CONTROL CIRCUIT CAPABLE OF IDENTIFYING ERROR DATA IN FLASH MEMORY AND STORAGE SYSTEM AND METHOD THEREOF

• US 20100325524A1
• Filed: 08/17/2009
• Published: 12/23/2010
• Est. Priority Date: 06/23/2009
• Status: Active Grant

• Current Assignee: Phison Electronics Corporation
• Original Assignee: Phison Electronics Corporation
• Inventors: YANG, Jiunn-Yeong, YEH, Chih-Kang
• Granted Patent: US 8,607,123 B2
• Time in Patent Office: Days
• US Class Current: 714/773
• CPC Class Codes: G06F 11/1068 in sector programmable memories, e.g. flash disk G06F11/1072 takes precedence
• CPC Class Codes: G11C 16/04 using variable threshold transistors, e.g. FAMOS
• CPC Class Codes: G11C 29/76 using address translation or modifications

Abstract

A flash memory control circuit including a microprocessor unit, a first interface unit for connecting a flash memory, a second interface unit for connecting a computer host, an error correcting unit, a memory management unit, and a marking unit is provided. The memory management unit divides each page in the flash memory into a plurality of data bit areas, and a plurality of redundancy bit areas and a plurality of error correcting bit areas corresponding to the data bit areas, wherein each of the data bit areas has a plurality of sectors for respectively storing a sector data. The marking unit stores a data accuracy mark corresponding to each sector data in the corresponding redundancy bit area to record the status of the sector data. Thereby, the flash memory controller can effectively identify error data in the flash memory by using the error correcting codes and the data accuracy marks.

Claims

1. A flash memory control circuit, comprising:

a microprocessor unit;

a first interface unit, coupled to the microprocessor unit, and used to connect a flash memory, wherein the flash memory has a plurality of physical blocks, and each of the physical blocks has a plurality of pages;

a second interface unit, coupled to the microprocessor unit, and used to connect a computer host;

an error correcting unit, coupled to the microprocessor unit;

a memory management unit, coupled to the microprocessor unit, and used to divide each of the pages into at least one data bit area, and at least one redundancy bit area and at least one error correcting bit area corresponding to the data bit area, wherein the data bit area has a plurality of sectors to store a plurality of sector data; and

a marking unit, coupled to the microprocessor unit, wherein when the computer host writes a plurality of sector data into one of the data bit areas, the error correcting unit generates an error correcting code according to the sector data, the memory management unit writes the sector data into one of the data bit areas and the error correcting code into the corresponding error correcting bit area, and the marking unit records the data accuracy marks as a normal status in the corresponding redundancy bit area, wherein each of the data accuracy marks is corresponding to one of the sector data.

2. The flash memory control circuit according to claim 1, wherein when the memory management unit copies the sector data stored in one of the data bit areas to another one of the data bit areas, the error correcting unit determines whether the sector data contains an error bit that cannot be corrected according to the error correcting code in the corresponding error correcting bit area,

wherein when the sector data contains the error bit that cannot be corrected, the marking unit records the data accuracy marks in the corresponding redundancy bit area as an error status.

3. The flash memory control circuit according to claim 2 further comprising an identification unit coupled to the microprocessor unit,

wherein when the computer host reads the sector data from the flash memory, the error correcting unit corrects the sector data according to the error correcting code corresponding to the sector data, and the identification unit identifies whether the sector data is accurate according to a error correction result and the data accuracy marks corresponding to the sector data.

4. The flash memory control circuit according to claim 3, wherein when the sector data is not accurate, the identification unit sends an error message to the computer host.

5. The flash memory control circuit according to claim 4, wherein when the computer host receives the error message and restores at least one of the sector data, the marking unit records the data accuracy mark corresponding to the restored sector data as the normal status.

6. A flash memory storage system, comprising:

a connector, used to connect a computer host;

a flash memory, having a plurality of physical blocks, wherein each of the physical blocks has a plurality of pages; and

a flash memory controller, coupled to the connector and the flash memory, and used to divide each of the pages into at least one data bit area, and at least one redundancy bit area and at least one error correcting bit area corresponding to the data bit area, wherein the data bit area has a plurality of sectors for storing a plurality of sector data,

wherein when the computer host writes a plurality of sector data into one of the data bit areas, the flash memory controller generates an error correcting code according to the sector data, writes the sector data into one of the data bit areas, writes the error correcting code into the corresponding error correcting bit area, and records the data accuracy marks in the corresponding redundancy bit area as a normal status, wherein each of the data accuracy marks is corresponding to one of the sector data.

