Merge tag 'bitmap-for-7.3' of https://github.com/norov/linux

Pull bitmap updates from Yury Norov:
 "The usual set of fixes, cleanups and performance improvements together
  with a couple of new tests:

   - bitmap_find_next_zero_area_off() optimization (Sunyi)

   - bitmap_find_next_zero_area_off(): return size when no zero area is
     found (Yury)

   - bitmap vs IDA vs Maple Tree performance test (Yury)

   - get rid of cpumap_print_to_pagebuf() (Yury)

   - use nr_node_ids in __nodemask_pr_numnodes() (Li RongQing)

   - bitops: make the *_bit_le functions use unsigned long (Benjamin)

   - bitmap scatter & gather test fix (Christophe)

   - use __ASSEMBLER__ in bitmap header files (Thomas)"

* tag 'bitmap-for-7.3' of https://github.com/norov/linux: (25 commits)
  lib: test bitmap vs IDA vs Maple Tree performance for region allocations
  bitmap: Return size when no zero area is found
  media: s5p-mfc: Treat bitmap size as allocation failure
  crypto: ccp: Treat bitmap size as allocation failure
  powerpc/msi: Treat bitmap size as allocation failure
  ARM: dma-mapping: Treat bitmap size as allocation failure
  bitmap: drop bitmap_next_set_region()
  nodemask: reduce bitmap width to nr_node_ids in __nodemask_pr_numnodes()
  bitmap: Properly initialise destination bitmap for scatter & gather test
  lib/bitmap-str: get rid of cpumap_print_to_pagebuf()
  perf: Use sysfs_emit() for cpumask show callbacks
  PCI/sysfs: Use sysfs_emit() for cpumask show callbacks
  RDMA/hfi1: Use sysfs_emit() for cpumask show helper
  hwtracing: hisi_ptt: Use sysfs_emit() for cpumask show
  fpga: dfl-fme-perf: Use sysfs_emit() for cpumask show
  devfreq: Use sysfs_emit() for cpumask show callbacks
  cpu: Use sysfs_emit() for cpumask show callback
  x86/events: Use sysfs_emit() for cpumask show callbacks
  powerpc: Use sysfs_emit() for cpumask show callbacks
  arm: Use sysfs_emit() for cpumask show callbacks
  ...

MAINTAINERS

@@ -4614,6 +4614,7 @@ F:	lib/bitmap.c
 F:	lib/cpumask.c
 F:	lib/find_bit.c
 F:	lib/find_bit_benchmark.c
+F:	lib/region_alloc_benchmark.c
 F:	lib/test_bitmap.c
 F:	lib/tests/cpumask_kunit.c
 F:	tools/include/linux/bitfield.h
@@ -15608,6 +15609,7 @@ F:	Documentation/core-api/maple_tree.rst
 F:	include/linux/maple_tree.h
 F:	include/trace/events/maple_tree.h
 F:	lib/maple_tree.c
+F:	lib/region_alloc_benchmark.c
 F:	lib/test_maple_tree.c
 F:	rust/helpers/maple_tree.c
 F:	rust/kernel/maple_tree.rs
@@ -29448,6 +29450,7 @@ F:	Documentation/core-api/xarray.rst
 F:	include/linux/idr.h
 F:	include/linux/xarray.h
 F:	lib/idr.c
+F:	lib/region_alloc_benchmark.c
 F:	lib/test_xarray.c
 F:	lib/xarray.c
 F:	tools/testing/radix-tree

arch/arm/mach-imx/mmdc.c

@@ -127,7 +127,7 @@ static ssize_t mmdc_pmu_cpumask_show(struct device *dev,
 {
 	struct mmdc_pmu *pmu_mmdc = dev_get_drvdata(dev);
 
