iommu/vt-d: keep shared resources when failed to initialize iommu devices

Data structure drhd->iommu is shared between DMA remapping driver and
interrupt remapping driver, so DMA remapping driver shouldn't release
drhd->iommu when it failed to initialize IOMMU devices. Otherwise it
may cause invalid memory access to the interrupt remapping driver.

Sample stack dump:
[   13.315090] BUG: unable to handle kernel paging request at ffffc9000605a088
[   13.323221] IP: [<ffffffff81461bac>] qi_submit_sync+0x15c/0x400
[   13.330107] PGD 82f81e067 PUD c2f81e067 PMD 82e846067 PTE 0
[   13.336818] Oops: 0002 [#1] SMP
[   13.340757] Modules linked in:
[   13.344422] CPU: 0 PID: 4 Comm: kworker/0:0 Not tainted 3.13.0-rc1-gerry+ #7
[   13.352474] Hardware name: Intel Corporation LH Pass ........../SVRBD-ROW_T,                                               BIOS SE5C600.86B.99.99.x059.091020121352 09/10/2012
[   13.365659] Workqueue: events work_for_cpu_fn
[   13.370774] task: ffff88042ddf00d0 ti: ffff88042ddee000 task.ti: ffff88042dde                                              e000
[   13.379389] RIP: 0010:[<ffffffff81461bac>]  [<ffffffff81461bac>] qi_submit_sy                                              nc+0x15c/0x400
[   13.389055] RSP: 0000:ffff88042ddef940  EFLAGS: 00010002
[   13.395151] RAX: 00000000000005e0 RBX: 0000000000000082 RCX: 0000000200000025
[   13.403308] RDX: ffffc9000605a000 RSI: 0000000000000010 RDI: ffff88042ddb8610
[   13.411446] RBP: ffff88042ddef9a0 R08: 00000000000005d0 R09: 0000000000000001
[   13.419599] R10: 0000000000000000 R11: 000000000000005d R12: 000000000000005c
[   13.427742] R13: ffff88102d84d300 R14: 0000000000000174 R15: ffff88042ddb4800
[   13.435877] FS:  0000000000000000(0000) GS:ffff88043de00000(0000) knlGS:00000                                              00000000000
[   13.445168] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[   13.451749] CR2: ffffc9000605a088 CR3: 0000000001a0b000 CR4: 00000000000407f0
[   13.459895] Stack:
[   13.462297]  ffff88042ddb85d0 000000000000005d ffff88042ddef9b0 0000000000000                                              5d0
[   13.471147]  00000000000005c0 ffff88042ddb8000 000000000000005c 0000000000000                                              015
[   13.480001]  ffff88042ddb4800 0000000000000282 ffff88042ddefa40 ffff88042ddef                                              ac0
[   13.488855] Call Trace:
[   13.491771]  [<ffffffff8146848d>] modify_irte+0x9d/0xd0
[   13.497778]  [<ffffffff8146886d>] intel_setup_ioapic_entry+0x10d/0x290
[   13.505250]  [<ffffffff810a92a6>] ? trace_hardirqs_on_caller+0x16/0x1e0
[   13.512824]  [<ffffffff810346b0>] ? default_init_apic_ldr+0x60/0x60
[   13.519998]  [<ffffffff81468be0>] setup_ioapic_remapped_entry+0x20/0x30
[   13.527566]  [<ffffffff8103683a>] io_apic_setup_irq_pin+0x12a/0x2c0
[   13.534742]  [<ffffffff8136673b>] ? acpi_pci_irq_find_prt_entry+0x2b9/0x2d8
[   13.544102]  [<ffffffff81037fd5>] io_apic_setup_irq_pin_once+0x85/0xa0
[   13.551568]  [<ffffffff8103816f>] ? mp_find_ioapic_pin+0x8f/0xf0
[   13.558434]  [<ffffffff81038044>] io_apic_set_pci_routing+0x34/0x70
[   13.565621]  [<ffffffff8102f4cf>] mp_register_gsi+0xaf/0x1c0
[   13.572111]  [<ffffffff8102f5ee>] acpi_register_gsi_ioapic+0xe/0x10
[   13.579286]  [<ffffffff8102f33f>] acpi_register_gsi+0xf/0x20
[   13.585779]  [<ffffffff81366b86>] acpi_pci_irq_enable+0x171/0x1e3
[   13.592764]  [<ffffffff8146d771>] pcibios_enable_device+0x31/0x40
[   13.599744]  [<ffffffff81320e9b>] do_pci_enable_device+0x3b/0x60
[   13.606633]  [<ffffffff81322248>] pci_enable_device_flags+0xc8/0x120
[   13.613887]  [<ffffffff813222f3>] pci_enable_device+0x13/0x20
[   13.620484]  [<ffffffff8132fa7e>] pcie_port_device_register+0x1e/0x510
[   13.627947]  [<ffffffff810a92a6>] ? trace_hardirqs_on_caller+0x16/0x1e0
[   13.635510]  [<ffffffff810a947d>] ? trace_hardirqs_on+0xd/0x10
[   13.642189]  [<ffffffff813302b8>] pcie_portdrv_probe+0x58/0xc0
[   13.648877]  [<ffffffff81323ba5>] local_pci_probe+0x45/0xa0
[   13.655266]  [<ffffffff8106bc44>] work_for_cpu_fn+0x14/0x20
[   13.661656]  [<ffffffff8106fa79>] process_one_work+0x369/0x710
[   13.668334]  [<ffffffff8106fa02>] ? process_one_work+0x2f2/0x710
[   13.675215]  [<ffffffff81071d56>] ? worker_thread+0x46/0x690
[   13.681714]  [<ffffffff81072194>] worker_thread+0x484/0x690
[   13.688109]  [<ffffffff81071d10>] ? cancel_delayed_work_sync+0x20/0x20
[   13.695576]  [<ffffffff81079c60>] kthread+0xf0/0x110
[   13.701300]  [<ffffffff8108e7bf>] ? local_clock+0x3f/0x50
[   13.707492]  [<ffffffff81079b70>] ? kthread_create_on_node+0x250/0x250
[   13.714959]  [<ffffffff81574d2c>] ret_from_fork+0x7c/0xb0
[   13.721152]  [<ffffffff81079b70>] ? kthread_create_on_node+0x250/0x250
Signed-off-by: NJiang Liu <jiang.liu@linux.intel.com>
Signed-off-by: NJoerg Roedel <joro@8bytes.org>

