IOMMU: propagate IOMMU Device-TLB flush error up to IOMMU suspending (top level ones)

Signed-off-by: Quan Xu <quan.xu@intel.com>
Acked-by: Kevin Tian <kevin.tian@intel.com>
Acked-by: Suravee Suthikulpanit <suravee.suthikulpanit@amd.com>
Reviewed-by: Jan Beulich <jbeulich@suse.com>

xen/arch/x86/acpi/power.c

@@ -43,36 +43,70 @@ struct acpi_sleep_info acpi_sinfo;
 
 void do_suspend_lowlevel(void);
 
+enum dev_power_saved
+{
+    SAVED_NONE,
+    SAVED_CONSOLE,
+    SAVED_TIME,
+    SAVED_I8259A,
+    SAVED_IOAPIC,
+    SAVED_IOMMU,
+    SAVED_LAPIC,
+    SAVED_ALL,
+};
+
 static int device_power_down(void)
 {
-    console_suspend();
+    if ( console_suspend() )
+        return SAVED_NONE;
 
-    time_suspend();
+    if ( time_suspend() )
+        return SAVED_CONSOLE;
 
-    i8259A_suspend();
+    if ( i8259A_suspend() )
+        return SAVED_TIME;
 
+    /* ioapic_suspend cannot fail */
     ioapic_suspend();
 
-    iommu_suspend();
+    if ( iommu_suspend() )
+        return SAVED_IOAPIC;
 
-    lapic_suspend();
+    if ( lapic_suspend() )
+        return SAVED_IOMMU;
 
-    return 0;
+    return SAVED_ALL;
 }
 
-static void device_power_up(void)
+static void device_power_up(enum dev_power_saved saved)
 {
-    lapic_resume();
-
-    iommu_resume();
-
-    ioapic_resume();
-
-    i8259A_resume();
-
-    time_resume();
-
-    console_resume();
+    switch ( saved )
+    {
+    case SAVED_ALL:
+    case SAVED_LAPIC:
+        lapic_resume();
+        /* fall through */
+    case SAVED_IOMMU:
+        iommu_resume();
+        /* fall through */
+    case SAVED_IOAPIC:
+        ioapic_resume();
+        /* fall through */
+    case SAVED_I8259A:
+        i8259A_resume();
+        /* fall through */
+    case SAVED_TIME:
+        time_resume();
+        /* fall through */
+    case SAVED_CONSOLE:
+        console_resume();
+        /* fall through */
+    case SAVED_NONE:
+        break;
+    default:
+        BUG();
+        break;
+    }
 }
 
 static void freeze_domains(void)
@@ -165,12 +199,16 @@ static int enter_state(u32 state)
     local_irq_save(flags);
     spin_debug_disable();
 
-    if ( (error = device_power_down()) )
+    if ( (error = device_power_down()) != SAVED_ALL )
     {
         printk(XENLOG_ERR "Some devices failed to power down.");
         system_state = SYS_STATE_resume;
+        device_power_up(error);
+        error = -EIO;
         goto done;
     }
+    else
+        error = 0;
 
     ACPI_FLUSH_CPU_CACHE();
 
@@ -196,7 +234,7 @@ static int enter_state(u32 state)
     write_cr4(cr4 & ~X86_CR4_MCE);
     write_efer(read_efer());
 
-    device_power_up();
+    device_power_up(SAVED_ALL);
 
     mcheck_init(&boot_cpu_data, 0);
     write_cr4(cr4);

xen/drivers/passthrough/amd/iommu_init.c

@@ -1362,7 +1362,14 @@ static void invalidate_all_devices(void)
     iterate_ivrs_mappings(_invalidate_all_devices);
 }
 
-void amd_iommu_suspend(void)
+int amd_iommu_suspend(void)
+{
+    amd_iommu_crash_shutdown();
+
+    return 0;
+}
+
+void amd_iommu_crash_shutdown(void)
 {
     struct amd_iommu *iommu;
 

xen/drivers/passthrough/amd/pci_amd_iommu.c

@@ -633,6 +633,6 @@ const struct iommu_ops amd_iommu_ops = {
     .suspend = amd_iommu_suspend,
     .resume = amd_iommu_resume,
     .share_p2m = amd_iommu_share_p2m,
-    .crash_shutdown = amd_iommu_suspend,
+    .crash_shutdown = amd_iommu_crash_shutdown,
     .dump_p2m_table = amd_dump_p2m_table,
 };

xen/drivers/passthrough/iommu.c

@@ -379,10 +379,12 @@ int __init iommu_setup(void)
     return rc;
 }
 
-void iommu_suspend()
+int iommu_suspend()
 {
     if ( iommu_enabled )
-        iommu_get_ops()->suspend();
+        return iommu_get_ops()->suspend();
+
+    return 0;
 }
 
