blob: 9a431a7d0f5d6c61d45687d580137f04878ca4a7 [file] [log] [blame]
Bjorn Helgaas32e62c62006-05-05 17:19:50 -06001 MEMORY ATTRIBUTE ALIASING ON IA-64
2
3 Bjorn Helgaas
4 <bjorn.helgaas@hp.com>
5 May 4, 2006
6
7
8MEMORY ATTRIBUTES
9
10 Itanium supports several attributes for virtual memory references.
11 The attribute is part of the virtual translation, i.e., it is
12 contained in the TLB entry. The ones of most interest to the Linux
13 kernel are:
14
15 WB Write-back (cacheable)
16 UC Uncacheable
17 WC Write-coalescing
18
19 System memory typically uses the WB attribute. The UC attribute is
20 used for memory-mapped I/O devices. The WC attribute is uncacheable
21 like UC is, but writes may be delayed and combined to increase
22 performance for things like frame buffers.
23
24 The Itanium architecture requires that we avoid accessing the same
25 page with both a cacheable mapping and an uncacheable mapping[1].
26
27 The design of the chipset determines which attributes are supported
28 on which regions of the address space. For example, some chipsets
29 support either WB or UC access to main memory, while others support
30 only WB access.
31
32MEMORY MAP
33
34 Platform firmware describes the physical memory map and the
35 supported attributes for each region. At boot-time, the kernel uses
36 the EFI GetMemoryMap() interface. ACPI can also describe memory
37 devices and the attributes they support, but Linux/ia64 currently
38 doesn't use this information.
39
40 The kernel uses the efi_memmap table returned from GetMemoryMap() to
41 learn the attributes supported by each region of physical address
42 space. Unfortunately, this table does not completely describe the
43 address space because some machines omit some or all of the MMIO
44 regions from the map.
45
46 The kernel maintains another table, kern_memmap, which describes the
47 memory Linux is actually using and the attribute for each region.
48 This contains only system memory; it does not contain MMIO space.
49
50 The kern_memmap table typically contains only a subset of the system
51 memory described by the efi_memmap. Linux/ia64 can't use all memory
52 in the system because of constraints imposed by the identity mapping
53 scheme.
54
55 The efi_memmap table is preserved unmodified because the original
56 boot-time information is required for kexec.
57
58KERNEL IDENTITY MAPPINGS
59
60 Linux/ia64 identity mappings are done with large pages, currently
61 either 16MB or 64MB, referred to as "granules." Cacheable mappings
62 are speculative[2], so the processor can read any location in the
63 page at any time, independent of the programmer's intentions. This
64 means that to avoid attribute aliasing, Linux can create a cacheable
65 identity mapping only when the entire granule supports cacheable
66 access.
67
68 Therefore, kern_memmap contains only full granule-sized regions that
69 can referenced safely by an identity mapping.
70
71 Uncacheable mappings are not speculative, so the processor will
72 generate UC accesses only to locations explicitly referenced by
73 software. This allows UC identity mappings to cover granules that
74 are only partially populated, or populated with a combination of UC
75 and WB regions.
76
77USER MAPPINGS
78
79 User mappings are typically done with 16K or 64K pages. The smaller
80 page size allows more flexibility because only 16K or 64K has to be
81 homogeneous with respect to memory attributes.
82
83POTENTIAL ATTRIBUTE ALIASING CASES
84
85 There are several ways the kernel creates new mappings:
86
87 mmap of /dev/mem
88
89 This uses remap_pfn_range(), which creates user mappings. These
90 mappings may be either WB or UC. If the region being mapped
91 happens to be in kern_memmap, meaning that it may also be mapped
92 by a kernel identity mapping, the user mapping must use the same
93 attribute as the kernel mapping.
94
95 If the region is not in kern_memmap, the user mapping should use
96 an attribute reported as being supported in the EFI memory map.
97
98 Since the EFI memory map does not describe MMIO on some
99 machines, this should use an uncacheable mapping as a fallback.
100
101 mmap of /sys/class/pci_bus/.../legacy_mem
102
103 This is very similar to mmap of /dev/mem, except that legacy_mem
104 only allows mmap of the one megabyte "legacy MMIO" area for a
105 specific PCI bus. Typically this is the first megabyte of
106 physical address space, but it may be different on machines with
107 several VGA devices.
108
109 "X" uses this to access VGA frame buffers. Using legacy_mem
110 rather than /dev/mem allows multiple instances of X to talk to
111 different VGA cards.
112
113 The /dev/mem mmap constraints apply.
114
Bjorn Helgaas32e62c62006-05-05 17:19:50 -0600115 read/write of /dev/mem
116
117 This uses copy_from_user(), which implicitly uses a kernel
118 identity mapping. This is obviously safe for things in
119 kern_memmap.
