[Xen-devel] [PATCH v5 2/2] x86: add accessors for scratch cpu mask

[Roger Pau Monne <roger.pau@citrix.com>]

Current usage of the per-CPU scratch cpumask is dangerous since
there's no way to figure out if the mask is already being used except
for manual code inspection of all the callers and possible call paths.

This is unsafe and not reliable, so introduce a minimal get/put
infrastructure to prevent nested usage of the scratch mask and usage
in interrupt context.

Move the declaration of scratch_cpumask to smp.c in order to place the
declaration and the accessors as close as possible.

Signed-off-by: Roger Pau Monné <roger.pau@citrix.com>
---
Changes since v4:
 - Fix get_scratch_cpumask call order in _clear_irq_vector.
 - Remove double newline in __do_update_va_mapping.
 - Constify scratch_cpumask_use.
 - Don't explicitly print the address in the format string, a followup
   patch will be sent to make %p[sS] do so.

Changes since v3:
 - Fix commit message.
 - Split the cpumask taken section into two in _clear_irq_vector.
 - Add an empty statement in do_mmuext_op to avoid a break.
 - Change the logic used to release the scratch cpumask in
   __do_update_va_mapping.
 - Add a %ps print to scratch_cpumask helper.
 - Remove printing the current IP, as that would be done by BUG
   anyway.
 - Pass the cpumask to put_scratch_cpumask and zap the pointer.

Changes since v1:
 - Use __builtin_return_address(0) instead of __func__.
 - Move declaration of scratch_cpumask and scratch_cpumask accessor to
   smp.c.
 - Do not allow usage in #MC or #NMI context.
---
 xen/arch/x86/io_apic.c    |  6 ++++--
 xen/arch/x86/irq.c        | 14 ++++++++++----
 xen/arch/x86/mm.c         | 39 +++++++++++++++++++++++++++------------
 xen/arch/x86/msi.c        |  4 +++-
 xen/arch/x86/smp.c        | 25 +++++++++++++++++++++++++
 xen/arch/x86/smpboot.c    |  1 -
 xen/include/asm-x86/smp.h | 14 ++++++++++++++
 7 files changed, 83 insertions(+), 20 deletions(-)

diff --git a/xen/arch/x86/io_apic.c b/xen/arch/x86/io_apic.c
index e98e08e9c8..0bb994f0ba 100644
--- a/xen/arch/x86/io_apic.c
+++ b/xen/arch/x86/io_apic.c
@@ -2236,10 +2236,11 @@ int io_apic_set_pci_routing (int ioapic, int pin, int irq, int edge_level, int a
     entry.vector = vector;
 
     if (cpumask_intersects(desc->arch.cpu_mask, TARGET_CPUS)) {
-        cpumask_t *mask = this_cpu(scratch_cpumask);
+        cpumask_t *mask = get_scratch_cpumask();
 
         cpumask_and(mask, desc->arch.cpu_mask, TARGET_CPUS);
         SET_DEST(entry, logical, cpu_mask_to_apicid(mask));
+        put_scratch_cpumask(mask);
     } else {
         printk(XENLOG_ERR "IRQ%d: no target CPU (%*pb vs %*pb)\n",
                irq, CPUMASK_PR(desc->arch.cpu_mask), CPUMASK_PR(TARGET_CPUS));
@@ -2433,10 +2434,11 @@ int ioapic_guest_write(unsigned long physbase, unsigned int reg, u32 val)
 
     if ( cpumask_intersects(desc->arch.cpu_mask, TARGET_CPUS) )
     {
-        cpumask_t *mask = this_cpu(scratch_cpumask);
+        cpumask_t *mask = get_scratch_cpumask();
 
         cpumask_and(mask, desc->arch.cpu_mask, TARGET_CPUS);
         SET_DEST(rte, logical, cpu_mask_to_apicid(mask));
+        put_scratch_cpumask(mask);
     }
     else
     {
diff --git a/xen/arch/x86/irq.c b/xen/arch/x86/irq.c
index cc2eb8e925..0a526ee800 100644
--- a/xen/arch/x86/irq.c
+++ b/xen/arch/x86/irq.c
@@ -196,7 +196,7 @@ static void _clear_irq_vector(struct irq_desc *desc)
 {
     unsigned int cpu, old_vector, irq = desc->irq;
     unsigned int vector = desc->arch.vector;
-    cpumask_t *tmp_mask = this_cpu(scratch_cpumask);
+    cpumask_t *tmp_mask = get_scratch_cpumask();
 