7. The flash memory storage system according to claim 6, wherein when the flash memory controller copies the sector data stored in one of the data bit areas to another one of the data bit areas, the flash memory controller determines whether the sector data contains an error bit that cannot be corrected according to the error correcting code in the corresponding error correcting bit area,

wherein when the sector data contains the error bit that cannot be corrected, the flash memory controller records the data accuracy marks in the corresponding redundancy bit area as an error status.

8. The flash memory storage system according to claim 7, wherein when the computer host reads the sector data from the flash memory, the flash memory controller corrects the sector data according to the error correcting code corresponding to the sector data and identifies whether the sector data is accurate according to a error correction result and the data accuracy marks corresponding to the sector data.

9. The flash memory storage system according to claim 8, wherein when the sector data is not accurate, the flash memory controller sends an error message to the computer host.

10. The flash memory storage system according to claim 9, wherein when the computer host receives the error message and restores at least one of the sector data, the marking unit records the data accuracy mark corresponding to the restored sector data as the normal status.

11. A method for identifying error data in a flash memory, comprising:

providing a flash memory, wherein the flash memory has a plurality of physical blocks, and each of the physical blocks has a plurality of pages;

dividing each of the pages into at least one data bit area, and at least one redundancy bit area and at least one error correcting bit area corresponding to the data bit area, wherein the data bit area has a plurality of sectors;

configuring a plurality of data accuracy marks in each of the redundancy bit areas by using a marking unit;

when a computer host writes a plurality of sector data into one of the data bit areas, writing an error correcting code corresponding to the sector data in the corresponding error correcting bit area, and recording the data accuracy marks in the corresponding redundancy bit area as a normal status by using the marking unit, wherein each of the data accuracy marks is corresponding to one of the sector datas;

when the sector data stored in one of the data bit areas is copied to another one of the data bit areas, determining whether the sector data contains an error bit that cannot be corrected according to the error correcting code in the corresponding error correcting bit area; and

recording the data accuracy marks in the corresponding redundancy bit area as an error status by using the marking unit when the sector data contains the error bit that cannot be corrected.

12. The method according to claim 11, further comprising when the computer host reads the sector data from the flash memory, identifying whether the sector data is accurate according to the error correcting code and the data accuracy marks corresponding to the sector data by using an identification unit.

13. The method according to claim 12, further comprising sending an error message to the computer host when the sector data is not accurate.

14. The method according to claim 13, further comprising when the computer host receives the error message and restores at least one of the sector data, recording the data accuracy mark corresponding to the restored sector data as the normal status.

15. A method for identifying error data in a flash memory, comprising:

providing a flash memory, wherein the flash memory has a plurality of physical blocks, and each of the physical blocks has a plurality of pages;

dividing each of the pages into at least one data bit area, and at least one redundancy bit area and at least one error correcting bit area corresponding to the data bit area, wherein the data bit area has a sector;

configuring a data accuracy mark in each of the redundancy bit areas by using a marking unit;

when a computer host writes a sector data into one of the data bit areas, writing an error correcting code corresponding to the sector data into the corresponding error correcting bit area, and recording the data accuracy mark in the corresponding redundancy bit area as a normal status by using the marking unit;

when the sector data stored in one of the data bit areas is copied to another one of the data bit areas, determining whether the sector data contains an error bit that cannot be corrected according to the error correcting code in the corresponding error correcting bit area; and

recording the data accuracy mark in the corresponding redundancy bit area as an error status by using the marking unit when the sector data contains the error bit that cannot be corrected.

16. The method according to claim 15, further comprising when the computer host reads the sector data from the flash memory, identifying whether the sector data is accurate according to the error correcting code and the data accuracy mark corresponding to the sector data by using an identification unit.

17. The method according to claim 16, further comprising sending an error message to the computer host when the sector data is not accurate.

18. The method according to claim 17, further comprising when the computer host receives the error message and restores the sector data, recording the data accuracy mark corresponding to the restored sector data as the normal status.