| /freebsd/share/man/man9/ |
| H A D | bus_dma.9 | 80 .Nd Bus and Machine Independent DMA Mapping Interface
163 Direct Memory Access (DMA) is a method of transferring data
165 A DMA transaction can be achieved between device to memory,
166 device to device, or memory to memory.
170 API is a bus, device, and machine-independent (MI) interface to
182 For example, if a DMA engine in a device is limited to 32-bit addresses,
190 For example, a device might require 16-byte alignment of its descriptor ring
201 The per-group tags can then inherit these restrictions from this
203 tag rather than having to list them explicitly when creating the per-group tags.
205 A mapping structure
[all …]
|
| H A D | bus_map_resource.9 | 1 .\" -*- nroff -*-
51 These functions create or destroy a mapping of a previously activated
58 .Bl -tag -width indent
67 A set of optional properties to apply when creating a mapping.
70 to request a mapping of the entire resource with the default properties.
72 The resource mapping to create or destroy.
84 members that can be used for CPU access to the mapping.
87 member which contains the virtual address of the mapping if one exists.
96 a pointer to a mapping object can be passed as the first argument to
103 .Ss Optional Mapping Properties
[all …]
|
| H A D | shm_map.9 | 32 .Nd "map shared memory objects into the kernel's address space"
45 functions provide an API for mapping shared memory objects into the kernel.
46 Shared memory objects are created by
50 A shared memory object cannot be shrunk while it is mapped into the kernel.
53 Shared memory objects can still be grown while mapped into the kernel.
64 function locates the shared memory object associated with the open file
73 will be set to the start of the mapping.
74 All pages for the range will be wired into memory upon successful return.
93 for the lifetime of the mapping.
105 The following function accepts a file descriptor for a shared memory
[all …]
|
| H A D | sf_buf.9 | 36 .Nd manage temporary kernel address space mapping for memory pages
53 space mappings for physical memory pages.
54 On systems with a direct memory map region (allowing all physical pages to be
58 direct memory map region, the
60 will manage a temporary kernel address space mapping valid for the lifetime
68 for a physical memory page.
71 memory; the caller should already have arranged for the page to be wired,
76 .Bl -tag -width SFB_CPUPRIVATE
96 to only arrange that the temporary mapping be valid on the current CPU,
123 releases only the temporary kernel address space mapping, not the page
[all …]
|
| H A D | bus_activate_resource.9 | 1 .\" -*- nroff -*-
53 the PCI bus driver enables memory decoding in a PCI device's command register
54 when activating a memory resource.
57 .Bl -tag -width indent
67 .Ss Resource Mapping
70 tag and handle will create a mapping of the entire resource when activated.
71 The tag and handle for this mapping are stored in
79 API to access device registers or memory described by
81 If the mapping is associated with a virtual address,
85 This implicit mapping can be disabled by passing the
[all …]
|
| H A D | vm_map.9 | 31 .Nd virtual address space portion of virtual memory subsystem
50 .Bd -literal -offset indent
70 .Bl -tag -width ".Va needs_wakeup"
98 .Bl -tag -width ".Dv MAP_PREFAULT_MADVISE"
115 to specify the copy-on-write properties of regions within the map:
116 .Bl -tag -width ".Dv MAP_PREFAULT_MADVISE"
118 The mapping is copy-on-write.
120 The mapping should not generate page faults.
122 The mapping should be prefaulted into physical memory.
124 The mapping should be partially prefaulted into physical memory.
[all …]
|
| /freebsd/contrib/llvm-project/compiler-rt/lib/tsan/rtl/ |
| H A D | tsan_platform.h | 1 //===-- tsan_platform.h --------
[all...] |
| /freebsd/contrib/llvm-project/compiler-rt/lib/nsan/ |
| H A D | nsan_platform.h | 1 //===------------------------ nsan_platform.h -------------------*- C++ -*-===//
5 // SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
7 //===----------------------------------------------------------------------===//
11 //===----------------------------------------------------------------------===//
18 // NSan uses two regions of memory to store information:
19 // - 'shadow memory' stores the shadow copies of numerical values stored in
20 // application memory.