     BUG_ON(!valid_irq_vector(vector));
 
@@ -208,6 +208,7 @@ static void _clear_irq_vector(struct irq_desc *desc)
         ASSERT(per_cpu(vector_irq, cpu)[vector] == irq);
         per_cpu(vector_irq, cpu)[vector] = ~irq;
     }
+    put_scratch_cpumask(tmp_mask);
 
     desc->arch.vector = IRQ_VECTOR_UNASSIGNED;
     cpumask_clear(desc->arch.cpu_mask);
@@ -227,8 +228,9 @@ static void _clear_irq_vector(struct irq_desc *desc)
 
     /* If we were in motion, also clear desc->arch.old_vector */
     old_vector = desc->arch.old_vector;
-    cpumask_and(tmp_mask, desc->arch.old_cpu_mask, &cpu_online_map);
 
+    tmp_mask = get_scratch_cpumask();
+    cpumask_and(tmp_mask, desc->arch.old_cpu_mask, &cpu_online_map);
     for_each_cpu(cpu, tmp_mask)
     {
         ASSERT(per_cpu(vector_irq, cpu)[old_vector] == irq);
@@ -236,6 +238,7 @@ static void _clear_irq_vector(struct irq_desc *desc)
         per_cpu(vector_irq, cpu)[old_vector] = ~irq;
     }
 
+    put_scratch_cpumask(tmp_mask);
     release_old_vec(desc);
 
     desc->arch.move_in_progress = 0;
@@ -1152,10 +1155,11 @@ static void irq_guest_eoi_timer_fn(void *data)
         break;
 
     case ACKTYPE_EOI:
-        cpu_eoi_map = this_cpu(scratch_cpumask);
+        cpu_eoi_map = get_scratch_cpumask();
         cpumask_copy(cpu_eoi_map, action->cpu_eoi_map);
         spin_unlock_irq(&desc->lock);
         on_selected_cpus(cpu_eoi_map, set_eoi_ready, desc, 0);
+        put_scratch_cpumask(cpu_eoi_map);
         return;
     }
 
@@ -2531,12 +2535,12 @@ void fixup_irqs(const cpumask_t *mask, bool verbose)
     unsigned int irq;
     static int warned;
     struct irq_desc *desc;
+    cpumask_t *affinity = get_scratch_cpumask();
 
     for ( irq = 0; irq < nr_irqs; irq++ )
     {
         bool break_affinity = false, set_affinity = true;
         unsigned int vector;
-        cpumask_t *affinity = this_cpu(scratch_cpumask);
 
         if ( irq == 2 )
             continue;
@@ -2640,6 +2644,8 @@ void fixup_irqs(const cpumask_t *mask, bool verbose)
                    irq, CPUMASK_PR(affinity));
     }
 
+    put_scratch_cpumask(affinity);
+
     /* That doesn't seem sufficient.  Give it 1ms. */
     local_irq_enable();
     mdelay(1);
diff --git a/xen/arch/x86/mm.c b/xen/arch/x86/mm.c
index 70b87c4830..22787bbd6c 100644
--- a/xen/arch/x86/mm.c
+++ b/xen/arch/x86/mm.c
@@ -1262,7 +1262,7 @@ void put_page_from_l1e(l1_pgentry_t l1e, struct domain *l1e_owner)
              (l1e_owner == pg_owner) )
         {
             struct vcpu *v;
-            cpumask_t *mask = this_cpu(scratch_cpumask);
+            cpumask_t *mask = get_scratch_cpumask();
 
             cpumask_clear(mask);
 
@@ -1279,6 +1279,7 @@ void put_page_from_l1e(l1_pgentry_t l1e, struct domain *l1e_owner)
 
             if ( !cpumask_empty(mask) )
                 flush_tlb_mask(mask);
+            put_scratch_cpumask(mask);
         }
 #endif /* CONFIG_PV_LDT_PAGING */
         put_page(page);
@@ -2903,7 +2904,7 @@ static int _get_page_type(struct page_info *page, unsigned long type,
                  * vital that no other CPUs are left with mappings of a frame
                  * which is about to become writeable to the guest.
                  */
-                cpumask_t *mask = this_cpu(scratch_cpumask);
+                cpumask_t *mask = get_scratch_cpumask();
 
