iommu: Add calls for IOMMU_DEBUG_PAGEALLOC

Add calls for the new iommu debug config IOMMU_DEBUG_PAGEALLOC:
- iommu_debug_init: Enable the debug mode if configured by the user.
- iommu_debug_map: Track iommu pages mapped, using physical address.
- iommu_debug_unmap_begin: Track start of iommu unmap operation, with
  IOVA and size.
- iommu_debug_unmap_end: Track the end of unmap operation, passing the
  actual unmapped size versus the tracked one at unmap_begin.

We have to do the unmap_begin/end as once pages are unmapped we lose
the information of the physical address.
This is racy, but the API is racy by construction as it uses refcounts
and doesn't attempt to lock/synchronize with the IOMMU API as that will
be costly, meaning that possibility of false negative exists.

Reviewed-by: Samiullah Khawaja <skhawaja@google.com>
Reviewed-by: Lu Baolu <baolu.lu@linux.intel.com>
Reviewed-by: Pranjal Shrivastava <praan@google.com>
Signed-off-by: Mostafa Saleh <smostafa@google.com>
Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>

Author: misaleh

drivers/iommu/iommu-debug-pagealloc.c

@@ -5,11 +5,15 @@
  * IOMMU API debug page alloc sanitizer
  */
 #include <linux/atomic.h>
+#include <linux/iommu.h>
 #include <linux/iommu-debug-pagealloc.h>
 #include <linux/kernel.h>
 #include <linux/page_ext.h>
 
+#include "iommu-priv.h"
+
 static bool needed;
+DEFINE_STATIC_KEY_FALSE(iommu_debug_initialized);
 
 struct iommu_debug_metadata {
 	atomic_t ref;
@@ -25,6 +29,30 @@ struct page_ext_operations page_iommu_debug_ops = {
 	.need = need_iommu_debug,
 };
 
+void __iommu_debug_map(struct iommu_domain *domain, phys_addr_t phys, size_t size)
+{
+}
+
+void __iommu_debug_unmap_begin(struct iommu_domain *domain,
+			       unsigned long iova, size_t size)
+{
+}
+
+void __iommu_debug_unmap_end(struct iommu_domain *domain,
+			     unsigned long iova, size_t size,
+			     size_t unmapped)
+{
+}
+
+void iommu_debug_init(void)
+{
+	if (!needed)
+		return;
+
+	pr_info("iommu: Debugging page allocations, expect overhead or disable iommu.debug_pagealloc");
+	static_branch_enable(&iommu_debug_initialized);
+}
+
 static int __init iommu_debug_pagealloc(char *str)
 {
 	return kstrtobool(str, &needed);

drivers/iommu/iommu-priv.h

@@ -5,6 +5,7 @@
 #define __LINUX_IOMMU_PRIV_H
 
 #include <linux/iommu.h>
+#include <linux/iommu-debug-pagealloc.h>
 #include <linux/msi.h>
 
 static inline const struct iommu_ops *dev_iommu_ops(struct device *dev)
@@ -65,4 +66,61 @@ static inline int iommufd_sw_msi(struct iommu_domain *domain,
 int iommu_replace_device_pasid(struct iommu_domain *domain,
 			       struct device *dev, ioasid_t pasid,
 			       struct iommu_attach_handle *handle);
+
+#ifdef CONFIG_IOMMU_DEBUG_PAGEALLOC
+
+void __iommu_debug_map(struct iommu_domain *domain, phys_addr_t phys,
+		       size_t size);
+void __iommu_debug_unmap_begin(struct iommu_domain *domain,
+			       unsigned long iova, size_t size);
+void __iommu_debug_unmap_end(struct iommu_domain *domain,
+			     unsigned long iova, size_t size, size_t unmapped);
+
+static inline void iommu_debug_map(struct iommu_domain *domain,
+				   phys_addr_t phys, size_t size)
+{
+	if (static_branch_unlikely(&iommu_debug_initialized))
+		__iommu_debug_map(domain, phys, size);
+}
+
+static inline void iommu_debug_unmap_begin(struct iommu_domain *domain,
+					   unsigned long iova, size_t size)
+{
+	if (static_branch_unlikely(&iommu_debug_initialized))
+		__iommu_debug_unmap_begin(domain, iova, size);
+}
+
+static inline void iommu_debug_unmap_end(struct iommu_domain *domain,
+					 unsigned long iova, size_t size,
+					 size_t unmapped)
+{
+	if (static_branch_unlikely(&iommu_debug_initialized))
+		__iommu_debug_unmap_end(domain, iova, size, unmapped);
+}
+
+void iommu_debug_init(void);
+
+#else
+static inline void iommu_debug_map(struct iommu_domain *domain,
+				   phys_addr_t phys, size_t size)
+{
+}
+
+static inline void iommu_debug_unmap_begin(struct iommu_domain *domain,
+					   unsigned long iova, size_t size)
+{
+}
+
+static inline void iommu_debug_unmap_end(struct iommu_domain *domain,
+					 unsigned long iova, size_t size,
+					 size_t unmapped)
+{
+}
+
+static inline void iommu_debug_init(void)
+{
+}
+
+#endif /* CONFIG_IOMMU_DEBUG_PAGEALLOC */
+
 #endif /* __LINUX_IOMMU_PRIV_H */

drivers/iommu/iommu.c

@@ -237,6 +237,8 @@ static int __init iommu_subsys_init(void)
 	if (!nb)
 		return -ENOMEM;
 
+	iommu_debug_init();
+
 	for (int i = 0; i < ARRAY_SIZE(iommu_buses); i++) {
 		nb[i].notifier_call = iommu_bus_notifier;
 		bus_register_notifier(iommu_buses[i], &nb[i]);
@@ -2629,10 +2631,12 @@ int iommu_map_nosync(struct iommu_domain *domain, unsigned long iova,
 	}
 
 	/* unroll mapping in case something went wrong */
-	if (ret)
+	if (ret) {
 		iommu_unmap(domain, orig_iova, orig_size - size);
-	else
+	} else {
 		trace_map(orig_iova, orig_paddr, orig_size);
+		iommu_debug_map(domain, orig_paddr, orig_size);
+	}
 
 	return ret;
 }
@@ -2694,6 +2698,8 @@ static size_t __iommu_unmap(struct iommu_domain *domain,
 
 	pr_debug("unmap this: iova 0x%lx size 0x%zx\n", iova, size);
 
+	iommu_debug_unmap_begin(domain, iova, size);
+
 	/*
 	 * Keep iterating until we either unmap 'size' bytes (or more)
 	 * or we hit an area that isn't mapped.
@@ -2714,6 +2720,7 @@ static size_t __iommu_unmap(struct iommu_domain *domain,
 	}
 
 	trace_unmap(orig_iova, size, unmapped);
+	iommu_debug_unmap_end(domain, orig_iova, size, unmapped);
 	return unmapped;
 }
 

include/linux/iommu-debug-pagealloc.h

@@ -9,6 +9,7 @@
 #define __LINUX_IOMMU_DEBUG_PAGEALLOC_H
 
 #ifdef CONFIG_IOMMU_DEBUG_PAGEALLOC
+DECLARE_STATIC_KEY_FALSE(iommu_debug_initialized);
 
 extern struct page_ext_operations page_iommu_debug_ops;