In the quest to remove all stack VLA usage from the kernel[1], this removes
the on-stack working buffers in favor of pre-allocated working buffers
(which were already used in other places). Since these routines must
already be serialized (since they work on bch->ecc_buf), adding the usage
of bch->ecc_work would be similarly safe. Additionally, since "max m" is
only 15, this was adjusted to just use a fixed size array in those cases.
[1] https://lkml.kernel.org/r/CA+55aFzCG-zNmZwX4A2FQpadafLfEzK6CC=qPXydAacU1RqZWA@mail.gmail.com
Signed-off-by: Kees Cook <[email protected]>
---
This is directed at linux-mtd because it's the only user of this library
and it's how it originally entered the kernel tree...
---
include/linux/bch.h | 4 ++--
lib/bch.c | 27 +++++++++++++++------------
2 files changed, 17 insertions(+), 14 deletions(-)
diff --git a/include/linux/bch.h b/include/linux/bch.h
index 295b4ef153bb..4d46e6a73319 100644
--- a/include/linux/bch.h
+++ b/include/linux/bch.h
@@ -39,7 +39,7 @@
* @a_log_tab: Galois field GF(2^m) log lookup table
* @mod8_tab: remainder generator polynomial lookup tables
* @ecc_buf: ecc parity words buffer
- * @ecc_buf2: ecc parity words buffer
+ * @ecc_work: ecc parity words working buffer
* @xi_tab: GF(2^m) base for solving degree 2 polynomial roots
* @syn: syndrome buffer
* @cache: log-based polynomial representation buffer
@@ -57,7 +57,7 @@ struct bch_control {
uint16_t *a_log_tab;
uint32_t *mod8_tab;
uint32_t *ecc_buf;
- uint32_t *ecc_buf2;
+ uint32_t *ecc_work;
unsigned int *xi_tab;
unsigned int *syn;
int *cache;
diff --git a/lib/bch.c b/lib/bch.c
index bc89dfe4d1b3..f14eac93ecc4 100644
--- a/lib/bch.c
+++ b/lib/bch.c
@@ -78,10 +78,12 @@
#define GF_M(_p) (CONFIG_BCH_CONST_M)
#define GF_T(_p) (CONFIG_BCH_CONST_T)
#define GF_N(_p) ((1 << (CONFIG_BCH_CONST_M))-1)
+#define BCH_MAX_M (CONFIG_BCH_CONST_M)
#else
#define GF_M(_p) ((_p)->m)
#define GF_T(_p) ((_p)->t)
#define GF_N(_p) ((_p)->n)
+#define BCH_MAX_M 15
#endif
#define BCH_ECC_WORDS(_p) DIV_ROUND_UP(GF_M(_p)*GF_T(_p), 32)
@@ -187,7 +189,7 @@ void encode_bch(struct bch_control *bch, const uint8_t *data,
const unsigned int l = BCH_ECC_WORDS(bch)-1;
unsigned int i, mlen;
unsigned long m;
- uint32_t w, r[l+1];
+ uint32_t w;
const uint32_t * const tab0 = bch->mod8_tab;
const uint32_t * const tab1 = tab0 + 256*(l+1);
const uint32_t * const tab2 = tab1 + 256*(l+1);
@@ -198,7 +200,7 @@ void encode_bch(struct bch_control *bch, const uint8_t *data,
/* load ecc parity bytes into internal 32-bit buffer */
load_ecc8(bch, bch->ecc_buf, ecc);
} else {
- memset(bch->ecc_buf, 0, sizeof(r));
+ memset(bch->ecc_work, 0, bch->ecc_bytes);
}
/* process first unaligned data bytes */
@@ -215,7 +217,7 @@ void encode_bch(struct bch_control *bch, const uint8_t *data,
mlen = len/4;
data += 4*mlen;
len -= 4*mlen;
- memcpy(r, bch->ecc_buf, sizeof(r));
+ memcpy(bch->ecc_work, bch->ecc_buf, bch->ecc_bytes);
/*
* split each 32-bit word into 4 polynomials of weight 8 as follows:
@@ -229,6 +231,8 @@ void encode_bch(struct bch_control *bch, const uint8_t *data,
* xxxxxxxx yyyyyyyy zzzzzzzz tttttttt mod g = r0^r1^r2^r3
*/
while (mlen--) {
+ uint32_t *r = bch->ecc_work;
+
/* input data is read in big-endian format */
