[v7] linuxapp, eal: Fix the memory leak issue of logid

  From: Ziye Yang <optimistyzy@gmail.com>

This patch is used to fix the memory leak issue of logid.
We use the ASAN test in SPDK when intergrating DPDK and
find this memory leak issue.

By the way, we also fix several missed function call of
rte_atomic32_clear.

Signed-off-by: Ziye Yang <ziye.yang@intel.com>
---
 lib/librte_eal/linuxapp/eal/eal.c | 11 +++++++----
 1 file changed, 7 insertions(+), 4 deletions(-)
  

> -----Original Message-----
> From: Yang, Ziye
> Sent: Tuesday, September 11, 2018 2:28 AM
> To: dev@dpdk.org
> Cc: Ananyev, Konstantin <konstantin.ananyev@intel.com>; Ziye Yang <optimistyzy@gmail.com>
> Subject: [PATCH v7] linuxapp, eal: Fix the memory leak issue of logid
> 
> From: Ziye Yang <optimistyzy@gmail.com>
> 
> This patch is used to fix the memory leak issue of logid.
> We use the ASAN test in SPDK when intergrating DPDK and
> find this memory leak issue.
> 
> By the way, we also fix several missed function call of
> rte_atomic32_clear.
> 
> Signed-off-by: Ziye Yang <ziye.yang@intel.com>
> ---
>  lib/librte_eal/linuxapp/eal/eal.c | 11 +++++++----
>  1 file changed, 7 insertions(+), 4 deletions(-)
> 
> diff --git a/lib/librte_eal/linuxapp/eal/eal.c b/lib/librte_eal/linuxapp/eal/eal.c
> index e59ac65..a5129e5 100644
> --- a/lib/librte_eal/linuxapp/eal/eal.c
> +++ b/lib/librte_eal/linuxapp/eal/eal.c
> @@ -793,7 +793,8 @@ static void rte_eal_init_alert(const char *msg)
>  	int i, fctret, ret;
>  	pthread_t thread_id;
>  	static rte_atomic32_t run_once = RTE_ATOMIC32_INIT(0);
> -	const char *logid;
> +	const char *p;
> +	static char logid[PATH_MAX];
>  	char cpuset[RTE_CPU_AFFINITY_STR_LEN];
>  	char thread_name[RTE_MAX_THREAD_NAME_LEN];
> 
> @@ -810,9 +811,8 @@ static void rte_eal_init_alert(const char *msg)
>  		return -1;
>  	}
> 
> -	logid = strrchr(argv[0], '/');
> -	logid = strdup(logid ? logid + 1: argv[0]);
> -
> +	p = strrchr(argv[0], '/');
> +	snprintf(logid, sizeof(logid), "%s", (p ? p + 1 : argv[0]));
>  	thread_id = pthread_self();
> 
>  	eal_reset_internal_config(&internal_config);
> @@ -823,6 +823,7 @@ static void rte_eal_init_alert(const char *msg)
>  	if (rte_eal_cpu_init() < 0) {
>  		rte_eal_init_alert("Cannot detect lcores.");
>  		rte_errno = ENOTSUP;
> +		rte_atomic32_clear(&run_once);
>  		return -1;
>  	}
> 
> @@ -851,6 +852,7 @@ static void rte_eal_init_alert(const char *msg)
> 
>  	if (rte_eal_intr_init() < 0) {
>  		rte_eal_init_alert("Cannot init interrupt-handling thread\n");
> +		rte_atomic32_clear(&run_once);
>  		return -1;
>  	}
> 
> @@ -861,6 +863,7 @@ static void rte_eal_init_alert(const char *msg)
>  		rte_eal_init_alert("failed to init mp channel\n");
>  		if (rte_eal_process_type() == RTE_PROC_PRIMARY) {
>  			rte_errno = EFAULT;
> +			rte_atomic32_clear(&run_once);
>  			return -1;
>  		}
>  	}
> --

Acked-by: Konstantin Ananyev <konstantin.ananyev@intel.com>

> 1.9.3
  

Ziye Yang <ziye.yang@intel.com> writes:

> From: Ziye Yang <optimistyzy@gmail.com>
>
> This patch is used to fix the memory leak issue of logid.
> We use the ASAN test in SPDK when intergrating DPDK and
> find this memory leak issue.
>
> By the way, we also fix several missed function call of
> rte_atomic32_clear.

This part I don't understand.  It should be a separate proposal.

