[v5,03/11] dataplane: add host memory mapping code

The data plane thread needs to map guest physical addresses to host
pointers.  Normally this is done with cpu_physical_memory_map() but the
function assumes the global mutex is held.  The data plane thread does
not touch the global mutex and therefore needs a thread-safe memory
mapping mechanism.

Hostmem registers a MemoryListener similar to how vhost collects and
pushes memory region information into the kernel.  There is a
fine-grained lock on the regions list which is held during lookup and
when installing a new regions list.

When the physical memory map changes the MemoryListener callbacks are
invoked.  They build up a new list of memory regions which is finally
installed when the list has been completed.

Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
---
 hw/dataplane/Makefile.objs |   3 +
 hw/dataplane/hostmem.c     | 173 +++++++++++++++++++++++++++++++++++++++++++++
 hw/dataplane/hostmem.h     |  57 +++++++++++++++
 3 files changed, 233 insertions(+)
 create mode 100644 hw/dataplane/Makefile.objs
 create mode 100644 hw/dataplane/hostmem.c
 create mode 100644 hw/dataplane/hostmem.h

On Thu, Dec 6, 2012 at 4:47 AM, Stefan Hajnoczi <stefanha@redhat.com> wrote:
> The data plane thread needs to map guest physical addresses to host
> pointers.  Normally this is done with cpu_physical_memory_map() but the
> function assumes the global mutex is held.  The data plane thread does
> not touch the global mutex and therefore needs a thread-safe memory
> mapping mechanism.
>
> Hostmem registers a MemoryListener similar to how vhost collects and
> pushes memory region information into the kernel.  There is a
> fine-grained lock on the regions list which is held during lookup and
> when installing a new regions list.
>
> When the physical memory map changes the MemoryListener callbacks are
> invoked.  They build up a new list of memory regions which is finally
> installed when the list has been completed.
>
> Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
> ---
>  hw/dataplane/Makefile.objs |   3 +
>  hw/dataplane/hostmem.c     | 173 +++++++++++++++++++++++++++++++++++++++++++++
>  hw/dataplane/hostmem.h     |  57 +++++++++++++++
>  3 files changed, 233 insertions(+)
>  create mode 100644 hw/dataplane/Makefile.objs
>  create mode 100644 hw/dataplane/hostmem.c
>  create mode 100644 hw/dataplane/hostmem.h
>
> diff --git a/hw/dataplane/Makefile.objs b/hw/dataplane/Makefile.objs
> new file mode 100644
> index 0000000..8c8dea1
> --- /dev/null
> +++ b/hw/dataplane/Makefile.objs
> @@ -0,0 +1,3 @@
> +ifeq ($(CONFIG_VIRTIO), y)
> +common-obj-$(CONFIG_VIRTIO_BLK_DATA_PLANE) += hostmem.o
> +endif
> diff --git a/hw/dataplane/hostmem.c b/hw/dataplane/hostmem.c
> new file mode 100644
> index 0000000..ae92ca2
> --- /dev/null
> +++ b/hw/dataplane/hostmem.c
> @@ -0,0 +1,173 @@
> +/*
> + * Thread-safe guest to host memory mapping
> + *
> + * Copyright 2012 Red Hat, Inc. and/or its affiliates
> + *
> + * Authors:
> + *   Stefan Hajnoczi <stefanha@redhat.com>
> + *
> + * This work is licensed under the terms of the GNU GPL, version 2 or later.
> + * See the COPYING file in the top-level directory.
> + *
> + */
> +
> +#include "exec-memory.h"
> +#include "hostmem.h"
> +
> +static int hostmem_lookup_cmp(const void *phys_, const void *region_)
> +{
> +    hwaddr phys = *(const hwaddr *)phys_;
> +    const HostmemRegion *region = region_;
> +
> +    if (phys < region->guest_addr) {
> +        return -1;
> +    } else if (phys >= region->guest_addr + region->size) {
> +        return 1;
> +    } else {
> +        return 0;
> +    }
> +}
> +
> +/**
> + * Map guest physical address to host pointer
> + */
> +void *hostmem_lookup(Hostmem *hostmem, hwaddr phys, hwaddr len, bool is_write)
> +{
> +    HostmemRegion *region;
> +    void *host_addr = NULL;
> +    hwaddr offset_within_region;
> +
> +    qemu_mutex_lock(&hostmem->current_regions_lock);
