Merge tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux

Pull arm64 updates from Will Deacon:
 "ACPI:

   - Improve error reporting when failing to manage SDEI on AGDI device
     removal

  Assembly routines:

   - Improve register constraints so that the compiler can make use of
     the zero register instead of moving an immediate #0 into a GPR

   - Allow the compiler to allocate the registers used for CAS
     instructions

  CPU features and system registers:

   - Cleanups to the way in which CPU features are identified from the
     ID register fields

   - Extend system register definition generation to handle Enum types
     when defining shared register fields

   - Generate definitions for new _EL2 registers and add new fields for
     ID_AA64PFR1_EL1

   - Allow SVE to be disabled separately from SME on the kernel
     command-line

  Tracing:

   - Support for "direct calls" in ftrace, which enables BPF tracing for
     arm64

  Kdump:

   - Don't bother unmapping the crashkernel from the linear mapping,
     which then allows us to use huge (block) mappings and reduce TLB
     pressure when a crashkernel is loaded.

  Memory management:

   - Try again to remove data cache invalidation from the coherent DMA
     allocation path

   - Simplify the fixmap code by mapping at page granularity

   - Allow the kfence pool to be allocated early, preventing the rest of
     the linear mapping from being forced to page granularity

  Perf and PMU:

   - Move CPU PMU code out to drivers/perf/ where it can be reused by
     the 32-bit ARM architecture when running on ARMv8 CPUs

   - Fix race between CPU PMU probing and pKVM host de-privilege

   - Add support for Apple M2 CPU PMU

   - Adjust the generic PERF_COUNT_HW_BRANCH_INSTRUCTIONS event
     dynamically, depending on what the CPU actually supports

   - Minor fixes and cleanups to system PMU drivers

  Stack tracing:

   - Use the XPACLRI instruction to strip PAC from pointers, rather than
     rolling our own function in C

   - Remove redundant PAC removal for toolchains that handle this in
     their builtins

   - Make backtracing more resilient in the face of instrumentation

  Miscellaneous:

   - Fix single-step with KGDB

   - Remove harmless warning when 'nokaslr' is passed on the kernel
     command-line

   - Minor fixes and cleanups across the board"

* tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux: (72 commits)
  KVM: arm64: Ensure CPU PMU probes before pKVM host de-privilege
  arm64: kexec: include reboot.h
  arm64: delete dead code in this_cpu_set_vectors()
  arm64/cpufeature: Use helper macro to specify ID register for capabilites
  drivers/perf: hisi: add NULL check for name
  drivers/perf: hisi: Remove redundant initialized of pmu->name
  arm64/cpufeature: Consistently use symbolic constants for min_field_value
  arm64/cpufeature: Pull out helper for CPUID register definitions
  arm64/sysreg: Convert HFGITR_EL2 to automatic generation
  ACPI: AGDI: Improve error reporting for problems during .remove()
  arm64: kernel: Fix kernel warning when nokaslr is passed to commandline
  perf/arm-cmn: Fix port detection for CMN-700
  arm64: kgdb: Set PSTATE.SS to 1 to re-enable single-step
  arm64: move PAC masks to <asm/pointer_auth.h>
  arm64: use XPACLRI to strip PAC
  arm64: avoid redundant PAC stripping in __builtin_return_address()
  arm64/sme: Fix some comments of ARM SME
  arm64/signal: Alloc tpidr2 sigframe after checking system_supports_tpidr2()
  arm64/signal: Use system_supports_tpidr2() to check TPIDR2
  arm64/idreg: Don't disable SME when disabling SVE
  ...

4 files changed, 40 insertions, 434 deletions

diff --git a/kernel/bpf/trampoline.c b/kernel/bpf/trampoline.c
index d0ed7d6f5eec..a14d0af534b3 100644
--- a/kernel/bpf/trampoline.c
+++ b/kernel/bpf/trampoline.c
@@ -45,8 +45,8 @@ static int bpf_tramp_ftrace_ops_func(struct ftrace_ops *ops, enum ftrace_ops_cmd
 		lockdep_assert_held_once(&tr->mutex);
 