-	return cpumap_print_to_pagebuf(true, buf, &pmu_mmdc->cpu);
+	return sysfs_emit(buf, "%*pbl\n", cpumask_pr_args(&pmu_mmdc->cpu));
 }
 
 static struct device_attribute mmdc_pmu_cpumask_attr =

arch/arm/mm/cache-l2x0-pmu.c

@@ -390,7 +390,7 @@ static struct attribute_group l2x0_pmu_event_attrs_group = {
 static ssize_t l2x0_pmu_cpumask_show(struct device *dev,
 				     struct device_attribute *attr, char *buf)
 {
-	return cpumap_print_to_pagebuf(true, buf, &pmu_cpu);
+	return sysfs_emit(buf, "%*pbl\n", cpumask_pr_args(&pmu_cpu));
 }
 
 static struct device_attribute l2x0_pmu_cpumask_attr =

arch/arm/mm/dma-mapping.c

@@ -773,7 +773,7 @@ static inline dma_addr_t __alloc_iova(struct dma_iommu_mapping *mapping,
 		start = bitmap_find_next_zero_area(mapping->bitmaps[i],
 				mapping->bits, 0, count, align);
 
-		if (start > mapping->bits)
+		if (start >= mapping->bits)
 			continue;
 
 		bitmap_set(mapping->bitmaps[i], start, count);
@@ -794,7 +794,7 @@ static inline dma_addr_t __alloc_iova(struct dma_iommu_mapping *mapping,
 		start = bitmap_find_next_zero_area(mapping->bitmaps[i],
 				mapping->bits, 0, count, align);
 
-		if (start > mapping->bits) {
+		if (start >= mapping->bits) {
 			spin_unlock_irqrestore(&mapping->lock, flags);
 			return DMA_MAPPING_ERROR;
 		}

arch/powerpc/kernel/cacheinfo.c

@@ -690,7 +690,8 @@ show_shared_cpumap(struct kobject *k, struct kobj_attribute *attr, char *buf, bo
 
 	mask = &cache->shared_cpu_map;
 
-	return cpumap_print_to_pagebuf(list, buf, mask);
+	return sysfs_emit(buf, list ? "%*pbl\n" : "%*pb\n",
+			  cpumask_pr_args(mask));
 }
 
 static ssize_t shared_cpu_map_show(struct kobject *k, struct kobj_attribute *attr, char *buf)

arch/powerpc/perf/hv-24x7.c

@@ -429,7 +429,7 @@ static char *memdup_to_str(char *maybe_str, int max_len, gfp_t gfp)
 static ssize_t cpumask_show(struct device *dev,
 			    struct device_attribute *attr, char *buf)
 {
-	return cpumap_print_to_pagebuf(true, buf, &hv_24x7_cpumask);
+	return sysfs_emit(buf, "%*pbl\n", cpumask_pr_args(&hv_24x7_cpumask));
 }
 
 static ssize_t sockets_show(struct device *dev,

arch/powerpc/perf/hv-gpci.c

@@ -100,7 +100,7 @@ static ssize_t kernel_version_show(struct device *dev,
 static ssize_t cpumask_show(struct device *dev,
 			    struct device_attribute *attr, char *buf)
 {
-	return cpumap_print_to_pagebuf(true, buf, &hv_gpci_cpumask);
+	return sysfs_emit(buf, "%*pbl\n", cpumask_pr_args(&hv_gpci_cpumask));
 }
 
 /* Interface attribute array index to store system information */

arch/powerpc/perf/imc-pmu.c

@@ -117,7 +117,7 @@ static ssize_t imc_pmu_cpumask_get_attr(struct device *dev,
 		return 0;
 	}
 
-	return cpumap_print_to_pagebuf(true, buf, active_mask);
+	return sysfs_emit(buf, "%*pbl\n", cpumask_pr_args(active_mask));
 }
 
 static DEVICE_ATTR(cpumask, S_IRUGO, imc_pmu_cpumask_get_attr, NULL);

arch/powerpc/sysdev/msi_bitmap.c

@@ -21,7 +21,7 @@ int msi_bitmap_alloc_hwirqs(struct msi_bitmap *bmp, int num)
 
 	offset = bitmap_find_next_zero_area(bmp->bitmap, bmp->irq_count, 0,
 					    num, (1 << order) - 1);
-	if (offset > bmp->irq_count)
+	if (offset >= bmp->irq_count)
 		goto err;
 
 	bitmap_set(bmp->bitmap, offset, num);

