Merge tag 'nand/for-5.8' of git://git.kernel.org/pub/scm/linux/kernel/git/mtd/linux into mtd/next

Raw NAND core changes:
* Stop using nand_release(), patched all drivers.
* Give more information about the ECC weakness when not matching the
  chip's requirement.
* MAINTAINERS updates.
* Support emulated SLC mode on MLC NANDs.
* Support "constrained" controllers, adapt the core and ONFI/JEDEC
  table parsing and Micron's code.
* Take check_only into account.
* Add an invalid ECC mode to discriminate with valid ones.
* Return an enum from of_get_nand_ecc_algo().
* Drop OOB_FIRST placement scheme.
* Introduce nand_extract_bits().
* Ensure a consistent bitflips numbering.
* BCH lib:
  - Allow easy bit swapping.
  - Rework a little bit the exported function names.
* Fix nand_gpio_waitrdy().
* Propage CS selection to sub operations.
* Add a NAND_NO_BBM_QUIRK flag.
* Give the possibility to verify a read operation is supported.
* Add a helper to check supported operations.
* Avoid indirect access to ->data_buf().
* Rename the use_bufpoi variables.
* Fix comments about the use of bufpoi.
* Rename a NAND chip option.
* Reorder the nand_chip->options flags.
* Translate obscure bitfields into readable macros.
* Timings:
  - Fix default values.
  - Add mode information to the timings structure.

Raw NAND controller driver changes:
* Fixed many error paths.
* Arasan
  - New driver
* Au1550nd:
  - Various cleanups
  - Migration to ->exec_op()
* brcmnand:
  - Misc cleanup.
  - Support v2.1-v2.2 controllers.
  - Remove unused including <linux/version.h>.
  - Correctly verify erased pages.
  - Fix Hamming OOB layout.
* Cadence
  - Make cadence_nand_attach_chip static.
* Cafe:
  - Set the NAND_NO_BBM_QUIRK flag
* cmx270:
  - Remove this controller driver.
* cs553x:
  - Misc cleanup
  - Migration to ->exec_op()
* Davinci:
  - Misc cleanup.
  - Migration to ->exec_op()
* Denali:
  - Add more delays before latching incoming data
* Diskonchip:
   - Misc cleanup
   - Migration to ->exec_op()
* Fsmc:
  - Change to non-atomic bit operations.
* GPMI:
  - Use nand_extract_bits()
  - Fix runtime PM imbalance.
* Ingenic:
  - Migration to exec_op()
  - Fix the RB gpio active-high property on qi, lb60
  - Make qi_lb60_ooblayout_ops static.
* Marvell:
   - Misc cleanup and small fixes
* Nandsim:
  - Fix the error paths, driver wide.
* Omap_elm:
  - Fix runtime PM imbalance.
* STM32_FMC2:
  - Misc cleanups (error cases, comments, timeout valus, cosmetic
    changes).

1 files changed, 107 insertions, 45 deletions

diff --git a/lib/bch.c b/lib/bch.c
index 052d3fb753a0..7c031ee8b93b 100644
--- a/lib/bch.c
+++ b/lib/bch.c
@@ -23,15 +23,15 @@
  * This library provides runtime configurable encoding/decoding of binary
  * Bose-Chaudhuri-Hocquenghem (BCH) codes.
  *
- * Call init_bch to get a pointer to a newly allocated bch_control structure for
+ * Call bch_init to get a pointer to a newly allocated bch_control structure for
  * the given m (Galois field order), t (error correction capability) and
  * (optional) primitive polynomial parameters.
  *
- * Call encode_bch to compute and store ecc parity bytes to a given buffer.
- * Call decode_bch to detect and locate errors in received data.
+ * Call bch_encode to compute and store ecc parity bytes to a given buffer.
+ * Call bch_decode to detect and locate errors in received data.
  *
  * On systems supporting hw BCH features, intermediate results may be provided
- * to decode_bch in order to skip certain steps. See decode_bch() documentation
+ * to bch_decode in order to skip certain steps. See bch_decode() documentation
  * for details.
  *
  * Option CONFIG_BCH_CONST_PARAMS can be used to force fixed values of
@@ -114,10 +114,53 @@ struct gf_poly_deg1 {
 	unsigned int   c[2];
 };
 
