mirror of
https://github.com/torvalds/linux.git
synced 2024-12-25 12:21:37 +00:00
Merge branch 'akpm' (patches from Andrew)
Merge misc updates from Andrew Morton: - a few random little subsystems - almost all of the MM patches which are staged ahead of linux-next material. I'll trickle to post-linux-next work in as the dependents get merged up. Subsystems affected by this patch series: kthread, kbuild, ide, ntfs, ocfs2, arch, and mm (slab-generic, slab, slub, dax, debug, pagecache, gup, swap, shmem, memcg, pagemap, mremap, hmm, vmalloc, documentation, kasan, pagealloc, memory-failure, hugetlb, vmscan, z3fold, compaction, oom-kill, migration, cma, page-poison, userfaultfd, zswap, zsmalloc, uaccess, zram, and cleanups). * emailed patches from Andrew Morton <akpm@linux-foundation.org>: (200 commits) mm: cleanup kstrto*() usage mm: fix fall-through warnings for Clang mm: slub: convert sysfs sprintf family to sysfs_emit/sysfs_emit_at mm: shmem: convert shmem_enabled_show to use sysfs_emit_at mm:backing-dev: use sysfs_emit in macro defining functions mm: huge_memory: convert remaining use of sprintf to sysfs_emit and neatening mm: use sysfs_emit for struct kobject * uses mm: fix kernel-doc markups zram: break the strict dependency from lzo zram: add stat to gather incompressible pages since zram set up zram: support page writeback mm/process_vm_access: remove redundant initialization of iov_r mm/zsmalloc.c: rework the list_add code in insert_zspage() mm/zswap: move to use crypto_acomp API for hardware acceleration mm/zswap: fix passing zero to 'PTR_ERR' warning mm/zswap: make struct kernel_param_ops definitions const userfaultfd/selftests: hint the test runner on required privilege userfaultfd/selftests: fix retval check for userfaultfd_open() userfaultfd/selftests: always dump something in modes userfaultfd: selftests: make __{s,u}64 format specifiers portable ...
This commit is contained in:
commit
ac73e3dc8a
@ -266,6 +266,7 @@ line of text and contains the following stats separated by whitespace:
|
||||
No memory is allocated for such pages.
|
||||
pages_compacted the number of pages freed during compaction
|
||||
huge_pages the number of incompressible pages
|
||||
huge_pages_since the number of incompressible pages since zram set up
|
||||
================ =============================================================
|
||||
|
||||
File /sys/block/zram<id>/bd_stat
|
||||
@ -334,6 +335,11 @@ Admin can request writeback of those idle pages at right timing via::
|
||||
|
||||
With the command, zram writeback idle pages from memory to the storage.
|
||||
|
||||
If admin want to write a specific page in zram device to backing device,
|
||||
they could write a page index into the interface.
|
||||
|
||||
echo "page_index=1251" > /sys/block/zramX/writeback
|
||||
|
||||
If there are lots of write IO with flash device, potentially, it has
|
||||
flash wearout problem so that admin needs to design write limitation
|
||||
to guarantee storage health for entire product life.
|
||||
|
@ -219,13 +219,11 @@ Under below explanation, we assume CONFIG_MEM_RES_CTRL_SWAP=y.
|
||||
|
||||
This is an easy way to test page migration, too.
|
||||
|
||||
9.5 mkdir/rmdir
|
||||
---------------
|
||||
9.5 nested cgroups
|
||||
------------------
|
||||
|
||||
When using hierarchy, mkdir/rmdir test should be done.
|
||||
Use tests like the following::
|
||||
Use tests like the following for testing nested cgroups::
|
||||
|
||||
echo 1 >/opt/cgroup/01/memory/use_hierarchy
|
||||
mkdir /opt/cgroup/01/child_a
|
||||
mkdir /opt/cgroup/01/child_b
|
||||
|
||||
|
@ -77,6 +77,8 @@ Brief summary of control files.
|
||||
memory.soft_limit_in_bytes set/show soft limit of memory usage
|
||||
memory.stat show various statistics
|
||||
memory.use_hierarchy set/show hierarchical account enabled
|
||||
This knob is deprecated and shouldn't be
|
||||
used.
|
||||
memory.force_empty trigger forced page reclaim
|
||||
memory.pressure_level set memory pressure notifications
|
||||
memory.swappiness set/show swappiness parameter of vmscan
|
||||
@ -495,16 +497,13 @@ cgroup might have some charge associated with it, even though all
|
||||
tasks have migrated away from it. (because we charge against pages, not
|
||||
against tasks.)
|
||||
|
||||
We move the stats to root (if use_hierarchy==0) or parent (if
|
||||
use_hierarchy==1), and no change on the charge except uncharging
|
||||
We move the stats to parent, and no change on the charge except uncharging
|
||||
from the child.
|
||||
|
||||
Charges recorded in swap information is not updated at removal of cgroup.
|
||||
Recorded information is discarded and a cgroup which uses swap (swapcache)
|
||||
will be charged as a new owner of it.
|
||||
|
||||
About use_hierarchy, see Section 6.
|
||||
|
||||
5. Misc. interfaces
|
||||
===================
|
||||
|
||||
@ -527,8 +526,6 @@ About use_hierarchy, see Section 6.
|
||||
write will still return success. In this case, it is expected that
|
||||
memory.kmem.usage_in_bytes == memory.usage_in_bytes.
|
||||
|
||||
About use_hierarchy, see Section 6.
|
||||
|
||||
5.2 stat file
|
||||
-------------
|
||||
|
||||
@ -675,32 +672,21 @@ hierarchy::
|
||||
d e
|
||||
|
||||
In the diagram above, with hierarchical accounting enabled, all memory
|
||||
usage of e, is accounted to its ancestors up until the root (i.e, c and root),
|
||||
that has memory.use_hierarchy enabled. If one of the ancestors goes over its
|
||||
limit, the reclaim algorithm reclaims from the tasks in the ancestor and the
|
||||
children of the ancestor.
|
||||
usage of e, is accounted to its ancestors up until the root (i.e, c and root).
|
||||
If one of the ancestors goes over its limit, the reclaim algorithm reclaims
|
||||
from the tasks in the ancestor and the children of the ancestor.
|
||||
|
||||
6.1 Enabling hierarchical accounting and reclaim
|
||||
------------------------------------------------
|
||||
6.1 Hierarchical accounting and reclaim
|
||||
---------------------------------------
|
||||
|
||||
A memory cgroup by default disables the hierarchy feature. Support
|
||||
can be enabled by writing 1 to memory.use_hierarchy file of the root cgroup::
|
||||
Hierarchical accounting is enabled by default. Disabling the hierarchical
|
||||
accounting is deprecated. An attempt to do it will result in a failure
|
||||
and a warning printed to dmesg.
|
||||
|
||||
For compatibility reasons writing 1 to memory.use_hierarchy will always pass::
|
||||
|
||||
# echo 1 > memory.use_hierarchy
|
||||
|
||||
The feature can be disabled by::
|
||||
|
||||
# echo 0 > memory.use_hierarchy
|
||||
|
||||
NOTE1:
|
||||
Enabling/disabling will fail if either the cgroup already has other
|
||||
cgroups created below it, or if the parent cgroup has use_hierarchy
|
||||
enabled.
|
||||
|
||||
NOTE2:
|
||||
When panic_on_oom is set to "2", the whole system will panic in
|
||||
case of an OOM event in any cgroup.
|
||||
|
||||
7. Soft limits
|
||||
==============
|
||||
|
||||
|
@ -1274,6 +1274,9 @@ PAGE_SIZE multiple when read back.
|
||||
kernel_stack
|
||||
Amount of memory allocated to kernel stacks.
|
||||
|
||||
pagetables
|
||||
Amount of memory allocated for page tables.
|
||||
|
||||
percpu(npn)
|
||||
Amount of memory used for storing per-cpu kernel
|
||||
data structures.
|
||||
@ -1300,6 +1303,14 @@ PAGE_SIZE multiple when read back.
|
||||
Amount of memory used in anonymous mappings backed by
|
||||
transparent hugepages
|
||||
|
||||
file_thp
|
||||
Amount of cached filesystem data backed by transparent
|
||||
hugepages
|
||||
|
||||
shmem_thp
|
||||
Amount of shm, tmpfs, shared anonymous mmap()s backed by
|
||||
transparent hugepages
|
||||
|
||||
inactive_anon, active_anon, inactive_file, active_file, unevictable
|
||||
Amount of memory, swap-backed and filesystem-backed,
|
||||
on the internal memory management lists used by the
|
||||
|
@ -401,21 +401,6 @@ compact_fail
|
||||
is incremented if the system tries to compact memory
|
||||
but failed.
|
||||
|
||||
compact_pages_moved
|
||||
is incremented each time a page is moved. If
|
||||
this value is increasing rapidly, it implies that the system
|
||||
is copying a lot of data to satisfy the huge page allocation.
|
||||
It is possible that the cost of copying exceeds any savings
|
||||
from reduced TLB misses.
|
||||
|
||||
compact_pagemigrate_failed
|
||||
is incremented when the underlying mechanism
|
||||
for moving a page failed.
|
||||
|
||||
compact_blocks_moved
|
||||
is incremented each time memory compaction examines
|
||||
a huge page aligned range of pages.
|
||||
|
||||
It is possible to establish how long the stalls were using the function
|
||||
tracer to record how long was spent in __alloc_pages_nodemask and
|
||||
using the mm_page_alloc tracepoint to identify which allocations were
|
||||
|
@ -873,12 +873,17 @@ file-backed pages is less than the high watermark in a zone.
|
||||
unprivileged_userfaultfd
|
||||
========================
|
||||
|
||||
This flag controls whether unprivileged users can use the userfaultfd
|
||||
system calls. Set this to 1 to allow unprivileged users to use the
|
||||
userfaultfd system calls, or set this to 0 to restrict userfaultfd to only
|
||||
privileged users (with SYS_CAP_PTRACE capability).
|
||||
This flag controls the mode in which unprivileged users can use the
|
||||
userfaultfd system calls. Set this to 0 to restrict unprivileged users
|
||||
to handle page faults in user mode only. In this case, users without
|
||||
SYS_CAP_PTRACE must pass UFFD_USER_MODE_ONLY in order for userfaultfd to
|
||||
succeed. Prohibiting use of userfaultfd for handling faults from kernel
|
||||
mode may make certain vulnerabilities more difficult to exploit.
|
||||
|
||||
The default value is 1.
|
||||
Set this to 1 to allow unprivileged users to use the userfaultfd system
|
||||
calls without any restrictions.
|
||||
|
||||
The default value is 0.
|
||||
|
||||
|
||||
user_reserve_kbytes
|
||||
|
@ -147,6 +147,10 @@ The address of a chunk allocated with `kmalloc` is aligned to at least
|
||||
ARCH_KMALLOC_MINALIGN bytes. For sizes which are a power of two, the
|
||||
alignment is also guaranteed to be at least the respective size.
|
||||
|
||||
Chunks allocated with kmalloc() can be resized with krealloc(). Similarly
|
||||
to kmalloc_array(): a helper for resizing arrays is provided in the form of
|
||||
krealloc_array().
|
||||
|
||||
For large allocations you can use vmalloc() and vzalloc(), or directly
|
||||
request pages from the page allocator. The memory allocated by `vmalloc`
|
||||
and related functions is not physically contiguous.
|
||||
|
@ -221,12 +221,12 @@ Unit testing
|
||||
============
|
||||
This file::
|
||||
|
||||
tools/testing/selftests/vm/gup_benchmark.c
|
||||
tools/testing/selftests/vm/gup_test.c
|
||||
|
||||
has the following new calls to exercise the new pin*() wrapper functions:
|
||||
|
||||
* PIN_FAST_BENCHMARK (./gup_benchmark -a)
|
||||
* PIN_BENCHMARK (./gup_benchmark -b)
|
||||
* PIN_FAST_BENCHMARK (./gup_test -a)
|
||||
* PIN_BASIC_TEST (./gup_test -b)
|
||||
|
||||
You can monitor how many total dma-pinned pages have been acquired and released
|
||||
since the system was booted, via two new /proc/vmstat entries: ::
|
||||
|
@ -190,8 +190,9 @@ function calls GCC directly inserts the code to check the shadow memory.
|
||||
This option significantly enlarges kernel but it gives x1.1-x2 performance
|
||||
boost over outline instrumented kernel.
|
||||
|
||||
Generic KASAN prints up to 2 call_rcu() call stacks in reports, the last one
|
||||
and the second to last.
|
||||
Generic KASAN also reports the last 2 call stacks to creation of work that
|
||||
potentially has access to an object. Call stacks for the following are shown:
|
||||
call_rcu() and workqueue queuing.
|
||||
|
||||
Software tag-based KASAN
|
||||
~~~~~~~~~~~~~~~~~~~~~~~~
|
||||
|
@ -4,7 +4,7 @@
|
||||
Tmpfs
|
||||
=====
|
||||
|
||||
Tmpfs is a file system which keeps all files in virtual memory.
|
||||
Tmpfs is a file system which keeps all of its files in virtual memory.
|
||||
|
||||
|
||||
Everything in tmpfs is temporary in the sense that no files will be
|
||||
@ -35,7 +35,7 @@ tmpfs has the following uses:
|
||||
memory.
|
||||
|
||||
This mount does not depend on CONFIG_TMPFS. If CONFIG_TMPFS is not
|
||||
set, the user visible part of tmpfs is not build. But the internal
|
||||
set, the user visible part of tmpfs is not built. But the internal
|
||||
mechanisms are always present.
|
||||
|
||||
2) glibc 2.2 and above expects tmpfs to be mounted at /dev/shm for
|
||||
@ -50,7 +50,7 @@ tmpfs has the following uses:
|
||||
This mount is _not_ needed for SYSV shared memory. The internal
|
||||
mount is used for that. (In the 2.3 kernel versions it was
|
||||
necessary to mount the predecessor of tmpfs (shm fs) to use SYSV
|
||||
shared memory)
|
||||
shared memory.)
|
||||
|
||||
3) Some people (including me) find it very convenient to mount it
|
||||
e.g. on /tmp and /var/tmp and have a big swap partition. And now
|
||||
@ -83,7 +83,7 @@ If nr_blocks=0 (or size=0), blocks will not be limited in that instance;
|
||||
if nr_inodes=0, inodes will not be limited. It is generally unwise to
|
||||
mount with such options, since it allows any user with write access to
|
||||
use up all the memory on the machine; but enhances the scalability of
|
||||
that instance in a system with many cpus making intensive use of it.
|
||||
that instance in a system with many CPUs making intensive use of it.
|
||||
|
||||
|
||||
tmpfs has a mount option to set the NUMA memory allocation policy for
|
||||
|
@ -51,8 +51,7 @@ call :c:func:`free_area_init` function. Yet, the mappings array is not
|
||||
usable until the call to :c:func:`memblock_free_all` that hands all the
|
||||
memory to the page allocator.
|
||||
|
||||
If an architecture enables `CONFIG_ARCH_HAS_HOLES_MEMORYMODEL` option,
|
||||
it may free parts of the `mem_map` array that do not cover the
|
||||
An architecture may free parts of the `mem_map` array that do not cover the
|
||||
actual physical pages. In such case, the architecture specific
|
||||
:c:func:`pfn_valid` implementation should take the holes in the
|
||||
`mem_map` into account.
|
||||
|
@ -41,17 +41,17 @@ size change due to this facility.
