[dpdk-stable] [PATCH] malloc: notify primary process about hotplug in secondary

[dpdk-stable] [PATCH] malloc: notify primary process about hotplug in secondary

[Seth Howell]

When secondary process hotplugs memory, it sends a request
to primary, which then performs the real mmap() and sends
sync requests to all secondary processes. Upon receiving
such sync request, each secondary process will notify the
upper layers of hotplugged memory (and will call all
locally registered event callbacks).

In the end we'll end up with memory event callbacks fired
in all the processes except the primary, which is a bug.

This gets critical if memory is hotplugged while a VFIO
device is attached, as the VFIO memory registration -
which is done from a memory event callback present in the
primary process only - is never called.

After this patch, a primary process fires memory event
callbacks before secondary processes start their
synchronizations - both for hotplug and hotremove.

Fixes: 07dcbfe0101f ("malloc: support multiprocess memory hotplug")

Signed-off-by: Seth Howell <seth.howell@intel.com>
Signed-off-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
---
 lib/librte_eal/common/malloc_mp.c | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/lib/librte_eal/common/malloc_mp.c b/lib/librte_eal/common/malloc_mp.c
index 5f2d4e0be..f3a13353b 100644
--- a/lib/librte_eal/common/malloc_mp.c
+++ b/lib/librte_eal/common/malloc_mp.c
@@ -209,6 +209,8 @@ handle_alloc_request(const struct malloc_mp_req *m,
 
 	map_addr = ms[0]->addr;
 
+	eal_memalloc_mem_event_notify(RTE_MEM_EVENT_ALLOC, map_addr, alloc_sz);
+
 	/* we have succeeded in allocating memory, but we still need to sync
 	 * with other processes. however, since DPDK IPC is single-threaded, we
 	 * send an asynchronous request and exit this callback.
@@ -258,6 +260,9 @@ handle_request(const struct rte_mp_msg *msg, const void *peer __rte_unused)
 	if (m->t == REQ_TYPE_ALLOC) {
 		ret = handle_alloc_request(m, entry);
 	} else if (m->t == REQ_TYPE_FREE) {
+		eal_memalloc_mem_event_notify(RTE_MEM_EVENT_FREE,
+				m->free_req.addr, m->free_req.len);
+
 		ret = malloc_heap_free_pages(m->free_req.addr,
 				m->free_req.len);
 	} else {
@@ -436,6 +441,9 @@ handle_sync_response(const struct rte_mp_msg *request,
 		memset(&rb_msg, 0, sizeof(rb_msg));
 
 		/* we've failed to sync, so do a rollback */
+		eal_memalloc_mem_event_notify(RTE_MEM_EVENT_FREE,
+				state->map_addr, state->map_len);
+
 		rollback_expand_heap(state->ms, state->ms_len, state->elem,
 				state->map_addr, state->map_len);
 
-- 
2.17.2

[dpdk-stable] [PATCH v2] malloc: notify primary process about hotplug in secondary

[Seth Howell]

When secondary process hotplugs memory, it sends a request
to primary, which then performs the real mmap() and sends
sync requests to all secondary processes. Upon receiving
such sync request, each secondary process will notify the
upper layers of hotplugged memory (and will call all
locally registered event callbacks).

In the end we'll end up with memory event callbacks fired
in all the processes except the primary, which is a bug.

This gets critical if memory is hotplugged while a VFIO
device is attached, as the VFIO memory registration -
which is done from a memory event callback present in the
primary process only - is never called.

After this patch, a primary process fires memory event
callbacks before secondary processes start their
synchronizations - both for hotplug and hotremove.

