qemu-devel.nongnu.org archive mirror
 help / color / mirror / Atom feed
From: Paolo Bonzini <pbonzini@redhat.com>
To: Liu Ping Fan <qemulist@gmail.com>
Cc: Peter Maydell <peter.maydell@linaro.org>,
	Anthony Liguori <anthony@codemonkey.ws>,
	"Michael S. Tsirkin" <mst@redhat.com>,
	Jan Kiszka <jan.kiszka@siemens.com>,
	qemu-devel@nongnu.org, Stefan Hajnoczi <stefanha@redhat.com>
Subject: Re: [Qemu-devel] [RFC PATCH 2/2] mem: prepare address_space listener rcu style
Date: Mon, 13 May 2013 11:31:41 +0200	[thread overview]
Message-ID: <5190B2FD.7090008@redhat.com> (raw)
In-Reply-To: <1368415264-10800-3-git-send-email-qemulist@gmail.com>

Il 13/05/2013 05:21, Liu Ping Fan ha scritto:
> From: Liu Ping Fan <pingfank@linux.vnet.ibm.com>
> 
> Each address space listener has PhysPageMap *cur_map, *next_map,
> the switch from cur_map to next_map complete the RCU style. The
> mem_commit() do the switch, and it is against reader but AddressSpace's
> lock or later RCU mechanism (around address_space_translate() ).
> 
> Signed-off-by: Liu Ping Fan <pingfank@linux.vnet.ibm.com>
> ---
>  exec.c                         |   36 +++++++++++++++++++++++++++---------
>  include/exec/memory-internal.h |   11 ++++++++++-
>  2 files changed, 37 insertions(+), 10 deletions(-)
> 
> diff --git a/exec.c b/exec.c
> index bb4e540..e5871d6 100644
> --- a/exec.c
> +++ b/exec.c
> @@ -186,24 +186,26 @@ static void phys_page_set(AddressSpaceDispatch *d,
>                            hwaddr index, hwaddr nb,
>                            uint16_t leaf)
>  {
> +    PhysPageMap *map = d->next_map;
>      /* Wildly overreserve - it doesn't matter much. */
>      phys_map_node_reserve(3 * P_L2_LEVELS);
>  
> -    phys_page_set_level(&d->phys_map, &index, &nb, leaf, P_L2_LEVELS - 1);
> +    phys_page_set_level(&map->root, &index, &nb, leaf, P_L2_LEVELS - 1);
>  }
>  
>  static PhysSection *phys_section_find(AddressSpaceDispatch *d,
>                                        hwaddr index)
>  {
> -    PhysPageEntry lp = d->phys_map;
>      PhysPageEntry *p;
> -    PhysSection *phys_sections = cur_pgtbl->phys_sections;
> -    Node *phys_map_nodes = cur_pgtbl->phys_map_nodes;
> +    PhysPageEntry lp = d->cur_map->root;
> +    PhysPageTable *pgtbl = d->cur_map->pgtbl;
> +    PhysSection *phys_sections = pgtbl->phys_sections;
> +    Node *phys_map_nodes = pgtbl->phys_map_nodes;
>      int i;
>  
>      for (i = P_L2_LEVELS - 1; i >= 0 && !lp.is_leaf; i--) {
>          if (lp.ptr == PHYS_MAP_NODE_NIL) {
> -            return &phys_sections[cur_pgtbl->phys_section_unassigned];
> +            return &phys_sections[pgtbl->phys_section_unassigned];
>          }
>          p = phys_map_nodes[lp.ptr];
>          lp = p[(index >> (i * L2_BITS)) & (L2_SIZE - 1)];
> @@ -234,7 +236,7 @@ MemoryRegionSection *address_space_translate(AddressSpace *as, hwaddr addr,
>      IOMMUTLBEntry iotlb;
>      MemoryRegionSection *section;
>      hwaddr len = *plen;
> -
> +    PhysPageTable *pgtbl = cur_pgtbl;

d->cur_map->pgtbl.