|
||||
- Without page owner::
|
||||
|
||||
text data bss dec hex filename
|
||||
40662 1493 644 42799 a72f mm/page_alloc.o
|
||||
48392 2333 644 51369 c8a9 mm/page_alloc.o
|
||||
|
||||
- With page owner::
|
||||
|
||||
text data bss dec hex filename
|
||||
40892 1493 644 43029 a815 mm/page_alloc.o
|
||||
1427 24 8 1459 5b3 mm/page_ext.o
|
||||
2722 50 0 2772 ad4 mm/page_owner.o
|
||||
48800 2445 644 51889 cab1 mm/page_alloc.o
|
||||
6574 108 29 6711 1a37 mm/page_owner.o
|
||||
1025 8 8 1041 411 mm/page_ext.o
|
||||
|
||||
Although, roughly, 4 KB code is added in total, page_alloc.o increase by
|
||||
230 bytes and only half of it is in hotpath. Building the kernel with
|
||||
Although, roughly, 8 KB code is added in total, page_alloc.o increase by
|
||||
520 bytes and less than half of it is in hotpath. Building the kernel with
|
||||
page owner and turning it on if needed would be great option to debug
|
||||
kernel memory problem.
|
||||
|
||||
|
21
arch/Kconfig
21
arch/Kconfig
@ -261,7 +261,7 @@ config ARCH_HAS_SET_DIRECT_MAP
|
||||
|
||||
#
|
||||
# Select if the architecture provides the arch_dma_set_uncached symbol to
|
||||
# either provide an uncached segement alias for a DMA allocation, or
|
||||
# either provide an uncached segment alias for a DMA allocation, or
|
||||
# to remap the page tables in place.
|
||||
#
|
||||
config ARCH_HAS_DMA_SET_UNCACHED
|
||||
@ -314,14 +314,14 @@ config ARCH_32BIT_OFF_T
|
||||
config HAVE_ASM_MODVERSIONS
|
||||
bool
|
||||
help
|
||||
This symbol should be selected by an architecure if it provides
|
||||
This symbol should be selected by an architecture if it provides
|
||||
<asm/asm-prototypes.h> to support the module versioning for symbols
|
||||
exported from assembly code.
|
||||
|
||||
config HAVE_REGS_AND_STACK_ACCESS_API
|
||||
bool
|
||||
help
|
||||
This symbol should be selected by an architecure if it supports
|
||||
This symbol should be selected by an architecture if it supports
|
||||
the API needed to access registers and stack entries from pt_regs,
|
||||
declared in asm/ptrace.h
|
||||
For example the kprobes-based event tracer needs this API.
|
||||
@ -336,7 +336,7 @@ config HAVE_RSEQ
|
||||
config HAVE_FUNCTION_ARG_ACCESS_API
|
||||
bool
|
||||
help
|
||||
This symbol should be selected by an architecure if it supports
|
||||
This symbol should be selected by an architecture if it supports
|
||||
the API needed to access function arguments from pt_regs,
|
||||
declared in asm/ptrace.h
|
||||
|
||||
@ -665,6 +665,13 @@ config HAVE_IRQ_TIME_ACCOUNTING
|
||||
Archs need to ensure they use a high enough resolution clock to
|
||||
support irq time accounting and then call enable_sched_clock_irqtime().
|
||||
|
||||
config HAVE_MOVE_PUD
|
||||
bool
|
||||
help
|
||||
Architectures that select this are able to move page tables at the
|
||||
PUD level. If there are only 3 page table levels, the move effectively
|
||||
happens at the PGD level.
|
||||
|
||||
config HAVE_MOVE_PMD
|
||||
bool
|
||||
help
|
||||
@ -1054,6 +1061,12 @@ config ARCH_WANT_LD_ORPHAN_WARN
|
||||
by the linker, since the locations of such sections can change between linker
|
||||
versions.
|
||||
|
||||
config HAVE_ARCH_PFN_VALID
|
||||
bool
|
||||
|
||||
config ARCH_SUPPORTS_DEBUG_PAGEALLOC
|
||||
bool
|
||||
|
||||
source "kernel/gcov/Kconfig"
|
||||
|
||||
source "scripts/gcc-plugins/Kconfig"
|
||||
|
@ -40,6 +40,7 @@ config ALPHA
|
||||
select CPU_NO_EFFICIENT_FFS if !ALPHA_EV67
|
||||
select MMU_GATHER_NO_RANGE
|
||||
select SET_FS
|
||||
select SPARSEMEM_EXTREME if SPARSEMEM
|
||||
help
|
||||
The Alpha is a 64-bit general-purpose processor designed and
|
||||
marketed by the Digital Equipment Corporation of blessed memory,
|
||||
@ -551,12 +552,19 @@ config NR_CPUS
|
||||
|
||||
config ARCH_DISCONTIGMEM_ENABLE
|
||||
bool "Discontiguous Memory Support"
|
||||
depends on BROKEN
|
||||
help
|
||||
Say Y to support efficient handling of discontiguous physical memory,
|
||||
for architectures which are either NUMA (Non-Uniform Memory Access)
|
||||
or have huge holes in the physical address space for other reasons.
|
||||
See <file:Documentation/vm/numa.rst> for more.
|
||||
|
||||
config ARCH_SPARSEMEM_ENABLE
|
||||
bool "Sparse Memory Support"
|
||||
help
|
||||
Say Y to support efficient handling of discontiguous physical memory,
|
||||
for systems that have huge holes in the physical address space.
|
||||
|
||||
config NUMA
|
||||
bool "NUMA Support (EXPERIMENTAL)"
|
||||
depends on DISCONTIGMEM && BROKEN
|
||||
|
@ -6,6 +6,8 @@
|
||||
#ifndef _ASM_MMZONE_H_
|
||||
#define _ASM_MMZONE_H_
|
||||
|
||||
#ifdef CONFIG_DISCONTIGMEM
|
||||
|
||||
#include <asm/smp.h>
|
||||
|
||||
/*
|
||||
@ -45,8 +47,6 @@ PLAT_NODE_DATA_LOCALNR(unsigned long p, int n)
|
||||
}
|
||||
#endif
|
||||
|
||||
#ifdef CONFIG_DISCONTIGMEM
|
||||
|
||||
/*
|
||||
* Following are macros that each numa implementation must define.
|
||||
*/
|
||||
@ -68,11 +68,6 @@ PLAT_NODE_DATA_LOCALNR(unsigned long p, int n)
|
||||
/* XXX: FIXME -- nyc */
|
||||
#define kern_addr_valid(kaddr) (0)
|
||||
|
||||
#define virt_to_page(kaddr) pfn_to_page(__pa(kaddr) >> PAGE_SHIFT)
|
||||
|
||||
#define pmd_page(pmd) (pfn_to_page(pmd_val(pmd) >> 32))
|
||||
#define pte_pfn(pte) (pte_val(pte) >> 32)
|
||||
|
||||
#define mk_pte(page, pgprot) \
|
||||
({ \
|
||||
pte_t pte; \
|
||||
@ -95,16 +90,11 @@ PLAT_NODE_DATA_LOCALNR(unsigned long p, int n)
|
||||
__xx; \
|
||||
})
|
||||
|
||||
#define page_to_pa(page) \
|
||||
(page_to_pfn(page) << PAGE_SHIFT)
|
||||
|
||||
#define pfn_to_nid(pfn) pa_to_nid(((u64)(pfn) << PAGE_SHIFT))
|
||||
#define pfn_valid(pfn) \
|
||||
(((pfn) - node_start_pfn(pfn_to_nid(pfn))) < \
|
||||
node_spanned_pages(pfn_to_nid(pfn))) \
|
||||
|
||||
#define virt_addr_valid(kaddr) pfn_valid((__pa(kaddr) >> PAGE_SHIFT))
|
||||
|
||||
#endif /* CONFIG_DISCONTIGMEM */
|
||||
|
||||
#endif /* _ASM_MMZONE_H_ */
|
||||
|
@ -83,12 +83,13 @@ typedef struct page *pgtable_t;
|
||||
|
||||
#define __pa(x) ((unsigned long) (x) - PAGE_OFFSET)
|
||||
#define __va(x) ((void *)((unsigned long) (x) + PAGE_OFFSET))
|
||||
#ifndef CONFIG_DISCONTIGMEM
|
||||
#define virt_to_page(kaddr) pfn_to_page(__pa(kaddr) >> PAGE_SHIFT)
|
||||
|
||||
#define virt_to_page(kaddr) pfn_to_page(__pa(kaddr) >> PAGE_SHIFT)
|
||||
#define virt_addr_valid(kaddr) pfn_valid((__pa(kaddr) >> PAGE_SHIFT))
|
||||
|
||||
#ifdef CONFIG_FLATMEM
|
||||
#define pfn_valid(pfn) ((pfn) < max_mapnr)
|
||||
#define virt_addr_valid(kaddr) pfn_valid(__pa(kaddr) >> PAGE_SHIFT)
|
||||
#endif /* CONFIG_DISCONTIGMEM */
|
||||
#endif /* CONFIG_FLATMEM */
|
||||
|
||||
#include <asm-generic/memory_model.h>
|
||||
#include <asm-generic/getorder.h>
|
||||
|
@ -203,10 +203,10 @@ extern unsigned long __zero_page(void);
|
||||
* Conversion functions: convert a page and protection to a page entry,
|
||||
* and a page entry and page directory to the page they refer to.
|
||||
*/
|
||||
#ifndef CONFIG_DISCONTIGMEM
|
||||
#define page_to_pa(page) (((page) - mem_map) << PAGE_SHIFT)
|
||||
|
||||
#define page_to_pa(page) (page_to_pfn(page) << PAGE_SHIFT)
|
||||
#define pte_pfn(pte) (pte_val(pte) >> 32)
|
||||
|
||||
#ifndef CONFIG_DISCONTIGMEM
|
||||
#define pte_page(pte) pfn_to_page(pte_pfn(pte))
|
||||
#define mk_pte(page, pgprot) \
|
||||
({ \
|
||||
@ -236,10 +236,8 @@ pmd_page_vaddr(pmd_t pmd)
|
||||
return ((pmd_val(pmd) & _PFN_MASK) >> (32-PAGE_SHIFT)) + PAGE_OFFSET;
|
||||
}
|
||||
|
||||
#ifndef CONFIG_DISCONTIGMEM
|
||||
#define pmd_page(pmd) (mem_map + ((pmd_val(pmd) & _PFN_MASK) >> 32))
|
||||
#define pud_page(pud) (mem_map + ((pud_val(pud) & _PFN_MASK) >> 32))
|
||||
#endif
|
||||
#define pmd_page(pmd) (pfn_to_page(pmd_val(pmd) >> 32))
|
||||
#define pud_page(pud) (pfn_to_page(pud_val(pud) >> 32))
|
||||
|
||||
extern inline unsigned long pud_page_vaddr(pud_t pgd)
|
||||
{ return PAGE_OFFSET + ((pud_val(pgd) & _PFN_MASK) >> (32-PAGE_SHIFT)); }
|
||||
|
18
arch/alpha/include/asm/sparsemem.h
Normal file
18
arch/alpha/include/asm/sparsemem.h
Normal file
@ -0,0 +1,18 @@
|
||||
/* SPDX-License-Identifier: GPL-2.0 */
|
||||
#ifndef _ASM_ALPHA_SPARSEMEM_H
|
||||
#define _ASM_ALPHA_SPARSEMEM_H
|
||||
|
||||
#ifdef CONFIG_SPARSEMEM
|
||||
|
||||
#define SECTION_SIZE_BITS 27
|
||||
|
||||
/*
|
||||
* According to "Alpha Architecture Reference Manual" physical
|
||||
* addresses are at most 48 bits.
