diff mbox series

[kernel,v2] powerpc/powernv/ioda: Fix race in TCE level allocation

Message ID 20190611050838.124094-1-aik@ozlabs.ru (mailing list archive)
State Superseded
Headers show
Series [kernel,v2] powerpc/powernv/ioda: Fix race in TCE level allocation | expand

Checks

Context Check Description
snowpatch_ozlabs/apply_patch success Successfully applied on branch next (a3bf9fbdad600b1e4335dd90979f8d6072e4f602)
snowpatch_ozlabs/build-ppc64le warning Build succeeded but added 30 new sparse warnings
snowpatch_ozlabs/build-ppc64be warning Build succeeded but added 3 new sparse warnings
snowpatch_ozlabs/build-ppc64e success Build succeeded
snowpatch_ozlabs/build-pmac32 success Build succeeded
snowpatch_ozlabs/checkpatch warning total: 0 errors, 0 warnings, 3 checks, 38 lines checked

Commit Message

Alexey Kardashevskiy June 11, 2019, 5:08 a.m. UTC
pnv_tce() returns a pointer to a TCE entry and originally a TCE table
would be pre-allocated. For the default case of 2GB window the table
needs only a single level and that is fine. However if more levels are
requested, it is possible to get a race when 2 threads want a pointer
to a TCE entry from the same page of TCEs.

This adds cmpxchg to handle the race. Note that once a TCE is non-zero,
it cannot become zero again.

CC: stable@vger.kernel.org # v4.19+
Fixes: a68bd1267b72 ("powerpc/powernv/ioda: Allocate indirect TCE levels on demand")
Signed-off-by: Alexey Kardashevskiy <aik@ozlabs.ru>
---

The race occurs about 30 times in the first 3 minutes of copying files
via rsync and that's about it.

This fixes EEH's from
https://patchwork.ozlabs.org/project/linuxppc-dev/list/?series=110810

---
Changes:
v2:
* replaced spin_lock with cmpxchg+readonce
---
 arch/powerpc/platforms/powernv/pci-ioda-tce.c | 18 +++++++++++++-----
 1 file changed, 13 insertions(+), 5 deletions(-)
diff mbox series

Patch

diff --git a/arch/powerpc/platforms/powernv/pci-ioda-tce.c b/arch/powerpc/platforms/powernv/pci-ioda-tce.c
index e28f03e1eb5e..8d6569590161 100644
--- a/arch/powerpc/platforms/powernv/pci-ioda-tce.c
+++ b/arch/powerpc/platforms/powernv/pci-ioda-tce.c
@@ -48,6 +48,9 @@  static __be64 *pnv_alloc_tce_level(int nid, unsigned int shift)
 	return addr;
 }
 
+static void pnv_pci_ioda2_table_do_free_pages(__be64 *addr,
+		unsigned long size, unsigned int levels);
+
 static __be64 *pnv_tce(struct iommu_table *tbl, bool user, long idx, bool alloc)
 {
 	__be64 *tmp = user ? tbl->it_userspace : (__be64 *) tbl->it_base;
@@ -57,9 +60,9 @@  static __be64 *pnv_tce(struct iommu_table *tbl, bool user, long idx, bool alloc)
 
 	while (level) {
 		int n = (idx & mask) >> (level * shift);
-		unsigned long tce;
+		unsigned long oldtce, tce = be64_to_cpu(READ_ONCE(tmp[n]));
 
-		if (tmp[n] == 0) {
+		if (!tce) {
 			__be64 *tmp2;
 
 			if (!alloc)
@@ -70,10 +73,15 @@  static __be64 *pnv_tce(struct iommu_table *tbl, bool user, long idx, bool alloc)
 			if (!tmp2)
 				return NULL;
 
-			tmp[n] = cpu_to_be64(__pa(tmp2) |
-					TCE_PCI_READ | TCE_PCI_WRITE);
+			tce = __pa(tmp2) | TCE_PCI_READ | TCE_PCI_WRITE;
+			oldtce = be64_to_cpu(cmpxchg(&tmp[n], 0,
+					cpu_to_be64(tce)));
+			if (oldtce) {
+				pnv_pci_ioda2_table_do_free_pages(tmp2,
+					ilog2(tbl->it_level_size) + 3, 1);
+				tce = oldtce;
+			}
 		}
-		tce = be64_to_cpu(tmp[n]);
 
 		tmp = __va(tce & ~(TCE_PCI_READ | TCE_PCI_WRITE));
 		idx &= ~mask;