+static u8 swap_bits_table[] = {
+	0x00, 0x80, 0x40, 0xc0, 0x20, 0xa0, 0x60, 0xe0,
+	0x10, 0x90, 0x50, 0xd0, 0x30, 0xb0, 0x70, 0xf0,
+	0x08, 0x88, 0x48, 0xc8, 0x28, 0xa8, 0x68, 0xe8,
+	0x18, 0x98, 0x58, 0xd8, 0x38, 0xb8, 0x78, 0xf8,
+	0x04, 0x84, 0x44, 0xc4, 0x24, 0xa4, 0x64, 0xe4,
+	0x14, 0x94, 0x54, 0xd4, 0x34, 0xb4, 0x74, 0xf4,
+	0x0c, 0x8c, 0x4c, 0xcc, 0x2c, 0xac, 0x6c, 0xec,
+	0x1c, 0x9c, 0x5c, 0xdc, 0x3c, 0xbc, 0x7c, 0xfc,
+	0x02, 0x82, 0x42, 0xc2, 0x22, 0xa2, 0x62, 0xe2,
+	0x12, 0x92, 0x52, 0xd2, 0x32, 0xb2, 0x72, 0xf2,
+	0x0a, 0x8a, 0x4a, 0xca, 0x2a, 0xaa, 0x6a, 0xea,
+	0x1a, 0x9a, 0x5a, 0xda, 0x3a, 0xba, 0x7a, 0xfa,
+	0x06, 0x86, 0x46, 0xc6, 0x26, 0xa6, 0x66, 0xe6,
+	0x16, 0x96, 0x56, 0xd6, 0x36, 0xb6, 0x76, 0xf6,
+	0x0e, 0x8e, 0x4e, 0xce, 0x2e, 0xae, 0x6e, 0xee,
+	0x1e, 0x9e, 0x5e, 0xde, 0x3e, 0xbe, 0x7e, 0xfe,
+	0x01, 0x81, 0x41, 0xc1, 0x21, 0xa1, 0x61, 0xe1,
+	0x11, 0x91, 0x51, 0xd1, 0x31, 0xb1, 0x71, 0xf1,
+	0x09, 0x89, 0x49, 0xc9, 0x29, 0xa9, 0x69, 0xe9,
+	0x19, 0x99, 0x59, 0xd9, 0x39, 0xb9, 0x79, 0xf9,
+	0x05, 0x85, 0x45, 0xc5, 0x25, 0xa5, 0x65, 0xe5,
+	0x15, 0x95, 0x55, 0xd5, 0x35, 0xb5, 0x75, 0xf5,
+	0x0d, 0x8d, 0x4d, 0xcd, 0x2d, 0xad, 0x6d, 0xed,
+	0x1d, 0x9d, 0x5d, 0xdd, 0x3d, 0xbd, 0x7d, 0xfd,
+	0x03, 0x83, 0x43, 0xc3, 0x23, 0xa3, 0x63, 0xe3,
+	0x13, 0x93, 0x53, 0xd3, 0x33, 0xb3, 0x73, 0xf3,
+	0x0b, 0x8b, 0x4b, 0xcb, 0x2b, 0xab, 0x6b, 0xeb,
+	0x1b, 0x9b, 0x5b, 0xdb, 0x3b, 0xbb, 0x7b, 0xfb,
+	0x07, 0x87, 0x47, 0xc7, 0x27, 0xa7, 0x67, 0xe7,
+	0x17, 0x97, 0x57, 0xd7, 0x37, 0xb7, 0x77, 0xf7,
+	0x0f, 0x8f, 0x4f, 0xcf, 0x2f, 0xaf, 0x6f, 0xef,
+	0x1f, 0x9f, 0x5f, 0xdf, 0x3f, 0xbf, 0x7f, 0xff,
+};
+
+static u8 swap_bits(struct bch_control *bch, u8 in)
+{
+	if (!bch->swap_bits)
+		return in;
+
+	return swap_bits_table[in];
+}
+
 /*
- * same as encode_bch(), but process input data one byte at a time
+ * same as bch_encode(), but process input data one byte at a time
  */
-static void encode_bch_unaligned(struct bch_control *bch,
+static void bch_encode_unaligned(struct bch_control *bch,
 				 const unsigned char *data, unsigned int len,
 				 uint32_t *ecc)
 {
@@ -126,7 +169,9 @@ static void encode_bch_unaligned(struct bch_control *bch,
 	const int l = BCH_ECC_WORDS(bch)-1;
 