w = r[0]^cpu_to_be32(*pdata++);
p0 = tab0 + (l+1)*((w >> 0) & 0xff);
@@ -241,7 +245,7 @@ void encode_bch(struct bch_control *bch, const uint8_t *data,
r[l] = p0[l]^p1[l]^p2[l]^p3[l];
}
- memcpy(bch->ecc_buf, r, sizeof(r));
+ memcpy(bch->ecc_buf, bch->ecc_work, bch->ecc_bytes);
/* process last unaligned bytes */
if (len)
@@ -434,7 +438,7 @@ static int solve_linear_system(struct bch_control *bch, unsigned int *rows,
{
const int m = GF_M(bch);
unsigned int tmp, mask;
- int rem, c, r, p, k, param[m];
+ int rem, c, r, p, k, param[BCH_MAX_M];
k = 0;
mask = 1 << m;
@@ -1009,10 +1013,10 @@ int decode_bch(struct bch_control *bch, const uint8_t *data, unsigned int len,
}
/* load received ecc or assume it was XORed in calc_ecc */
if (recv_ecc) {
- load_ecc8(bch, bch->ecc_buf2, recv_ecc);
+ load_ecc8(bch, bch->ecc_work, recv_ecc);
/* XOR received and calculated ecc */
for (i = 0, sum = 0; i < (int)ecc_words; i++) {
- bch->ecc_buf[i] ^= bch->ecc_buf2[i];
+ bch->ecc_buf[i] ^= bch->ecc_work[i];
sum |= bch->ecc_buf[i];
}
if (!sum)
@@ -1114,7 +1118,7 @@ static int build_deg2_base(struct bch_control *bch)
{
const int m = GF_M(bch);
int i, j, r;
- unsigned int sum, x, y, remaining, ak = 0, xi[m];
+ unsigned int sum, x, y, remaining, ak = 0, xi[BCH_MAX_M];
/* find k s.t. Tr(a^k) = 1 and 0 <= k < m */
for (i = 0; i < m; i++) {
@@ -1254,7 +1258,6 @@ struct bch_control *init_bch(int m, int t, unsigned int prim_poly)
struct bch_control *bch = NULL;
const int min_m = 5;
- const int max_m = 15;
/* default primitive polynomials */
static const unsigned int prim_poly_tab[] = {
@@ -1270,7 +1273,7 @@ struct bch_control *init_bch(int m, int t, unsigned int prim_poly)
goto fail;
}
#endif
- if ((m < min_m) || (m > max_m))
+ if ((m < min_m) || (m > BCH_MAX_M))
/*
* values of m greater than 15 are not currently supported;
* supporting m > 15 would require changing table base type
@@ -1300,7 +1303,7 @@ struct bch_control *init_bch(int m, int t, unsigned int prim_poly)
bch->a_log_tab = bch_alloc((1+bch->n)*sizeof(*bch->a_log_tab), &err);
bch->mod8_tab = bch_alloc(words*1024*sizeof(*bch->mod8_tab), &err);
bch->ecc_buf = bch_alloc(words*sizeof(*bch->ecc_buf), &err);
- bch->ecc_buf2 = bch_alloc(words*sizeof(*bch->ecc_buf2), &err);
+ bch->ecc_work = bch_alloc(words*sizeof(*bch->ecc_work), &err);
bch->xi_tab = bch_alloc(m*sizeof(*bch->xi_tab), &err);
bch->syn = bch_alloc(2*t*sizeof(*bch->syn), &err);
bch->cache = bch_alloc(2*t*sizeof(*bch->cache), &err);
@@ -1349,7 +1352,7 @@ void free_bch(struct bch_control *bch)
kfree(bch->a_log_tab);
kfree(bch->mod8_tab);
kfree(bch->ecc_buf);
- kfree(bch->ecc_buf2);
+ kfree(bch->ecc_work);
kfree(bch->xi_tab);
kfree(bch->syn);
kfree(bch->cache);
--
2.17.0
--
Kees Cook
Pixel Security
On Tue, May 29, 2018 at 03:42:07PM -0700, Kees Cook wrote:
> In the quest to remove all stack VLA usage from the kernel[1], this removes
> the on-stack working buffers in favor of pre-allocated working buffers
> (which were already used in other places). Since these routines must
> already be serialized (since they work on bch->ecc_buf), adding the usage
> of bch->ecc_work would be similarly safe. Additionally, since "max m" is
> only 15, this was adjusted to just use a fixed size array in those cases.