21 // - 'shadow types' is used to determine which value type each byte of memory
25 // - bit 1-0: whether the corresponding value is of unknown (00),
27 // - bit 5-2: the index of this byte in the value, or 0000 if type is
[all …]
|
| /freebsd/lib/libsys/ |
| H A D | mmap.2 | 33 .Nd allocate memory, or map files or devices into memory
55 Any such extension beyond the end of the mapped object will be zero-filled.
59 references a regular file or a shared memory object, the range of
79 The virtual memory subsystem does not impose any restrictions on the
85 is non-zero, it is used as a hint to the system.
94 deletes any previous mapping in the allocated address range.
102 .Bl -tag -width PROT_WRITE -compact
131 argument specifies the type of the mapped object, mapping options and
134 Sharing, mapping type and options are specified in the
139 .Bl -tag -width MAP_PREFAULT_READ
[all …]
|
| H A D | shm_open.2 | 34 .Nd "shared memory object operations"
62 shared memory object named
85 then a new shared memory object named
89 the shared memory object is created with mode
96 flags are specified and a shared memory object named
105 If an existing shared memory object is opened with
110 then the shared memory object will be truncated to a size of zero.
130 In this case, an anonymous, unnamed shared memory object is created.
137 the shared memory object will be garbage collected when the last reference to
138 the shared memory object is removed.
[all …]
|
| /freebsd/share/doc/papers/newvm/ |
| H A D | a.t | 31 Appendix A \- Virtual Memory Interface
33 Mapping pages
36 by allowing pages to be mapped into memory. These mapped
42 /* protections are chosen from these bits, or-ed together */
49 /* flags contain mapping type, sharing type and options */
50 /* mapping type; choose one */
52 #define MAP_ANON 0x0002 /* allocated from memory, swap space */
68 The cpu-dependent size of a page is returned by the
91 A successful \fImmap\fP will delete any previous mapping
97 mapping options, and
[all …]
|
| /freebsd/share/doc/psd/05.sysman/ |
| H A D | 1.2.t | 28 .sh "Memory management\(dg
37 Each process begins execution with three logical areas of memory
39 The text area is read-only and shared, while the data and stack
57 Mapping pages
60 by allowing pages to be mapped into memory. These mapped
66 /* protections are chosen from these bits, or-ed together */
73 /* flags contain mapping type, sharing type and options */
74 /* mapping type; choose one */
76 #define MAP_ANON 0x0002 /* allocated from memory, swap space */
93 The cpu-dependent size of a page is returned by the
[all …]
|
| /freebsd/sys/contrib/device-tree/Bindings/reserved-memory/ |
| H A D | reserved-memory.yaml | 1 # SPDX-License-Identifier: (GPL-2.0 OR BSD-2-Clause)
3 ---
4 $id: http://devicetree.org/schemas/reserved-memory/reserved-memory.yaml#
5 $schema: http://devicetree.org/meta-schemas/core.yaml#
7 title: /reserved-memory Child Node Common
10 - devicetree-spec@vger.kernel.org
13 Reserved memory is specified as a node under the /reserved-memory node. The
14 operating system shall exclude reserved memory from normal usage one can
16 memory regions. Such memory regions are usually designed for the special
19 Each child of the reserved-memory node specifies one or more regions
[all …]
|
| /freebsd/sys/kern/ |
| H A D | subr_devmap.c | 1 /*-
28 /* Routines for mapping device memory. */
45 #define DEVMAP_PADDR_NOTFOUND ((vm_paddr_t)(-1))
51 * The allocated-kva (akva) devmap table and metadata. Platforms can call
68 * Print the contents of the static mapping table using the provided printf-like
82 for (pd = devmap_table; pd->pd_size != 0; ++pd) { in devmap_dump_table()
83 prfunc(" 0x%08jx - 0x%08jx mapped at VA 0x%08jx\n", in devmap_dump_table()
84 (uintmax_t)pd->pd_pa, in devmap_dump_table()
85 (uintmax_t)(pd->pd_pa + pd->pd_size - 1), in devmap_dump_table()
86 (uintmax_t)pd->pd_va); in devmap_dump_table()
[all …]
|
| /freebsd/sys/contrib/edk2/Include/Protocol/ |
| H A D | PciRootBridgeIo.h | 4 PCI Root Bridge I/O protocol is used by PCI Bus Driver to perform PCI Memory, PCI I/O,
8 Copyright (c) 2006 - 2018, Intel Corporation. All rights reserved.<BR>
9 SPDX-License-Identifier: BSD-2-Clause-Patent
53 /// A read operation from system memory by a bus master that is not capable of producing
58 /// A write operation from system memory by a bus master that is not capable of producing
63 /// Provides both read and write access to system memory by both the processor and a bus
68 /// A read operation from system memory by a bus master that is capable of producing PCI
73 /// A write operation to system memory by a bus master that is capable of producing PCI
78 /// Provides both read and write access to system memory by both the processor and a bus
124 @param Width Signifies the width of the memory or I/O operations.
