kernel/linux.git/drivers/virtio/virtio_mem.c, branch v6.12.91

mm/memory_hotplug: skip adjust_managed_page_count() for PageOffline() pages when offlining

2024-07-04T02:30:18+00:00

We currently have a hack for virtio-mem in place to handle memory offlining with PageOffline pages for which we already adjusted the managed page count. Let's enlighten memory offlining code so we can get rid of that hack, and document the situation. Link: https://lkml.kernel.org/r/20240607090939.89524-4-david@redhat.com Signed-off-by: David Hildenbrand Acked-by: Oscar Salvador Cc: Alexander Potapenko Cc: Dexuan Cui Cc: Dmitry Vyukov Cc: Eugenio Pérez Cc: Haiyang Zhang Cc: Jason Wang Cc: Juergen Gross Cc: "K. Y. Srinivasan" Cc: Marco Elver Cc: Michael S. Tsirkin Cc: Mike Rapoport (IBM) Cc: Oleksandr Tyshchenko Cc: Stefano Stabellini Cc: Wei Liu Cc: Xuan Zhuo Signed-off-by: Andrew Morton

mm/memory_hotplug: initialize memmap of !ZONE_DEVICE with PageOffline() instead of PageReserved()

2024-07-04T02:30:18+00:00

We currently initialize the memmap such that PG_reserved is set and the refcount of the page is 1. In virtio-mem code, we have to manually clear that PG_reserved flag to make memory offlining with partially hotplugged memory blocks possible: has_unmovable_pages() would otherwise bail out on such pages. We want to avoid PG_reserved where possible and move to typed pages instead. Further, we want to further enlighten memory offlining code about PG_offline: offline pages in an online memory section. One example is handling managed page count adjustments in a cleaner way during memory offlining. So let's initialize the pages with PG_offline instead of PG_reserved. generic_online_page()->__free_pages_core() will now clear that flag before handing that memory to the buddy. Note that the page refcount is still 1 and would forbid offlining of such memory except when special care is take during GOING_OFFLINE as currently only implemented by virtio-mem. With this change, we can now get non-PageReserved() pages in the XEN balloon list. From what I can tell, that can already happen via decrease_reservation(), so that should be fine. HV-balloon should not really observe a change: partial online memory blocks still cannot get surprise-offlined, because the refcount of these PageOffline() pages is 1. Update virtio-mem, HV-balloon and XEN-balloon code to be aware that hotplugged pages are now PageOffline() instead of PageReserved() before they are handed over to the buddy. We'll leave the ZONE_DEVICE case alone for now. Note that self-hosted vmemmap pages will no longer be marked as reserved. This matches ordinary vmemmap pages allocated from the buddy during memory hotplug. Now, really only vmemmap pages allocated from memblock during early boot will be marked reserved. Existing PageReserved() checks seem to be handling all relevant cases correctly even after this change. Link: https://lkml.kernel.org/r/20240607090939.89524-3-david@redhat.com Signed-off-by: David Hildenbrand Acked-by: Oscar Salvador [generic memory-hotplug bits] Cc: Alexander Potapenko Cc: Dexuan Cui Cc: Dmitry Vyukov Cc: Eugenio Pérez Cc: Haiyang Zhang Cc: Jason Wang Cc: Juergen Gross Cc: "K. Y. Srinivasan" Cc: Marco Elver Cc: Michael S. Tsirkin Cc: Mike Rapoport (IBM) Cc: Oleksandr Tyshchenko Cc: Stefano Stabellini Cc: Wei Liu Cc: Xuan Zhuo Signed-off-by: Andrew Morton

Merge tag 'for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mst/vhost

2024-05-23T19:04:36+00:00

Pull virtio updates from Michael Tsirkin: "Several new features here: - virtio-net is finally supported in vduse - virtio (balloon and mem) interaction with suspend is improved - vhost-scsi now handles signals better/faster And fixes, cleanups all over the place" * tag 'for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mst/vhost: (48 commits) virtio-pci: Check if is_avq is NULL virtio: delete vq in vp_find_vqs_msix() when request_irq() fails MAINTAINERS: add Eugenio Pérez as reviewer vhost-vdpa: Remove usage of the deprecated ida_simple_xx() API vp_vdpa: don't allocate unused msix vectors sound: virtio: drop owner assignment fuse: virtio: drop owner assignment scsi: virtio: drop owner assignment rpmsg: virtio: drop owner assignment nvdimm: virtio_pmem: drop owner assignment wifi: mac80211_hwsim: drop owner assignment vsock/virtio: drop owner assignment net: 9p: virtio: drop owner assignment net: virtio: drop owner assignment net: caif: virtio: drop owner assignment misc: nsm: drop owner assignment iommu: virtio: drop owner assignment drm/virtio: drop owner assignment gpio: virtio: drop owner assignment firmware: arm_scmi: virtio: drop owner assignment ...

