Interface between a pair of processors, such as host and peripheral-controlling processors in data processing systems

• US 4,449,182 A
• Filed: 10/05/1981
• Issued: 05/15/1984
• Est. Priority Date: 10/05/1981
• Status: Expired due to Term

• Current Assignee: Hewlett-Packard Development Company, L.P. (HP Inc.)
• Original Assignee: Digital Equipment Corporation (HP Inc.)
• Inventors: Gardner, Edward A., Lary, Richard F., Rubinson, Barry L., Keck, Dale R., Grace, William A.
• Primary Examiner(s): Ruggiero, Joseph F.
• Assistant Examiner(s): Harkcom, Gary V.
• Application Number:
  US06/308,826
• Time in Patent Office: 953 Days
• Field of Search: 364/200 MS File, 364/900 MS File, 371/21
• US Class Current: 710/60
• CPC Class Codes: G06F 13/126 and has means for transferring I/O instructions and statuses between control unit and main processor
• CPC Class Codes: G06F 15/17356 Indirect interconnection networks
• CPC Class Codes: G06F 15/177 Initialisation or configuration control processor initialisation G06F9/4405
• CPC Class Codes: G06F 9/4405 Initialisation of multiprocessor systems

Abstract

An interface mechanism (10) between two processors, such as a host processor (70) and a processor (31) in an intelligent controller (30) for mass storage devices (40), and utilizing a set of data structures employing a dedicated communications region (80A) in host memory (80). Interprocessor commands and responses are communicated as packets over an I/O bus (60) of the host (70), to and from the communication region (80A), through a pair of ring-type queues (80D) and (80E). The entry of each ring location (e.g., 132, 134, 136, 138) points to another location in the communications region where a command or response is placed. The filling and emptying of ring entries (132-138) is controlled through the use of an `ownership` byte or bit (278) associated with each entry. The ownership bit (278) is placed in a first state when the message source (70 or 31) has filled the entry and in a second state when the entry has been emptied. Each processor keeps track of the rings'"'"' status, to prevent the sending of more messages than the rings can hold. These rings permit each processor to operate at its own speed, without creating race conditions and obviate the need for hardware interlock capability on the I/O bus (60).

Claims

1. In a data processing system which includes first and second processors (70 and 31), a memory (80) to which information can be written by each of said processors and from which information can be read by each of said processors, such memory having a plurality of locations for storing said information, and bus means (60) for interconnecting the first and second processors and said memory, to enable communications therebetween, said bus means being of the type which has no hardware interlock capability which is usable by the other of said processors to selectively prevent the other of said processors from accessing said memory locations, the improvement comprising:

communications control means for controlling communications between said processors and permitting the first processor to send a plurality of commands in sequence to the second processor via the bus means, and for permitting the second processor to send responses to those commands to the first processor via the bus means;

the communications control means including a plurality of locations in said memory, termed interface memory locations, adapted to serve as a communications interface between the first and second processors, all commands and responses being transmitted through such interface memory locations;

the interface memory locations comprising a pair of ring buffers;

a first one of said ring buffers being adapted to buffer the transmission of messages issued by the first processor and a second one of said ring buffers being adapted to buffer the reception of messages transmitted by the second processor;

each of said ring buffers including a plurality of memory locations adapted to receive from an associated one of said processors a descriptor signifying another location in said memory;

for said first ring buffer, the location signified by such descriptor being a location containing a message for transmission to the second processor;

for said second ring buffer, the location signified by such descriptor being a location for holding a message from the second processor; and

the communications control means permitting each of said processors to operate at its own rate, independent of the other of said processors, and to access a ring buffer for writing thereto only when the buffer does not contain information previously written to such buffer but not yet read from it and for reading to such buffer only when the buffer contains information written to it but not yet read therefrom, thus preventing race conditions from developing across said bus means in relation to accessing the interface memory locations.

2. The apparatus of claim 1 wherein there is associated with each ring buffer entry a bit whose state indicates the status of that entry;

for each entry of the first ring buffer, the first processor being adapted to place such entry'"'"'s ownership bit in a predetermined first state when a descriptor is written into said entry, and the second processor being adapted to cause the state of the ownership bit to change when such descriptor is read from said entry;

for each entry of the second ring buffer, the second processor being adapted to place such entry'"'"'s ownership bit in a predetermined first state when a descriptor is written into said entry, and the first processor being adapted to cause the state of the ownership bit to change when such descriptor is read from said entry;

the first and second processors being adapted to read ring buffer entries in sequence and to read each ring buffer entry only when the ownership bit of said entry is in said predetermined first state, whereby an entry may not be read twice and an entry may not be read before a descriptor is written thereto.