> +    region = bsearch(&phys, hostmem->current_regions,
> +                     hostmem->num_current_regions,
> +                     sizeof(hostmem->current_regions[0]),
> +                     hostmem_lookup_cmp);
> +    if (!region) {
> +        goto out;
> +    }
> +    if (is_write && region->readonly) {
> +        goto out;
> +    }
> +    offset_within_region = phys - region->guest_addr;
> +    if (offset_within_region + len <= region->size) {
> +        host_addr = region->host_addr + offset_within_region;
> +    }
> +out:
> +    qemu_mutex_unlock(&hostmem->current_regions_lock);
> +
> +    return host_addr;
> +}
> +
> +/**
> + * Install new regions list
> + */
> +static void hostmem_listener_commit(MemoryListener *listener)
> +{
> +    Hostmem *hostmem = container_of(listener, Hostmem, listener);
> +
> +    qemu_mutex_lock(&hostmem->current_regions_lock);
> +    g_free(hostmem->current_regions);
> +    hostmem->current_regions = hostmem->new_regions;
> +    hostmem->num_current_regions = hostmem->num_new_regions;
> +    qemu_mutex_unlock(&hostmem->current_regions_lock);
> +
> +    /* Reset new regions list */
> +    hostmem->new_regions = NULL;
> +    hostmem->num_new_regions = 0;
> +}
> +
> +/**
> + * Add a MemoryRegionSection to the new regions list
> + */
> +static void hostmem_append_new_region(Hostmem *hostmem,
> +                                      MemoryRegionSection *section)
> +{
> +    void *ram_ptr = memory_region_get_ram_ptr(section->mr);
> +    size_t num = hostmem->num_new_regions;
> +    size_t new_size = (num + 1) * sizeof(hostmem->new_regions[0]);
> +
> +    hostmem->new_regions = g_realloc(hostmem->new_regions, new_size);
> +    hostmem->new_regions[num] = (HostmemRegion){
> +        .host_addr = ram_ptr + section->offset_within_region,
> +        .guest_addr = section->offset_within_address_space,
> +        .size = section->size,
> +        .readonly = section->readonly,
> +    };
> +    hostmem->num_new_regions++;
> +}
> +
> +static void hostmem_listener_append_region(MemoryListener *listener,
> +                                           MemoryRegionSection *section)
> +{
> +    Hostmem *hostmem = container_of(listener, Hostmem, listener);
> +
> +    /* Ignore non-RAM regions, we may not be able to map them */
> +    if (!memory_region_is_ram(section->mr)) {
> +        return;
> +    }
> +
> +    /* Ignore regions with dirty logging, we cannot mark them dirty */
> +    if (memory_region_is_logging(section->mr)) {
> +        return;
> +    }
> +
> +    hostmem_append_new_region(hostmem, section);
> +}
> +
> +/* We don't implement most MemoryListener callbacks, use these nop stubs */
> +static void hostmem_listener_dummy(MemoryListener *listener)
> +{
> +}
> +
> +static void hostmem_listener_section_dummy(MemoryListener *listener,
> +                                           MemoryRegionSection *section)
> +{
> +}
> +
> +static void hostmem_listener_eventfd_dummy(MemoryListener *listener,
> +                                           MemoryRegionSection *section,
> +                                           bool match_data, uint64_t data,
> +                                           EventNotifier *e)
> +{
> +}
> +
> +static void hostmem_listener_coalesced_mmio_dummy(MemoryListener *listener,
> +                                                  MemoryRegionSection *section,
> +                                                  hwaddr addr, hwaddr len)
> +{
> +}
> +
> +void hostmem_init(Hostmem *hostmem)
> +{
> +    memset(hostmem, 0, sizeof(*hostmem));
> +
> +    hostmem->listener = (MemoryListener){
> +        .begin = hostmem_listener_dummy,
> +        .commit = hostmem_listener_commit,

I think, here, if we sync on big lock, and flush out dangling pointer
in data-plane thread, then we can survive from the unplug.
> +        .region_add = hostmem_listener_append_region,
> +        .region_del = hostmem_listener_section_dummy,

