From e04b742f74c236202b7a505c2688068969d00e65 Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Tue, 5 Mar 2019 15:42:27 -0800 Subject: kexec: export PG_offline to VMCOREINFO Right now, pages inflated as part of a balloon driver will be dumped by dump tools like makedumpfile. While XEN is able to check in the crash kernel whether a certain pfn is actuall backed by memory in the hypervisor (see xen_oldmem_pfn_is_ram) and optimize this case, dumps of other balloon inflated memory will essentially result in zero pages getting allocated by the hypervisor and the dump getting filled with this data. The allocation and reading of zero pages can directly be avoided if a dumping tool could know which pages only contain stale information not to be dumped. We now have PG_offline which can be (and already is by virtio-balloon) used for marking pages as logically offline. Follow up patches will make use of this flag also in other balloon implementations. Let's export PG_offline via PAGE_OFFLINE_MAPCOUNT_VALUE, so makedumpfile can directly skip pages that are logically offline and the content therefore stale. Please note that this is also helpful for a problem we were seeing under Hyper-V: Dumping logically offline memory (pages kept fake offline while onlining a section via online_page_callback) would under some condicions result in a kernel panic when dumping them. Link: http://lkml.kernel.org/r/20181119101616.8901-4-david@redhat.com Signed-off-by: David Hildenbrand Acked-by: Michael S. Tsirkin Acked-by: Dave Young Cc: "Kirill A. Shutemov" Cc: Baoquan He Cc: Omar Sandoval Cc: Arnd Bergmann Cc: Matthew Wilcox Cc: Michal Hocko Cc: Lianbo Jiang Cc: Borislav Petkov Cc: Kazuhito Hagio Cc: Alexander Duyck Cc: Alexey Dobriyan Cc: Boris Ostrovsky Cc: Christian Hansen Cc: David Rientjes Cc: Greg Kroah-Hartman Cc: Haiyang Zhang Cc: Jonathan Corbet Cc: Juergen Gross Cc: Julien Freche Cc: Kairui Song Cc: Konstantin Khlebnikov Cc: "K. Y. Srinivasan" Cc: Len Brown Cc: Michal Hocko Cc: Mike Rapoport Cc: Miles Chen Cc: Nadav Amit Cc: Naoya Horiguchi Cc: Pankaj gupta Cc: Pavel Machek Cc: Pavel Tatashin Cc: Rafael J. Wysocki Cc: "Rafael J. Wysocki" Cc: Stefano Stabellini Cc: Stephen Hemminger Cc: Stephen Rothwell Cc: Vitaly Kuznetsov Cc: Vlastimil Babka Cc: Xavier Deguillard Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/crash_core.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'kernel') diff --git a/kernel/crash_core.c b/kernel/crash_core.c index 933cb3e45b98..093c9f917ed0 100644 --- a/kernel/crash_core.c +++ b/kernel/crash_core.c @@ -464,6 +464,8 @@ static int __init crash_save_vmcoreinfo_init(void) VMCOREINFO_NUMBER(PAGE_BUDDY_MAPCOUNT_VALUE); #ifdef CONFIG_HUGETLB_PAGE VMCOREINFO_NUMBER(HUGETLB_PAGE_DTOR); +#define PAGE_OFFLINE_MAPCOUNT_VALUE (~PG_offline) + VMCOREINFO_NUMBER(PAGE_OFFLINE_MAPCOUNT_VALUE); #endif arch_crash_save_vmcoreinfo(); -- cgit v1.2.3-58-ga151 From 5b56db37218e6503906c6057c177a84f0a0ba551 Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Tue, 5 Mar 2019 15:42:45 -0800 Subject: PM/Hibernate: use pfn_to_online_page() Let's use pfn_to_online_page() instead of pfn_to_page() when checking for saveable pages to not save/restore offline memory sections. Link: http://lkml.kernel.org/r/20181119101616.8901-8-david@redhat.com Signed-off-by: David Hildenbrand Suggested-by: Michal Hocko Acked-by: Michal Hocko Acked-by: Pavel Machek Acked-by: Rafael J. Wysocki Cc: Len Brown Cc: Matthew Wilcox Cc: "Michael S. Tsirkin" Cc: Alexander Duyck Cc: Alexey Dobriyan Cc: Arnd Bergmann Cc: Baoquan He Cc: Borislav Petkov Cc: Boris Ostrovsky Cc: Christian Hansen Cc: Dave Young Cc: David Rientjes Cc: Greg Kroah-Hartman Cc: Haiyang Zhang Cc: Jonathan Corbet Cc: Juergen Gross Cc: Julien Freche Cc: Kairui Song Cc: Kazuhito Hagio Cc: "Kirill A. Shutemov" Cc: Konstantin Khlebnikov Cc: "K. Y. Srinivasan" Cc: Lianbo Jiang Cc: Mike Rapoport Cc: Miles Chen Cc: Nadav Amit Cc: Naoya Horiguchi Cc: Omar Sandoval Cc: Pankaj gupta Cc: Pavel Tatashin Cc: "Rafael J. Wysocki" Cc: Stefano Stabellini Cc: Stephen Hemminger Cc: Stephen Rothwell Cc: Vitaly Kuznetsov Cc: Vlastimil Babka Cc: Xavier Deguillard Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/power/snapshot.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'kernel') diff --git a/kernel/power/snapshot.c b/kernel/power/snapshot.c index 640b2034edd6..87e6dd57819f 100644 --- a/kernel/power/snapshot.c +++ b/kernel/power/snapshot.c @@ -1215,8 +1215,8 @@ static struct page *saveable_highmem_page(struct zone *zone, unsigned long pfn) if (!pfn_valid(pfn)) return NULL; - page = pfn_to_page(pfn); - if (page_zone(page) != zone) + page = pfn_to_online_page(pfn); + if (!page || page_zone(page) != zone) return NULL; BUG_ON(!PageHighMem(page)); @@ -1277,8 +1277,8 @@ static struct page *saveable_page(struct zone *zone, unsigned long pfn) if (!pfn_valid(pfn)) return NULL; - page = pfn_to_page(pfn); - if (page_zone(page) != zone) + page = pfn_to_online_page(pfn); + if (!page || page_zone(page) != zone) return NULL; BUG_ON(PageHighMem(page)); -- cgit v1.2.3-58-ga151 From abd02ac616e32d818a0478e68924beac8ba5e5d8 Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Tue, 5 Mar 2019 15:42:50 -0800 Subject: PM/Hibernate: exclude all PageOffline() pages The content of pages that are marked PG_offline is not of interest (e.g. inflated by a balloon driver), let's skip these pages. In saveable_highmem_page(), move the PageReserved() check to a new check along with the PageOffline() check to separate it from the swsusp checks. [david@redhat.com: v2] Link: http://lkml.kernel.org/r/20181122100627.5189-9-david@redhat.com Link: http://lkml.kernel.org/r/20181119101616.8901-9-david@redhat.com Signed-off-by: David Hildenbrand Acked-by: Pavel Machek Acked-by: Rafael J. Wysocki Cc: Pavel Machek Cc: Len Brown Cc: Matthew Wilcox Cc: Michal Hocko Cc: "Michael S. Tsirkin" Cc: Alexander Duyck Cc: Alexey Dobriyan Cc: Arnd Bergmann Cc: Baoquan He Cc: Borislav Petkov Cc: Boris Ostrovsky Cc: Christian Hansen Cc: Dave Young Cc: David Rientjes Cc: Greg Kroah-Hartman Cc: Haiyang Zhang Cc: Jonathan Corbet Cc: Juergen Gross Cc: Julien Freche Cc: Kairui Song Cc: Kazuhito Hagio Cc: "Kirill A. Shutemov" Cc: Konstantin Khlebnikov Cc: "K. Y. Srinivasan" Cc: Lianbo Jiang Cc: Michal Hocko Cc: Mike Rapoport Cc: Miles Chen Cc: Nadav Amit Cc: Naoya Horiguchi Cc: Omar Sandoval Cc: Pankaj gupta Cc: Pavel Tatashin Cc: "Rafael J. Wysocki" Cc: Stefano Stabellini Cc: Stephen Hemminger Cc: Stephen Rothwell Cc: Vitaly Kuznetsov Cc: Vlastimil Babka Cc: Xavier Deguillard Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/power/snapshot.c | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) (limited to 'kernel') diff --git a/kernel/power/snapshot.c b/kernel/power/snapshot.c index 87e6dd57819f..4802b039b89f 