                 BUG_ON(in_irq());
                 cpumask_copy(mask, d->dirty_cpumask);
@@ -2919,6 +2920,7 @@ static int _get_page_type(struct page_info *page, unsigned long type,
                     perfc_incr(need_flush_tlb_flush);
                     flush_tlb_mask(mask);
                 }
+                put_scratch_cpumask(mask);
 
                 /* We lose existing type and validity. */
                 nx &= ~(PGT_type_mask | PGT_validated);
@@ -3635,7 +3637,7 @@ long do_mmuext_op(
         case MMUEXT_TLB_FLUSH_MULTI:
         case MMUEXT_INVLPG_MULTI:
         {
-            cpumask_t *mask = this_cpu(scratch_cpumask);
+            cpumask_t *mask = get_scratch_cpumask();
 
             if ( unlikely(currd != pg_owner) )
                 rc = -EPERM;
@@ -3645,12 +3647,13 @@ long do_mmuext_op(
                                    mask)) )
                 rc = -EINVAL;
             if ( unlikely(rc) )
-                break;
-
-            if ( op.cmd == MMUEXT_TLB_FLUSH_MULTI )
+                ;
+            else if ( op.cmd == MMUEXT_TLB_FLUSH_MULTI )
                 flush_tlb_mask(mask);
             else if ( __addr_ok(op.arg1.linear_addr) )
                 flush_tlb_one_mask(mask, op.arg1.linear_addr);
+            put_scratch_cpumask(mask);
+
             break;
         }
 
@@ -3683,7 +3686,7 @@ long do_mmuext_op(
             else if ( likely(cache_flush_permitted(currd)) )
             {
                 unsigned int cpu;
-                cpumask_t *mask = this_cpu(scratch_cpumask);
+                cpumask_t *mask = get_scratch_cpumask();
 
                 cpumask_clear(mask);
                 for_each_online_cpu(cpu)
@@ -3691,6 +3694,7 @@ long do_mmuext_op(
                                              per_cpu(cpu_sibling_mask, cpu)) )
                         __cpumask_set_cpu(cpu, mask);
                 flush_mask(mask, FLUSH_CACHE);
+                put_scratch_cpumask(mask);
             }
             else
                 rc = -EINVAL;
@@ -4156,12 +4160,13 @@ long do_mmu_update(
          * Force other vCPU-s of the affected guest to pick up L4 entry
          * changes (if any).
          */
-        unsigned int cpu = smp_processor_id();
-        cpumask_t *mask = per_cpu(scratch_cpumask, cpu);
+        cpumask_t *mask = get_scratch_cpumask();
 
-        cpumask_andnot(mask, pt_owner->dirty_cpumask, cpumask_of(cpu));
+        cpumask_andnot(mask, pt_owner->dirty_cpumask,
+                       cpumask_of(smp_processor_id()));
         if ( !cpumask_empty(mask) )
             flush_mask(mask, FLUSH_TLB_GLOBAL | FLUSH_ROOT_PGTBL);
+        put_scratch_cpumask(mask);
     }
 
     perfc_add(num_page_updates, i);
@@ -4353,7 +4358,7 @@ static int __do_update_va_mapping(
             mask = d->dirty_cpumask;
             break;
         default:
-            mask = this_cpu(scratch_cpumask);
+            mask = get_scratch_cpumask();
             rc = vcpumask_to_pcpumask(d, const_guest_handle_from_ptr(bmap_ptr,
                                                                      void),
                                       mask);
@@ -4373,7 +4378,7 @@ static int __do_update_va_mapping(
             mask = d->dirty_cpumask;
             break;
         default:
-            mask = this_cpu(scratch_cpumask);
+            mask = get_scratch_cpumask();
             rc = vcpumask_to_pcpumask(d, const_guest_handle_from_ptr(bmap_ptr,
                                                                      void),
                                       mask);
@@ -4384,6 +4389,16 @@ static int __do_update_va_mapping(
         break;
     }
 
