[Xen-devel] [PATCH v12 5/6] x86/ioreq server: Asynchronously reset outstanding p2m_ioreq_server entries.

[Yu Zhang <yu.c.zhang@xxxxxxxxxxxxxxx>]

After an ioreq server has unmapped, the remaining p2m_ioreq_server
entries need to be reset back to p2m_ram_rw. This patch does this
asynchronously with the current p2m_change_entry_type_global()
interface.

New field entry_count is introduced in struct p2m_domain, to record
the number of p2m_ioreq_server p2m page table entries. One nature of
these entries is that they only point to 4K sized page frames, because
all p2m_ioreq_server entries are originated from p2m_ram_rw ones in
p2m_change_type_one(). We do not need to worry about the counting for
2M/1G sized pages.

This patch disallows mapping of an ioreq server, when there's still
p2m_ioreq_server entry left, in case another mapping occurs right after
the current one being unmapped, releases its lock, with p2m table not
synced yet.

This patch also disallows live migration, when there's remaining
p2m_ioreq_server entry in p2m table. The core reason is our current
implementation of p2m_change_entry_type_global() lacks information
to resync p2m_ioreq_server entries correctly if global_logdirty is
on.

Signed-off-by: Yu Zhang <yu.c.zhang@xxxxxxxxxxxxxxx>
Reviewed-by: Paul Durrant <paul.durrant@xxxxxxxxxx>
---
Cc: Paul Durrant <paul.durrant@xxxxxxxxxx>
Cc: Jan Beulich <jbeulich@xxxxxxxx>
Cc: Andrew Cooper <andrew.cooper3@xxxxxxxxxx>
Cc: George Dunlap <george.dunlap@xxxxxxxxxxxxx>
Cc: Jun Nakajima <jun.nakajima@xxxxxxxxx>
Cc: Kevin Tian <kevin.tian@xxxxxxxxx>

changes in v7:
  - According to comments from George: add code to increase the
    entry_count.
  - Comment changes in {ept,p2m_pt}_set_entry.

changes in v6:
  - According to comments from Jan & George: move the count from
    p2m_change_type_one() to {ept,p2m_pt}_set_entry.
  - According to comments from George: comments change.

changes in v5:
  - According to comments from Jan: use unsigned long for entry_count;
  - According to comments from Jan: refuse mapping requirement when
    there's p2m_ioreq_server remained in p2m table.
  - Added "Reviewed-by: Paul Durrant <paul.durrant@xxxxxxxxxx>"

changes in v4:
  - According to comments from Jan: use ASSERT() instead of 'if'
    condition in p2m_change_type_one().
  - According to comments from Jan: commit message changes to mention
    the p2m_ioreq_server are all based on 4K sized pages.

changes in v3:
  - Move the synchronously resetting logic into patch 5.
  - According to comments from Jan: introduce p2m_check_changeable()
    to clarify the p2m type change code.
  - According to comments from George: use locks in the same order
    to avoid deadlock, call p2m_change_entry_type_global() after unmap
    of the ioreq server is finished.

changes in v2:
  - Move the calculation of ioreq server page entry_cout into
    p2m_change_type_one() so that we do not need a seperate lock.
    Note: entry_count is also calculated in resolve_misconfig()/
    do_recalc(), fortunately callers of both routines have p2m
    lock protected already.
  - Simplify logic in hvmop_set_mem_type().
  - Introduce routine p2m_finish_type_change() to walk the p2m
    table and do the p2m reset.
---
 xen/arch/x86/hvm/ioreq.c  |  8 ++++++++
 xen/arch/x86/mm/hap/hap.c |  9 +++++++++
 xen/arch/x86/mm/p2m-ept.c | 24 +++++++++++++++++++++++-
 xen/arch/x86/mm/p2m-pt.c  | 30 ++++++++++++++++++++++++++++--
 xen/arch/x86/mm/p2m.c     |  9 +++++++++
 xen/include/asm-x86/p2m.h |  9 ++++++++-
 6 files changed, 85 insertions(+), 4 deletions(-)