>      for (;;) {
>          section = address_space_lookup_region(as, addr);
>  
> @@ -254,7 +256,7 @@ MemoryRegionSection *address_space_translate(AddressSpace *as, hwaddr addr,
>                  | (addr & iotlb.addr_mask));
>          len = MIN(len, (addr | iotlb.addr_mask) - addr + 1);
>          if (!iotlb.perm[is_write]) {
> -            section = &cur_pgtbl->phys_sections[cur_pgtbl->phys_section_unassigned].section;
> +            section = &pgtbl->phys_sections[pgtbl->phys_section_unassigned].section;
>              break;
>          }
>  
> @@ -1703,7 +1705,21 @@ static void mem_begin(MemoryListener *listener)
>  {
>      AddressSpaceDispatch *d = container_of(listener, AddressSpaceDispatch, listener);
>  
> -    d->phys_map.ptr = PHYS_MAP_NODE_NIL;
> +    d->next_map = g_new0(PhysPageMap, 1);
> +    d->next_map->pgtbl = next_pgtbl;
> +}
> +
> +static void mem_commit(MemoryListener *listener)
> +{
> +    AddressSpaceDispatch *d = container_of(listener, AddressSpaceDispatch, listener);
> +    PhysPageMap *m = d->cur_map;
> +
> +    d->cur_map = d->next_map;
> +    /* Fixme, Currently, we rely on biglock or address-space lock against
> +    * reader. So here, we can safely drop it.
> +    * After RCU, should change to call_rcu()
> +    */
> +    g_free(m);
>  }
>  
>  static void core_begin(MemoryListener *listener)
> @@ -1771,11 +1787,12 @@ void address_space_init_dispatch(AddressSpace *as)
>  {
>      AddressSpaceDispatch *d = g_new(AddressSpaceDispatch, 1);
>  
> -    d->phys_map  = (PhysPageEntry) { .ptr = PHYS_MAP_NODE_NIL, .is_leaf = 0 };
> +    d->cur_map = g_new0(PhysPageMap, 1);
>      d->listener = (MemoryListener) {
>          .begin = mem_begin,
>          .region_add = mem_add,
>          .region_nop = mem_add,
> +        .commit = mem_commit,
>          .priority = 0,
>      };
>      as->dispatch = d;
> @@ -1787,6 +1804,7 @@ void address_space_destroy_dispatch(AddressSpace *as)
>      AddressSpaceDispatch *d = as->dispatch;
>  
>      memory_listener_unregister(&d->listener);
> +    g_free(d->cur_map);
>      g_free(d);
>      as->dispatch = NULL;
>  }
> diff --git a/include/exec/memory-internal.h b/include/exec/memory-internal.h
> index 1b156fd..0dfe260 100644
> --- a/include/exec/memory-internal.h
> +++ b/include/exec/memory-internal.h
> @@ -30,13 +30,22 @@ struct PhysPageEntry {
>      uint16_t ptr : 15;
>  };
>  
> +struct PhysPageTable;
> +typedef struct PhysPageMap PhysPageMap;
> +
> +struct PhysPageMap {
> +    PhysPageEntry root;
> +    struct PhysPageTable *pgtbl;

cur_pgtbl should be introduced in patch 1 already.

> +};
> +
>  typedef struct AddressSpaceDispatch AddressSpaceDispatch;
>  
>  struct AddressSpaceDispatch {
>      /* This is a multi-level map on the physical address space.
>       * The bottom level has pointers to MemoryRegionSections.
>       */
> -    PhysPageEntry phys_map;
> +    PhysPageMap *cur_map;
> +    PhysPageMap *next_map;

Pointers are quite expensive here.  With RCU we can fetch a consistent
root/table pair like this:

    rcu_read_lock();
    do {
        pgtbl = d->cur_pgtbl;
        smp_rmb();
        root = d->cur_root;

        /* RCU ensures that d->cur_pgtbl remains alive, thus it cannot
         * be recycled while this loop is running.  If
         * d->cur_pgtbl == pgtbl, the root is the right one for this
         * pgtable.
         */
        smp_rmb();
    } while (d->cur_pgtbl == pgtbl);
    ...
    rcu_read_unlock();

Remember to have a matching smp_wmb() in mem_commit, and to write ->root
first:

    old_pgtbl = d->cur_pgtbl;
    smp_wmb();
    d->cur_root = d->next_root;

    /* Write the root before updating the page table.  */
    smp_wmb();
    d->cur_pgtbl = d->next_pgtbl;

    /* Write cur_pgtbl before possibly destroying the old one.  */
    smp_mb();
    page_table_unref(old_pgtbl); /* uses call_rcu if --refcount == 0 */

If you are renaming fields, please do it as the first step.

Paolo

>      MemoryListener listener;
>  };
>  
> 

  reply	other threads:[~2013-05-13  9:31 UTC|newest]

Thread overview: 18+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2013-05-13  3:21 [Qemu-devel] [RFC PATCH 0/2] make memory listener prepared for rcu style Liu Ping Fan
2013-05-13  3:21 ` [Qemu-devel] [RFC PATCH 1/2] mem: make phys_section and phys_map_nodes prepared for RCU Liu Ping Fan
2013-05-13  9:20   ` Paolo Bonzini
2013-05-14  3:38     ` liu ping fan
2013-05-14  9:27       ` Paolo Bonzini
2013-05-15  7:04         ` liu ping fan
2013-05-26 13:02         ` liu ping fan
2013-05-27 11:54           ` Paolo Bonzini
2013-05-29  1:52             ` liu ping fan
2013-05-13  3:21 ` [Qemu-devel] [RFC PATCH 2/2] mem: prepare address_space listener rcu style Liu Ping Fan
2013-05-13  9:31   ` Paolo Bonzini [this message]
2013-05-14  5:47     ` liu ping fan
2013-05-14  9:34       ` Paolo Bonzini
2013-05-15  1:29         ` liu ping fan
2013-05-15  8:22           ` Paolo Bonzini
2013-05-15  9:11             ` liu ping fan
2013-05-15  9:19               ` Paolo Bonzini
2013-05-16  9:09     ` Paolo Bonzini

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=5190B2FD.7090008@redhat.com \
    --to=pbonzini@redhat.com \
    --cc=anthony@codemonkey.ws \
    --cc=jan.kiszka@siemens.com \
    --cc=mst@redhat.com \
    --cc=peter.maydell@linaro.org \
    --cc=qemu-devel@nongnu.org \
    --cc=qemulist@gmail.com \
    --cc=stefanha@redhat.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).