Fixes: 07dcbfe0101f ("malloc: support multiprocess memory hotplug")

Signed-off-by: Seth Howell <seth.howell@intel.com>
Signed-off-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
---
 lib/librte_eal/common/malloc_mp.c | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/lib/librte_eal/common/malloc_mp.c b/lib/librte_eal/common/malloc_mp.c
index 5f2d4e0be..f3a13353b 100644
--- a/lib/librte_eal/common/malloc_mp.c
+++ b/lib/librte_eal/common/malloc_mp.c
@@ -209,6 +209,8 @@ handle_alloc_request(const struct malloc_mp_req *m,
 
 	map_addr = ms[0]->addr;
 
+	eal_memalloc_mem_event_notify(RTE_MEM_EVENT_ALLOC, map_addr, alloc_sz);
+
 	/* we have succeeded in allocating memory, but we still need to sync
 	 * with other processes. however, since DPDK IPC is single-threaded, we
 	 * send an asynchronous request and exit this callback.
@@ -258,6 +260,9 @@ handle_request(const struct rte_mp_msg *msg, const void *peer __rte_unused)
 	if (m->t == REQ_TYPE_ALLOC) {
 		ret = handle_alloc_request(m, entry);
 	} else if (m->t == REQ_TYPE_FREE) {
+		eal_memalloc_mem_event_notify(RTE_MEM_EVENT_FREE,
+				m->free_req.addr, m->free_req.len);
+
 		ret = malloc_heap_free_pages(m->free_req.addr,
 				m->free_req.len);
 	} else {
@@ -436,6 +441,9 @@ handle_sync_response(const struct rte_mp_msg *request,
 		memset(&rb_msg, 0, sizeof(rb_msg));
 
 		/* we've failed to sync, so do a rollback */
+		eal_memalloc_mem_event_notify(RTE_MEM_EVENT_FREE,
+				state->map_addr, state->map_len);
+
 		rollback_expand_heap(state->ms, state->ms_len, state->elem,
 				state->map_addr, state->map_len);
 
-- 
2.17.2

Re: [dpdk-stable] [PATCH v2] malloc: notify primary process about hotplug in secondary

[Stojaczyk, Dariusz]

Hi Kevin, is the merge window for DPDK 18.08.1 and 18.05.2 still open? This fix is critical for multi-process memory hotplug and you might want to pull it in.
D.

> -----Original Message-----
> From: Howell, Seth
> Sent: Friday, December 7, 2018 9:11 PM
> To: Burakov, Anatoly <anatoly.burakov@intel.com>
> Cc: dev@dpdk.org; stable@dpdk.org; Howell, Seth
> <seth.howell@intel.com>; Stojaczyk, Dariusz <dariusz.stojaczyk@intel.com>
> Subject: [PATCH v2] malloc: notify primary process about hotplug in
> secondary
> 
> When secondary process hotplugs memory, it sends a request
> to primary, which then performs the real mmap() and sends
> sync requests to all secondary processes. Upon receiving
> such sync request, each secondary process will notify the
> upper layers of hotplugged memory (and will call all
> locally registered event callbacks).
> 
> In the end we'll end up with memory event callbacks fired
> in all the processes except the primary, which is a bug.
> 
> This gets critical if memory is hotplugged while a VFIO
> device is attached, as the VFIO memory registration -
> which is done from a memory event callback present in the
> primary process only - is never called.
> 
> After this patch, a primary process fires memory event
> callbacks before secondary processes start their
> synchronizations - both for hotplug and hotremove.
> 
> Fixes: 07dcbfe0101f ("malloc: support multiprocess memory hotplug")
> 
> Signed-off-by: Seth Howell <seth.howell@intel.com>
> Signed-off-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
> ---
>  lib/librte_eal/common/malloc_mp.c | 8 ++++++++
>  1 file changed, 8 insertions(+)
> 
> diff --git a/lib/librte_eal/common/malloc_mp.c
> b/lib/librte_eal/common/malloc_mp.c
> index 5f2d4e0be..f3a13353b 100644
> --- a/lib/librte_eal/common/malloc_mp.c
> +++ b/lib/librte_eal/common/malloc_mp.c
> @@ -209,6 +209,8 @@ handle_alloc_request(const struct malloc_mp_req
> *m,
> 
>  	map_addr = ms[0]->addr;
> 
> +	eal_memalloc_mem_event_notify(RTE_MEM_EVENT_ALLOC,
> map_addr, alloc_sz);
> +
>  	/* we have succeeded in allocating memory, but we still need to sync
>  	 * with other processes. however, since DPDK IPC is single-threaded,
> we
>  	 * send an asynchronous request and exit this callback.
> @@ -258,6 +260,9 @@ handle_request(const struct rte_mp_msg *msg,
> const void *peer __rte_unused)
>  	if (m->t == REQ_TYPE_ALLOC) {
>  		ret = handle_alloc_request(m, entry);
>  	} else if (m->t == REQ_TYPE_FREE) {
> +		eal_memalloc_mem_event_notify(RTE_MEM_EVENT_FREE,
> +				m->free_req.addr, m->free_req.len);
> +
>  		ret = malloc_heap_free_pages(m->free_req.addr,
>  				m->free_req.len);
>  	} else {
> @@ -436,6 +441,9 @@ handle_sync_response(const struct rte_mp_msg
> *request,
>  		memset(&rb_msg, 0, sizeof(rb_msg));
> 
>  		/* we've failed to sync, so do a rollback */
> +		eal_memalloc_mem_event_notify(RTE_MEM_EVENT_FREE,
> +				state->map_addr, state->map_len);
> +
>  		rollback_expand_heap(state->ms, state->ms_len, state-
> >elem,
>  				state->map_addr, state->map_len);
> 
> --
> 2.17.2

