diff mbox series

[PATCHv2,4/8] arm64: module/ftrace: intialize PLT at load time

Message ID 20191029165832.33606-5-mark.rutland@arm.com
State Accepted
Commit f1a54ae9af0da4d76239256ed640a93ab3aadac0
Headers show
Series arm64: ftrace cleanup + FTRACE_WITH_REGS | expand

Commit Message

Mark Rutland Oct. 29, 2019, 4:58 p.m. UTC
Currently we lazily-initialize a module's ftrace PLT at runtime when we
install the first ftrace call. To do so we have to apply a number of
sanity checks, transiently mark the module text as RW, and perform an
IPI as part of handling Neoverse-N1 erratum #1542419.

We only expect the ftrace trampoline to point at ftrace_caller() (AKA
FTRACE_ADDR), so let's simplify all of this by intializing the PLT at
module load time, before the module loader marks the module RO and
performs the intial I-cache maintenance for the module.

Thus we can rely on the module having been correctly intialized, and can
simplify the runtime work necessary to install an ftrace call in a
module. This will also allow for the removal of module_disable_ro().

Tested by forcing ftrace_make_call() to use the module PLT, and then
loading up a module after setting up ftrace with:

| echo ":mod:<module-name>" > set_ftrace_filter;
| echo function > current_tracer;
| modprobe <module-name>

Since FTRACE_ADDR is only defined when CONFIG_DYNAMIC_FTRACE is
selected, we wrap its use along with most of module_init_ftrace_plt()
with ifdeffery rather than using IS_ENABLED().

Signed-off-by: Mark Rutland <mark.rutland@arm.com>

Reviewed-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>

Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: James Morse <james.morse@arm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Will Deacon <will@kernel.org>
---
 arch/arm64/kernel/ftrace.c | 55 ++++++++++++----------------------------------
 arch/arm64/kernel/module.c | 32 +++++++++++++++++----------
 2 files changed, 35 insertions(+), 52 deletions(-)

-- 
2.11.0

Comments

Amit Kachhap Nov. 2, 2019, 12:20 p.m. UTC | #1
Hi,

On 10/29/19 10:28 PM, Mark Rutland wrote:
> Currently we lazily-initialize a module's ftrace PLT at runtime when we

> install the first ftrace call. To do so we have to apply a number of

> sanity checks, transiently mark the module text as RW, and perform an

> IPI as part of handling Neoverse-N1 erratum #1542419.

> 

> We only expect the ftrace trampoline to point at ftrace_caller() (AKA

> FTRACE_ADDR), so let's simplify all of this by intializing the PLT at

> module load time, before the module loader marks the module RO and

> performs the intial I-cache maintenance for the module.

> 

> Thus we can rely on the module having been correctly intialized, and can

> simplify the runtime work necessary to install an ftrace call in a

> module. This will also allow for the removal of module_disable_ro().

> 

> Tested by forcing ftrace_make_call() to use the module PLT, and then

> loading up a module after setting up ftrace with:

> 

> | echo ":mod:<module-name>" > set_ftrace_filter;

> | echo function > current_tracer;

> | modprobe <module-name>

> 

> Since FTRACE_ADDR is only defined when CONFIG_DYNAMIC_FTRACE is

> selected, we wrap its use along with most of module_init_ftrace_plt()

> with ifdeffery rather than using IS_ENABLED().

> 

> Signed-off-by: Mark Rutland <mark.rutland@arm.com>

> Reviewed-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>

> Cc: Catalin Marinas <catalin.marinas@arm.com>

> Cc: James Morse <james.morse@arm.com>

> Cc: Peter Zijlstra <peterz@infradead.org>

> Cc: Will Deacon <will@kernel.org>

> ---

>   arch/arm64/kernel/ftrace.c | 55 ++++++++++++----------------------------------

>   arch/arm64/kernel/module.c | 32 +++++++++++++++++----------

>   2 files changed, 35 insertions(+), 52 deletions(-)

> 

> diff --git a/arch/arm64/kernel/ftrace.c b/arch/arm64/kernel/ftrace.c

> index 06e56b470315..822718eafdb4 100644

> --- a/arch/arm64/kernel/ftrace.c

> +++ b/arch/arm64/kernel/ftrace.c

> @@ -73,10 +73,22 @@ int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)

>   

>   	if (offset < -SZ_128M || offset >= SZ_128M) {

>   #ifdef CONFIG_ARM64_MODULE_PLTS

> -		struct plt_entry trampoline, *dst;

>   		struct module *mod;

>   

>   		/*

> +		 * There is only one ftrace trampoline per module. For now,

> +		 * this is not a problem since on arm64, all dynamic ftrace

> +		 * invocations are routed via ftrace_caller(). This will need

> +		 * to be revisited if support for multiple ftrace entry points

> +		 * is added in the future, but for now, the pr_err() below

> +		 * deals with a theoretical issue only.

