[PATCH] x86/mm/kmmio: Fix mmiotrace for page unaligned addresses

[Karol Herbst]

If something calls ioremap with an address not aligned to PAGE_SIZE, the
returned address might be not aligned as well. This led to a probe
registered on exactly the returned address, but the entire page was armed
for mmiotracing.

On calling iounmap the address passed to unregister_kmmio_probe was
PAGE_SIZE aligned by the caller leading to a complete freeze of the
machine.

We should always page align addresses while (un)registerung mappings,
because the mmiotracer works on top of pages, not mappings. We still keep
track of the probes based on their real addresses and lengths though,
because the mmiotrace still needs to know what are mapped memory regions.

Also move the call to mmiotrace_iounmap prior page aligning the address,
so that all probes are unregistered properly, otherwise the kernel ends up
failing memory allocations randomly after disabling the mmiotracer.

Cc: Steven Rostedt <rostedt@xxxxxxxxxxx>
Cc: Ingo Molnar <mingo@xxxxxxxxxx>
Cc: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
Cc: Pekka Paalanen <ppaalanen@xxxxxxxxx>
Cc: nouveau@xxxxxxxxxxxxxxxxxxxxx
Cc: x86@xxxxxxxxxx
Acked-by: Pekka Paalanen <ppaalanen@xxxxxxxxx>
Tested-by: Lyude <lyude@xxxxxxxxxx>
Signed-off-by: Karol Herbst <kherbst@xxxxxxxxxx>
---
 arch/x86/mm/ioremap.c |  4 ++--
 arch/x86/mm/kmmio.c   | 12 +++++++-----
 2 files changed, 9 insertions(+), 7 deletions(-)

diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c
index 34f0e1847dd6..5d4c358778dd 100644
--- a/arch/x86/mm/ioremap.c
+++ b/arch/x86/mm/ioremap.c
@@ -349,11 +349,11 @@ void iounmap(volatile void __iomem *addr)
 		return;
 	}
 
+	mmiotrace_iounmap(addr);
+
 	addr = (volatile void __iomem *)
 		(PAGE_MASK & (unsigned long __force)addr);
 
-	mmiotrace_iounmap(addr);
-
 	/* Use the vm area unlocked, assuming the caller
 	   ensures there isn't another iounmap for the same address
 	   in parallel. Reuse of the virtual address is prevented by
diff --git a/arch/x86/mm/kmmio.c b/arch/x86/mm/kmmio.c
index c21c2ed04612..58477ec3d66d 100644
--- a/arch/x86/mm/kmmio.c
+++ b/arch/x86/mm/kmmio.c
@@ -435,17 +435,18 @@ int register_kmmio_probe(struct kmmio_probe *p)
 	unsigned long flags;
 	int ret = 0;
 	unsigned long size = 0;
+	unsigned long addr = p->addr & PAGE_MASK;
 	const unsigned long size_lim = p->len + (p->addr & ~PAGE_MASK);
 	unsigned int l;
 	pte_t *pte;
 
 	spin_lock_irqsave(&kmmio_lock, flags);
-	if (get_kmmio_probe(p->addr)) {
+	if (get_kmmio_probe(addr)) {
 		ret = -EEXIST;
 		goto out;
 	}
 
-	pte = lookup_address(p->addr, &l);
+	pte = lookup_address(addr, &l);
 	if (!pte) {
 		ret = -EINVAL;
 		goto out;
@@ -454,7 +455,7 @@ int register_kmmio_probe(struct kmmio_probe *p)
 	kmmio_count++;
 	list_add_rcu(&p->list, &kmmio_probes);
 	while (size < size_lim) {
-		if (add_kmmio_fault_page(p->addr + size))
+		if (add_kmmio_fault_page(addr + size))
 			pr_err("Unable to set page fault.\n");
 		size += page_level_size(l);
 	}
@@ -528,19 +529,20 @@ void unregister_kmmio_probe(struct kmmio_probe *p)
 {
 	unsigned long flags;
 	unsigned long size = 0;
+	unsigned long addr = p->addr & PAGE_MASK;
 	const unsigned long size_lim = p->len + (p->addr & ~PAGE_MASK);
 	struct kmmio_fault_page *release_list = NULL;
 	struct kmmio_delayed_release *drelease;
 	unsigned int l;
 	pte_t *pte;
 
-	pte = lookup_address(p->addr, &l);
+	pte = lookup_address(addr, &l);
 	if (!pte)
 		return;
 
 	spin_lock_irqsave(&kmmio_lock, flags);
 	while (size < size_lim) {
-		release_kmmio_fault_page(p->addr + size, &release_list);
+		release_kmmio_fault_page(addr + size, &release_list);
 		size += page_level_size(l);
 	}
 	list_del_rcu(&p->list);
-- 
2.14.3