Re: [dpdk-stable] [PATCH v2] malloc: notify primary process about hotplug in secondary

[Kevin Traynor]

On 12/07/2018 12:30 PM, Stojaczyk, Dariusz wrote:
> Hi Kevin, is the merge window for DPDK 18.08.1 and 18.05.2 still open? This fix is critical for multi-process memory hotplug and you might want to pull it in.
> D.
> 

Hi Dariusz,

I can still take patches for 18.08.1 but the patch must be applied in
the main tree before it can be backported. DPDK 18.05 is not maintained
anymore.

>> -----Original Message-----
>> From: Howell, Seth
>> Sent: Friday, December 7, 2018 9:11 PM
>> To: Burakov, Anatoly <anatoly.burakov@intel.com>
>> Cc: dev@dpdk.org; stable@dpdk.org; Howell, Seth
>> <seth.howell@intel.com>; Stojaczyk, Dariusz <dariusz.stojaczyk@intel.com>
>> Subject: [PATCH v2] malloc: notify primary process about hotplug in
>> secondary
>>
>> When secondary process hotplugs memory, it sends a request
>> to primary, which then performs the real mmap() and sends
>> sync requests to all secondary processes. Upon receiving
>> such sync request, each secondary process will notify the
>> upper layers of hotplugged memory (and will call all
>> locally registered event callbacks).
>>
>> In the end we'll end up with memory event callbacks fired
>> in all the processes except the primary, which is a bug.
>>
>> This gets critical if memory is hotplugged while a VFIO
>> device is attached, as the VFIO memory registration -
>> which is done from a memory event callback present in the
>> primary process only - is never called.
>>
>> After this patch, a primary process fires memory event
>> callbacks before secondary processes start their
>> synchronizations - both for hotplug and hotremove.
>>
>> Fixes: 07dcbfe0101f ("malloc: support multiprocess memory hotplug")

In this case I know because you mailed, but for future, 'Cc:
stable@dpdk.org' tag should also be inserted here in the commit message
so it can be found by scripts.

Kevin.

