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, 342 insertions, 0 deletions

diff --git a/security/ipe/hooks.c b/security/ipe/hooks.c
new file mode 100644
index 000000000..0ae54a880
--- /dev/null
+++ b/security/ipe/hooks.c
@@ -0,0 +1,342 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2020-2024 Microsoft Corporation. All rights reserved.
+ */
+
+#include <linux/fs.h>
+#include <linux/fs_struct.h>
+#include <linux/types.h>
+#include <linux/binfmts.h>
+#include <linux/mman.h>
+#include <linux/blk_types.h>
+
+#include "ipe.h"
+#include "hooks.h"
+#include "eval.h"
+#include "digest.h"
+
+/**
+ * ipe_bprm_check_security() - ipe security hook function for bprm check.
+ * @bprm: Supplies a pointer to a linux_binprm structure to source the file
+ *	  being evaluated.
+ *
+ * This LSM hook is called when a binary is loaded through the exec
+ * family of system calls.
+ *
+ * Return:
+ * * %0		- Success
+ * * %-EACCES	- Did not pass IPE policy
+ */
+int ipe_bprm_check_security(struct linux_binprm *bprm)
+{
+	struct ipe_eval_ctx ctx = IPE_EVAL_CTX_INIT;
+
+	ipe_build_eval_ctx(&ctx, bprm->file, IPE_OP_EXEC, IPE_HOOK_BPRM_CHECK);
+	return ipe_evaluate_event(&ctx);
+}
+
+/**
+ * ipe_bprm_creds_for_exec() - ipe security hook function for bprm creds check.
+ * @bprm: Supplies a pointer to a linux_binprm structure to source the file
+ *	  being evaluated.
+ *
+ * This LSM hook is called when userspace signals the kernel to check a file
+ * for execution through the execveat syscall with the AT_EXECVE_CHECK flag.
+ * The hook triggers IPE policy evaluation on the script file and returns
+ * the policy decision to userspace. The userspace program receives the
+ * return code and can decide whether to proceed with script execution.
+ *
+ * Return:
+ * * %0		- Success
+ * * %-EACCES	- Did not pass IPE policy
+ */
+int ipe_bprm_creds_for_exec(struct linux_binprm *bprm)
+{
+	struct ipe_eval_ctx ctx = IPE_EVAL_CTX_INIT;
+
+	if (!bprm->is_check)
+		return 0;
+
+	ipe_build_eval_ctx(&ctx, bprm->file, IPE_OP_EXEC,
+			   IPE_HOOK_BPRM_CREDS_FOR_EXEC);
+	return ipe_evaluate_event(&ctx);
+}
+
+/**
+ * ipe_mmap_file() - ipe security hook function for mmap check.
+ * @f: File being mmap'd. Can be NULL in the case of anonymous memory.
+ * @reqprot: The requested protection on the mmap, passed from usermode.
+ * @prot: The effective protection on the mmap, resolved from reqprot and
+ *	  system configuration.
+ * @flags: Unused.
+ *
+ * This hook is called when a file is loaded through the mmap
+ * family of system calls.
+ *
+ * Return:
+ * * %0		- Success
+ * * %-EACCES	- Did not pass IPE policy
+ */
+int ipe_mmap_file(struct file *f, unsigned long reqprot __always_unused,
+		  unsigned long prot, unsigned long flags)
+{
+	struct ipe_eval_ctx ctx = IPE_EVAL_CTX_INIT;
+
+	if (prot & PROT_EXEC) {
+		ipe_build_eval_ctx(&ctx, f, IPE_OP_EXEC, IPE_HOOK_MMAP);
+		return ipe_evaluate_event(&ctx);
+	}
+
+	return 0;
+}
+
+/**
+ * ipe_file_mprotect() - ipe security hook function for mprotect check.
+ * @vma: Existing virtual memory area created by mmap or similar.
+ * @reqprot: The requested protection on the mmap, passed from usermode.
+ * @prot: The effective protection on the mmap, resolved from reqprot and
+ *	  system configuration.
+ *
+ * This LSM hook is called when a mmap'd region of memory is changing
+ * its protections via mprotect.