100644 --- a/kernel/power/snapshot.c +++ b/kernel/power/snapshot.c @@ -1221,8 +1221,10 @@ static struct page *saveable_highmem_page(struct zone *zone, unsigned long pfn) BUG_ON(!PageHighMem(page)); - if (swsusp_page_is_forbidden(page) || swsusp_page_is_free(page) || - PageReserved(page)) + if (swsusp_page_is_forbidden(page) || swsusp_page_is_free(page)) + return NULL; + + if (PageReserved(page) || PageOffline(page)) return NULL; if (page_is_guard(page)) @@ -1286,6 +1288,9 @@ static struct page *saveable_page(struct zone *zone, unsigned long pfn) if (swsusp_page_is_forbidden(page) || swsusp_page_is_free(page)) return NULL; + if (PageOffline(page)) + return NULL; + if (PageReserved(page) && (!kernel_page_present(page) || pfn_is_nosave(pfn))) return NULL; -- cgit v1.2.3-58-ga151 From 98fa15f34cb379864757670b8e8743b21456a20e Mon Sep 17 00:00:00 2001 From: Anshuman Khandual Date: Tue, 5 Mar 2019 15:42:58 -0800 Subject: mm: replace all open encodings for NUMA_NO_NODE Patch series "Replace all open encodings for NUMA_NO_NODE", v3. All these places for replacement were found by running the following grep patterns on the entire kernel code. Please let me know if this might have missed some instances. This might also have replaced some false positives. I will appreciate suggestions, inputs and review. 1. git grep "nid == -1" 2. git grep "node == -1" 3. git grep "nid = -1" 4. git grep "node = -1" This patch (of 2): At present there are multiple places where invalid node number is encoded as -1. Even though implicitly understood it is always better to have macros in there. Replace these open encodings for an invalid node number with the global macro NUMA_NO_NODE. This helps remove NUMA related assumptions like 'invalid node' from various places redirecting them to a common definition. Link: http://lkml.kernel.org/r/1545127933-10711-2-git-send-email-anshuman.khandual@arm.com Signed-off-by: Anshuman Khandual Reviewed-by: David Hildenbrand Acked-by: Jeff Kirsher [ixgbe] Acked-by: Jens Axboe [mtip32xx] Acked-by: Vinod Koul [dmaengine.c] Acked-by: Michael Ellerman [powerpc] Acked-by: Doug Ledford [drivers/infiniband] Cc: Joseph Qi Cc: Hans Verkuil Cc: Stephen Rothwell Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/alpha/include/asm/topology.h | 3 ++- arch/ia64/kernel/numa.c | 2 +- arch/ia64/mm/discontig.c | 6 +++--- arch/powerpc/include/asm/pci-bridge.h | 3 ++- arch/powerpc/kernel/paca.c | 3 ++- arch/powerpc/kernel/pci-common.c | 3 ++- arch/powerpc/mm/numa.c | 14 +++++++------- arch/powerpc/platforms/powernv/memtrace.c | 5 +++-- arch/sparc/kernel/pci_fire.c | 3 ++- arch/sparc/kernel/pci_schizo.c | 3 ++- arch/sparc/kernel/psycho_common.c | 3 ++- arch/sparc/kernel/sbus.c | 3 ++- arch/sparc/mm/init_64.c | 6 +++--- arch/x86/include/asm/pci.h | 3 ++- arch/x86/kernel/apic/x2apic_uv_x.c | 7 ++++--- arch/x86/kernel/smpboot.c | 3 ++- drivers/block/mtip32xx/mtip32xx.c | 5 +++-- drivers/dma/dmaengine.c | 4 +++- drivers/infiniband/hw/hfi1/affinity.c | 3 ++- drivers/infiniband/hw/hfi1/init.c | 3 ++- drivers/iommu/dmar.c | 5 +++-- drivers/iommu/intel-iommu.c | 3 ++- drivers/misc/sgi-xp/xpc_uv.c | 3 ++- drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 5 +++-- include/linux/device.h | 2 +- init/init_task.c | 3 ++- kernel/kthread.c | 3 ++- kernel/sched/fair.c | 15 ++++++++------- lib/cpumask.c | 3 ++- mm/huge_memory.c | 13 +++++++------ mm/hugetlb.c | 3 ++- mm/ksm.c | 2 +- mm/memory.c | 7 ++++--- mm/memory_hotplug.c | 12 ++++++------ mm/mempolicy.c | 2 +- mm/page_alloc.c | 4 ++-- mm/page_ext.c | 2 +- net/core/pktgen.c | 3 ++- net/qrtr/qrtr.c | 3 ++- 39 files changed, 104 insertions(+), 74 deletions(-) (limited to 'kernel') diff --git a/arch/alpha/include/asm/topology.h b/arch/alpha/include/asm/topology.h index e6e13a85796a..5a77a40567fa 100644 --- a/arch/alpha/include/asm/topology.h +++ b/arch/alpha/include/asm/topology.h @@ -4,6 +4,7 @@ #include #include +#include #include #ifdef CONFIG_NUMA @@ -29,7 +30,7 @@ static const struct cpumask *cpumask_of_node(int node) { int cpu; - if (node == -1) + if (node == NUMA_NO_NODE) return cpu_all_mask; cpumask_clear(&node_to_cpumask_map[node]); diff --git a/arch/ia64/kernel/numa.c b/arch/ia64/kernel/numa.c index 92c376279c6d..1315da6c7aeb 100644 --- a/arch/ia64/kernel/numa.c +++ b/arch/ia64/kernel/numa.c @@ -74,7 +74,7 @@ void __init build_cpu_to_node_map(void) cpumask_clear(&node_to_cpu_mask[node]); for_each_possible_early_cpu(cpu) { - node = -1; + node = NUMA_NO_NODE; for (i = 0; i < NR_CPUS; ++i) if (cpu_physical_id(cpu) == node_cpuid[i].phys_id) { node = node_cpuid[i].nid; diff --git a/arch/ia64/mm/discontig.c b/arch/ia64/mm/discontig.c index 8a965784340c..f9c36750c6a4 100644 --- a/arch/ia64/mm/discontig.c +++ b/arch/ia64/mm/discontig.c @@ -227,7 +227,7 @@ void __init setup_per_cpu_areas(void) * CPUs are put into groups according to node. Walk cpu_map * and create new groups at node boundaries. */ - prev_node = -1; + prev_node = NUMA_NO_NODE; ai->nr_groups = 0; for (unit = 0; unit < nr_units; unit++) { cpu = cpu_map[unit]; @@ -435,7 +435,7 @@ static void __init *memory_less_node_alloc(int nid, unsigned long pernodesize) { void *ptr = NULL; u8 best = 0xff; - int bestnode = -1, node, anynode = 0; + int bestnode = NUMA_NO_NODE, node, anynode = 0; for_each_online_node(node) { if (node_isset(node, memory_less_mask)) @@ -447,7 +447,7 @@ static void __init *memory_less_node_alloc(int nid, unsigned long pernodesize) anynode = node; } - if (bestnode == -1) + if (bestnode == NUMA_NO_NODE) bestnode = anynode; ptr = memblock_alloc_try_nid(pernodesize, PERCPU_PAGE_SIZE, diff --git a/arch/powerpc/include/asm/pci-bridge.h b/arch/powerpc/include/asm/pci-bridge.h index aee4fcc24990..77fc21278fa2 100644 --- a/arch/powerpc/include/asm/pci-bridge.h +++ b/arch/powerpc/include/asm/pci-bridge.h @@ -10,6 +10,7 @@ #include #include #include +#include struct device_node; @@ -265,7 +266,7 @@ extern int pcibios_map_io_space(struct pci_bus *bus); #ifdef CONFIG_NUMA #define PHB_SET_NODE(PHB, NODE) ((PHB)->node = (NODE)) #else -#define PHB_SET_NODE(PHB, NODE) ((PHB)->node = -1) +#define PHB_SET_NODE(PHB, NODE) ((PHB)->node = NUMA_NO_NODE) #endif #endif /* CONFIG_PPC64 */ diff --git a/arch/powerpc/kernel/paca.c b/arch/powerpc/kernel/paca.c index 913bfca09c4f..b8480127793d 100644 --- a/arch/powerpc/kernel/paca.c +++ b/arch/powerpc/kernel/paca.c @@ -11,6 +11,7 @@ #include #include #include +#include #include #include @@ -36,7 +37,7 @@ static void *__init alloc_paca_data(unsigned long size, unsigned long align, * which will put its paca in the right place. */ if (cpu == boot_cpuid) { - nid = -1; + nid = NUMA_NO_NODE; memblock_set_bottom_up(true); } else { nid = early_cpu_to_node(cpu); diff --git a/arch/powerpc/kernel/pci-common.c b/arch/powerpc/kernel/pci-common.c index 