[PATCH 5/5] vtd: Move intremap table to xenheap

Interrupt remapping entries often needs to be accessed, and we're creating
pointers to it on demand, which brings a lot of complexity (e.g
GET_IREMAP_ENTRY() macro), move it to xenheap such that it's persistently
mapped and we won't have to worry about mapping and unmapping individual
intremap table pages.

Signed-off-by: Teddy Astie <[email protected]>
---
 xen/drivers/passthrough/vtd/intremap.c | 61 +++++++++-----------------
 xen/drivers/passthrough/vtd/iommu.h    | 16 +------
 xen/drivers/passthrough/vtd/utils.c    | 22 +++-------
 3 files changed, 26 insertions(+), 73 deletions(-)

diff --git a/xen/drivers/passthrough/vtd/intremap.c b/xen/drivers/passthrough/vtd/intremap.c
index dd2788efd7..fc683516cb 100644
--- a/xen/drivers/passthrough/vtd/intremap.c
+++ b/xen/drivers/passthrough/vtd/intremap.c
@@ -17,6 +17,7 @@
  * Copyright (C) Xiaohui Xin <[email protected]>
  */
 
+#include <xen/mm.h>
 #include <xen/irq.h>
 #include <xen/sched.h>
 #include <xen/iommu.h>
@@ -208,21 +209,19 @@ static void update_irte(struct vtd_iommu *iommu, struct iremap_entry *entry,
 /* Mark specified intr remap entry as free */
 static void free_remap_entry(struct vtd_iommu *iommu, int index)
 {
-    struct iremap_entry *iremap_entry = NULL, *iremap_entries, new_ire = { };
+    struct iremap_entry *iremap_entry = NULL, new_ire = { };
 
     if ( index < 0 || index > IREMAP_ENTRY_NR - 1 )
         return;
 
     ASSERT(spin_is_locked(&iommu->intremap.lock));
 
-    GET_IREMAP_ENTRY(iommu->intremap.maddr, index,
-                     iremap_entries, iremap_entry);
+    iremap_entry = &iommu->intremap.entries[index];
 
     update_irte(iommu, iremap_entry, &new_ire, false);
     iommu_sync_cache(iremap_entry, sizeof(*iremap_entry));
     iommu_flush_iec_index(iommu, 0, index);
 
-    unmap_vtd_domain_page(iremap_entries);
     iommu->intremap.num--;
 }
 
@@ -232,25 +231,13 @@ static void free_remap_entry(struct vtd_iommu *iommu, int index)
  */
 static unsigned int alloc_remap_entry(struct vtd_iommu *iommu, unsigned int nr)
 {
-    struct iremap_entry *iremap_entries = NULL;
     unsigned int i, found;
 
     ASSERT(spin_is_locked(&iommu->intremap.lock));
 
     for ( found = i = 0; i < IREMAP_ENTRY_NR; i++ )
     {
-        struct iremap_entry *p;
-        if ( i % (1 << IREMAP_ENTRY_ORDER) == 0 )
-        {
-            /* This entry across page boundry */
-            if ( iremap_entries )
-                unmap_vtd_domain_page(iremap_entries);
-
-            GET_IREMAP_ENTRY(iommu->intremap.maddr, i,
-                             iremap_entries, p);
-        }
-        else
-            p = &iremap_entries[i % (1 << IREMAP_ENTRY_ORDER)];
+        struct iremap_entry *p = &iommu->intremap.entries[i];
 
         if ( p->val ) /* not a free entry */
             found = 0;
@@ -258,9 +245,6 @@ static unsigned int alloc_remap_entry(struct vtd_iommu *iommu, unsigned int nr)
             break;
     }
 
-    if ( iremap_entries )
-        unmap_vtd_domain_page(iremap_entries);
-
     if ( i < IREMAP_ENTRY_NR )
         iommu->intremap.num += nr;
 
@@ -270,7 +254,7 @@ static unsigned int alloc_remap_entry(struct vtd_iommu *iommu, unsigned int nr)
 static int remap_entry_to_ioapic_rte(
     struct vtd_iommu *iommu, int index, struct IO_APIC_route_entry *old_rte)
 {
-    struct iremap_entry *iremap_entry = NULL, *iremap_entries;
+    struct iremap_entry *iremap_entry = NULL;
     unsigned long flags;
 
     if ( index < 0 || index > IREMAP_ENTRY_NR - 1 )
@@ -283,15 +267,13 @@ static int remap_entry_to_ioapic_rte(
 
     spin_lock_irqsave(&iommu->intremap.lock, flags);
 
-    GET_IREMAP_ENTRY(iommu->intremap.maddr, index,
-                     iremap_entries, iremap_entry);
+    iremap_entry = &iommu->intremap.entries[index];
 
     if ( iremap_entry->val == 0 )
     {
         dprintk(XENLOG_ERR VTDPREFIX,
                 "IO-APIC index (%d) has an empty entry\n",
                 index);
-        unmap_vtd_domain_page(iremap_entries);
         spin_unlock_irqrestore(&iommu->intremap.lock, flags);
         return -EFAULT;
     }
@@ -309,7 +291,6 @@ static int remap_entry_to_ioapic_rte(
         old_rte->dest.logical.logical_dest = iremap_entry->remap.dst >> 8;
     }
 
