterlist *tsgl;
+	unsigned int tsgl_entries;
+
+	unsigned int outlen;
+	unsigned int areqlen;
+
+	union {
+		struct aead_request aead_req;
+		struct skcipher_request skcipher_req;
+	} cra_u;
+
+	/* req ctx trails this struct */
+};
+
+/**
+ * struct af_alg_ctx - definition of the crypto context
+ *
+ * The crypto context tracks the input data during the lifetime of an AF_ALG
+ * socket.
+ *
+ * @tsgl_list:		Link to TX SGL
+ * @iv:			IV for cipher operation
+ * @state:		Existing state for continuing operation
+ * @aead_assoclen:	Length of AAD for AEAD cipher operations
+ * @wait:		For waiting for completion of async crypto ops
+ * @used:		TX bytes sent to kernel. This variable is used to
+ *			ensure that user space cannot cause the kernel
+ *			to allocate too much memory in sendmsg operation.
+ * @rcvused:		Total RX bytes to be filled by kernel. This variable
+ *			is used to ensure user space cannot cause the kernel
+ *			to allocate too much memory in a recvmsg operation.
+ * @more:		More data to be expected from user space?
+ * @merge:		Shall new data from user space be merged into existing
+ *			SG?
+ * @enc:		Cryptographic operation to be performed when
+ *			recvmsg is invoked.
+ * @write:		True if we are in the middle of a write.
+ * @init:		True if metadata has been sent.
+ * @len:		Length of memory allocated for this data structure.
+ * @inflight:		Non-zero when requests are in flight, for debugging only.
+ */
+struct af_alg_ctx {
+	struct list_head tsgl_list;
+
+	void *iv;
+	void *state;
+	size_t aead_assoclen;
+
+	struct crypto_wait wait;
+
+	size_t used;
+	atomic_t rcvused;
+
+	bool		more:1,
+			merge:1,
+			enc:1,
+			write:1,
+			init:1;
+
+	unsigned int len;
+
+	unsigned int inflight;
+};
+
+/* Flags for af_alg_allowlist_entry::flags: */
+#define AF_ALG_UNPRIVILEGED BIT(0) /* Unprivileged use is allowed */
+
+struct af_alg_allowlist_entry {
+	const char *name;
+	u32 flags;
+};
+
+int af_alg_register_type(const struct af_alg_type *type);
+int af_alg_unregister_type(const struct af_alg_type *type);
+
+int af_alg_check_restriction(const char *name,
+			     const struct af_alg_allowlist_entry allowlist[]);
+
+int af_alg_release(struct socket *sock);
+void af_alg_release_parent(struct sock *sk);
+int af_alg_accept(struct sock *sk, struct socket *newsock,
+		  struct proto_accept_arg *arg);
+
+void af_alg_free_sg(struct af_alg_sgl *sgl);
+
+static inline struct alg_sock *alg_sk(struct sock *sk)
+{
+	return (struct alg_sock *)sk;
+}
+
+/**
+ * af_alg_sndbuf - Size of available buffer for sending data from user space to kernel.
+ *
+ * @sk: socket of connection to user space
+ *
+ * Returns: number of bytes still available
+ */
+static inline int af_alg_sndbuf(struct sock *sk)
+{
+	struct alg_sock *ask = alg_sk(sk);
+	struct af_alg_ctx *ctx = ask->private;
+
+	return max_t(int, max_t(int, sk->sk_sndbuf & PAGE_MASK, PAGE_SIZE) -
+			  ctx->used, 0);
+}
+
+/**
+ * af_alg_writable - Can the send buffer still be written to?
+ *
+ * @sk: socket of connection to user space
+ *
+ * Returns: true => writable, false => not writable
+ */
+static inline bool af_alg_writable(struct sock *sk)
+{
+	return PAGE_SIZE <= af_alg_sndbuf(sk);
+}
+
+/**
+ * af_alg_rcvbuf - Size of available buffer used by kernel for the RX user space operation.
+ *
+ * @sk: socket of connection to user space
+ *
+ * Returns: number of bytes still available
+ */
+static inline int af_alg_rcvbuf(struct sock *sk)
+{
+	struct alg_sock *ask = alg_sk(sk);
+	struct af_alg_ctx *ctx = ask->private;
+
+	return max_t(int, max_t(int, sk->sk_rcvbuf & PAGE_MASK, PAGE_SIZE) -
+		     atomic_read(&ctx->rcvused), 0);
+}
+
+/**
+ * af_alg_readable - Can the RX buffer still be read from?
+ *
+ * @sk: socket of connection to user space
+ *
+ * Returns: true => readable, false => not readable
+ */
+static inline bool af_alg_readable(struct sock *sk)
+{
+	return PAGE_SIZE <= af_alg_rcvbuf(sk);
+}
+
+unsigned int af_alg_count_tsgl(struct sock *sk, size_t bytes);
+void af_alg_pull_tsgl(struct sock *sk, size_t used, struct scatterlist *dst);
+void af_alg_wmem_wakeup(struct sock *sk);
+int af_alg_wait_for_data(struct sock *sk, unsigned flags, unsigned min);
+int af_alg_sendmsg(struct socket *sock, struct msghdr *msg, size_t size,
+		   unsigned int ivsize);
+void af_alg_free_resources(struct af_alg_async_req *areq);
+__poll_t af_alg_poll(struct file *file, struct socket *sock,
+			 poll_table *wait);
+struct af_alg_async_req *af_alg_alloc_areq(struct sock *sk,
+					   unsigned int areqlen);
+int af_alg_get_rsgl(struct sock *sk, struct msghdr *msg, int flags,
+		    struct af_alg_async_req *areq, size_t maxsize,
+		    size_t *outlen);
+
+/*
+ * Mask used to disable unsupported algorithm implementations.
+ *
+ * This is the same as FSCRYPT_CRYPTOAPI_MASK in fs/crypto/fscrypt_private.h.
+ * In additions to the motivations there, this API is exposed to userspace
+ * that might not be fully trusted.
+ */
+#define AF_ALG_CRYPTOAPI_MASK                             \
+	(CRYPTO_ALG_ASYNC | CRYPTO_ALG_ALLOCATES_MEMORY | \
+	 CRYPTO_ALG_KERN_DRIVER_ONLY)
+
+
+#endif	/* _CRYPTO_IF_ALG_H */