arch/x86/events/amd/iommu.c

@@ -137,7 +137,7 @@ static ssize_t _iommu_cpumask_show(struct device *dev,
 				   struct device_attribute *attr,
 				   char *buf)
 {
-	return cpumap_print_to_pagebuf(true, buf, &iommu_cpumask);
+	return sysfs_emit(buf, "%*pbl\n", cpumask_pr_args(&iommu_cpumask));
 }
 static DEVICE_ATTR(cpumask, S_IRUGO, _iommu_cpumask_show, NULL);
 

arch/x86/events/amd/power.c

@@ -150,7 +150,7 @@ static void pmu_event_read(struct perf_event *event)
 static ssize_t
 get_attr_cpumask(struct device *dev, struct device_attribute *attr, char *buf)
 {
-	return cpumap_print_to_pagebuf(true, buf, &cpu_mask);
+	return sysfs_emit(buf, "%*pbl\n", cpumask_pr_args(&cpu_mask));
 }
 
 static DEVICE_ATTR(cpumask, S_IRUGO, get_attr_cpumask, NULL);

arch/x86/events/amd/uncore.c

@@ -353,7 +353,7 @@ static ssize_t amd_uncore_attr_show_cpumask(struct device *dev,
 	struct pmu *ptr = dev_get_drvdata(dev);
 	struct amd_uncore_pmu *pmu = container_of(ptr, struct amd_uncore_pmu, pmu);
 
-	return cpumap_print_to_pagebuf(true, buf, &pmu->active_mask);
+	return sysfs_emit(buf, "%*pbl\n", cpumask_pr_args(&pmu->active_mask));
 }
 static DEVICE_ATTR(cpumask, S_IRUGO, amd_uncore_attr_show_cpumask, NULL);
 

arch/x86/events/intel/core.c

@@ -7590,7 +7590,7 @@ static ssize_t intel_hybrid_get_attr_cpus(struct device *dev,
 	struct x86_hybrid_pmu *pmu =
 		container_of(dev_get_drvdata(dev), struct x86_hybrid_pmu, pmu);
 
-	return cpumap_print_to_pagebuf(true, buf, &pmu->supported_cpus);
+	return sysfs_emit(buf, "%*pbl\n", cpumask_pr_args(&pmu->supported_cpus));
 }
 
 static DEVICE_ATTR(cpus, S_IRUGO, intel_hybrid_get_attr_cpus, NULL);

arch/x86/events/intel/uncore.c

@@ -861,7 +861,7 @@ static ssize_t uncore_get_attr_cpumask(struct device *dev,
 {
 	struct intel_uncore_pmu *pmu = container_of(dev_get_drvdata(dev), struct intel_uncore_pmu, pmu);
 
-	return cpumap_print_to_pagebuf(true, buf, &pmu->cpu_mask);
+	return sysfs_emit(buf, "%*pbl\n", cpumask_pr_args(&pmu->cpu_mask));
 }
 
 static DEVICE_ATTR(cpumask, S_IRUGO, uncore_get_attr_cpumask, NULL);

drivers/base/cpu.c

@@ -218,7 +218,7 @@ static ssize_t show_cpus_attr(struct device *dev,
 {
 	struct cpu_attr *ca = container_of(attr, struct cpu_attr, attr);
 
-	return cpumap_print_to_pagebuf(true, buf, ca->map);
+	return sysfs_emit(buf, "%*pbl\n", cpumask_pr_args(ca->map));
 }
 
 #define _CPU_ATTR(name, map) \

drivers/crypto/ccp/ccp-dev-v3.c

@@ -28,7 +28,7 @@ static u32 ccp_alloc_ksb(struct ccp_cmd_queue *cmd_q, unsigned int count)
 							ccp->sb_count,
 							ccp->sb_start,
 							count, 0);
-		if (start <= ccp->sb_count) {
+		if (start < ccp->sb_count) {
 			bitmap_set(ccp->sb, start, count);
 
 			mutex_unlock(&ccp->sb_mutex);

