Automatic defect management in memory devices

1. A method for data storage, comprising:

in a memory that includes multiple memory cells arranged in blocks, storing a first page in a first group of the memory cells within a given block of the memory and storing a second page in a second group of the memory cells within the given block of the memory;

identifying a pattern of respective positions of one or more defective memory cells in the first page of the first group;

modifying an error correction (ECC) code word associated with the second page based upon the pattern; and

recovering the second page by decoding the modified ECC code word.

2. The method according to claim 1 , wherein identifying the pattern comprises identifying one or more defective bit lines in the given block.

3. The method according to claim 2 , wherein identifying the defective bit lines comprises detecting a similarity between respective patterns of the positions of the defective memory cells in multiple word lines of the block.

4. The method according to claim 2 , wherein identifying the defective bit lines comprises receiving information indicative of the defective bit lines from a tester that tested the memory.

5. The method according to claim 1 , wherein the first and second groups of the memory cells belong to respective first and second word lines of the given block.

6. The method according to claim 1 , wherein storing the first and second pages comprises storing the ECC code word and a second ECC code word.

7. The method according to claim 6 , wherein modifying the ECC code word, which is stored in the memory cells of the second group corresponding to the identified pattern, comprises marking respective bits of the ECC code word as having low reliability, and wherein decoding the ECC code word comprises decoding based on the bits marked as having the low reliability.

8. The method according to claim 7 , wherein marking the bits comprises specifying the bits as erasures.

9. The method according to claim 7 , wherein marking the bits comprises assigning low soft-decoding metrics to the bits.

10. The method according to claim 1 , wherein the first group equals the second group.

11. The method according to claim 1 , wherein recovery of the second page is performed without identifying the defective memory cells in the second group of the memory cells.

12. Apparatus for data storage, comprising:

an interface configured to communicate with a memory that includes multiple memory cells arranged in blocks; and

a processor configured to store a first page in a first group of the memory cells within a given block of the memory and to store a second page in a second group of the memory cells within the given block of the memory;

wherein the processor is further configured to:

identify a pattern of respective positions of one or more defective memory cells in the first page of the first group;

modify an error correction (ECC) code word associated with the second page based upon the pattern; and

decode the modified ECC code word to recover the second page.

13. The apparatus according to claim 12 , wherein the processor is configured to identify one or more defective bit lines in the given block to identify the pattern of respective positions of one or more defective memory cells.

14. The apparatus according to claim 13 , wherein the processor is configured to identify the defective bit lines by detecting a similarity between respective patterns of the positions of the defective memory cells in multiple word lines of the block.

15. The apparatus according to claim 13 , wherein the processor is configured to receive information indicative of the defective bit lines from a tester that tested the memory.

16. The apparatus according to claim 12 , wherein the first and second groups of the memory cells belong to respective first and second word lines of the given block.

17. The apparatus according to claim 12 , wherein the processor is configured to store the ECC code word in the second page, and a second ECC code word in the first page.

18. The apparatus according to claim 17 , wherein the processor is configured to mark respective bits of the ECC code word, which is stored in the memory cells of the second group corresponding to the identified pattern, as having low reliability, and to decode the ECC code word based on the bits marked as having the low reliability.

19. The apparatus according to claim 18 , wherein the processor is configured to mark the bits by specifying the bits as erasures.

20. The apparatus according to claim 18 , wherein the processor is configured to mark the bits by assigning low soft-decoding metrics to the bits.

21. The apparatus according to claim 12 , wherein the first group equals the second group.

22. The apparatus according to claim 12 , wherein the processor is configured to recover the second page without identifying the defective memory cells in the second group of the memory cells.

23. Apparatus for data storage, comprising:

a memory comprising multiple memory cells arranged in blocks; and

a processor configured to:

store a first page in a first group of the memory cells within a given block of the memory and to store a second page in a second group of the memory cells within the given block of the memory;

identify a pattern of respective positions of one or more defective memory cells in the first group;

modify an error correction (ECC) code word associated with the second page based upon the pattern; and

decode the modified ECC code word to recover the second page.

24. The apparatus according to claim 23 , wherein the processor is configured to:

store the ECC code word in the second page, and a second ECC code word in the first page;

mark respective bits of the ECC code word, which is stored in the memory cells of the second group corresponding to the identified pattern, as having low reliability; and

decode the ECC code word based on the bits marked as having the low reliability.