drivers/iommu/dmar.c

@@ -53,6 +53,7 @@ struct acpi_table_header * __initdata dmar_tbl;
 static acpi_size dmar_tbl_size;
 
 static int alloc_iommu(struct dmar_drhd_unit *drhd);
+static void free_iommu(struct intel_iommu *iommu);
 
 static void __init dmar_register_drhd_unit(struct dmar_drhd_unit *drhd)
 {
@@ -205,25 +206,28 @@ dmar_parse_one_drhd(struct acpi_dmar_header *header)
 	return 0;
 }
 
+static void dmar_free_drhd(struct dmar_drhd_unit *dmaru)
+{
+	if (dmaru->devices && dmaru->devices_cnt)
+		dmar_free_dev_scope(&dmaru->devices, &dmaru->devices_cnt);
+	if (dmaru->iommu)
+		free_iommu(dmaru->iommu);
+	kfree(dmaru);
+}
+
 static int __init dmar_parse_dev(struct dmar_drhd_unit *dmaru)
 {
 	struct acpi_dmar_hardware_unit *drhd;
-	int ret = 0;
 
 	drhd = (struct acpi_dmar_hardware_unit *) dmaru->hdr;
 
 	if (dmaru->include_all)
 		return 0;
 
-	ret = dmar_parse_dev_scope((void *)(drhd + 1),
-				((void *)drhd) + drhd->header.length,
-				&dmaru->devices_cnt, &dmaru->devices,
-				drhd->segment);
-	if (ret) {
-		list_del(&dmaru->list);
-		kfree(dmaru);
-	}
-	return ret;
+	return dmar_parse_dev_scope((void *)(drhd + 1),
+				    ((void *)drhd) + drhd->header.length,
+				    &dmaru->devices_cnt, &dmaru->devices,
+				    drhd->segment);
 }
 
 #ifdef CONFIG_ACPI_NUMA
@@ -435,7 +439,7 @@ dmar_find_matched_drhd_unit(struct pci_dev *dev)
 int __init dmar_dev_scope_init(void)
 {
 	static int dmar_dev_scope_initialized;
-	struct dmar_drhd_unit *drhd, *drhd_n;
+	struct dmar_drhd_unit *drhd;
 	int ret = -ENODEV;
 
 	if (dmar_dev_scope_initialized)
@@ -444,7 +448,7 @@ int __init dmar_dev_scope_init(void)
 	if (list_empty(&dmar_drhd_units))
 		goto fail;
 
