CN102567275B - Method and system for memory access among multiple operation systems on multi-core processor - Google Patents

Method and system for memory access among multiple operation systems on multi-core processor Download PDF

Info

Publication number
CN102567275B
CN102567275B CN201110211429.1A CN201110211429A CN102567275B CN 102567275 B CN102567275 B CN 102567275B CN 201110211429 A CN201110211429 A CN 201110211429A CN 102567275 B CN102567275 B CN 102567275B
Authority
CN
China
Prior art keywords
operating system
internal memory
access
accessed
memory
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Expired - Fee Related
Application number
CN201110211429.1A
Other languages
Chinese (zh)
Other versions
CN102567275A (en
Inventor
张武
查奇文
郭秀岩
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Institute of Acoustics CAS
Original Assignee
Institute of Acoustics CAS
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Institute of Acoustics CAS filed Critical Institute of Acoustics CAS
Priority to CN201110211429.1A priority Critical patent/CN102567275B/en
Publication of CN102567275A publication Critical patent/CN102567275A/en
Application granted granted Critical
Publication of CN102567275B publication Critical patent/CN102567275B/en
Expired - Fee Related legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Landscapes

  • Storage Device Security (AREA)

Abstract

The invention discloses a method and a system for memory access among multiple operation systems on a multi-core processor. The method is characterized in that a plurality of operation systems can be simultaneously operated on the multi-core processor, wherein each operation system is used for managing an independent and non-overlapping memory space on a shared physical memory; one optional operation system can guarantee safety access to the memory space managed by the operation system by the aid of a locking mechanism; and one optional operation system can guarantee safety access to memory spaces managed by the other operation systems by means of inter-core communication and by the aid of the locking mechanism. By the aid of the method, safety access to the memory spaces among the multiple operation systems on the multi-core processor is realized, each operation system is ensured to safely access to the whole shared physical memory, and high-efficiency interaction and data transfer among the operation systems can be realized. Based on the method, safe and high-efficiency exchange and operation of data among the operation systems can be realized.