Hi Kees,
Using an on-stack buffer instead of a pre-allocated buffer was done initially
for performance reasons. For "usual" (m,t) values (for instance m=13, t=4),
there is a huge performance difference between the on-stack buffer version and
the kmalloc version. I didn't investigate the reason for this, but I ran a
quick benchmark on my PC:
little-endian, type sizes: int=4 long=8 longlong=8
cpu: Intel(R) Core(TM) i5 CPU 650 @ 3.20GHz
calibration: iter=4.9143µs niter=2034 nsamples=200 m=13 t=4
Buffer allocation | Encoding throughput (Mbit/s)
---------------------------------------------------
on-stack, VLA | 3988
on-stack, fixed | 4494
kmalloc | 1967
The first line shows the performance of the current code, using a VLA.
The second line shows the performance when r[] is allocated on the stack with
a fixed, constant size (the maximum allowed value).
The third line shows the performance when r is a pre-allocated working buffer.
In fact, when using a pre-allocated buffer there is no need to introduce 'ecc_work':
you can directly point 'r' to bch->ecc_buf and remove memcpy() surrounding the
'while (mlen--)' loop. Everything happens inside the 'bch->ecc_buf' buffer.
But with a big performance penalty. Looks like declaring a temporary buffer on the
stack to store ECC values allows GCC to do a better job at optimizing the loop.
So rather than introducing 'ecc_work', I suggest we compute the maximum allowed
size for r[] and use that:
sizeof(r) = sizeof(uint32_t)*(l+1)
l+1 = BCH_ECC_WORDS(bch) = DIV_ROUND_UP(m*t, 32)
We also know that:
m*t < 2^m - 1 (ECC maximum size)
therefore:
l+1 < DIV_ROUND_UP(2^m - 1, 32) < 2^(m-5)
So instead of 'uint32_t r[l+1]' we could declare 'uint32_t r[1 << (BCH_MAX_M-5)]'.
And replace 'sizeof(r)' with 'sizeof(*bch->ecc_buf)*(l+1)' in memset/memcpy calls.
In practice the actual maximum size of r[] is (1 << (15-5))*sizeof(uint32_t) = 4096 bytes.
What do you think ?
--
Ivan
> [1] https://lkml.kernel.org/r/CA+55aFzCG-zNmZwX4A2FQpadafLfEzK6CC=qPXydAacU1RqZWA@mail.gmail.com
>
> Signed-off-by: Kees Cook <[email protected]>
> ---
> This is directed at linux-mtd because it's the only user of this library
> and it's how it originally entered the kernel tree...