>>
>> Signed-off-by: Seth Howell <seth.howell@intel.com>
>> Signed-off-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
>> ---
>>  lib/librte_eal/common/malloc_mp.c | 8 ++++++++
>>  1 file changed, 8 insertions(+)
>>
>> diff --git a/lib/librte_eal/common/malloc_mp.c
>> b/lib/librte_eal/common/malloc_mp.c
>> index 5f2d4e0be..f3a13353b 100644
>> --- a/lib/librte_eal/common/malloc_mp.c
>> +++ b/lib/librte_eal/common/malloc_mp.c
>> @@ -209,6 +209,8 @@ handle_alloc_request(const struct malloc_mp_req
>> *m,
>>
>>  	map_addr = ms[0]->addr;
>>
>> +	eal_memalloc_mem_event_notify(RTE_MEM_EVENT_ALLOC,
>> map_addr, alloc_sz);
>> +
>>  	/* we have succeeded in allocating memory, but we still need to sync
>>  	 * with other processes. however, since DPDK IPC is single-threaded,
>> we
>>  	 * send an asynchronous request and exit this callback.
>> @@ -258,6 +260,9 @@ handle_request(const struct rte_mp_msg *msg,
>> const void *peer __rte_unused)
>>  	if (m->t == REQ_TYPE_ALLOC) {
>>  		ret = handle_alloc_request(m, entry);
>>  	} else if (m->t == REQ_TYPE_FREE) {
>> +		eal_memalloc_mem_event_notify(RTE_MEM_EVENT_FREE,
>> +				m->free_req.addr, m->free_req.len);
>> +
>>  		ret = malloc_heap_free_pages(m->free_req.addr,
>>  				m->free_req.len);
>>  	} else {
>> @@ -436,6 +441,9 @@ handle_sync_response(const struct rte_mp_msg
>> *request,
>>  		memset(&rb_msg, 0, sizeof(rb_msg));
>>
>>  		/* we've failed to sync, so do a rollback */
>> +		eal_memalloc_mem_event_notify(RTE_MEM_EVENT_FREE,
>> +				state->map_addr, state->map_len);
>> +
>>  		rollback_expand_heap(state->ms, state->ms_len, state-
>>> elem,
>>  				state->map_addr, state->map_len);
>>
>> --
>> 2.17.2
> 

Re: [dpdk-stable] [PATCH v2] malloc: notify primary process about hotplug in secondary

[Burakov, Anatoly]

On 07-Dec-18 8:10 PM, Seth Howell wrote:
> When secondary process hotplugs memory, it sends a request
> to primary, which then performs the real mmap() and sends
> sync requests to all secondary processes. Upon receiving
> such sync request, each secondary process will notify the
> upper layers of hotplugged memory (and will call all
> locally registered event callbacks).
> 
> In the end we'll end up with memory event callbacks fired
> in all the processes except the primary, which is a bug.
> 
> This gets critical if memory is hotplugged while a VFIO
> device is attached, as the VFIO memory registration -
> which is done from a memory event callback present in the
> primary process only - is never called.
> 
> After this patch, a primary process fires memory event
> callbacks before secondary processes start their
> synchronizations - both for hotplug and hotremove.
> 
> Fixes: 07dcbfe0101f ("malloc: support multiprocess memory hotplug")
> 
> Signed-off-by: Seth Howell <seth.howell@intel.com>
> Signed-off-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
> ---

Lost my review tag...

Reviewed-by: Anatoly Burakov <anatoly.burakov@intel.com>

-- 
Thanks,
Anatoly

Re: [dpdk-stable] [PATCH v2] malloc: notify primary process about hotplug in secondary

[Thomas Monjalon]

07/12/2018 21:30, Stojaczyk, Dariusz:
> Hi Kevin, is the merge window for DPDK 18.08.1 and 18.05.2 still open? This fix is critical for multi-process memory hotplug and you might want to pull it in.

First thing to do is to make sure stable@dpdk.org is Cc'ed
in the patch, below Fixes:.


