lk/linux-kernel-test
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

IB/mthca: Avoid integer overflow when allocating huge ICM table

Browse Source 
In mthca_alloc_icm_table(), the number of entries to allocate for the
table->icm array is computed by calculating obj_size * nobj and then
dividing by MTHCA_TABLE_CHUNK_SIZE.  If nobj is really large, then
obj_size * nobj may overflow and the division may get the wrong value
(even a negative value).  Fix this by calculating the number of
objects per chunk and then dividing nobj by this value instead.

This patch allows crazy configurations such as loading ib_mthca with
the module parameter num_mtt=33554432 to work properly.

Signed-off-by: Roland Dreier <rolandd@cisco.com>
This commit is contained in:
Roland Dreier
2008-04-16 21:01:13 -07:00
parent 19773539d6
commit c263ff65d5
1 changed files with 3 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
drivers/infiniband/hw/mthca/mthca_memfree.c
View File

@@ -359,12 +359,14 @@ struct mthca_icm_table *mthca_alloc_icm_table(struct mthca_dev *dev,
int use_lowmem, int use_coherent) int use_lowmem, int use_coherent)
{ {
struct mthca_icm_table *table; struct mthca_icm_table *table;
int obj_per_chunk;
int num_icm; int num_icm;
unsigned chunk_size; unsigned chunk_size;
int i; int i;
u8 status; u8 status;
num_icm = (obj_size * nobj + MTHCA_TABLE_CHUNK_SIZE - 1) / MTHCA_TABLE_CHUNK_SIZE; obj_per_chunk = MTHCA_TABLE_CHUNK_SIZE / obj_size;
num_icm = DIV_ROUND_UP(nobj, obj_per_chunk);
table = kmalloc(sizeof *table + num_icm * sizeof *table->icm, GFP_KERNEL); table = kmalloc(sizeof *table + num_icm * sizeof *table->icm, GFP_KERNEL);
if (!table) if (!table)