 	while (len--) {
-		p = bch->mod8_tab + (l+1)*(((ecc[0] >> 24)^(*data++)) & 0xff);
+		u8 tmp = swap_bits(bch, *data++);
+
+		p = bch->mod8_tab + (l+1)*(((ecc[0] >> 24)^(tmp)) & 0xff);
 
 		for (i = 0; i < l; i++)
 			ecc[i] = ((ecc[i] << 8)|(ecc[i+1] >> 24))^(*p++);
@@ -145,10 +190,16 @@ static void load_ecc8(struct bch_control *bch, uint32_t *dst,
 	unsigned int i, nwords = BCH_ECC_WORDS(bch)-1;
 
 	for (i = 0; i < nwords; i++, src += 4)
-		dst[i] = (src[0] << 24)|(src[1] << 16)|(src[2] << 8)|src[3];
+		dst[i] = ((u32)swap_bits(bch, src[0]) << 24) |
+			((u32)swap_bits(bch, src[1]) << 16) |
+			((u32)swap_bits(bch, src[2]) << 8) |
+			swap_bits(bch, src[3]);
 
 	memcpy(pad, src, BCH_ECC_BYTES(bch)-4*nwords);
-	dst[nwords] = (pad[0] << 24)|(pad[1] << 16)|(pad[2] << 8)|pad[3];
+	dst[nwords] = ((u32)swap_bits(bch, pad[0]) << 24) |
+		((u32)swap_bits(bch, pad[1]) << 16) |
+		((u32)swap_bits(bch, pad[2]) << 8) |
+		swap_bits(bch, pad[3]);
 }
 
 /*
@@ -161,20 +212,20 @@ static void store_ecc8(struct bch_control *bch, uint8_t *dst,
 	unsigned int i, nwords = BCH_ECC_WORDS(bch)-1;
 
 	for (i = 0; i < nwords; i++) {
-		*dst++ = (src[i] >> 24);
-		*dst++ = (src[i] >> 16) & 0xff;
-		*dst++ = (src[i] >>  8) & 0xff;
-		*dst++ = (src[i] >>  0) & 0xff;
+		*dst++ = swap_bits(bch, src[i] >> 24);
+		*dst++ = swap_bits(bch, src[i] >> 16);
+		*dst++ = swap_bits(bch, src[i] >> 8);
+		*dst++ = swap_bits(bch, src[i]);
 	}
-	pad[0] = (src[nwords] >> 24);
-	pad[1] = (src[nwords] >> 16) & 0xff;
-	pad[2] = (src[nwords] >>  8) & 0xff;
-	pad[3] = (src[nwords] >>  0) & 0xff;
+	pad[0] = swap_bits(bch, src[nwords] >> 24);
+	pad[1] = swap_bits(bch, src[nwords] >> 16);
+	pad[2] = swap_bits(bch, src[nwords] >> 8);
+	pad[3] = swap_bits(bch, src[nwords]);
 	memcpy(dst, pad, BCH_ECC_BYTES(bch)-4*nwords);
 }
 
 /**
- * encode_bch - calculate BCH ecc parity of data
+ * bch_encode - calculate BCH ecc parity of data
  * @bch:   BCH control structure
  * @data:  data to encode
  * @len:   data length in bytes
@@ -187,7 +238,7 @@ static void store_ecc8(struct bch_control *bch, uint8_t *dst,
  * The exact number of computed ecc parity bits is given by member @ecc_bits of
  * @bch; it may be less than m*t for large values of t.
  */
-void encode_bch(struct bch_control *bch, const uint8_t *data,
+void bch_encode(struct bch_control *bch, const uint8_t *data,
 		unsigned int len, uint8_t *ecc)
 {
 	const unsigned int l = BCH_ECC_WORDS(bch)-1;
@@ -215,7 +266,7 @@ void encode_bch(struct bch_control *bch, const uint8_t *data,
 	m = ((unsigned long)data) & 3;
 	if (m) {
 		mlen = (len < (4-m)) ? len : 4-m;
-		encode_bch_unaligned(bch, data, mlen, bch->ecc_buf);
+		bch_encode_unaligned(bch, data, mlen, bch->ecc_buf);
 		data += mlen;
 		len  -= mlen;
 	}
@@ -240,7 +291,13 @@ void encode_bch(struct bch_control *bch, const uint8_t *data,
 	 */
 	while (mlen--) {
 		/* input data is read in big-endian format */
-		w = r[0]^cpu_to_be32(*pdata++);
+		w = cpu_to_be32(*pdata++);
+		if (bch->swap_bits)
+			w = (u32)swap_bits(bch, w) |
+			    ((u32)swap_bits(bch, w >> 8) << 8) |
+			    ((u32)swap_bits(bch, w >> 16) << 16) |
+			    ((u32)swap_bits(bch, w >> 24) << 24);
+		w ^= r[0];
 		p0 = tab0 + (l+1)*((w >>  0) & 0xff);
 		p1 = tab1 + (l+1)*((w >>  8) & 0xff);
 		p2 = tab2 + (l+1)*((w >> 16) & 0xff);
@@ -255,13 +312,13 @@ void encode_bch(struct bch_control *bch, const uint8_t *data,
 