> Signed-off-by: Ziye Yang <ziye.yang@intel.com>
> ---
>  lib/librte_eal/linuxapp/eal/eal.c | 11 +++++++----
>  1 file changed, 7 insertions(+), 4 deletions(-)
>
> diff --git a/lib/librte_eal/linuxapp/eal/eal.c b/lib/librte_eal/linuxapp/eal/eal.c
> index e59ac65..a5129e5 100644
> --- a/lib/librte_eal/linuxapp/eal/eal.c
> +++ b/lib/librte_eal/linuxapp/eal/eal.c
> @@ -793,7 +793,8 @@ static void rte_eal_init_alert(const char *msg)
>  	int i, fctret, ret;
>  	pthread_t thread_id;
>  	static rte_atomic32_t run_once = RTE_ATOMIC32_INIT(0);
> -	const char *logid;
> +	const char *p;
> +	static char logid[PATH_MAX];

On a linux system, PATH_MAX is 4096, but an argument may be
MAX_ARG_STRLEN which is significantly higher.

Have you thought about an alternative where you keep the strdup and add
an atexit() handler to do the free?  Otherwise, you'll need to add code
to check the string length as well and enforce some kind of size
restriction.

>  	char cpuset[RTE_CPU_AFFINITY_STR_LEN];
>  	char thread_name[RTE_MAX_THREAD_NAME_LEN];
>  
> @@ -810,9 +811,8 @@ static void rte_eal_init_alert(const char *msg)
>  		return -1;
>  	}
>  
> -	logid = strrchr(argv[0], '/');
> -	logid = strdup(logid ? logid + 1: argv[0]);
> -
> +	p = strrchr(argv[0], '/');
> +	snprintf(logid, sizeof(logid), "%s", (p ? p + 1 : argv[0]));
>  	thread_id = pthread_self();
>  
>  	eal_reset_internal_config(&internal_config);
> @@ -823,6 +823,7 @@ static void rte_eal_init_alert(const char *msg)
>  	if (rte_eal_cpu_init() < 0) {
>  		rte_eal_init_alert("Cannot detect lcores.");
>  		rte_errno = ENOTSUP;
> +		rte_atomic32_clear(&run_once);

This is not recoverable.  No amount of retry will allow the user to
re-init the eal - the hardware isn't supported.  Why clear the run_once
flag?

>  		return -1;
>  	}
>  
> @@ -851,6 +852,7 @@ static void rte_eal_init_alert(const char *msg)
>  
>  	if (rte_eal_intr_init() < 0) {
>  		rte_eal_init_alert("Cannot init interrupt-handling thread\n");
> +		rte_atomic32_clear(&run_once);

Arguable whether or not this is recoverable.  IIRC, the eal_intr_init
spawns a thread - if it fails to spawn the likelihood is the process
won't be able to continue.

>  		return -1;
>  	}
>  
> @@ -861,6 +863,7 @@ static void rte_eal_init_alert(const char *msg)
>  		rte_eal_init_alert("failed to init mp channel\n");
>  		if (rte_eal_process_type() == RTE_PROC_PRIMARY) {
>  			rte_errno = EFAULT;
> +			rte_atomic32_clear(&run_once);

This is also not recoverable.  Why clear the run_once flag?

>  			return -1;
>  		}
>  	}
  

> -----Original Message-----
> From: Aaron Conole [mailto:aconole@redhat.com]
> Sent: Tuesday, September 11, 2018 2:47 PM
> To: Yang, Ziye <ziye.yang@intel.com>
> Cc: dev@dpdk.org; Ananyev, Konstantin <konstantin.ananyev@intel.com>; Ziye Yang <optimistyzy@gmail.com>
> Subject: Re: [dpdk-dev] [PATCH v7] linuxapp, eal: Fix the memory leak issue of logid
> 
> Ziye Yang <ziye.yang@intel.com> writes:
> 
> > From: Ziye Yang <optimistyzy@gmail.com>
> >
> > This patch is used to fix the memory leak issue of logid.
> > We use the ASAN test in SPDK when intergrating DPDK and
> > find this memory leak issue.
> >
> > By the way, we also fix several missed function call of
> > rte_atomic32_clear.
> 
> This part I don't understand.  It should be a separate proposal.
> 
> > Signed-off-by: Ziye Yang <ziye.yang@intel.com>
> > ---
> >  lib/librte_eal/linuxapp/eal/eal.c | 11 +++++++----
> >  1 file changed, 7 insertions(+), 4 deletions(-)
> >
> > diff --git a/lib/librte_eal/linuxapp/eal/eal.c b/lib/librte_eal/linuxapp/eal/eal.c
> > index e59ac65..a5129e5 100644
> > --- a/lib/librte_eal/linuxapp/eal/eal.c
> > +++ b/lib/librte_eal/linuxapp/eal/eal.c
> > @@ -793,7 +793,8 @@ static void rte_eal_init_alert(const char *msg)
> >  	int i, fctret, ret;
> >  	pthread_t thread_id;
> >  	static rte_atomic32_t run_once = RTE_ATOMIC32_INIT(0);
> > -	const char *logid;
> > +	const char *p;
> > +	static char logid[PATH_MAX];
> 
> On a linux system, PATH_MAX is 4096, but an argument may be
> MAX_ARG_STRLEN which is significantly higher.