virtio: mem: drop owner assignment

2024-05-22T12:31:16+00:00

virtio core already sets the .owner, so driver does not need to. Signed-off-by: Krzysztof Kozlowski Message-Id: <20240331-module-owner-virtio-v2-4-98f04bfaf46a@linaro.org> Signed-off-by: Michael S. Tsirkin

virtio-mem: support suspend+resume

2024-05-22T12:31:15+00:00

With virtio-mem, primarily hibernation is problematic: as the machine shuts down, the virtio-mem device loses its state. Powering the machine back up is like losing a bunch of DIMMs. While there would be ways to add limited support, suspend+resume is more commonly used for VMs and "easier" to support cleanly. s2idle can be supported without any device dependencies. Similarly, one would expect suspend-to-ram (i.e., S3) to work out of the box. However, QEMU currently unplugs all device memory when resuming the VM, using a cold reset on the "wakeup" path. In order to support S3, we need a feature flag for the device to tell us if memory remains plugged when waking up. In the future, QEMU will implement this feature. So let's always support s2idle and support S3 with plugged memory only if the device indicates support. Block hibernation early using the PM notifier. Trying to hibernate now fails early: # echo disk > /sys/power/state [ 26.455369] PM: hibernation: hibernation entry [ 26.458271] virtio_mem virtio0: hibernation is not supported. [ 26.462498] PM: hibernation: hibernation exit -bash: echo: write error: Operation not permitted s2idle works even without the new feature bit: # echo s2idle > /sys/power/mem_sleep # echo mem > /sys/power/state [ 52.083725] PM: suspend entry (s2idle) [ 52.095950] Filesystems sync: 0.010 seconds [ 52.101493] Freezing user space processes [ 52.104213] Freezing user space processes completed (elapsed 0.001 seconds) [ 52.106520] OOM killer disabled. [ 52.107655] Freezing remaining freezable tasks [ 52.110880] Freezing remaining freezable tasks completed (elapsed 0.001 seconds) [ 52.113296] printk: Suspending console(s) (use no_console_suspend to debug) S3 does not work without the feature bit when memory is plugged: # echo deep > /sys/power/mem_sleep # echo mem > /sys/power/state [ 32.788281] PM: suspend entry (deep) [ 32.816630] Filesystems sync: 0.027 seconds [ 32.820029] Freezing user space processes [ 32.823870] Freezing user space processes completed (elapsed 0.001 seconds) [ 32.827756] OOM killer disabled. [ 32.829608] Freezing remaining freezable tasks [ 32.833842] Freezing remaining freezable tasks completed (elapsed 0.001 seconds) [ 32.837953] printk: Suspending console(s) (use no_console_suspend to debug) [ 32.916172] virtio_mem virtio0: suspend+resume with plugged memory is not supported [ 32.916181] virtio-pci 0000:00:02.0: PM: pci_pm_suspend(): virtio_pci_freeze+0x0/0x50 returns -1 [ 32.916197] virtio-pci 0000:00:02.0: PM: dpm_run_callback(): pci_pm_suspend+0x0/0x170 returns -1 [ 32.916210] virtio-pci 0000:00:02.0: PM: failed to suspend async: error -1 But S3 works with the new feature bit when memory is plugged (patched QEMU): # echo deep > /sys/power/mem_sleep # echo mem > /sys/power/state [ 33.983694] PM: suspend entry (deep) [ 34.009828] Filesystems sync: 0.024 seconds [ 34.013589] Freezing user space processes [ 34.016722] Freezing user space processes completed (elapsed 0.001 seconds) [ 34.019092] OOM killer disabled. [ 34.020291] Freezing remaining freezable tasks [ 34.023549] Freezing remaining freezable tasks completed (elapsed 0.001 seconds) [ 34.026090] printk: Suspending console(s) (use no_console_suspend to debug) Cc: "Michael S. Tsirkin" Cc: Jason Wang Cc: Xuan Zhuo Signed-off-by: David Hildenbrand Message-Id: <20240318120645.105664-1-david@redhat.com> Signed-off-by: Michael S. Tsirkin