 void iommu_resume()

xen/drivers/passthrough/vtd/iommu.c

@@ -541,7 +541,7 @@ static int iommu_flush_iotlb_psi(
     return status;
 }
 
-static void iommu_flush_all(void)
+static int __must_check iommu_flush_all(void)
 {
     struct acpi_drhd_unit *drhd;
     struct iommu *iommu;
@@ -555,6 +555,8 @@ static void iommu_flush_all(void)
         flush_dev_iotlb = find_ats_dev_drhd(iommu) ? 1 : 0;
         iommu_flush_iotlb_global(iommu, 0, flush_dev_iotlb);
     }
+
+    return 0;
 }
 
 static void __intel_iommu_iotlb_flush(struct domain *d, unsigned long gfn,
@@ -1259,7 +1261,9 @@ static void __hwdom_init intel_iommu_hwdom_init(struct domain *d)
     setup_hwdom_pci_devices(d, setup_hwdom_device);
     setup_hwdom_rmrr(d);
 
-    iommu_flush_all();
+    if ( iommu_flush_all() )
+        printk(XENLOG_WARNING VTDPREFIX
+               " IOMMU flush all failed for hardware domain\n");
 
     for_each_drhd_unit ( drhd )
     {
@@ -2001,7 +2005,7 @@ int adjust_vtd_irq_affinities(void)
 }
 __initcall(adjust_vtd_irq_affinities);
 
-static int init_vtd_hw(void)
+static int __must_check init_vtd_hw(void)
 {
     struct acpi_drhd_unit *drhd;
     struct iommu *iommu;
@@ -2099,8 +2103,8 @@ static int init_vtd_hw(void)
             return -EIO;
         }
     }
-    iommu_flush_all();
-    return 0;
+
+    return iommu_flush_all();
 }
 
 static void __hwdom_init setup_hwdom_rmrr(struct domain *d)
@@ -2389,16 +2393,25 @@ static int intel_iommu_group_id(u16 seg, u8 bus, u8 devfn)
 }
 
 static u32 iommu_state[MAX_IOMMUS][MAX_IOMMU_REGS];
-static void vtd_suspend(void)
+
+static int __must_check vtd_suspend(void)
 {
     struct acpi_drhd_unit *drhd;
     struct iommu *iommu;
     u32    i;
+    int rc;
 
     if ( !iommu_enabled )
-        return;
+        return 0;
 
-    iommu_flush_all();
+    rc = iommu_flush_all();
+    if ( unlikely(rc) )
+    {
+        printk(XENLOG_WARNING VTDPREFIX
+               " suspend: IOMMU flush all failed: %d\n", rc);
+
+        return rc;
+    }
 
     for_each_drhd_unit ( drhd )
     {
@@ -2427,6 +2440,8 @@ static void vtd_suspend(void)
         if ( !iommu_intremap && iommu_qinval )
             disable_qinval(iommu);
     }
+
+    return 0;
 }
 
 static void vtd_crash_shutdown(void)
@@ -2437,7 +2452,9 @@ static void vtd_crash_shutdown(void)
     if ( !iommu_enabled )
         return;
 
-    iommu_flush_all();
+    if ( iommu_flush_all() )
+        printk(XENLOG_WARNING VTDPREFIX
+               " crash shutdown: IOMMU flush all failed\n");
 
     for_each_drhd_unit ( drhd )
     {

xen/include/asm-x86/hvm/svm/amd-iommu-proto.h

@@ -120,7 +120,7 @@ extern unsigned long *shared_intremap_inuse;
 
 /* power management support */
 void amd_iommu_resume(void);
-void amd_iommu_suspend(void);
+int __must_check amd_iommu_suspend(void);
 void amd_iommu_crash_shutdown(void);
 
 /* guest iommu support */

xen/include/xen/iommu.h

@@ -175,7 +175,7 @@ struct iommu_ops {
     unsigned int (*read_apic_from_ire)(unsigned int apic, unsigned int reg);
     int (*setup_hpet_msi)(struct msi_desc *);
 #endif /* CONFIG_X86 */
-    void (*suspend)(void);
+    int __must_check (*suspend)(void);
     void (*resume)(void);
     void (*share_p2m)(struct domain *d);
     void (*crash_shutdown)(void);
@@ -185,7 +185,7 @@ struct iommu_ops {
     void (*dump_p2m_table)(struct domain *d);
 };
 
-void iommu_suspend(void);
+int __must_check iommu_suspend(void);
 void iommu_resume(void);
 void iommu_crash_shutdown(void);
 int iommu_get_reserved_device_memory(iommu_grdm_t *, void *);