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, 393 insertions, 0 deletions

diff --git a/security/ipe/eval.c b/security/ipe/eval.c
new file mode 100644
index 000000000..21439c5be
--- /dev/null
+++ b/security/ipe/eval.c
@@ -0,0 +1,393 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2020-2024 Microsoft Corporation. All rights reserved.
+ */
+
+#include <linux/fs.h>
+#include <linux/types.h>
+#include <linux/slab.h>
+#include <linux/file.h>
+#include <linux/sched.h>
+#include <linux/rcupdate.h>
+#include <linux/moduleparam.h>
+#include <linux/fsverity.h>
+
+#include "ipe.h"
+#include "eval.h"
+#include "policy.h"
+#include "audit.h"
+#include "digest.h"
+
+struct ipe_policy __rcu *ipe_active_policy;
+bool success_audit;
+bool enforce = true;
+#define INO_BLOCK_DEV(ino) ((ino)->i_sb->s_bdev)
+
+#define FILE_SUPERBLOCK(f) ((f)->f_path.mnt->mnt_sb)
+
+/**
+ * build_ipe_sb_ctx() - Build initramfs field of an ipe evaluation context.
+ * @ctx: Supplies a pointer to the context to be populated.
+ * @file: Supplies the file struct of the file triggered IPE event.
+ */
+static void build_ipe_sb_ctx(struct ipe_eval_ctx *ctx, const struct file *const file)
+{
+	ctx->initramfs = ipe_sb(FILE_SUPERBLOCK(file))->initramfs;
+}
+
+#ifdef CONFIG_IPE_PROP_DM_VERITY
+/**
+ * build_ipe_bdev_ctx() - Build ipe_bdev field of an evaluation context.
+ * @ctx: Supplies a pointer to the context to be populated.
+ * @ino: Supplies the inode struct of the file triggered IPE event.
+ */
+static void build_ipe_bdev_ctx(struct ipe_eval_ctx *ctx, const struct inode *const ino)
+{
+	if (INO_BLOCK_DEV(ino))
+		ctx->ipe_bdev = ipe_bdev(INO_BLOCK_DEV(ino));
+}
+#else
+static void build_ipe_bdev_ctx(struct ipe_eval_ctx *ctx, const struct inode *const ino)
+{
+}
+#endif /* CONFIG_IPE_PROP_DM_VERITY */
+
+#ifdef CONFIG_IPE_PROP_FS_VERITY
+#ifdef CONFIG_IPE_PROP_FS_VERITY_BUILTIN_SIG
+static void build_ipe_inode_blob_ctx(struct ipe_eval_ctx *ctx,
+				     const struct inode *const ino)
+{
+	ctx->ipe_inode = ipe_inode(ctx->ino);
+}
+#else
+static inline void build_ipe_inode_blob_ctx(struct ipe_eval_ctx *ctx,
+					    const struct inode *const ino)
+{
+}
+#endif /* CONFIG_IPE_PROP_FS_VERITY_BUILTIN_SIG */
+
+/**
+ * build_ipe_inode_ctx() - Build inode fields of an evaluation context.
+ * @ctx: Supplies a pointer to the context to be populated.
+ * @ino: Supplies the inode struct of the file triggered IPE event.
+ */
+static void build_ipe_inode_ctx(struct ipe_eval_ctx *ctx, const struct inode *const ino)
+{
+	ctx->ino = ino;
+	build_ipe_inode_blob_ctx(ctx, ino);
+}
+#else
+static void build_ipe_inode_ctx(struct ipe_eval_ctx *ctx, const struct inode *const ino)
+{
+}
+#endif /* CONFIG_IPE_PROP_FS_VERITY */
+
+/**
+ * ipe_build_eval_ctx() - Build an ipe evaluation context.
+ * @ctx: Supplies a pointer to the context to be populated.
+ * @file: Supplies a pointer to the file to associated with the evaluation.
+ * @op: Supplies the IPE policy operation associated with the evaluation.
+ * @hook: Supplies the LSM hook associated with the evaluation.
+ */
+void ipe_build_eval_ctx(struct ipe_eval_ctx *ctx,
+			const struct file *file,
+			enum ipe_op_type op,
+			enum ipe_hook_type hook)
+{
+	struct inode *ino;
+
+	ctx->file = file;
+	ctx->op = op;
+	ctx->hook = hook;
+
+	if (file) {
+		build_ipe_sb_ctx(ctx, file);
+		ino = d_real_inode(file->f_path.dentry);
+		build_ipe_bdev_ctx(ctx, ino);
+		build_ipe_inode_ctx(ctx, ino);
+	}
+}
+
+/**
+ * evaluate_boot_verified() - Evaluate @ctx for the boot verified property.
+ * @ctx: Supplies a pointer to the context being evaluated.