Description

The method and system of internal storage access between a plurality of operating system on a kind of polycaryon processor
Technical field
The present invention designs polycaryon processor and multiple operating system field, especially relates on a kind of polycaryon processor the method and system of internal storage access between a plurality of operating system.
Background technology
Along with the continuous progress of infotech, computer hardware is develop rapidly also.In the evolution of information industry, single core processor exposes various limitations, simple by improving dominant frequency, cannot meet the performance requirement more and more expanded, and the integrated level of the single core processor convergence limit, and power consumption is also more and more higher.Along with the development of processor technology, the use of polycaryon processor becomes trend gradually.Polycaryon processor is with respect to single core processor, although the dominant frequency of each processor core is lower, overall power is less; And can expand more core and improve performance, a plurality of processor cores can be optimized different application by structures such as serial, parallel, mixed production lines, both can give full play to the performance of processor, can improve again the execution efficiency of application program.Along with the needs of Vehicles Collected from Market economic development, people require further to improve to processor speed, business computing market value, application prospect, power consumption etc. aspect of performance, and polycaryon processor has become the main flow of server and individual operating platform.
Polycaryon processor has brought huge variation to people, brings more productivity advantage and remarkable performance performance.In the general processor field, the main flow of INTEL Corp. and AMD's release is all polycaryon processor towards desktop and service-oriented device processor at present, the II of the Athon towards the desktop series processors that for example AMD releases and Opteron 6000 series processors of service-oriented device.In built-in field, as the Cortex processor based on ARM, OCTEON series processors and various high-performance processors based on PowerPC based on MIPS have been widely used in the fields such as mobile phone, single-chip microcomputer, router, server.
Current much operating system is all supported polycaryon processor, such as Linux can be by by the SMP mode, supporting polycaryon processor, and an operating system of the common support of a plurality of core.And on polycaryon processor, all core can be divided into to different groups, all load operation systems on every group of core.Or even can load an operating system at each core.
All cores of polycaryon processor are all to be connected to above identical physical memory by Memory Controller Hub usually.In the single operating moved on multi-core processor system, different endorsing with the mechanism by locking guarantees the secure access to same accessed internal memory, but the core on the different operating system moved on multi-core processor system just can not guarantee by the mechanism locked the secure access of same accessed internal memory.So while on polycaryon processor, moving a plurality of operating system, common way is that physical memory is divided into to different memory headrooms, and each operating system has independently memory headroom separately, and each system all can only be accessed the memory headroom of oneself, independent operating, do not interfere with each other.Although so do the secure access that can guarantee internal memory, each operating system can only be accessed the part of physical memory, and is unfavorable for the mutual and data transmission between operating system.
Summary of the invention
The object of the invention is to, while for overcoming prior art, on polycaryon processor, moving a plurality of operating system, each operating system can only be accessed the part of physical memory, therefore be unfavorable for the problems such as mutual and data transmission between operating system, thereby the method and system of internal storage access between a plurality of operating system are provided on a kind of polycaryon processor.
The invention provides on a kind of polycaryon processor the method for internal memory secure access between a plurality of operating system, independent nonoverlapping memory headroom on shared physical memory in each operating system management, with the inter-core message communication mechanism, realizes the internal memory secure access between multiple operating system.The method of communicating by letter by inter-core message, guaranteed the secure access of a plurality of operating system to same accessed internal memory, thereby make all operating system can use whole physical memory, and make the mutual and data between operating system transmit more convenient.
The invention provides on a kind of polycaryon processor the method for internal memory secure access between a plurality of operating system, the method is for the mutual access of a plurality of operating system institute managing internal memory that moves on multinuclear operating system, wherein each operating system by memory management mechanism separately, manage in to exist on physical address space be independent nonoverlapping, and each operating system can be utilized physical address travel all over physical memory space, and described method comprises:
The memory headroom of managing by other operating systems of inter-core message communication mechanism secure access between described a plurality of operating system, specifically comprise initiatively accessing step and passive access step;
The active accessing step, when the first operating system need to be accessed the memory headroom of the second operating system, the first operating system is locked to accessed internal memory by internuclear communication notifications the second operating system, after the second operating system has locked, by the mode of internuclear communication, notify the first operating system can the accessed internal memory of secure access, after the first operating system A has accessed accessed internal memory, by the mode of internuclear communication, notify the second operating system B to accessed internal memory release;