88e4f69a09e5..4538e8ddde80 100644 --- a/arch/powerpc/kernel/pci-common.c +++ b/arch/powerpc/kernel/pci-common.c @@ -32,6 +32,7 @@ #include #include #include +#include #include #include @@ -132,7 +133,7 @@ struct pci_controller *pcibios_alloc_controller(struct device_node *dev) int nid = of_node_to_nid(dev); if (nid < 0 || !node_online(nid)) - nid = -1; + nid = NUMA_NO_NODE; PHB_SET_NODE(phb, nid); } diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c index 87f0dd004295..270cefb75cca 100644 --- a/arch/powerpc/mm/numa.c +++ b/arch/powerpc/mm/numa.c @@ -215,7 +215,7 @@ static void initialize_distance_lookup_table(int nid, */ static int associativity_to_nid(const __be32 *associativity) { - int nid = -1; + int nid = NUMA_NO_NODE; if (min_common_depth == -1) goto out; @@ -225,7 +225,7 @@ static int associativity_to_nid(const __be32 *associativity) /* POWER4 LPAR uses 0xffff as invalid node */ if (nid == 0xffff || nid >= MAX_NUMNODES) - nid = -1; + nid = NUMA_NO_NODE; if (nid > 0 && of_read_number(associativity, 1) >= distance_ref_points_depth) { @@ -244,7 +244,7 @@ out: */ static int of_node_to_nid_single(struct device_node *device) { - int nid = -1; + int nid = NUMA_NO_NODE; const __be32 *tmp; tmp = of_get_associativity(device); @@ -256,7 +256,7 @@ static int of_node_to_nid_single(struct device_node *device) /* Walk the device tree upwards, looking for an associativity id */ int of_node_to_nid(struct device_node *device) { - int nid = -1; + int nid = NUMA_NO_NODE; of_node_get(device); while (device) { @@ -454,7 +454,7 @@ static int of_drconf_to_nid_single(struct drmem_lmb *lmb) */ static int numa_setup_cpu(unsigned long lcpu) { - int nid = -1; + int nid = NUMA_NO_NODE; struct device_node *cpu; /* @@ -930,7 +930,7 @@ static int hot_add_drconf_scn_to_nid(unsigned long scn_addr) { struct drmem_lmb *lmb; unsigned long lmb_size; - int nid = -1; + int nid = NUMA_NO_NODE; lmb_size = drmem_lmb_size(); @@ -960,7 +960,7 @@ static int hot_add_drconf_scn_to_nid(unsigned long scn_addr) static int hot_add_node_scn_to_nid(unsigned long scn_addr) { struct device_node *memory; - int nid = -1; + int nid = NUMA_NO_NODE; for_each_node_by_type(memory, "memory") { unsigned long start, size; diff --git a/arch/powerpc/platforms/powernv/memtrace.c b/arch/powerpc/platforms/powernv/memtrace.c index 84d038ed3882..248a38ad25c7 100644 --- a/arch/powerpc/platforms/powernv/memtrace.c +++ b/arch/powerpc/platforms/powernv/memtrace.c @@ -20,6 +20,7 @@ #include #include #include +#include #include #include @@ -223,7 +224,7 @@ static int memtrace_online(void) ent = &memtrace_array[i]; /* We have onlined this chunk previously */ - if (ent->nid == -1) + if (ent->nid == NUMA_NO_NODE) continue; /* Remove from io mappings */ @@ -257,7 +258,7 @@ static int memtrace_online(void) */ debugfs_remove_recursive(ent->dir); pr_info("Added trace memory back to node %d\n", ent->nid); - ent->size = ent->start = ent->nid = -1; + ent->size = ent->start = ent->nid = NUMA_NO_NODE; } if (ret) return ret; diff --git a/arch/sparc/kernel/pci_fire.c b/arch/sparc/kernel/pci_fire.c index be71ae086622..0ca08d455e80 100644 --- a/arch/sparc/kernel/pci_fire.c +++ b/arch/sparc/kernel/pci_fire.c @@ -11,6 +11,7 @@ #include #include #include +#include #include #include @@ -416,7 +417,7 @@ static int pci_fire_pbm_init(struct pci_pbm_info *pbm, struct device_node *dp = op->dev.of_node; int err; - pbm->numa_node = -1; + pbm->numa_node = NUMA_NO_NODE; pbm->pci_ops = &sun4u_pci_ops; pbm->config_space_reg_bits = 12; diff --git a/arch/sparc/kernel/pci_schizo.c b/arch/sparc/kernel/pci_schizo.c index 934b97c72f7c..421aba00e6b0 100644 --- a/arch/sparc/kernel/pci_schizo.c +++ b/arch/sparc/kernel/pci_schizo.c @@ -12,6 +12,7 @@ #include #include #include +#include #include #include @@ -1347,7 +1348,7 @@ static int schizo_pbm_init(struct pci_pbm_info *pbm, pbm->next = pci_pbm_root; pci_pbm_root = pbm; - pbm->numa_node = -1; + pbm->numa_node = NUMA_NO_NODE; pbm->pci_ops = &sun4u_pci_ops; pbm->config_space_reg_bits = 8; diff --git a/arch/sparc/kernel/psycho_common.c b/arch/sparc/kernel/psycho_common.c index 81aa91e5c0e6..e90bcb6bad7f 100644 --- a/arch/sparc/kernel/psycho_common.c +++ b/arch/sparc/kernel/psycho_common.c @@ -5,6 +5,7 @@ */ #include #include +#include #include @@ -454,7 +455,7 @@ void psycho_pbm_init_common(struct pci_pbm_info *pbm, struct platform_device *op struct device_node *dp = op->dev.of_node; pbm->name = dp->full_name; - pbm->numa_node = -1; + pbm->numa_node = NUMA_NO_NODE; pbm->chip_type = chip_type; pbm->chip_version = of_getintprop_default(dp, "version#", 0); pbm->chip_revision = of_getintprop_default(dp, "module-revision#", 0); diff --git a/arch/sparc/kernel/sbus.c b/arch/sparc/kernel/sbus.c index 41c5deb581b8..32141e1006c4 100644 --- a/arch/sparc/kernel/sbus.c +++ b/arch/sparc/kernel/sbus.c @@ -15,6 +15,7 @@ #include #include #include +#include #include #include @@ -561,7 +562,7 @@ static void __init sbus_iommu_init(struct platform_device *op) op->dev.archdata.iommu = iommu; op->dev.archdata.stc = strbuf; - op->dev.archdata.numa_node = -1; + op->dev.archdata.numa_node = NUMA_NO_NODE; reg_base = regs + SYSIO_IOMMUREG_BASE; iommu->iommu_control = reg_base + IOMMU_CONTROL; diff --git a/arch/sparc/mm/init_64.c b/arch/sparc/mm/init_64.c index b4221d3727d0..9e6bd868ba6f 100644 --- a/arch/sparc/mm/init_64.c +++ b/arch/sparc/mm/init_64.c @@ -976,13 +976,13 @@ static u64 __init memblock_nid_range_sun4u(u64 start, u64 end, int *nid) { int prev_nid, new_nid; - prev_nid = -1; + prev_nid = NUMA_NO_NODE; for ( ; start < end; start += PAGE_SIZE) { for (new_nid = 0; new_nid < num_node_masks; new_nid++) { struct node_mem_mask *p = &node_masks[new_nid]; if ((start & p->mask) == p->match) { - if (prev_nid == -1) + if (prev_nid == NUMA_NO_NODE) prev_nid = new_nid; break; } @@ -1208,7 +1208,7 @@ int of_node_to_nid(struct device_node *dp) md = mdesc_grab(); count = 0; - nid = -1; + nid = NUMA_NO_NODE; mdesc_for_each_node_by_name(md, grp, "group") { if (!scan_arcs_for_cfg_handle(md, grp, cfg_handle)) { nid = count; diff --git a/arch/x86/include/asm/pci.h b/arch/x86/include/asm/pci.h index 662963681ea6..e662f987dfa2 100644 --- a/arch/x86/include/asm/pci.h +++ b/arch/x86/include/asm/pci.h @@ -7,6 +7,7 @@ #include #include #include +#include #include #include #include @@ -141,7 +142,7 @@ cpumask_of_pcibus(const struct pci_bus *bus) int node; node = __pcibus_to_node(bus); - return (node == -1) ? cpu_online_mask : + return (node == NUMA_NO_NODE) ? cpu_online_mask : cpumask_of_node(node); } #endif diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c index a555da094157..1e225528f0d7 100644 --- a/arch/x86/kernel/apic/x2apic_uv_x.c +++ b/arch/x86/kernel/apic/x2apic_uv_x.c @@ -27,6 +27,7 @@ #include #include #include +#include #include #include @@ -1390,7 +1391,7 @@ static