+ *
+ * Return:
+ * * %true	- The current @ctx match the @p
+ * * %false	- The current @ctx doesn't match the @p
+ */
+static bool evaluate_boot_verified(const struct ipe_eval_ctx *const ctx)
+{
+	return ctx->initramfs;
+}
+
+#ifdef CONFIG_IPE_PROP_DM_VERITY
+/**
+ * evaluate_dmv_roothash() - Evaluate @ctx against a dmv roothash property.
+ * @ctx: Supplies a pointer to the context being evaluated.
+ * @p: Supplies a pointer to the property being evaluated.
+ *
+ * Return:
+ * * %true	- The current @ctx match the @p
+ * * %false	- The current @ctx doesn't match the @p
+ */
+static bool evaluate_dmv_roothash(const struct ipe_eval_ctx *const ctx,
+				  struct ipe_prop *p)
+{
+	return !!ctx->ipe_bdev &&
+	       !!ctx->ipe_bdev->root_hash &&
+	       ipe_digest_eval(p->value,
+			       ctx->ipe_bdev->root_hash);
+}
+#else
+static bool evaluate_dmv_roothash(const struct ipe_eval_ctx *const ctx,
+				  struct ipe_prop *p)
+{
+	return false;
+}
+#endif /* CONFIG_IPE_PROP_DM_VERITY */
+
+#ifdef CONFIG_IPE_PROP_DM_VERITY_SIGNATURE
+/**
+ * evaluate_dmv_sig_false() - Evaluate @ctx against a dmv sig false property.
+ * @ctx: Supplies a pointer to the context being evaluated.
+ *
+ * Return:
+ * * %true	- The current @ctx match the property
+ * * %false	- The current @ctx doesn't match the property
+ */
+static bool evaluate_dmv_sig_false(const struct ipe_eval_ctx *const ctx)
+{
+	return !ctx->ipe_bdev || (!ctx->ipe_bdev->dm_verity_signed);
+}
+
+/**
+ * evaluate_dmv_sig_true() - Evaluate @ctx against a dmv sig true property.
+ * @ctx: Supplies a pointer to the context being evaluated.
+ *
+ * Return:
+ * * %true	- The current @ctx match the property
+ * * %false	- The current @ctx doesn't match the property
+ */
+static bool evaluate_dmv_sig_true(const struct ipe_eval_ctx *const ctx)
+{
+	return !evaluate_dmv_sig_false(ctx);
+}
+#else
+static bool evaluate_dmv_sig_false(const struct ipe_eval_ctx *const ctx)
+{
+	return false;
+}
+
+static bool evaluate_dmv_sig_true(const struct ipe_eval_ctx *const ctx)
+{
+	return false;
+}
+#endif /* CONFIG_IPE_PROP_DM_VERITY_SIGNATURE */
+
+#ifdef CONFIG_IPE_PROP_FS_VERITY
+/**
+ * evaluate_fsv_digest() - Evaluate @ctx against a fsv digest property.
+ * @ctx: Supplies a pointer to the context being evaluated.
+ * @p: Supplies a pointer to the property being evaluated.
+ *
+ * Return:
+ * * %true	- The current @ctx match the @p
+ * * %false	- The current @ctx doesn't match the @p
+ */
+static bool evaluate_fsv_digest(const struct ipe_eval_ctx *const ctx,
+				struct ipe_prop *p)
+{
+	enum hash_algo alg;
+	u8 digest[FS_VERITY_MAX_DIGEST_SIZE];
+	struct digest_info info;
+
+	if (!ctx->ino)
+		return false;
+	if (!fsverity_get_digest((struct inode *)ctx->ino,
+				 digest,
+				 NULL,
+				 &alg))
+		return false;
+
+	info.alg = hash_algo_name[alg];
+	info.digest = digest;
+	info.digest_len = hash_digest_size[alg];
+
+	return ipe_digest_eval(p->value, &info);
+}
+#else
+static bool evaluate_fsv_digest(const struct ipe_eval_ctx *const ctx,
+				struct ipe_prop *p)
+{
+	return false;
+}
+#endif /* CONFIG_IPE_PROP_FS_VERITY */
+
+#ifdef CONFIG_IPE_PROP_FS_VERITY_BUILTIN_SIG
+/**
+ * evaluate_fsv_sig_false() - Evaluate @ctx against a fsv sig false property.
+ * @ctx: Supplies a pointer to the context being evaluated.
+ *
+ * Return:
+ * * %true	- The current @ctx match the property
+ * * %false	- The current @ctx doesn't match the property
+ */
+static bool evaluate_fsv_sig_false(const struct ipe_eval_ctx *const ctx)
+{
+	return !ctx->ino ||
+	       !IS_VERITY(ctx->ino) ||
+	       !ctx->ipe_inode ||
+	       !ctx->ipe_inode->fs_verity_signed;
+}
+
+/**
+ * evaluate_fsv_sig_true() - Evaluate @ctx against a fsv sig true property.
+ * @ctx: Supplies a pointer to the context being evaluated.