The passive access step, when the first operating system A needs the second operating system B to visit its memory headroom, after the first operating system A has locked to accessed internal memory, by internuclear communication mechanism, notify the second operating system B to carry out secure access to accessed internal memory, after the second operating system B has accessed, by the mode of internuclear communication, notify the first operating system A to carry out release to accessed internal memory.
In technique scheme, described active accessing step comprises:
Step 201, the first operating system A is physical address by the virtual address translation of accessed internal memory, then by access request message, notifies the second operating system B; Described access request message comprises following field: the physical address of accessed internal memory, access rights;
Step 202 after the second operating system B receives access request message, parses physical address and the length of accessed internal memory from message;
Step 203, the second operating system B obtains the virtual address of accessed internal memory according to physical address, and the second operating system B waits for the spin lock of accessed internal memory;
Step 204, after the second operating system B obtains the spin lock of accessed internal memory, notify the first operating system A secure access accessed internal memory by the success message that locks;
Step 205, the first operating system A, after receiving the success message that locks, starts to access accessed internal memory according to access rights, and the operation of executable operations type definition;
Step 206, the first operating system A, after having accessed accessed internal memory, completes message informing operating system B access by access and finishes.
Step 207, the second operating system B is after receiving and having accessed message, operating system B is to discharging the spin lock of accessed internal memory.
Wherein, the described access request message of step 201 also comprises following field: the length of accessed internal memory and action type.
In technique scheme, described passive access step comprises: the accessed message of step 302 described request comprises following field: the physical address of accessed internal memory, action type and access rights
Step 301, the second operating system B waits for the spin lock of accessed internal memory;
Step 302, the second operating system B, after obtaining spin lock, is physical address by virtual address translation, then by asking accessed message informing the first operating system A to access accessed internal memory;
Step 303, the first operating system A becomes virtual address by the physical address translations of accessed internal memory after receiving the accessed message of request, and then the mode of operation according to access rights and action type definition conducts interviews to accessed internal memory;
Step 304, after the first operating system A completes the accessing operation of accessed internal memory, complete message informing the second operating system B access by access and complete;
Step 305, after the second operating system B receives and accessed message, discharge the spin lock of accessed internal memory.
Wherein, the accessed message of step 302 described request also comprises the length of accessed internal memory.
Based on the method for internal memory secure access between a plurality of operating system on above polycaryon processor, the present invention also provides a kind of a plurality of operating system data to be carried out to the method for the processing of pipeline system.
The step of the processing of wherein said continuous-flow type is: by a plurality of operating system, the processing mode according to streamline is completed by a plurality of operating system respectively a Processing tasks to internal memory, thereby realizes the associated treatment between a plurality of operating system; The first operating system A is after first operation completed accessed internal memory, by this method, notify the second operating system B to complete second operation to accessed internal memory, then notify the 3rd operating system C to complete the 3rd operation to accessed internal memory, these operations do not need data are copied between a plurality of operating system.
Based on above method, the present invention also provides on a kind of polycaryon processor the system of internal storage access between a plurality of operating system, this system is for the mutual access of a plurality of operating system institute managing internal memory that moves on polycaryon processor, wherein each operating system by memory management mechanism separately, manage in to exist on physical address space be independent nonoverlapping, and each operating system can be utilized physical address travel all over physical memory space, described system comprises: the active access modules, in the time of need to accessing the memory headroom of the second operating system for the first operating system, the first operating system is locked to accessed internal memory by internuclear communication notifications the second operating system, after the second operating system has locked, by the mode of internuclear communication, notify the first operating system can the accessed internal memory of secure access, after the complete accessed internal memory of the first operating system access, by the mode of internuclear communication, notify the second operating system to accessed internal memory release.
The passive access module, while for the first operating system, needing the second operating system to visit its memory headroom, after the first operating system has locked to accessed internal memory, by internuclear communication mechanism, notify the second operating system to carry out secure access to accessed internal memory, after the second operating system access completes, by the mode of internuclear communication, notify the first operating system to carry out release to accessed internal memory.