> +		 */

> +		if (addr != FTRACE_ADDR) {

> +			pr_err("ftrace: far branches to multiple entry points unsupported inside a single module\n");

> +			return -EINVAL;

> +		}

> +

> +		/*

>   		 * On kernels that support module PLTs, the offset between the

>   		 * branch instruction and its target may legally exceed the

>   		 * range of an ordinary relative 'bl' opcode. In this case, we

> @@ -93,46 +105,7 @@ int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)

>   		if (WARN_ON(!mod))

>   			return -EINVAL;

>   

> -		/*

> -		 * There is only one ftrace trampoline per module. For now,

> -		 * this is not a problem since on arm64, all dynamic ftrace

> -		 * invocations are routed via ftrace_caller(). This will need

> -		 * to be revisited if support for multiple ftrace entry points

> -		 * is added in the future, but for now, the pr_err() below

> -		 * deals with a theoretical issue only.

> -		 *

> -		 * Note that PLTs are place relative, and plt_entries_equal()

> -		 * checks whether they point to the same target. Here, we need

> -		 * to check if the actual opcodes are in fact identical,

> -		 * regardless of the offset in memory so use memcmp() instead.

> -		 */

> -		dst = mod->arch.ftrace_trampoline;

> -		trampoline = get_plt_entry(addr, dst);

> -		if (memcmp(dst, &trampoline, sizeof(trampoline))) {

> -			if (plt_entry_is_initialized(dst)) {

> -				pr_err("ftrace: far branches to multiple entry points unsupported inside a single module\n");

> -				return -EINVAL;

> -			}

> -

> -			/* point the trampoline to our ftrace entry point */

> -			module_disable_ro(mod);

> -			*dst = trampoline;

> -			module_enable_ro(mod, true);

> -

> -			/*

> -			 * Ensure updated trampoline is visible to instruction

> -			 * fetch before we patch in the branch. Although the

> -			 * architecture doesn't require an IPI in this case,

> -			 * Neoverse-N1 erratum #1542419 does require one

> -			 * if the TLB maintenance in module_enable_ro() is

> -			 * skipped due to rodata_enabled. It doesn't seem worth

> -			 * it to make it conditional given that this is

> -			 * certainly not a fast-path.

> -			 */

> -			flush_icache_range((unsigned long)&dst[0],

> -					   (unsigned long)&dst[1]);

> -		}

> -		addr = (unsigned long)dst;

> +		addr = (unsigned long)mod->arch.ftrace_trampoline;

>   #else /* CONFIG_ARM64_MODULE_PLTS */

>   		return -EINVAL;

>   #endif /* CONFIG_ARM64_MODULE_PLTS */

> diff --git a/arch/arm64/kernel/module.c b/arch/arm64/kernel/module.c

> index 763a86d52fef..5f5bc3b94da7 100644

> --- a/arch/arm64/kernel/module.c

> +++ b/arch/arm64/kernel/module.c

> @@ -9,6 +9,7 @@

>   

>   #include <linux/bitops.h>

>   #include <linux/elf.h>

> +#include <linux/ftrace.h>

>   #include <linux/gfp.h>

>   #include <linux/kasan.h>

>   #include <linux/kernel.h>

> @@ -485,24 +486,33 @@ static const Elf_Shdr *find_section(const Elf_Ehdr *hdr,

>   	return NULL;

>   }

>   

> +int module_init_ftrace_plt(const Elf_Ehdr *hdr,

> +			   const Elf_Shdr *sechdrs,

> +			   struct module *mod)

I think this function can be made static as it is not used anywhere.