> ---
> include/linux/bch.h | 4 ++--
> lib/bch.c | 27 +++++++++++++++------------
> 2 files changed, 17 insertions(+), 14 deletions(-)
>
> diff --git a/include/linux/bch.h b/include/linux/bch.h
> index 295b4ef153bb..4d46e6a73319 100644
> --- a/include/linux/bch.h
> +++ b/include/linux/bch.h
> @@ -39,7 +39,7 @@
> * @a_log_tab: Galois field GF(2^m) log lookup table
> * @mod8_tab: remainder generator polynomial lookup tables
> * @ecc_buf: ecc parity words buffer
> - * @ecc_buf2: ecc parity words buffer
> + * @ecc_work: ecc parity words working buffer
> * @xi_tab: GF(2^m) base for solving degree 2 polynomial roots
> * @syn: syndrome buffer
> * @cache: log-based polynomial representation buffer
> @@ -57,7 +57,7 @@ struct bch_control {
> uint16_t *a_log_tab;
> uint32_t *mod8_tab;
> uint32_t *ecc_buf;
> - uint32_t *ecc_buf2;
> + uint32_t *ecc_work;
> unsigned int *xi_tab;
> unsigned int *syn;
> int *cache;
> diff --git a/lib/bch.c b/lib/bch.c
> index bc89dfe4d1b3..f14eac93ecc4 100644
> --- a/lib/bch.c
> +++ b/lib/bch.c
> @@ -78,10 +78,12 @@
> #define GF_M(_p) (CONFIG_BCH_CONST_M)
> #define GF_T(_p) (CONFIG_BCH_CONST_T)
> #define GF_N(_p) ((1 << (CONFIG_BCH_CONST_M))-1)
> +#define BCH_MAX_M (CONFIG_BCH_CONST_M)
> #else
> #define GF_M(_p) ((_p)->m)
> #define GF_T(_p) ((_p)->t)
> #define GF_N(_p) ((_p)->n)
> +#define BCH_MAX_M 15
> #endif
>
> #define BCH_ECC_WORDS(_p) DIV_ROUND_UP(GF_M(_p)*GF_T(_p), 32)
> @@ -187,7 +189,7 @@ void encode_bch(struct bch_control *bch, const uint8_t *data,
> const unsigned int l = BCH_ECC_WORDS(bch)-1;
> unsigned int i, mlen;
> unsigned long m;
> - uint32_t w, r[l+1];
> + uint32_t w;
> const uint32_t * const tab0 = bch->mod8_tab;
> const uint32_t * const tab1 = tab0 + 256*(l+1);
> const uint32_t * const tab2 = tab1 + 256*(l+1);
> @@ -198,7 +200,7 @@ void encode_bch(struct bch_control *bch, const uint8_t *data,
> /* load ecc parity bytes into internal 32-bit buffer */
> load_ecc8(bch, bch->ecc_buf, ecc);
> } else {
> - memset(bch->ecc_buf, 0, sizeof(r));
> + memset(bch->ecc_work, 0, bch->ecc_bytes);
> }
>
> /* process first unaligned data bytes */
> @@ -215,7 +217,7 @@ void encode_bch(struct bch_control *bch, const uint8_t *data,
> mlen = len/4;
> data += 4*mlen;
> len -= 4*mlen;
> - memcpy(r, bch->ecc_buf, sizeof(r));
> + memcpy(bch->ecc_work, bch->ecc_buf, bch->ecc_bytes);
>
> /*
> * split each 32-bit word into 4 polynomials of weight 8 as follows:
> @@ -229,6 +231,8 @@ void encode_bch(struct bch_control *bch, const uint8_t *data,
> * xxxxxxxx yyyyyyyy zzzzzzzz tttttttt mod g = r0^r1^r2^r3
> */
> while (mlen--) {
> + uint32_t *r = bch->ecc_work;
> +
> /* input data is read in big-endian format */
> w = r[0]^cpu_to_be32(*pdata++);
> p0 = tab0 + (l+1)*((w >> 0) & 0xff);
> @@ -241,7 +245,7 @@ void encode_bch(struct bch_control *bch, const uint8_t *data,
>
> r[l] = p0[l]^p1[l]^p2[l]^p3[l];
> }
> - memcpy(bch->ecc_buf, r, sizeof(r));
> + memcpy(bch->ecc_buf, bch->ecc_work, bch->ecc_bytes);
>
> /* process last unaligned bytes */
> if (len)
> @@ -434,7 +438,7 @@ static int solve_linear_system(struct bch_control *bch, unsigned int *rows,
> {
> const int m = GF_M(bch);
> unsigned int tmp, mask;
> - int rem, c, r, p, k, param[m];
> + int rem, c, r, p, k, param[BCH_MAX_M];
>
> k = 0;
> mask = 1 << m;
> @@ -1009,10 +1013,10 @@ int decode_bch(struct bch_control *bch, const uint8_t *data, unsigned int len,
> }
> /* load received ecc or assume it was XORed in calc_ecc */
> if (recv_ecc) {