Technique scheme, described active access modules and passive access module further comprise separately:
Message transmission module, for sending the internuclear communication information between the first operating system and the second operating system; Described packets of information contains: initiatively access request message, the success message that locks, accessed message and passive access request message.
The message acceptance parsing module, for resolving the internuclear communication information of acceptance, and send action type corresponding operational order; The packets of information of described parsing contains: the physical address and the length that parse accessed internal memory from access message; The physical address of the accessed internal memory parsed from the passive access request message and length, action type, access rights.
Address conversion module, be virtual memory address and be physical address by the virtual address translation of accessed internal memory for the physical address translations by accessed internal memory.
Add lock module, locked and release for the operating system to being allowed to access; Described locking comprises: to accessed memory setting spin lock.
In technique scheme, described active access request message comprises following field: the physical address of accessed internal memory and length, access rights; Described passive access request message comprises following field: the physical address of accessed internal memory and length, access rights, action type.
The invention has the advantages that, the present invention has realized on the polycaryon processor exclusive reference of a plurality of operating systems of operation to the Same Physical internal memory simultaneously.This method has also realized that on the polycaryon processor, a plurality of operating system is carried out the processing of pipeline system to data, for example operating system A is after the-item operation completed accessed internal memory, can notify operating system B to complete second operation to accessed internal memory by this method, then notify operating system C to complete the 3rd operation to accessed internal memory, these operations do not need data are copied.Based on the method, can realize data security, exchange efficiently and operation between a plurality of operating system.
The accompanying drawing explanation
Fig. 1 is the method for internal storage access between a plurality of operating system on the bright middle polycaryon processor of this law;
Fig. 2-a is the schematic block diagram that in the present invention, operating system is initiatively accessed other operating system institute's managing internal memory spaces;
Fig. 2-b is the process flow diagram that in the present invention, operating system is initiatively accessed other operating system institute's managing internal memory spaces;
Fig. 3-a is the schematic block diagram in other this operating system of operating system access institute's managing internal memory spaces of operating system proactive notification in the present invention;
Fig. 3-b is the flow process in other this operating system of operating system access institute's managing internal memory spaces of operating system proactive notification in the present invention.
Embodiment
Below in conjunction with accompanying drawing, content of the present invention is described in detail.
Concrete grammar of the present invention is:
Move a plurality of operating system on a polycaryon processor, these operating systems can be Linux, real time operating system or simple execution environment simultaneously, and each operating system may operate on one or more core.
In the present invention, each operating system by memory management mechanism separately, manage in to exist on physical address space be independent nonoverlapping, but each operating system can be utilized physical address travel all over physical memory space.As shown in Figure 1, during memory headroom that operating system A accessing operation system B manages, must realize the secure access to accessed internal memory by internuclear communication and locking mechanisms.
When operating system A needs the memory headroom of accessing operation system B, operating system A, by inter-core message communication, notifies the physical address of the accessed internal memory of operating system B, length, access rights and the action type of accessed internal memory; After operating system B receives message, wait for to obtain the lock of accessed internal memory, accessed internal memory is locked, then by inter-core message, notify the operating system A can the accessed internal memory of secure access; After operating system A receives message, access memory, notify operating system B internal storage access complete by inter-core message after completing access; After operating system B receives message, to accessed internal memory release.
When operating system B needs the memory headroom of operating system A accessing operation system B, at first operating system B obtains the lock of accessed internal memory, then accessed internal memory is locked, by inter-core message communication, notify the physical address of the accessed internal memory of operating system A, length, access rights and the action type of accessed internal memory after having locked; After operating system A receives message, the length according to physical address and the accessed internal memory of action type, accessed internal memory, conduct interviews to accessed internal memory, after having accessed, by inter-core message, notifies operating system B to access; After operating system B receives message, accessed internal memory is carried out to release.
Access rights comprise read-only, only write and readable writing.Read-only expression can only be from accessed internal memory reading out data, and only writing expression can only be to accessed internal memory data writing, readable write expression both can be from accessed internal memory reading out data, again can be to accessed internal memory data writing.For example, when the memory headroom that need to manage operating system B as operating system A carries out read-only operation, access rights are set to read-only.