 		/* Instead of updating the trampoline here, we propagate
-		 * -EAGAIN to register_ftrace_direct_multi(). Then we can
-		 * retry register_ftrace_direct_multi() after updating the
+		 * -EAGAIN to register_ftrace_direct(). Then we can
+		 * retry register_ftrace_direct() after updating the
 		 * trampoline.
 		 */
 		if ((tr->flags & BPF_TRAMP_F_CALL_ORIG) &&
@@ -198,7 +198,7 @@ static int unregister_fentry(struct bpf_trampoline *tr, void *old_addr)
 	int ret;
 
 	if (tr->func.ftrace_managed)
-		ret = unregister_ftrace_direct_multi(tr->fops, (long)old_addr);
+		ret = unregister_ftrace_direct(tr->fops, (long)old_addr, false);
 	else
 		ret = bpf_arch_text_poke(ip, BPF_MOD_CALL, old_addr, NULL);
 
@@ -215,9 +215,9 @@ static int modify_fentry(struct bpf_trampoline *tr, void *old_addr, void *new_ad
 
 	if (tr->func.ftrace_managed) {
 		if (lock_direct_mutex)
-			ret = modify_ftrace_direct_multi(tr->fops, (long)new_addr);
+			ret = modify_ftrace_direct(tr->fops, (long)new_addr);
 		else
-			ret = modify_ftrace_direct_multi_nolock(tr->fops, (long)new_addr);
+			ret = modify_ftrace_direct_nolock(tr->fops, (long)new_addr);
 	} else {
 		ret = bpf_arch_text_poke(ip, BPF_MOD_CALL, old_addr, new_addr);
 	}
@@ -243,7 +243,7 @@ static int register_fentry(struct bpf_trampoline *tr, void *new_addr)
 
 	if (tr->func.ftrace_managed) {
 		ftrace_set_filter_ip(tr->fops, (unsigned long)ip, 0, 1);
-		ret = register_ftrace_direct_multi(tr->fops, (long)new_addr);
+		ret = register_ftrace_direct(tr->fops, (long)new_addr);
 	} else {
 		ret = bpf_arch_text_poke(ip, BPF_MOD_CALL, NULL, new_addr);
 	}
diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig
index a856d4a34c67..5b1e7fa41ca8 100644
--- a/kernel/trace/Kconfig
+++ b/kernel/trace/Kconfig
@@ -257,7 +257,7 @@ config DYNAMIC_FTRACE_WITH_REGS
 
 config DYNAMIC_FTRACE_WITH_DIRECT_CALLS
 	def_bool y
-	depends on DYNAMIC_FTRACE_WITH_REGS
+	depends on DYNAMIC_FTRACE_WITH_REGS || DYNAMIC_FTRACE_WITH_ARGS
 	depends on HAVE_DYNAMIC_FTRACE_WITH_DIRECT_CALLS
 
 config DYNAMIC_FTRACE_WITH_CALL_OPS
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index c67bcc89a771..3b46dba3f69b 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -2583,28 +2583,13 @@ ftrace_add_rec_direct(unsigned long ip, unsigned long addr,
 static void call_direct_funcs(unsigned long ip, unsigned long pip,
 			      struct ftrace_ops *ops, struct ftrace_regs *fregs)
 {
-	unsigned long addr;
+	unsigned long addr = READ_ONCE(ops->direct_call);
 
-	addr = ftrace_find_rec_direct(ip);
 	if (!addr)
 		return;
 
 	arch_ftrace_set_direct_caller(fregs, addr);
 }
-
-static struct ftrace_ops direct_ops = {
-	.func		= call_direct_funcs,
-	.flags		= FTRACE_OPS_FL_DIRECT | FTRACE_OPS_FL_SAVE_REGS
-			  | FTRACE_OPS_FL_PERMANENT,
-	/*
-	 * By declaring the main trampoline as this trampoline
-	 * it will never have one allocated for it. Allocated
-	 * trampolines should not call direct functions.
-	 * The direct_ops should only be called by the builtin
-	 * ftrace_regs_caller trampoline.
-	 */
-	.trampoline	= FTRACE_REGS_ADDR,
-};
 #endif /* CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS */
 
 /**
@@ -5301,391 +5286,9 @@ struct ftrace_direct_func {
 
 static LIST_HEAD(ftrace_direct_funcs);
 