fix missing vmalloc.h includes

2024-04-26T03:55:49+00:00

Patch series "Memory allocation profiling", v6. Overview: Low overhead [1] per-callsite memory allocation profiling. Not just for debug kernels, overhead low enough to be deployed in production. Example output: root@moria-kvm:~# sort -rn /proc/allocinfo 127664128 31168 mm/page_ext.c:270 func:alloc_page_ext 56373248 4737 mm/slub.c:2259 func:alloc_slab_page 14880768 3633 mm/readahead.c:247 func:page_cache_ra_unbounded 14417920 3520 mm/mm_init.c:2530 func:alloc_large_system_hash 13377536 234 block/blk-mq.c:3421 func:blk_mq_alloc_rqs 11718656 2861 mm/filemap.c:1919 func:__filemap_get_folio 9192960 2800 kernel/fork.c:307 func:alloc_thread_stack_node 4206592 4 net/netfilter/nf_conntrack_core.c:2567 func:nf_ct_alloc_hashtable 4136960 1010 drivers/staging/ctagmod/ctagmod.c:20 [ctagmod] func:ctagmod_start 3940352 962 mm/memory.c:4214 func:alloc_anon_folio 2894464 22613 fs/kernfs/dir.c:615 func:__kernfs_new_node ... Usage: kconfig options: - CONFIG_MEM_ALLOC_PROFILING - CONFIG_MEM_ALLOC_PROFILING_ENABLED_BY_DEFAULT - CONFIG_MEM_ALLOC_PROFILING_DEBUG adds warnings for allocations that weren't accounted because of a missing annotation sysctl: /proc/sys/vm/mem_profiling Runtime info: /proc/allocinfo Notes: [1]: Overhead To measure the overhead we are comparing the following configurations: (1) Baseline with CONFIG_MEMCG_KMEM=n (2) Disabled by default (CONFIG_MEM_ALLOC_PROFILING=y && CONFIG_MEM_ALLOC_PROFILING_BY_DEFAULT=n) (3) Enabled by default (CONFIG_MEM_ALLOC_PROFILING=y && CONFIG_MEM_ALLOC_PROFILING_BY_DEFAULT=y) (4) Enabled at runtime (CONFIG_MEM_ALLOC_PROFILING=y && CONFIG_MEM_ALLOC_PROFILING_BY_DEFAULT=n && /proc/sys/vm/mem_profiling=1) (5) Baseline with CONFIG_MEMCG_KMEM=y && allocating with __GFP_ACCOUNT (6) Disabled by default (CONFIG_MEM_ALLOC_PROFILING=y && CONFIG_MEM_ALLOC_PROFILING_BY_DEFAULT=n) && CONFIG_MEMCG_KMEM=y (7) Enabled by default (CONFIG_MEM_ALLOC_PROFILING=y && CONFIG_MEM_ALLOC_PROFILING_BY_DEFAULT=y) && CONFIG_MEMCG_KMEM=y Performance overhead: To evaluate performance we implemented an in-kernel test executing multiple get_free_page/free_page and kmalloc/kfree calls with allocation sizes growing from 8 to 240 bytes with CPU frequency set to max and CPU affinity set to a specific CPU to minimize the noise. Below are results from running the test on Ubuntu 22.04.2 LTS with 6.8.0-rc1 kernel on 56 core Intel Xeon: kmalloc pgalloc (1 baseline) 6.764s 16.902s (2 default disabled) 6.793s (+0.43%) 17.007s (+0.62%) (3 default enabled) 7.197s (+6.40%) 23.666s (+40.02%) (4 runtime enabled) 7.405s (+9.48%) 23.901s (+41.41%) (5 memcg) 13.388s (+97.94%) 48.460s (+186.71%) (6 def disabled+memcg) 13.332s (+97.10%) 48.105s (+184.61%) (7 def enabled+memcg) 13.446s (+98.78%) 54.963s (+225.18%) Memory overhead: Kernel size: text data bss dec diff (1) 26515311 18890222 17018880 62424413 (2) 26524728 19423818 16740352 62688898 264485 (3) 26524724 19423818 16740352 62688894 264481 (4) 26524728 19423818 16740352 62688898 264485 (5) 26541782 18964374 16957440 62463596 39183 Memory consumption on a 56 core Intel CPU with 125GB of memory: Code tags: 192 kB PageExts: 262144 kB (256MB) SlabExts: 9876 kB (9.6MB) PcpuExts: 512 kB (0.5MB) Total overhead is 0.2% of total memory. Benchmarks: Hackbench tests run 100 times: hackbench -s 512 -l 200 -g 15 -f 25 -P baseline disabled profiling enabled profiling avg 0.3543 0.3559 (+0.0016) 0.3566 (+0.0023) stdev 0.0137 0.0188 0.0077 hackbench -l 10000 baseline disabled profiling enabled profiling avg 6.4218 6.4306 (+0.0088) 6.5077 (+0.0859) stdev 0.0933 0.0286 0.0489 stress-ng tests: stress-ng --class memory --seq 4 -t 60 stress-ng --class cpu --seq 4 -t 60 Results posted at: https://evilpiepirate.org/~kent/memalloc_prof_v4_stress-ng/ [2] https://lore.kernel.org/all/20240306182440.2003814-1-surenb@google.com/ This patch (of 37): The next patch drops vmalloc.h from a system header in order to fix a circular dependency; this adds it to all the files that were pulling it in implicitly. [kent.overstreet@linux.dev: fix arch/alpha/lib/memcpy.c] Link: https://lkml.kernel.org/r/20240327002152.3339937-1-kent.overstreet@linux.dev [surenb@google.com: fix arch/x86/mm/numa_32.c] Link: https://lkml.kernel.org/r/20240402180933.1663992-1-surenb@google.com [kent.overstreet@linux.dev: a few places were depending on sizes.h] Link: https://lkml.kernel.org/r/20240404034744.1664840-1-kent.overstreet@linux.dev [arnd@arndb.de: fix mm/kasan/hw_tags.c] Link: https://lkml.kernel.org/r/20240404124435.3121534-1-arnd@kernel.org [surenb@google.com: fix arc build] Link: https://lkml.kernel.org/r/20240405225115.431056-1-surenb@google.com Link: https://lkml.kernel.org/r/20240321163705.3067592-1-surenb@google.com Link: https://lkml.kernel.org/r/20240321163705.3067592-2-surenb@google.com Signed-off-by: Kent Overstreet Signed-off-by: Suren Baghdasaryan Signed-off-by: Arnd Bergmann Reviewed-by: Pasha Tatashin Tested-by: Kees Cook Cc: Alexander Viro Cc: Alex Gaynor Cc: Alice Ryhl Cc: Andreas Hindborg Cc: Benno Lossin Cc: "Björn Roy Baron" Cc: Boqun Feng Cc: Christoph Lameter Cc: Dennis Zhou Cc: Gary Guo Cc: Miguel Ojeda Cc: Peter Zijlstra Cc: Tejun Heo Cc: Vlastimil Babka Cc: Wedson Almeida Filho Signed-off-by: Andrew Morton