Action type means between operating system the disposal route to accessed internal memory.These operations can be the processing according to engagement arithmetic to accessed data in EMS memory, the data in the accessed internal memory of operating system B being managed such as operating system A according to certain algorithm be encrypted, decipher, compress, the processing such as decompression.
Core concept of the present invention is a plurality of operating system of operation on polycaryon processor, the nonoverlapping memory headroom of independence on each operating system management person's same physical internal memory.During memory headroom by each this operating system of operating system access, can be by locking to realize secure access; And by internuclear communication with lock, can realize the secure access to other operating system institute's managing internal memory spaces, thereby realize the travel all over physical memory that each operating system can safety.
In order to make purpose of the present invention and scheme clearer, below the present invention is described in detail:
A plurality of operating system of operation on polycaryon processor, it is whole physical memory space that physical memory is reflected in the virtual memory space of each operating system, but the virtual memory spatial mappings that each operating system is managed is independent nonoverlapping memory headroom to physical memory.Each operating system can be passed through the memory headroom of this operating system management of access of locking mechanisms safety.As shown in Figure 1, if the situation of the memory headroom that operating system A accessing operation system B manages occurs, must guarantee by internuclear communication and locking mechanisms the secure access of the memory headroom that operating system A manages operating system B.Specifically be divided into following two kinds of situations:
(1) as shown in Fig. 2-a and Fig. 2-b, operating system A needs initiatively access to be positioned at the accessed internal memory of memory headroom B, and idiographic flow is as follows:
Step 201, operating system A is converted to physical address (addr) by the virtual address of accessed internal memory (ptr_a), then by access request message, notifies operating system B.Access request message comprises following field: the length (len) of the physical address of accessed internal memory (addr), accessed internal memory, access rights (authority) and action type (op);
Step 201 after operating system B receives access request message, parses physical address (addr) and the length (len) of accessed internal memory from message.
Then, operating system B obtains the virtual address (ptr_b) of accessed internal memory to step 203 according to physical address (addr).Next, operating system B waits for the spin lock (spinlock) of accessed internal memory;
Step 204, the spin lock (spinlock) that operating system B obtains accessed internal memory afterwards, by the accessed internal memory of success message notice operating system A secure access that locks;
Step 205, operating system A, after receiving the success message that locks, starts to access accessed internal memory according to access rights (authority), and the operation of executable operations type (op) definition;
Step 206, operating system A, after having accessed accessed internal memory, completes message informing operating system B access by access and finishes;
Step 207, operating system B after receiving and having accessed message, the spin lock (spinlock) of operating system B to discharging accessed internal memory.
In above flow process, when operating system A wants to access accessed internal memory, operating system C or operating system D also likely want to access accessed internal memory, and this is that the message of operating system A, operating system C and operating system D request access can form queue there at operating system B.Message queue has guaranteed beyond operating system B to only have an operating system at the accessed internal memory of competition.And spinlock has guaranteed to only have a core an of operating system or this operating system to access accessed internal memory.
(2) as shown in Fig. 3-a and Fig. 3-b, operating system B needs operating system A to visit to be positioned at the accessed internal memory of memory headroom B, and idiographic flow is as follows:
Step 301, operating system B waits for the spin lock (spinlock) of accessed internal memory;
Step 302, operating system B is obtaining spin lock (spinlock) afterwards, and virtual address (ptr_b) is converted to physical address (addr), then by asking accessed message informing operating system A to access accessed internal memory.Ask accessed message to comprise following field: the length (len) of the physical address of accessed internal memory (addr), accessed internal memory, action type (op) and access rights (authority);
Step 303, after operating system A receives the accessed message of request, convert the physical address of accessed internal memory (addr) to virtual address (ptr_a), then the mode of operation according to access rights (authority) and action type (op) definition conducts interviews to accessed internal memory;
Step 304, after operating system A completes the accessing operation of accessed internal memory, complete message informing operating system B access by access and complete;
Step 305, after operating system B receives and accessed message, discharge the spin lock (spinlock) of accessed internal memory.
In above flow process, spin lock (spinlock) has guaranteed to only have a core of this operating system or has only had an accessed internal memory of other operating system access.
It is to be noted, the foregoing is only the present invention's preferred embodiment of internal memory secure access between multiple operating system on polycaryon processor, not be used for limiting practical range of the present invention, technician with professional knowledge base can realize the present invention by above embodiment, therefore every any variation, modification and improvement according to making within the spirit and principles in the present invention, all covered by the scope of the claims of the present invention.