-/**
- * ftrace_find_direct_func - test an address if it is a registered direct caller
- * @addr: The address of a registered direct caller
- *
- * This searches to see if a ftrace direct caller has been registered
- * at a specific address, and if so, it returns a descriptor for it.
- *
- * This can be used by architecture code to see if an address is
- * a direct caller (trampoline) attached to a fentry/mcount location.
- * This is useful for the function_graph tracer, as it may need to
- * do adjustments if it traced a location that also has a direct
- * trampoline attached to it.
- */
-struct ftrace_direct_func *ftrace_find_direct_func(unsigned long addr)
-{
-	struct ftrace_direct_func *entry;
-	bool found = false;
-
-	/* May be called by fgraph trampoline (protected by rcu tasks) */
-	list_for_each_entry_rcu(entry, &ftrace_direct_funcs, next) {
-		if (entry->addr == addr) {
-			found = true;
-			break;
-		}
-	}
-	if (found)
-		return entry;
-
-	return NULL;
-}
-
-static struct ftrace_direct_func *ftrace_alloc_direct_func(unsigned long addr)
-{
-	struct ftrace_direct_func *direct;
-
-	direct = kmalloc(sizeof(*direct), GFP_KERNEL);
-	if (!direct)
-		return NULL;
-	direct->addr = addr;
-	direct->count = 0;
-	list_add_rcu(&direct->next, &ftrace_direct_funcs);
-	ftrace_direct_func_count++;
-	return direct;
-}
-
 static int register_ftrace_function_nolock(struct ftrace_ops *ops);
 