diff --git a/xen/arch/x86/hvm/ioreq.c b/xen/arch/x86/hvm/ioreq.c
index 5bf3b6d..07a6c26 100644
--- a/xen/arch/x86/hvm/ioreq.c
+++ b/xen/arch/x86/hvm/ioreq.c
@@ -955,6 +955,14 @@ int hvm_map_mem_type_to_ioreq_server(struct domain *d, 
ioservid_t id,
 
     spin_unlock_recursive(&d->arch.hvm_domain.ioreq_server.lock);
 
+    if ( rc == 0 && flags == 0 )
+    {
+        struct p2m_domain *p2m = p2m_get_hostp2m(d);
+
+        if ( read_atomic(&p2m->ioreq.entry_count) )
+            p2m_change_entry_type_global(d, p2m_ioreq_server, p2m_ram_rw);
+    }
+
     return rc;
 }
 
diff --git a/xen/arch/x86/mm/hap/hap.c b/xen/arch/x86/mm/hap/hap.c
index a57b385..4b591fe 100644
--- a/xen/arch/x86/mm/hap/hap.c
+++ b/xen/arch/x86/mm/hap/hap.c
@@ -187,6 +187,15 @@ out:
  */
 static int hap_enable_log_dirty(struct domain *d, bool_t log_global)
 {
+    struct p2m_domain *p2m = p2m_get_hostp2m(d);
+
+    /*
+     * Refuse to turn on global log-dirty mode if
+     * there are outstanding p2m_ioreq_server pages.
+     */
+    if ( log_global && read_atomic(&p2m->ioreq.entry_count) )
+        return -EBUSY;
+
     /* turn on PG_log_dirty bit in paging mode */
     paging_lock(d);
     d->arch.paging.mode |= PG_log_dirty;
diff --git a/xen/arch/x86/mm/p2m-ept.c b/xen/arch/x86/mm/p2m-ept.c
index cc1eb21..ecd5ceb 100644
--- a/xen/arch/x86/mm/p2m-ept.c
+++ b/xen/arch/x86/mm/p2m-ept.c
@@ -544,6 +544,12 @@ static int resolve_misconfig(struct p2m_domain *p2m, 
unsigned long gfn)
                     e.ipat = ipat;
                     if ( e.recalc && p2m_is_changeable(e.sa_p2mt) )
                     {
+                         if ( e.sa_p2mt == p2m_ioreq_server )
+                         {
+                             ASSERT(p2m->ioreq.entry_count > 0);
+                             p2m->ioreq.entry_count--;
+                         }
+
                          e.sa_p2mt = p2m_is_logdirty_range(p2m, gfn + i, gfn + 
i)
                                      ? p2m_ram_logdirty : p2m_ram_rw;
                          ept_p2m_type_to_flags(p2m, &e, e.sa_p2mt, e.access);
@@ -816,6 +822,22 @@ ept_set_entry(struct p2m_domain *p2m, unsigned long gfn, 
mfn_t mfn,
         new_entry.suppress_ve = is_epte_valid(&old_entry) ?
                                     old_entry.suppress_ve : 1;
 