drivers/crypto/ccp/ccp-dev-v5.c

@@ -47,7 +47,7 @@ static u32 ccp_lsb_alloc(struct ccp_cmd_queue *cmd_q, unsigned int count)
 							MAX_LSB_CNT * LSB_SIZE,
 							0,
 							count, 0);
-		if (start <= MAX_LSB_CNT * LSB_SIZE) {
+		if (start < MAX_LSB_CNT * LSB_SIZE) {
 			bitmap_set(ccp->lsbmap, start, count);
 
 			mutex_unlock(&ccp->sb_mutex);

drivers/devfreq/event/rockchip-dfi.c

@@ -354,7 +354,7 @@ static ssize_t ddr_perf_cpumask_show(struct device *dev,
 	struct pmu *pmu = dev_get_drvdata(dev);
 	struct rockchip_dfi *dfi = container_of(pmu, struct rockchip_dfi, pmu);
 
-	return cpumap_print_to_pagebuf(true, buf, cpumask_of(dfi->cpu));
+	return sysfs_emit(buf, "%*pbl\n", cpumask_pr_args(cpumask_of(dfi->cpu)));
 }
 
 static struct device_attribute ddr_perf_cpumask_attr =

drivers/devfreq/hisi_uncore_freq.c

@@ -540,7 +540,7 @@ static ssize_t related_cpus_show(struct device *dev,
 {
 	struct hisi_uncore_freq *uncore = dev_get_drvdata(dev->parent);
 
-	return cpumap_print_to_pagebuf(true, buf, &uncore->related_cpus);
+	return sysfs_emit(buf, "%*pbl\n", cpumask_pr_args(&uncore->related_cpus));
 }
 
 static DEVICE_ATTR_RO(related_cpus);

drivers/firmware/psci/psci_checker.c

@@ -186,7 +186,6 @@ static int hotplug_tests(void)
 {
 	int i, nb_cpu_group, err = -ENOMEM;
 	cpumask_var_t offlined_cpus, *cpu_groups;
-	char *page_buf;
 
 	if (!alloc_cpumask_var(&offlined_cpus, GFP_KERNEL))
 		return err;
@@ -194,10 +193,6 @@ static int hotplug_tests(void)
 	nb_cpu_group = alloc_init_cpu_groups(&cpu_groups);
 	if (nb_cpu_group < 0)
 		goto out_free_cpus;
-	page_buf = (char *)__get_free_page(GFP_KERNEL);
-	if (!page_buf)
-		goto out_free_cpu_groups;
-
 	/*
 	 * Of course the last CPU cannot be powered down and cpu_down() should
 	 * refuse doing that.
@@ -210,17 +205,11 @@ static int hotplug_tests(void)
 	 * off, the cpu group itself should shut down.
 	 */
 	for (i = 0; i < nb_cpu_group; ++i) {
-		ssize_t len = cpumap_print_to_pagebuf(true, page_buf,
-						      cpu_groups[i]);
-		/* Remove trailing newline. */
-		page_buf[len - 1] = '\0';
-		pr_info("Trying to turn off and on again group %d (CPUs %s)\n",
-			i, page_buf);
+		pr_info("Trying to turn off and on again group %d (CPUs %*pbl)\n",
+			i, cpumask_pr_args(cpu_groups[i]));
 		err += down_and_up_cpus(cpu_groups[i], offlined_cpus);
 	}
 
-	free_page((unsigned long)page_buf);
-out_free_cpu_groups:
 	free_cpu_groups(nb_cpu_group, &cpu_groups);
 out_free_cpus:
 	free_cpumask_var(offlined_cpus);

drivers/fpga/dfl-fme-perf.c

@@ -183,7 +183,7 @@ static ssize_t cpumask_show(struct device *dev,
 
 	priv = to_fme_perf_priv(pmu);
 
-	return cpumap_print_to_pagebuf(true, buf, cpumask_of(priv->cpu));
+	return sysfs_emit(buf, "%*pbl\n", cpumask_pr_args(cpumask_of(priv->cpu)));
 }
 static DEVICE_ATTR_RO(cpumask);
 

drivers/hwtracing/ptt/hisi_ptt.c

@@ -780,7 +780,7 @@ static ssize_t cpumask_show(struct device *dev, struct device_attribute *attr,
 	struct hisi_ptt *hisi_ptt = to_hisi_ptt(dev_get_drvdata(dev));
 	const cpumask_t *cpumask = cpumask_of_node(dev_to_node(&hisi_ptt->pdev->dev));
 