-/**
- * register_ftrace_direct - Call a custom trampoline directly
- * @ip: The address of the nop at the beginning of a function
- * @addr: The address of the trampoline to call at @ip
- *
- * This is used to connect a direct call from the nop location (@ip)
- * at the start of ftrace traced functions. The location that it calls
- * (@addr) must be able to handle a direct call, and save the parameters
- * of the function being traced, and restore them (or inject new ones
- * if needed), before returning.
- *
- * Returns:
- *  0 on success
- *  -EBUSY - Another direct function is already attached (there can be only one)
- *  -ENODEV - @ip does not point to a ftrace nop location (or not supported)
- *  -ENOMEM - There was an allocation failure.
- */
-int register_ftrace_direct(unsigned long ip, unsigned long addr)
-{
-	struct ftrace_direct_func *direct;
-	struct ftrace_func_entry *entry;
-	struct ftrace_hash *free_hash = NULL;
-	struct dyn_ftrace *rec;
-	int ret = -ENODEV;
-
-	mutex_lock(&direct_mutex);
-
-	ip = ftrace_location(ip);
-	if (!ip)
-		goto out_unlock;
-
-	/* See if there's a direct function at @ip already */
-	ret = -EBUSY;
-	if (ftrace_find_rec_direct(ip))
-		goto out_unlock;
-
-	ret = -ENODEV;
-	rec = lookup_rec(ip, ip);
-	if (!rec)
-		goto out_unlock;
-
-	/*
-	 * Check if the rec says it has a direct call but we didn't
-	 * find one earlier?
-	 */
-	if (WARN_ON(rec->flags & FTRACE_FL_DIRECT))
-		goto out_unlock;
-
-	/* Make sure the ip points to the exact record */
-	if (ip != rec->ip) {
-		ip = rec->ip;
-		/* Need to check this ip for a direct. */
-		if (ftrace_find_rec_direct(ip))
-			goto out_unlock;
-	}
-
-	ret = -ENOMEM;
-	direct = ftrace_find_direct_func(addr);
-	if (!direct) {
-		direct = ftrace_alloc_direct_func(addr);
-		if (!direct)
-			goto out_unlock;
-	}
-
-	entry = ftrace_add_rec_direct(ip, addr, &free_hash);
-	if (!entry)
-		goto out_unlock;
-
-	ret = ftrace_set_filter_ip(&direct_ops, ip, 0, 0);
-
-	if (!ret && !(direct_ops.flags & FTRACE_OPS_FL_ENABLED)) {
-		ret = register_ftrace_function_nolock(&direct_ops);
-		if (ret)
-			ftrace_set_filter_ip(&direct_ops, ip, 1, 0);
-	}
-
-	if (ret) {
-		remove_hash_entry(direct_functions, entry);
-		kfree(entry);
-		if (!direct->count) {
-			list_del_rcu(&direct->next);
-			synchronize_rcu_tasks();
-			kfree(direct);
-			if (free_hash)
-				free_ftrace_hash(free_hash);
-			free_hash = NULL;
-			ftrace_direct_func_count--;
-		}
-	} else {
-		direct->count++;
-	}
- out_unlock:
-	mutex_unlock(&direct_mutex);
-
-	if (free_hash) {
-		synchronize_rcu_tasks();
-		free_ftrace_hash(free_hash);
-	}
-
-	return ret;
-}
-EXPORT_SYMBOL_GPL(register_ftrace_direct);
-
-static struct ftrace_func_entry *find_direct_entry(unsigned long *ip,
-						   struct dyn_ftrace **recp)
-{
-	struct ftrace_func_entry *entry;
-	struct dyn_ftrace *rec;
-
-	rec = lookup_rec(*ip, *ip);
-	if (!rec)
-		return NULL;
-
-	entry = __ftrace_lookup_ip(direct_functions, rec->ip);
-	if (!entry) {
-		WARN_ON(rec->flags & FTRACE_FL_DIRECT);
-		return NULL;
-	}
-
-	WARN_ON(!(rec->flags & FTRACE_FL_DIRECT));
-
-	/* Passed in ip just needs to be on the call site */
-	*ip = rec->ip;
-
-	if (recp)
-		*recp = rec;
-
-	return entry;
-}
-
-int unregister_ftrace_direct(unsigned long ip, unsigned long addr)
-{
-	struct ftrace_direct_func *direct;
-	struct ftrace_func_entry *entry;
-	struct ftrace_hash *hash;
-	int ret = -ENODEV;
-
-	mutex_lock(&direct_mutex);
-
-	ip = ftrace_location(ip);
-	if (!ip)
-		goto out_unlock;
-
-	entry = find_direct_entry(&ip, NULL);
-	if (!entry)
-		goto out_unlock;
-
-	hash = direct_ops.func_hash->filter_hash;
-	if (hash->count == 1)
-		unregister_ftrace_function(&direct_ops);
-
-	ret = ftrace_set_filter_ip(&direct_ops, ip, 1, 0);
-
-	WARN_ON(ret);
-
-	remove_hash_entry(direct_functions, entry);
-
-	direct = ftrace_find_direct_func(addr);
-	if (!WARN_ON(!direct)) {
-		/* This is the good path (see the ! before WARN) */
-		direct->count--;
-		WARN_ON(direct->count < 0);
-		if (!direct->count) {
-			list_del_rcu(&direct->next);
-			synchronize_rcu_tasks();
-			kfree(direct);
-			kfree(entry);
-			ftrace_direct_func_count--;
-		}
-	}
- out_unlock:
-	mutex_unlock(&direct_mutex);
-
-	return ret;
-}
-EXPORT_SYMBOL_GPL(unregister_ftrace_direct);
-
-static struct ftrace_ops stub_ops = {
-	.func		= ftrace_stub,
-};
-
-/**
- * ftrace_modify_direct_caller - modify ftrace nop directly
- * @entry: The ftrace hash entry of the direct helper for @rec
- * @rec: The record representing the function site to patch
- * @old_addr: The location that the site at @rec->ip currently calls