+    switch ( flags & ~UVMF_FLUSHTYPE_MASK )
+    {
+    case UVMF_LOCAL:
+    case UVMF_ALL:
+        break;
+
+    default:
+        put_scratch_cpumask(mask);
+    }
+
     return rc;
 }
 
diff --git a/xen/arch/x86/msi.c b/xen/arch/x86/msi.c
index 161ee60dbe..6d198f8665 100644
--- a/xen/arch/x86/msi.c
+++ b/xen/arch/x86/msi.c
@@ -159,13 +159,15 @@ void msi_compose_msg(unsigned vector, const cpumask_t *cpu_mask, struct msi_msg
 
     if ( cpu_mask )
     {
-        cpumask_t *mask = this_cpu(scratch_cpumask);
+        cpumask_t *mask;
 
         if ( !cpumask_intersects(cpu_mask, &cpu_online_map) )
             return;
 
+        mask = get_scratch_cpumask();
         cpumask_and(mask, cpu_mask, &cpu_online_map);
         msg->dest32 = cpu_mask_to_apicid(mask);
+        put_scratch_cpumask(mask);
     }
 
     msg->address_hi = MSI_ADDR_BASE_HI;
diff --git a/xen/arch/x86/smp.c b/xen/arch/x86/smp.c
index dd0b49d731..084ad32653 100644
--- a/xen/arch/x86/smp.c
+++ b/xen/arch/x86/smp.c
@@ -25,6 +25,31 @@
 #include <irq_vectors.h>
 #include <mach_apic.h>
 
+DEFINE_PER_CPU_READ_MOSTLY(cpumask_var_t, scratch_cpumask);
+
+#ifndef NDEBUG
+cpumask_t *scratch_cpumask(bool use)
+{
+    static DEFINE_PER_CPU(const void *, scratch_cpumask_use);
+
+    /*
+     * Due to reentrancy scratch cpumask cannot be used in IRQ, #MC or NMI
+     * context.
+     */
+    BUG_ON(in_irq() || in_mce_handler() || in_nmi_handler());
+
+    if ( use && unlikely(this_cpu(scratch_cpumask_use)) )
+    {
+        printk("scratch CPU mask already in use by %ps\n",
+               this_cpu(scratch_cpumask_use));
+        BUG();
+    }
+    this_cpu(scratch_cpumask_use) = use ? __builtin_return_address(0) : NULL;
+
+    return use ? this_cpu(scratch_cpumask) : NULL;
+}
+#endif
+
 /* Helper functions to prepare APIC register values. */
 static unsigned int prepare_ICR(unsigned int shortcut, int vector)
 {
diff --git a/xen/arch/x86/smpboot.c b/xen/arch/x86/smpboot.c
index 6c548b0b53..e26b61a8b4 100644
--- a/xen/arch/x86/smpboot.c
+++ b/xen/arch/x86/smpboot.c
@@ -54,7 +54,6 @@ DEFINE_PER_CPU_READ_MOSTLY(cpumask_var_t, cpu_sibling_mask);
 /* representing HT and core siblings of each logical CPU */
 DEFINE_PER_CPU_READ_MOSTLY(cpumask_var_t, cpu_core_mask);
 
-DEFINE_PER_CPU_READ_MOSTLY(cpumask_var_t, scratch_cpumask);
 static cpumask_t scratch_cpu0mask;
 
 DEFINE_PER_CPU_READ_MOSTLY(cpumask_var_t, send_ipi_cpumask);
diff --git a/xen/include/asm-x86/smp.h b/xen/include/asm-x86/smp.h
index 6150363655..acce9c24a4 100644
--- a/xen/include/asm-x86/smp.h
+++ b/xen/include/asm-x86/smp.h
@@ -24,6 +24,20 @@ DECLARE_PER_CPU(cpumask_var_t, cpu_core_mask);
 DECLARE_PER_CPU(cpumask_var_t, scratch_cpumask);
 DECLARE_PER_CPU(cpumask_var_t, send_ipi_cpumask);
 
+#ifndef NDEBUG
+/* Not to be called directly, use {get/put}_scratch_cpumask(). */
+cpumask_t *scratch_cpumask(bool use);
+#define get_scratch_cpumask() scratch_cpumask(true)
+#define put_scratch_cpumask(m) do {             \
+    BUG_ON((m) != this_cpu(scratch_cpumask));   \
+    scratch_cpumask(false);                     \
+    (m) = NULL;                                 \
+} while ( false )
+#else
+#define get_scratch_cpumask() this_cpu(scratch_cpumask)
+#define put_scratch_cpumask(m)
+#endif
+
 /*
  * Do we, for platform reasons, need to actually keep CPUs online when we
  * would otherwise prefer them to be off?
-- 
2.25.0


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