摘要:
In some embodiments, a comparator compares an incoming memory address with a memory address currently being copied by a memory copy operation. A holding buffer holds the incoming address prior to forwarding it to a memory read/write queue if the incoming memory address is the same as the memory address currently being copied by the memory copy operation, forwards the buffered incoming memory address to the read/write queue once the memory copy operation for the memory address currently being copied has finished. Other embodiments are described and claimed.
摘要:
An embodiment of the present invention is a technique to perform address translation. A table structure is indexed by a source identifier of an input/output (I/O) transaction specifying a guest physical address and requested by an I/O device to map the I/O device to a domain assigned to the I/O device. An address translation structure translates the guest physical address to a host physical address corresponding to the I/O transaction.
摘要:
An embodiment of the present invention is a technique to enhance address translation performance. A register stores capability indicators to indicate capability supported by a circuit in a chipset for address translation of a guest physical address to a host physical address. A plurality of multi-level page tables is used for page walking in the address translation. Each of the page tables has page table entries. Each of the page table entries has at least an entry specifier corresponding to the capability indicated by the capability indicators.
摘要:
In some embodiments, a memory transaction is received that was sent over an unordered interconnect. A determination is made as to whether an address conflict exists between the memory transaction and another memory transaction. If the address conflict exists the memory transaction is forwarded only after waiting until the conflict is resolved. Other embodiments are described and claimed.
摘要:
In some embodiments, a comparator compares an incoming memory address with a memory address currently being copied by a memory copy operation. A holding buffer holds the incoming address prior to forwarding it to a memory read/write queue if the incoming memory address is the same as the memory address currently being copied by the memory copy operation, forwards the buffered incoming memory address to the read/write queue once the memory copy operation for the memory address currently being copied has finished. Other embodiments are described and claimed.
摘要:
A method and apparatus is described herein for supporting direct memory accesses between peer I/O devices. It is determined whether a guest physical address (GPA) referenced by an access generated from an I/O device, is within a range of GPAs associated with local I/O devices based at least in part on a GPA base and a GPA window size. If the GPA is within the window, then the GPA is translated to an HPA based at least in part on a base HPA associated with a local device and then forwarded to that local device. However, if the GPA is not within the window, then the access is forwarded upstream.
摘要:
A method and apparatus is described herein for supporting direct memory accesses between peer I/O devices. It is determined whether a guest physical address (GPA) referenced by an access generated from an I/O device, is within a range of GPAs associated with local I/O devices based at least in part on a GPA base and a GPA window size. If the GPA is within the window, then the GPA is translated to an HPA based at least in part on a base HPA associated with a local device and then forwarded to that local device. However, if the GPA is not within the window, then the access is forwarded upstream.
摘要:
An embodiment of the present invention is a technique to perform address translation. A table structure is indexed by a source identifier of an input/output (I/O) transaction specifying a guest physical address and requested by an I/O device to map the I/O device to a domain assigned to the I/O device. An address translation structure translates the guest physical address to a host physical address corresponding to the I/O transaction.
摘要:
An embodiment of the present invention is a technique to process faults in a direct memory access address translation. A register set stores global control or status information for fault processing of a fault generated by an input/output (I/O) transaction requested by an I/O device. An address translation structure translates a guest physical address to a host physical address. The guest physical address corresponds to the I/O transaction and is mapped to a domain. The address translation structure has at least an entry associated with the domain and domain-specific control information for the fault processing.
摘要:
A configuration agent may control domain partition management in a server platform. A configuration agent may allow out-of-band system management agents to directly access configuration registers which control domain partitions. Accesses by in-band agents may only be allowed, in some embodiments, during a configuration mode, such as a system management mode.