|
||||
* https://download.majix.org/dec/alpha_arch_ref.pdf
|
||||
*/
|
||||
#define MAX_PHYSMEM_BITS 48
|
||||
|
||||
#endif /* CONFIG_SPARSEMEM */
|
||||
|
||||
#endif /* _ASM_ALPHA_SPARSEMEM_H */
|
@ -648,6 +648,7 @@ setup_arch(char **cmdline_p)
|
||||
/* Find our memory. */
|
||||
setup_memory(kernel_end);
|
||||
memblock_set_bottom_up(true);
|
||||
sparse_init();
|
||||
|
||||
/* First guess at cpu cache sizes. Do this before init_arch. */
|
||||
determine_cpu_caches(cpu->type);
|
||||
|
@ -67,6 +67,7 @@ config GENERIC_CSUM
|
||||
|
||||
config ARCH_DISCONTIGMEM_ENABLE
|
||||
def_bool n
|
||||
depends on BROKEN
|
||||
|
||||
config ARCH_FLATMEM_ENABLE
|
||||
def_bool y
|
||||
@ -506,7 +507,7 @@ config LINUX_RAM_BASE
|
||||
|
||||
config HIGHMEM
|
||||
bool "High Memory Support"
|
||||
select ARCH_DISCONTIGMEM_ENABLE
|
||||
select HAVE_ARCH_PFN_VALID
|
||||
select KMAP_LOCAL
|
||||
help
|
||||
With ARC 2G:2G address split, only upper 2G is directly addressable by
|
||||
|
@ -82,11 +82,25 @@ typedef pte_t * pgtable_t;
|
||||
*/
|
||||
#define virt_to_pfn(kaddr) (__pa(kaddr) >> PAGE_SHIFT)
|
||||
|
||||
#define ARCH_PFN_OFFSET virt_to_pfn(CONFIG_LINUX_RAM_BASE)
|
||||
/*
|
||||
* When HIGHMEM is enabled we have holes in the memory map so we need
|
||||
* pfn_valid() that takes into account the actual extents of the physical
|
||||
* memory
|
||||
*/
|
||||
#ifdef CONFIG_HIGHMEM
|
||||
|
||||
#ifdef CONFIG_FLATMEM
|
||||
extern unsigned long arch_pfn_offset;
|
||||
#define ARCH_PFN_OFFSET arch_pfn_offset
|
||||
|
||||
extern int pfn_valid(unsigned long pfn);
|
||||
#define pfn_valid pfn_valid
|
||||
|
||||
#else /* CONFIG_HIGHMEM */
|
||||
|
||||
#define ARCH_PFN_OFFSET virt_to_pfn(CONFIG_LINUX_RAM_BASE)
|
||||
#define pfn_valid(pfn) (((pfn) - ARCH_PFN_OFFSET) < max_mapnr)
|
||||
#endif
|
||||
|
||||
#endif /* CONFIG_HIGHMEM */
|
||||
|
||||
/*
|
||||
* __pa, __va, virt_to_page (ALERT: deprecated, don't use them)
|
||||
|
@ -28,6 +28,8 @@ static unsigned long low_mem_sz;
|
||||
static unsigned long min_high_pfn, max_high_pfn;
|
||||
static phys_addr_t high_mem_start;
|
||||
static phys_addr_t high_mem_sz;
|
||||
unsigned long arch_pfn_offset;
|
||||
EXPORT_SYMBOL(arch_pfn_offset);
|
||||
#endif
|
||||
|
||||
#ifdef CONFIG_DISCONTIGMEM
|
||||
@ -98,16 +100,11 @@ void __init setup_arch_memory(void)
|
||||
init_mm.brk = (unsigned long)_end;
|
||||
|
||||
/* first page of system - kernel .vector starts here */
|
||||
min_low_pfn = ARCH_PFN_OFFSET;
|
||||
min_low_pfn = virt_to_pfn(CONFIG_LINUX_RAM_BASE);
|
||||
|
||||
/* Last usable page of low mem */
|
||||
max_low_pfn = max_pfn = PFN_DOWN(low_mem_start + low_mem_sz);
|
||||
|
||||
#ifdef CONFIG_FLATMEM
|
||||
/* pfn_valid() uses this */
|
||||
max_mapnr = max_low_pfn - min_low_pfn;
|
||||
#endif
|
||||
|
||||
/*------------- bootmem allocator setup -----------------------*/
|
||||
|
||||
/*
|
||||
@ -153,7 +150,9 @@ void __init setup_arch_memory(void)
|
||||
* DISCONTIGMEM in turns requires multiple nodes. node 0 above is
|
||||
* populated with normal memory zone while node 1 only has highmem
|
||||
*/
|
||||
#ifdef CONFIG_DISCONTIGMEM
|
||||
node_set_online(1);
|
||||
#endif
|
||||
|
||||
min_high_pfn = PFN_DOWN(high_mem_start);
|
||||
max_high_pfn = PFN_DOWN(high_mem_start + high_mem_sz);
|
||||
@ -161,8 +160,15 @@ void __init setup_arch_memory(void)
|
||||
max_zone_pfn[ZONE_HIGHMEM] = min_low_pfn;
|
||||
|
||||
high_memory = (void *)(min_high_pfn << PAGE_SHIFT);
|
||||
|
||||
arch_pfn_offset = min(min_low_pfn, min_high_pfn);
|
||||
kmap_init();
|
||||
#endif
|
||||
|
||||
#else /* CONFIG_HIGHMEM */
|
||||
/* pfn_valid() uses this when FLATMEM=y and HIGHMEM=n */
|
||||
max_mapnr = max_low_pfn - min_low_pfn;
|
||||
|
||||
#endif /* CONFIG_HIGHMEM */
|
||||
|
||||
free_area_init(max_zone_pfn);
|
||||
}
|
||||
@ -190,3 +196,12 @@ void __init mem_init(void)
|
||||
highmem_init();
|
||||
mem_init_print_info(NULL);
|
||||
}
|
||||
|
||||
#ifdef CONFIG_HIGHMEM
|
||||
int pfn_valid(unsigned long pfn)
|
||||
{
|
||||
return (pfn >= min_high_pfn && pfn <= max_high_pfn) ||
|
||||
(pfn >= min_low_pfn && pfn <= max_low_pfn);
|
||||
}
|
||||
EXPORT_SYMBOL(pfn_valid);
|
||||
#endif
|
||||
|
@ -25,7 +25,7 @@ config ARM
|
||||
select ARCH_HAS_TICK_BROADCAST if GENERIC_CLOCKEVENTS_BROADCAST
|
||||
select ARCH_HAVE_CUSTOM_GPIO_H
|
||||
select ARCH_HAS_GCOV_PROFILE_ALL
|
||||
select ARCH_KEEP_MEMBLOCK if HAVE_ARCH_PFN_VALID || KEXEC
|
||||
select ARCH_KEEP_MEMBLOCK
|
||||
select ARCH_MIGHT_HAVE_PC_PARPORT
|
||||
select ARCH_NO_SG_CHAIN if !ARM_HAS_SG_CHAIN
|
||||
select ARCH_OPTIONAL_KERNEL_RWX if ARCH_HAS_STRICT_KERNEL_RWX
|
||||
@ -69,6 +69,7 @@ config ARM
|
||||
select HAVE_ARCH_JUMP_LABEL if !XIP_KERNEL && !CPU_ENDIAN_BE32 && MMU
|
||||
select HAVE_ARCH_KGDB if !CPU_ENDIAN_BE32 && MMU
|
||||
select HAVE_ARCH_MMAP_RND_BITS if MMU
|
||||
select HAVE_ARCH_PFN_VALID
|
||||
select HAVE_ARCH_SECCOMP
|
||||
select HAVE_ARCH_SECCOMP_FILTER if AEABI && !OABI_COMPAT
|
||||
select HAVE_ARCH_THREAD_STRUCT_WHITELIST
|
||||
@ -520,7 +521,6 @@ config ARCH_S3C24XX
|
||||
config ARCH_OMAP1
|
||||
bool "TI OMAP1"
|
||||
depends on MMU
|
||||
select ARCH_HAS_HOLES_MEMORYMODEL
|
||||
select ARCH_OMAP
|
||||
select CLKDEV_LOOKUP
|
||||
select CLKSRC_MMIO
|
||||
@ -1480,9 +1480,6 @@ config OABI_COMPAT
|
||||
UNPREDICTABLE (in fact it can be predicted that it won't work
|
||||
at all). If in doubt say N.
|
||||
|
||||
config ARCH_HAS_HOLES_MEMORYMODEL
|
||||
bool
|
||||
|
||||
config ARCH_SELECT_MEMORY_MODEL
|
||||
bool
|
||||
|
||||
@ -1493,9 +1490,6 @@ config ARCH_SPARSEMEM_ENABLE
|
||||
bool
|
||||
select SPARSEMEM_STATIC if SPARSEMEM
|
||||
|
||||
config HAVE_ARCH_PFN_VALID
|
||||
def_bool ARCH_HAS_HOLES_MEMORYMODEL || !SPARSEMEM
|
||||
|
||||
config HIGHMEM
|
||||
bool "High Memory Support"
|
||||
depends on MMU
|
||||
|
@ -50,15 +50,6 @@ static const struct vm_special_mapping vdso_data_mapping = {
|
||||
static int vdso_mremap(const struct vm_special_mapping *sm,
|
||||
struct vm_area_struct *new_vma)
|
||||
{
|
||||
unsigned long new_size = new_vma->vm_end - new_vma->vm_start;
|
||||
unsigned long vdso_size;
|
||||
|
||||
/* without VVAR page */
|
||||
vdso_size = (vdso_total_pages - 1) << PAGE_SHIFT;
|
||||
|
||||
if (vdso_size != new_size)
|
||||
return -EINVAL;
|
||||
|
||||
current->mm->context.vdso = new_vma->vm_start;
|
||||
|
||||
return 0;
|
||||
|
@ -211,7 +211,6 @@ config ARCH_BRCMSTB
|
||||
select BCM7038_L1_IRQ
|
||||
select BRCMSTB_L2_IRQ
|
||||
select BCM7120_L2_IRQ
|
||||
select ARCH_HAS_HOLES_MEMORYMODEL
|
||||
select ZONE_DMA if ARM_LPAE
|
||||
select SOC_BRCMSTB
|
||||
select SOC_BUS
|
||||
|
@ -5,7 +5,6 @@ menuconfig ARCH_DAVINCI
|
||||
depends on ARCH_MULTI_V5
|
||||
select DAVINCI_TIMER
|
||||
select ZONE_DMA
|
||||
select ARCH_HAS_HOLES_MEMORYMODEL
|
||||
select PM_GENERIC_DOMAINS if PM
|
||||
select PM_GENERIC_DOMAINS_OF if PM && OF
|
||||
select REGMAP_MMIO
|
||||
|
@ -8,7 +8,6 @@
|
||||
menuconfig ARCH_EXYNOS
|
||||
bool "Samsung Exynos"
|
||||
depends on ARCH_MULTI_V7
|
||||
select ARCH_HAS_HOLES_MEMORYMODEL
|
||||
select ARCH_SUPPORTS_BIG_ENDIAN
|
||||
select ARM_AMBA
|
||||
select ARM_GIC
|
||||
|
@ -2,7 +2,6 @@
|
||||
config ARCH_HIGHBANK
|
||||
bool "Calxeda ECX-1000/2000 (Highbank/Midway)"
|
||||
depends on ARCH_MULTI_V7
|
||||
select ARCH_HAS_HOLES_MEMORYMODEL
|
||||
select ARCH_SUPPORTS_BIG_ENDIAN
|
||||
select ARM_AMBA
|
||||
select ARM_ERRATA_764369 if SMP
|
||||
|
@ -93,7 +93,6 @@ config SOC_DRA7XX
|
||||
config ARCH_OMAP2PLUS
|
||||
bool
|
||||
select ARCH_HAS_BANDGAP
|
||||
select ARCH_HAS_HOLES_MEMORYMODEL
|
||||
select ARCH_HAS_RESET_CONTROLLER
|
||||
select ARCH_OMAP
|
||||
select CLKSRC_MMIO
|
||||
|
@ -8,7 +8,6 @@
|
||||
config ARCH_S5PV210
|
||||
bool "Samsung S5PV210/S5PC110"
|
||||
depends on ARCH_MULTI_V7
|
||||
select ARCH_HAS_HOLES_MEMORYMODEL
|
||||
select ARM_VIC
|
||||
select CLKSRC_SAMSUNG_PWM
|
||||
select COMMON_CLK_SAMSUNG
|
||||
|
@ -3,7 +3,6 @@ config ARCH_TANGO
|
||||
bool "Sigma Designs Tango4 (SMP87xx)"
|
||||
depends on ARCH_MULTI_V7
|
||||
# Cortex-A9 MPCore r3p0, PL310 r3p2
|
||||
select ARCH_HAS_HOLES_MEMORYMODEL
|
||||
select ARM_ERRATA_754322
|
||||
select ARM_ERRATA_764369 if SMP
|
||||
select ARM_ERRATA_775420
|
||||
|
@ -267,83 +267,6 @@ static inline void poison_init_mem(void *s, size_t count)
|
||||
*p++ = 0xe7fddef0;
|
||||
}
|
||||
|
||||
static inline void __init
|
||||
free_memmap(unsigned long start_pfn, unsigned long end_pfn)
|
||||
{
|
||||
struct page *start_pg, *end_pg;
|
||||
phys_addr_t pg, pgend;
|
||||
|
||||
/*
|
||||
* Convert start_pfn/end_pfn to a struct page pointer.
|
||||
*/
|
||||
start_pg = pfn_to_page(start_pfn - 1) + 1;
|
||||
end_pg = pfn_to_page(end_pfn - 1) + 1;
|
||||
|
||||
/*
|
||||
* Convert to physical addresses, and
|
||||
* round start upwards and end downwards.
|
||||
*/
|
||||
pg = PAGE_ALIGN(__pa(start_pg));
|
||||
pgend = __pa(end_pg) & PAGE_MASK;
|
||||
|
||||
/*
|
||||
* If there are free pages between these,
|
||||
* free the section of the memmap array.
|
||||
*/
|
||||
if (pg < pgend)
|
||||
memblock_free_early(pg, pgend - pg);
|
||||
}
|
||||
|
||||
/*
|
||||
* The mem_map array can get very big. Free the unused area of the memory map.
|
||||
*/
|
||||
static void __init free_unused_memmap(void)
|
||||
{
|
||||
unsigned long start, end, prev_end = 0;
|
||||
int i;
|
||||
|
||||
/*
|
||||
* This relies on each bank being in address order.
|
||||
* The banks are sorted previously in bootmem_init().
|
||||
*/
|
||||
for_each_mem_pfn_range(i, MAX_NUMNODES, &start, &end, NULL) {
|
||||
#ifdef CONFIG_SPARSEMEM
|
||||
/*
|
||||
* Take care not to free memmap entries that don't exist
|
||||
* due to SPARSEMEM sections which aren't present.
|
||||
*/
|
||||
start = min(start,
|
||||
ALIGN(prev_end, PAGES_PER_SECTION));
|
||||
#else
|
||||
/*
|
||||
* Align down here since the VM subsystem insists that the
|
||||
* memmap entries are valid from the bank start aligned to
|
||||
* MAX_ORDER_NR_PAGES.
|
||||
*/
|
||||
start = round_down(start, MAX_ORDER_NR_PAGES);
|
||||
#endif
|
||||
/*
|
||||
* If we had a previous bank, and there is a space
|
||||
* between the current bank and the previous, free it.
|
||||
*/
|
||||
if (prev_end && prev_end < start)
|
||||
free_memmap(prev_end, start);
|
||||
|
||||
/*
|
||||
* Align up here since the VM subsystem insists that the
|
||||
* memmap entries are valid from the bank end aligned to
|
||||
* MAX_ORDER_NR_PAGES.
|
||||
*/
|
||||
prev_end = ALIGN(end, MAX_ORDER_NR_PAGES);
|
||||
}
|
||||
|
||||
#ifdef CONFIG_SPARSEMEM
|
||||
if (!IS_ALIGNED(prev_end, PAGES_PER_SECTION))
|
||||
free_memmap(prev_end,
|
||||
ALIGN(prev_end, PAGES_PER_SECTION));
|
||||
#endif
|
||||
}
|
||||
|
||||
static void __init free_highpages(void)
|
||||
{
|
||||
#ifdef CONFIG_HIGHMEM
|
||||
@ -385,7 +308,6 @@ void __init mem_init(void)
|
||||
set_max_mapnr(pfn_to_page(max_pfn) - mem_map);
|
||||
|
||||
/* this will put all unused low memory onto the freelists */
|
||||
free_unused_memmap();
|
||||
memblock_free_all();
|
||||
|
||||
#ifdef CONFIG_SA1111
|
||||
|
@ -71,6 +71,7 @@ config ARM64
|
||||
select ARCH_USE_QUEUED_RWLOCKS
|
||||
select ARCH_USE_QUEUED_SPINLOCKS
|
||||
select ARCH_USE_SYM_ANNOTATIONS
|
||||
select ARCH_SUPPORTS_DEBUG_PAGEALLOC
|
||||
select ARCH_SUPPORTS_MEMORY_FAILURE
|
||||
select ARCH_SUPPORTS_SHADOW_CALL_STACK if CC_HAVE_SHADOW_CALL_STACK
|
||||
select ARCH_SUPPORTS_ATOMIC_RMW
|
||||
@ -125,6 +126,7 @@ config ARM64
|
||||
select HANDLE_DOMAIN_IRQ
|
||||
select HARDIRQS_SW_RESEND
|
||||
select HAVE_MOVE_PMD
|
||||
select HAVE_MOVE_PUD
|
||||
select HAVE_PCI
|
||||
select HAVE_ACPI_APEI if (ACPI && EFI)
|
||||
select HAVE_ALIGNED_STRUCT_PAGE if SLUB
|
||||
@ -139,6 +141,7 @@ config ARM64
|
||||
select HAVE_ARCH_KGDB
|
||||
select HAVE_ARCH_MMAP_RND_BITS
|
||||
select HAVE_ARCH_MMAP_RND_COMPAT_BITS if COMPAT
|
||||
select HAVE_ARCH_PFN_VALID
|
||||
select HAVE_ARCH_PREL32_RELOCATIONS
|
||||
select HAVE_ARCH_SECCOMP_FILTER
|
||||
select HAVE_ARCH_STACKLEAK
|
||||
@ -1027,9 +1030,6 @@ config HOLES_IN_ZONE
|
||||
|
||||
source "kernel/Kconfig.hz"
|
||||
|
||||
config ARCH_SUPPORTS_DEBUG_PAGEALLOC
|
||||
def_bool y
|
||||
|
||||
config ARCH_SPARSEMEM_ENABLE
|
||||
def_bool y
|
||||
select SPARSEMEM_VMEMMAP_ENABLE
|
||||
@ -1043,9 +1043,6 @@ config ARCH_SELECT_MEMORY_MODEL
|
||||
config ARCH_FLATMEM_ENABLE
|
||||
def_bool !NUMA
|
||||
|
||||
config HAVE_ARCH_PFN_VALID
|
||||
def_bool y
|
||||
|
||||
config HW_PERF_EVENTS
|
||||
def_bool y
|
||||
depends on ARM_PMU
|
||||
|
@ -140,6 +140,7 @@ int set_memory_valid(unsigned long addr, int numpages, int enable);
|
||||
|
||||
int set_direct_map_invalid_noflush(struct page *page);
|
||||
int set_direct_map_default_noflush(struct page *page);
|
||||
bool kernel_page_present(struct page *page);
|
||||
|
||||
#include <asm-generic/cacheflush.h>
|
||||
|
||||
|
@ -463,6 +463,7 @@ static inline pmd_t pmd_mkdevmap(pmd_t pmd)
|
||||
#define pfn_pud(pfn,prot) __pud(__phys_to_pud_val((phys_addr_t)(pfn) << PAGE_SHIFT) | pgprot_val(prot))
|
||||
|
||||
#define set_pmd_at(mm, addr, pmdp, pmd) set_pte_at(mm, addr, (pte_t *)pmdp, pmd_pte(pmd))
|
||||
#define set_pud_at(mm, addr, pudp, pud) set_pte_at(mm, addr, (pte_t *)pudp, pud_pte(pud))
|
||||
|
||||
#define __p4d_to_phys(p4d) __pte_to_phys(p4d_pte(p4d))
|
||||
#define __phys_to_p4d_val(phys) __phys_to_pte_val(phys)
|
||||
|
@ -78,17 +78,9 @@ static union {
|
||||
} vdso_data_store __page_aligned_data;
|
||||
struct vdso_data *vdso_data = vdso_data_store.data;
|
||||
|
||||
static int __vdso_remap(enum vdso_abi abi,
|
||||
const struct vm_special_mapping *sm,
|
||||
static int vdso_mremap(const struct vm_special_mapping *sm,
|
||||
struct vm_area_struct *new_vma)
|
||||
{
|
||||
unsigned long new_size = new_vma->vm_end - new_vma->vm_start;
|
||||
unsigned long vdso_size = vdso_info[abi].vdso_code_end -
|
||||
vdso_info[abi].vdso_code_start;
|
||||
|
||||
if (vdso_size != new_size)
|
||||
return -EINVAL;
|
||||
|
||||
current->mm->context.vdso = (void *)new_vma->vm_start;
|
||||
|
||||
return 0;
|
||||
@ -219,17 +211,6 @@ static vm_fault_t vvar_fault(const struct vm_special_mapping *sm,
|
||||
return vmf_insert_pfn(vma, vmf->address, pfn);
|
||||
}
|
||||
|
||||
static int vvar_mremap(const struct vm_special_mapping *sm,
|
||||
struct vm_area_struct *new_vma)
|
||||
{
|
||||
unsigned long new_size = new_vma->vm_end - new_vma->vm_start;
|
||||
|
||||
if (new_size != VVAR_NR_PAGES * PAGE_SIZE)
|
||||
return -EINVAL;
|
||||
|
||||
return 0;
|
||||
}
|
||||
|
||||
static int __setup_additional_pages(enum vdso_abi abi,
|
||||
struct mm_struct *mm,
|
||||
struct linux_binprm *bprm,
|
||||
@ -280,12 +261,6 @@ up_fail:
|
||||
/*
|
||||
* Create and map the vectors page for AArch32 tasks.