 	/* process last unaligned bytes */
 	if (len)
-		encode_bch_unaligned(bch, data, len, bch->ecc_buf);
+		bch_encode_unaligned(bch, data, len, bch->ecc_buf);
 
 	/* store ecc parity bytes into original parity buffer */
 	if (ecc)
 		store_ecc8(bch, ecc, bch->ecc_buf);
 }
-EXPORT_SYMBOL_GPL(encode_bch);
+EXPORT_SYMBOL_GPL(bch_encode);
 
 static inline int modulo(struct bch_control *bch, unsigned int v)
 {
@@ -952,7 +1009,7 @@ static int chien_search(struct bch_control *bch, unsigned int len,
 #endif /* USE_CHIEN_SEARCH */
 
 /**
- * decode_bch - decode received codeword and find bit error locations
+ * bch_decode - decode received codeword and find bit error locations
  * @bch:      BCH control structure
  * @data:     received data, ignored if @calc_ecc is provided
  * @len:      data length in bytes, must always be provided
@@ -966,22 +1023,22 @@ static int chien_search(struct bch_control *bch, unsigned int len,
  *  invalid parameters were provided
  *
  * Depending on the available hw BCH support and the need to compute @calc_ecc
- * separately (using encode_bch()), this function should be called with one of
+ * separately (using bch_encode()), this function should be called with one of
  * the following parameter configurations -
  *
  * by providing @data and @recv_ecc only:
- *   decode_bch(@bch, @data, @len, @recv_ecc, NULL, NULL, @errloc)
+ *   bch_decode(@bch, @data, @len, @recv_ecc, NULL, NULL, @errloc)
  *
  * by providing @recv_ecc and @calc_ecc:
- *   decode_bch(@bch, NULL, @len, @recv_ecc, @calc_ecc, NULL, @errloc)
+ *   bch_decode(@bch, NULL, @len, @recv_ecc, @calc_ecc, NULL, @errloc)
  *
  * by providing ecc = recv_ecc XOR calc_ecc:
- *   decode_bch(@bch, NULL, @len, NULL, ecc, NULL, @errloc)
+ *   bch_decode(@bch, NULL, @len, NULL, ecc, NULL, @errloc)
  *
  * by providing syndrome results @syn:
- *   decode_bch(@bch, NULL, @len, NULL, NULL, @syn, @errloc)
+ *   bch_decode(@bch, NULL, @len, NULL, NULL, @syn, @errloc)
  *
- * Once decode_bch() has successfully returned with a positive value, error
+ * Once bch_decode() has successfully returned with a positive value, error
  * locations returned in array @errloc should be interpreted as follows -
  *
  * if (errloc[n] >= 8*len), then n-th error is located in ecc (no need for
@@ -993,7 +1050,7 @@ static int chien_search(struct bch_control *bch, unsigned int len,
  * Note that this function does not perform any data correction by itself, it
  * merely indicates error locations.
  */
-int decode_bch(struct bch_control *bch, const uint8_t *data, unsigned int len,
+int bch_decode(struct bch_control *bch, const uint8_t *data, unsigned int len,
 	       const uint8_t *recv_ecc, const uint8_t *calc_ecc,
 	       const unsigned int *syn, unsigned int *errloc)
 {
@@ -1012,7 +1069,7 @@ int decode_bch(struct bch_control *bch, const uint8_t *data, unsigned int len,
 			/* compute received data ecc into an internal buffer */
 			if (!data || !recv_ecc)
 				return -EINVAL;
-			encode_bch(bch, data, len, NULL);
+			bch_encode(bch, data, len, NULL);
 		} else {
 			/* load provided calculated ecc */
 			load_ecc8(bch, bch->ecc_buf, calc_ecc);
@@ -1048,12 +1105,14 @@ int decode_bch(struct bch_control *bch, const uint8_t *data, unsigned int len,
 				break;
 			}
 			errloc[i] = nbits-1-errloc[i];
-			errloc[i] = (errloc[i] & ~7)|(7-(errloc[i] & 7));
+			if (!bch->swap_bits)
+				errloc[i] = (errloc[i] & ~7) |
+					    (7-(errloc[i] & 7));
 		}
 	}
 	return (err >= 0) ? err : -EBADMSG;
 }
-EXPORT_SYMBOL_GPL(decode_bch);
+EXPORT_SYMBOL_GPL(bch_decode);
 