Thanks,
Amit Daniel
> +{

> +#if defined(CONFIG_ARM64_MODULE_PLTS) && defined(CONFIG_DYNAMIC_FTRACE)

> +	const Elf_Shdr *s;

> +	struct plt_entry *plt;

> +

> +	s = find_section(hdr, sechdrs, ".text.ftrace_trampoline");

> +	if (!s)

> +		return -ENOEXEC;

> +

> +	plt = (void *)s->sh_addr;

> +	*plt = get_plt_entry(FTRACE_ADDR, plt);

> +	mod->arch.ftrace_trampoline = plt;

> +#endif

> +	return 0;

> +}

> +

>   int module_finalize(const Elf_Ehdr *hdr,

>   		    const Elf_Shdr *sechdrs,

>   		    struct module *me)

>   {

>   	const Elf_Shdr *s;

> -

>   	s = find_section(hdr, sechdrs, ".altinstructions");

>   	if (s)

>   		apply_alternatives_module((void *)s->sh_addr, s->sh_size);

>   

> -#ifdef CONFIG_ARM64_MODULE_PLTS

> -	if (IS_ENABLED(CONFIG_DYNAMIC_FTRACE)) {

> -		s = find_section(hdr, sechdrs, ".text.ftrace_trampoline");

> -		if (!s)

> -			return -ENOEXEC;

> -		me->arch.ftrace_trampoline = (void *)s->sh_addr;

> -	}

> -#endif

> -

> -	return 0;

> +	return module_init_ftrace_plt(hdr, sechdrs, me);

>   }

>
Mark Rutland Nov. 4, 2019, 1:55 p.m. UTC | #2
On Sat, Nov 02, 2019 at 05:50:02PM +0530, Amit Daniel Kachhap wrote:
> On 10/29/19 10:28 PM, Mark Rutland wrote:

> > @@ -485,24 +486,33 @@ static const Elf_Shdr *find_section(const Elf_Ehdr *hdr,

> >   	return NULL;

> >   }

> > +int module_init_ftrace_plt(const Elf_Ehdr *hdr,

> > +			   const Elf_Shdr *sechdrs,

> > +			   struct module *mod)

> I think this function can be made static as it is not used anywhere.


It's only called by module_finalize() below, so making it static makese
sense; done.

Thanks
Mark.

> > +{

> > +#if defined(CONFIG_ARM64_MODULE_PLTS) && defined(CONFIG_DYNAMIC_FTRACE)

> > +	const Elf_Shdr *s;

> > +	struct plt_entry *plt;

> > +

> > +	s = find_section(hdr, sechdrs, ".text.ftrace_trampoline");

> > +	if (!s)

> > +		return -ENOEXEC;

> > +

> > +	plt = (void *)s->sh_addr;

> > +	*plt = get_plt_entry(FTRACE_ADDR, plt);

> > +	mod->arch.ftrace_trampoline = plt;

> > +#endif

> > +	return 0;

> > +}

> > +

> >   int module_finalize(const Elf_Ehdr *hdr,

> >   		    const Elf_Shdr *sechdrs,

> >   		    struct module *me)

> >   {

> >   	const Elf_Shdr *s;

> > -

> >   	s = find_section(hdr, sechdrs, ".altinstructions");

> >   	if (s)

> >   		apply_alternatives_module((void *)s->sh_addr, s->sh_size);

> > -#ifdef CONFIG_ARM64_MODULE_PLTS

> > -	if (IS_ENABLED(CONFIG_DYNAMIC_FTRACE)) {

> > -		s = find_section(hdr, sechdrs, ".text.ftrace_trampoline");

> > -		if (!s)

> > -			return -ENOEXEC;

> > -		me->arch.ftrace_trampoline = (void *)s->sh_addr;

> > -	}

> > -#endif

> > -

> > -	return 0;

> > +	return module_init_ftrace_plt(hdr, sechdrs, me);

> >   }

> >
diff mbox series

Patch

diff --git a/arch/arm64/kernel/ftrace.c b/arch/arm64/kernel/ftrace.c
index 06e56b470315..822718eafdb4 100644
--- a/arch/arm64/kernel/ftrace.c
+++ b/arch/arm64/kernel/ftrace.c
@@ -73,10 +73,22 @@  int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
 
 	if (offset < -SZ_128M || offset >= SZ_128M) {
 #ifdef CONFIG_ARM64_MODULE_PLTS
-		struct plt_entry trampoline, *dst;
 		struct module *mod;
 
 		/*
+		 * There is only one ftrace trampoline per module. For now,
+		 * this is not a problem since on arm64, all dynamic ftrace
+		 * invocations are routed via ftrace_caller(). This will need
+		 * to be revisited if support for multiple ftrace entry points
+		 * is added in the future, but for now, the pr_err() below
+		 * deals with a theoretical issue only.
+		 */
+		if (addr != FTRACE_ADDR) {
+			pr_err("ftrace: far branches to multiple entry points unsupported inside a single module\n");
+			return -EINVAL;
+		}
+
+		/*
 		 * On kernels that support module PLTs, the offset between the
 		 * branch instruction and its target may legally exceed the
 		 * range of an ordinary relative 'bl' opcode. In this case, we
@@ -93,46 +105,7 @@  int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
 		if (WARN_ON(!mod))
 			return -EINVAL;
 