-	return cpumap_print_to_pagebuf(true, buf, cpumask);
+	return sysfs_emit(buf, "%*pbl\n", cpumask_pr_args(cpumask));
 }
 static DEVICE_ATTR_RO(cpumask);
 

drivers/infiniband/hw/hfi1/sdma.c

@@ -11,6 +11,7 @@
 #include <linux/timer.h>
 #include <linux/vmalloc.h>
 #include <linux/highmem.h>
+#include <linux/sysfs.h>
 
 #include "hfi.h"
 #include "common.h"
@@ -1049,7 +1050,7 @@ ssize_t sdma_get_cpu_to_sde_map(struct sdma_engine *sde, char *buf)
 	if (cpumask_empty(&sde->cpu_mask))
 		snprintf(buf, PAGE_SIZE, "%s\n", "empty");
 	else
-		cpumap_print_to_pagebuf(true, buf, &sde->cpu_mask);
+		sysfs_emit(buf, "%*pbl\n", cpumask_pr_args(&sde->cpu_mask));
 	mutex_unlock(&process_to_sde_mutex);
 	return strnlen(buf, PAGE_SIZE);
 }

drivers/media/platform/samsung/s5p-mfc/s5p_mfc_opr.c

@@ -43,7 +43,7 @@ int s5p_mfc_alloc_priv_buf(struct s5p_mfc_dev *dev, unsigned int mem_ctx,
 
 	if (dev->mem_virt) {
 		start = bitmap_find_next_zero_area(dev->mem_bitmap, bits, 0, count, align);
-		if (start > bits)
+		if (start >= bits)
 			goto no_mem;
 
 		bitmap_set(dev->mem_bitmap, start, count);

drivers/pci/pci-sysfs.c

@@ -112,7 +112,8 @@ static ssize_t pci_dev_show_local_cpu(struct device *dev, bool list,
 #else
 	mask = cpumask_of_pcibus(to_pci_dev(dev)->bus);
 #endif
-	return cpumap_print_to_pagebuf(list, buf, mask);
+	return sysfs_emit(buf, list ? "%*pbl\n" : "%*pb\n",
+			  cpumask_pr_args(mask));
 }
 
 static ssize_t local_cpus_show(struct device *dev,
@@ -137,7 +138,7 @@ static ssize_t cpuaffinity_show(struct device *dev,
 {
 	const struct cpumask *cpumask = cpumask_of_pcibus(to_pci_bus(dev));
 
-	return cpumap_print_to_pagebuf(false, buf, cpumask);
+	return sysfs_emit(buf, "%*pb\n", cpumask_pr_args(cpumask));
 }
 static DEVICE_ATTR_RO(cpuaffinity);
 
@@ -146,7 +147,7 @@ static ssize_t cpulistaffinity_show(struct device *dev,
 {
 	const struct cpumask *cpumask = cpumask_of_pcibus(to_pci_bus(dev));
 
-	return cpumap_print_to_pagebuf(true, buf, cpumask);
+	return sysfs_emit(buf, "%*pbl\n", cpumask_pr_args(cpumask));
 }
 static DEVICE_ATTR_RO(cpulistaffinity);
 

drivers/perf/alibaba_uncore_drw_pmu.c

@@ -221,7 +221,7 @@ static ssize_t ali_drw_pmu_cpumask_show(struct device *dev,
 {
 	struct ali_drw_pmu *drw_pmu = to_ali_drw_pmu(dev_get_drvdata(dev));
 
-	return cpumap_print_to_pagebuf(true, buf, cpumask_of(drw_pmu->cpu));
+	return sysfs_emit(buf, "%*pbl\n", cpumask_pr_args(cpumask_of(drw_pmu->cpu)));
 }
 
 static struct device_attribute ali_drw_pmu_cpumask_attr =

drivers/perf/amlogic/meson_ddr_pmu_core.c

@@ -191,7 +191,7 @@ static ssize_t meson_ddr_perf_cpumask_show(struct device *dev,
 {
 	struct ddr_pmu *pmu = dev_get_drvdata(dev);
 