[all …]
|
| H A D | DeviceIo.h | 5 memory mapped IO, IO, PCI Config space, and DMA.
7 Copyright (c) 2006 - 2018, Intel Corporation. All rights reserved.<BR>
8 SPDX-License-Identifier: BSD-2-Clause-Patent
51 Enables a driver to access device registers in the appropriate memory or I/O space.
90 Memory for the Device Path is allocated from the pool.
107 /// A read operation from system memory by a bus master.
112 /// A write operation to system memory by a bus master.
117 /// Provides both read and write access to system memory
126 Provides the device-specific addresses needed to access system memory.
129 …aram Operation Indicates if the bus master is going to read or write to system memory.
[all …]
|
| /freebsd/contrib/processor-trace/libipt/internal/include/ |
| H A D | pt_section.h | 2 * Copyright (c) 2013-2019, Intel Corporation
39 #include "intel-pt.h"
44 /* A section of contiguous memory loaded from a file. */
57 /* A pointer to OS-specific file status for detecting changes.
61 * is owned by the OS-specific mmap-based section implementation.
65 /* A pointer to implementation-specific mapping information - NULL if
68 * This field is set in pt_section_map() and owned by the mapping
71 void *mapping; member
98 /* A pointer to the unmap function - NULL if the section is currently
101 * This field is set in pt_section_map() and owned by the mapping
[all …]
|
| /freebsd/sys/contrib/xen/ |
| H A D | memory.h | 2 * memory.h
4 * Memory reservation and information.
34 * Increase or decrease the specified domain's memory reservation. Returns the
45 * devices often have a 32-bit limitation even in 64-bit systems). If zero
53 #define XENMEMF_get_node(x) ((((x) >> 8) - 1) & 0xffu)
54 /* Flag to populate physmap with populate-on-demand entries */
71 * IN: GPFN bases of extents to populate with memory
100 * An atomic exchange of memory pages. If return code is zero then
101 * @out.extent_list provides GMFNs of the newly-allocated memory.
111 * [IN] Details of memory extents to be exchanged (GMFN bases).
[all …]
|
| /freebsd/contrib/processor-trace/libipt/internal/include/posix/ |
| H A D | pt_section_posix.h | 2 * Copyright (c) 2015-2019, Intel Corporation
38 /* Fstat-based file status. */
44 /* MMAP-based section mapping information. */
49 /* The mapped memory size. */
52 /* The begin and end of the mapped memory. */
59 * On success, sets @section's mapping, unmap, and read pointers.
62 * Returns -pte_internal if @section or @file are NULL.
63 * Returns -pte_invalid if @section can't be mapped.
69 * On success, clears @section's mapping, unmap, and read pointers.
72 * Returns -pte_internal if @section is NULL.
[all …]
|
| /freebsd/contrib/llvm-project/llvm/tools/llvm-rtdyld/ |
| H A D | llvm-rtdyld.cpp | 1 //===-- llvm-rtdyld.cpp - MCJIT Testing Tool ------------------------------===//
5 // SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
7 //===----------------------------------------------------------------------===//
9 // This is a testing tool for use with the MC-JIT LLVM components.
