[PATCH RFC 39/55] x86: switch root_pgt to mfn_t and use new APIs

[Wei Liu <wei.liu2@citrix.com>]

This then requires moving declaration of root page table mfn into mm.h
and modify setup_cpu_root_pgt to have a single exit path.

We also need to force map_domain_page to use direct map when switching
per-domain mappings. This is contrary to our end goal of removing
direct map, but this will be removed once we make map_domain_page
context-switch safe in another (large) patch series.

Signed-off-by: Wei Liu <wei.liu2@citrix.com>
---
 xen/arch/x86/domain.c           | 15 ++++++++++++---
 xen/arch/x86/domain_page.c      |  2 +-
 xen/arch/x86/mm.c               |  2 +-
 xen/arch/x86/pv/domain.c        |  2 +-
 xen/arch/x86/smpboot.c          | 40 +++++++++++++++++++++++++++-------------
 xen/include/asm-x86/mm.h        |  2 ++
 xen/include/asm-x86/processor.h |  1 -
 7 files changed, 44 insertions(+), 20 deletions(-)

diff --git a/xen/arch/x86/domain.c b/xen/arch/x86/domain.c
index 32dc4253ff..603495e55a 100644
--- a/xen/arch/x86/domain.c
+++ b/xen/arch/x86/domain.c
@@ -68,6 +68,7 @@
 #include <asm/pv/domain.h>
 #include <asm/pv/mm.h>
 #include <asm/spec_ctrl.h>
+#include <asm/setup.h>
 
 DEFINE_PER_CPU(struct vcpu *, curr_vcpu);
 
@@ -1589,12 +1590,20 @@ void paravirt_ctxt_switch_from(struct vcpu *v)
 
 void paravirt_ctxt_switch_to(struct vcpu *v)
 {
-    root_pgentry_t *root_pgt = this_cpu(root_pgt);
+    mfn_t rpt_mfn = this_cpu(root_pgt_mfn);
 
-    if ( root_pgt )
-        root_pgt[root_table_offset(PERDOMAIN_VIRT_START)] =
+    if ( !mfn_eq(rpt_mfn, INVALID_MFN) )
+    {
+        root_pgentry_t *rpt;
+
+        mapcache_override_current(INVALID_VCPU);
+        rpt = map_xen_pagetable_new(rpt_mfn);
+        rpt[root_table_offset(PERDOMAIN_VIRT_START)] =
             l4e_from_page(v->domain->arch.perdomain_l3_pg,
                           __PAGE_HYPERVISOR_RW);
+        UNMAP_XEN_PAGETABLE_NEW(rpt);
+        mapcache_override_current(NULL);
+    }
 
     if ( unlikely(v->arch.dr7 & DR7_ACTIVE_MASK) )
         activate_debugregs(v);
diff --git a/xen/arch/x86/domain_page.c b/xen/arch/x86/domain_page.c
index 24083e9a86..cfcffd35f3 100644
--- a/xen/arch/x86/domain_page.c
+++ b/xen/arch/x86/domain_page.c
@@ -57,7 +57,7 @@ static inline struct vcpu *mapcache_current_vcpu(void)
     return v;
 }
 
-void __init mapcache_override_current(struct vcpu *v)
+void mapcache_override_current(struct vcpu *v)
 {
     this_cpu(override) = v;
 }
diff --git a/xen/arch/x86/mm.c b/xen/arch/x86/mm.c
index 9e115ef0b8..44c9df5c9e 100644
--- a/xen/arch/x86/mm.c
+++ b/xen/arch/x86/mm.c
@@ -564,7 +564,7 @@ void write_ptbase(struct vcpu *v)
     if ( is_pv_vcpu(v) && v->domain->arch.pv.xpti )
     {
         cpu_info->root_pgt_changed = true;
-        cpu_info->pv_cr3 = __pa(this_cpu(root_pgt));
+        cpu_info->pv_cr3 = mfn_to_maddr(this_cpu(root_pgt_mfn));
         if ( new_cr4 & X86_CR4_PCIDE )
             cpu_info->pv_cr3 |= get_pcid_bits(v, true);
         switch_cr3_cr4(v->arch.cr3, new_cr4);
diff --git a/xen/arch/x86/pv/domain.c b/xen/arch/x86/pv/domain.c
index 7e84b04082..2fd944b7e3 100644
--- a/xen/arch/x86/pv/domain.c
+++ b/xen/arch/x86/pv/domain.c
@@ -303,7 +303,7 @@ static void _toggle_guest_pt(struct vcpu *v)
         struct cpu_info *cpu_info = get_cpu_info();
 
         cpu_info->root_pgt_changed = true;
-        cpu_info->pv_cr3 = __pa(this_cpu(root_pgt)) |
+        cpu_info->pv_cr3 = mfn_to_maddr(this_cpu(root_pgt_mfn)) |
                            (d->arch.pv.pcid ? get_pcid_bits(v, true) : 0);
     }
 
diff --git a/xen/arch/x86/smpboot.c b/xen/arch/x86/smpboot.c
index a9a39cea6e..32dce00d10 100644
--- a/xen/arch/x86/smpboot.c
+++ b/xen/arch/x86/smpboot.c
@@ -819,7 +819,7 @@ static int clone_mapping(const void *ptr, root_pgentry_t *rpt)
     return rc;
 }
 