-	return cpumap_print_to_pagebuf(true, buf, cpumask_of(pmu->cpu));
+	return sysfs_emit(buf, "%*pbl\n", cpumask_pr_args(cpumask_of(pmu->cpu)));
 }
 
 static struct device_attribute meson_ddr_perf_cpumask_attr =

drivers/perf/arm-cci.c

@@ -1351,7 +1351,7 @@ static ssize_t pmu_cpumask_attr_show(struct device *dev,
 	struct pmu *pmu = dev_get_drvdata(dev);
 	struct cci_pmu *cci_pmu = to_cci_pmu(pmu);
 
-	return cpumap_print_to_pagebuf(true, buf, cpumask_of(cci_pmu->cpu));
+	return sysfs_emit(buf, "%*pbl\n", cpumask_pr_args(cpumask_of(cci_pmu->cpu)));
 }
 
 static struct device_attribute pmu_cpumask_attr =

drivers/perf/arm-ccn.c

@@ -537,7 +537,7 @@ static ssize_t arm_ccn_pmu_cpumask_show(struct device *dev,
 {
 	struct arm_ccn *ccn = pmu_to_arm_ccn(dev_get_drvdata(dev));
 
-	return cpumap_print_to_pagebuf(true, buf, cpumask_of(ccn->dt.cpu));
+	return sysfs_emit(buf, "%*pbl\n", cpumask_pr_args(cpumask_of(ccn->dt.cpu)));
 }
 
 static struct device_attribute arm_ccn_pmu_cpumask_attr =

drivers/perf/arm-cmn.c

@@ -1516,7 +1516,7 @@ static ssize_t arm_cmn_cpumask_show(struct device *dev,
 {
 	struct arm_cmn *cmn = to_cmn(dev_get_drvdata(dev));
 
-	return cpumap_print_to_pagebuf(true, buf, cpumask_of(cmn->cpu));
+	return sysfs_emit(buf, "%*pbl\n", cpumask_pr_args(cpumask_of(cmn->cpu)));
 }
 
 static struct device_attribute arm_cmn_cpumask_attr =

drivers/perf/arm-ni.c

@@ -239,7 +239,7 @@ static ssize_t arm_ni_cpumask_show(struct device *dev,
 {
 	struct arm_ni *ni = cd_to_ni(pmu_to_cd(dev_get_drvdata(dev)));
 
-	return cpumap_print_to_pagebuf(true, buf, cpumask_of(ni->cpu));
+	return sysfs_emit(buf, "%*pbl\n", cpumask_pr_args(cpumask_of(ni->cpu)));
 }
 
 static struct device_attribute arm_ni_cpumask_attr =

drivers/perf/arm_cspmu/arm_cspmu.c

@@ -337,7 +337,7 @@ static ssize_t arm_cspmu_cpumask_show(struct device *dev,
 	default:
 		return 0;
 	}
-	return cpumap_print_to_pagebuf(true, buf, cpumask);
+	return sysfs_emit(buf, "%*pbl\n", cpumask_pr_args(cpumask));
 }
 
 static struct attribute *arm_cspmu_cpumask_attrs[] = {

drivers/perf/arm_dmc620_pmu.c

@@ -237,8 +237,8 @@ static ssize_t dmc620_pmu_cpumask_show(struct device *dev,
 {
 	struct dmc620_pmu *dmc620_pmu = to_dmc620_pmu(dev_get_drvdata(dev));
 