And here we should remove the corresponding info in hostmem

Regards,
Pingfan
> +        .region_nop = hostmem_listener_append_region,
> +        .log_start = hostmem_listener_section_dummy,
> +        .log_stop = hostmem_listener_section_dummy,
> +        .log_sync = hostmem_listener_section_dummy,
> +        .log_global_start = hostmem_listener_dummy,
> +        .log_global_stop = hostmem_listener_dummy,
> +        .eventfd_add = hostmem_listener_eventfd_dummy,
> +        .eventfd_del = hostmem_listener_eventfd_dummy,
> +        .coalesced_mmio_add = hostmem_listener_coalesced_mmio_dummy,
> +        .coalesced_mmio_del = hostmem_listener_coalesced_mmio_dummy,
> +        .priority = 10,
> +    };
> +
> +    memory_listener_register(&hostmem->listener, &address_space_memory);
> +    if (hostmem->num_new_regions > 0) {
> +        hostmem_listener_commit(&hostmem->listener);
> +    }
> +}
> +
> +void hostmem_finalize(Hostmem *hostmem)
> +{
> +    memory_listener_unregister(&hostmem->listener);
> +    g_free(hostmem->new_regions);
> +    g_free(hostmem->current_regions);
> +}
> diff --git a/hw/dataplane/hostmem.h b/hw/dataplane/hostmem.h
> new file mode 100644
> index 0000000..6d87841
> --- /dev/null
> +++ b/hw/dataplane/hostmem.h
> @@ -0,0 +1,57 @@
> +/*
> + * Thread-safe guest to host memory mapping
> + *
> + * Copyright 2012 Red Hat, Inc. and/or its affiliates
> + *
> + * Authors:
> + *   Stefan Hajnoczi <stefanha@redhat.com>
> + *
> + * This work is licensed under the terms of the GNU GPL, version 2 or later.
> + * See the COPYING file in the top-level directory.
> + *
> + */
> +
> +#ifndef HOSTMEM_H
> +#define HOSTMEM_H
> +
> +#include "memory.h"
> +#include "qemu-thread.h"
> +
> +typedef struct {
> +    void *host_addr;
> +    hwaddr guest_addr;
> +    uint64_t size;
> +    bool readonly;
> +} HostmemRegion;
> +
> +typedef struct {
> +    /* The listener is invoked when regions change and a new list of regions is
> +     * built up completely before they are installed.
> +     */
> +    MemoryListener listener;
> +    HostmemRegion *new_regions;
> +    size_t num_new_regions;
> +
> +    /* Current regions are accessed from multiple threads either to lookup
> +     * addresses or to install a new list of regions.  The lock protects the
> +     * pointer and the regions.
> +     */
> +    QemuMutex current_regions_lock;
> +    HostmemRegion *current_regions;
> +    size_t num_current_regions;
> +} Hostmem;
> +
> +void hostmem_init(Hostmem *hostmem);
> +void hostmem_finalize(Hostmem *hostmem);
> +
> +/**
> + * Map a guest physical address to a pointer
> + *
> + * Note that there is map/unmap mechanism here.  The caller must ensure that
> + * mapped memory is no longer used across events like hot memory unplug.  This
> + * can be done with other mechanisms like bdrv_drain_all() that quiesce
> + * in-flight I/O.
> + */
> +void *hostmem_lookup(Hostmem *hostmem, hwaddr phys, hwaddr len, bool is_write);
> +
> +#endif /* HOSTMEM_H */
> --
> 1.8.0.1
>
>

On Sun, Dec 09, 2012 at 12:02:52PM +0800, liu ping fan wrote:
> On Thu, Dec 6, 2012 at 4:47 AM, Stefan Hajnoczi <stefanha@redhat.com> wrote:
> > +void hostmem_init(Hostmem *hostmem)
> > +{
> > +    memset(hostmem, 0, sizeof(*hostmem));
> > +
> > +    hostmem->listener = (MemoryListener){
> > +        .begin = hostmem_listener_dummy,
> > +        .commit = hostmem_listener_commit,
> 
> I think, here, if we sync on big lock, and flush out dangling pointer
> in data-plane thread, then we can survive from the unplug.

Hot unplug support requires that the data plane thread completes all
requests and doesn't process any new requests until the critical region
completes (e.g. hot memory unplug).

vm_stop() + bdrv_drain_all() achieves this:
1. vcpus are stopped so no new requests can be submitted by the guest.
2. bdrv_drain_all() completes all Linux AIO requests so we're no longer
   accessing guest memory.

vcpus should be enabled again after hot unplug.

> > +        .region_add = hostmem_listener_append_region,
> > +        .region_del = hostmem_listener_section_dummy,
> 
> And here we should remove the corresponding info in hostmem

.region_del() is not necessary because we rebuild a fresh memory region
list.  We never update the memory region list once it has been
installed.

This means the .region_add() and .region_nop() information is enough to
build a fresh list from scratch.

Stefan