+ *
+ * Return:
+ * * %0		- Success
+ * * %-EACCES	- Did not pass IPE policy
+ */
+int ipe_file_mprotect(struct vm_area_struct *vma,
+		      unsigned long reqprot __always_unused,
+		      unsigned long prot)
+{
+	struct ipe_eval_ctx ctx = IPE_EVAL_CTX_INIT;
+
+	/* Already Executable */
+	if (vma->vm_flags & VM_EXEC)
+		return 0;
+
+	if (prot & PROT_EXEC) {
+		ipe_build_eval_ctx(&ctx, vma->vm_file, IPE_OP_EXEC, IPE_HOOK_MPROTECT);
+		return ipe_evaluate_event(&ctx);
+	}
+
+	return 0;
+}
+
+/**
+ * ipe_kernel_read_file() - ipe security hook function for kernel read.
+ * @file: Supplies a pointer to the file structure being read in from disk.
+ * @id: Supplies the enumeration identifying the purpose of the read.
+ * @contents: Unused.
+ *
+ * This LSM hook is called when a file is read from disk in the kernel.
+ *
+ * Return:
+ * * %0		- Success
+ * * %-EACCES	- Did not pass IPE policy
+ */
+int ipe_kernel_read_file(struct file *file, enum kernel_read_file_id id,
+			 bool contents)
+{
+	struct ipe_eval_ctx ctx = IPE_EVAL_CTX_INIT;
+	enum ipe_op_type op;
+
+	switch (id) {
+	case READING_FIRMWARE:
+		op = IPE_OP_FIRMWARE;
+		break;
+	case READING_MODULE:
+	case READING_MODULE_COMPRESSED:
+		op = IPE_OP_KERNEL_MODULE;
+		break;
+	case READING_KEXEC_INITRAMFS:
+		op = IPE_OP_KEXEC_INITRAMFS;
+		break;
+	case READING_KEXEC_IMAGE:
+		op = IPE_OP_KEXEC_IMAGE;
+		break;
+	case READING_POLICY:
+		op = IPE_OP_POLICY;
+		break;
+	case READING_X509_CERTIFICATE:
+		op = IPE_OP_X509;
+		break;
+	default:
+		op = IPE_OP_INVALID;
+		WARN(1, "no rule setup for kernel_read_file enum %d", id);
+	}
+
+	ipe_build_eval_ctx(&ctx, file, op, IPE_HOOK_KERNEL_READ);
+	return ipe_evaluate_event(&ctx);
+}
+
+/**
+ * ipe_kernel_load_data() - ipe security hook function for kernel load data.
+ * @id: Supplies the enumeration identifying the purpose of the load.
+ * @contents: Unused.
+ *
+ * This LSM hook is called when a data buffer provided by userspace is loading
+ * into the kernel.
+ *
+ * Return:
+ * * %0		- Success
+ * * %-EACCES	- Did not pass IPE policy
+ */
+int ipe_kernel_load_data(enum kernel_load_data_id id, bool contents)
+{
+	struct ipe_eval_ctx ctx = IPE_EVAL_CTX_INIT;
+	enum ipe_op_type op;
+
+	switch (id) {
+	case LOADING_FIRMWARE:
+		op = IPE_OP_FIRMWARE;
+		break;
+	case LOADING_MODULE:
+		op = IPE_OP_KERNEL_MODULE;
+		break;
+	case LOADING_KEXEC_INITRAMFS:
+		op = IPE_OP_KEXEC_INITRAMFS;
+		break;
+	case LOADING_KEXEC_IMAGE:
+		op = IPE_OP_KEXEC_IMAGE;
+		break;
+	case LOADING_POLICY:
+		op = IPE_OP_POLICY;
+		break;
+	case LOADING_X509_CERTIFICATE:
+		op = IPE_OP_X509;
+		break;
+	default:
+		op = IPE_OP_INVALID;
+		WARN(1, "no rule setup for kernel_load_data enum %d", id);
+	}
+
+	ipe_build_eval_ctx(&ctx, NULL, op, IPE_HOOK_KERNEL_LOAD);
+	return ipe_evaluate_event(&ctx);
+}
+
+/**
+ * ipe_unpack_initramfs() - Mark the current rootfs as initramfs.
