diff options
71 files changed, 1087 insertions, 1020 deletions
diff --git a/Documentation/filesystems/proc.txt b/Documentation/filesystems/proc.txt index fb4735fd73b0..99ca040e3f90 100644 --- a/Documentation/filesystems/proc.txt +++ b/Documentation/filesystems/proc.txt @@ -486,8 +486,8 @@ replaced by copy-on-write) part of the underlying shmem object out on swap. "SwapPss" shows proportional swap share of this mapping. Unlike "Swap", this does not take into account swapped out page of underlying shmem objects. "Locked" indicates whether the mapping is locked in memory or not. -"THPeligible" indicates whether the mapping is eligible for THP pages - 1 if -true, 0 otherwise. +"THPeligible" indicates whether the mapping is eligible for allocating THP +pages - 1 if true, 0 otherwise. It just shows the current status. "VmFlags" field deserves a separate description. This member represents the kernel flags associated with the particular virtual memory area in two letter encoded diff --git a/Documentation/vm/memory-model.rst b/Documentation/vm/memory-model.rst index 382f72ace1fc..58a12376b7df 100644 --- a/Documentation/vm/memory-model.rst +++ b/Documentation/vm/memory-model.rst @@ -181,3 +181,43 @@ that is eventually passed to vmemmap_populate() through a long chain of function calls. The vmemmap_populate() implementation may use the `vmem_altmap` along with :c:func:`altmap_alloc_block_buf` helper to allocate memory map on the persistent memory device. + +ZONE_DEVICE +=========== +The `ZONE_DEVICE` facility builds upon `SPARSEMEM_VMEMMAP` to offer +`struct page` `mem_map` services for device driver identified physical +address ranges. The "device" aspect of `ZONE_DEVICE` relates to the fact +that the page objects for these address ranges are never marked online, +and that a reference must be taken against the device, not just the page +to keep the memory pinned for active use. `ZONE_DEVICE`, via +:c:func:`devm_memremap_pages`, performs just enough memory hotplug to +turn on :c:func:`pfn_to_page`, :c:func:`page_to_pfn`, and +:c:func:`get_user_pages` service for the given range of pfns. Since the +page reference count never drops below 1 the page is never tracked as +free memory and the page's `struct list_head lru` space is repurposed +for back referencing to the host device / driver that mapped the memory. + +While `SPARSEMEM` presents memory as a collection of sections, +optionally collected into memory blocks, `ZONE_DEVICE` users have a need +for smaller granularity of populating the `mem_map`. Given that +`ZONE_DEVICE` memory is never marked online it is subsequently never +subject to its memory ranges being exposed through the sysfs memory +hotplug api on memory block boundaries. The implementation relies on +this lack of user-api constraint to allow sub-section sized memory +ranges to be specified to :c:func:`arch_add_memory`, the top-half of +memory hotplug. Sub-section support allows for 2MB as the cross-arch +common alignment granularity for :c:func:`devm_memremap_pages`. + +The users of `ZONE_DEVICE` are: + +* pmem: Map platform persistent memory to be used as a direct-I/O target + via DAX mappings. + +* hmm: Extend `ZONE_DEVICE` with `->page_fault()` and `->page_free()` + event callbacks to allow a device-driver to coordinate memory management + events related to device-memory, typically GPU memory. See + Documentation/vm/hmm.rst. + +* p2pdma: Create `struct page` objects to allow peer devices in a + PCI/-E topology to coordinate direct-DMA operations between themselves, + i.e. bypass host memory. diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c index e661469cabdd..750a69dde39b 100644 --- a/arch/arm64/mm/mmu.c +++ b/arch/arm64/mm/mmu.c @@ -1074,4 +1074,21 @@ int arch_add_memory(int nid, u64 start, u64 size, return __add_pages(nid, start >> PAGE_SHIFT, size >> PAGE_SHIFT, restrictions); } +void arch_remove_memory(int nid, u64 start, u64 size, + struct vmem_altmap *altmap) +{ + unsigned long start_pfn = start >> PAGE_SHIFT; + unsigned long nr_pages = size >> PAGE_SHIFT; + struct zone *zone; + + /* + * FIXME: Cleanup page tables (also in arch_add_memory() in case + * adding fails). Until then, this function should only be used + * during memory hotplug (adding memory), not for memory + * unplug. ARCH_ENABLE_MEMORY_HOTREMOVE must not be + * unlocked yet. + */ + zone = page_zone(pfn_to_page(start_pfn)); + __remove_pages(zone, start_pfn, nr_pages, altmap); +} #endif diff --git a/arch/ia64/mm/init.c b/arch/ia64/mm/init.c index d28e29103bdb..aae75fd7b810 100644 --- a/arch/ia64/mm/init.c +++ b/arch/ia64/mm/init.c @@ -681,7 +681,6 @@ int arch_add_memory(int nid, u64 start, u64 size, return ret; } -#ifdef CONFIG_MEMORY_HOTREMOVE void arch_remove_memory(int nid, u64 start, u64 size, struct vmem_altmap *altmap) { @@ -693,4 +692,3 @@ void arch_remove_memory(int nid, u64 start, u64 size, __remove_pages(zone, start_pfn, nr_pages, altmap); } #endif -#endif diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c index 26a8da3723bb..9259337d7374 100644 --- a/arch/powerpc/mm/mem.c +++ b/arch/powerpc/mm/mem.c @@ -125,7 +125,6 @@ int __ref arch_add_memory(int nid, u64 start, u64 size, return __add_pages(nid, start_pfn, nr_pages, restrictions); } -#ifdef CONFIG_MEMORY_HOTREMOVE void __ref arch_remove_memory(int nid, u64 start, u64 size, struct vmem_altmap *altmap) { @@ -151,7 +150,6 @@ void __ref arch_remove_memory(int nid, u64 start, u64 size, pr_warn("Hash collision while resizing HPT\n"); } #endif -#endif /* CONFIG_MEMORY_HOTPLUG */ #ifndef CONFIG_NEED_MULTIPLE_NODES void __init mem_topology_setup(void) diff --git a/arch/powerpc/platforms/powernv/memtrace.c b/arch/powerpc/platforms/powernv/memtrace.c index 5e53c1392d3b..eb2e75dac369 100644 --- a/arch/powerpc/platforms/powernv/memtrace.c +++ b/arch/powerpc/platforms/powernv/memtrace.c @@ -70,23 +70,23 @@ static int change_memblock_state(struct memory_block *mem, void *arg) /* called with device_hotplug_lock held */ static bool memtrace_offline_pages(u32 nid, u64 start_pfn, u64 nr_pages) { - u64 end_pfn = start_pfn + nr_pages - 1; + const unsigned long start = PFN_PHYS(start_pfn); + const unsigned long size = PFN_PHYS(nr_pages); - if (walk_memory_range(start_pfn, end_pfn, NULL, - check_memblock_online)) + if (walk_memory_blocks(start, size, NULL, check_memblock_online)) return false; - walk_memory_range(start_pfn, end_pfn, (void *)MEM_GOING_OFFLINE, - change_memblock_state); + walk_memory_blocks(start, size, (void *)MEM_GOING_OFFLINE, + change_memblock_state); if (offline_pages(start_pfn, nr_pages)) { - walk_memory_range(start_pfn, end_pfn, (void *)MEM_ONLINE, - change_memblock_state); + walk_memory_blocks(start, size, (void *)MEM_ONLINE, + change_memblock_state); return false; } - walk_memory_range(start_pfn, end_pfn, (void *)MEM_OFFLINE, - change_memblock_state); + walk_memory_blocks(start, size, (void *)MEM_OFFLINE, + change_memblock_state); return true; @@ -242,9 +242,8 @@ static int memtrace_online(void) */ if (!memhp_auto_online) { lock_device_hotplug(); - walk_memory_range(PFN_DOWN(ent->start), - PFN_UP(ent->start + ent->size - 1), - NULL, online_mem_block); + walk_memory_blocks(ent->start, ent->size, NULL, + online_mem_block); unlock_device_hotplug(); } diff --git a/arch/s390/appldata/appldata_base.c b/arch/s390/appldata/appldata_base.c index e4b58240ec53..aa738cad1338 100644 --- a/arch/s390/appldata/appldata_base.c +++ b/arch/s390/appldata/appldata_base.c @@ -220,15 +220,13 @@ appldata_timer_handler(struct ctl_table *ctl, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { int timer_active = appldata_timer_active; - int zero = 0; - int one = 1; int rc; struct ctl_table ctl_entry = { .procname = ctl->procname, .data = &timer_active, .maxlen = sizeof(int), - .extra1 = &zero, - .extra2 = &one, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE, }; rc = proc_douintvec_minmax(&ctl_entry, write, buffer, lenp, ppos); @@ -255,13 +253,12 @@ appldata_interval_handler(struct ctl_table *ctl, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { int interval = appldata_interval; - int one = 1; int rc; struct ctl_table ctl_entry = { .procname = ctl->procname, .data = &interval, .maxlen = sizeof(int), - .extra1 = &one, + .extra1 = SYSCTL_ONE, }; rc = proc_dointvec_minmax(&ctl_entry, write, buffer, lenp, ppos); @@ -289,13 +286,11 @@ appldata_generic_handler(struct ctl_table *ctl, int write, struct list_head *lh; int rc, found; int active; - int zero = 0; - int one = 1; struct ctl_table ctl_entry = { .data = &active, .maxlen = sizeof(int), - .extra1 = &zero, - .extra2 = &one, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE, }; found = 0; diff --git a/arch/s390/kernel/topology.c b/arch/s390/kernel/topology.c index 8964a3f60aad..2db6fb405a9a 100644 --- a/arch/s390/kernel/topology.c +++ b/arch/s390/kernel/topology.c @@ -587,15 +587,13 @@ static int topology_ctl_handler(struct ctl_table *ctl, int write, { int enabled = topology_is_enabled(); int new_mode; - int zero = 0; - int one = 1; int rc; struct ctl_table ctl_entry = { .procname = ctl->procname, .data = &enabled, .maxlen = sizeof(int), - .extra1 = &zero, - .extra2 = &one, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE, }; rc = proc_douintvec_minmax(&ctl_entry, write, buffer, lenp, ppos); diff --git a/arch/s390/mm/init.c b/arch/s390/mm/init.c index f0bee6af3960..4e5bbe328594 100644 --- a/arch/s390/mm/init.c +++ b/arch/s390/mm/init.c @@ -273,6 +273,9 @@ int arch_add_memory(int nid, u64 start, u64 size, unsigned long size_pages = PFN_DOWN(size); int rc; + if (WARN_ON_ONCE(restrictions->altmap)) + return -EINVAL; + rc = vmem_add_mapping(start, size); if (rc) return rc; @@ -283,16 +286,15 @@ int arch_add_memory(int nid, u64 start, u64 size, return rc; } -#ifdef CONFIG_MEMORY_HOTREMOVE void arch_remove_memory(int nid, u64 start, u64 size, struct vmem_altmap *altmap) { - /* - * There is no hardware or firmware interface which could trigger a - * hot memory remove on s390. So there is nothing that needs to be - * implemented. - */ - BUG(); + unsigned long start_pfn = start >> PAGE_SHIFT; + unsigned long nr_pages = size >> PAGE_SHIFT; + struct zone *zone; + + zone = page_zone(pfn_to_page(start_pfn)); + __remove_pages(zone, start_pfn, nr_pages, altmap); + vmem_remove_mapping(start, size); } -#endif #endif /* CONFIG_MEMORY_HOTPLUG */ diff --git a/arch/sh/mm/init.c b/arch/sh/mm/init.c index 13c6a6bb5fd9..dfdbaa50946e 100644 --- a/arch/sh/mm/init.c +++ b/arch/sh/mm/init.c @@ -429,7 +429,6 @@ int memory_add_physaddr_to_nid(u64 addr) EXPORT_SYMBOL_GPL(memory_add_physaddr_to_nid); #endif -#ifdef CONFIG_MEMORY_HOTREMOVE void arch_remove_memory(int nid, u64 start, u64 size, struct vmem_altmap *altmap) { @@ -440,5 +439,4 @@ void arch_remove_memory(int nid, u64 start, u64 size, zone = page_zone(pfn_to_page(start_pfn)); __remove_pages(zone, start_pfn, nr_pages, altmap); } -#endif #endif /* CONFIG_MEMORY_HOTPLUG */ diff --git a/arch/x86/entry/vdso/vdso32-setup.c b/arch/x86/entry/vdso/vdso32-setup.c index 42d4c89f990e..240626e7f55a 100644 --- a/arch/x86/entry/vdso/vdso32-setup.c +++ b/arch/x86/entry/vdso/vdso32-setup.c @@ -65,9 +65,6 @@ subsys_initcall(sysenter_setup); /* Register vsyscall32 into the ABI table */ #include <linux/sysctl.h> -static const int zero; -static const int one = 1; - static struct ctl_table abi_table2[] = { { .procname = "vsyscall32", @@ -75,8 +72,8 @@ static struct ctl_table abi_table2[] = { .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, - .extra1 = (int *)&zero, - .extra2 = (int *)&one, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE, }, {} }; diff --git a/arch/x86/kernel/itmt.c b/arch/x86/kernel/itmt.c index 838cf8a32c49..1cb3ca9bba49 100644 --- a/arch/x86/kernel/itmt.c +++ b/arch/x86/kernel/itmt.c @@ -65,8 +65,6 @@ static int sched_itmt_update_handler(struct ctl_table *table, int write, return ret; } -static unsigned int zero; -static unsigned int one = 1; static struct ctl_table itmt_kern_table[] = { { .procname = "sched_itmt_enabled", @@ -74,8 +72,8 @@ static struct ctl_table itmt_kern_table[] = { .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = sched_itmt_update_handler, - .extra1 = &zero, - .extra2 = &one, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE, }, {} }; diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c index f265a4316179..4068abb9427f 100644 --- a/arch/x86/mm/init_32.c +++ b/arch/x86/mm/init_32.c @@ -860,7 +860,6 @@ int arch_add_memory(int nid, u64 start, u64 size, return __add_pages(nid, start_pfn, nr_pages, restrictions); } -#ifdef CONFIG_MEMORY_HOTREMOVE void arch_remove_memory(int nid, u64 start, u64 size, struct vmem_altmap *altmap) { @@ -872,7 +871,6 @@ void arch_remove_memory(int nid, u64 start, u64 size, __remove_pages(zone, start_pfn, nr_pages, altmap); } #endif -#endif int kernel_set_to_readonly __read_mostly; diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c index 08bbf648827b..a6b5c653727b 100644 --- a/arch/x86/mm/init_64.c +++ b/arch/x86/mm/init_64.c @@ -1198,7 +1198,6 @@ void __ref vmemmap_free(unsigned long start, unsigned long end, remove_pagetable(start, end, false, altmap); } -#ifdef CONFIG_MEMORY_HOTREMOVE static void __meminit kernel_physical_mapping_remove(unsigned long start, unsigned long end) { @@ -1219,7 +1218,6 @@ void __ref arch_remove_memory(int nid, u64 start, u64 size, __remove_pages(zone, start_pfn, nr_pages, altmap); kernel_physical_mapping_remove(start, start + size); } -#endif #endif /* CONFIG_MEMORY_HOTPLUG */ static struct kcore_list kcore_vsyscall; @@ -1520,7 +1518,9 @@ int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node, { int err; - if (boot_cpu_has(X86_FEATURE_PSE)) + if (end - start < PAGES_PER_SECTION * sizeof(struct page)) + err = vmemmap_populate_basepages(start, end, node); + else if (boot_cpu_has(X86_FEATURE_PSE)) err = vmemmap_populate_hugepages(start, end, node, altmap); else if (altmap) { pr_err_once("%s: no cpu support for altmap allocations\n", diff --git a/drivers/acpi/acpi_memhotplug.c b/drivers/acpi/acpi_memhotplug.c index db013dc21c02..e294f44a7850 100644 --- a/drivers/acpi/acpi_memhotplug.c +++ b/drivers/acpi/acpi_memhotplug.c @@ -155,16 +155,6 @@ static int acpi_memory_check_device(struct acpi_memory_device *mem_device) return 0; } -static unsigned long acpi_meminfo_start_pfn(struct acpi_memory_info *info) -{ - return PFN_DOWN(info->start_addr); -} - -static unsigned long acpi_meminfo_end_pfn(struct acpi_memory_info *info) -{ - return PFN_UP(info->start_addr + info->length-1); -} - static int acpi_bind_memblk(struct memory_block *mem, void *arg) { return acpi_bind_one(&mem->dev, arg); @@ -173,9 +163,8 @@ static int acpi_bind_memblk(struct memory_block *mem, void *arg) static int acpi_bind_memory_blocks(struct acpi_memory_info *info, struct acpi_device *adev) { - return walk_memory_range(acpi_meminfo_start_pfn(info), - acpi_meminfo_end_pfn(info), adev, - acpi_bind_memblk); + return walk_memory_blocks(info->start_addr, info->length, adev, + acpi_bind_memblk); } static int acpi_unbind_memblk(struct memory_block *mem, void *arg) @@ -186,8 +175,8 @@ static int acpi_unbind_memblk(struct memory_block *mem, void *arg) static void acpi_unbind_memory_blocks(struct acpi_memory_info *info) { - walk_memory_range(acpi_meminfo_start_pfn(info), - acpi_meminfo_end_pfn(info), NULL, acpi_unbind_memblk); + walk_memory_blocks(info->start_addr, info->length, NULL, + acpi_unbind_memblk); } static int acpi_memory_enable_device(struct acpi_memory_device *mem_device) diff --git a/drivers/base/firmware_loader/fallback_table.c b/drivers/base/firmware_loader/fallback_table.c index 776dd69cf5be..ba9d30b28edc 100644 --- a/drivers/base/firmware_loader/fallback_table.c +++ b/drivers/base/firmware_loader/fallback_table.c @@ -16,9 +16,6 @@ * firmware fallback configuration table */ -static unsigned int zero; -static unsigned int one = 1; - struct firmware_fallback_config fw_fallback_config = { .force_sysfs_fallback = IS_ENABLED(CONFIG_FW_LOADER_USER_HELPER_FALLBACK), .loading_timeout = 60, @@ -26,6 +23,7 @@ struct firmware_fallback_config fw_fallback_config = { }; EXPORT_SYMBOL_GPL(fw_fallback_config); +#ifdef CONFIG_SYSCTL struct ctl_table firmware_config_table[] = { { .procname = "force_sysfs_fallback", @@ -33,8 +31,8 @@ struct ctl_table firmware_config_table[] = { .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_douintvec_minmax, - .extra1 = &zero, - .extra2 = &one, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE, }, { .procname = "ignore_sysfs_fallback", @@ -42,9 +40,10 @@ struct ctl_table firmware_config_table[] = { .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_douintvec_minmax, - .extra1 = &zero, - .extra2 = &one, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE, }, { } }; EXPORT_SYMBOL_GPL(firmware_config_table); +#endif diff --git a/drivers/base/memory.c b/drivers/base/memory.c index f180427e48f4..20c39d1bcef8 100644 --- a/drivers/base/memory.c +++ b/drivers/base/memory.c |