3. The data processing system of claim 1 wherein the communications control means is further adapted to provide such communications while each of the processors is permitted to operate at its own rate, independent of the other processor, and while avoiding processor interruption for a multiplicity of read and write operations.

4. In a data processing system which includes first and second processors (70 and 31), a memory (80) adapted to be used by said processors for containing information to be shared by the processors, and bus means (60) for interconnecting the first and second processors and the memory, the bus means (60) being of the type which has no hardware interlock capability which is usable by each of said processors to selectively prevent the other of said processors from accessing at least a portion of said memory, the improvement comprising:

the first and second processors (70 and

     31) being adapted to employ a portion (80A) of said memory as a communications region accessible by both of said processors, so that all commands and responses can be transmitted from one of said processors to the other of said processors through such portion of memory;

the communications region of memory including a pair of ring buffers (80D and 80E);

a first one of said ring buffers (80D) buffering the transmission of messages issued by the first processor (70) and a second one of said ring buffers (80E) buffering the reception of messages transmitted by the second processor (31);

each of said ring buffers including a plurality of memory locations (e.g., 132, 134, 136 and

     138) adapted to receive from the associated transmitting one of said processors a descriptor signifying another location in said memory;

for said first ring buffer, the location signified by such descriptor being a location containing a message for transmission to the second processor;

for said second ring buffer, the location signified by such descriptor being a location for storing, at least temporarily, a message from the second processor; and

the first and second processors (70 and

     31) further being adapted to control access to said communications region (80A) such that information written therein by one of said processors may not be read twice by the other processor and a location where information is to be written by one of the processors may not be read by the other processor before said information has been written,

so that race conditions are prevented from developing across said bus means in the course of inter-processor communications, and messages are transmitted from said ring buffers in the same sequence as that in which they are issued by the processors, while each of the processors is permitted to operate at its own rate, with substantial independence from the other processor.

5. The apparatus of claim 4 wherein said ring buffers are adapted to permit the first processor to send a plurality of commands in sequence to the second processor via the bus means, and to permit the second processor to send responses to those commands to the first processor via the bus means.

6. The apparatus of claim 5 wherein the first processor (70) is a host computer'"'"'s (1) central processor, the second processor (31) is a processor in a controller (2, 30) for a secondary storage device (40), and the bus means includes an input/output bus (60) for interconnecting said host computer with said secondary storage device.

7. The apparatus of claim 5 wherein there is associated with each ring buffer entry a byte of at least one bit, termed the ownership byte (FIG. 3B-133, 135, 137, 139;

FIG. 8-278), whose state indicates the status of that entry;

for each entry of the first ring buffer (80D), the first processor (70) being adapted to place such entry'"'"'s ownership byte in a predetermined first state when a descriptor is written into said entry, and the second processor (31) being adapted to cause the state of the ownership byte to change when such descriptor is read from said entry;

for each entry of the second ring buffer (80E), the second processor (31) being adapted to a place such entry'"'"'s ownership byte in a predetermined first state when a descriptor is written into said entry, and the first processor (70) being adapted to cause the state of the ownership byte to change when such descriptor is read from said entry;

the first and second processors being adapted to read ring buffer entries in sequence and to read each ring buffer entry only when the ownership byte of said entry is in said predetermined first state, whereby an entry may not be read twice and an entry may not be read before a descriptor is written thereto.

8. The apparatus of claim 7 wherein said ownership byte (278) is the most significant bit in each descriptor (260, 264).

9. The apparatus of claim 5 wherein the controller (2, 30) further includes pointer means (32, 34) for keeping track of the current first and second ring buffer entries.

10. The apparatus of claim 5 further including means for limiting the generation of processor interrupt requests to the first processor in connection with the sending of commands and receipt of responses by said processor, such that interrupt requests to said processor are generated substantially only when an empty ring buffer becomes not-empty and when a full ring buffer becomes not-full.

11. The apparatus of claim 10 wherein the size of each ring buffer is communicated by said first processor to the second processor at the time of initializing a communications path betweem them.

12. The apparatus of claim 11 wherein the processors (70, 31) communicate by sending message packets to each other, and further including:

the first ring buffer (80D) being adapted to hold up to M commands to be executed;

an input/output device class driver (3) associated with the first processor (70) for sending commands to and receiving responses from an input/output device (40);

the second processor (31) being adapted to provide to the class driver (3) in its first response packet the number M of commands of a predetermined length which said buffer can hold;

the class driver being adapted to maintain a credit account having a credit account balance indicative of the number of commands the buffer can accept at any instant;

the credit account balance initially being set to equal M and being decremented by one each time the class driver issues a command and being incremented by the value;

the second processor further being adapted to provide to the class driver, with each response packet, a credit value (FIG. 9,

     288) representing the number of commands executed to evoke the response;

the class driver incrementing the credit account balance by said credit value; and

the first processor and class driver being adapted so as not to issue any commands when the credit account balance is zero and further being adapted to issue only commands which are immediately executed when the credit account balance is one.