+    /*
+     * p2m_ioreq_server is only used for 4K pages, so the
+     * count shall only happen on ept page table entries.
+     */
+    if ( p2mt == p2m_ioreq_server )
+    {
+        ASSERT(i == 0);
+        p2m->ioreq.entry_count++;
+    }
+
+    if ( ept_entry->sa_p2mt == p2m_ioreq_server )
+    {
+        ASSERT(p2m->ioreq.entry_count > 0 && i == 0);
+        p2m->ioreq.entry_count--;
+    }
+
     rc = atomic_write_ept_entry(ept_entry, new_entry, target);
     if ( unlikely(rc) )
         old_entry.epte = 0;
@@ -965,7 +987,7 @@ static mfn_t ept_get_entry(struct p2m_domain *p2m,
     if ( is_epte_valid(ept_entry) )
     {
         if ( (recalc || ept_entry->recalc) &&
-             p2m_is_changeable(ept_entry->sa_p2mt) )
+             p2m_check_changeable(ept_entry->sa_p2mt) )
             *t = p2m_is_logdirty_range(p2m, gfn, gfn) ? p2m_ram_logdirty
                                                       : p2m_ram_rw;
         else
diff --git a/xen/arch/x86/mm/p2m-pt.c b/xen/arch/x86/mm/p2m-pt.c
index c0055f3..4b2ff9e 100644
--- a/xen/arch/x86/mm/p2m-pt.c
+++ b/xen/arch/x86/mm/p2m-pt.c
@@ -436,11 +436,13 @@ static int do_recalc(struct p2m_domain *p2m, unsigned 
long gfn)
          needs_recalc(l1, *pent) )
     {
         l1_pgentry_t e = *pent;
+        p2m_type_t p2mt_old;
 
         if ( !valid_recalc(l1, e) )
             P2M_DEBUG("bogus recalc leaf at d%d:%lx:%u\n",
                       p2m->domain->domain_id, gfn, level);
-        if ( p2m_is_changeable(p2m_flags_to_type(l1e_get_flags(e))) )
+        p2mt_old = p2m_flags_to_type(l1e_get_flags(e));
+        if ( p2m_is_changeable(p2mt_old) )
         {
             unsigned long mask = ~0UL << (level * PAGETABLE_ORDER);
             p2m_type_t p2mt = p2m_is_logdirty_range(p2m, gfn & mask, gfn | 
~mask)
@@ -460,6 +462,13 @@ static int do_recalc(struct p2m_domain *p2m, unsigned long 
gfn)
                      mfn &= ~((unsigned long)_PAGE_PSE_PAT >> PAGE_SHIFT);
                 flags |= _PAGE_PSE;
             }
+
+            if ( p2mt_old == p2m_ioreq_server )
+            {
+                ASSERT(p2m->ioreq.entry_count > 0);
+                p2m->ioreq.entry_count--;
+            }
+
             e = l1e_from_pfn(mfn, flags);
             p2m_add_iommu_flags(&e, level,
                                 (p2mt == p2m_ram_rw)
@@ -606,6 +615,8 @@ p2m_pt_set_entry(struct p2m_domain *p2m, unsigned long gfn, 
mfn_t mfn,
 
     if ( page_order == PAGE_ORDER_4K )
     {
+        p2m_type_t p2mt_old;
+
         rc = p2m_next_level(p2m, &table, &gfn_remainder, gfn,
                             L2_PAGETABLE_SHIFT - PAGE_SHIFT,
                             L2_PAGETABLE_ENTRIES, PGT_l1_page_table, 1);
@@ -629,6 +640,21 @@ p2m_pt_set_entry(struct p2m_domain *p2m, unsigned long 
gfn, mfn_t mfn,
         if ( entry_content.l1 != 0 )
             p2m_add_iommu_flags(&entry_content, 0, iommu_pte_flags);
 