+ *
+ * Return:
+ * * %true - The current @ctx match the property
+ * * %false - The current @ctx doesn't match the property
+ */
+static bool evaluate_fsv_sig_true(const struct ipe_eval_ctx *const ctx)
+{
+	return !evaluate_fsv_sig_false(ctx);
+}
+#else
+static bool evaluate_fsv_sig_false(const struct ipe_eval_ctx *const ctx)
+{
+	return false;
+}
+
+static bool evaluate_fsv_sig_true(const struct ipe_eval_ctx *const ctx)
+{
+	return false;
+}
+#endif /* CONFIG_IPE_PROP_FS_VERITY_BUILTIN_SIG */
+
+/**
+ * evaluate_property() - Analyze @ctx against a rule property.
+ * @ctx: Supplies a pointer to the context to be evaluated.
+ * @p: Supplies a pointer to the property to be evaluated.
+ *
+ * This function Determines whether the specified @ctx
+ * matches the conditions defined by a rule property @p.
+ *
+ * Return:
+ * * %true	- The current @ctx match the @p
+ * * %false	- The current @ctx doesn't match the @p
+ */
+static bool evaluate_property(const struct ipe_eval_ctx *const ctx,
+			      struct ipe_prop *p)
+{
+	switch (p->type) {
+	case IPE_PROP_BOOT_VERIFIED_FALSE:
+		return !evaluate_boot_verified(ctx);
+	case IPE_PROP_BOOT_VERIFIED_TRUE:
+		return evaluate_boot_verified(ctx);
+	case IPE_PROP_DMV_ROOTHASH:
+		return evaluate_dmv_roothash(ctx, p);
+	case IPE_PROP_DMV_SIG_FALSE:
+		return evaluate_dmv_sig_false(ctx);
+	case IPE_PROP_DMV_SIG_TRUE:
+		return evaluate_dmv_sig_true(ctx);
+	case IPE_PROP_FSV_DIGEST:
+		return evaluate_fsv_digest(ctx, p);
+	case IPE_PROP_FSV_SIG_FALSE:
+		return evaluate_fsv_sig_false(ctx);
+	case IPE_PROP_FSV_SIG_TRUE:
+		return evaluate_fsv_sig_true(ctx);
+	default:
+		return false;
+	}
+}
+
+/**
+ * ipe_evaluate_event() - Analyze @ctx against the current active policy.
+ * @ctx: Supplies a pointer to the context to be evaluated.
+ *
+ * This is the loop where all policy evaluations happen against the IPE policy.
+ *
+ * Return:
+ * * %0		- Success
+ * * %-EACCES	- @ctx did not pass evaluation
+ */
+int ipe_evaluate_event(const struct ipe_eval_ctx *const ctx)
+{
+	const struct ipe_op_table *rules = NULL;
+	const struct ipe_rule *rule = NULL;
+	struct ipe_policy *pol = NULL;
+	struct ipe_prop *prop = NULL;
+	enum ipe_action_type action;
+	enum ipe_match match_type;
+	bool match = false;
+	int rc = 0;
+
+	rcu_read_lock();
+
+	pol = rcu_dereference(ipe_active_policy);
+	if (!pol) {
+		rcu_read_unlock();
+		return 0;
+	}
+
+	if (ctx->op == IPE_OP_INVALID) {
+		if (pol->parsed->global_default_action == IPE_ACTION_INVALID) {
+			WARN(1, "no default rule set for unknown op, ALLOW it");
+			action = IPE_ACTION_ALLOW;
+		} else {
+			action = pol->parsed->global_default_action;
+		}
+		match_type = IPE_MATCH_GLOBAL;
+		goto eval;
+	}
+
+	rules = &pol->parsed->rules[ctx->op];
+
+	list_for_each_entry(rule, &rules->rules, next) {
+		match = true;
+
+		list_for_each_entry(prop, &rule->props, next) {
+			match = evaluate_property(ctx, prop);
+			if (!match)
+				break;
+		}
+
+		if (match)
+			break;
+	}
+
+	if (match) {
+		action = rule->action;
+		match_type = IPE_MATCH_RULE;
+	} else if (rules->default_action != IPE_ACTION_INVALID) {
+		action = rules->default_action;
+		match_type = IPE_MATCH_TABLE;
+	} else {
+		action = pol->parsed->global_default_action;
+		match_type = IPE_MATCH_GLOBAL;
+	}
+
+eval:
+	ipe_audit_match(ctx, match_type, action, rule);
+	rcu_read_unlock();
+
+	if (action == IPE_ACTION_DENY)
+		rc = -EACCES;
+
+	if (!READ_ONCE(enforce))
+		rc = 0;
+
+	return rc;
+}
+
+/* Set the right module name */
+#ifdef KBUILD_MODNAME
+#undef KBUILD_MODNAME
+#define KBUILD_MODNAME "ipe"
+#endif
+
+module_param(success_audit, bool, 0400);
+MODULE_PARM_DESC(success_audit, "Start IPE with success auditing enabled");
+module_param(enforce, bool, 0400);
+MODULE_PARM_DESC(enforce, "Start IPE in enforce or permissive mode");