-		/*
-		 * There is only one ftrace trampoline per module. For now,
-		 * this is not a problem since on arm64, all dynamic ftrace
-		 * invocations are routed via ftrace_caller(). This will need
-		 * to be revisited if support for multiple ftrace entry points
-		 * is added in the future, but for now, the pr_err() below
-		 * deals with a theoretical issue only.
-		 *
-		 * Note that PLTs are place relative, and plt_entries_equal()
-		 * checks whether they point to the same target. Here, we need
-		 * to check if the actual opcodes are in fact identical,
-		 * regardless of the offset in memory so use memcmp() instead.
-		 */
-		dst = mod->arch.ftrace_trampoline;
-		trampoline = get_plt_entry(addr, dst);
-		if (memcmp(dst, &trampoline, sizeof(trampoline))) {
-			if (plt_entry_is_initialized(dst)) {
-				pr_err("ftrace: far branches to multiple entry points unsupported inside a single module\n");
-				return -EINVAL;
-			}
-
-			/* point the trampoline to our ftrace entry point */
-			module_disable_ro(mod);
-			*dst = trampoline;
-			module_enable_ro(mod, true);
-
-			/*
-			 * Ensure updated trampoline is visible to instruction
-			 * fetch before we patch in the branch. Although the
-			 * architecture doesn't require an IPI in this case,
-			 * Neoverse-N1 erratum #1542419 does require one
-			 * if the TLB maintenance in module_enable_ro() is
-			 * skipped due to rodata_enabled. It doesn't seem worth
-			 * it to make it conditional given that this is
-			 * certainly not a fast-path.
-			 */
-			flush_icache_range((unsigned long)&dst[0],
-					   (unsigned long)&dst[1]);
-		}
-		addr = (unsigned long)dst;
+		addr = (unsigned long)mod->arch.ftrace_trampoline;
 #else /* CONFIG_ARM64_MODULE_PLTS */
 		return -EINVAL;
 #endif /* CONFIG_ARM64_MODULE_PLTS */
diff --git a/arch/arm64/kernel/module.c b/arch/arm64/kernel/module.c
index 763a86d52fef..5f5bc3b94da7 100644
--- a/arch/arm64/kernel/module.c
+++ b/arch/arm64/kernel/module.c
@@ -9,6 +9,7 @@ 
 
 #include <linux/bitops.h>
 #include <linux/elf.h>
+#include <linux/ftrace.h>
 #include <linux/gfp.h>
 #include <linux/kasan.h>
 #include <linux/kernel.h>
@@ -485,24 +486,33 @@  static const Elf_Shdr *find_section(const Elf_Ehdr *hdr,
 	return NULL;
 }
 
+int module_init_ftrace_plt(const Elf_Ehdr *hdr,
+			   const Elf_Shdr *sechdrs,
+			   struct module *mod)
+{
+#if defined(CONFIG_ARM64_MODULE_PLTS) && defined(CONFIG_DYNAMIC_FTRACE)
+	const Elf_Shdr *s;
+	struct plt_entry *plt;
+
+	s = find_section(hdr, sechdrs, ".text.ftrace_trampoline");
+	if (!s)
+		return -ENOEXEC;
+
+	plt = (void *)s->sh_addr;
+	*plt = get_plt_entry(FTRACE_ADDR, plt);
+	mod->arch.ftrace_trampoline = plt;
+#endif
+	return 0;
+}
+
 int module_finalize(const Elf_Ehdr *hdr,
 		    const Elf_Shdr *sechdrs,
 		    struct module *me)
 {
 	const Elf_Shdr *s;
-
 	s = find_section(hdr, sechdrs, ".altinstructions");
 	if (s)
 		apply_alternatives_module((void *)s->sh_addr, s->sh_size);
 
-#ifdef CONFIG_ARM64_MODULE_PLTS
-	if (IS_ENABLED(CONFIG_DYNAMIC_FTRACE)) {
-		s = find_section(hdr, sechdrs, ".text.ftrace_trampoline");
-		if (!s)
-			return -ENOEXEC;
-		me->arch.ftrace_trampoline = (void *)s->sh_addr;
-	}
-#endif
-
-	return 0;
+	return module_init_ftrace_plt(hdr, sechdrs, me);
 }