On Mon, Jun 17, 2013 at 07:52:14PM -0600, Alex Williamson wrote:
> static void free_pagetable(struct protection_domain *domain)
> {
> - int i, j;
> - u64 *p1, *p2, *p3;
> + int i, j, k, l, m, depth = domain->mode;
> + u64 *p1, *p2, *p3, *p4, *p5, *p6;
>
> p1 = domain->pt_root;
>
> if (!p1)
> return;
>
> - for (i = 0; i < 512; ++i) {
> + for (i = 0; depth > 1 && i < 512; ++i) {
> if (!IOMMU_PTE_PRESENT(p1[i]))
> continue;
>
> p2 = IOMMU_PTE_PAGE(p1[i]);
> - for (j = 0; j < 512; ++j) {
> + for (j = 0; depth > 2 && j < 512; ++j) {
> if (!IOMMU_PTE_PRESENT(p2[j]))
> continue;
> +
> p3 = IOMMU_PTE_PAGE(p2[j]);
> + for (k = 0; depth > 3 && k < 512; ++k) {
> + if (!IOMMU_PTE_PRESENT(p3[k]))
> + continue;
> +
> + p4 = IOMMU_PTE_PAGE(p3[k]);
> + for (l = 0; depth > 4 && l < 512; ++l) {
> + if (!IOMMU_PTE_PRESENT(p4[l]))
> + continue;
> +
> + p5 = IOMMU_PTE_PAGE(p4[l]);
> + for (m = 0; depth > 5 && m < 512; ++m) {
> + if (!IOMMU_PTE_PRESENT(p5[m]))
> + continue;
> + p6 = IOMMU_PTE_PAGE(p5[m]);
> + free_page((unsigned long)p6);
> + }
> +
> + free_page((unsigned long)p5);
> + }
> +
> + free_page((unsigned long)p4);
> + }
> +
> free_page((unsigned long)p3);
> }
Hmm, actually a recursive version would make more sense here. But since
recursion is a bad idea in the kernel, how about this approach instead:
>From d500d538ad1370679d05667663dcaf8603d529db Mon Sep 17 00:00:00 2001
From: Joerg Roedel <j...@8bytes.org>
Date: Thu, 20 Jun 2013 20:22:58 +0200
Subject: [PATCH] iommu/amd: Fix memory leak in free_pagetable
The IOMMU pagetables can have up to 3 levels, but the code
in free_pagetable() only releases the first 3 levels. Fix
this leak by releasing all levels.
Reported-by: Alex Williamson <alex.william...@redhat.com>
Signed-off-by: Joerg Roedel <j...@8bytes.org>
---
drivers/iommu/amd_iommu.c | 73 ++++++++++++++++++++++++++++++---------------
1 file changed, 49 insertions(+), 24 deletions(-)
diff --git a/drivers/iommu/amd_iommu.c b/drivers/iommu/amd_iommu.c
index 21d02b0..5cde682 100644
--- a/drivers/iommu/amd_iommu.c
+++ b/drivers/iommu/amd_iommu.c
@@ -1893,34 +1893,59 @@ static void domain_id_free(int id)
write_unlock_irqrestore(&amd_iommu_devtable_lock, flags);
}
+#define DEFINE_FREE_PT_FN(LVL, FN) \
+static void free_pt_##LVL (unsigned long __pt) \
+{ \
+ unsigned long p; \
+ u64 *pt; \
+ int i; \
+ \
+ pt = (u64 *)__pt; \
+ \
+ for (i = 0; i < 512; ++i) { \
+ if (!IOMMU_PTE_PRESENT(pt[i])) \
+ continue; \
+ \
+ p = (unsigned long)IOMMU_PTE_PAGE(pt[i]); \
+ FN(p); \
+ } \
+ free_page((unsigned long)pt); \
+}
+
+DEFINE_FREE_PT_FN(l2, free_page)
+DEFINE_FREE_PT_FN(l3, free_pt_l2)
+DEFINE_FREE_PT_FN(l4, free_pt_l3)
+DEFINE_FREE_PT_FN(l5, free_pt_l4)
+DEFINE_FREE_PT_FN(l6, free_pt_l5)
+
static void free_pagetable(struct protection_domain *domain)
{
- int i, j;
- u64 *p1, *p2, *p3;
-
- p1 = domain->pt_root;
-
- if (!p1)
- return;
-
- for (i = 0; i < 512; ++i) {
- if (!IOMMU_PTE_PRESENT(p1[i]))
- continue;
+ unsigned long root = (unsigned long)domain->pt_root;
- p2 = IOMMU_PTE_PAGE(p1[i]);
- for (j = 0; j < 512; ++j) {
- if (!IOMMU_PTE_PRESENT(p2[j]))
- continue;
- p3 = IOMMU_PTE_PAGE(p2[j]);
- free_page((unsigned long)p3);
- }
-
- free_page((unsigned long)p2);
+ switch (domain->mode) {
+ case PAGE_MODE_NONE:
+ break;
+ case PAGE_MODE_1_LEVEL:
+ free_page(root);
+ break;
+ case PAGE_MODE_2_LEVEL:
+ free_pt_l2(root);
+ break;
+ case PAGE_MODE_3_LEVEL:
+ free_pt_l3(root);
+ break;
+ case PAGE_MODE_4_LEVEL:
+ free_pt_l4(root);
+ break;
+ case PAGE_MODE_5_LEVEL:
+ free_pt_l5(root);
+ break;
+ case PAGE_MODE_6_LEVEL:
+ free_pt_l6(root);
+ break;
+ default:
+ BUG();
}
-
- free_page((unsigned long)p1);
-
- domain->pt_root = NULL;
}
static void free_gcr3_tbl_level1(u64 *tbl)
--
1.7.9.5
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majord...@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