mm, treewide: rename MAX_ORDER to MAX_PAGE_ORDER

2024-01-08T23:27:15+00:00

commit 23baf831a32c ("mm, treewide: redefine MAX_ORDER sanely") has changed the definition of MAX_ORDER to be inclusive. This has caused issues with code that was not yet upstream and depended on the previous definition. To draw attention to the altered meaning of the define, rename MAX_ORDER to MAX_PAGE_ORDER. Link: https://lkml.kernel.org/r/20231228144704.14033-2-kirill.shutemov@linux.intel.com Signed-off-by: Kirill A. Shutemov Cc: Linus Torvalds Signed-off-by: Andrew Morton

virtio-mem: check if the config changed before fake offlining memory

2023-08-10T19:51:46+00:00

If we repeatedly fail to fake offline memory to unplug it, we won't be sending any unplug requests to the device. However, we only check if the config changed when sending such (un)plug requests. We could end up trying for a long time to unplug memory, even though the config changed already and we're not supposed to unplug memory anymore. For example, the hypervisor might detect a low-memory situation while unplugging memory and decide to replug some memory. Continuing trying to unplug memory in that case can be problematic. So let's check on a more regular basis. Signed-off-by: David Hildenbrand Message-Id: <20230713145551.2824980-5-david@redhat.com> Signed-off-by: Michael S. Tsirkin

virtio-mem: keep retrying on offline_and_remove_memory() errors in Sub Block Mode (SBM)

2023-08-10T19:51:46+00:00

In case offline_and_remove_memory() fails in SBM, we leave a completely unplugged Linux memory block stick around until we try plugging memory again. We won't try removing that memory block again. offline_and_remove_memory() may, for example, fail if we're racing with another alloc_contig_range() user, if allocating temporary memory fails, or if some memory notifier rejected the offlining request. Let's handle that case better, by simple retrying to offline and remove such memory. Tested using CONFIG_MEMORY_NOTIFIER_ERROR_INJECT. Signed-off-by: David Hildenbrand Message-Id: <20230713145551.2824980-4-david@redhat.com> Signed-off-by: Michael S. Tsirkin

virtio-mem: convert most offline_and_remove_memory() errors to -EBUSY

2023-08-10T19:51:46+00:00

Just like we do with alloc_contig_range(), let's convert all unknown errors to -EBUSY, but WARN so we can look into the issue. For example, offline_pages() could fail with -EINTR, which would be unexpected in our case. Signed-off-by: David Hildenbrand Message-Id: <20230713145551.2824980-3-david@redhat.com> Signed-off-by: Michael S. Tsirkin