120
121 There may be corner cases of things that are not in kern_memmap,
122 but could be accessed this way. For example, registers in MMIO
123 space are not in kern_memmap, but could be accessed with a UC
124 mapping. This would not cause attribute aliasing. But
125 registers typically can be accessed only with four-byte or
126 eight-byte accesses, and the copy_from_user() path doesn't allow
127 any control over the access size, so this would be dangerous.
128
129 ioremap()
130
Bjorn Helgaasddd83ef2007-03-30 10:39:42 -0600131 This returns a mapping for use inside the kernel.
Bjorn Helgaas32e62c62006-05-05 17:19:50 -0600132
133 If the region is in kern_memmap, we should use the attribute
Bjorn Helgaasddd83ef2007-03-30 10:39:42 -0600134 specified there.
135
136 If the EFI memory map reports that the entire granule supports
137 WB, we should use that (granules that are partially reserved
138 or occupied by firmware do not appear in kern_memmap).
139
140 If the granule contains non-WB memory, but we can cover the
141 region safely with kernel page table mappings, we can use
142 ioremap_page_range() as most other architectures do.
143
144 Failing all of the above, we have to fall back to a UC mapping.
Bjorn Helgaas32e62c62006-05-05 17:19:50 -0600145
146PAST PROBLEM CASES
147
148 mmap of various MMIO regions from /dev/mem by "X" on Intel platforms
149
150 The EFI memory map may not report these MMIO regions.
151
152 These must be allowed so that X will work. This means that
153 when the EFI memory map is incomplete, every /dev/mem mmap must
154 succeed. It may create either WB or UC user mappings, depending
155 on whether the region is in kern_memmap or the EFI memory map.
156
Bjorn Helgaasddd83ef2007-03-30 10:39:42 -0600157 mmap of 0x0-0x9FFFF /dev/mem by "hwinfo" on HP sx1000 with VGA enabled
Bjorn Helgaas32e62c62006-05-05 17:19:50 -0600158
159 See https://bugzilla.novell.com/show_bug.cgi?id=140858.
160
161 The EFI memory map reports the following attributes:
162 0x00000-0x9FFFF WB only
163 0xA0000-0xBFFFF UC only (VGA frame buffer)
164 0xC0000-0xFFFFF WB only
165
166 This mmap is done with user pages, not kernel identity mappings,
167 so it is safe to use WB mappings.
168
169 The kernel VGA driver may ioremap the VGA frame buffer at 0xA0000,
Bjorn Helgaasddd83ef2007-03-30 10:39:42 -0600170 which uses a granule-sized UC mapping. This granule will cover some
171 WB-only memory, but since UC is non-speculative, the processor will
172 never generate an uncacheable reference to the WB-only areas unless
173 the driver explicitly touches them.
Bjorn Helgaas32e62c62006-05-05 17:19:50 -0600174
175 mmap of 0x0-0xFFFFF legacy_mem by "X"
176
Bjorn Helgaasddd83ef2007-03-30 10:39:42 -0600177 If the EFI memory map reports that the entire range supports the
178 same attributes, we can allow the mmap (and we will prefer WB if
179 supported, as is the case with HP sx[12]000 machines with VGA
180 disabled).
Bjorn Helgaas32e62c62006-05-05 17:19:50 -0600181
Bjorn Helgaasddd83ef2007-03-30 10:39:42 -0600182 If EFI reports the range as partly WB and partly UC (as on sx[12]000
183 machines with VGA enabled), we must fail the mmap because there's no
184 safe attribute to use.
Bjorn Helgaas32e62c62006-05-05 17:19:50 -0600185
Bjorn Helgaasddd83ef2007-03-30 10:39:42 -0600186 If EFI reports some of the range but not all (as on Intel firmware
187 that doesn't report the VGA frame buffer at all), we should fail the
188 mmap and force the user to map just the specific region of interest.
Bjorn Helgaas32e62c62006-05-05 17:19:50 -0600189
190 mmap of 0xA0000-0xBFFFF legacy_mem by "X" on HP sx1000 with VGA disabled
191
192 The EFI memory map reports the following attributes:
193 0x00000-0xFFFFF WB only (no VGA MMIO hole)
194
195 This is a special case of the previous case, and the mmap should
196 fail for the same reason as above.
197
Bjorn Helgaasddd83ef2007-03-30 10:39:42 -0600198 read of /sys/devices/.../rom
199
200 For VGA devices, this may cause an ioremap() of 0xC0000. This
201 used to be done with a UC mapping, because the VGA frame buffer
202 at 0xA0000 prevents use of a WB granule. The UC mapping causes
203 an MCA on HP sx[12]000 chipsets.
204
205 We should use WB page table mappings to avoid covering the VGA
206 frame buffer.
207
Bjorn Helgaas32e62c62006-05-05 17:19:50 -0600208NOTES
209
210 [1] SDM rev 2.2, vol 2, sec 4.4.1.
211 [2] SDM rev 2.2, vol 2, sec 4.4.6.