void __init build_socket_tables(void) } /* Set socket -> node values: */ - lnid = -1; + lnid = NUMA_NO_NODE; for_each_present_cpu(cpu) { int nid = cpu_to_node(cpu); int apicid, sockid; @@ -1521,7 +1522,7 @@ static void __init uv_system_init_hub(void) new_hub->pnode = 0xffff; new_hub->numa_blade_id = uv_node_to_blade_id(nodeid); - new_hub->memory_nid = -1; + new_hub->memory_nid = NUMA_NO_NODE; new_hub->nr_possible_cpus = 0; new_hub->nr_online_cpus = 0; } @@ -1538,7 +1539,7 @@ static void __init uv_system_init_hub(void) uv_cpu_info_per(cpu)->p_uv_hub_info = uv_hub_info_list(nodeid); uv_cpu_info_per(cpu)->blade_cpu_id = uv_cpu_hub_info(cpu)->nr_possible_cpus++; - if (uv_cpu_hub_info(cpu)->memory_nid == -1) + if (uv_cpu_hub_info(cpu)->memory_nid == NUMA_NO_NODE) uv_cpu_hub_info(cpu)->memory_nid = cpu_to_node(cpu); /* Init memoryless node: */ diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index ccd1f2a8e557..c91ff9f9fe8a 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -56,6 +56,7 @@ #include #include #include +#include #include #include @@ -841,7 +842,7 @@ wakeup_secondary_cpu_via_init(int phys_apicid, unsigned long start_eip) /* reduce the number of lines printed when booting a large cpu count system */ static void announce_cpu(int cpu, int apicid) { - static int current_node = -1; + static int current_node = NUMA_NO_NODE; int node = early_cpu_to_node(cpu); static int width, node_width; diff --git a/drivers/block/mtip32xx/mtip32xx.c b/drivers/block/mtip32xx/mtip32xx.c index 88e8440e75c3..2f3ee4d6af82 100644 --- a/drivers/block/mtip32xx/mtip32xx.c +++ b/drivers/block/mtip32xx/mtip32xx.c @@ -40,6 +40,7 @@ #include #include #include +#include #include "mtip32xx.h" #define HW_CMD_SLOT_SZ (MTIP_MAX_COMMAND_SLOTS * 32) @@ -4018,9 +4019,9 @@ static int get_least_used_cpu_on_node(int node) /* Helper for selecting a node in round robin mode */ static inline int mtip_get_next_rr_node(void) { - static int next_node = -1; + static int next_node = NUMA_NO_NODE; - if (next_node == -1) { + if (next_node == NUMA_NO_NODE) { next_node = first_online_node; return next_node; } diff --git a/drivers/dma/dmaengine.c b/drivers/dma/dmaengine.c index f1a441ab395d..3a11b1092e80 100644 --- a/drivers/dma/dmaengine.c +++ b/drivers/dma/dmaengine.c @@ -63,6 +63,7 @@ #include #include #include +#include static DEFINE_MUTEX(dma_list_mutex); static DEFINE_IDA(dma_ida); @@ -386,7 +387,8 @@ EXPORT_SYMBOL(dma_issue_pending_all); static bool dma_chan_is_local(struct dma_chan *chan, int cpu) { int node = dev_to_node(chan->device->dev); - return node == -1 || cpumask_test_cpu(cpu, cpumask_of_node(node)); + return node == NUMA_NO_NODE || + cpumask_test_cpu(cpu, cpumask_of_node(node)); } /** diff --git a/drivers/infiniband/hw/hfi1/affinity.c b/drivers/infiniband/hw/hfi1/affinity.c index 2baf38cc1e23..4fe662c3bbc1 100644 --- a/drivers/infiniband/hw/hfi1/affinity.c +++ b/drivers/infiniband/hw/hfi1/affinity.c @@ -48,6 +48,7 @@ #include #include #include +#include #include "hfi.h" #include "affinity.h" @@ -777,7 +778,7 @@ void hfi1_dev_affinity_clean_up(struct hfi1_devdata *dd) _dev_comp_vect_cpu_mask_clean_up(dd, entry); unlock: mutex_unlock(&node_affinity.lock); - dd->node = -1; + dd->node = NUMA_NO_NODE; } /* diff --git a/drivers/infiniband/hw/hfi1/init.c b/drivers/infiniband/hw/hfi1/init.c index 7835eb52e7c5..441b06e2a154 100644 --- a/drivers/infiniband/hw/hfi1/init.c +++ b/drivers/infiniband/hw/hfi1/init.c @@ -54,6 +54,7 @@ #include #include #include +#include #include #include "hfi.h" @@ -1303,7 +1304,7 @@ static struct hfi1_devdata *hfi1_alloc_devdata(struct pci_dev *pdev, dd->unit = ret; list_add(&dd->list, &hfi1_dev_list); } - dd->node = -1; + dd->node = NUMA_NO_NODE; spin_unlock_irqrestore(&hfi1_devs_lock, flags); idr_preload_end(); diff --git a/drivers/iommu/dmar.c b/drivers/iommu/dmar.c index 58dc70bffd5b..9c49300e9fb7 100644 --- a/drivers/iommu/dmar.c +++ b/drivers/iommu/dmar.c @@ -39,6 +39,7 @@ #include #include #include +#include #include #include @@ -477,7 +478,7 @@ static int dmar_parse_one_rhsa(struct acpi_dmar_header *header, void *arg) int node = acpi_map_pxm_to_node(rhsa->proximity_domain); if (!node_online(node)) - node = -1; + node = NUMA_NO_NODE; drhd->iommu->node = node; return 0; } @@ -1062,7 +1063,7 @@ static int alloc_iommu(struct dmar_drhd_unit *drhd) iommu->msagaw = msagaw; iommu->segment = drhd->segment; - iommu->node = -1; + iommu->node = NUMA_NO_NODE; ver = readl(iommu->reg + DMAR_VER_REG); pr_info("%s: reg_base_addr %llx ver %d:%d cap %llx ecap %llx\n", diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c index 78188bf7e90d..39a33dec4d0b 100644 --- a/drivers/iommu/intel-iommu.c +++ b/drivers/iommu/intel-iommu.c @@ -47,6 +47,7 @@ #include #include #include +#include #include #include #include @@ -1716,7 +1717,7 @@ static struct dmar_domain *alloc_domain(int flags) return NULL; memset(domain, 0, sizeof(*domain)); - domain->nid = -1; + domain->nid = NUMA_NO_NODE; domain->flags = flags; domain->has_iotlb_device = false; INIT_LIST_HEAD(&domain->devices); diff --git a/drivers/misc/sgi-xp/xpc_uv.c b/drivers/misc/sgi-xp/xpc_uv.c index 0441abe87880..9e443df44b3b 100644 --- a/drivers/misc/sgi-xp/xpc_uv.c +++ b/drivers/misc/sgi-xp/xpc_uv.c @@ -22,6 +22,7 @@ #include #include #include +#include #include #if defined CONFIG_X86_64 #include @@ -61,7 +62,7 @@ static struct xpc_heartbeat_uv *xpc_heartbeat_uv; XPC_NOTIFY_MSG_SIZE_UV) #define XPC_NOTIFY_IRQ_NAME "xpc_notify" -static int xpc_mq_node = -1; +static int xpc_mq_node = NUMA_NO_NODE; static struct xpc_gru_mq_uv *xpc_activate_mq_uv; static struct xpc_gru_mq_uv *xpc_notify_mq_uv; diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index a4e7584a50cb..e100054a3765 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -27,6 +27,7 @@ #include #include #include +#include #include #include #include @@ -6418,7 +6419,7 @@ int ixgbe_setup_tx_resources(struct ixgbe_ring *tx_ring) { struct device *dev = tx_ring->dev; int orig_node = dev_to_node(dev); - int ring_node = -1; + int ring_node = NUMA_NO_NODE; int size; size = sizeof(struct ixgbe_tx_buffer) * tx_ring->count; @@ -6512,7 +6513,7 @@ int ixgbe_setup_rx_resources(struct ixgbe_adapter *adapter, { struct device *dev = rx_ring->dev; int orig_node = dev_to_node(dev); - int ring_node = -1; + int ring_node = NUMA_NO_NODE; int size; size = sizeof(struct ixgbe_rx_buffer) * rx_ring->count; diff --git a/include/linux/device.h b/include/linux/device.h index 6cb4640b6160..4d2f13e8c540 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -1095,7 +1095,7 @@ static inline void set_dev_node(struct device *dev, int node) #else static inline int dev_to_node(struct device *dev) { - return -1; + return NUMA_NO_NODE; } static inline void set_dev_node(struct device *dev, int node) { diff --git a/init/init_task.c