Home
last modified time | relevance | path

Searched full:migration (Results 1 – 25 of 429) sorted by relevance

12345678910>>...18

/Linux-v6.1/Documentation/mm/
Dpage_migration.rst4 Page migration
7 Page migration allows moving the physical location of pages between
15 The main intent of page migration is to reduce the latency of memory accesses
19 Page migration allows a process to manually relocate the node on which its
25 Page migration functions are provided by the numactl package by Andi Kleen
29 migration. cat ``/proc/<pid>/numa_maps`` allows an easy review of where the
33 Manual migration is useful if for example the scheduler has relocated
37 manual page migration support. Automatic page migration may be implemented
54 Page migration allows the preservation of the relative location of pages
55 within a group of nodes for all migration techniques which will preserve a
[all …]
Dhmm.rst25 Finally, the last section presents a new migration helper that allows
106 Shared address space and migration
126 main memory to device memory using existing migration mechanisms and everything
130 memory for the device memory and second to perform migration. Policy decisions
133 Note that any CPU access to a device page triggers a page fault and a migration
136 address A triggers a page fault and initiates a migration back to main memory.
271 Migration to and from device memory
306 The overall migration steps are similar to migrating NUMA pages within system
307 memory (see :ref:`Page migration <page_migration>`) but the steps are split
314 be held for the duration of the migration.
[all …]
/Linux-v6.1/tools/testing/selftests/kvm/
Drseq_test.c26 * Any bug related to task migration is likely to be timing-dependent; perform
92 * that a migration may have occurred in between rseq and sched in migration_worker()
93 * CPU ID reads. An odd sequence count indicates a migration in migration_worker()
95 * a migration occurred since the count was last read. in migration_worker()
117 * 1. To allow sched_setaffinity() to prompt migration before in migration_worker()
134 * before the next round of migration. The test's check on in migration_worker()
135 * the rseq CPU ID must wait for migration to complete in in migration_worker()
137 * will be missed if the next migration starts before the in migration_worker()
198 "Only one usable CPU, task migration not possible"); in calc_min_max_cpu()
238 * Verify rseq's CPU matches sched's CPU. Ensure migration in main()
[all …]
/Linux-v6.1/tools/testing/selftests/vm/
Dmigration.c3 * The main purpose of the tests here is to exercise the migration entry code
22 FIXTURE(migration) in FIXTURE() argument
31 FIXTURE_SETUP(migration) in FIXTURE_SETUP() argument
56 FIXTURE_TEARDOWN(migration) in FIXTURE_TEARDOWN() argument
110 * Basic migration entry testing. One thread will move pages back and forth
112 * migration entry wait paths in the kernel.
114 TEST_F_TIMEOUT(migration, private_anon, 2*RUNTIME)
139 TEST_F_TIMEOUT(migration, shared_anon, 2*RUNTIME)
167 * Tests the pmd migration entry paths.
169 TEST_F_TIMEOUT(migration, private_anon_thp, 2*RUNTIME)
/Linux-v6.1/mm/
Dmigrate.c3 * Memory Migration functionality - linux/mm/migrate.c
7 * Page migration was first developed in the context of the memory hotplug
8 * project. The main authors of the migration code are:
86 * compaction threads can race against page migration functions in isolate_movable_page()
90 * being (wrongly) re-isolated while it is under migration, in isolate_movable_page()
132 * from where they were once taken off for compaction/migration.
172 * Restore a potential migration pte to a working pte entry
192 /* PMD-mapped THP migration entry */ in remove_migration_pte()
207 * Recheck VMA as permissions can change since migration started in remove_migration_pte()
272 * Get rid of all migration entries and replace them by
[all …]
Dmigrate_device.c3 * Device Memory Migration functionality.
179 * any kind of migration. Side effect is that it "freezes" the in migrate_vma_collect_pmd()
192 * migration as it is only best effort anyway. in migrate_vma_collect_pmd()
194 * If we can lock the page it's safe to set up a migration entry in migrate_vma_collect_pmd()
196 * single process setting up the migration entry now is an in migrate_vma_collect_pmd()
226 /* Setup special migration page table entry */ in migrate_vma_collect_pmd()
293 * @migrate: migrate struct containing all migration information
325 * folio_migrate_mapping(), except that here we allow migration of a
360 * Unmaps pages for migration. Returns number of source pfns marked as
440 * migrate_vma_unmap() - replace page mapping with special migration pte entry
[all …]
Dcompaction.c6 * this heavily depends upon page migration to do all the real heavy
301 * is necessary for the block to be a migration source/target. in __reset_isolation_pfn()
814 /* async migration should just abort */ in isolate_migratepages_block()
831 /* Time to isolate some pages for migration */ in isolate_migratepages_block()
836 * We have isolated all migration candidates in the in isolate_migratepages_block()
996 * Migration will fail if an anonymous page is pinned in memory, in isolate_migratepages_block()
1177 * scanning in the near future or migration failed in which case the in isolate_migratepages_block()
1269 /* Returns true if the page is within a block suitable for migration to */
1273 /* If the page is a large free page, then disallow migration */ in suitable_migration_target()
1287 /* If the block is MIGRATE_MOVABLE or MIGRATE_CMA, allow migration */ in suitable_migration_target()
[all …]
DKconfig508 depends on MIGRATION
547 bool "Allow for balloon memory compaction/migration"
555 by the guest workload. Allowing the compaction & migration for memory
564 select MIGRATION
594 # support for page migration
596 config MIGRATION config
597 bool "Page migration"
601 Allows the migration of the physical location of pages of processes
605 pages as migration can relocate pages to satisfy a huge page
609 def_bool MIGRATION && ZONE_DEVICE
[all …]
/Linux-v6.1/include/linux/
Dmigrate.h17 * - negative errno on page migration failure;
18 * - zero on page migration success;
23 * struct movable_operations - Driver page migration
37 * If page migration is successful, the driver should call
40 * -EAGAIN. The VM interprets this as a temporary migration failure and
41 * will retry it later. Any other error value is a permanent migration
42 * failure and migration will not be retried.