11 //===----------------------------------------------------------------------===//
34 #include "llvm/Support/Memory.h"
72 "Like -printlineinfo but does not load the object first"),
74 "Load, link and verify the resulting memory image.")),
95 cl::desc("Target a specific cpu type (-mcpu=help for details)"),
96 cl::value_desc("cpu-name"), cl::init(""), cl::cat(RTDyldCategory));
[all …]
|
| /freebsd/share/man/man4/ |
| H A D | re.4 | 15 .\" 4. Neither the name of the author nor the names of any co-contributors
41 .Bd -ragged -offset indent
49 .Bd -literal -offset indent
67 features, and use a descriptor-based DMA mechanism.
71 The 8139C+ is a single-chip solution combining both a 10/100 MAC and PHY.
73 The 816xS, 811xS, 8168 and 8111 are single-chip devices containing both a
76 in both 32-bit PCI and 64-bit PCI models.
78 embedded LAN-on-motherboard applications.
90 .Bl -tag -width ".Cm 10baseT/UTP"
102 .Cm full-duplex
[all …]
|
| /freebsd/sys/dev/ice/ |
| H A D | ice_resmgr.c | 1 /* SPDX-License-Identifier: BSD-3-Clause */
40 * assigning them, will fill in the mapping array with a map of
41 * resource IDs to PF-space resource indices.
52 MALLOC_DEFINE(M_ICE_RESMGR, "ice-resmgr", "Intel(R) 100Gb Network Driver resmgr allocations");
59 * ice_resmgr_init - Initialize a resource manager structure
71 resmgr->resources = bit_alloc(num_res, M_ICE_RESMGR, M_NOWAIT); in ice_resmgr_init()
72 if (resmgr->resource in ice_resmgr_init()
[all...] |
| /freebsd/contrib/processor-trace/libipt/internal/include/windows/ |
| H A D | pt_section_windows.h | 2 * Copyright (c) 2015-2019, Intel Corporation
39 /* Fstat-based file status. */
45 /* FileView-based section mapping information. */
56 /* The begin and end of the mapped memory. */
65 * On success, sets @section's mapping, unmap, and read pointers.
68 * Returns -pte_internal if @section is NULL.
69 * Returns -pte_invalid if @section can't be mapped.
75 * On success, clears @section's mapping, unmap, and read pointers.
77 * This function should not be called directly; call @section->unmap() instead.
80 * Returns -pte_internal if @section is NULL.
[all …]
|
| /freebsd/sys/contrib/device-tree/Bindings/mfd/ |
| H A D | aspeed-lpc.txt | 5 The LPC bus is a means to bridge a host CPU to a number of low-bandwidth
11 The LPC controller is represented as a multi-function device to account for the
18 APB-to-LPC bridging amonst other functions.
21 as LPC firmware hub cycles, configuration of the LPC-to-AHB mapping, UART
33 [1] https://www.renesas.com/en-sg/doc/products/mpumcu/001/rej09b0078_h8s2168.pdf?key=7c888374547021…
34 …el.com/content/dam/www/public/us/en/documents/product-briefs/ipmi-second-gen-interface-spec-v2-rev…
40 - compatible: One of:
41 "aspeed,ast2400-lpc-v2", "simple-mfd", "syscon"
42 "aspeed,ast2500-lpc-v2", "simple-mfd", "syscon"
43 "aspeed,ast2600-lpc-v2", "simple-mfd", "syscon"
[all …]
|
| /freebsd/sys/contrib/device-tree/Bindings/powerpc/4xx/ |
| H A D | ppc440spe-adma.txt | 3 Device nodes needed for operation of the ppc440spe-adma driver
5 for DMA engines and Memory Queue Module node. The latter is used
6 by ADMA driver for configuration of RAID-6 H/W capabilities of
15 - compatible : "ibm,i2o-440spe";
16 - reg : <registers mapping>
17 - dcr-reg : <DCR registers range>
22 compatible = "ibm,i2o-440spe";
24 dcr-reg = <0x060 0x020>;
32 - compatible : "ibm,dma-440spe";
33 - cell-index : 1 cell, hardware index of the DMA engine
[all …]
|