[PATCH v2 09/14] x86/mm: prepare destroy_perdomain_mapping() for per-vCPU perdomain areas

[George Dunlap <dunlapg@xxxxxxxxx>]

From: Roger Pau Monné <roger.pau@xxxxxxxxxx>

We want to change per-domain mappings to be per-vCPU mappings.  In
preparation for that, we want to arrange that
destroy_perdomain_mapping() work either with a single perdomain area,
or with a per-vCPU perdomain area.

The remaining callers are already in a vCPU context, so we just need
to change the parameter from a domain pointer to a vCPU pointer.

Since we now have a specific vCPU in mind, we have the option of using
the linear page table mapping rather than map-and-walk.  As in
populate_perdomain_mapping(), the linear page table fast path is keyed
off this_cpu(pgtable_vcpu) matching the target vCPU, which is the
conditional that implies "the linear mapping area points to v's
per-domain area".

Signed-off-by: Roger Pau Monné <roger.pau@xxxxxxxxxx>
Assisted-by: Claude Code:claude-fable-5, Claude Code:claude-opus-4-8
Signed-off-by: George Dunlap <gwd@xxxxxxxxxxxxxx>
---
Changes in v2:
- Added to the series

Changes since the previously posted version:
- Key the fast path off pgtable_vcpu instead of current, matching
  populate_perdomain_mapping(), and drop the sync_local_execstate()
  call.
- Also convert the pv_destroy_ldt() call, added by the stash-removal
  batch.
- Reword and retitle for clarity (was: "x86/mm: switch
  destroy_perdomain_mapping() parameter from domain to vCPU").
---
 xen/arch/x86/include/asm/mm.h       |  2 +-
 xen/arch/x86/mm.c                   | 23 ++++++++++++++++++++++-
 xen/arch/x86/pv/descriptor-tables.c |  2 +-
 xen/arch/x86/pv/domain.c            |  3 +--
 xen/arch/x86/x86_64/mm.c            |  2 +-
 5 files changed, 26 insertions(+), 6 deletions(-)

diff --git a/xen/arch/x86/include/asm/mm.h b/xen/arch/x86/include/asm/mm.h
index 30eaec9179..9a8fda782e 100644
--- a/xen/arch/x86/include/asm/mm.h
+++ b/xen/arch/x86/include/asm/mm.h
@@ -605,7 +605,7 @@ int create_perdomain_mapping(struct domain *d, unsigned 
long va,
 void populate_perdomain_mapping(const struct vcpu *v, unsigned long va,
                                 const mfn_t *mfn, unsigned int nr,
                                 unsigned int flags);
-void destroy_perdomain_mapping(struct domain *d, unsigned long va,
+void destroy_perdomain_mapping(const struct vcpu *v, unsigned long va,
                                unsigned int nr);
 void free_perdomain_mappings(struct domain *d);
 
diff --git a/xen/arch/x86/mm.c b/xen/arch/x86/mm.c
index 48d1b427c5..fc524ef0c3 100644
--- a/xen/arch/x86/mm.c
+++ b/xen/arch/x86/mm.c
@@ -6456,10 +6456,11 @@ void populate_perdomain_mapping(const struct vcpu *v, 
unsigned long va,
     local_irq_restore(irq_flags);
 }
 
-void destroy_perdomain_mapping(struct domain *d, unsigned long va,
+void destroy_perdomain_mapping(const struct vcpu *v, unsigned long va,
                                unsigned int nr)
 {
     const l3_pgentry_t *l3tab, *pl3e;
+    const struct domain *d = v->domain;
 
     ASSERT(va >= PERDOMAIN_VIRT_START &&
            va < PERDOMAIN_VIRT_SLOT(PERDOMAIN_SLOTS));
@@ -6468,6 +6469,26 @@ void destroy_perdomain_mapping(struct domain *d, 
unsigned long va,
     if ( !d->arch.perdomain_l3_pg )
         return;
 
+    if ( likely(this_cpu(pgtable_vcpu) == v) )
+    {
+        l1_pgentry_t *pl1e;
+
+        /*
+         * Fast path: v's page-tables are loaded on this pCPU, so the L1
+         * entries can be zapped using the recursive linear mappings.
+         */
+        pl1e = &__linear_l1_table[l1_linear_offset(va)];
+
+        for ( ; nr--; pl1e++ )
+        {
+            if ( perdomain_l1e_needs_freeing(*pl1e) )
+                free_domheap_page(l1e_get_page(*pl1e));
+            l1e_write(pl1e, l1e_empty());
+        }
+
+        return;
+    }
+
     l3tab = __map_domain_page(d->arch.perdomain_l3_pg);
     pl3e = l3tab + l3_table_offset(va);
 
diff --git a/xen/arch/x86/pv/descriptor-tables.c 
b/xen/arch/x86/pv/descriptor-tables.c
index 261bf29c90..0c1ea4ce3a 100644
--- a/xen/arch/x86/pv/descriptor-tables.c
+++ b/xen/arch/x86/pv/descriptor-tables.c
@@ -27,7 +27,7 @@ bool pv_destroy_ldt(struct vcpu *v)
 
     ASSERT(v == current || !vcpu_cpu_dirty(v));
 
-    destroy_perdomain_mapping(v->domain, LDT_VIRT_START(v), nr_frames);
+    destroy_perdomain_mapping(v, LDT_VIRT_START(v), nr_frames);
 
     for ( i = 0; i < nr_frames; i++ )
     {
diff --git a/xen/arch/x86/pv/domain.c b/xen/arch/x86/pv/domain.c
index b936ca9b26..40b834e1a4 100644
--- a/xen/arch/x86/pv/domain.c
+++ b/xen/arch/x86/pv/domain.c
@@ -319,8 +319,7 @@ static int pv_create_gdt_ldt_l1tab(struct vcpu *v)
 
 static void pv_destroy_gdt_ldt_l1tab(struct vcpu *v)
 {
-    destroy_perdomain_mapping(v->domain, GDT_VIRT_START(v),
-                              1U << GDT_LDT_VCPU_SHIFT);
+    destroy_perdomain_mapping(v, GDT_VIRT_START(v), 1U << GDT_LDT_VCPU_SHIFT);
 }
 
 void pv_vcpu_destroy(struct vcpu *v)
diff --git a/xen/arch/x86/x86_64/mm.c b/xen/arch/x86/x86_64/mm.c
index ffeda06e08..aa74acec82 100644
--- a/xen/arch/x86/x86_64/mm.c
+++ b/xen/arch/x86/x86_64/mm.c
@@ -738,7 +738,7 @@ int setup_compat_arg_xlat(struct vcpu *v)
 
 void free_compat_arg_xlat(struct vcpu *v)
 {
-    destroy_perdomain_mapping(v->domain, ARG_XLAT_START(v),
+    destroy_perdomain_mapping(v, ARG_XLAT_START(v),
                               PFN_UP(COMPAT_ARG_XLAT_SIZE));
 }
 
-- 
2.55.0