 /*
  * generate Galois field lookup tables
@@ -1236,27 +1295,29 @@ finish:
 }
 
 /**
- * init_bch - initialize a BCH encoder/decoder
+ * bch_init - initialize a BCH encoder/decoder
  * @m:          Galois field order, should be in the range 5-15
  * @t:          maximum error correction capability, in bits
  * @prim_poly:  user-provided primitive polynomial (or 0 to use default)
+ * @swap_bits:  swap bits within data and syndrome bytes
  *
  * Returns:
  *  a newly allocated BCH control structure if successful, NULL otherwise
  *
  * This initialization can take some time, as lookup tables are built for fast
  * encoding/decoding; make sure not to call this function from a time critical
- * path. Usually, init_bch() should be called on module/driver init and
- * free_bch() should be called to release memory on exit.
+ * path. Usually, bch_init() should be called on module/driver init and
+ * bch_free() should be called to release memory on exit.
  *
  * You may provide your own primitive polynomial of degree @m in argument
- * @prim_poly, or let init_bch() use its default polynomial.
+ * @prim_poly, or let bch_init() use its default polynomial.
  *
- * Once init_bch() has successfully returned a pointer to a newly allocated
+ * Once bch_init() has successfully returned a pointer to a newly allocated
  * BCH control structure, ecc length in bytes is given by member @ecc_bytes of
  * the structure.
  */
-struct bch_control *init_bch(int m, int t, unsigned int prim_poly)
+struct bch_control *bch_init(int m, int t, unsigned int prim_poly,
+			     bool swap_bits)
 {
 	int err = 0;
 	unsigned int i, words;
@@ -1321,6 +1382,7 @@ struct bch_control *init_bch(int m, int t, unsigned int prim_poly)
 	bch->syn       = bch_alloc(2*t*sizeof(*bch->syn), &err);
 	bch->cache     = bch_alloc(2*t*sizeof(*bch->cache), &err);
 	bch->elp       = bch_alloc((t+1)*sizeof(struct gf_poly_deg1), &err);
+	bch->swap_bits = swap_bits;
 
 	for (i = 0; i < ARRAY_SIZE(bch->poly_2t); i++)
 		bch->poly_2t[i] = bch_alloc(GF_POLY_SZ(2*t), &err);
@@ -1347,16 +1409,16 @@ struct bch_control *init_bch(int m, int t, unsigned int prim_poly)
 	return bch;
 
 fail:
-	free_bch(bch);
+	bch_free(bch);
 	return NULL;
 }
-EXPORT_SYMBOL_GPL(init_bch);
+EXPORT_SYMBOL_GPL(bch_init);
 
 /**
- *  free_bch - free the BCH control structure
+ *  bch_free - free the BCH control structure
  *  @bch:    BCH control structure to release
  */
-void free_bch(struct bch_control *bch)
+void bch_free(struct bch_control *bch)
 {
 	unsigned int i;
 
@@ -1377,7 +1439,7 @@ void free_bch(struct bch_control *bch)
 		kfree(bch);
 	}
 }
-EXPORT_SYMBOL_GPL(free_bch);
+EXPORT_SYMBOL_GPL(bch_free);
 
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Ivan Djelic <ivan.djelic@parrot.com>");