> - load_ecc8(bch, bch->ecc_buf2, recv_ecc);
> + load_ecc8(bch, bch->ecc_work, recv_ecc);
> /* XOR received and calculated ecc */
> for (i = 0, sum = 0; i < (int)ecc_words; i++) {
> - bch->ecc_buf[i] ^= bch->ecc_buf2[i];
> + bch->ecc_buf[i] ^= bch->ecc_work[i];
> sum |= bch->ecc_buf[i];
> }
> if (!sum)
> @@ -1114,7 +1118,7 @@ static int build_deg2_base(struct bch_control *bch)
> {
> const int m = GF_M(bch);
> int i, j, r;
> - unsigned int sum, x, y, remaining, ak = 0, xi[m];
> + unsigned int sum, x, y, remaining, ak = 0, xi[BCH_MAX_M];
>
> /* find k s.t. Tr(a^k) = 1 and 0 <= k < m */
> for (i = 0; i < m; i++) {
> @@ -1254,7 +1258,6 @@ struct bch_control *init_bch(int m, int t, unsigned int prim_poly)
> struct bch_control *bch = NULL;
>
> const int min_m = 5;
> - const int max_m = 15;
>
> /* default primitive polynomials */
> static const unsigned int prim_poly_tab[] = {
> @@ -1270,7 +1273,7 @@ struct bch_control *init_bch(int m, int t, unsigned int prim_poly)
> goto fail;
> }
> #endif
> - if ((m < min_m) || (m > max_m))
> + if ((m < min_m) || (m > BCH_MAX_M))
> /*
> * values of m greater than 15 are not currently supported;
> * supporting m > 15 would require changing table base type
> @@ -1300,7 +1303,7 @@ struct bch_control *init_bch(int m, int t, unsigned int prim_poly)
> bch->a_log_tab = bch_alloc((1+bch->n)*sizeof(*bch->a_log_tab), &err);
> bch->mod8_tab = bch_alloc(words*1024*sizeof(*bch->mod8_tab), &err);
> bch->ecc_buf = bch_alloc(words*sizeof(*bch->ecc_buf), &err);
> - bch->ecc_buf2 = bch_alloc(words*sizeof(*bch->ecc_buf2), &err);
> + bch->ecc_work = bch_alloc(words*sizeof(*bch->ecc_work), &err);
> bch->xi_tab = bch_alloc(m*sizeof(*bch->xi_tab), &err);
> bch->syn = bch_alloc(2*t*sizeof(*bch->syn), &err);
> bch->cache = bch_alloc(2*t*sizeof(*bch->cache), &err);
> @@ -1349,7 +1352,7 @@ void free_bch(struct bch_control *bch)
> kfree(bch->a_log_tab);
> kfree(bch->mod8_tab);
> kfree(bch->ecc_buf);
> - kfree(bch->ecc_buf2);
> + kfree(bch->ecc_work);
> kfree(bch->xi_tab);
> kfree(bch->syn);
> kfree(bch->cache);
> --
> 2.17.0
>
>
> --
> Kees Cook
> Pixel Security
On Wed, May 30, 2018 at 6:46 AM, Ivan Djelic <[email protected]> wrote:
> On Tue, May 29, 2018 at 03:42:07PM -0700, Kees Cook wrote:
>> In the quest to remove all stack VLA usage from the kernel[1], this removes
>> the on-stack working buffers in favor of pre-allocated working buffers
>> (which were already used in other places). Since these routines must
>> already be serialized (since they work on bch->ecc_buf), adding the usage
>> of bch->ecc_work would be similarly safe. Additionally, since "max m" is
>> only 15, this was adjusted to just use a fixed size array in those cases.
>
> Hi Kees,
>
> Using an on-stack buffer instead of a pre-allocated buffer was done initially
> for performance reasons. For "usual" (m,t) values (for instance m=13, t=4),
> there is a huge performance difference between the on-stack buffer version and
> the kmalloc version. I didn't investigate the reason for this, but I ran a
> quick benchmark on my PC:
>
> little-endian, type sizes: int=4 long=8 longlong=8
> cpu: Intel(R) Core(TM) i5 CPU 650 @ 3.20GHz
> calibration: iter=4.9143µs niter=2034 nsamples=200 m=13 t=4
>
> Buffer allocation | Encoding throughput (Mbit/s)
> ---------------------------------------------------
> on-stack, VLA | 3988
> on-stack, fixed | 4494
> kmalloc | 1967
>
> The first line shows the performance of the current code, using a VLA.