- * @new_addr: The location that the site at @rec->ip should call
- *
- * An architecture may overwrite this function to optimize the
- * changing of the direct callback on an ftrace nop location.
- * This is called with the ftrace_lock mutex held, and no other
- * ftrace callbacks are on the associated record (@rec). Thus,
- * it is safe to modify the ftrace record, where it should be
- * currently calling @old_addr directly, to call @new_addr.
- *
- * This is called with direct_mutex locked.
- *
- * Safety checks should be made to make sure that the code at
- * @rec->ip is currently calling @old_addr. And this must
- * also update entry->direct to @new_addr.
- */
-int __weak ftrace_modify_direct_caller(struct ftrace_func_entry *entry,
-				       struct dyn_ftrace *rec,
-				       unsigned long old_addr,
-				       unsigned long new_addr)
-{
-	unsigned long ip = rec->ip;
-	int ret;
-
-	lockdep_assert_held(&direct_mutex);
-
-	/*
-	 * The ftrace_lock was used to determine if the record
-	 * had more than one registered user to it. If it did,
-	 * we needed to prevent that from changing to do the quick
-	 * switch. But if it did not (only a direct caller was attached)
-	 * then this function is called. But this function can deal
-	 * with attached callers to the rec that we care about, and
-	 * since this function uses standard ftrace calls that take
-	 * the ftrace_lock mutex, we need to release it.
-	 */
-	mutex_unlock(&ftrace_lock);
-
-	/*
-	 * By setting a stub function at the same address, we force
-	 * the code to call the iterator and the direct_ops helper.
-	 * This means that @ip does not call the direct call, and
-	 * we can simply modify it.
-	 */
-	ret = ftrace_set_filter_ip(&stub_ops, ip, 0, 0);
-	if (ret)
-		goto out_lock;
-
-	ret = register_ftrace_function_nolock(&stub_ops);
-	if (ret) {
-		ftrace_set_filter_ip(&stub_ops, ip, 1, 0);
-		goto out_lock;
-	}
-
-	entry->direct = new_addr;
-
-	/*
-	 * By removing the stub, we put back the direct call, calling
-	 * the @new_addr.
-	 */
-	unregister_ftrace_function(&stub_ops);
-	ftrace_set_filter_ip(&stub_ops, ip, 1, 0);
-
- out_lock:
-	mutex_lock(&ftrace_lock);
-
-	return ret;
-}
-
-/**
- * modify_ftrace_direct - Modify an existing direct call to call something else
- * @ip: The instruction pointer to modify
- * @old_addr: The address that the current @ip calls directly
- * @new_addr: The address that the @ip should call
- *
- * This modifies a ftrace direct caller at an instruction pointer without
- * having to disable it first. The direct call will switch over to the
- * @new_addr without missing anything.
- *
- * Returns: zero on success. Non zero on error, which includes:
- *  -ENODEV : the @ip given has no direct caller attached
- *  -EINVAL : the @old_addr does not match the current direct caller
- */
-int modify_ftrace_direct(unsigned long ip,
-			 unsigned long old_addr, unsigned long new_addr)
-{
-	struct ftrace_direct_func *direct, *new_direct = NULL;
-	struct ftrace_func_entry *entry;
-	struct dyn_ftrace *rec;
-	int ret = -ENODEV;
-
-	mutex_lock(&direct_mutex);
-
-	mutex_lock(&ftrace_lock);
-
-	ip = ftrace_location(ip);
-	if (!ip)
-		goto out_unlock;
-
-	entry = find_direct_entry(&ip, &rec);
-	if (!entry)
-		goto out_unlock;
-
-	ret = -EINVAL;
-	if (entry->direct != old_addr)
-		goto out_unlock;
-
-	direct = ftrace_find_direct_func(old_addr);
-	if (WARN_ON(!direct))
-		goto out_unlock;
-	if (direct->count > 1) {
-		ret = -ENOMEM;
-		new_direct = ftrace_alloc_direct_func(new_addr);
-		if (!new_direct)
-			goto out_unlock;
-		direct->count--;
-		new_direct->count++;
-	} else {
-		direct->addr = new_addr;
-	}
-
-	/*
-	 * If there's no other ftrace callback on the rec->ip location,
-	 * then it can be changed directly by the architecture.
-	 * If there is another caller, then we just need to change the
-	 * direct caller helper to point to @new_addr.
-	 */
-	if (ftrace_rec_count(rec) == 1) {
-		ret = ftrace_modify_direct_caller(entry, rec, old_addr, new_addr);
-	} else {
-		entry->direct = new_addr;
-		ret = 0;
-	}
-
-	if (ret) {
-		direct->addr = old_addr;
-		if (unlikely(new_direct)) {
-			direct->count++;
-			list_del_rcu(&new_direct->next);
-			synchronize_rcu_tasks();
-			kfree(new_direct);
-			ftrace_direct_func_count--;
-		}
-	}
-
- out_unlock:
-	mutex_unlock(&ftrace_lock);
-	mutex_unlock(&direct_mutex);
-	return ret;
-}
-EXPORT_SYMBOL_GPL(modify_ftrace_direct);
-
-#define MULTI_FLAGS (FTRACE_OPS_FL_DIRECT | FTRACE_OPS_FL_SAVE_REGS)
+#define MULTI_FLAGS (FTRACE_OPS_FL_DIRECT | FTRACE_OPS_FL_SAVE_ARGS)
 