But we only interested here in 'basename(argv[0])'.
Surely it shouldn't be bigger than PATH_MAX unless something is terribly wrong here.

> 
> Have you thought about an alternative where you keep the strdup and add
> an atexit() handler to do the free?  Otherwise, you'll need to add code
> to check the string length as well and enforce some kind of size
> restriction.

snprintf() below will do a safe truncation for us.

> 
> >  	char cpuset[RTE_CPU_AFFINITY_STR_LEN];
> >  	char thread_name[RTE_MAX_THREAD_NAME_LEN];
> >
> > @@ -810,9 +811,8 @@ static void rte_eal_init_alert(const char *msg)
> >  		return -1;
> >  	}
> >
> > -	logid = strrchr(argv[0], '/');
> > -	logid = strdup(logid ? logid + 1: argv[0]);
> > -
> > +	p = strrchr(argv[0], '/');
> > +	snprintf(logid, sizeof(logid), "%s", (p ? p + 1 : argv[0]));
> >  	thread_id = pthread_self();
> >
> >  	eal_reset_internal_config(&internal_config);
> > @@ -823,6 +823,7 @@ static void rte_eal_init_alert(const char *msg)
> >  	if (rte_eal_cpu_init() < 0) {
> >  		rte_eal_init_alert("Cannot detect lcores.");
> >  		rte_errno = ENOTSUP;
> > +		rte_atomic32_clear(&run_once);
> 
> This is not recoverable.  No amount of retry will allow the user to
> re-init the eal - the hardware isn't supported.  Why clear the run_once
> flag?
> 
> >  		return -1;
> >  	}
> >
> > @@ -851,6 +852,7 @@ static void rte_eal_init_alert(const char *msg)
> >
> >  	if (rte_eal_intr_init() < 0) {
> >  		rte_eal_init_alert("Cannot init interrupt-handling thread\n");
> > +		rte_atomic32_clear(&run_once);
> 
> Arguable whether or not this is recoverable.  IIRC, the eal_intr_init
> spawns a thread - if it fails to spawn the likelihood is the process
> won't be able to continue.
> 
> >  		return -1;
> >  	}
> >
> > @@ -861,6 +863,7 @@ static void rte_eal_init_alert(const char *msg)
> >  		rte_eal_init_alert("failed to init mp channel\n");
> >  		if (rte_eal_process_type() == RTE_PROC_PRIMARY) {
> >  			rte_errno = EFAULT;
> > +			rte_atomic32_clear(&run_once);
> 
> This is also not recoverable.  Why clear the run_once flag?
> 
> >  			return -1;
> >  		}
> >  	}
  

"Ananyev, Konstantin" <konstantin.ananyev@intel.com> writes:

>> -----Original Message-----
>> From: Aaron Conole [mailto:aconole@redhat.com]
>> Sent: Tuesday, September 11, 2018 2:47 PM
>> To: Yang, Ziye <ziye.yang@intel.com>
>> Cc: dev@dpdk.org; Ananyev, Konstantin
>> <konstantin.ananyev@intel.com>; Ziye Yang <optimistyzy@gmail.com>
>> Subject: Re: [dpdk-dev] [PATCH v7] linuxapp, eal: Fix the memory leak issue of logid
>> 
>> Ziye Yang <ziye.yang@intel.com> writes:
>> 
>> > From: Ziye Yang <optimistyzy@gmail.com>
>> >
>> > This patch is used to fix the memory leak issue of logid.
>> > We use the ASAN test in SPDK when intergrating DPDK and
>> > find this memory leak issue.
>> >
>> > By the way, we also fix several missed function call of
>> > rte_atomic32_clear.
>> 
>> This part I don't understand.  It should be a separate proposal.
>> 
>> > Signed-off-by: Ziye Yang <ziye.yang@intel.com>
>> > ---
>> >  lib/librte_eal/linuxapp/eal/eal.c | 11 +++++++----
>> >  1 file changed, 7 insertions(+), 4 deletions(-)
>> >
>> > diff --git a/lib/librte_eal/linuxapp/eal/eal.c b/lib/librte_eal/linuxapp/eal/eal.c
>> > index e59ac65..a5129e5 100644
>> > --- a/lib/librte_eal/linuxapp/eal/eal.c
>> > +++ b/lib/librte_eal/linuxapp/eal/eal.c
>> > @@ -793,7 +793,8 @@ static void rte_eal_init_alert(const char *msg)
>> >  	int i, fctret, ret;
>> >  	pthread_t thread_id;
>> >  	static rte_atomic32_t run_once = RTE_ATOMIC32_INIT(0);
>> > -	const char *logid;
>> > +	const char *p;
>> > +	static char logid[PATH_MAX];
>> 
>> On a linux system, PATH_MAX is 4096, but an argument may be
>> MAX_ARG_STRLEN which is significantly higher.
>
> But we only interested here in 'basename(argv[0])'.
> Surely it shouldn't be bigger than PATH_MAX unless something is terribly wrong here.