+        p2mt_old = p2m_flags_to_type(l1e_get_flags(*p2m_entry));
+
+        /*
+         * p2m_ioreq_server is only used for 4K pages, so
+         * the count shall only be performed for level 1 entries.
+         */
+        if ( p2mt == p2m_ioreq_server )
+            p2m->ioreq.entry_count++;
+
+        if ( p2mt_old == p2m_ioreq_server )
+        {
+            ASSERT(p2m->ioreq.entry_count > 0);
+            p2m->ioreq.entry_count--;
+        }
+
         /* level 1 entry */
         p2m->write_p2m_entry(p2m, gfn, p2m_entry, entry_content, 1);
         /* NB: paging_write_p2m_entry() handles tlb flushes properly */
@@ -729,7 +755,7 @@ p2m_pt_set_entry(struct p2m_domain *p2m, unsigned long gfn, 
mfn_t mfn,
 static inline p2m_type_t recalc_type(bool_t recalc, p2m_type_t t,
                                      struct p2m_domain *p2m, unsigned long gfn)
 {
-    if ( !recalc || !p2m_is_changeable(t) )
+    if ( !recalc || !p2m_check_changeable(t) )
         return t;
     return p2m_is_logdirty_range(p2m, gfn, gfn) ? p2m_ram_logdirty
                                                 : p2m_ram_rw;
diff --git a/xen/arch/x86/mm/p2m.c b/xen/arch/x86/mm/p2m.c
index b84add0..4169d18 100644
--- a/xen/arch/x86/mm/p2m.c
+++ b/xen/arch/x86/mm/p2m.c
@@ -317,6 +317,15 @@ int p2m_set_ioreq_server(struct domain *d,
         if ( p2m->ioreq.server != NULL )
             goto out;
 
+        /*
+         * It is possible that an ioreq server has just been unmapped,
+         * released the spin lock, with some p2m_ioreq_server entries
+         * in p2m table remained. We shall refuse another ioreq server
+         * mapping request in such case.
+         */
+        if ( read_atomic(&p2m->ioreq.entry_count) )
+            goto out;
+
         p2m->ioreq.server = s;
         p2m->ioreq.flags = flags;
     }
diff --git a/xen/include/asm-x86/p2m.h b/xen/include/asm-x86/p2m.h
index 4521620..e7e390d 100644
--- a/xen/include/asm-x86/p2m.h
+++ b/xen/include/asm-x86/p2m.h
@@ -120,7 +120,10 @@ typedef unsigned int p2m_query_t;
 
 /* Types that can be subject to bulk transitions. */
 #define P2M_CHANGEABLE_TYPES (p2m_to_mask(p2m_ram_rw) \
-                              | p2m_to_mask(p2m_ram_logdirty) )
+                              | p2m_to_mask(p2m_ram_logdirty) \
+                              | p2m_to_mask(p2m_ioreq_server) )
+
+#define P2M_IOREQ_TYPES (p2m_to_mask(p2m_ioreq_server))
 
 #define P2M_POD_TYPES (p2m_to_mask(p2m_populate_on_demand))
 
@@ -157,6 +160,7 @@ typedef unsigned int p2m_query_t;
 #define p2m_is_readonly(_t) (p2m_to_mask(_t) & P2M_RO_TYPES)
 #define p2m_is_discard_write(_t) (p2m_to_mask(_t) & P2M_DISCARD_WRITE_TYPES)
 #define p2m_is_changeable(_t) (p2m_to_mask(_t) & P2M_CHANGEABLE_TYPES)
+#define p2m_is_ioreq(_t) (p2m_to_mask(_t) & P2M_IOREQ_TYPES)
 #define p2m_is_pod(_t) (p2m_to_mask(_t) & P2M_POD_TYPES)
 #define p2m_is_grant(_t) (p2m_to_mask(_t) & P2M_GRANT_TYPES)
 /* Grant types are *not* considered valid, because they can be
@@ -178,6 +182,8 @@ typedef unsigned int p2m_query_t;
 
 #define p2m_allows_invalid_mfn(t) (p2m_to_mask(t) & P2M_INVALID_MFN_TYPES)
 
+#define p2m_check_changeable(t) (p2m_is_changeable(t) && !p2m_is_ioreq(t))
+
 typedef enum {
     p2m_host,
     p2m_nested,
@@ -349,6 +355,7 @@ struct p2m_domain {
           * are to be emulated by an ioreq server.
           */
          unsigned int flags;
+         unsigned long entry_count;
      } ioreq;
 };
 
-- 
1.9.1


_______________________________________________
Xen-devel mailing list
Xen-devel@xxxxxxxxxxxxx
https://lists.xen.org/xen-devel