Method and system for managing a flash memory mass storage system

• US 5,956,473 A
• Filed: 11/25/1996
• Issued: 09/21/1999
• Est. Priority Date: 11/25/1996
• Status: Expired due to Term

• Current Assignee: Macronix International Co., Ltd.
• Original Assignee: Macronix International Co., Ltd.
• Inventors: Lin, Chun-Hung, Lee, Li-Jen, Hu, Ting-Chung, Lee, Ju-Xu, Lee, Tai-Yao, Ma, Chung-Wen
• Primary Examiner(s): Decady, Albert
• Application Number:
  US08/755,194
• Time in Patent Office: 1,030 Days
• Field of Search: 395/180, 395/181, 395/182.03, 395/182.04, 395/182.05, 395/182.06, 395/185.06, 395/185.07, 365/189.01, 365/185.33
• US Class Current: 714/5.1
• CPC Class Codes: G06F 11/1068 in sector programmable memories, e.g. flash disk G06F11/1072 takes precedence
• CPC Class Codes: G06F 12/0246 in block erasable memory, e.g. flash memory
• CPC Class Codes: G06F 2212/1036 Life time enhancement
• CPC Class Codes: G06F 2212/7211 Wear leveling
• CPC Class Codes: G06F 3/0616 in relation to life time, e.g. increasing Mean Time Between Failures [MTBF]
• CPC Class Codes: G06F 3/0652 Erasing, e.g. deleting, data cleaning, moving of data to a wastebasket
• CPC Class Codes: G06F 3/0679 Non-volatile semiconductor memory device, e.g. flash memory, one time programmable memory [OTP]
• CPC Class Codes: G11C 16/349 Arrangements for evaluating degradation, retention or wearout, e.g. by counting erase cycles
• CPC Class Codes: G11C 16/3495 Circuits or methods to detect or delay wearout of nonvolatile EPROM or EEPROM memory devices, e.g. by counting numbers of erase or reprogram cycles, by using multiple memory areas serially or cyclically
• CPC Class Codes: G11C 29/765 in solid state disks

Abstract

The present application discloses methods to provide defect management, wear leveling and data security to a mass storage system implemented using flash memory. The flash memory is organized into a plurality of blocks. Each block has a special region for storing its attributes. In defect management, defects arising from manufacturing and on-the-fly defects are scanned. Defective blocks are marked by altering its attributes. The present application also discloses a wear leveling method in which the difference between the number of erasures of any two blocks (except the defective blocks) is within a predetermined value. The present application further discloses a new error detection and correction method. The same data is stored in two separate memory locations. The content of these two locations are later "ored" or "anded" together (depending on the nature of error giving rise to the error) to recover the correct data.

Claims

1. A method for managing a mass storage system implemented using flash memory, comprising the steps of:

(a) dividing said flash memory into a plurality of data blocks;

(b) indicating that specified data blocks belong to a first type of blocks, said first type designating blocks being used to store data organized in accordance with a pre-defined addressing scheme;

(c) indicating that specified data blocks belong to a second type of blocks, said second type designating blocks being used as image buffers of associated blocks of the first type for storing data, and as later replacements of the associated blocks of the first type;

(d) indicating that specified data blocks belong to a third type of blocks, said third type designating blocks containing data that will be erased;

(e) changing at least one of said plurality of blocks from one of said first, said second and said third types of blocks to another type; and

(f) equalizing the number of erasures for a subset of said plurality of data blocks.

2. The method of claim 1 wherein said equalizing step comprises the steps of:

(a) determining an age count for said subset of blocks; and

(b) equalizing said age count for said subset of blocks.

3. The method of claim 2 wherein said step of determining said age count comprises the steps of:

(a) assigning a region in each of said subset of blocks for storing said age count; and

(b) increasing said age count each time when a block in said subset of blocks is erased.

4. A method for managing a mass storage system implemented using flash memory, comprising the steps of:

(a) dividing said flash memory into a plurality of data blocks;

(b) indicating that specified data blocks belong to a first type of blocks, said first type designating blocks being used to store data organized in accordance with a pre-defined addressing scheme;

(c) indicating that specified data blocks belong to a second type of blocks, said second type designating blocks being used as image buffers of associated blocks of the first type for storing data, and as later replacements of the associated blocks of the first type;

(d) indicating that specified data blocks belong to a third type of blocks, said third type designating blocks containing data that will be erased;

(e) changing at least one of said plurality of blocks from one of said first, said second and said third types of blocks to another type; and

(f) preserving valid data in a subset of said plurality of blocks.

5. The method of claim 4 wherein said preserving step further comprises the step of marking a block in said first type of blocks dirty after valid data is written into a block in said second type of blocks.

6. The method of claim 4 wherein said preserving step further comprises the steps of:

(a) dividing a block in said subset into a plurality of sectors, each block having a start portion, a data portion, and an end portion; and

(b) marking a sector in said block valid only when said start and said end portions contain valid data.

7. The method of claim 4 wherein said preserving step further comprises the steps of:

(a) dividing a block in said subset into a plurality of sectors, each block having a start portion, a data portion, and an end portion; and

(b) marking a sector in said block clean only when no data has been written into said start and said end portions.

8. The method of claim 4 wherein said preserving step further comprises the steps of:

(a) storing a piece of data in two separate memory locations; and

(b) forming an "OR" operation of data in said two separate memory locations to recover said piece of data.

9. The method of claim 4 wherein said preserving step further comprises the steps of:

(a) storing a piece of data in two separate memory locations; and

(b) forming an "AND" operation of data in said two separate memory locations to recover said piece of data.

10. The method of claim 8 wherein said piece of data comprises information associated with the memory location and sector address.

11. The method of claim 9 wherein said piece of data comprises information associated with the memory location and sector address.

12. The method of claim 8 wherein said piece of data comprises information not protected by ECC.

13. The method of claim 9 wherein said piece of data comprises information not protected by ECC.