13. In a data processing system which includes first and second processors, (70 and 31) a memory (80) adapted to be used by said processors, and bus means (60, 110, 90) for interconnecting the first and second processors and memory to enable communications therebetween, said bus means being of the type which has no hardware interlock capability which is usable by each of said processors to selectively prevent the other of said processors from accessing at least a portion of said memory, the improvement comprising:

at least a portion (80A) of said memory (80) being adapted to serve as a communications region accessible by both of said processors all commands and responses being transmitted from one processor to the other through such portion of memory;

means (278) for controlling access to information in said communications region whereby information written therein by one of said processors may not be read twice by the other processor and wherein a location where information is to be written by one of the processors may not be read by the other processor before said information has been written;

the communications region of memory including a pair of ring buffers (80D, 80E);

a first one of said ring buffers (80D) being adapted to buffer the transmission of messages issued by the first processor and a second one of said ring buffers (80E) being adapted to buffer the reception of messages transmitted by the second processor;

each of said ring buffers including a plurality of memory locations (e.g., FIG. 3B-132, 134, 136,

     138) adapted to receive from an associated one of said processors a descriptor (260,

     264) signifying another location in said memory;

for said first ring buffer, the location signified by such descriptor being a location containing a message for transmission to the second processor; and

for said second ring buffer, the location signified by such descriptor being a location for holding a message from the second processor,

so that race conditions are prevented from developing across said bus means and messages are transmitted from said ring buffers in the same sequence as that in which they are issued by the processors, while each of the processors is permitted to operate at its own rate, independent of the other processor.

14. The apparatus of claim 13 wherein said ring buffers are adapted to permit the first processor to send a plurality of commands in sequence to the second processor via the bus means, and to permit the second processor to send responses to those commands to the first processor via the bus means.

15. The apparatus of claim 14 wherein the first processor is a host computer'"'"'s (1) central processor (70), the second processor is a processor (31) in a controller (2, 30) for a secondary storage device (40), and the bus means includes an input/output bus (60) for interconnecting said host computer with said secondary storage device.

16. The apparatus of claim 15 wherein there is associated with each ring buffer entry a byte of at least one bit, termed the ownership byte (FIG. 3B-133, 135, 137, 139;

FIG. 8,

     278), whose state indicates the status of that entry;

for each entry of the first ring buffer (80D), the first processor (70) being adapted to place such entry'"'"'s ownership byte in a predetermined first state when a descriptor (260,

     264) is written into said entry, and the second processor (31) being adapted to cause the state of the ownership byte to change when such descriptor is read from said entry;

for each entry of the second ring buffer (80E), the second processor (31) being adapted to place such entry'"'"'s ownership byte in a predetermined first state when a descriptor is written into said entry, and the first processor (70) being adapted to cause the state of the ownership byte to change when such descriptor is read from said entry;

the first and second processors being adapted to read ring buffer entries in sequence and to read each ring buffer entry only when the ownership byte of said entry is in said predetermined first state, whereby an entry may not be read twice and an entry may not be read before a descriptor is written thereto.

17. The apparatus of claim 15 wherein the controller further includes pointer means (32, 34) for keeping track of the current first and second ring buffer entries.

18. The apparatus of claim 15 further including means for reducing the generation of processor interrupt requests to the first processor in the sending of commands thereby and responses thereto, such that interrupt requests to said processor are generated substantially only when an empty ring buffer becomes non-empty and when a full ring buffer becomes not full.

19. The apparatus of claim 18 wherein the size of each ring buffer is communicated by said first processor to the other of said processors at the time of initializing the communications path between them.

20. The apparatus of claim 19 wherein the processors communicate by sending message packets to each other, and further including:

a buffer associated with the second processor for holding up to M commands to be executed;

an input/output device class driver associated with the first processor for sending commands to and receiving responses from an input/output device;

the second processor being adapted to provide to the class driver in its first response packet the number M of commands of a predetermined length which said buffer can hold;

the class driver being adapted to maintain a credit account having a credit account balance indicative of the number of commands the buffer can accept at any instant;

the credit account balance initially being set to equal M and being decremented by one each time the class driver issues a command and being incremented by the value;

the second processor further being adapted to provide to the class driver, with each response packet, a credit value representing the number of commands executed to evoke the response;

the class driver incrementing the credit account balance by said credit value; and

the first processor and class driver being adapted so as not to issue any commands when the credit account balance is zero and further being adapted to issue only commands which are immediately executed when the credit account balance is one.

21. The apparatus of claim 16 wherein said ownership byte is the most significant bit in each descriptor.