AMD/IOMMU: drop command completion timeout

First and foremost - such timeouts were not signaled to callers, making
them believe they're fine to e.g. free previously unmapped pages.

Mirror VT-d's behavior: A fixed number of loop iterations is not a
suitable way to detect timeouts in an environment (CPU and bus speeds)
independent manner anyway. Furthermore, leaving an in-progress operation
pending when it appears to take too long is problematic: If a command
completed later, the signaling of its completion may instead be
understood to signal a subsequently started command's completion.

Log excessively long processing times (with a progressive threshold) to
have some indication of problems in this area. Allow callers to specify
a non-default timeout bias for this logging, using the same values as
VT-d does, which in particular means a (by default) much larger value
for device IO TLB invalidation.

This is part of XSA-373 / CVE-2021-28692.

Signed-off-by: Jan Beulich <jbeulich@suse.com>
Reviewed-by: Paul Durrant <paul@xen.org>

xen/drivers/passthrough/amd/iommu_cmd.c

@@ -46,10 +46,12 @@ static void send_iommu_command(struct amd_iommu *iommu,
     writel(tail, iommu->mmio_base + IOMMU_CMD_BUFFER_TAIL_OFFSET);
 }
 
-static void flush_command_buffer(struct amd_iommu *iommu)
+static void flush_command_buffer(struct amd_iommu *iommu,
+                                 unsigned int timeout_base)
 {
-    unsigned int cmd[4], status, loop_count;
-    bool comp_wait;
+    uint32_t cmd[4];
+    s_time_t start, timeout;
+    static unsigned int __read_mostly threshold = 1;
 
     /* RW1C 'ComWaitInt' in status register */
     writel(IOMMU_STATUS_COMP_WAIT_INT,
@@ -65,22 +67,29 @@ static void flush_command_buffer(struct amd_iommu *iommu)
                          IOMMU_COMP_WAIT_I_FLAG_SHIFT, &cmd[0]);
     send_iommu_command(iommu, cmd);
 
-    /* Make loop_count long enough for polling completion wait bit */
-    loop_count = 1000;
-    do {
-        status = readl(iommu->mmio_base + IOMMU_STATUS_MMIO_OFFSET);
-        comp_wait = status & IOMMU_STATUS_COMP_WAIT_INT;
-        --loop_count;
-    } while ( !comp_wait && loop_count );
-
-    if ( comp_wait )
+    start = NOW();
+    timeout = start + (timeout_base ?: 100) * MILLISECS(threshold);
+    while ( !(readl(iommu->mmio_base + IOMMU_STATUS_MMIO_OFFSET) &
+              IOMMU_STATUS_COMP_WAIT_INT) )
     {
-        /* RW1C 'ComWaitInt' in status register */
-        writel(IOMMU_STATUS_COMP_WAIT_INT,
-               iommu->mmio_base + IOMMU_STATUS_MMIO_OFFSET);
-        return;
+        if ( timeout && NOW() > timeout )
+        {
+            threshold |= threshold << 1;
+            printk(XENLOG_WARNING
+                   "AMD IOMMU %pp: %scompletion wait taking too long\n",
+                   &PCI_SBDF2(iommu->seg, iommu->bdf),
+                   timeout_base ? "iotlb " : "");
+            timeout = 0;
+        }
+        cpu_relax();
     }
-    AMD_IOMMU_DEBUG("Warning: ComWaitInt bit did not assert!\n");
+
+    if ( !timeout )
+        printk(XENLOG_WARNING
+               "AMD IOMMU %pp: %scompletion wait took %lums\n",
+               &PCI_SBDF2(iommu->seg, iommu->bdf),
+               timeout_base ? "iotlb " : "",
+               (NOW() - start) / 10000000);
 }
 
 /* Build low level iommu command messages */
@@ -291,7 +300,7 @@ void amd_iommu_flush_iotlb(u8 devfn, const struct pci_dev *pdev,
     /* send INVALIDATE_IOTLB_PAGES command */
     spin_lock_irqsave(&iommu->lock, flags);
     invalidate_iotlb_pages(iommu, maxpend, 0, queueid, daddr, req_id, order);
-    flush_command_buffer(iommu);
+    flush_command_buffer(iommu, iommu_dev_iotlb_timeout);
     spin_unlock_irqrestore(&iommu->lock, flags);
 }
 
@@ -328,7 +337,7 @@ static void _amd_iommu_flush_pages(struct domain *d,
     {
         spin_lock_irqsave(&iommu->lock, flags);
         invalidate_iommu_pages(iommu, daddr, dom_id, order);
-        flush_command_buffer(iommu);
+        flush_command_buffer(iommu, 0);
         spin_unlock_irqrestore(&iommu->lock, flags);
     }
 
@@ -352,7 +361,7 @@ void amd_iommu_flush_device(struct amd_iommu *iommu, uint16_t bdf)
     ASSERT( spin_is_locked(&iommu->lock) );
 
     invalidate_dev_table_entry(iommu, bdf);
-    flush_command_buffer(iommu);
+    flush_command_buffer(iommu, 0);
 }
 
 void amd_iommu_flush_intremap(struct amd_iommu *iommu, uint16_t bdf)
@@ -360,7 +369,7 @@ void amd_iommu_flush_intremap(struct amd_iommu *iommu, uint16_t bdf)
     ASSERT( spin_is_locked(&iommu->lock) );
 
     invalidate_interrupt_table(iommu, bdf);
-    flush_command_buffer(iommu);
+    flush_command_buffer(iommu, 0);
 }
 
 void amd_iommu_flush_all_caches(struct amd_iommu *iommu)
@@ -368,7 +377,7 @@ void amd_iommu_flush_all_caches(struct amd_iommu *iommu)
     ASSERT( spin_is_locked(&iommu->lock) );
 
     invalidate_iommu_all(iommu);
-    flush_command_buffer(iommu);
+    flush_command_buffer(iommu, 0);
 }
 
 void amd_iommu_send_guest_cmd(struct amd_iommu *iommu, u32 cmd[])
@@ -378,7 +387,8 @@ void amd_iommu_send_guest_cmd(struct amd_iommu *iommu, u32 cmd[])
     spin_lock_irqsave(&iommu->lock, flags);
 
     send_iommu_command(iommu, cmd);
-    flush_command_buffer(iommu);
+    /* TBD: Timeout selection may require peeking into cmd[]. */
+    flush_command_buffer(iommu, 0);
 
     spin_unlock_irqrestore(&iommu->lock, flags);
 }