|
||||
*/
|
||||
static int aarch32_vdso_mremap(const struct vm_special_mapping *sm,
|
||||
struct vm_area_struct *new_vma)
|
||||
{
|
||||
return __vdso_remap(VDSO_ABI_AA32, sm, new_vma);
|
||||
}
|
||||
|
||||
enum aarch32_map {
|
||||
AA32_MAP_VECTORS, /* kuser helpers */
|
||||
AA32_MAP_SIGPAGE,
|
||||
@ -308,11 +283,10 @@ static struct vm_special_mapping aarch32_vdso_maps[] = {
|
||||
[AA32_MAP_VVAR] = {
|
||||
.name = "[vvar]",
|
||||
.fault = vvar_fault,
|
||||
.mremap = vvar_mremap,
|
||||
},
|
||||
[AA32_MAP_VDSO] = {
|
||||
.name = "[vdso]",
|
||||
.mremap = aarch32_vdso_mremap,
|
||||
.mremap = vdso_mremap,
|
||||
},
|
||||
};
|
||||
|
||||
@ -453,12 +427,6 @@ out:
|
||||
}
|
||||
#endif /* CONFIG_COMPAT */
|
||||
|
||||
static int vdso_mremap(const struct vm_special_mapping *sm,
|
||||
struct vm_area_struct *new_vma)
|
||||
{
|
||||
return __vdso_remap(VDSO_ABI_AA64, sm, new_vma);
|
||||
}
|
||||
|
||||
enum aarch64_map {
|
||||
AA64_MAP_VVAR,
|
||||
AA64_MAP_VDSO,
|
||||
@ -468,7 +436,6 @@ static struct vm_special_mapping aarch64_vdso_maps[] __ro_after_init = {
|
||||
[AA64_MAP_VVAR] = {
|
||||
.name = "[vvar]",
|
||||
.fault = vvar_fault,
|
||||
.mremap = vvar_mremap,
|
||||
},
|
||||
[AA64_MAP_VDSO] = {
|
||||
.name = "[vdso]",
|
||||
|
@ -444,71 +444,6 @@ void __init bootmem_init(void)
|
||||
memblock_dump_all();
|
||||
}
|
||||
|
||||
#ifndef CONFIG_SPARSEMEM_VMEMMAP
|
||||
static inline void free_memmap(unsigned long start_pfn, unsigned long end_pfn)
|
||||
{
|
||||
struct page *start_pg, *end_pg;
|
||||
unsigned long pg, pgend;
|
||||
|
||||
/*
|
||||
* Convert start_pfn/end_pfn to a struct page pointer.
|
||||
*/
|
||||
start_pg = pfn_to_page(start_pfn - 1) + 1;
|
||||
end_pg = pfn_to_page(end_pfn - 1) + 1;
|
||||
|
||||
/*
|
||||
* Convert to physical addresses, and round start upwards and end
|
||||
* downwards.
|
||||
*/
|
||||
pg = (unsigned long)PAGE_ALIGN(__pa(start_pg));
|
||||
pgend = (unsigned long)__pa(end_pg) & PAGE_MASK;
|
||||
|
||||
/*
|
||||
* If there are free pages between these, free the section of the
|
||||
* memmap array.
|
||||
*/
|
||||
if (pg < pgend)
|
||||
memblock_free(pg, pgend - pg);
|
||||
}
|
||||
|
||||
/*
|
||||
* The mem_map array can get very big. Free the unused area of the memory map.
|
||||
*/
|
||||
static void __init free_unused_memmap(void)
|
||||
{
|
||||
unsigned long start, end, prev_end = 0;
|
||||
int i;
|
||||
|
||||
for_each_mem_pfn_range(i, MAX_NUMNODES, &start, &end, NULL) {
|
||||
#ifdef CONFIG_SPARSEMEM
|
||||
/*
|
||||
* Take care not to free memmap entries that don't exist due
|
||||
* to SPARSEMEM sections which aren't present.
|
||||
*/
|
||||
start = min(start, ALIGN(prev_end, PAGES_PER_SECTION));
|
||||
#endif
|
||||
/*
|
||||
* If we had a previous bank, and there is a space between the
|
||||
* current bank and the previous, free it.
|
||||
*/
|
||||
if (prev_end && prev_end < start)
|
||||
free_memmap(prev_end, start);
|
||||
|
||||
/*
|
||||
* Align up here since the VM subsystem insists that the
|
||||
* memmap entries are valid from the bank end aligned to
|
||||
* MAX_ORDER_NR_PAGES.
|
||||
*/
|
||||
prev_end = ALIGN(end, MAX_ORDER_NR_PAGES);
|
||||
}
|
||||
|
||||
#ifdef CONFIG_SPARSEMEM
|
||||
if (!IS_ALIGNED(prev_end, PAGES_PER_SECTION))
|
||||
free_memmap(prev_end, ALIGN(prev_end, PAGES_PER_SECTION));
|
||||
#endif
|
||||
}
|
||||
#endif /* !CONFIG_SPARSEMEM_VMEMMAP */
|
||||
|
||||
/*
|
||||
* mem_init() marks the free areas in the mem_map and tells us how much memory
|
||||
* is free. This is done after various parts of the system have claimed their
|
||||
@ -524,9 +459,6 @@ void __init mem_init(void)
|
||||
|
||||
set_max_mapnr(max_pfn - PHYS_PFN_OFFSET);
|
||||
|
||||
#ifndef CONFIG_SPARSEMEM_VMEMMAP
|
||||
free_unused_memmap();
|
||||
#endif
|
||||
/* this will put all unused low memory onto the freelists */
|
||||
memblock_free_all();
|
||||
|
||||
|
@ -155,7 +155,7 @@ int set_direct_map_invalid_noflush(struct page *page)
|
||||
.clear_mask = __pgprot(PTE_VALID),
|
||||
};
|
||||
|
||||
if (!rodata_full)
|
||||
if (!debug_pagealloc_enabled() && !rodata_full)
|
||||
return 0;
|
||||
|
||||
return apply_to_page_range(&init_mm,
|
||||
@ -170,7 +170,7 @@ int set_direct_map_default_noflush(struct page *page)
|
||||
.clear_mask = __pgprot(PTE_RDONLY),
|
||||
};
|
||||
|
||||
if (!rodata_full)
|
||||
if (!debug_pagealloc_enabled() && !rodata_full)
|
||||
return 0;
|
||||
|
||||
return apply_to_page_range(&init_mm,
|
||||
@ -178,6 +178,7 @@ int set_direct_map_default_noflush(struct page *page)
|
||||
PAGE_SIZE, change_page_range, &data);
|
||||
}
|
||||
|
||||
#ifdef CONFIG_DEBUG_PAGEALLOC
|
||||
void __kernel_map_pages(struct page *page, int numpages, int enable)
|
||||
{
|
||||
if (!debug_pagealloc_enabled() && !rodata_full)
|
||||
@ -185,6 +186,7 @@ void __kernel_map_pages(struct page *page, int numpages, int enable)
|
||||
|
||||
set_memory_valid((unsigned long)page_address(page), numpages, enable);
|
||||
}
|
||||
#endif /* CONFIG_DEBUG_PAGEALLOC */
|
||||
|
||||
/*
|
||||
* This function is used to determine if a linear map page has been marked as
|
||||
|
@ -288,6 +288,7 @@ config ARCH_SELECT_MEMORY_MODEL
|
||||
|
||||
config ARCH_DISCONTIGMEM_ENABLE
|
||||
def_bool y
|
||||
depends on BROKEN
|
||||
help
|
||||
Say Y to support efficient handling of discontiguous physical memory,
|
||||
for architectures which are either NUMA (Non-Uniform Memory Access)
|
||||
@ -299,12 +300,11 @@ config ARCH_FLATMEM_ENABLE
|
||||
|
||||
config ARCH_SPARSEMEM_ENABLE
|
||||
def_bool y
|
||||
depends on ARCH_DISCONTIGMEM_ENABLE
|
||||
select SPARSEMEM_VMEMMAP_ENABLE
|
||||
|
||||
config ARCH_DISCONTIGMEM_DEFAULT
|
||||
config ARCH_SPARSEMEM_DEFAULT
|
||||
def_bool y
|
||||
depends on ARCH_DISCONTIGMEM_ENABLE
|
||||
depends on ARCH_SPARSEMEM_ENABLE
|
||||
|
||||
config NUMA
|
||||
bool "NUMA support"
|
||||
@ -329,7 +329,7 @@ config NODES_SHIFT
|
||||
# VIRTUAL_MEM_MAP has been retained for historical reasons.
|
||||
config VIRTUAL_MEM_MAP
|
||||
bool "Virtual mem map"
|
||||
depends on !SPARSEMEM
|
||||
depends on !SPARSEMEM && !FLATMEM
|
||||
default y
|
||||
help
|
||||
Say Y to compile the kernel with support for a virtual mem map.
|
||||
@ -342,9 +342,6 @@ config HOLES_IN_ZONE
|
||||
bool
|
||||
default y if VIRTUAL_MEM_MAP
|
||||
|
||||
config HAVE_ARCH_EARLY_PFN_TO_NID
|
||||
def_bool NUMA && SPARSEMEM
|
||||
|
||||
config HAVE_ARCH_NODEDATA_EXTENSION
|
||||
def_bool y
|
||||
depends on NUMA
|
||||
|
@ -59,10 +59,8 @@ extern int reserve_elfcorehdr(u64 *start, u64 *end);
|
||||
extern int register_active_ranges(u64 start, u64 len, int nid);
|
||||
|
||||
#ifdef CONFIG_VIRTUAL_MEM_MAP
|
||||
# define LARGE_GAP 0x40000000 /* Use virtual mem map if hole is > than this */
|
||||
extern unsigned long VMALLOC_END;
|
||||
extern struct page *vmem_map;
|
||||
extern int find_largest_hole(u64 start, u64 end, void *arg);
|
||||
extern int create_mem_map_page_table(u64 start, u64 end, void *arg);
|
||||
extern int vmemmap_find_next_valid_pfn(int, int);
|
||||
#else
|
||||
|
@ -19,15 +19,12 @@
|
||||
#include <linux/mm.h>
|
||||
#include <linux/nmi.h>
|
||||
#include <linux/swap.h>
|
||||
#include <linux/sizes.h>
|
||||
|
||||
#include <asm/meminit.h>
|
||||
#include <asm/sections.h>
|
||||
#include <asm/mca.h>
|
||||
|
||||
#ifdef CONFIG_VIRTUAL_MEM_MAP
|
||||
static unsigned long max_gap;
|
||||
#endif
|
||||
|
||||
/* physical address where the bootmem map is located */
|
||||
unsigned long bootmap_start;
|
||||
|
||||
@ -166,6 +163,32 @@ find_memory (void)
|
||||
alloc_per_cpu_data();
|
||||
}
|
||||
|
||||
static int __init find_largest_hole(u64 start, u64 end, void *arg)
|
||||
{
|
||||
u64 *max_gap = arg;
|
||||
|
||||
static u64 last_end = PAGE_OFFSET;
|
||||
|
||||
/* NOTE: this algorithm assumes efi memmap table is ordered */
|
||||
|
||||
if (*max_gap < (start - last_end))
|
||||
*max_gap = start - last_end;
|
||||
last_end = end;
|
||||
return 0;
|
||||
}
|
||||
|
||||
static void __init verify_gap_absence(void)
|
||||
{
|
||||
unsigned long max_gap;
|
||||
|
||||
/* Forbid FLATMEM if hole is > than 1G */
|
||||
efi_memmap_walk(find_largest_hole, (u64 *)&max_gap);
|
||||
if (max_gap >= SZ_1G)
|
||||
panic("Cannot use FLATMEM with %ldMB hole\n"
|
||||
"Please switch over to SPARSEMEM\n",
|
||||
(max_gap >> 20));
|
||||
}
|
||||
|
||||
/*
|
||||
* Set up the page tables.