> > -----Original Message-----
> > From: Howell, Seth
> > Sent: Friday, December 7, 2018 9:11 PM
> > To: Burakov, Anatoly <anatoly.burakov@intel.com>
> > Cc: dev@dpdk.org; stable@dpdk.org; Howell, Seth
> > <seth.howell@intel.com>; Stojaczyk, Dariusz <dariusz.stojaczyk@intel.com>
> > Subject: [PATCH v2] malloc: notify primary process about hotplug in
> > secondary
> > 
> > When secondary process hotplugs memory, it sends a request
> > to primary, which then performs the real mmap() and sends
> > sync requests to all secondary processes. Upon receiving
> > such sync request, each secondary process will notify the
> > upper layers of hotplugged memory (and will call all
> > locally registered event callbacks).
> > 
> > In the end we'll end up with memory event callbacks fired
> > in all the processes except the primary, which is a bug.
> > 
> > This gets critical if memory is hotplugged while a VFIO
> > device is attached, as the VFIO memory registration -
> > which is done from a memory event callback present in the
> > primary process only - is never called.
> > 
> > After this patch, a primary process fires memory event
> > callbacks before secondary processes start their
> > synchronizations - both for hotplug and hotremove.
> > 
> > Fixes: 07dcbfe0101f ("malloc: support multiprocess memory hotplug")
> > 
> > Signed-off-by: Seth Howell <seth.howell@intel.com>
> > Signed-off-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
> > ---
> >  lib/librte_eal/common/malloc_mp.c | 8 ++++++++
> >  1 file changed, 8 insertions(+)
> > 
> > diff --git a/lib/librte_eal/common/malloc_mp.c
> > b/lib/librte_eal/common/malloc_mp.c
> > index 5f2d4e0be..f3a13353b 100644
> > --- a/lib/librte_eal/common/malloc_mp.c
> > +++ b/lib/librte_eal/common/malloc_mp.c
> > @@ -209,6 +209,8 @@ handle_alloc_request(const struct malloc_mp_req
> > *m,
> > 
> >  	map_addr = ms[0]->addr;
> > 
> > +	eal_memalloc_mem_event_notify(RTE_MEM_EVENT_ALLOC,
> > map_addr, alloc_sz);
> > +
> >  	/* we have succeeded in allocating memory, but we still need to sync
> >  	 * with other processes. however, since DPDK IPC is single-threaded,
> > we
> >  	 * send an asynchronous request and exit this callback.
> > @@ -258,6 +260,9 @@ handle_request(const struct rte_mp_msg *msg,
> > const void *peer __rte_unused)
> >  	if (m->t == REQ_TYPE_ALLOC) {
> >  		ret = handle_alloc_request(m, entry);
> >  	} else if (m->t == REQ_TYPE_FREE) {
> > +		eal_memalloc_mem_event_notify(RTE_MEM_EVENT_FREE,
> > +				m->free_req.addr, m->free_req.len);
> > +
> >  		ret = malloc_heap_free_pages(m->free_req.addr,
> >  				m->free_req.len);
> >  	} else {
> > @@ -436,6 +441,9 @@ handle_sync_response(const struct rte_mp_msg
> > *request,
> >  		memset(&rb_msg, 0, sizeof(rb_msg));
> > 
> >  		/* we've failed to sync, so do a rollback */
> > +		eal_memalloc_mem_event_notify(RTE_MEM_EVENT_FREE,
> > +				state->map_addr, state->map_len);
> > +
> >  		rollback_expand_heap(state->ms, state->ms_len, state-
> > >elem,
> >  				state->map_addr, state->map_len);
> > 
> > --
> > 2.17.2
> 

Re: [dpdk-stable] [PATCH v2] malloc: notify primary process about hotplug in secondary

[Thomas Monjalon]

10/12/2018 11:49, Burakov, Anatoly:
> On 07-Dec-18 8:10 PM, Seth Howell wrote:
> > When secondary process hotplugs memory, it sends a request
> > to primary, which then performs the real mmap() and sends
> > sync requests to all secondary processes. Upon receiving
> > such sync request, each secondary process will notify the
> > upper layers of hotplugged memory (and will call all
> > locally registered event callbacks).
> > 
> > In the end we'll end up with memory event callbacks fired
> > in all the processes except the primary, which is a bug.
> > 
> > This gets critical if memory is hotplugged while a VFIO
> > device is attached, as the VFIO memory registration -
> > which is done from a memory event callback present in the
> > primary process only - is never called.
> > 
> > After this patch, a primary process fires memory event
> > callbacks before secondary processes start their
> > synchronizations - both for hotplug and hotremove.
> > 
> > Fixes: 07dcbfe0101f ("malloc: support multiprocess memory hotplug")
> > 
> > Signed-off-by: Seth Howell <seth.howell@intel.com>
> > Signed-off-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
> > ---
> 
> Lost my review tag...
> 
> Reviewed-by: Anatoly Burakov <anatoly.burakov@intel.com>

+Cc: stable@dpdk.org

Applied, thanks