 static int check_direct_multi(struct ftrace_ops *ops)
 {
@@ -5714,7 +5317,7 @@ static void remove_direct_functions_hash(struct ftrace_hash *hash, unsigned long
 }
 
 /**
- * register_ftrace_direct_multi - Call a custom trampoline directly
+ * register_ftrace_direct - Call a custom trampoline directly
  * for multiple functions registered in @ops
  * @ops: The address of the struct ftrace_ops object
  * @addr: The address of the trampoline to call at @ops functions
@@ -5735,7 +5338,7 @@ static void remove_direct_functions_hash(struct ftrace_hash *hash, unsigned long
  *  -ENODEV  - @ip does not point to a ftrace nop location (or not supported)
  *  -ENOMEM  - There was an allocation failure.
  */
-int register_ftrace_direct_multi(struct ftrace_ops *ops, unsigned long addr)
+int register_ftrace_direct(struct ftrace_ops *ops, unsigned long addr)
 {
 	struct ftrace_hash *hash, *free_hash = NULL;
 	struct ftrace_func_entry *entry, *new;
@@ -5777,6 +5380,7 @@ int register_ftrace_direct_multi(struct ftrace_ops *ops, unsigned long addr)
 	ops->func = call_direct_funcs;
 	ops->flags = MULTI_FLAGS;
 	ops->trampoline = FTRACE_REGS_ADDR;
+	ops->direct_call = addr;
 
 	err = register_ftrace_function_nolock(ops);
 
@@ -5793,11 +5397,11 @@ int register_ftrace_direct_multi(struct ftrace_ops *ops, unsigned long addr)
 	}
 	return err;
 }
-EXPORT_SYMBOL_GPL(register_ftrace_direct_multi);
+EXPORT_SYMBOL_GPL(register_ftrace_direct);
 
 /**
- * unregister_ftrace_direct_multi - Remove calls to custom trampoline
- * previously registered by register_ftrace_direct_multi for @ops object.
+ * unregister_ftrace_direct - Remove calls to custom trampoline
+ * previously registered by register_ftrace_direct for @ops object.
  * @ops: The address of the struct ftrace_ops object
  *
  * This is used to remove a direct calls to @addr from the nop locations
@@ -5808,7 +5412,8 @@ EXPORT_SYMBOL_GPL(register_ftrace_direct_multi);
  *  0 on success
  *  -EINVAL - The @ops object was not properly registered.
  */
-int unregister_ftrace_direct_multi(struct ftrace_ops *ops, unsigned long addr)
+int unregister_ftrace_direct(struct ftrace_ops *ops, unsigned long addr,
+			     bool free_filters)
 {
 	struct ftrace_hash *hash = ops->func_hash->filter_hash;
 	int err;
@@ -5826,12 +5431,15 @@ int unregister_ftrace_direct_multi(struct ftrace_ops *ops, unsigned long addr)
 	/* cleanup for possible another register call */
 	ops->func = NULL;
 	ops->trampoline = 0;
+
+	if (free_filters)
+		ftrace_free_filter(ops);
 	return err;
 }
-EXPORT_SYMBOL_GPL(unregister_ftrace_direct_multi);
+EXPORT_SYMBOL_GPL(unregister_ftrace_direct);
 
 static int
-__modify_ftrace_direct_multi(struct ftrace_ops *ops, unsigned long addr)
+__modify_ftrace_direct(struct ftrace_ops *ops, unsigned long addr)
 {
 	struct ftrace_hash *hash;
 	struct ftrace_func_entry *entry, *iter;
@@ -5847,6 +5455,7 @@ __modify_ftrace_direct_multi(struct ftrace_ops *ops, unsigned long addr)
 	/* Enable the tmp_ops to have the same functions as the direct ops */
 	ftrace_ops_init(&tmp_ops);
 	tmp_ops.func_hash = ops->func_hash;
+	tmp_ops.direct_call = addr;
 
 	err = register_ftrace_function_nolock(&tmp_ops);
 	if (err)
@@ -5868,6 +5477,8 @@ __modify_ftrace_direct_multi(struct ftrace_ops *ops, unsigned long addr)
 			entry->direct = addr;
 		}
 	}
+	/* Prevent store tearing if a trampoline concurrently accesses the value */
+	WRITE_ONCE(ops->direct_call, addr);
 
 	mutex_unlock(&ftrace_lock);
 
@@ -5878,7 +5489,7 @@ __modify_ftrace_direct_multi(struct ftrace_ops *ops, unsigned long addr)
 }
 