+ */
+void ipe_unpack_initramfs(void)
+{
+	ipe_sb(current->fs->root.mnt->mnt_sb)->initramfs = true;
+}
+
+#ifdef CONFIG_IPE_PROP_DM_VERITY
+/**
+ * ipe_bdev_free_security() - Free IPE's LSM blob of block_devices.
+ * @bdev: Supplies a pointer to a block_device that contains the structure
+ *	  to free.
+ */
+void ipe_bdev_free_security(struct block_device *bdev)
+{
+	struct ipe_bdev *blob = ipe_bdev(bdev);
+
+	ipe_digest_free(blob->root_hash);
+}
+
+#ifdef CONFIG_IPE_PROP_DM_VERITY_SIGNATURE
+static void ipe_set_dmverity_signature(struct ipe_bdev *blob,
+				       const void *value,
+				       size_t size)
+{
+	blob->dm_verity_signed = size > 0 && value;
+}
+#else
+static inline void ipe_set_dmverity_signature(struct ipe_bdev *blob,
+					      const void *value,
+					      size_t size)
+{
+}
+#endif /* CONFIG_IPE_PROP_DM_VERITY_SIGNATURE */
+
+/**
+ * ipe_bdev_setintegrity() - Save integrity data from a bdev to IPE's LSM blob.
+ * @bdev: Supplies a pointer to a block_device that contains the LSM blob.
+ * @type: Supplies the integrity type.
+ * @value: Supplies the value to store.
+ * @size: The size of @value.
+ *
+ * This hook is currently used to save dm-verity's root hash or the existence
+ * of a validated signed dm-verity root hash into LSM blob.
+ *
+ * Return: %0 on success. If an error occurs, the function will return the
+ * -errno.
+ */
+int ipe_bdev_setintegrity(struct block_device *bdev, enum lsm_integrity_type type,
+			  const void *value, size_t size)
+{
+	const struct dm_verity_digest *digest = NULL;
+	struct ipe_bdev *blob = ipe_bdev(bdev);
+	struct digest_info *info = NULL;
+
+	if (type == LSM_INT_DMVERITY_SIG_VALID) {
+		ipe_set_dmverity_signature(blob, value, size);
+
+		return 0;
+	}
+
+	if (type != LSM_INT_DMVERITY_ROOTHASH)
+		return -EINVAL;
+
+	if (!value) {
+		ipe_digest_free(blob->root_hash);
+		blob->root_hash = NULL;
+
+		return 0;
+	}
+	digest = value;
+
+	info = kzalloc_obj(*info);
+	if (!info)
+		return -ENOMEM;
+
+	info->digest = kmemdup(digest->digest, digest->digest_len, GFP_KERNEL);
+	if (!info->digest)
+		goto err;
+
+	info->alg = kstrdup(digest->alg, GFP_KERNEL);
+	if (!info->alg)
+		goto err;
+
+	info->digest_len = digest->digest_len;
+
+	ipe_digest_free(blob->root_hash);
+	blob->root_hash = info;
+
+	return 0;
+err:
+	ipe_digest_free(info);
+
+	return -ENOMEM;
+}
+#endif /* CONFIG_IPE_PROP_DM_VERITY */
+
+#ifdef CONFIG_IPE_PROP_FS_VERITY_BUILTIN_SIG
+/**
+ * ipe_inode_setintegrity() - save integrity data from a inode to IPE's LSM blob.
+ * @inode: The inode to source the security blob from.
+ * @type: Supplies the integrity type.
+ * @value: The value to be stored.
+ * @size: The size of @value.
+ *
+ * This hook is currently used to save the existence of a validated fs-verity
+ * builtin signature into LSM blob.
+ *
+ * Return: %0 on success. If an error occurs, the function will return the
+ * -errno.
+ */
+int ipe_inode_setintegrity(const struct inode *inode,
+			   enum lsm_integrity_type type,
+			   const void *value, size_t size)
+{
+	struct ipe_inode *inode_sec = ipe_inode(inode);
+
+	if (type == LSM_INT_FSVERITY_BUILTINSIG_VALID) {
+		inode_sec->fs_verity_signed = size > 0 && value;
+		return 0;
+	}
+
+	return -EINVAL;
+}
+#endif /* CONFIG_IPE_PROP_FS_VERITY_BUILTIN_SIG */