Merge tag 'please-pull-apei' into x86/ras

APEI is currently implemented so that it depends on x86 hardware.
The primary dependency is that GHES uses the x86 NMI for hardware
error notification and MCE for memory error handling. These patches
remove that dependency.

Other APEI features such as error reporting via external IRQ, error
serialization, or error injection, do not require changes to use them
on non-x86 architectures.

The following patch set eliminates the APEI Kconfig x86 dependency
by making these changes:
- treat NMI notification as GHES architecture - HAVE_ACPI_APEI_NMI
- group and wrap around #ifdef CONFIG_HAVE_ACPI_APEI_NMI code which
  is used only for NMI path
- identify architectural boxes and abstract it accordingly (tlb flush and MCE)
- rework ioremap for both IRQ and NMI context

NMI code is kept in ghes.c file since NMI and IRQ context are tightly coupled.

Note, these patches introduce no functional changes for x86. The NMI notification
feature is hard selected for x86. Architectures that want to use this
feature should also provide NMI code infrastructure.

4 files changed, 28 insertions, 25 deletions

diff --git a/drivers/iommu/amd_iommu_v2.c b/drivers/iommu/amd_iommu_v2.c
index d4daa05efe60..499b4366a98d 100644
--- a/drivers/iommu/amd_iommu_v2.c
+++ b/drivers/iommu/amd_iommu_v2.c
@@ -45,7 +45,7 @@ struct pri_queue {
 struct pasid_state {
 	struct list_head list;			/* For global state-list */
 	atomic_t count;				/* Reference count */
-	atomic_t mmu_notifier_count;		/* Counting nested mmu_notifier
+	unsigned mmu_notifier_count;		/* Counting nested mmu_notifier
 						   calls */
 	struct task_struct *task;		/* Task bound to this PASID */
 	struct mm_struct *mm;			/* mm_struct for the faults */
@@ -53,7 +53,8 @@ struct pasid_state {
 	struct pri_queue pri[PRI_QUEUE_SIZE];	/* PRI tag states */
 	struct device_state *device_state;	/* Link to our device_state */
 	int pasid;				/* PASID index */
-	spinlock_t lock;			/* Protect pri_queues */
+	spinlock_t lock;			/* Protect pri_queues and
+						   mmu_notifer_count */
 	wait_queue_head_t wq;			/* To wait for count == 0 */
 };
 
@@ -431,15 +432,19 @@ static void mn_invalidate_range_start(struct mmu_notifier *mn,
 {
 	struct pasid_state *pasid_state;
 	struct device_state *dev_state;
+	unsigned long flags;
 
 	pasid_state = mn_to_state(mn);
 	dev_state   = pasid_state->device_state;
 
-	if (atomic_add_return(1, &pasid_state->mmu_notifier_count) == 1) {
+	spin_lock_irqsave(&pasid_state->lock, flags);
+	if (pasid_state->mmu_notifier_count == 0) {
 		amd_iommu_domain_set_gcr3(dev_state->domain,
 					  pasid_state->pasid,
 					  __pa(empty_page_table));
 	}
+	pasid_state->mmu_notifier_count += 1;
+	spin_unlock_irqrestore(&pasid_state->lock, flags);
 }
 
 static void mn_invalidate_range_end(struct mmu_notifier *mn,
@@ -448,15 +453,19 @@ static void mn_invalidate_range_end(struct mmu_notifier *mn,
 {
 	struct pasid_state *pasid_state;
 	struct device_state *dev_state;
+	unsigned long flags;
 
 	pasid_state = mn_to_state(mn);
 	dev_state   = pasid_state->device_state;
 
-	if (atomic_dec_and_test(&pasid_state->mmu_notifier_count)) {
+	spin_lock_irqsave(&pasid_state->lock, flags);
+	pasid_state->mmu_notifier_count -= 1;
+	if (pasid_state->mmu_notifier_count == 0) {
 		amd_iommu_domain_set_gcr3(dev_state->domain,
 					  pasid_state->pasid,
 					  __pa(pasid_state->mm->pgd));
 	}
+	spin_unlock_irqrestore(&pasid_state->lock, flags);
 }
 
 static void mn_release(struct mmu_notifier *mn, struct mm_struct *mm)
@@ -650,7 +659,6 @@ int amd_iommu_bind_pasid(struct pci_dev *pdev, int pasid,
 		goto out;
 
 	atomic_set(&pasid_state->count, 1);
-	atomic_set(&pasid_state->mmu_notifier_count, 0);
 	init_waitqueue_head(&pasid_state->wq);
 	spin_lock_init(&pasid_state->lock);
 
diff --git a/drivers/iommu/fsl_pamu.c b/drivers/iommu/fsl_pamu.c
index b99dd88e31b9..bb446d742a2d 100644
--- a/drivers/iommu/fsl_pamu.c
+++ b/drivers/iommu/fsl_pamu.c
@@ -170,10 +170,10 @@ int pamu_disable_liodn(int liodn)
 static unsigned int map_addrspace_size_to_wse(phys_addr_t addrspace_size)
 {
 	/* Bug if not a power of 2 */
-	BUG_ON(!is_power_of_2(addrspace_size));
+	BUG_ON((addrspace_size & (addrspace_size - 1)));
 