 /**
- * modify_ftrace_direct_multi_nolock - Modify an existing direct 'multi' call
+ * modify_ftrace_direct_nolock - Modify an existing direct 'multi' call
  * to call something else
  * @ops: The address of the struct ftrace_ops object
  * @addr: The address of the new trampoline to call at @ops functions
@@ -5895,19 +5506,19 @@ __modify_ftrace_direct_multi(struct ftrace_ops *ops, unsigned long addr)
  * Returns: zero on success. Non zero on error, which includes:
  *  -EINVAL - The @ops object was not properly registered.
  */
-int modify_ftrace_direct_multi_nolock(struct ftrace_ops *ops, unsigned long addr)
+int modify_ftrace_direct_nolock(struct ftrace_ops *ops, unsigned long addr)
 {
 	if (check_direct_multi(ops))
 		return -EINVAL;
 	if (!(ops->flags & FTRACE_OPS_FL_ENABLED))
 		return -EINVAL;
 
-	return __modify_ftrace_direct_multi(ops, addr);
+	return __modify_ftrace_direct(ops, addr);
 }
-EXPORT_SYMBOL_GPL(modify_ftrace_direct_multi_nolock);
+EXPORT_SYMBOL_GPL(modify_ftrace_direct_nolock);
 
 /**
- * modify_ftrace_direct_multi - Modify an existing direct 'multi' call
+ * modify_ftrace_direct - Modify an existing direct 'multi' call
  * to call something else
  * @ops: The address of the struct ftrace_ops object
  * @addr: The address of the new trampoline to call at @ops functions
@@ -5921,7 +5532,7 @@ EXPORT_SYMBOL_GPL(modify_ftrace_direct_multi_nolock);
  * Returns: zero on success. Non zero on error, which includes:
  *  -EINVAL - The @ops object was not properly registered.
  */
-int modify_ftrace_direct_multi(struct ftrace_ops *ops, unsigned long addr)
+int modify_ftrace_direct(struct ftrace_ops *ops, unsigned long addr)
 {
 	int err;
 
@@ -5931,11 +5542,11 @@ int modify_ftrace_direct_multi(struct ftrace_ops *ops, unsigned long addr)
 		return -EINVAL;
 
 	mutex_lock(&direct_mutex);
-	err = __modify_ftrace_direct_multi(ops, addr);
+	err = __modify_ftrace_direct(ops, addr);
 	mutex_unlock(&direct_mutex);
 	return err;
 }
-EXPORT_SYMBOL_GPL(modify_ftrace_direct_multi);
+EXPORT_SYMBOL_GPL(modify_ftrace_direct);
 #endif /* CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS */
 
 /**
diff --git a/kernel/trace/trace_selftest.c b/kernel/trace/trace_selftest.c
index ff0536cea968..a931d9aaea26 100644
--- a/kernel/trace/trace_selftest.c
+++ b/kernel/trace/trace_selftest.c
@@ -785,14 +785,7 @@ static struct fgraph_ops fgraph_ops __initdata  = {
 };
 
 #ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS
-#ifndef CALL_DEPTH_ACCOUNT
-#define CALL_DEPTH_ACCOUNT ""
-#endif
-
-noinline __noclone static void trace_direct_tramp(void)
-{
-	asm(CALL_DEPTH_ACCOUNT);
-}
+static struct ftrace_ops direct;
 #endif
 
 /*
@@ -870,8 +863,9 @@ trace_selftest_startup_function_graph(struct tracer *trace,
 	 * Register direct function together with graph tracer
 	 * and make sure we get graph trace.
 	 */
-	ret = register_ftrace_direct((unsigned long) DYN_FTRACE_TEST_NAME,
-				     (unsigned long) trace_direct_tramp);
+	ftrace_set_filter_ip(&direct, (unsigned long)DYN_FTRACE_TEST_NAME, 0, 0);
+	ret = register_ftrace_direct(&direct,
+				     (unsigned long)ftrace_stub_direct_tramp);
 	if (ret)
 		goto out;
 
@@ -891,8 +885,9 @@ trace_selftest_startup_function_graph(struct tracer *trace,
 
 	unregister_ftrace_graph(&fgraph_ops);
 
-	ret = unregister_ftrace_direct((unsigned long) DYN_FTRACE_TEST_NAME,
-				       (unsigned long) trace_direct_tramp);
+	ret = unregister_ftrace_direct(&direct,
+				       (unsigned long)ftrace_stub_direct_tramp,
+				       true);
 	if (ret)
 		goto out;