Claims (7)

1. the method for internal storage access between a plurality of operating system on a polycaryon processor, the method is for the mutual access of a plurality of operating system institute managing internal memory realizing moving on multinuclear operating system, wherein each operating system by memory management mechanism separately, manage in to exist on physical address space be independent nonoverlapping, and each operating system can be utilized physical address travel all over physical memory space, described method is to access by the inter-core message communication mechanism memory headroom that other operating systems are managed between described a plurality of operating system, comprise initiatively accessing step and passive access step,
The active accessing step, when the first operating system need to initiatively be accessed the memory headroom of the second operating system, the first operating system is locked to accessed internal memory by internuclear communication notifications the second operating system, after the second operating system has locked, by the mode of internuclear communication, notify the first operating system can the accessed internal memory of secure access, after the complete accessed internal memory of the first operating system access, by the mode of internuclear communication, notify the second operating system to accessed internal memory release;
The passive access step, when the first operating system needs the second operating system to visit its memory headroom, after the first operating system has locked to accessed internal memory, by internuclear communication mechanism, notify the second operating system to carry out secure access to accessed internal memory, after the second operating system access completes, by the mode of internuclear communication, notify the first operating system to carry out release to accessed internal memory.
2. the method for internal storage access between a plurality of operating system on polycaryon processor according to claim 1, is characterized in that, described active accessing step comprises:
Step 201, the first operating system is physical address by the virtual address translation of accessed internal memory, then by access request message, notifies the second operating system; Described access request message comprises following field: the physical address of accessed internal memory, access rights;
Step 202 after the second operating system is received access request message, parses physical address and the length of accessed internal memory from message;
Step 203, the second operating system obtains the virtual address of accessed internal memory according to physical address, and the second operating system is waited for the spin lock of accessed internal memory;
Step 204, after the second operating system obtains the spin lock of accessed internal memory, notify the first operating system security to access accessed internal memory by the success message that locks;
Step 205, the first operating system, after receiving the success message that locks, starts to access accessed internal memory according to access rights, and the operation of executable operations type definition;
Step 206, the first operating system, after having accessed accessed internal memory, completes message informing the second operating system access by access and finishes;
Step 207, the second operating system is after receiving and having accessed message, this second operating system is to discharging the spin lock of accessed internal memory;
Wherein, the described access request message of step 201 also comprises following field: the length of accessed internal memory and action type.
3. the method for internal storage access between a plurality of operating system on polycaryon processor according to claim 1, it is characterized in that, described passive access step comprises: the accessed message of step 302 described request comprises following field: the physical address of accessed internal memory, action type and access rights
Step 301, the first operating system is waited for the spin lock of accessed internal memory;
Step 302, the first operating system, after obtaining spin lock, is physical address by virtual address translation, then by the accessed internal memory of accessed message informing the second operating system access of request;
Step 303, the second operating system becomes virtual address by the physical address translations of accessed internal memory after receiving the accessed message of request, and then the mode of operation according to access rights and action type definition conducts interviews to accessed internal memory;
Step 304, the second operating system completes message informing the first operating system access by access and completes after the accessing operation of accessed internal memory is completed;
Step 305, after the first operating system is received and accessed message, discharge the spin lock of accessed internal memory.
4. the method for internal storage access between a plurality of operating system on polycaryon processor according to claim 3, is characterized in that, the accessed message of step 302 described request also comprises the length of accessed internal memory.
5. the system of internal storage access between a plurality of operating system on a polycaryon processor, this system is for the mutual access of a plurality of operating system institute managing internal memory that moves on multinuclear operating system, wherein each operating system by memory management mechanism separately, manage in to exist on physical address space be independent nonoverlapping, and each operating system can be utilized physical address travel all over physical memory space, and described system comprises:
The active access modules, in the time of need to accessing the memory headroom of the second operating system for the first operating system, the first operating system is locked to accessed internal memory by internuclear communication notifications the second operating system, after the second operating system has locked, by the mode of internuclear communication, notify the first operating system can the accessed internal memory of secure access, after the complete accessed internal memory of the first operating system access, by the mode of internuclear communication, notify the second operating system to accessed internal memory release;
The passive access module, while for the first operating system, needing the second operating system to visit its memory headroom, after the first operating system has locked to accessed internal memory, by internuclear communication mechanism, notify the second operating system to carry out secure access to accessed internal memory, after the second operating system access completes, by the mode of internuclear communication, notify the first operating system to carry out release to accessed internal memory.
6. the system of internal storage access between a plurality of operating system on polycaryon processor according to claim 5, is characterized in that, described active access modules and passive access module further comprise separately:
Message transmission module, for sending the internuclear communication information between the first operating system and the second operating system; Described packets of information contains: initiatively access request message, passive access request message, lock success message and access complete message;
The message acceptance parsing module, for resolving the internuclear communication information of acceptance, and send the corresponding operating order; The packets of information of described parsing contains: the physical address of the accessed internal memory parsed from the active access request message, length and access rights; The physical address of the accessed internal memory parsed from the passive access request message and length, action type, access rights;
Address conversion module, be virtual memory address and be physical address by virtual address translation for the physical address translations by accessed internal memory;
Add lock module, for accessed internal memory is locked; Described locking comprises: to accessed memory setting spin lock.
7. the system of internal storage access between a plurality of operating system on polycaryon processor according to claim 6, is characterized in that, described active access request message comprises following field: the length of the physical address of accessed internal memory and access rights and accessed internal memory;
The passive access request message comprises following field: the length of the physical address of accessed internal memory and access rights, accessed internal memory, action type.
CN201110211429.1A 2010-12-08 2011-07-27 Method and system for memory access among multiple operation systems on multi-core processor Expired - Fee Related CN102567275B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201110211429.1A CN102567275B (en) 2010-12-08 2011-07-27 Method and system for memory access among multiple operation systems on multi-core processor