-	return cpumap_print_to_pagebuf(true, buf,
-				       cpumask_of(dmc620_pmu->irq->cpu));
+	return sysfs_emit(buf, "%*pbl\n",
+			  cpumask_pr_args(cpumask_of(dmc620_pmu->irq->cpu)));
 }
 
 static struct device_attribute dmc620_pmu_cpumask_attr =

drivers/perf/arm_dsu_pmu.c

@@ -157,7 +157,7 @@ static ssize_t dsu_pmu_cpumask_show(struct device *dev,
 	default:
 		return 0;
 	}
-	return cpumap_print_to_pagebuf(true, buf, cpumask);
+	return sysfs_emit(buf, "%*pbl\n", cpumask_pr_args(cpumask));
 }
 
 static struct attribute *dsu_pmu_format_attrs[] = {

drivers/perf/arm_pmu.c

@@ -570,7 +570,7 @@ static ssize_t cpus_show(struct device *dev,
 			 struct device_attribute *attr, char *buf)
 {
 	struct arm_pmu *armpmu = to_arm_pmu(dev_get_drvdata(dev));
-	return cpumap_print_to_pagebuf(true, buf, &armpmu->supported_cpus);
+	return sysfs_emit(buf, "%*pbl\n", cpumask_pr_args(&armpmu->supported_cpus));
 }
 
 static DEVICE_ATTR_RO(cpus);

drivers/perf/arm_smmuv3_pmu.c

@@ -537,7 +537,7 @@ static ssize_t smmu_pmu_cpumask_show(struct device *dev,
 {
 	struct smmu_pmu *smmu_pmu = to_smmu_pmu(dev_get_drvdata(dev));
 
-	return cpumap_print_to_pagebuf(true, buf, cpumask_of(smmu_pmu->on_cpu));
+	return sysfs_emit(buf, "%*pbl\n", cpumask_pr_args(cpumask_of(smmu_pmu->on_cpu)));
 }
 
 static struct device_attribute smmu_pmu_cpumask_attr =

drivers/perf/arm_spe_pmu.c

@@ -343,7 +343,7 @@ static ssize_t cpumask_show(struct device *dev,
 {
 	struct arm_spe_pmu *spe_pmu = dev_get_drvdata(dev);
 
-	return cpumap_print_to_pagebuf(true, buf, &spe_pmu->supported_cpus);
+	return sysfs_emit(buf, "%*pbl\n", cpumask_pr_args(&spe_pmu->supported_cpus));
 }
 static DEVICE_ATTR_RO(cpumask);
 

drivers/perf/cxl_pmu.c

@@ -568,7 +568,7 @@ static ssize_t cpumask_show(struct device *dev, struct device_attribute *attr,
 {
 	struct cxl_pmu_info *info = dev_get_drvdata(dev);
 
-	return cpumap_print_to_pagebuf(true, buf, cpumask_of(info->on_cpu));
+	return sysfs_emit(buf, "%*pbl\n", cpumask_pr_args(cpumask_of(info->on_cpu)));
 }
 static DEVICE_ATTR_RO(cpumask);
 

drivers/perf/dwc_pcie_pmu.c

@@ -121,7 +121,7 @@ static ssize_t cpumask_show(struct device *dev,
 {
 	struct dwc_pcie_pmu *pcie_pmu = to_dwc_pcie_pmu(dev_get_drvdata(dev));
 
-	return cpumap_print_to_pagebuf(true, buf, cpumask_of(pcie_pmu->on_cpu));
+	return sysfs_emit(buf, "%*pbl\n", cpumask_pr_args(cpumask_of(pcie_pmu->on_cpu)));
 }
 static DEVICE_ATTR_RO(cpumask);
 

drivers/perf/fsl_imx8_ddr_perf.c

@@ -237,7 +237,7 @@ static ssize_t ddr_perf_cpumask_show(struct device *dev,
 {
 	struct ddr_pmu *pmu = dev_get_drvdata(dev);
 
-	return cpumap_print_to_pagebuf(true, buf, cpumask_of(pmu->cpu));
+	return sysfs_emit(buf, "%*pbl\n", cpumask_pr_args(cpumask_of(pmu->cpu)));
 }
 
 static struct device_attribute ddr_perf_cpumask_attr =

drivers/perf/fsl_imx9_ddr_perf.c

@@ -159,7 +159,7 @@ static ssize_t ddr_perf_cpumask_show(struct device *dev,
 {
 	struct ddr_pmu *pmu = dev_get_drvdata(dev);
 