-    unmap_vtd_domain_page(iremap_entries);
     spin_unlock_irqrestore(&iommu->intremap.lock, flags);
 
     return 0;
@@ -319,7 +300,7 @@ static int ioapic_rte_to_remap_entry(struct vtd_iommu *iommu,
     int apic, unsigned int ioapic_pin, struct IO_APIC_route_entry *old_rte,
     struct IO_APIC_route_entry new_rte)
 {
-    struct iremap_entry *iremap_entry = NULL, *iremap_entries;
+    struct iremap_entry *iremap_entry = NULL;
     struct iremap_entry new_ire;
     struct IO_APIC_route_remap_entry *remap_rte;
     int index;
@@ -347,8 +328,7 @@ static int ioapic_rte_to_remap_entry(struct vtd_iommu *iommu,
         return -EFAULT;
     }
 
-    GET_IREMAP_ENTRY(iommu->intremap.maddr, index,
-                     iremap_entries, iremap_entry);
+    iremap_entry = &iommu->intremap.entries[index];
 
     new_ire = *iremap_entry;
 
@@ -388,7 +368,6 @@ static int ioapic_rte_to_remap_entry(struct vtd_iommu *iommu,
     iommu_sync_cache(iremap_entry, sizeof(*iremap_entry));
     iommu_flush_iec_index(iommu, 0, index);
 
-    unmap_vtd_domain_page(iremap_entries);
     spin_unlock_irqrestore(&iommu->intremap.lock, flags);
     return 0;
 }
@@ -500,7 +479,7 @@ static int msi_msg_to_remap_entry(
     struct vtd_iommu *iommu, struct pci_dev *pdev,
     struct msi_desc *msi_desc, struct msi_msg *msg)
 {
-    struct iremap_entry *iremap_entry = NULL, *iremap_entries, new_ire = { };
+    struct iremap_entry *iremap_entry = NULL, new_ire = { };
     struct msi_msg_remap_entry *remap_rte;
     unsigned int index, i, nr = 1;
     unsigned long flags;
@@ -556,8 +535,7 @@ static int msi_msg_to_remap_entry(
         return -EFAULT;
     }
 
-    GET_IREMAP_ENTRY(iommu->intremap.maddr, index,
-                     iremap_entries, iremap_entry);
+    iremap_entry = &iommu->intremap.entries[index];
 
     if ( !pi_desc )
     {
@@ -604,7 +582,6 @@ static int msi_msg_to_remap_entry(
     iommu_sync_cache(iremap_entry, sizeof(*iremap_entry));
     iommu_flush_iec_index(iommu, 0, index);
 
-    unmap_vtd_domain_page(iremap_entries);
     spin_unlock_irqrestore(&iommu->intremap.lock, flags);
 
     return alloc;
@@ -628,7 +605,7 @@ int __init cf_check intel_setup_hpet_msi(struct msi_desc *msi_desc)
     unsigned long flags;
     int rc = 0;
 
-    if ( !iommu->intremap.maddr )
+    if ( !iommu->intremap.entries )
         return 0;
 
     spin_lock_irqsave(&iommu->intremap.lock, flags);
@@ -663,7 +640,7 @@ int enable_intremap(struct vtd_iommu *iommu, int eim)
     sts = dmar_readl(iommu->reg, DMAR_GSTS_REG);
 
     /* Return if already enabled by Xen */
-    if ( (sts & DMA_GSTS_IRES) && iommu->intremap.maddr )
+    if ( (sts & DMA_GSTS_IRES) && iommu->intremap.entries )
         return 0;
 
     if ( !(sts & DMA_GSTS_QIES) )
@@ -679,16 +656,18 @@ int enable_intremap(struct vtd_iommu *iommu, int eim)
                " Compatibility Format Interrupts permitted on IOMMU #%u:"
                " Device pass-through will be insecure\n", iommu->index);
 
-    if ( iommu->intremap.maddr == 0 )
+    if ( !iommu->intremap.entries )
     {
-        iommu->intremap.maddr = alloc_pgtable_maddr(IREMAP_ARCH_PAGE_NR,
-                                                    iommu->node);
-        if ( iommu->intremap.maddr == 0 )
+        iommu->intremap.entries =
+            alloc_xenheap_pages(get_order_from_pages(IREMAP_ARCH_PAGE_NR),
+                                                     MEMF_node(iommu->node));
+        if ( !iommu->intremap.entries )
         {
             dprintk(XENLOG_WARNING VTDPREFIX,
-                    "Cannot allocate memory for ir_ctrl->iremap_maddr\n");
+                    "Cannot allocate memory for iommu->intremap.entries\n");
             return -ENOMEM;
         }
+        memset(iommu->intremap.entries, 0, IREMAP_ARCH_PAGE_NR * PAGE_SIZE);
 
         iommu->intremap.num = 0;
     }
@@ -700,7 +679,7 @@ int enable_intremap(struct vtd_iommu *iommu, int eim)
      * Interrupt Mode.
      */
     dmar_writeq(iommu->reg, DMAR_IRTA_REG,
-                iommu->intremap.maddr | IRTA_REG_TABLE_SIZE |
+                virt_to_maddr(iommu->intremap.entries) | IRTA_REG_TABLE_SIZE |
                 (eim ? IRTA_EIME : 0));
 