Applications Claiming Priority (3)

Application Number Priority Date Filing Date Title
CN201010590429.2 2010-12-08
CN201010590429 2010-12-08
CN201110211429.1A CN102567275B (en) 2010-12-08 2011-07-27 Method and system for memory access among multiple operation systems on multi-core processor

Publications (2)

Publication Number Publication Date
CN102567275A CN102567275A (en) 2012-07-11
CN102567275B true CN102567275B (en) 2014-01-08

Family

ID=46412722

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201110211429.1A Expired - Fee Related CN102567275B (en) 2010-12-08 2011-07-27 Method and system for memory access among multiple operation systems on multi-core processor

Country Status (1)

Country Link
CN (1) CN102567275B (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US11853767B2 (en) 2019-10-29 2023-12-26 Guangdong Oppo Mobile Telecommunications Corp., Ltd. Inter-core data processing method, system on chip and electronic device

Families Citing this family (20)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104102549B (en) * 2013-04-01 2017-12-15 华为技术有限公司 A kind of method, apparatus and chip for realizing multithreading mutually exclusive operation
CN104346317B (en) * 2013-07-23 2019-08-27 南京中兴软件有限责任公司 Shared resource access method and device
KR20160075669A (en) * 2013-12-23 2016-06-29 인텔 코포레이션 System-on-a-chip(soc) including hybrid processor cores
CN104346229B (en) * 2014-11-14 2018-06-05 国家电网公司 A kind of processing method for the optimization of embedded OS Inter-Process Communication
CN105900070B (en) * 2014-11-28 2019-03-08 华为技术有限公司 Access partition method and device
CN106980595B (en) * 2014-12-05 2019-08-13 三星半导体(中国)研究开发有限公司 The multiprocessor communication system and its communication means of shared physical memory
CN104572484B (en) * 2015-01-23 2017-12-12 宇龙计算机通信科技(深圳)有限公司 Memory allocation method, memory allocation device and terminal
CN106612362A (en) * 2015-10-21 2017-05-03 中兴通讯股份有限公司 Terminal, and method and device for data transmission
CN105468567B (en) * 2015-11-24 2018-02-06 无锡江南计算技术研究所 A kind of discrete memory access optimization method of isomery many-core
CN106407131B (en) * 2016-03-30 2019-06-11 沈阳泰科易科技有限公司 Memory pool access method and device
CN107844713A (en) * 2016-09-18 2018-03-27 展讯通信(上海)有限公司 A kind of electronic equipment for running credible performing environment
CN106685981B (en) * 2017-01-13 2021-03-23 北京元心科技有限公司 Multi-system data encryption transmission method and device
CN107193759A (en) * 2017-04-18 2017-09-22 上海交通大学 The virtual method of device memory administrative unit
US10521273B2 (en) * 2017-06-08 2019-12-31 Cisco Technology, Inc. Physical partitioning of computing resources for server virtualization
CN108280020B (en) * 2018-01-23 2021-09-14 广州视源电子科技股份有限公司 Monitoring method and device of computer equipment, terminal and computer storage medium
TWI650648B (en) * 2018-02-09 2019-02-11 慧榮科技股份有限公司 System wafer and method for accessing memory in system wafer
CN109542830B (en) * 2018-11-21 2022-03-01 北京灵汐科技有限公司 Data processing system and data processing method
CN111259408B (en) * 2018-12-03 2023-05-30 斑马智行网络(香港)有限公司 Application authority management and checking method, device, equipment and storage medium
CN110471705A (en) * 2019-07-15 2019-11-19 江苏泛腾电子科技有限公司 A kind of customization dual system
CN111062054A (en) * 2019-12-13 2020-04-24 重庆擎华信息科技有限公司 Data processing method, device and system