47 * If migration fails on the isolated page, the VM informs the driver
48 * that the page is no longer a candidate for migration by calling
Dballoon_compaction.h7 * Balloon page migration makes use of the general non-lru movable page
11 * page->mapping is used in context of non-lru page migration to reference
12 * the address space operations for page isolation/migration/compaction.
17 * and safely perform balloon's page compaction and migration we must, always,
33 * compaction / migration.
51 * have to cope for page compaction / migration, as well as it serves the
55 unsigned long isolated_pages; /* # of isolated pages for migration */
Dvfio.h100 * @migration_set_state: Optional callback to change the migration state for
101 * devices that support migration. It's mandatory for
102 * VFIO_DEVICE_FEATURE_MIGRATION migration support.
105 * of stream or error whenever the migration FSM leaves a data transfer
107 * @migration_get_state: Optional callback to get the migration state for
108 * devices that support migration. It's mandatory for
109 * VFIO_DEVICE_FEATURE_MIGRATION migration support.
/Linux-v6.1/drivers/gpu/drm/i915/gem/selftests/
Di915_gem_migrate.c137 * Migration will implicitly unbind (asynchronously) any bound in lmem_pages_migrate_one()
144 pr_err("Object failed migration to smem\n"); in lmem_pages_migrate_one()
163 pr_err("Object failed migration to lmem\n"); in lmem_pages_migrate_one()
269 /* Finally sync migration and check content. */ in __igt_lmem_pages_migrate()
360 * This subtest tests that unbinding at migration is indeed performed
362 * that spinner to have terminated. Before each migration we bind a
363 * vma, which should then be async unbound by the migration operation.
368 * Note that each async bind operation is awaiting the previous migration
369 * due to the moving fence resulting from the migration.
443 * arming the migration error check and block async migration. This
/Linux-v6.1/Documentation/networking/
Dnet_failover.rst24 datapath. It also enables hypervisor controlled live migration of a VM with
65 be brought UP during live migration to allow uninterrupted communication.
113 Live Migration of a VM with SR-IOV VF & virtio-net in STANDBY mode
116 net_failover also enables hypervisor controlled live migration to be supported
120 Here is a sample script that shows the steps to initiate live migration from
165 # Clean up FDB entries after migration completes.
169 On the destination hypervisor, a shared bridge 'br0' is created before migration
173 The following script is executed on the destination hypervisor once migration
/Linux-v6.1/Documentation/admin-guide/mm/
Duserfaultfd.rst228 migration. Postcopy live migration is one form of memory
233 migration to QEMU.
241 It is generally beneficial to run one pass of precopy live migration
242 just before starting postcopy live migration, in order to avoid
245 The implementation of postcopy live migration currently uses one
251 in the destination node, into the socket, and the migration thread of
261 by the parallel QEMU migration thread).
269 migration thread in the QEMU running in the destination node will
277 migration around and a single per-page bitmap has to be maintained in
284 postcopy thread just before ``UFFDIO_COPY|ZEROPAGE`` runs in the migration
/Linux-v6.1/Documentation/admin-guide/cgroup-v1/
Dmemcg_test.rst102 The logic is very clear. (About migration, see below)
129 7. Page Migration
162 9.3 Migration
165 For NUMA, migration is an another special case. To do easy test, cpuset
166 is useful. Following is a sample script to do migration::
179 In above set, when you moves a task from 01 to 02, page migration to
211 This is an easy way to test page migration, too.
298 9.9 Move charges at task migration
301 Charges associated with a task can be moved along with task migration.
/Linux-v6.1/Documentation/ABI/testing/
Dsysfs-kernel-mm-numa11 Page migration during reclaim is intended for systems
16 Allowing page migration during reclaim enables these
18 when the fast tier is under pressure. This migration
/Linux-v6.1/kernel/cgroup/
Dcgroup-internal.h106 /* used to track tasks and csets during migration */
121 * Before migration is committed, the target migration tasks are on
124 * or ->dst_csets depending on whether migration is committed.