> The second line shows the performance when r[] is allocated on the stack with
> a fixed, constant size (the maximum allowed value).
> The third line shows the performance when r is a pre-allocated working buffer.
>
> In fact, when using a pre-allocated buffer there is no need to introduce 'ecc_work':
> you can directly point 'r' to bch->ecc_buf and remove memcpy() surrounding the
> 'while (mlen--)' loop. Everything happens inside the 'bch->ecc_buf' buffer.
> But with a big performance penalty. Looks like declaring a temporary buffer on the
> stack to store ECC values allows GCC to do a better job at optimizing the loop.
>
> So rather than introducing 'ecc_work', I suggest we compute the maximum allowed
> size for r[] and use that:
>
> sizeof(r) = sizeof(uint32_t)*(l+1)
> l+1 = BCH_ECC_WORDS(bch) = DIV_ROUND_UP(m*t, 32)
>
> We also know that:
>
> m*t < 2^m - 1 (ECC maximum size)
>
> therefore:
>
> l+1 < DIV_ROUND_UP(2^m - 1, 32) < 2^(m-5)
>
> So instead of 'uint32_t r[l+1]' we could declare 'uint32_t r[1 << (BCH_MAX_M-5)]'.
> And replace 'sizeof(r)' with 'sizeof(*bch->ecc_buf)*(l+1)' in memset/memcpy calls.
> In practice the actual maximum size of r[] is (1 << (15-5))*sizeof(uint32_t) = 4096 bytes.
>
> What do you think ?
I actually did that implementation first since I didn't realize how
large that allocation could get. 4096 is a HUGE stack allocation. The
kernel build warns at 2048. The defaults seen during allmodconfig are:
CONFIG_BCH_CONST_M=14
CONFIG_BCH_CONST_T=4
So those builds are already seeing a large stack allocation, but it
was hidden from the checking tools before because it was a dynamic
stack allocation:
lib/bch.c: In function ‘encode_bch’:
lib/bch.c:261:1: warning: the frame size of 2288 bytes is larger than
2048 bytes [-Wframe-larger-than=]
This could be masked in the Makefile, though, since this is already
the situation the code runs under. I'll send that patch...
-Kees
--
Kees Cook
Pixel Security
Hi Kees,
I love your patch! Perhaps something to improve:
[auto build test WARNING on linus/master]
[also build test WARNING on v4.17-rc7 next-20180530]
[if your patch is applied to the wrong git tree, please drop us a note to help improve the system]
url: https://github.com/0day-ci/linux/commits/Kees-Cook/lib-bch-Remove-VLA-usage/20180531-055540
reproduce:
# apt-get install sparse
make ARCH=x86_64 allmodconfig
make C=1 CF=-D__CHECK_ENDIAN__
sparse warnings: (new ones prefixed by >>)
>> lib/bch.c:237:26: sparse: restricted __be32 degrades to integer
vim +237 lib/bch.c
437aa565 Ivan Djelic 2011-03-11 171
437aa565 Ivan Djelic 2011-03-11 172 /**
437aa565 Ivan Djelic 2011-03-11 173 * encode_bch - calculate BCH ecc parity of data
437aa565 Ivan Djelic 2011-03-11 174 * @bch: BCH control structure
437aa565 Ivan Djelic 2011-03-11 175 * @data: data to encode
437aa565 Ivan Djelic 2011-03-11 176 * @len: data length in bytes
437aa565 Ivan Djelic 2011-03-11 177 * @ecc: ecc parity data, must be initialized by caller
437aa565 Ivan Djelic 2011-03-11 178 *
437aa565 Ivan Djelic 2011-03-11 179 * The @ecc parity array is used both as input and output parameter, in order to
437aa565 Ivan Djelic 2011-03-11 180 * allow incremental computations. It should be of the size indicated by member
437aa565 Ivan Djelic 2011-03-11 181 * @ecc_bytes of @bch, and should be initialized to 0 before the first call.