The application has full control of what it passes into
EAL, but does it sanitize and scrub the arguments?  We make an
assumption that the argv,argc are direct from cmdline and are calls by
the user at a shell.  But nothing forces this to be true.

>> 
>> Have you thought about an alternative where you keep the strdup and add
>> an atexit() handler to do the free?  Otherwise, you'll need to add code
>> to check the string length as well and enforce some kind of size
>> restriction.
>
> snprintf() below will do a safe truncation for us.

Anyway, yes.  I completely glossed over it.

>> 
>> >  	char cpuset[RTE_CPU_AFFINITY_STR_LEN];
>> >  	char thread_name[RTE_MAX_THREAD_NAME_LEN];
>> >
>> > @@ -810,9 +811,8 @@ static void rte_eal_init_alert(const char *msg)
>> >  		return -1;
>> >  	}
>> >
>> > -	logid = strrchr(argv[0], '/');
>> > -	logid = strdup(logid ? logid + 1: argv[0]);
>> > -
>> > +	p = strrchr(argv[0], '/');
>> > +	snprintf(logid, sizeof(logid), "%s", (p ? p + 1 : argv[0]));
>> >  	thread_id = pthread_self();
>> >
>> >  	eal_reset_internal_config(&internal_config);
>> > @@ -823,6 +823,7 @@ static void rte_eal_init_alert(const char *msg)
>> >  	if (rte_eal_cpu_init() < 0) {
>> >  		rte_eal_init_alert("Cannot detect lcores.");
>> >  		rte_errno = ENOTSUP;
>> > +		rte_atomic32_clear(&run_once);
>> 
>> This is not recoverable.  No amount of retry will allow the user to
>> re-init the eal - the hardware isn't supported.  Why clear the run_once
>> flag?
>> 
>> >  		return -1;
>> >  	}
>> >
>> > @@ -851,6 +852,7 @@ static void rte_eal_init_alert(const char *msg)
>> >
>> >  	if (rte_eal_intr_init() < 0) {
>> >  		rte_eal_init_alert("Cannot init interrupt-handling thread\n");
>> > +		rte_atomic32_clear(&run_once);
>> 
>> Arguable whether or not this is recoverable.  IIRC, the eal_intr_init
>> spawns a thread - if it fails to spawn the likelihood is the process
>> won't be able to continue.
>> 
>> >  		return -1;
>> >  	}
>> >
>> > @@ -861,6 +863,7 @@ static void rte_eal_init_alert(const char *msg)
>> >  		rte_eal_init_alert("failed to init mp channel\n");
>> >  		if (rte_eal_process_type() == RTE_PROC_PRIMARY) {
>> >  			rte_errno = EFAULT;
>> > +			rte_atomic32_clear(&run_once);
>> 
>> This is also not recoverable.  Why clear the run_once flag?
>> 
>> >  			return -1;
>> >  		}
>> >  	}
  

On second thought - please just fold in the patch I
proposed back in July that I was told would be merged:

  http://mails.dpdk.org/archives/dev/2018-July/108445.html
  http://mails.dpdk.org/archives/dev/2018-August/109177.html

It doesn't include the issues calling rte_atomic32_clear (that I have
concerns about) and preserves an arbitrary length value being passed
through argv/argc.