134 /* migration context also tracks preloading */
138 * atomic success or failure on actual migration.
146 /* subsystems affected by migration */
/Linux-v6.1/Documentation/virt/kvm/devices/
Dvm.rst291 Allows userspace to stop migration mode, needed for PGSTE migration.
292 Setting this attribute when migration mode is not active will have no
301 Allows userspace to start migration mode, needed for PGSTE migration.
302 Setting this attribute when migration mode is already active will have
306 :Returns: -ENOMEM if there is not enough free memory to start migration mode;
313 Allows userspace to query the status of migration mode.
316 the data itself is either 0 if migration mode is disabled or 1
/Linux-v6.1/arch/powerpc/platforms/pseries/
Dvas.c491 * lost the credit or with migration. So just remove the entry in vas_deallocate_window()
635 * For partition migration, reopen all windows that are closed in reconfig_open_windows()
649 * Open windows if they are closed only with migration or in reconfig_open_windows()
659 * This window is closed with DLPAR and migration events. in reconfig_open_windows()
662 * migration notifier. So the user space can issue DLPAR in reconfig_open_windows()
663 * CPU hotplug while migration in progress. In this case in reconfig_open_windows()
735 * or for migration before. Go for next window. in reconfig_close_windows()
736 * For migration, nothing to do since this window in reconfig_close_windows()
778 * No way to stop migration for these failures. in reconfig_close_windows()
787 * For migration, do not depend on lpar_creds in case if in reconfig_close_windows()
[all …]
Dmobility.c3 * Support for Partition Mobility/Migration
113 * represented by the node is never interrupted by the migration. in delete_dt_node()
477 * If the memory transfer is already complete and the migration in wait_for_vasi_session_completed()
744 * When the migration is initiated, the hypervisor changes VAS in pseries_migrate_partition()
748 * faults from the migration event. So reduce this time window in pseries_migrate_partition()
806 * Used by drmgr to determine the kernel behavior of the migration interface.
808 * Version 1: Performs all PAPR requirements for migration including
813 static CLASS_ATTR_WO(migration);
826 pr_err("unable to create migration sysfs file (%d)\n", rc); in mobility_sysfs_init()
/Linux-v6.1/tools/perf/scripts/python/bin/
Dsched-migration-report2 # description: sched migration overview
3 perf script $@ -s "$PERF_EXEC_PATH"/scripts/python/sched-migration.py
/Linux-v6.1/include/uapi/linux/
Dvfio.h810 * Indicates the device can support the migration API through
832 * Upon VFIO_DEVICE_FEATURE_SET, execute a migration state change on the VFIO
836 * The kernel migration driver must fully transition the device to the new state
839 * The kernel migration driver must not generate asynchronous device state
851 * this FD when it is finished. The user must consider the migration data stream
856 * Upon VFIO_DEVICE_FEATURE_GET, get the current migration state of the VFIO
866 * The device migration Finite State Machine is described by the enum
867 * vfio_device_mig_state. Some of the FSM arcs will create a migration data
868 * transfer session by returning a FD, in this case the migration data will
889 * migration driver must accept and respond to interaction to support external
[all …]
/Linux-v6.1/fs/ocfs2/dlm/
Ddlmmaster.c822 /* if there is a migration in progress, let the migration in dlm_get_lock_resource()
824 * of the MIGRATION mle: either the migrate finished or in dlm_get_lock_resource()
836 mig ? "MIGRATION" : "BLOCK"); in dlm_get_lock_resource()
1591 mlog(0, "migration mle was found (%u->%u)\n", in dlm_master_request_handler()
1824 " from %u for migration\n", in dlm_assert_master_handler()
1829 " from %u for migration, ignoring\n", in dlm_assert_master_handler()
1931 mlog(0, "finishing off migration of lockres %.*s, " in dlm_assert_master_handler()
1977 * ref given by the master / migration request message. in dlm_assert_master_handler()
2119 * prevent migration from starting while we're still asserting in dlm_assert_master_worker()
2120 * our dominance. The reserved ast delays migration. in dlm_assert_master_worker()
[all …]
/Linux-v6.1/drivers/gpu/drm/amd/amdkfd/
Dkfd_svm.h71 * @migrate_mutex: to serialize range migration, validation and mapping update
91 * @granularity:migration granularity, log2 num pages
198 /* SVM API and HMM page migration work together, device memory type
199 * is initialized to not 0 when page migration register device memory.
/Linux-v6.1/drivers/misc/sgi-gru/
Dgrutlbpurge.c106 * - intrablade process migration between cpus is not frequent but is
109 * blade because of intrablade migration
110 * - interblade migration is rare. Processes migrate their GRU context to
112 * - if interblade migration occurs, migration back to the original blade

12345678910>>...18