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101403979A (en) * 2008-10-27 2009-04-08 成都市华为赛门铁克科技有限公司 Locking method for self-spinning lock and computer system
CN101477511A (en) * 2008-12-31 2009-07-08 杭州华三通信技术有限公司 Method and apparatus for sharing memory medium between multiple operating systems
CN101847105A (en) * 2009-03-26 2010-09-29 联想(北京)有限公司 Computer and internal memory sharing method of a plurality of operation systems

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2009091829A1 (en) * 2008-01-14 2009-07-23 Bivio Networks, Inc. Systems and methods for asymmetric multiprocessing

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101403979A (en) * 2008-10-27 2009-04-08 成都市华为赛门铁克科技有限公司 Locking method for self-spinning lock and computer system
CN101477511A (en) * 2008-12-31 2009-07-08 杭州华三通信技术有限公司 Method and apparatus for sharing memory medium between multiple operating systems
CN101847105A (en) * 2009-03-26 2010-09-29 联想(北京)有限公司 Computer and internal memory sharing method of a plurality of operation systems

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
张荫芾 等.支持多核架构的微内核操作***设计.《计算机工程》.2009,第35卷(第23期),
支持多核架构的微内核操作***设计;张荫芾 等;《计算机工程》;20091205;第35卷(第23期);全文 *

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US11853767B2 (en) 2019-10-29 2023-12-26 Guangdong Oppo Mobile Telecommunications Corp., Ltd. Inter-core data processing method, system on chip and electronic device

Also Published As

Publication number Publication date
CN102567275A (en) 2012-07-11

Similar Documents

Publication Publication Date Title
CN102567275B (en) Method and system for memory access among multiple operation systems on multi-core processor
US10574545B2 (en) Techniques for analytics-driven hybrid concurrency control in clouds
Lo'ai et al. A mobile cloud computing model using the cloudlet scheme for big data applications
CN102651775B (en) Based on method, the equipment and system of many tenants shared object management of cloud computing
US20160283282A1 (en) Optimization of map-reduce shuffle performance through shuffler i/o pipeline actions and planning
CN107949834A (en) Virtualize trusted storage device
CN104102549B (en) A kind of method, apparatus and chip for realizing multithreading mutually exclusive operation
CN105339899A (en) Method and controller for clustering applications in a software-defined network
Fei et al. FlexNFV: Flexible network service chaining with dynamic scaling
CN101521680A (en) Dual-mode wireless thin terminal device and method for utilizing external computing resources
CN104951238A (en) Method and device for managing data storage in distributed virtual environment
CN103747439B (en) Wireless controller equipment, wireless authentication processing method, system, networking
US8732346B2 (en) Coordination of direct I/O with a filter
CN111950866B (en) Role-based multi-tenant organization structure management system, method, equipment and medium
CN106537343A (en) System and method for parallel processing using dynamically configurable proactive co-processing cells
CN104166581A (en) Virtualization method for increment manufacturing device
CN111327447B (en) Distributed system, arbitration method, node device and storage medium
US20230336557A1 (en) Resource allocating and management in a computer network
CN111209263A (en) Data storage method, device, equipment and storage medium
CN103294622B (en) Digital processing device, hybrid architecture system and memory pool access method
CN110278236B (en) Enterprise business convergence communication method and device
Wen et al. A service-integrated sensor network middleware applied to industrial solutions of IoT related
Wang Mobile Information System of Ceramic Appreciation and Communication Management Based on Mobile Edge Computing
Tapas et al. IoT deployment for smarter cities with special reference to mobility
Chen et al. Design of remote industrial control system based on STM32

Legal Events

Date Code Title Description
C06 Publication
PB01 Publication
C10 Entry into substantive examination
SE01 Entry into force of request for substantive examination
C14 Grant of patent or utility model
GR01 Patent grant
CF01 Termination of patent right due to non-payment of annual fee
CF01 Termination of patent right due to non-payment of annual fee

Granted publication date: 20140108

Termination date: 20200727