/barrelfish-master/doc/002-mackerel/ |
H A D | Mackerel.tex | 1057 large buffer to fully capture. This is also potentially a large 1529 large buffer to fully capture. This is also potentially a large
|
/barrelfish-master/doc/006-routing/ |
H A D | Routing.tex | 75 \item \textbf{Memory}: Any ICD link will require some memory to buffer unsent messages and messages that have been received but not yet delivered. Some links will require additional memory for the channel itself. For instance, the shared-memory UMP driver on x86 requires two pages of physical memory per binding. In general, the amount of memory required is governed by the number of messages in flight and 76 the number of messages in buffer. 165 The virtual circuit switching approach would also allow to reserve some resources on the nodes for each channel. Per-channel reserved resources could include buffer space to save received, but not yet forwarded messages, or bandwidth on the ICD links. This is potentially very useful for congestion and flow control. Note that we cannot simply drop messages in case of congested links, as we want to provide a reliable messaging service. As of now, we do not reserve resources on the nodes, but allocate required resources dynamically. 279 It is possible that one dispatcher on a multi-hop channel is sending at a faster rate than the receiving dispatcher can handle incoming messages and process them. Because we want to provide a reliable messaging service, we cannot just drop messages in such a case, but have to buffer them and deliver them eventually. To limit the space needed to buffer undelivered messages, we decided to implement a flow control mechanism within the multi-hop interconnect driver. The flow control mechanism allows the receiving dispatcher to control the transmission speed, so that it is not overwhelmed with messages.
|
/barrelfish-master/doc/011-idc/ |
H A D | IDC.tex | 264 integers (ie. a data buffer). 594 All binding implementations can buffer exactly one outgoing message. If another 595 send function is called on the same binding while the buffer is full, the 985 a buffer that is used to store incoming messages. The dispatcher can have 999 endpoint buffer. 1003 endpoint buffer and then make the receiver dispatcher runnable (which will cause 1007 rest of the message out of the buffer and invoking appropriate user-defined 1020 receiver, where it sets up its own endpoint cap and buffer and binding struct, 1049 communication. The shared memory is split into a send buffer and a receive 1050 buffer (Figur [all...] |
/barrelfish-master/doc/013-capability-mgmt/ |
H A D | type_system.tex | 398 buffer} within that dispatcher. The endpoint buffer is specified as 413 \item Parameter 2: The endpoint buffer size to set on the capability. 432 epoffset 64 "Offset of endpoint buffer within dispatcher 434 buflen 32 "Length of endpoint buffer in words"; 841 \arg Location of buffer to hold capability representation 844 capability into the given buffer. 852 \arg Location of buffer to hold capability representation 855 dispatcher's capability into the given buffer. 892 \item \verb|KernelCmd_Setup_trace|: Set up trace buffer [all...] |
/barrelfish-master/doc/015-disk-driver-arch/ |
H A D | blockdevfs.tex | 54 \item \lstinline+read(void *handle, size_t pos, void *buffer, size_t bytes,+\\ 56 \item \lstinline+write(void *handle, size_t pos, void *buffer, size_t bytes,+\\ 93 buffer using \lstinline+ahci_dma_region_alloc+, constructing an appropriate 98 buffer to the user buffer, frees the \acs{dma} buffer, and calls the user 100 to the \acs{dma} buffer (using \lstinline+ahci_dma_region_copy_in+) and updates 102 \lstinline+rx_write_command_completed_cb+ which frees the \acs{dma} buffer and
|
H A D | design.tex | 68 libahci tries to hide the necessary bit-twiddling and \acs{dma} buffer
|
H A D | flounder-ahci.tex | 34 @ata(command=0xC8, dma_arg=buffer, dma_size=read_size, 37 out uint8 buffer[buffer_size]); 39 @ata(command=0xC8, dma_arg=buffer, dma_size=512, lba=lba) 40 rpc read_dma_block(in uint32 lba, out uint8 buffer[buffer_size]); 42 @ata(command=0xCA, dma_arg=buffer, is_write=1, lba=lba) 43 rpc write_dma(in uint8 buffer[buffer_size], in uint32 lba, 46 @ata(command=0xEC, dma_arg=buffer, dma_size=512) 47 rpc identify_device(out uint8 buffer[buffer_size]); 104 \item The size of a buffer may be extracted from its type if that is an 154 data must be copied out of the \acs{dma} region into an allocated buffer t [all...] |
H A D | libahci.tex | 30 subsystem in the form of a \acs{dma} buffer pool, which allows for \acs{dma} 31 buffer allocation and freeing. 34 buffer pool. After that, calls to \lstinline+ahci_dma_region_alloc+ and 40 Additionally the buffer pool provides helper functions that facilitate copying 41 data in and out of a buffer (\lstinline+ahci_dma_region_copy_in+ and 71 \acs{dma} buffer pool uses a doubly linked free list for maintaining the free 105 \lstinline+struct ahci_dma_region+ for the buffer that will be returned, 106 including computing the virtual and physical addresses of the buffer, and 120 successor in order to prevent excessive fragmentation of the buffer pool 128 buffer, [all...] |
H A D | related.tex | 8 This larger disk subsystem often utilizes a general buffer layer which the OS
|
H A D | running.tex | 79 first need to copy the map into a larger buffer. The memory map is then sorted
|
H A D | usage.tex | 110 to calculate some values, allocate a buffer and fill this buffer with the 129 call, pass it the binding, the buffer, the number of bytes to write, the 158 At the end, we do a simple verification and free the allocated buffer.