|
||||
*/
|
||||
@ -177,37 +200,12 @@ paging_init (void)
|
||||
unsigned long max_zone_pfns[MAX_NR_ZONES];
|
||||
|
||||
memset(max_zone_pfns, 0, sizeof(max_zone_pfns));
|
||||
#ifdef CONFIG_ZONE_DMA32
|
||||
max_dma = virt_to_phys((void *) MAX_DMA_ADDRESS) >> PAGE_SHIFT;
|
||||
max_zone_pfns[ZONE_DMA32] = max_dma;
|
||||
#endif
|
||||
max_zone_pfns[ZONE_NORMAL] = max_low_pfn;
|
||||
|
||||
#ifdef CONFIG_VIRTUAL_MEM_MAP
|
||||
efi_memmap_walk(find_largest_hole, (u64 *)&max_gap);
|
||||
if (max_gap < LARGE_GAP) {
|
||||
vmem_map = (struct page *) 0;
|
||||
} else {
|
||||
unsigned long map_size;
|
||||
verify_gap_absence();
|
||||
|
||||
/* allocate virtual_mem_map */
|
||||
|
||||
map_size = PAGE_ALIGN(ALIGN(max_low_pfn, MAX_ORDER_NR_PAGES) *
|
||||
sizeof(struct page));
|
||||
VMALLOC_END -= map_size;
|
||||
vmem_map = (struct page *) VMALLOC_END;
|
||||
efi_memmap_walk(create_mem_map_page_table, NULL);
|
||||
|
||||
/*
|
||||
* alloc_node_mem_map makes an adjustment for mem_map
|
||||
* which isn't compatible with vmem_map.
|
||||
*/
|
||||
NODE_DATA(0)->node_mem_map = vmem_map +
|
||||
find_min_pfn_with_active_regions();
|
||||
|
||||
printk("Virtual mem_map starts at 0x%p\n", mem_map);
|
||||
}
|
||||
#endif /* !CONFIG_VIRTUAL_MEM_MAP */
|
||||
free_area_init(max_zone_pfns);
|
||||
zero_page_memmap_ptr = virt_to_page(ia64_imva(empty_zero_page));
|
||||
}
|
||||
|
@ -584,6 +584,25 @@ void call_pernode_memory(unsigned long start, unsigned long len, void *arg)
|
||||
}
|
||||
}
|
||||
|
||||
static void __init virtual_map_init(void)
|
||||
{
|
||||
#ifdef CONFIG_VIRTUAL_MEM_MAP
|
||||
int node;
|
||||
|
||||
VMALLOC_END -= PAGE_ALIGN(ALIGN(max_low_pfn, MAX_ORDER_NR_PAGES) *
|
||||
sizeof(struct page));
|
||||
vmem_map = (struct page *) VMALLOC_END;
|
||||
efi_memmap_walk(create_mem_map_page_table, NULL);
|
||||
printk("Virtual mem_map starts at 0x%p\n", vmem_map);
|
||||
|
||||
for_each_online_node(node) {
|
||||
unsigned long pfn_offset = mem_data[node].min_pfn;
|
||||
|
||||
NODE_DATA(node)->node_mem_map = vmem_map + pfn_offset;
|
||||
}
|
||||
#endif
|
||||
}
|
||||
|
||||
/**
|
||||
* paging_init - setup page tables
|
||||
*
|
||||
@ -593,38 +612,17 @@ void call_pernode_memory(unsigned long start, unsigned long len, void *arg)
|
||||
void __init paging_init(void)
|
||||
{
|
||||
unsigned long max_dma;
|
||||
unsigned long pfn_offset = 0;
|
||||
unsigned long max_pfn = 0;
|
||||
int node;
|
||||
unsigned long max_zone_pfns[MAX_NR_ZONES];
|
||||
|
||||
max_dma = virt_to_phys((void *) MAX_DMA_ADDRESS) >> PAGE_SHIFT;
|
||||
|
||||
sparse_init();
|
||||
|
||||
#ifdef CONFIG_VIRTUAL_MEM_MAP
|
||||
VMALLOC_END -= PAGE_ALIGN(ALIGN(max_low_pfn, MAX_ORDER_NR_PAGES) *
|
||||
sizeof(struct page));
|
||||
vmem_map = (struct page *) VMALLOC_END;
|
||||
efi_memmap_walk(create_mem_map_page_table, NULL);
|
||||
printk("Virtual mem_map starts at 0x%p\n", vmem_map);
|
||||
#endif
|
||||
|
||||
for_each_online_node(node) {
|
||||
pfn_offset = mem_data[node].min_pfn;
|
||||
|
||||
#ifdef CONFIG_VIRTUAL_MEM_MAP
|
||||
NODE_DATA(node)->node_mem_map = vmem_map + pfn_offset;
|
||||
#endif
|
||||
if (mem_data[node].max_pfn > max_pfn)
|
||||
max_pfn = mem_data[node].max_pfn;
|
||||
}
|
||||
virtual_map_init();
|
||||
|
||||
memset(max_zone_pfns, 0, sizeof(max_zone_pfns));
|
||||
#ifdef CONFIG_ZONE_DMA32
|
||||
max_zone_pfns[ZONE_DMA32] = max_dma;
|
||||
#endif
|
||||
max_zone_pfns[ZONE_NORMAL] = max_pfn;
|
||||
max_zone_pfns[ZONE_NORMAL] = max_low_pfn;
|
||||
free_area_init(max_zone_pfns);
|
||||
|
||||
zero_page_memmap_ptr = virt_to_page(ia64_imva(empty_zero_page));
|
||||
|
@ -574,20 +574,6 @@ ia64_pfn_valid (unsigned long pfn)
|
||||
}
|
||||
EXPORT_SYMBOL(ia64_pfn_valid);
|
||||
|
||||
int __init find_largest_hole(u64 start, u64 end, void *arg)
|
||||
{
|
||||
u64 *max_gap = arg;
|
||||
|
||||
static u64 last_end = PAGE_OFFSET;
|
||||
|
||||
/* NOTE: this algorithm assumes efi memmap table is ordered */
|
||||
|
||||
if (*max_gap < (start - last_end))
|
||||
*max_gap = start - last_end;
|
||||
last_end = end;
|
||||
return 0;
|
||||
}
|
||||
|
||||
#endif /* CONFIG_VIRTUAL_MEM_MAP */
|
||||
|
||||
int __init register_active_ranges(u64 start, u64 len, int nid)
|
||||
|
@ -58,36 +58,6 @@ paddr_to_nid(unsigned long paddr)
|
||||
EXPORT_SYMBOL(paddr_to_nid);
|
||||
|
||||
#if defined(CONFIG_SPARSEMEM) && defined(CONFIG_NUMA)
|
||||
/*
|
||||
* Because of holes evaluate on section limits.
|
||||
* If the section of memory exists, then return the node where the section
|
||||
* resides. Otherwise return node 0 as the default. This is used by
|
||||
* SPARSEMEM to allocate the SPARSEMEM sectionmap on the NUMA node where
|
||||
* the section resides.
|
||||
*/
|
||||
int __meminit __early_pfn_to_nid(unsigned long pfn,
|
||||
struct mminit_pfnnid_cache *state)
|
||||
{
|
||||
int i, section = pfn >> PFN_SECTION_SHIFT, ssec, esec;
|
||||
|
||||
if (section >= state->last_start && section < state->last_end)
|
||||
return state->last_nid;
|
||||
|
||||
for (i = 0; i < num_node_memblks; i++) {
|
||||
ssec = node_memblk[i].start_paddr >> PA_SECTION_SHIFT;
|
||||
esec = (node_memblk[i].start_paddr + node_memblk[i].size +
|
||||
((1L << PA_SECTION_SHIFT) - 1)) >> PA_SECTION_SHIFT;
|
||||
if (section >= ssec && section < esec) {
|
||||
state->last_start = ssec;
|
||||
state->last_end = esec;
|
||||
state->last_nid = node_memblk[i].nid;
|
||||
return node_memblk[i].nid;
|
||||
}
|
||||
}
|
||||
|
||||
return -1;
|
||||
}
|
||||
|
||||
void numa_clear_node(int cpu)
|
||||
{
|
||||
unmap_cpu_from_node(cpu, NUMA_NO_NODE);
|
||||
|
@ -20,6 +20,7 @@ choice
|
||||
|
||||
config M68KCLASSIC
|
||||
bool "Classic M68K CPU family support"
|
||||
select HAVE_ARCH_PFN_VALID
|
||||
|
||||
config COLDFIRE
|
||||
bool "Coldfire CPU family support"
|
||||
@ -373,16 +374,38 @@ config RMW_INSNS
|
||||
config SINGLE_MEMORY_CHUNK
|
||||
bool "Use one physical chunk of memory only" if ADVANCED && !SUN3
|
||||
depends on MMU
|
||||
default y if SUN3
|
||||
select NEED_MULTIPLE_NODES
|
||||
default y if SUN3 || MMU_COLDFIRE
|
||||
help
|
||||
Ignore all but the first contiguous chunk of physical memory for VM
|
||||
purposes. This will save a few bytes kernel size and may speed up
|
||||
some operations. Say N if not sure.
|
||||
some operations.
|
||||
When this option os set to N, you may want to lower "Maximum zone
|
||||
order" to save memory that could be wasted for unused memory map.
|
||||
Say N if not sure.
|
||||
|
||||
config ARCH_DISCONTIGMEM_ENABLE
|
||||
depends on BROKEN
|
||||
def_bool MMU && !SINGLE_MEMORY_CHUNK
|
||||
|
||||
config FORCE_MAX_ZONEORDER
|
||||
int "Maximum zone order" if ADVANCED
|
||||
depends on !SINGLE_MEMORY_CHUNK
|
||||
default "11"
|
||||
help
|
||||
The kernel memory allocator divides physically contiguous memory
|
||||
blocks into "zones", where each zone is a power of two number of
|
||||
pages. This option selects the largest power of two that the kernel
|
||||
keeps in the memory allocator. If you need to allocate very large
|
||||
blocks of physically contiguous memory, then you may need to
|
||||
increase this value.
|
||||
|
||||
For systems that have holes in their physical address space this
|
||||
value also defines the minimal size of the hole that allows
|
||||
freeing unused memory map.
|
||||
|
||||
This config option is actually maximum order plus one. For example,
|
||||
a value of 11 means that the largest free memory block is 2^10 pages.
|
||||
|
||||
config 060_WRITETHROUGH
|
||||
bool "Use write-through caching for 68060 supervisor accesses"
|
||||
depends on ADVANCED && M68060
|
||||
@ -406,7 +429,7 @@ config M68K_L2_CACHE
|
||||
config NODES_SHIFT
|
||||
int
|
||||
default "3"
|
||||
depends on !SINGLE_MEMORY_CHUNK
|
||||
depends on DISCONTIGMEM
|
||||
|
||||
config CPU_HAS_NO_BITFIELDS
|
||||
bool
|
||||
|
@ -62,8 +62,10 @@ extern unsigned long _ramend;
|
||||
#include <asm/page_no.h>
|
||||
#endif
|
||||
|
||||
#ifdef CONFIG_DISCONTIGMEM
|
||||
#define __phys_to_pfn(paddr) ((unsigned long)((paddr) >> PAGE_SHIFT))
|
||||
#define __pfn_to_phys(pfn) PFN_PHYS(pfn)
|
||||
#endif
|
||||
|
||||
#include <asm-generic/getorder.h>
|
||||
|
||||
|
@ -126,7 +126,7 @@ static inline void *__va(unsigned long x)
|
||||
|
||||
extern int m68k_virt_to_node_shift;
|
||||
|
||||
#ifdef CONFIG_SINGLE_MEMORY_CHUNK
|
||||
#ifndef CONFIG_DISCONTIGMEM
|
||||
#define __virt_to_node(addr) (&pg_data_map[0])
|
||||
#else
|
||||
extern struct pglist_data *pg_data_table[];
|
||||
@ -153,6 +153,7 @@ static inline __attribute_const__ int __virt_to_node_shift(void)
|
||||
pfn_to_virt(page_to_pfn(page)); \
|
||||
})
|
||||
|
||||
#ifdef CONFIG_DISCONTIGMEM
|
||||
#define pfn_to_page(pfn) ({ \
|
||||
unsigned long __pfn = (pfn); \
|
||||
struct pglist_data *pgdat; \
|
||||
@ -165,6 +166,10 @@ static inline __attribute_const__ int __virt_to_node_shift(void)
|
||||
pgdat = &pg_data_map[page_to_nid(__p)]; \
|
||||
((__p) - pgdat->node_mem_map) + pgdat->node_start_pfn; \
|
||||
})
|
||||
#else
|
||||
#define ARCH_PFN_OFFSET (m68k_memory[0].addr)
|
||||
#include <asm-generic/memory_model.h>
|
||||
#endif
|
||||
|
||||
#define virt_addr_valid(kaddr) ((void *)(kaddr) >= (void *)PAGE_OFFSET && (void *)(kaddr) < high_memory)
|
||||
#define pfn_valid(pfn) virt_addr_valid(pfn_to_virt(pfn))
|
||||
|
@ -29,12 +29,7 @@ static inline void *phys_to_virt(unsigned long address)
|
||||
}
|
||||
|
||||
/* Permanent address of a page. */
|
||||
#if defined(CONFIG_MMU) && defined(CONFIG_SINGLE_MEMORY_CHUNK)
|
||||
#define page_to_phys(page) \
|
||||
__pa(PAGE_OFFSET + (((page) - pg_data_map[0].node_mem_map) << PAGE_SHIFT))
|
||||
#else
|
||||
#define page_to_phys(page) (page_to_pfn(page) << PAGE_SHIFT)
|
||||
#endif
|
||||
|
||||
/*
|
||||
* IO bus memory addresses are 1:1 with the physical address,
|
||||
|
@ -42,19 +42,19 @@ EXPORT_SYMBOL(empty_zero_page);
|
||||
|
||||
#ifdef CONFIG_MMU
|
||||
|
||||
int m68k_virt_to_node_shift;
|
||||
|
||||
#ifdef CONFIG_DISCONTIGMEM
|
||||
pg_data_t pg_data_map[MAX_NUMNODES];
|
||||
EXPORT_SYMBOL(pg_data_map);
|
||||
|
||||
int m68k_virt_to_node_shift;
|
||||
|
||||
#ifndef CONFIG_SINGLE_MEMORY_CHUNK
|
||||
pg_data_t *pg_data_table[65];
|
||||
EXPORT_SYMBOL(pg_data_table);
|
||||
#endif
|
||||
|
||||
void __init m68k_setup_node(int node)
|
||||
{
|
||||
#ifndef CONFIG_SINGLE_MEMORY_CHUNK
|
||||
#ifdef CONFIG_DISCONTIGMEM
|
||||
struct m68k_mem_info *info = m68k_memory + node;
|
||||
int i, end;
|
||||
|
||||
|
@ -263,10 +263,6 @@ int main(int argc, char **argv)
|
||||
fprintf(out_file, " const struct vm_special_mapping *sm,\n");
|
||||
fprintf(out_file, " struct vm_area_struct *new_vma)\n");
|
||||
fprintf(out_file, "{\n");
|
||||
fprintf(out_file, " unsigned long new_size =\n");
|
||||
fprintf(out_file, " new_vma->vm_end - new_vma->vm_start;\n");
|
||||
fprintf(out_file, " if (vdso_image.size != new_size)\n");
|
||||
fprintf(out_file, " return -EINVAL;\n");
|
||||
fprintf(out_file, " current->mm->context.vdso =\n");
|
||||
fprintf(out_file, " (void *)(new_vma->vm_start);\n");
|
||||
fprintf(out_file, " return 0;\n");
|
||||
|
@ -34,7 +34,7 @@ pgd_t *pgd_alloc(struct mm_struct *mm)
|
||||
cpu_dcache_wb_range((unsigned long)new_pgd,
|
||||
(unsigned long)new_pgd +
|