-DEFINE_PER_CPU(root_pgentry_t *, root_pgt);
+DEFINE_PER_CPU(mfn_t, root_pgt_mfn);
 
 static root_pgentry_t common_pgt;
 
@@ -827,19 +827,27 @@ extern const char _stextentry[], _etextentry[];
 
 static int setup_cpu_root_pgt(unsigned int cpu)
 {
-    root_pgentry_t *rpt;
+    root_pgentry_t *rpt = NULL;
+    mfn_t rpt_mfn;
     unsigned int off;
     int rc;
 
     if ( !opt_xpti_hwdom && !opt_xpti_domu )
-        return 0;
+    {
+        rc = 0;
+        goto out;
+    }
 
-    rpt = alloc_xen_pagetable();
-    if ( !rpt )
-        return -ENOMEM;
+    rpt_mfn = alloc_xen_pagetable_new();
+    if ( mfn_eq(rpt_mfn, INVALID_MFN) )
+    {
+        rc = -ENOMEM;
+        goto out;
+    }
 
+    rpt = map_xen_pagetable_new(rpt_mfn);
     clear_page(rpt);
-    per_cpu(root_pgt, cpu) = rpt;
+    per_cpu(root_pgt_mfn, cpu) = rpt_mfn;
 
     rpt[root_table_offset(RO_MPT_VIRT_START)] =
         idle_pg_table[root_table_offset(RO_MPT_VIRT_START)];
@@ -856,7 +864,7 @@ static int setup_cpu_root_pgt(unsigned int cpu)
             rc = clone_mapping(ptr, rpt);
 
         if ( rc )
-            return rc;
+            goto out;
 
         common_pgt = rpt[root_table_offset(XEN_VIRT_START)];
     }
@@ -875,19 +883,24 @@ static int setup_cpu_root_pgt(unsigned int cpu)
     if ( !rc )
         rc = clone_mapping((void *)per_cpu(stubs.addr, cpu), rpt);
 
+ out:
+    UNMAP_XEN_PAGETABLE_NEW(rpt);
     return rc;
 }
 
 static void cleanup_cpu_root_pgt(unsigned int cpu)
 {
-    root_pgentry_t *rpt = per_cpu(root_pgt, cpu);
+    mfn_t rpt_mfn = per_cpu(root_pgt_mfn, cpu);
+    root_pgentry_t *rpt;
     unsigned int r;
     unsigned long stub_linear = per_cpu(stubs.addr, cpu);
 
-    if ( !rpt )
+    if ( mfn_eq(rpt_mfn, INVALID_MFN) )
         return;
 
-    per_cpu(root_pgt, cpu) = NULL;
+    per_cpu(root_pgt_mfn, cpu) = INVALID_MFN;
+
+    rpt = map_xen_pagetable_new(rpt_mfn);
 
     for ( r = root_table_offset(DIRECTMAP_VIRT_START);
           r < root_table_offset(HYPERVISOR_VIRT_END); ++r )
@@ -932,7 +945,8 @@ static void cleanup_cpu_root_pgt(unsigned int cpu)
         free_xen_pagetable_new(l3t_mfn);
     }
 
-    free_xen_pagetable(rpt);
+    UNMAP_XEN_PAGETABLE_NEW(rpt);
+    free_xen_pagetable_new(rpt_mfn);
 
     /* Also zap the stub mapping for this CPU. */
     if ( stub_linear )
@@ -1138,7 +1152,7 @@ void __init smp_prepare_cpus(void)
     rc = setup_cpu_root_pgt(0);
     if ( rc )
         panic("Error %d setting up PV root page table\n", rc);
-    if ( per_cpu(root_pgt, 0) )
+    if ( !mfn_eq(per_cpu(root_pgt_mfn, 0), INVALID_MFN) )
     {
         get_cpu_info()->pv_cr3 = 0;
 
diff --git a/xen/include/asm-x86/mm.h b/xen/include/asm-x86/mm.h
index 4378d9f815..708b84bb89 100644
--- a/xen/include/asm-x86/mm.h
+++ b/xen/include/asm-x86/mm.h
@@ -657,4 +657,6 @@ void free_xen_pagetable_new(mfn_t mfn);
 
 l1_pgentry_t *virt_to_xen_l1e(unsigned long v);
 
+DECLARE_PER_CPU(mfn_t, root_pgt_mfn);
+
 #endif /* __ASM_X86_MM_H__ */
diff --git a/xen/include/asm-x86/processor.h b/xen/include/asm-x86/processor.h
index df01ae30d7..9f98ac96f5 100644
--- a/xen/include/asm-x86/processor.h
+++ b/xen/include/asm-x86/processor.h
@@ -449,7 +449,6 @@ extern idt_entry_t idt_table[];
 extern idt_entry_t *idt_tables[];
 
 DECLARE_PER_CPU(struct tss_struct, init_tss);
-DECLARE_PER_CPU(root_pgentry_t *, root_pgt);
 
 extern void write_ptbase(struct vcpu *v);
 
-- 
2.11.0


_______________________________________________
Xen-devel mailing list
Xen-devel@lists.xenproject.org
https://lists.xenproject.org/mailman/listinfo/xen-devel