b/init/init_task.c index 5aebe3be4d7c..26131e73aa6d 100644 --- a/init/init_task.c +++ b/init/init_task.c @@ -10,6 +10,7 @@ #include #include #include +#include #include #include @@ -154,7 +155,7 @@ struct task_struct init_task .vtime.state = VTIME_SYS, #endif #ifdef CONFIG_NUMA_BALANCING - .numa_preferred_nid = -1, + .numa_preferred_nid = NUMA_NO_NODE, .numa_group = NULL, .numa_faults = NULL, #endif diff --git a/kernel/kthread.c b/kernel/kthread.c index 087d18d771b5..ebebbcf3c5de 100644 --- a/kernel/kthread.c +++ b/kernel/kthread.c @@ -20,6 +20,7 @@ #include #include #include +#include #include static DEFINE_SPINLOCK(kthread_create_lock); @@ -675,7 +676,7 @@ __kthread_create_worker(int cpu, unsigned int flags, { struct kthread_worker *worker; struct task_struct *task; - int node = -1; + int node = NUMA_NO_NODE; worker = kzalloc(sizeof(*worker), GFP_KERNEL); if (!worker) diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 310d0637fe4b..0e6a0ef129c5 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -1160,7 +1160,7 @@ void init_numa_balancing(unsigned long clone_flags, struct task_struct *p) /* New address space, reset the preferred nid */ if (!(clone_flags & CLONE_VM)) { - p->numa_preferred_nid = -1; + p->numa_preferred_nid = NUMA_NO_NODE; return; } @@ -1180,13 +1180,13 @@ void init_numa_balancing(unsigned long clone_flags, struct task_struct *p) static void account_numa_enqueue(struct rq *rq, struct task_struct *p) { - rq->nr_numa_running += (p->numa_preferred_nid != -1); + rq->nr_numa_running += (p->numa_preferred_nid != NUMA_NO_NODE); rq->nr_preferred_running += (p->numa_preferred_nid == task_node(p)); } static void account_numa_dequeue(struct rq *rq, struct task_struct *p) { - rq->nr_numa_running -= (p->numa_preferred_nid != -1); + rq->nr_numa_running -= (p->numa_preferred_nid != NUMA_NO_NODE); rq->nr_preferred_running -= (p->numa_preferred_nid == task_node(p)); } @@ -1400,7 +1400,7 @@ bool should_numa_migrate_memory(struct task_struct *p, struct page * page, * two full passes of the "multi-stage node selection" test that is * executed below. */ - if ((p->numa_preferred_nid == -1 || p->numa_scan_seq <= 4) && + if ((p->numa_preferred_nid == NUMA_NO_NODE || p->numa_scan_seq <= 4) && (cpupid_pid_unset(last_cpupid) || cpupid_match_pid(p, last_cpupid))) return true; @@ -1848,7 +1848,7 @@ static void numa_migrate_preferred(struct task_struct *p) unsigned long interval = HZ; /* This task has no NUMA fault statistics yet */ - if (unlikely(p->numa_preferred_nid == -1 || !p->numa_faults)) + if (unlikely(p->numa_preferred_nid == NUMA_NO_NODE || !p->numa_faults)) return; /* Periodically retry migrating the task to the preferred node */ @@ -2095,7 +2095,7 @@ static int preferred_group_nid(struct task_struct *p, int nid) static void task_numa_placement(struct task_struct *p) { - int seq, nid, max_nid = -1; + int seq, nid, max_nid = NUMA_NO_NODE; unsigned long max_faults = 0; unsigned long fault_types[2] = { 0, 0 }; unsigned long total_faults; @@ -2638,7 +2638,8 @@ static void update_scan_period(struct task_struct *p, int new_cpu) * the preferred node. */ if (dst_nid == p->numa_preferred_nid || - (p->numa_preferred_nid != -1 && src_nid != p->numa_preferred_nid)) + (p->numa_preferred_nid != NUMA_NO_NODE && + src_nid != p->numa_preferred_nid)) return; } diff --git a/lib/cpumask.c b/lib/cpumask.c index 8d666ab84b5c..087a3e9a0202 100644 --- a/lib/cpumask.c +++ b/lib/cpumask.c @@ -5,6 +5,7 @@ #include #include #include +#include /** * cpumask_next - get the next cpu in a cpumask @@ -206,7 +207,7 @@ unsigned int cpumask_local_spread(unsigned int i, int node) /* Wrap: we always want a cpu. */ i %= num_online_cpus(); - if (node == -1) { + if (node == NUMA_NO_NODE) { for_each_cpu(cpu, cpu_online_mask) if (i-- == 0) return cpu; diff --git a/mm/huge_memory.c b/mm/huge_memory.c index faf357eaf0ce..d066f7ca1ee8 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -33,6 +33,7 @@ #include #include #include +#include #include #include @@ -1475,7 +1476,7 @@ vm_fault_t do_huge_pmd_numa_page(struct vm_fault *vmf, pmd_t pmd) struct anon_vma *anon_vma = NULL; struct page *page; unsigned long haddr = vmf->address & HPAGE_PMD_MASK; - int page_nid = -1, this_nid = numa_node_id(); + int page_nid = NUMA_NO_NODE, this_nid = numa_node_id(); int target_nid, last_cpupid = -1; bool page_locked; bool migrated = false; @@ -1520,7 +1521,7 @@ vm_fault_t do_huge_pmd_numa_page(struct vm_fault *vmf, pmd_t pmd) */ page_locked = trylock_page(page); target_nid = mpol_misplaced(page, vma, haddr); - if (target_nid == -1) { + if (target_nid == NUMA_NO_NODE) { /* If the page was locked, there are no parallel migrations */ if (page_locked) goto clear_pmdnuma; @@ -1528,7 +1529,7 @@ vm_fault_t do_huge_pmd_numa_page(struct vm_fault *vmf, pmd_t pmd) /* Migration could have started since the pmd_trans_migrating check */ if (!page_locked) { - page_nid = -1; + page_nid = NUMA_NO_NODE; if (!get_page_unless_zero(page)) goto out_unlock; spin_unlock(vmf->ptl); @@ -1549,14 +1550,14 @@ vm_fault_t do_huge_pmd_numa_page(struct vm_fault *vmf, pmd_t pmd) if (unlikely(!pmd_same(pmd, *vmf->pmd))) { unlock_page(page); put_page(page); - page_nid = -1; + page_nid = NUMA_NO_NODE; goto out_unlock; } /* Bail if we fail to protect against THP splits for any reason */ if (unlikely(!anon_vma)) { put_page(page); - page_nid = -1; + page_nid = NUMA_NO_NODE; goto clear_pmdnuma; } @@ -1618,7 +1619,7 @@ out: if (anon_vma) page_unlock_anon_vma_read(anon_vma); - if (page_nid != -1) + if (page_nid != NUMA_NO_NODE) task_numa_fault(last_cpupid, page_nid, HPAGE_PMD_NR, flags); diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 8dfdffc34a99..3c504fa6b460 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -25,6 +25,7 @@ #include #include #include +#include #include #include @@ -887,7 +888,7 @@ static struct page *dequeue_huge_page_nodemask(struct hstate *h, gfp_t gfp_mask, struct zonelist *zonelist; struct zone *zone; struct zoneref *z; - int node = -1; + int node = NUMA_NO_NODE; zonelist = node_zonelist(nid, gfp_mask); diff --git a/mm/ksm.c b/mm/ksm.c index 6c48ad13b4c9..fd2db6a74d3c 100644 --- a/mm/ksm.c +++ b/mm/ksm.c @@ -598,7 +598,7 @@ static struct stable_node *alloc_stable_node_chain(struct stable_node *dup, chain->chain_prune_time = jiffies; chain->rmap_hlist_len = STABLE_NODE_CHAIN; #if defined (CONFIG_DEBUG_VM) && defined(CONFIG_NUMA) - chain->nid = -1; /* debug */ + chain->nid = NUMA_NO_NODE; /* debug */ #endif ksm_stable_node_chains++; diff --git a/mm/memory.c b/mm/memory.c index e11ca9dd823f..eb40f32295d2 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -69,6 +69,7 @@ #include #include #include +#include #include #include @@ -3586,7 +3587,7 @@ static vm_fault_t do_numa_page(struct vm_fault *vmf) { struct vm_area_struct *vma = vmf->vma; struct page *page = NULL; - int page_nid = -1; + int page_nid = NUMA_NO_NODE; int last_cpupid; int target_nid; bool migrated = false; @@ -3653,7 +3654,7 @@ static vm_fault_t do_numa_page(struct vm_fault *vmf) target_nid = numa_migrate_prep(page, vma, vmf->address, page_nid, &flags); pte_unmap_unlock(vmf->pte, vmf->ptl); - if (target_nid == -1) { + if (target_nid == NUMA_NO_NODE) { put_page(page); goto out; } @@ -3667,7 +3668,7 @@ static vm_fault_t do_numa_page(struct vm_fault *vmf) flags |= TNF_MIGRATE_FAIL; out: - if (page_nid != -1) + if (page_nid != NUMA_NO_NODE) task_numa_fault(last_cpupid, page_nid, 1, flags); return 0; } diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index 4f07c8ddfdd7..b3d3c64d15df 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -702,9 +702,9 @@ static void node_states_check_changes_online(unsigned long nr_pages, { int nid = zone_to_nid(zone); - arg->status_change_nid = -1; - arg->status_change_nid_normal = -1; - arg->status_change_nid_high = -1; + arg->status_change_nid = NUMA_NO_NODE; + arg->status_change_nid_normal = NUMA_NO_NODE; + arg->status_change_nid_high = NUMA_NO_NODE; if (!node_state(nid, N_MEMORY)) arg->status_change_nid = nid; @@ -1509,9 +1509,9 @@ static void node_states_check_changes_offline(unsigned long nr_pages, unsigned long present_pages = 0; enum zone_type zt; - arg->status_change_nid = -1; - arg->status_change_nid_normal = -1; - arg->status_change_nid_high = -1; + arg->status_change_nid = NUMA_NO_NODE; + arg->status_change_nid_normal = NUMA_NO_NODE; + arg->status_change_nid_high = NUMA_NO_NODE; /* * Check whether node_states[N_NORMAL_MEMORY] will be changed. diff --git a/mm/mempolicy.c b/mm/mempolicy.c index ee2bce59d2bf..76e7e4bc3335 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -2304,7 +2304,7 @@ int mpol_misplaced(struct page *page, struct vm_area_struct *vma, unsigned long unsigned long pgoff; int thiscpu = raw_smp_processor_id(); int thisnid = cpu_to_node(thiscpu); - int polnid = -1; + int polnid = NUMA_NO_NODE; int ret = -1; pol = get_vma_policy(vma, addr); diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 5361bd078493..1f9f1409df9b 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -6016,7 +6016,7 @@ int __meminit __early_pfn_to_nid(unsigned long pfn, return state->last_nid; nid = memblock_search_pfn_nid(pfn, &start_pfn, &end_pfn); - if (nid != -1) { + if (nid != NUMA_NO_NODE) { state->last_start = start_pfn; state->last_end = end_pfn; state->last_nid = nid; @@ -6771,7 +6771,7 @@ unsigned long __init node_map_pfn_alignment(void) { unsigned long accl_mask = 0, last_end = 0; unsigned long start, end, mask; - int last_nid = -1; + int last_nid = NUMA_NO_NODE; int i, nid; for_each_mem_pfn_range(i, MAX_NUMNODES, &start, &end, &nid) { diff --git a/mm/page_ext.c b/mm/page_ext.c index 8c78b8d45117..762d5b7eb523 100644 --- a/mm/page_ext.c +++ b/mm/page_ext.c @@ -300,7 +300,7 @@ static int __meminit online_page_ext(unsigned long start_pfn, start = SECTION_ALIGN_DOWN(start_pfn); end = SECTION_ALIGN_UP(start_pfn + nr_pages); - if (nid == -1) { + if (nid == NUMA_NO_NODE) { /* * In this case, "nid" already exists and contains valid memory. * "start_pfn" passed to us is a pfn which is an arg for diff --git a/net/core/pktgen.c b/net/core/pktgen.c index 6ac919847ce6..f3f5a78cd062 100644 --- a/net/core/pktgen.c +++ b/net/core/pktgen.c @@ -158,6 +158,7 @@ #include #include #include +#include #include #include #include @@ -3625,7 +3626,7 @@ static int pktgen_add_device(struct pktgen_thread *t, const char *ifname) pkt_dev->svlan_cfi = 0; pkt_dev->svlan_id = 0xffff; pkt_dev->burst = 1; - pkt_dev->node = -1; + pkt_dev->node = NUMA_NO_NODE; err = pktgen_setup_dev(t->net, pkt_dev, ifname); if (err) diff --git a/net/qrtr/qrtr.c b/net/qrtr/qrtr.c index 86e1e37eb4e8..b37e6e0a1026 100644 --- a/net/qrtr/qrtr.c +++ b/net/qrtr/qrtr.c @@ -15,6 +15,7 @@ #include #include #include /* For TIOCINQ/OUTQ */ +#include #include @@ -101,7 +102,7 @@ static inline struct qrtr_sock *qrtr_sk(struct sock *sk) return container_of(sk, struct qrtr_sock, sk); } -static unsigned int qrtr_local_nid = -1; +static unsigned int qrtr_local_nid = NUMA_NO_NODE; /* for node ids */ static RADIX_TREE(qrtr_nodes, GFP_KERNEL); -- cgit v1.2.3-58-ga151 From 6b7e5cad651a2b1031a4c69a98f87e3532dd4cef Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Tue, 5 Mar 2019 15:43:41 -0800 Subject: mm: remove sysctl_extfrag_handler() sysctl_extfrag_handler() neglects to propagate the return value from proc_dointvec_minmax() to its caller. It's a wrapper that doesn't need to exist, so just use proc_dointvec_minmax() directly. Link: http://lkml.kernel.org/r/20190104032557.3056-1-willy@infradead.org Signed-off-by: Matthew Wilcox Reported-by: Aditya Pakki Acked-by: Mel Gorman Acked-by: Randy Dunlap Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/compaction.h | 2 -- kernel/sysctl.c | 2 +- mm/compaction.c | 8 -------- 3 files changed, 1 insertion(+), 11 deletions(-) (limited to 'kernel') diff --git a/include/linux/compaction.h b/include/linux/compaction.h index 68250a57aace..70d0256edd31 100644 --- a/include/linux/compaction.h +++ b/include/linux/compaction.h @@ -88,8 +88,6 @@ extern int sysctl_compact_memory; extern int sysctl_compaction_handler(struct ctl_table *table, int write, void __user *buffer, size_t *length, loff_t *ppos); extern int sysctl_extfrag_threshold; -extern int sysctl_extfrag_handler(struct ctl_table *table, int write, - void __user *buffer, size_t *length, loff_t *ppos); extern int sysctl_compact_unevictable_allowed; extern int fragmentation_index(struct zone *zone, unsigned int order); diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 7578e21a711b..9c78e06f7ba4 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -1460,7 +1460,7 @@ static struct ctl_table vm_table[] = { .data = &sysctl_extfrag_threshold, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = sysctl_extfrag_handler, + .proc_handler = proc_dointvec_minmax, .extra1 = &min_extfrag_threshold, .extra2 = &max_extfrag_threshold, }, diff --git a/mm/compaction.c b/mm/compaction.c index ef29490b0f46..c15b4bbc9e9e 100644 --- a/mm/compaction.c +++ b/mm/compaction.c @@ -1876,14 +1876,6 @@ int sysctl_compaction_handler(struct ctl_table *table, int write, return 0; } -int sysctl_extfrag_handler(struct ctl_table *table, int write, - void __user *buffer, size_t *length, loff_t *ppos) -{ - proc_dointvec_minmax(table, write, buffer, length, ppos); - - return 0; -} - #if defined(CONFIG_SYSFS) && defined(CONFIG_NUMA) static ssize_t sysfs_compact_node(struct device *dev, struct device_attribute *attr, -- cgit v1.2.3-58-ga151 From 5e1f0f098b4649fad53011246bcaeff011ffdf5d Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Tue, 5 Mar 2019 15:45:41 -0800 Subject: mm, compaction: capture a page under direct compaction Compaction is inherently race-prone as a suitable page freed during compaction can be allocated by any parallel task. This patch uses a capture_control structure to isolate a page immediately when it is freed by a direct compactor in the slow path of the page allocator. The intent is to avoid redundant scanning. 