||||
PTRS_PER_PGD * sizeof(pgd_t));
|
||||
inc_zone_page_state(virt_to_page((unsigned long *)new_pgd),
|
||||
inc_lruvec_page_state(virt_to_page((unsigned long *)new_pgd),
|
||||
NR_PAGETABLE);
|
||||
|
||||
return new_pgd;
|
||||
@ -59,7 +59,7 @@ void pgd_free(struct mm_struct *mm, pgd_t * pgd)
|
||||
|
||||
pte = pmd_page(*pmd);
|
||||
pmd_clear(pmd);
|
||||
dec_zone_page_state(virt_to_page((unsigned long *)pgd), NR_PAGETABLE);
|
||||
dec_lruvec_page_state(virt_to_page((unsigned long *)pgd), NR_PAGETABLE);
|
||||
pte_free(mm, pte);
|
||||
mm_dec_nr_ptes(mm);
|
||||
pmd_free(mm, pmd);
|
||||
|
@ -146,6 +146,7 @@ config PPC
|
||||
select ARCH_MIGHT_HAVE_PC_SERIO
|
||||
select ARCH_OPTIONAL_KERNEL_RWX if ARCH_HAS_STRICT_KERNEL_RWX
|
||||
select ARCH_SUPPORTS_ATOMIC_RMW
|
||||
select ARCH_SUPPORTS_DEBUG_PAGEALLOC if PPC32 || PPC_BOOK3S_64
|
||||
select ARCH_USE_BUILTIN_BSWAP
|
||||
select ARCH_USE_CMPXCHG_LOCKREF if PPC64
|
||||
select ARCH_USE_QUEUED_RWLOCKS if PPC_QUEUED_SPINLOCKS
|
||||
@ -356,10 +357,6 @@ config PPC_OF_PLATFORM_PCI
|
||||
depends on PCI
|
||||
depends on PPC64 # not supported on 32 bits yet
|
||||
|
||||
config ARCH_SUPPORTS_DEBUG_PAGEALLOC
|
||||
depends on PPC32 || PPC_BOOK3S_64
|
||||
def_bool y
|
||||
|
||||
config ARCH_SUPPORTS_UPROBES
|
||||
def_bool y
|
||||
|
||||
|
@ -14,6 +14,7 @@ config RISCV
|
||||
def_bool y
|
||||
select ARCH_CLOCKSOURCE_INIT
|
||||
select ARCH_SUPPORTS_ATOMIC_RMW
|
||||
select ARCH_SUPPORTS_DEBUG_PAGEALLOC if MMU
|
||||
select ARCH_HAS_BINFMT_FLAT
|
||||
select ARCH_HAS_DEBUG_VM_PGTABLE
|
||||
select ARCH_HAS_DEBUG_VIRTUAL if MMU
|
||||
@ -153,9 +154,6 @@ config ARCH_SELECT_MEMORY_MODEL
|
||||
config ARCH_WANT_GENERAL_HUGETLB
|
||||
def_bool y
|
||||
|
||||
config ARCH_SUPPORTS_DEBUG_PAGEALLOC
|
||||
def_bool y
|
||||
|
||||
config SYS_SUPPORTS_HUGETLBFS
|
||||
depends on MMU
|
||||
def_bool y
|
||||
|
@ -461,8 +461,6 @@ static inline int ptep_clear_flush_young(struct vm_area_struct *vma,
|
||||
#define VMALLOC_START 0
|
||||
#define VMALLOC_END TASK_SIZE
|
||||
|
||||
static inline void __kernel_map_pages(struct page *page, int numpages, int enable) {}
|
||||
|
||||
#endif /* !CONFIG_MMU */
|
||||
|
||||
#define kern_addr_valid(addr) (1) /* FIXME */
|
||||
|
@ -24,6 +24,7 @@ static inline int set_memory_nx(unsigned long addr, int numpages) { return 0; }
|
||||
|
||||
int set_direct_map_invalid_noflush(struct page *page);
|
||||
int set_direct_map_default_noflush(struct page *page);
|
||||
bool kernel_page_present(struct page *page);
|
||||
|
||||
#endif /* __ASSEMBLY__ */
|
||||
|
||||
|
@ -184,6 +184,7 @@ int set_direct_map_default_noflush(struct page *page)
|
||||
return ret;
|
||||
}
|
||||
|
||||
#ifdef CONFIG_DEBUG_PAGEALLOC
|
||||
void __kernel_map_pages(struct page *page, int numpages, int enable)
|
||||
{
|
||||
if (!debug_pagealloc_enabled())
|
||||
@ -196,3 +197,33 @@ void __kernel_map_pages(struct page *page, int numpages, int enable)
|
||||
__set_memory((unsigned long)page_address(page), numpages,
|
||||
__pgprot(0), __pgprot(_PAGE_PRESENT));
|
||||
}
|
||||
#endif
|
||||
|
||||
bool kernel_page_present(struct page *page)
|
||||
{
|
||||
unsigned long addr = (unsigned long)page_address(page);
|
||||
pgd_t *pgd;
|
||||
pud_t *pud;
|
||||
p4d_t *p4d;
|
||||
pmd_t *pmd;
|
||||
pte_t *pte;
|
||||
|
||||
pgd = pgd_offset_k(addr);
|
||||
if (!pgd_present(*pgd))
|
||||
return false;
|
||||
|
||||
p4d = p4d_offset(pgd, addr);
|
||||
if (!p4d_present(*p4d))
|
||||
return false;
|
||||
|
||||
pud = pud_offset(p4d, addr);
|
||||
if (!pud_present(*pud))
|
||||
return false;
|
||||
|
||||
pmd = pmd_offset(pud, addr);
|
||||
if (!pmd_present(*pmd))
|
||||
return false;
|
||||
|
||||
pte = pte_offset_kernel(pmd, addr);
|
||||
return pte_present(*pte);
|
||||
}
|
||||
|
@ -35,9 +35,6 @@ config GENERIC_LOCKBREAK
|
||||
config PGSTE
|
||||
def_bool y if KVM
|
||||
|
||||
config ARCH_SUPPORTS_DEBUG_PAGEALLOC
|
||||
def_bool y
|
||||
|
||||
config AUDIT_ARCH
|
||||
def_bool y
|
||||
|
||||
@ -105,6 +102,7 @@ config S390
|
||||
select ARCH_INLINE_WRITE_UNLOCK_IRQRESTORE
|
||||
select ARCH_STACKWALK
|
||||
select ARCH_SUPPORTS_ATOMIC_RMW
|
||||
select ARCH_SUPPORTS_DEBUG_PAGEALLOC
|
||||
select ARCH_SUPPORTS_NUMA_BALANCING
|
||||
select ARCH_USE_BUILTIN_BSWAP
|
||||
select ARCH_USE_CMPXCHG_LOCKREF
|
||||
|
@ -102,7 +102,7 @@ CONFIG_ZSMALLOC_STAT=y
|
||||
CONFIG_DEFERRED_STRUCT_PAGE_INIT=y
|
||||
CONFIG_IDLE_PAGE_TRACKING=y
|
||||
CONFIG_PERCPU_STATS=y
|
||||
CONFIG_GUP_BENCHMARK=y
|
||||
CONFIG_GUP_TEST=y
|
||||
CONFIG_NET=y
|
||||
CONFIG_PACKET=y
|
||||
CONFIG_PACKET_DIAG=m
|
||||
|
@ -95,7 +95,7 @@ CONFIG_ZSMALLOC_STAT=y
|
||||
CONFIG_DEFERRED_STRUCT_PAGE_INIT=y
|
||||
CONFIG_IDLE_PAGE_TRACKING=y
|
||||
CONFIG_PERCPU_STATS=y
|
||||
CONFIG_GUP_BENCHMARK=y
|
||||
CONFIG_GUP_TEST=y
|
||||
CONFIG_NET=y
|
||||
CONFIG_PACKET=y
|
||||
CONFIG_PACKET_DIAG=m
|
||||
|
@ -62,17 +62,8 @@ static vm_fault_t vdso_fault(const struct vm_special_mapping *sm,
|
||||
static int vdso_mremap(const struct vm_special_mapping *sm,
|
||||
struct vm_area_struct *vma)
|
||||
{
|
||||
unsigned long vdso_pages;
|
||||
|
||||
vdso_pages = vdso64_pages;
|
||||
|
||||
if ((vdso_pages << PAGE_SHIFT) != vma->vm_end - vma->vm_start)
|
||||
return -EINVAL;
|
||||
|
||||
if (WARN_ON_ONCE(current->mm != vma->vm_mm))
|
||||
return -EFAULT;
|
||||
|
||||
current->mm->context.vdso_base = vma->vm_start;
|
||||
|
||||
return 0;
|
||||
}
|
||||
|
||||
|
@ -88,6 +88,7 @@ config SPARC64
|
||||
select HAVE_C_RECORDMCOUNT
|
||||
select HAVE_ARCH_AUDITSYSCALL
|
||||
select ARCH_SUPPORTS_ATOMIC_RMW
|
||||
select ARCH_SUPPORTS_DEBUG_PAGEALLOC
|
||||
select HAVE_NMI
|
||||
select HAVE_REGS_AND_STACK_ACCESS_API
|
||||
select ARCH_USE_QUEUED_RWLOCKS
|
||||
@ -149,9 +150,6 @@ config GENERIC_ISA_DMA
|
||||
bool
|
||||
default y if SPARC32
|
||||
|
||||
config ARCH_SUPPORTS_DEBUG_PAGEALLOC
|
||||
def_bool y if SPARC64
|
||||
|
||||
config PGTABLE_LEVELS
|
||||
default 4 if 64BIT
|
||||
default 3
|
||||
|
@ -2894,7 +2894,7 @@ pgtable_t pte_alloc_one(struct mm_struct *mm)
|
||||
if (!page)
|
||||
return NULL;
|
||||
if (!pgtable_pte_page_ctor(page)) {
|
||||
free_unref_page(page);
|
||||
__free_page(page);
|
||||
return NULL;
|
||||
}
|
||||
return (pte_t *) page_address(page);
|
||||
|
@ -92,6 +92,7 @@ config X86
|
||||
select ARCH_STACKWALK
|
||||
select ARCH_SUPPORTS_ACPI
|
||||
select ARCH_SUPPORTS_ATOMIC_RMW
|
||||
select ARCH_SUPPORTS_DEBUG_PAGEALLOC
|
||||
select ARCH_SUPPORTS_NUMA_BALANCING if X86_64
|
||||
select ARCH_SUPPORTS_KMAP_LOCAL_FORCE_MAP if NR_CPUS <= 4096
|
||||
select ARCH_USE_BUILTIN_BSWAP
|
||||
@ -202,6 +203,7 @@ config X86
|
||||
select HAVE_MIXED_BREAKPOINTS_REGS
|
||||
select HAVE_MOD_ARCH_SPECIFIC
|
||||
select HAVE_MOVE_PMD
|
||||
select HAVE_MOVE_PUD
|
||||
select HAVE_NMI
|
||||
select HAVE_OPROFILE
|
||||
select HAVE_OPTPROBES
|
||||
@ -333,9 +335,6 @@ config ZONE_DMA32
|
||||
config AUDIT_ARCH
|
||||
def_bool y if X86_64
|
||||
|
||||
config ARCH_SUPPORTS_DEBUG_PAGEALLOC
|
||||
def_bool y
|
||||
|
||||
config KASAN_SHADOW_OFFSET
|
||||
hex
|
||||
depends on KASAN
|
||||
|
@ -89,30 +89,14 @@ static void vdso_fix_landing(const struct vdso_image *image,
|
||||
static int vdso_mremap(const struct vm_special_mapping *sm,
|
||||
struct vm_area_struct *new_vma)
|
||||
{
|
||||
unsigned long new_size = new_vma->vm_end - new_vma->vm_start;
|
||||
const struct vdso_image *image = current->mm->context.vdso_image;
|
||||
|
||||
if (image->size != new_size)
|
||||
return -EINVAL;
|
||||
|
||||
vdso_fix_landing(image, new_vma);
|
||||
current->mm->context.vdso = (void __user *)new_vma->vm_start;
|
||||
|
||||
return 0;
|
||||
}
|
||||
|
||||
static int vvar_mremap(const struct vm_special_mapping *sm,
|
||||
struct vm_area_struct *new_vma)
|
||||
{
|
||||
const struct vdso_image *image = new_vma->vm_mm->context.vdso_image;
|
||||
unsigned long new_size = new_vma->vm_end - new_vma->vm_start;
|
||||
|
||||
if (new_size != -image->sym_vvar_start)
|
||||
return -EINVAL;
|
||||
|
||||
return 0;
|
||||
}
|
||||
|
||||
#ifdef CONFIG_TIME_NS
|
||||
static struct page *find_timens_vvar_page(struct vm_area_struct *vma)
|
||||
{
|
||||
@ -252,7 +236,6 @@ static const struct vm_special_mapping vdso_mapping = {
|
||||
static const struct vm_special_mapping vvar_mapping = {
|
||||
.name = "[vvar]",
|
||||
.fault = vvar_fault,
|
||||
.mremap = vvar_mremap,
|
||||
};
|
||||
|
||||
/*
|
||||
|
@ -82,6 +82,7 @@ int set_pages_rw(struct page *page, int numpages);
|
||||
|
||||
int set_direct_map_invalid_noflush(struct page *page);
|
||||
int set_direct_map_default_noflush(struct page *page);
|
||||
bool kernel_page_present(struct page *page);
|
||||
|
||||
extern int kernel_set_to_readonly;
|
||||
|
||||
|
@ -1458,7 +1458,7 @@ static int pseudo_lock_dev_release(struct inode *inode, struct file *filp)
|
||||
return 0;
|
||||
}
|
||||
|
||||
static int pseudo_lock_dev_mremap(struct vm_area_struct *area)
|
||||
static int pseudo_lock_dev_mremap(struct vm_area_struct *area, unsigned long flags)
|
||||
{
|
||||
/* Not supported */
|
||||
return -EINVAL;
|
||||
|
@ -93,6 +93,7 @@ static struct mm_struct tboot_mm = {
|
||||
.pgd = swapper_pg_dir,
|
||||
.mm_users = ATOMIC_INIT(2),
|
||||
.mm_count = ATOMIC_INIT(1),
|
||||
.write_protect_seq = SEQCNT_ZERO(tboot_mm.write_protect_seq),
|
||||
MMAP_LOCK_INITIALIZER(init_mm)
|
||||
.page_table_lock = __SPIN_LOCK_UNLOCKED(init_mm.page_table_lock),
|
||||
.mmlist = LIST_HEAD_INIT(init_mm.mmlist),
|
||||
|
@ -2194,6 +2194,7 @@ int set_direct_map_default_noflush(struct page *page)
|
||||
return __set_pages_p(page, 1);
|
||||
}
|
||||
|
||||
#ifdef CONFIG_DEBUG_PAGEALLOC
|
||||
void __kernel_map_pages(struct page *page, int numpages, int enable)
|
||||
{
|
||||
if (PageHighMem(page))
|
||||
@ -2225,8 +2226,8 @@ void __kernel_map_pages(struct page *page, int numpages, int enable)
|
||||
|
||||
arch_flush_lazy_mmu_mode();
|
||||
}
|
||||
#endif /* CONFIG_DEBUG_PAGEALLOC */
|
||||
|
||||
#ifdef CONFIG_HIBERNATION
|
||||
bool kernel_page_present(struct page *page)
|
||||
{
|
||||
unsigned int level;
|
||||
@ -2238,7 +2239,6 @@ bool kernel_page_present(struct page *page)
|
||||
pte = lookup_address((unsigned long)page_address(page), &level);
|
||||
return (pte_val(*pte) & _PAGE_PRESENT);
|
||||
}
|
||||
#endif /* CONFIG_HIBERNATION */
|
||||
|
||||
int __init kernel_map_pages_in_pgd(pgd_t *pgd, u64 pfn, unsigned long address,
|
||||
unsigned numpages, unsigned long page_flags)
|
||||
|
@ -450,7 +450,7 @@ static ssize_t node_read_meminfo(struct device *dev,
|
||||
#ifdef CONFIG_SHADOW_CALL_STACK
|
||||
nid, node_page_state(pgdat, NR_KERNEL_SCS_KB),
|
||||
#endif
|
||||
nid, K(sum_zone_node_page_state(nid, NR_PAGETABLE)),
|
||||
nid, K(node_page_state(pgdat, NR_PAGETABLE)),
|
||||
nid, 0UL,
|
||||
nid, K(sum_zone_node_page_state(nid, NR_BOUNCE)),
|
||||
nid, K(node_page_state(pgdat, NR_WRITEBACK_TEMP)),
|
||||
|
@ -2,7 +2,7 @@
|
||||
config ZRAM
|
||||
tristate "Compressed RAM block device support"
|
||||
depends on BLOCK && SYSFS && ZSMALLOC && CRYPTO
|
||||
select CRYPTO_LZO
|
||||
depends on CRYPTO_LZO || CRYPTO_ZSTD || CRYPTO_LZ4 || CRYPTO_LZ4HC || CRYPTO_842
|
||||
help
|
||||
Creates virtual block devices called /dev/zramX (X = 0, 1, ...).