-	list_for_each_entry_safe(drhd, drhd_n, &dmar_drhd_units, list) {
+	list_for_each_entry(drhd, &dmar_drhd_units, list) {
 		ret = dmar_parse_dev(drhd);
 		if (ret)
 			goto fail;
@@ -725,12 +729,13 @@ static int alloc_iommu(struct dmar_drhd_unit *drhd)
 	return err;
 }
 
-void free_iommu(struct intel_iommu *iommu)
+static void free_iommu(struct intel_iommu *iommu)
 {
-	if (!iommu)
-		return;
-
-	free_dmar_iommu(iommu);
+	if (iommu->irq) {
+		free_irq(iommu->irq, iommu);
+		irq_set_handler_data(iommu->irq, NULL);
+		destroy_irq(iommu->irq);
+	}
 
 	if (iommu->reg)
 		unmap_iommu(iommu);
@@ -1368,4 +1373,21 @@ int __init dmar_ir_support(void)
 	return dmar->flags & 0x1;
 }
 
+static int __init dmar_free_unused_resources(void)
+{
+	struct dmar_drhd_unit *dmaru, *dmaru_n;
+
+	/* DMAR units are in use */
+	if (irq_remapping_enabled || intel_iommu_enabled)
+		return 0;
+
+	list_for_each_entry_safe(dmaru, dmaru_n, &dmar_drhd_units, list) {
+		list_del(&dmaru->list);
+		dmar_free_drhd(dmaru);
+	}
+
+	return 0;
+}
+
+late_initcall(dmar_free_unused_resources);
 IOMMU_INIT_POST(detect_intel_iommu);

drivers/iommu/intel-iommu.c

@@ -1265,7 +1265,7 @@ static int iommu_init_domains(struct intel_iommu *iommu)
 static void domain_exit(struct dmar_domain *domain);
 static void vm_domain_exit(struct dmar_domain *domain);
 
-void free_dmar_iommu(struct intel_iommu *iommu)
+static void free_dmar_iommu(struct intel_iommu *iommu)
 {
 	struct dmar_domain *domain;
 	int i;
@@ -1290,15 +1290,10 @@ void free_dmar_iommu(struct intel_iommu *iommu)
 	if (iommu->gcmd & DMA_GCMD_TE)
 		iommu_disable_translation(iommu);
 
-	if (iommu->irq) {
-		/* This will mask the irq */
-		free_irq(iommu->irq, iommu);
-		irq_set_handler_data(iommu->irq, NULL);
-		destroy_irq(iommu->irq);
-	}
-
 	kfree(iommu->domains);
 	kfree(iommu->domain_ids);
+	iommu->domains = NULL;
+	iommu->domain_ids = NULL;
 
 	g_iommus[iommu->seq_id] = NULL;
 
@@ -2627,7 +2622,7 @@ static int __init init_dmars(void)
 	return 0;
 error:
 	for_each_active_iommu(iommu, drhd)
-		free_iommu(iommu);
+		free_dmar_iommu(iommu);
 	kfree(g_iommus);
 	return ret;
 }

include/linux/dma_remapping.h

@@ -27,7 +27,6 @@ struct root_entry;
 
 
 #ifdef CONFIG_INTEL_IOMMU
-extern void free_dmar_iommu(struct intel_iommu *iommu);
 extern int iommu_calculate_agaw(struct intel_iommu *iommu);
 extern int iommu_calculate_max_sagaw(struct intel_iommu *iommu);
 extern int dmar_disabled;
@@ -41,9 +40,6 @@ static inline int iommu_calculate_max_sagaw(struct intel_iommu *iommu)
 {
 	return 0;
 }
-static inline void free_dmar_iommu(struct intel_iommu *iommu)
-{
-}
 #define dmar_disabled	(1)
 #define intel_iommu_enabled (0)
 #endif

include/linux/intel-iommu.h

@@ -348,7 +348,6 @@ static inline void __iommu_flush_cache(
 extern struct dmar_drhd_unit * dmar_find_matched_drhd_unit(struct pci_dev *dev);
 extern int dmar_find_matched_atsr_unit(struct pci_dev *dev);
 
-extern void free_iommu(struct intel_iommu *iommu);
 extern int dmar_enable_qi(struct intel_iommu *iommu);
 extern void dmar_disable_qi(struct intel_iommu *iommu);
 extern int dmar_reenable_qi(struct intel_iommu *iommu);