5.0.0-rc1 5.0.0-rc1 selective-v3r17 capture-v3r19 Amean fault-both-1 0.00 ( 0.00%) 0.00 * 0.00%* Amean fault-both-3 2582.11 ( 0.00%) 2563.68 ( 0.71%) Amean fault-both-5 4500.26 ( 0.00%) 4233.52 ( 5.93%) Amean fault-both-7 5819.53 ( 0.00%) 6333.65 ( -8.83%) Amean fault-both-12 9321.18 ( 0.00%) 9759.38 ( -4.70%) Amean fault-both-18 9782.76 ( 0.00%) 10338.76 ( -5.68%) Amean fault-both-24 15272.81 ( 0.00%) 13379.55 * 12.40%* Amean fault-both-30 15121.34 ( 0.00%) 16158.25 ( -6.86%) Amean fault-both-32 18466.67 ( 0.00%) 18971.21 ( -2.73%) Latency is only moderately affected but the devil is in the details. A closer examination indicates that base page fault latency is reduced but latency of huge pages is increased as it takes creater care to succeed. Part of the "problem" is that allocation success rates are close to 100% even when under pressure and compaction gets harder 5.0.0-rc1 5.0.0-rc1 selective-v3r17 capture-v3r19 Percentage huge-3 96.70 ( 0.00%) 98.23 ( 1.58%) Percentage huge-5 96.99 ( 0.00%) 95.30 ( -1.75%) Percentage huge-7 94.19 ( 0.00%) 97.24 ( 3.24%) Percentage huge-12 94.95 ( 0.00%) 97.35 ( 2.53%) Percentage huge-18 96.74 ( 0.00%) 97.30 ( 0.58%) Percentage huge-24 97.07 ( 0.00%) 97.55 ( 0.50%) Percentage huge-30 95.69 ( 0.00%) 98.50 ( 2.95%) Percentage huge-32 96.70 ( 0.00%) 99.27 ( 2.65%) And scan rates are reduced as expected by 6% for the migration scanner and 29% for the free scanner indicating that there is less redundant work. Compaction migrate scanned 20815362 19573286 Compaction free scanned 16352612 11510663 [mgorman@techsingularity.net: remove redundant check] Link: http://lkml.kernel.org/r/20190201143853.GH9565@techsingularity.net Link: http://lkml.kernel.org/r/20190118175136.31341-23-mgorman@techsingularity.net Signed-off-by: Mel Gorman Acked-by: Vlastimil Babka Cc: Andrea Arcangeli Cc: Dan Carpenter Cc: David Rientjes Cc: YueHaibing Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/compaction.h | 3 +- include/linux/sched.h | 4 +++ kernel/sched/core.c | 3 ++ mm/compaction.c | 31 +++++++++++++++----- mm/internal.h | 9 ++++++ mm/page_alloc.c | 73 +++++++++++++++++++++++++++++++++++++++++++--- 6 files changed, 111 insertions(+), 12 deletions(-) (limited to 'kernel') diff --git a/include/linux/compaction.h b/include/linux/compaction.h index 70d0256edd31..c960923d9ec2 100644 --- a/include/linux/compaction.h +++ b/include/linux/compaction.h @@ -93,7 +93,8 @@ extern int sysctl_compact_unevictable_allowed; extern int fragmentation_index(struct zone *zone, unsigned int order); extern enum compact_result try_to_compact_pages(gfp_t gfp_mask, unsigned int order, unsigned int alloc_flags, - const struct alloc_context *ac, enum compact_priority prio); + const struct alloc_context *ac, enum compact_priority prio, + struct page **page); 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 classzone_idx); diff --git a/include/linux/sched.h b/include/linux/sched.h index f9b43c989577..ebfb34fb9b30 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -47,6 +47,7 @@ struct pid_namespace; struct pipe_inode_info; struct rcu_node; struct reclaim_state; +struct capture_control; struct robust_list_head; struct sched_attr; struct sched_param; @@ -958,6 +959,9 @@ struct task_struct { struct io_context *io_context; +#ifdef CONFIG_COMPACTION + struct capture_control *capture_control; +#endif /* Ptrace state: */ unsigned long ptrace_message; kernel_siginfo_t *last_siginfo; diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 7cbb5658be80..916e956e92be 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -2190,6 +2190,9 @@ static void __sched_fork(unsigned long clone_flags, struct task_struct *p) INIT_HLIST_HEAD(&p->preempt_notifiers); #endif +#ifdef CONFIG_COMPACTION + p->capture_control = NULL; +#endif init_numa_balancing(clone_flags, p); } diff --git a/mm/compaction.c b/mm/compaction.c index 3084cee77fda..1cc871da3fda 100644 --- a/mm/compaction.c +++ b/mm/compaction.c @@ -2056,7 +2056,8 @@ bool compaction_zonelist_suitable(struct alloc_context *ac, int order, return false; } -static enum compact_result compact_zone(struct compact_control *cc) +static enum compact_result +compact_zone(struct compact_control *cc, struct capture_control *capc) { enum compact_result ret; unsigned long start_pfn = cc->zone->zone_start_pfn; @@ -2225,6 +2226,11 @@ check_drain: } } + /* Stop if a page has been captured */ + if (capc && capc->page) { + ret = COMPACT_SUCCESS; + break; + } } out: @@ -2258,7 +2264,8 @@ out: static enum compact_result compact_zone_order(struct zone *zone, int order, gfp_t gfp_mask, enum compact_priority prio, - unsigned int alloc_flags, int classzone_idx) + unsigned int alloc_flags, int classzone_idx, + struct page **capture) { enum compact_result ret; struct compact_control cc = { @@ -2279,14 +2286,24 @@ static enum compact_result compact_zone_order(struct zone *zone, int order, .ignore_skip_hint = (prio == MIN_COMPACT_PRIORITY), .ignore_block_suitable = (prio == MIN_COMPACT_PRIORITY) }; + struct capture_control capc = { + .cc = &cc, + .page = NULL, + }; + + if (capture) + current->capture_control = &capc; INIT_LIST_HEAD(&cc.freepages); INIT_LIST_HEAD(&cc.migratepages); - ret = compact_zone(&cc); + ret = compact_zone(&cc, &capc); VM_BUG_ON(!list_empty(&cc.freepages)); VM_BUG_ON(!list_empty(&cc.migratepages)); + *capture = capc.page; + current->capture_control = NULL; + return ret; } @@ -2304,7 +2321,7 @@ int sysctl_extfrag_threshold = 500; */ enum compact_result try_to_compact_pages(gfp_t gfp_mask, unsigned int order, unsigned int alloc_flags, const struct alloc_context *ac, - enum compact_priority prio) + enum compact_priority prio, struct page **capture) { int may_perform_io = gfp_mask & __GFP_IO; struct zoneref *z; @@ -2332,7 +2349,7 @@ enum compact_result try_to_compact_pages(gfp_t gfp_mask, unsigned int order, } status = compact_zone_order(zone, order, gfp_mask, prio, - alloc_flags, ac_classzone_idx(ac)); + alloc_flags, ac_classzone_idx(ac), capture); rc = max(status, rc); /* The allocation should succeed, stop compacting */ @@ -2400,7 +2417,7 @@ static void compact_node(int nid) INIT_LIST_HEAD(&cc.freepages); INIT_LIST_HEAD(&cc.migratepages); - compact_zone(&cc); + compact_zone(&cc, NULL); VM_BUG_ON(!list_empty(&cc.freepages)); VM_BUG_ON(!list_empty(&cc.migratepages)); @@ -2535,7 +2552,7 @@ static void kcompactd_do_work(pg_data_t *pgdat) if (kthread_should_stop()) return; - status = compact_zone(&cc); + status = compact_zone(&cc, NULL); if (status == COMPACT_SUCCESS) { compaction_defer_reset(zone, cc.order, false); diff --git a/mm/internal.h b/mm/internal.h index 31bb0be6fd52..9eeaf2b95166 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -209,6 +209,15 @@ struct compact_control { bool rescan; /* Rescanning the same pageblock */ }; +/* + * Used in direct compaction when a page should be taken from the freelists + * immediately when one is created during the free path. + */ +struct capture_control { + struct compact_control *cc; + struct page *page; +}; + unsigned long isolate_freepages_range(struct compact_control *cc, unsigned long start_pfn, unsigned long end_pfn); diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 2e132b9e7a93..09bf2c5f8b4b 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -789,6 +789,57 @@ static inline int page_is_buddy(struct page *page, struct page *buddy, return 0; } +#ifdef CONFIG_COMPACTION +static inline struct capture_control *task_capc(struct zone *zone) +{ + struct capture_control *capc = current->capture_control; + + return capc && + !(current->flags & PF_KTHREAD) && + !capc->page && + capc->cc->zone == zone && + capc->cc->direct_compaction ? capc : NULL; +} + +static inline bool +compaction_capture(struct capture_control *capc, struct page *page, + int order, int migratetype) +{ + if (!capc || order != capc->cc->order) + return false; + + /* Do not accidentally pollute CMA or isolated regions*/ + if (is_migrate_cma(migratetype) || + is_migrate_isolate(migratetype)) + return false; + + /* + * Do not let lower order allocations polluate a movable pageblock. + * This might let an unmovable request use a reclaimable pageblock + * and vice-versa but no more than normal fallback logic which can + * have trouble finding a high-order free page. + */ + if (order < pageblock_order && migratetype == MIGRATE_MOVABLE) + return false; + + capc->page = page; + return true; +} + +#else +static inline struct capture_control *task_capc(struct zone *zone) +{ + return NULL; +} + +static inline bool +compaction_capture(struct capture_control *capc, struct page *page, + int order, int migratetype) +{ + return false; +} +#endif /* CONFIG_COMPACTION */ + /* * Freeing function for a buddy system allocator. * @@ -822,6 +873,7 @@ static inline void __free_one_page(struct page *page, unsigned long uninitialized_var(buddy_pfn); struct page *buddy; unsigned int max_order; + struct capture_control *capc = task_capc(zone); max_order = min_t(unsigned int, MAX_ORDER, pageblock_order + 1); @@ -837,6 +889,11 @@ static inline void __free_one_page(struct page *page, continue_merging: while (order < max_order - 1) { + if (compaction_capture(capc, page, order, migratetype)) { + __mod_zone_freepage_state(zone, -(1 << order), + migratetype); + return; + } buddy_pfn = __find_buddy_pfn(pfn, order); buddy = page + (buddy_pfn - pfn); @@ -3710,7 +3767,7 @@ __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order, unsigned int alloc_flags, const struct alloc_context *ac, enum compact_priority prio, enum compact_result *compact_result) { - struct page *page; + struct page *page = NULL; unsigned long pflags; unsigned int noreclaim_flag; @@ -3721,13 +3778,15 @@ __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order, noreclaim_flag = memalloc_noreclaim_save(); *compact_result = try_to_compact_pages(gfp_mask, order, alloc_flags, ac, - prio); + prio, &page); memalloc_noreclaim_restore(noreclaim_flag); psi_memstall_leave(&pflags); - if (*compact_result <= COMPACT_INACTIVE) + if (*compact_result <= COMPACT_INACTIVE) { + WARN_ON_ONCE(page); return NULL; + } /* * At least in one zone compaction wasn't deferred or skipped, so let's @@ -3735,7 +3794,13 @@ __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order, */ count_vm_event(COMPACTSTALL); - page = get_page_from_freelist(gfp_mask, order, alloc_flags, ac); + /* Prep a captured page if available */ + if (page) + prep_new_page(page, order, gfp_mask, alloc_flags); + + /* Try get a page from the freelist if available */ + if (!page) + page = get_page_from_freelist(gfp_mask, order, alloc_flags, ac); if (page) { struct zone *zone = page_zone(page); -- cgit v1.2.3-58-ga151 From dc50537bdd1a0804fa2cbc990565ee9a944e66fa Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Tue, 5 Mar 2019 15:45:48 -0800 Subject: kernel: cgroup: add poll file operation Cgroup has a standardized poll/notification mechanism for waking all pollers on all fds when a filesystem node changes. To allow polling for custom events, add a .poll callback that can override the default. This is in preparation for pollable cgroup pressure files which have per-fd trigger configurations. Link: http://lkml.kernel.org/r/20190124211518.244221-3-surenb@google.com Signed-off-by: Johannes Weiner Signed-off-by: Suren Baghdasaryan Cc: Dennis Zhou Cc: Ingo Molnar Cc: Jens Axboe Cc: Li Zefan Cc: Peter Zijlstra Cc: Tejun Heo Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/cgroup-defs.h | 4 ++++ kernel/cgroup/cgroup.c | 12 ++++++++++++ 2 files changed, 16 insertions(+) (limited to 'kernel') diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h index 8fcbae1b8db0..aad3babef007 100644 --- a/include/linux/cgroup-defs.h +++ b/include/linux/cgroup-defs.h @@ -32,6 +32,7 @@ struct kernfs_node; struct kernfs_ops; struct kernfs_open_file; struct seq_file; +struct poll_table_struct; #define MAX_CGROUP_TYPE_NAMELEN 32 #define MAX_CGROUP_ROOT_NAMELEN 64 @@ -574,6 +575,9 @@ struct cftype { ssize_t (*write)(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off); + __poll_t (*poll)(struct kernfs_open_file *of, + struct poll_table_struct *pt); + #ifdef CONFIG_DEBUG_LOCK_ALLOC struct lock_class_key lockdep_key; #endif diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index cef98502b124..17828333f7c3 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -3534,6 +3534,16 @@ static ssize_t cgroup_file_write(struct kernfs_open_file *of, char *buf, return ret ?: nbytes; } +static __poll_t cgroup_file_poll(struct kernfs_open_file *of, poll_table *pt) +{ + struct cftype *cft = of->kn->priv; + + if (cft->poll) + return cft->poll(of, pt); + + return kernfs_generic_poll(of, pt); +} + static void *cgroup_seqfile_start(struct seq_file *seq, loff_t *ppos) { return seq_cft(seq)->seq_start(seq, ppos); @@ -3572,6 +3582,7 @@ static struct kernfs_ops cgroup_kf_single_ops = { .open = cgroup_file_open, .release = cgroup_file_release, .write = cgroup_file_write, + .poll = cgroup_file_poll, .seq_show = cgroup_seqfile_show, }; @@ -3580,6 +3591,7 @@ static struct kernfs_ops cgroup_kf_ops = { .open = cgroup_file_open, .release = cgroup_file_release, .write = cgroup_file_write, + .poll = cgroup_file_poll, .seq_start = cgroup_seqfile_start, .seq_next = cgroup_seqfile_next, .seq_stop = cgroup_seqfile_stop, -- cgit v1.2.3-58-ga151