:-)

-Aaron

"Ananyev, Konstantin" <konstantin.ananyev@intel.com> writes:

>> -----Original Message-----
>> From: Aaron Conole [mailto:aconole@redhat.com]
>> Sent: Tuesday, September 11, 2018 2:47 PM
>> To: Yang, Ziye <ziye.yang@intel.com>
>> Cc: dev@dpdk.org; Ananyev, Konstantin
>> <konstantin.ananyev@intel.com>; Ziye Yang <optimistyzy@gmail.com>
>> Subject: Re: [dpdk-dev] [PATCH v7] linuxapp, eal: Fix the memory
>> leak issue of logid
>> 
>> Ziye Yang <ziye.yang@intel.com> writes:
>> 
>> > From: Ziye Yang <optimistyzy@gmail.com>
>> >
>> > This patch is used to fix the memory leak issue of logid.
>> > We use the ASAN test in SPDK when intergrating DPDK and
>> > find this memory leak issue.
>> >
>> > By the way, we also fix several missed function call of
>> > rte_atomic32_clear.
>> 
>> This part I don't understand.  It should be a separate proposal.
>> 
>> > Signed-off-by: Ziye Yang <ziye.yang@intel.com>
>> > ---
>> >  lib/librte_eal/linuxapp/eal/eal.c | 11 +++++++----
>> >  1 file changed, 7 insertions(+), 4 deletions(-)
>> >
>> > diff --git a/lib/librte_eal/linuxapp/eal/eal.c b/lib/librte_eal/linuxapp/eal/eal.c
>> > index e59ac65..a5129e5 100644
>> > --- a/lib/librte_eal/linuxapp/eal/eal.c
>> > +++ b/lib/librte_eal/linuxapp/eal/eal.c
>> > @@ -793,7 +793,8 @@ static void rte_eal_init_alert(const char *msg)
>> >  	int i, fctret, ret;
>> >  	pthread_t thread_id;
>> >  	static rte_atomic32_t run_once = RTE_ATOMIC32_INIT(0);
>> > -	const char *logid;
>> > +	const char *p;
>> > +	static char logid[PATH_MAX];
>> 
>> On a linux system, PATH_MAX is 4096, but an argument may be
>> MAX_ARG_STRLEN which is significantly higher.
>
> But we only interested here in 'basename(argv[0])'.
> Surely it shouldn't be bigger than PATH_MAX unless something is
> terribly wrong here.
>
>> 
>> Have you thought about an alternative where you keep the strdup and add
>> an atexit() handler to do the free?  Otherwise, you'll need to add code
>> to check the string length as well and enforce some kind of size
>> restriction.
>
> snprintf() below will do a safe truncation for us.
>
>> 
>> >  	char cpuset[RTE_CPU_AFFINITY_STR_LEN];
>> >  	char thread_name[RTE_MAX_THREAD_NAME_LEN];
>> >
>> > @@ -810,9 +811,8 @@ static void rte_eal_init_alert(const char *msg)
>> >  		return -1;
>> >  	}
>> >
>> > -	logid = strrchr(argv[0], '/');
>> > -	logid = strdup(logid ? logid + 1: argv[0]);
>> > -
>> > +	p = strrchr(argv[0], '/');
>> > +	snprintf(logid, sizeof(logid), "%s", (p ? p + 1 : argv[0]));
>> >  	thread_id = pthread_self();
>> >
>> >  	eal_reset_internal_config(&internal_config);
>> > @@ -823,6 +823,7 @@ static void rte_eal_init_alert(const char *msg)
>> >  	if (rte_eal_cpu_init() < 0) {
>> >  		rte_eal_init_alert("Cannot detect lcores.");
>> >  		rte_errno = ENOTSUP;
>> > +		rte_atomic32_clear(&run_once);
>> 
>> This is not recoverable.  No amount of retry will allow the user to
>> re-init the eal - the hardware isn't supported.  Why clear the run_once
>> flag?
>> 
>> >  		return -1;
>> >  	}
>> >
>> > @@ -851,6 +852,7 @@ static void rte_eal_init_alert(const char *msg)
>> >
>> >  	if (rte_eal_intr_init() < 0) {
>> >  		rte_eal_init_alert("Cannot init interrupt-handling thread\n");
>> > +		rte_atomic32_clear(&run_once);
>> 
>> Arguable whether or not this is recoverable.  IIRC, the eal_intr_init
>> spawns a thread - if it fails to spawn the likelihood is the process
>> won't be able to continue.
>> 
>> >  		return -1;
>> >  	}
>> >
>> > @@ -861,6 +863,7 @@ static void rte_eal_init_alert(const char *msg)
>> >  		rte_eal_init_alert("failed to init mp channel\n");
>> >  		if (rte_eal_process_type() == RTE_PROC_PRIMARY) {
>> >  			rte_errno = EFAULT;
>> > +			rte_atomic32_clear(&run_once);
>> 
>> This is also not recoverable.  Why clear the run_once flag?
>> 
>> >  			return -1;
>> >  		}
>> >  	}