|
/barrelfish-master/doc/016-serial-ports/ |
H A D | Serial.tex | 130 DMA or interrupts. They should also not buffer any data in software
|
/barrelfish-master/doc/026-device-queues/ |
H A D | devif.tex | 94 For example, what happens when a guest accesses a memory buffer that is handed off 104 \item \textbf{Buffer}: A buffer is a chunk of memory within a region. 106 \item \textbf{Ownership}: An endpoint can own a buffer and transfer ownership of a buffer to another endpoint or device. 107 If an endpoint owns a buffer, it can alter it. If an endpoint alters a buffer that is not owned, 114 A buffer is a variable sized piece of memory within a previously to the \devif interface 121 queue on the stack can do an arbitrary transformation on the buffer that was enqueued 126 has to be considered. In certain cases, a write to a buffer might not have been written back 127 to memory before the buffer i [all...] |
/barrelfish-master/include/arpa/ |
H A D | nameser.h | 654 int ns_newmsg_init(u_char *buffer, size_t bufsiz, ns_newmsg *);
|
/barrelfish-master/include/bsm/ |
H A D | audit_record.h | 203 int au_close_buffer(int d, short event, u_char *buffer, size_t *buflen); 204 int au_close_token(token_t *tok, u_char *buffer, size_t *buflen);
|
/barrelfish-master/include/debug_log/ |
H A D | debug_log.h | 7 unsigned int debug_print_log_to_buffer(char *buffer, int max_size);
|
/barrelfish-master/include/lwip2/lwip/apps/ |
H A D | fs.h | 82 int fs_read_async(struct fs_file *file, char *buffer, int count, fs_wait_cb callback_fn, void *callback_arg); 84 int fs_read(struct fs_file *file, char *buffer, int count);
|
/barrelfish-master/include/lwip2/lwip/ |
H A D | def.h | 135 char* lwip_strnstr(const char* buffer, const char* token, size_t n);
|
/barrelfish-master/include/lwip2/netif/ppp/polarssl/ |
H A D | md4.c | 190 * MD4 process buffer 211 MEMCPY( (void *) (ctx->buffer + left), 213 md4_process( ctx, ctx->buffer ); 228 MEMCPY( (void *) (ctx->buffer + left), 270 * output = MD4( input buffer )
|
H A D | md4.h | 49 unsigned char buffer[64]; /*!< data block being processed */ member in struct:__anon153 65 * \brief MD4 process buffer 68 * \param input buffer holding the data 82 * \brief Output = MD4( input buffer ) 84 * \param input buffer holding the data
|
H A D | md5.c | 209 * MD5 process buffer 230 MEMCPY( (void *) (ctx->buffer + left), 232 md5_process( ctx, ctx->buffer ); 247 MEMCPY( (void *) (ctx->buffer + left), 289 * output = MD5( input buffer )
|
H A D | md5.h | 49 unsigned char buffer[64]; /*!< data block being processed */ member in struct:__anon154 65 * \brief MD5 process buffer 68 * \param input buffer holding the data 82 * \brief Output = MD5( input buffer ) 84 * \param input buffer holding the data
|
H A D | sha1.c | 243 * SHA-1 process buffer 264 MEMCPY( (void *) (ctx->buffer + left), 266 sha1_process( ctx, ctx->buffer ); 281 MEMCPY( (void *) (ctx->buffer + left), 324 * output = SHA-1( input buffer )
|
H A D | sha1.h | 49 unsigned char buffer[64]; /*!< data block being processed */ member in struct:__anon155 65 * \brief SHA-1 process buffer 68 * \param input buffer holding the data 82 * \brief Output = SHA-1( input buffer ) 84 * \param input buffer holding the data
|
/barrelfish-master/include/lwip2/netif/ppp/ |
H A D | pppcrypt.h | 127 #define lwip_arc4_crypt(context, buffer, length) mbedtls_arc4_crypt(context, length, buffer, buffer)
|