     /* set SIRTP */
diff --git a/xen/drivers/passthrough/vtd/iommu.h b/xen/drivers/passthrough/vtd/iommu.h
index ccb00889d7..0cd2c2ef3a 100644
--- a/xen/drivers/passthrough/vtd/iommu.h
+++ b/xen/drivers/passthrough/vtd/iommu.h
@@ -357,20 +357,6 @@ struct iremap_entry {
 #define iremap_set_present(v) do {(v).lo |= 1;} while(0)
 #define iremap_clear_present(v) do {(v).lo &= ~1;} while(0)
 
-/*
- * Get the intr remap entry:
- * maddr   - machine addr of the table
- * index   - index of the entry
- * entries - return addr of the page holding this entry, need unmap it
- * entry   - return required entry
- */
-#define GET_IREMAP_ENTRY(maddr, index, entries, entry)                        \
-do {                                                                          \
-    entries = (struct iremap_entry *)map_vtd_domain_page(                     \
-              (maddr) + (( (index) >> IREMAP_ENTRY_ORDER ) << PAGE_SHIFT ) ); \
-    entry = &entries[(index) % (1 << IREMAP_ENTRY_ORDER)];                    \
-} while(0)
-
 /* queue invalidation entry */
 struct qinval_entry {
     union {
@@ -491,7 +477,7 @@ struct vtd_iommu {
     uint64_t qinval_maddr;   /* queue invalidation page machine address */
 
     struct {
-        uint64_t maddr;   /* interrupt remap table machine address */
+        struct iremap_entry *entries; /* interrupt remap table entries */
         unsigned int num; /* total num of used interrupt remap entry */
         spinlock_t lock;  /* lock for irq remapping table */
     } intremap;
diff --git a/xen/drivers/passthrough/vtd/utils.c b/xen/drivers/passthrough/vtd/utils.c
index 7c4d032f4f..3ae4d35e2d 100644
--- a/xen/drivers/passthrough/vtd/utils.c
+++ b/xen/drivers/passthrough/vtd/utils.c
@@ -187,11 +187,12 @@ void cf_check vtd_dump_iommu_info(unsigned char key)
         {
             /* Dump interrupt remapping table. */
             uint64_t irta = dmar_readq(iommu->reg, DMAR_IRTA_REG);
-            uint64_t iremap_maddr = irta & PAGE_MASK;
             unsigned int nr_entry = 1 << ((irta & 0xF) + 1);
-            struct iremap_entry *iremap_entries = NULL;
             unsigned int print_cnt = 0;
 
+            /* Hardware must be using the same table as us. */
+            ASSERT((irta & PAGE_MASK) == virt_to_maddr(iommu->intremap.entries));
+
             printk("  Interrupt remapping table (nr_entry=%#x. "
                 "Only dump P=1 entries here):\n", nr_entry);
             printk("R means remapped format, P means posted format.\n");
@@ -199,18 +200,7 @@ void cf_check vtd_dump_iommu_info(unsigned char key)
             printk("P:       SVT  SQ   SID  V  AVL FPD              PDA  URG P\n");
             for ( i = 0; i < nr_entry; i++ )
             {
-                struct iremap_entry *p;
-                if ( i % (1 << IREMAP_ENTRY_ORDER) == 0 )
-                {
-                    /* This entry across page boundry */
-                    if ( iremap_entries )
-                        unmap_vtd_domain_page(iremap_entries);
-
-                    GET_IREMAP_ENTRY(iremap_maddr, i,
-                                     iremap_entries, p);
-                }
-                else
-                    p = &iremap_entries[i % (1 << IREMAP_ENTRY_ORDER)];
+                struct iremap_entry *p = &iommu->intremap.entries[i];
 
                 if ( !p->remap.p )
                     continue;
@@ -231,8 +221,6 @@ void cf_check vtd_dump_iommu_info(unsigned char key)
 
                 print_cnt++;
             }
-            if ( iremap_entries )
-                unmap_vtd_domain_page(iremap_entries);
             if ( iommu->intremap.num != print_cnt )
                 printk("Warning: Print %u IRTE (actually have %u)!\n",
                         print_cnt, iommu->intremap.num);
@@ -251,7 +239,7 @@ void cf_check vtd_dump_iommu_info(unsigned char key)
         {
             iommu = ioapic_to_iommu(mp_ioapics[apic].mpc_apicid);
 
-            if ( !iommu->intremap.maddr || !iommu->intremap.num )
+            if ( !iommu->intremap.entries || !iommu->intremap.num )
                 continue;
 
             printk( "\nRedirection table of IOAPIC %x:\n", apic);
-- 
2.54.0



-- 
Teddy Astie | Vates XCP-ng Developer

XCP-ng & Xen Orchestra - Vates solutions

web: https://vates.tech