|
||||
Pages written to these disks are compressed and stored in memory
|
||||
@ -14,6 +14,46 @@ config ZRAM
|
||||
|
||||
See Documentation/admin-guide/blockdev/zram.rst for more information.
|
||||
|
||||
choice
|
||||
prompt "Default zram compressor"
|
||||
default ZRAM_DEF_COMP_LZORLE
|
||||
depends on ZRAM
|
||||
|
||||
config ZRAM_DEF_COMP_LZORLE
|
||||
bool "lzo-rle"
|
||||
depends on CRYPTO_LZO
|
||||
|
||||
config ZRAM_DEF_COMP_ZSTD
|
||||
bool "zstd"
|
||||
depends on CRYPTO_ZSTD
|
||||
|
||||
config ZRAM_DEF_COMP_LZ4
|
||||
bool "lz4"
|
||||
depends on CRYPTO_LZ4
|
||||
|
||||
config ZRAM_DEF_COMP_LZO
|
||||
bool "lzo"
|
||||
depends on CRYPTO_LZO
|
||||
|
||||
config ZRAM_DEF_COMP_LZ4HC
|
||||
bool "lz4hc"
|
||||
depends on CRYPTO_LZ4HC
|
||||
|
||||
config ZRAM_DEF_COMP_842
|
||||
bool "842"
|
||||
depends on CRYPTO_842
|
||||
|
||||
endchoice
|
||||
|
||||
config ZRAM_DEF_COMP
|
||||
string
|
||||
default "lzo-rle" if ZRAM_DEF_COMP_LZORLE
|
||||
default "zstd" if ZRAM_DEF_COMP_ZSTD
|
||||
default "lz4" if ZRAM_DEF_COMP_LZ4
|
||||
default "lzo" if ZRAM_DEF_COMP_LZO
|
||||
default "lz4hc" if ZRAM_DEF_COMP_LZ4HC
|
||||
default "842" if ZRAM_DEF_COMP_842
|
||||
|
||||
config ZRAM_WRITEBACK
|
||||
bool "Write back incompressible or idle page to backing device"
|
||||
depends on ZRAM
|
||||
|
@ -15,8 +15,10 @@
|
||||
#include "zcomp.h"
|
||||
|
||||
static const char * const backends[] = {
|
||||
#if IS_ENABLED(CONFIG_CRYPTO_LZO)
|
||||
"lzo",
|
||||
"lzo-rle",
|
||||
#endif
|
||||
#if IS_ENABLED(CONFIG_CRYPTO_LZ4)
|
||||
"lz4",
|
||||
#endif
|
||||
|
@ -42,7 +42,7 @@ static DEFINE_IDR(zram_index_idr);
|
||||
static DEFINE_MUTEX(zram_index_mutex);
|
||||
|
||||
static int zram_major;
|
||||
static const char *default_compressor = "lzo-rle";
|
||||
static const char *default_compressor = CONFIG_ZRAM_DEF_COMP;
|
||||
|
||||
/* Module params (documentation at end) */
|
||||
static unsigned int num_devices = 1;
|
||||
@ -620,15 +620,19 @@ static int read_from_bdev_async(struct zram *zram, struct bio_vec *bvec,
|
||||
return 1;
|
||||
}
|
||||
|
||||
#define PAGE_WB_SIG "page_index="
|
||||
|
||||
#define PAGE_WRITEBACK 0
|
||||
#define HUGE_WRITEBACK 1
|
||||
#define IDLE_WRITEBACK 2
|
||||
|
||||
|
||||
static ssize_t writeback_store(struct device *dev,
|
||||
struct device_attribute *attr, const char *buf, size_t len)
|
||||
{
|
||||
struct zram *zram = dev_to_zram(dev);
|
||||
unsigned long nr_pages = zram->disksize >> PAGE_SHIFT;
|
||||
unsigned long index;
|
||||
unsigned long index = 0;
|
||||
struct bio bio;
|
||||
struct bio_vec bio_vec;
|
||||
struct page *page;
|
||||
@ -640,9 +644,18 @@ static ssize_t writeback_store(struct device *dev,
|
||||
mode = IDLE_WRITEBACK;
|
||||
else if (sysfs_streq(buf, "huge"))
|
||||
mode = HUGE_WRITEBACK;
|
||||
else
|
||||
else {
|
||||
if (strncmp(buf, PAGE_WB_SIG, sizeof(PAGE_WB_SIG) - 1))
|
||||
return -EINVAL;
|
||||
|
||||
ret = kstrtol(buf + sizeof(PAGE_WB_SIG) - 1, 10, &index);
|
||||
if (ret || index >= nr_pages)
|
||||
return -EINVAL;
|
||||
|
||||
nr_pages = 1;
|
||||
mode = PAGE_WRITEBACK;
|
||||
}
|
||||
|
||||
down_read(&zram->init_lock);
|
||||
if (!init_done(zram)) {
|
||||
ret = -EINVAL;
|
||||
@ -660,7 +673,7 @@ static ssize_t writeback_store(struct device *dev,
|
||||
goto release_init_lock;
|
||||
}
|
||||
|
||||
for (index = 0; index < nr_pages; index++) {
|
||||
while (nr_pages--) {
|
||||
struct bio_vec bvec;
|
||||
|
||||
bvec.bv_page = page;
|
||||
@ -1071,7 +1084,7 @@ static ssize_t mm_stat_show(struct device *dev,
|
||||
max_used = atomic_long_read(&zram->stats.max_used_pages);
|
||||
|
||||
ret = scnprintf(buf, PAGE_SIZE,
|
||||
"%8llu %8llu %8llu %8lu %8ld %8llu %8lu %8llu\n",
|
||||
"%8llu %8llu %8llu %8lu %8ld %8llu %8lu %8llu %8llu\n",
|
||||
orig_size << PAGE_SHIFT,
|
||||
(u64)atomic64_read(&zram->stats.compr_data_size),
|
||||
mem_used << PAGE_SHIFT,
|
||||
@ -1079,7 +1092,8 @@ static ssize_t mm_stat_show(struct device *dev,
|
||||
max_used << PAGE_SHIFT,
|
||||
(u64)atomic64_read(&zram->stats.same_pages),
|
||||
pool_stats.pages_compacted,
|
||||
(u64)atomic64_read(&zram->stats.huge_pages));
|
||||
(u64)atomic64_read(&zram->stats.huge_pages),
|
||||
(u64)atomic64_read(&zram->stats.huge_pages_since));
|
||||
up_read(&zram->init_lock);
|
||||
|
||||
return ret;
|
||||
@ -1411,6 +1425,7 @@ out:
|
||||
if (comp_len == PAGE_SIZE) {
|
||||
zram_set_flag(zram, index, ZRAM_HUGE);
|
||||
atomic64_inc(&zram->stats.huge_pages);
|
||||
atomic64_inc(&zram->stats.huge_pages_since);
|
||||
}
|
||||
|
||||
if (flags) {
|
||||
|
@ -78,6 +78,7 @@ struct zram_stats {
|
||||
atomic64_t notify_free; /* no. of swap slot free notifications */
|
||||
atomic64_t same_pages; /* no. of same element filled pages */
|
||||
atomic64_t huge_pages; /* no. of huge pages */
|
||||
atomic64_t huge_pages_since; /* no. of huge pages since zram set up */
|
||||
atomic64_t pages_stored; /* no. of pages currently stored */
|
||||
atomic_long_t max_used_pages; /* no. of maximum pages stored */
|
||||
atomic64_t writestall; /* no. of write slow paths */
|
||||
|
@ -256,7 +256,7 @@ static vm_fault_t dev_dax_fault(struct vm_fault *vmf)
|
||||
return dev_dax_huge_fault(vmf, PE_SIZE_PTE);
|
||||
}
|
||||
|
||||
static int dev_dax_split(struct vm_area_struct *vma, unsigned long addr)
|
||||
static int dev_dax_may_split(struct vm_area_struct *vma, unsigned long addr)
|
||||
{
|
||||
struct file *filp = vma->vm_file;
|
||||
struct dev_dax *dev_dax = filp->private_data;
|
||||
@ -277,7 +277,7 @@ static unsigned long dev_dax_pagesize(struct vm_area_struct *vma)
|
||||
static const struct vm_operations_struct dax_vm_ops = {
|
||||
.fault = dev_dax_fault,
|
||||
.huge_fault = dev_dax_huge_fault,
|
||||
.split = dev_dax_split,
|
||||
.may_split = dev_dax_may_split,
|
||||
.pagesize = dev_dax_pagesize,
|
||||
};
|
||||
|
||||
|
@ -61,7 +61,7 @@ static int dev_dax_kmem_probe(struct dev_dax *dev_dax)
|
||||
return -EINVAL;
|
||||
}
|
||||
|
||||
data = kzalloc(sizeof(*data) + sizeof(struct resource *) * dev_dax->nr_range, GFP_KERNEL);
|
||||
data = kzalloc(struct_size(data, res, dev_dax->nr_range), GFP_KERNEL);
|
||||
if (!data)
|
||||
return -ENOMEM;
|
||||
|
||||
|
@ -270,8 +270,7 @@ static struct sync_file *sync_file_merge(const char *name, struct sync_file *a,
|
||||
fences[i++] = dma_fence_get(a_fences[0]);
|
||||
|
||||
if (num_fences > i) {
|
||||
nfences = krealloc(fences, i * sizeof(*fences),
|
||||
GFP_KERNEL);
|
||||
nfences = krealloc_array(fences, i, sizeof(*fences), GFP_KERNEL);
|
||||
if (!nfences)
|
||||
goto err;
|
||||
|
||||
|
@ -207,8 +207,8 @@ static void enumerate_dimms(const struct dmi_header *dh, void *arg)
|
||||
if (!hw->num_dimms || !(hw->num_dimms % 16)) {
|
||||
struct dimm_info *new;
|
||||
|
||||
new = krealloc(hw->dimms, (hw->num_dimms + 16) * sizeof(struct dimm_info),
|
||||
GFP_KERNEL);
|
||||
new = krealloc_array(hw->dimms, hw->num_dimms + 16,
|
||||
sizeof(struct dimm_info), GFP_KERNEL);
|
||||
if (!new) {
|
||||
WARN_ON_ONCE(1);
|
||||
return;
|
||||
|
@ -57,6 +57,7 @@ struct mm_struct efi_mm = {
|
||||
.mm_rb = RB_ROOT,
|
||||
.mm_users = ATOMIC_INIT(2),
|
||||
.mm_count = ATOMIC_INIT(1),
|
||||
.write_protect_seq = SEQCNT_ZERO(efi_mm.write_protect_seq),
|
||||
MMAP_LOCK_INITIALIZER(efi_mm)
|
||||
.page_table_lock = __SPIN_LOCK_UNLOCKED(efi_mm.page_table_lock),
|
||||
.mmlist = LIST_HEAD_INIT(efi_mm.mmlist),
|
||||
|
@ -964,7 +964,8 @@ drm_atomic_get_connector_state(struct drm_atomic_state *state,
|
||||
struct __drm_connnectors_state *c;
|
||||
int alloc = max(index + 1, config->num_connector);
|
||||
|
||||
c = krealloc(state->connectors, alloc * sizeof(*state->connectors), GFP_KERNEL);
|
||||
c = krealloc_array(state->connectors, alloc,
|
||||
sizeof(*state->connectors), GFP_KERNEL);
|
||||
if (!c)
|
||||
return ERR_PTR(-ENOMEM);
|
||||
|
||||
|
@ -2002,7 +2002,7 @@ nr_pages_store(struct device *dev, struct device_attribute *attr,
|
||||
}
|
||||
|
||||
nr_wins++;
|
||||
rewin = krealloc(win, sizeof(*win) * nr_wins, GFP_KERNEL);
|
||||
rewin = krealloc_array(win, nr_wins, sizeof(*win), GFP_KERNEL);
|
||||
if (!rewin) {
|
||||
kfree(win);
|
||||
return -ENOMEM;
|
||||
|
@ -51,8 +51,6 @@ static void falconide_release_lock(void)
|
||||
static void falconide_get_lock(irq_handler_t handler, void *data)
|
||||
{
|
||||
if (falconide_intr_lock == 0) {
|
||||
if (in_interrupt() > 0)
|
||||
panic("Falcon IDE hasn't ST-DMA lock in interrupt");
|
||||
stdma_lock(handler, data);
|
||||
falconide_intr_lock = 1;
|
||||
}
|
||||
|
@ -1592,9 +1592,6 @@ EXPORT_SYMBOL_GPL(ide_port_unregister_devices);
|
||||
|
||||
static void ide_unregister(ide_hwif_t *hwif)
|
||||
{
|
||||
BUG_ON(in_interrupt());
|
||||
BUG_ON(irqs_disabled());
|
||||
|
||||
mutex_lock(&ide_cfg_mtx);
|
||||
|
||||
if (hwif->present) {
|
||||
|
@ -11,6 +11,7 @@ lkdtm-$(CONFIG_LKDTM) += usercopy.o
|
||||
lkdtm-$(CONFIG_LKDTM) += stackleak.o
|
||||
lkdtm-$(CONFIG_LKDTM) += cfi.o
|
||||
|
||||
KASAN_SANITIZE_rodata.o := n
|
||||
KASAN_SANITIZE_stackleak.o := n
|
||||
KCOV_INSTRUMENT_rodata.o := n
|
||||
|
||||
|
@ -39,7 +39,7 @@ int pinctrl_utils_reserve_map(struct pinctrl_dev *pctldev,
|
||||
if (old_num >= new_num)
|
||||
return 0;
|
||||
|
||||
new_map = krealloc(*map, sizeof(*new_map) * new_num, GFP_KERNEL);
|
||||
new_map = krealloc_array(*map, new_num, sizeof(*new_map), GFP_KERNEL);
|
||||
if (!new_map) {
|
||||
dev_err(pctldev->dev, "krealloc(map) failed\n");
|
||||
return -ENOMEM;
|
||||
|
@ -198,7 +198,8 @@ static int resize_iovec(struct vringh_kiov *iov, gfp_t gfp)
|
||||
|
||||
flag = (iov->max_num & VRINGH_IOV_ALLOCATED);
|
||||
if (flag)
|
||||
new = krealloc(iov->iov, new_num * sizeof(struct iovec), gfp);
|
||||
new = krealloc_array(iov->iov, new_num,
|
||||
sizeof(struct iovec), gfp);
|
||||
else {
|
||||
new = kmalloc_array(new_num, sizeof(struct iovec), gfp);
|
||||
if (new) {
|
||||
|
@ -1114,9 +1114,7 @@ static int virtballoon_validate(struct virtio_device *vdev)
|
||||
* page reporting as it could potentially change the contents
|
||||
* of our free pages.