 	/* window size is 2^(WSE+1) bytes */
-	return __ffs(addrspace_size) - 1;
+	return fls64(addrspace_size) - 2;
 }
 
 /* Derive the PAACE window count encoding for the subwindow count */
@@ -351,7 +351,7 @@ int pamu_config_ppaace(int liodn, phys_addr_t win_addr, phys_addr_t win_size,
 	struct paace *ppaace;
 	unsigned long fspi;
 
-	if (!is_power_of_2(win_size) || win_size < PAMU_PAGE_SIZE) {
+	if ((win_size & (win_size - 1)) || win_size < PAMU_PAGE_SIZE) {
 		pr_debug("window size too small or not a power of two %llx\n", win_size);
 		return -EINVAL;
 	}
@@ -464,7 +464,7 @@ int pamu_config_spaace(int liodn, u32 subwin_cnt, u32 subwin,
 		return -ENOENT;
 	}
 
-	if (!is_power_of_2(subwin_size) || subwin_size < PAMU_PAGE_SIZE) {
+	if ((subwin_size & (subwin_size - 1)) || subwin_size < PAMU_PAGE_SIZE) {
 		pr_debug("subwindow size out of range, or not a power of 2\n");
 		return -EINVAL;
 	}
diff --git a/drivers/iommu/fsl_pamu_domain.c b/drivers/iommu/fsl_pamu_domain.c
index 93072ba44b1d..af47648301a9 100644
--- a/drivers/iommu/fsl_pamu_domain.c
+++ b/drivers/iommu/fsl_pamu_domain.c
@@ -301,7 +301,7 @@ static int check_size(u64 size, dma_addr_t iova)
 	 * Size must be a power of two and at least be equal
 	 * to PAMU page size.
 	 */
-	if (!is_power_of_2(size) || size < PAMU_PAGE_SIZE) {
+	if ((size & (size - 1)) || size < PAMU_PAGE_SIZE) {
 		pr_debug("%s: size too small or not a power of two\n", __func__);
 		return -EINVAL;
 	}
@@ -335,11 +335,6 @@ static struct fsl_dma_domain *iommu_alloc_dma_domain(void)
 	return domain;
 }
 
-static inline struct device_domain_info *find_domain(struct device *dev)
-{
-	return dev->archdata.iommu_domain;
-}
-
 static void remove_device_ref(struct device_domain_info *info, u32 win_cnt)
 {
 	unsigned long flags;
@@ -380,7 +375,7 @@ static void attach_device(struct fsl_dma_domain *dma_domain, int liodn, struct d
 	 * Check here if the device is already attached to domain or not.
 	 * If the device is already attached to a domain detach it.
 	 */
-	old_domain_info = find_domain(dev);
+	old_domain_info = dev->archdata.iommu_domain;
 	if (old_domain_info && old_domain_info->domain != dma_domain) {
 		spin_unlock_irqrestore(&device_domain_lock, flags);
 		detach_device(dev, old_domain_info->domain);
@@ -399,7 +394,7 @@ static void attach_device(struct fsl_dma_domain *dma_domain, int liodn, struct d
 	 * the info for the first LIODN as all
 	 * LIODNs share the same domain
 	 */
-	if (!old_domain_info)
+	if (!dev->archdata.iommu_domain)
 		dev->archdata.iommu_domain = info;
 	spin_unlock_irqrestore(&device_domain_lock, flags);
 
@@ -1042,12 +1037,15 @@ root_bus:
 			group = get_shared_pci_device_group(pdev);
 	}
 
+	if (!group)
+		group = ERR_PTR(-ENODEV);
+
 	return group;
 }
 
 static int fsl_pamu_add_device(struct device *dev)
 {
-	struct iommu_group *group = NULL;
+	struct iommu_group *group = ERR_PTR(-ENODEV);
 	struct pci_dev *pdev;
 	const u32 *prop;
 	int ret, len;
@@ -1070,7 +1068,7 @@ static int fsl_pamu_add_device(struct device *dev)
 			group = get_device_iommu_group(dev);
 	}
 
-	if (!group || IS_ERR(group))
+	if (IS_ERR(group))
 		return PTR_ERR(group);
 
 	ret = iommu_group_add_device(group, dev);
diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c
index 6bb32773c3ac..51b6b77dc3e5 100644
--- a/drivers/iommu/intel-iommu.c
+++ b/drivers/iommu/intel-iommu.c
@@ -3816,14 +3816,11 @@ int dmar_iommu_notify_scope_dev(struct dmar_pci_notify_info *info)
 				((void *)rmrr) + rmrr->header.length,
 				rmrr->segment, rmrru->devices,
 				rmrru->devices_cnt);
-			if (ret > 0)
-				break;
-			else if(ret < 0)
+			if(ret < 0)
 				return ret;
 		} else if (info->event == BUS_NOTIFY_DEL_DEVICE) {
-			if (dmar_remove_dev_scope(info, rmrr->segment,
-				rmrru->devices, rmrru->devices_cnt))
-				break;
+			dmar_remove_dev_scope(info, rmrr->segment,
+				rmrru->devices, rmrru->devices_cnt);
 		}
 	}