437aa565 Ivan Djelic 2011-03-11 182 *
437aa565 Ivan Djelic 2011-03-11 183 * The exact number of computed ecc parity bits is given by member @ecc_bits of
437aa565 Ivan Djelic 2011-03-11 184 * @bch; it may be less than m*t for large values of t.
437aa565 Ivan Djelic 2011-03-11 185 */
437aa565 Ivan Djelic 2011-03-11 186 void encode_bch(struct bch_control *bch, const uint8_t *data,
437aa565 Ivan Djelic 2011-03-11 187 unsigned int len, uint8_t *ecc)
437aa565 Ivan Djelic 2011-03-11 188 {
437aa565 Ivan Djelic 2011-03-11 189 const unsigned int l = BCH_ECC_WORDS(bch)-1;
437aa565 Ivan Djelic 2011-03-11 190 unsigned int i, mlen;
437aa565 Ivan Djelic 2011-03-11 191 unsigned long m;
da5dc7be Kees Cook 2018-05-29 192 uint32_t w;
437aa565 Ivan Djelic 2011-03-11 193 const uint32_t * const tab0 = bch->mod8_tab;
437aa565 Ivan Djelic 2011-03-11 194 const uint32_t * const tab1 = tab0 + 256*(l+1);
437aa565 Ivan Djelic 2011-03-11 195 const uint32_t * const tab2 = tab1 + 256*(l+1);
437aa565 Ivan Djelic 2011-03-11 196 const uint32_t * const tab3 = tab2 + 256*(l+1);
437aa565 Ivan Djelic 2011-03-11 197 const uint32_t *pdata, *p0, *p1, *p2, *p3;
437aa565 Ivan Djelic 2011-03-11 198
437aa565 Ivan Djelic 2011-03-11 199 if (ecc) {
437aa565 Ivan Djelic 2011-03-11 200 /* load ecc parity bytes into internal 32-bit buffer */
437aa565 Ivan Djelic 2011-03-11 201 load_ecc8(bch, bch->ecc_buf, ecc);
437aa565 Ivan Djelic 2011-03-11 202 } else {
da5dc7be Kees Cook 2018-05-29 203 memset(bch->ecc_work, 0, bch->ecc_bytes);
437aa565 Ivan Djelic 2011-03-11 204 }
437aa565 Ivan Djelic 2011-03-11 205
437aa565 Ivan Djelic 2011-03-11 206 /* process first unaligned data bytes */
437aa565 Ivan Djelic 2011-03-11 207 m = ((unsigned long)data) & 3;
437aa565 Ivan Djelic 2011-03-11 208 if (m) {
437aa565 Ivan Djelic 2011-03-11 209 mlen = (len < (4-m)) ? len : 4-m;
437aa565 Ivan Djelic 2011-03-11 210 encode_bch_unaligned(bch, data, mlen, bch->ecc_buf);
437aa565 Ivan Djelic 2011-03-11 211 data += mlen;
437aa565 Ivan Djelic 2011-03-11 212 len -= mlen;
437aa565 Ivan Djelic 2011-03-11 213 }
437aa565 Ivan Djelic 2011-03-11 214
437aa565 Ivan Djelic 2011-03-11 215 /* process 32-bit aligned data words */
437aa565 Ivan Djelic 2011-03-11 216 pdata = (uint32_t *)data;
437aa565 Ivan Djelic 2011-03-11 217 mlen = len/4;
437aa565 Ivan Djelic 2011-03-11 218 data += 4*mlen;
437aa565 Ivan Djelic 2011-03-11 219 len -= 4*mlen;
da5dc7be Kees Cook 2018-05-29 220 memcpy(bch->ecc_work, bch->ecc_buf, bch->ecc_bytes);
437aa565 Ivan Djelic 2011-03-11 221
437aa565 Ivan Djelic 2011-03-11 222 /*
437aa565 Ivan Djelic 2011-03-11 223 * split each 32-bit word into 4 polynomials of weight 8 as follows:
437aa565 Ivan Djelic 2011-03-11 224 *
437aa565 Ivan Djelic 2011-03-11 225 * 31 ...24 23 ...16 15 ... 8 7 ... 0
437aa565 Ivan Djelic 2011-03-11 226 * xxxxxxxx yyyyyyyy zzzzzzzz tttttttt
437aa565 Ivan Djelic 2011-03-11 227 * tttttttt mod g = r0 (precomputed)
437aa565 Ivan Djelic 2011-03-11 228 * zzzzzzzz 00000000 mod g = r1 (precomputed)
437aa565 Ivan Djelic 2011-03-11 229 * yyyyyyyy 00000000 00000000 mod g = r2 (precomputed)
437aa565 Ivan Djelic 2011-03-11 230 * xxxxxxxx 00000000 00000000 00000000 mod g = r3 (precomputed)
437aa565 Ivan Djelic 2011-03-11 231 * xxxxxxxx yyyyyyyy zzzzzzzz tttttttt mod g = r0^r1^r2^r3
437aa565 Ivan Djelic 2011-03-11 232 */
437aa565 Ivan Djelic 2011-03-11 233 while (mlen--) {
da5dc7be Kees Cook 2018-05-29 234 uint32_t *r = bch->ecc_work;
da5dc7be Kees Cook 2018-05-29 235
437aa565 Ivan Djelic 2011-03-11 236 /* input data is read in big-endian format */
437aa565 Ivan Djelic 2011-03-11 @237 w = r[0]^cpu_to_be32(*pdata++);
437aa565 Ivan Djelic 2011-03-11 238 p0 = tab0 + (l+1)*((w >> 0) & 0xff);
437aa565 Ivan Djelic 2011-03-11 239 p1 = tab1 + (l+1)*((w >> 8) & 0xff);
437aa565 Ivan Djelic 2011-03-11 240 p2 = tab2 + (l+1)*((w >> 16) & 0xff);
437aa565 Ivan Djelic 2011-03-11 241 p3 = tab3 + (l+1)*((w >> 24) & 0xff);
437aa565 Ivan Djelic 2011-03-11 242
437aa565 Ivan Djelic 2011-03-11 243 for (i = 0; i < l; i++)
437aa565 Ivan Djelic 2011-03-11 244 r[i] = r[i+1]^p0[i]^p1[i]^p2[i]^p3[i];
437aa565 Ivan Djelic 2011-03-11 245
437aa565 Ivan Djelic 2011-03-11 246 r[l] = p0[l]^p1[l]^p2[l]^p3[l];
437aa565 Ivan Djelic 2011-03-11 247 }
da5dc7be Kees Cook 2018-05-29 248 memcpy(bch->ecc_buf, bch->ecc_work, bch->ecc_bytes);
437aa565 Ivan Djelic 2011-03-11 249
437aa565 Ivan Djelic 2011-03-11 250 /* process last unaligned bytes */
437aa565 Ivan Djelic 2011-03-11 251 if (len)
437aa565 Ivan Djelic 2011-03-11 252 encode_bch_unaligned(bch, data, len, bch->ecc_buf);
437aa565 Ivan Djelic 2011-03-11 253
437aa565 Ivan Djelic 2011-03-11 254 /* store ecc parity bytes into original parity buffer */
437aa565 Ivan Djelic 2011-03-11 255 if (ecc)
437aa565 Ivan Djelic 2011-03-11 256 store_ecc8(bch, ecc, bch->ecc_buf);
437aa565 Ivan Djelic 2011-03-11 257 }
437aa565 Ivan Djelic 2011-03-11 258 EXPORT_SYMBOL_GPL(encode_bch);
437aa565 Ivan Djelic 2011-03-11 259
:::::: The code at line 237 was first introduced by commit
:::::: 437aa565e2656776a7104aaacd792fe789ea8b2d lib: add shared BCH ECC library
:::::: TO: Ivan Djelic <[email protected]>
:::::: CC: David Woodhouse <[email protected]>
---
0-DAY kernel test infrastructure Open Source Technology Center
https://lists.01.org/pipermail/kbuild-all Intel Corporation