|
||||
*/
|
||||
if (!want_init_on_free() &&
|
||||
(IS_ENABLED(CONFIG_PAGE_POISONING_NO_SANITY) ||
|
||||
!page_poisoning_enabled()))
|
||||
if (!want_init_on_free() && !page_poisoning_enabled_static())
|
||||
__virtio_clear_bit(vdev, VIRTIO_BALLOON_F_PAGE_POISON);
|
||||
else if (!virtio_has_feature(vdev, VIRTIO_BALLOON_F_PAGE_POISON))
|
||||
__virtio_clear_bit(vdev, VIRTIO_BALLOON_F_REPORTING);
|
||||
|
@ -27,11 +27,6 @@ static int fill_list(unsigned int nr_pages)
|
||||
if (!res)
|
||||
return -ENOMEM;
|
||||
|
||||
pgmap = kzalloc(sizeof(*pgmap), GFP_KERNEL);
|
||||
if (!pgmap)
|
||||
goto err_pgmap;
|
||||
|
||||
pgmap->type = MEMORY_DEVICE_GENERIC;
|
||||
res->name = "Xen scratch";
|
||||
res->flags = IORESOURCE_MEM | IORESOURCE_BUSY;
|
||||
|
||||
@ -43,6 +38,11 @@ static int fill_list(unsigned int nr_pages)
|
||||
goto err_resource;
|
||||
}
|
||||
|
||||
pgmap = kzalloc(sizeof(*pgmap), GFP_KERNEL);
|
||||
if (!pgmap)
|
||||
goto err_pgmap;
|
||||
|
||||
pgmap->type = MEMORY_DEVICE_GENERIC;
|
||||
pgmap->range = (struct range) {
|
||||
.start = res->start,
|
||||
.end = res->end,
|
||||
@ -92,10 +92,10 @@ static int fill_list(unsigned int nr_pages)
|
||||
return 0;
|
||||
|
||||
err_memremap:
|
||||
release_resource(res);
|
||||
err_resource:
|
||||
kfree(pgmap);
|
||||
err_pgmap:
|
||||
release_resource(res);
|
||||
err_resource:
|
||||
kfree(res);
|
||||
return ret;
|
||||
}
|
||||
|
5
fs/aio.c
5
fs/aio.c
@ -323,13 +323,16 @@ static void aio_free_ring(struct kioctx *ctx)
|
||||
}
|
||||
}
|
||||
|
||||
static int aio_ring_mremap(struct vm_area_struct *vma)
|
||||
static int aio_ring_mremap(struct vm_area_struct *vma, unsigned long flags)
|
||||
{
|
||||
struct file *file = vma->vm_file;
|
||||
struct mm_struct *mm = vma->vm_mm;
|
||||
struct kioctx_table *table;
|
||||
int i, res = -EINVAL;
|
||||
|
||||
if (flags & MREMAP_DONTUNMAP)
|
||||
return -EINVAL;
|
||||
|
||||
spin_lock(&mm->ioctx_lock);
|
||||
rcu_read_lock();
|
||||
table = rcu_dereference(mm->ioctx_table);
|
||||
|
@ -323,7 +323,7 @@ static ssize_t ntfs_prepare_file_for_write(struct kiocb *iocb,
|
||||
unsigned long flags;
|
||||
struct file *file = iocb->ki_filp;
|
||||
struct inode *vi = file_inode(file);
|
||||
ntfs_inode *base_ni, *ni = NTFS_I(vi);
|
||||
ntfs_inode *ni = NTFS_I(vi);
|
||||
ntfs_volume *vol = ni->vol;
|
||||
|
||||
ntfs_debug("Entering for i_ino 0x%lx, attribute type 0x%x, pos "
|
||||
@ -365,9 +365,6 @@ static ssize_t ntfs_prepare_file_for_write(struct kiocb *iocb,
|
||||
err = -EOPNOTSUPP;
|
||||
goto out;
|
||||
}
|
||||
base_ni = ni;
|
||||
if (NInoAttr(ni))
|
||||
base_ni = ni->ext.base_ntfs_ino;
|
||||
err = file_remove_privs(file);
|
||||
if (unlikely(err))
|
||||
goto out;
|
||||
|
@ -2347,7 +2347,6 @@ int ntfs_truncate(struct inode *vi)
|
||||
ATTR_RECORD *a;
|
||||
const char *te = " Leaving file length out of sync with i_size.";
|
||||
int err, mp_size, size_change, alloc_change;
|
||||
u32 attr_len;
|
||||
|
||||
ntfs_debug("Entering for inode 0x%lx.", vi->i_ino);
|
||||
BUG_ON(NInoAttr(ni));
|
||||
@ -2721,7 +2720,6 @@ do_non_resident_truncate:
|
||||
* this cannot fail since we are making the attribute smaller thus by
|
||||
* definition there is enough space to do so.
|
||||
*/
|
||||
attr_len = le32_to_cpu(a->length);
|
||||
err = ntfs_attr_record_resize(m, a, mp_size +
|
||||
le16_to_cpu(a->data.non_resident.mapping_pairs_offset));
|
||||
BUG_ON(err);
|
||||
|
@ -478,7 +478,7 @@ bool ntfs_check_logfile(struct inode *log_vi, RESTART_PAGE_HEADER **rp)
|
||||
u8 *kaddr = NULL;
|
||||
RESTART_PAGE_HEADER *rstr1_ph = NULL;
|
||||
RESTART_PAGE_HEADER *rstr2_ph = NULL;
|
||||
int log_page_size, log_page_mask, err;
|
||||
int log_page_size, err;
|
||||
bool logfile_is_empty = true;
|
||||
u8 log_page_bits;
|
||||
|
||||
@ -501,7 +501,6 @@ bool ntfs_check_logfile(struct inode *log_vi, RESTART_PAGE_HEADER **rp)
|
||||
log_page_size = DefaultLogPageSize;
|
||||
else
|
||||
log_page_size = PAGE_SIZE;
|
||||
log_page_mask = log_page_size - 1;
|
||||
/*
|
||||
* Use ntfs_ffs() instead of ffs() to enable the compiler to
|
||||
* optimize log_page_size and log_page_bits into constants.
|
||||
|
@ -1198,7 +1198,6 @@ static int o2net_process_message(struct o2net_sock_container *sc,
|
||||
msglog(hdr, "bad magic\n");
|
||||
ret = -EINVAL;
|
||||
goto out;
|
||||
break;
|
||||
}
|
||||
|
||||
/* find a handler for it */
|
||||
|
@ -1088,8 +1088,8 @@ static int ocfs2_check_if_ancestor(struct ocfs2_super *osb,
|
||||
child_inode_no = parent_inode_no;
|
||||
|
||||
if (++i >= MAX_LOOKUP_TIMES) {
|
||||
mlog(ML_NOTICE, "max lookup times reached, filesystem "
|
||||
"may have nested directories, "
|
||||
mlog_ratelimited(ML_NOTICE, "max lookup times reached, "
|
||||
"filesystem may have nested directories, "
|
||||
"src inode: %llu, dest inode: %llu.\n",
|
||||
(unsigned long long)src_inode_no,
|
||||
(unsigned long long)dest_inode_no);
|
||||
|
@ -193,8 +193,6 @@ kclist_add_private(unsigned long pfn, unsigned long nr_pages, void *arg)
|
||||
return 1;
|
||||
|
||||
p = pfn_to_page(pfn);
|
||||
if (!memmap_valid_within(pfn, p, page_zone(p)))
|
||||
return 1;
|
||||
|
||||
ent = kmalloc(sizeof(*ent), GFP_KERNEL);
|
||||
if (!ent)
|
||||
|
@ -107,7 +107,7 @@ static int meminfo_proc_show(struct seq_file *m, void *v)
|
||||
global_node_page_state(NR_KERNEL_SCS_KB));
|
||||
#endif
|
||||
show_val_kb(m, "PageTables: ",
|
||||
global_zone_page_state(NR_PAGETABLE));
|
||||
global_node_page_state(NR_PAGETABLE));
|
||||
|
||||
show_val_kb(m, "NFS_Unstable: ", 0);
|
||||
show_val_kb(m, "Bounce: ",
|
||||
|
@ -28,7 +28,7 @@
|
||||
#include <linux/security.h>
|
||||
#include <linux/hugetlb.h>
|
||||
|
||||
int sysctl_unprivileged_userfaultfd __read_mostly = 1;
|
||||
int sysctl_unprivileged_userfaultfd __read_mostly;
|
||||
|
||||
static struct kmem_cache *userfaultfd_ctx_cachep __read_mostly;
|
||||
|
||||
@ -405,6 +405,13 @@ vm_fault_t handle_userfault(struct vm_fault *vmf, unsigned long reason)
|
||||
|
||||
if (ctx->features & UFFD_FEATURE_SIGBUS)
|
||||
goto out;
|
||||
if ((vmf->flags & FAULT_FLAG_USER) == 0 &&
|
||||
ctx->flags & UFFD_USER_MODE_ONLY) {
|
||||
printk_once(KERN_WARNING "uffd: Set unprivileged_userfaultfd "
|
||||
"sysctl knob to 1 if kernel faults must be handled "
|
||||
"without obtaining CAP_SYS_PTRACE capability\n");
|
||||
goto out;
|
||||
}
|
||||
|
||||
/*
|
||||
* If it's already released don't get it. This avoids to loop
|
||||
@ -1959,16 +1966,23 @@ SYSCALL_DEFINE1(userfaultfd, int, flags)
|
||||
struct userfaultfd_ctx *ctx;
|
||||
int fd;
|
||||
|
||||
if (!sysctl_unprivileged_userfaultfd && !capable(CAP_SYS_PTRACE))
|
||||
if (!sysctl_unprivileged_userfaultfd &&
|
||||
(flags & UFFD_USER_MODE_ONLY) == 0 &&
|
||||
!capable(CAP_SYS_PTRACE)) {
|
||||
printk_once(KERN_WARNING "uffd: Set unprivileged_userfaultfd "
|
||||
"sysctl knob to 1 if kernel faults must be handled "
|
||||
"without obtaining CAP_SYS_PTRACE capability\n");
|
||||
return -EPERM;
|
||||
}
|
||||
|
||||
BUG_ON(!current->mm);
|
||||
|
||||
/* Check the UFFD_* constants for consistency. */
|
||||
BUILD_BUG_ON(UFFD_USER_MODE_ONLY & UFFD_SHARED_FCNTL_FLAGS);
|
||||
BUILD_BUG_ON(UFFD_CLOEXEC != O_CLOEXEC);
|
||||
BUILD_BUG_ON(UFFD_NONBLOCK != O_NONBLOCK);
|
||||
|
||||
if (flags & ~UFFD_SHARED_FCNTL_FLAGS)
|
||||
if (flags & ~(UFFD_SHARED_FCNTL_FLAGS | UFFD_USER_MODE_ONLY))
|
||||
return -EINVAL;
|
||||
|
||||
ctx = kmem_cache_alloc(userfaultfd_ctx_cachep, GFP_KERNEL);
|
||||
|
@ -668,21 +668,6 @@ struct cgroup_subsys {
|
||||
*/
|
||||
bool threaded:1;
|
||||
|
||||
/*
|
||||
* If %false, this subsystem is properly hierarchical -
|
||||
* configuration, resource accounting and restriction on a parent
|
||||
* cgroup cover those of its children. If %true, hierarchy support
|
||||
* is broken in some ways - some subsystems ignore hierarchy
|
||||
* completely while others are only implemented half-way.
|
||||
*
|
||||
* It's now disallowed to create nested cgroups if the subsystem is
|
||||
* broken and cgroup core will emit a warning message on such
|
||||
* cases. Eventually, all subsystems will be made properly
|
||||
* hierarchical and this will go away.
|
||||
*/
|
||||
bool broken_hierarchy:1;
|
||||
bool warned_broken_hierarchy:1;
|
||||
|
||||
/* the following two fields are initialized automtically during boot */
|
||||
int id;
|
||||
const char *name;
|
||||
|
@ -98,11 +98,8 @@ extern void reset_isolation_suitable(pg_data_t *pgdat);
|
||||
extern enum compact_result compaction_suitable(struct zone *zone, int order,
|
||||
unsigned int alloc_flags, int highest_zoneidx);
|
||||
|
||||
extern void defer_compaction(struct zone *zone, int order);
|
||||
extern bool compaction_deferred(struct zone *zone, int order);
|
||||
extern void compaction_defer_reset(struct zone *zone, int order,
|
||||
bool alloc_success);
|
||||
extern bool compaction_restarting(struct zone *zone, int order);
|
||||
|
||||
/* Compaction has made some progress and retrying makes sense */
|
||||
static inline bool compaction_made_progress(enum compact_result result)
|
||||
@ -194,15 +191,6 @@ static inline enum compact_result compaction_suitable(struct zone *zone, int ord
|
||||
return COMPACT_SKIPPED;
|
||||
}
|
||||
|
||||
static inline void defer_compaction(struct zone *zone, int order)
|
||||
{
|
||||
}
|
||||
|
||||
static inline bool compaction_deferred(struct zone *zone, int order)
|
||||
{
|
||||
return true;
|
||||
}
|
||||
|
||||
static inline bool compaction_made_progress(enum compact_result result)
|
||||
{
|
||||
return false;
|
||||
|
@ -3230,7 +3230,7 @@ static inline bool vma_is_fsdax(struct vm_area_struct *vma)
|
||||
{
|
||||
struct inode *inode;
|
||||
|
||||
if (!vma->vm_file)
|
||||
if (!IS_ENABLED(CONFIG_FS_DAX) || !vma->vm_file)
|
||||
return false;
|
||||
if (!vma_is_dax(vma))
|
||||
return false;
|
||||
|
@ -580,8 +580,6 @@ void * __meminit alloc_pages_exact_nid(int nid, size_t size, gfp_t gfp_mask);
|
||||
|
||||
extern void __free_pages(struct page *page, unsigned int order);
|
||||
extern void free_pages(unsigned long addr, unsigned int order);
|
||||
extern void free_unref_page(struct page *page);
|
||||
extern void free_unref_page_list(struct list_head *list);
|
||||
|
||||
struct page_frag_cache;
|
||||
extern void __page_frag_cache_drain(struct page *page, unsigned int count);
|
||||
|
Some files were not shown because too many files have changed in this diff Show More
Loading…
Reference in New Issue
Block a user