-	return cpumap_print_to_pagebuf(true, buf, cpumask_of(pmu->cpu));
+	return sysfs_emit(buf, "%*pbl\n", cpumask_pr_args(cpumask_of(pmu->cpu)));
 }
 
 static struct device_attribute ddr_perf_cpumask_attr =

drivers/perf/fujitsu_uncore_pmu.c

@@ -373,7 +373,7 @@ static ssize_t cpumask_show(struct device *dev,
 {
 	struct uncore_pmu *uncorepmu = to_uncore_pmu(dev_get_drvdata(dev));
 
-	return cpumap_print_to_pagebuf(true, buf, cpumask_of(uncorepmu->cpu));
+	return sysfs_emit(buf, "%*pbl\n", cpumask_pr_args(cpumask_of(uncorepmu->cpu)));
 }
 static DEVICE_ATTR_RO(cpumask);
 

drivers/perf/hisilicon/hisi_pcie_pmu.c

@@ -121,7 +121,7 @@ static ssize_t cpumask_show(struct device *dev, struct device_attribute *attr, c
 {
 	struct hisi_pcie_pmu *pcie_pmu = to_pcie_pmu(dev_get_drvdata(dev));
 
-	return cpumap_print_to_pagebuf(true, buf, cpumask_of(pcie_pmu->on_cpu));
+	return sysfs_emit(buf, "%*pbl\n", cpumask_pr_args(cpumask_of(pcie_pmu->on_cpu)));
 }
 static DEVICE_ATTR_RO(cpumask);
 

drivers/perf/hisilicon/hisi_uncore_pmu.c

@@ -56,7 +56,7 @@ static ssize_t hisi_associated_cpus_sysfs_show(struct device *dev,
 {
 	struct hisi_pmu *hisi_pmu = to_hisi_pmu(dev_get_drvdata(dev));
 
-	return cpumap_print_to_pagebuf(true, buf, &hisi_pmu->associated_cpus);
+	return sysfs_emit(buf, "%*pbl\n", cpumask_pr_args(&hisi_pmu->associated_cpus));
 }
 static DEVICE_ATTR(associated_cpus, 0444, hisi_associated_cpus_sysfs_show, NULL);
 

drivers/perf/marvell_cn10k_ddr_pmu.c

@@ -471,7 +471,7 @@ static ssize_t cn10k_ddr_perf_cpumask_show(struct device *dev,
 {
 	struct cn10k_ddr_pmu *pmu = dev_get_drvdata(dev);
 
-	return cpumap_print_to_pagebuf(true, buf, cpumask_of(pmu->cpu));
+	return sysfs_emit(buf, "%*pbl\n", cpumask_pr_args(cpumask_of(pmu->cpu)));
 }
 
 static struct device_attribute cn10k_ddr_perf_cpumask_attr =

drivers/perf/marvell_cn10k_tad_pmu.c

@@ -258,7 +258,7 @@ static ssize_t tad_pmu_cpumask_show(struct device *dev,
 {
 	struct tad_pmu *tad_pmu = to_tad_pmu(dev_get_drvdata(dev));
 
-	return cpumap_print_to_pagebuf(true, buf, cpumask_of(tad_pmu->cpu));
+	return sysfs_emit(buf, "%*pbl\n", cpumask_pr_args(cpumask_of(tad_pmu->cpu)));
 }
 
 static DEVICE_ATTR(cpumask, 0444, tad_pmu_cpumask_show, NULL);

drivers/perf/marvell_pem_pmu.c

@@ -164,7 +164,7 @@ static ssize_t pem_perf_cpumask_show(struct device *dev,
 {
 	struct pem_pmu *pmu = dev_get_drvdata(dev);
 
-	return cpumap_print_to_pagebuf(true, buf, cpumask_of(pmu->cpu));
+	return sysfs_emit(buf, "%*pbl\n", cpumask_pr_args(cpumask_of(pmu->cpu)));
 }
 
 static struct device_attribute pem_perf_cpumask_attr =

drivers/perf/nvidia_t410_c2c_pmu.c

@@ -658,7 +658,7 @@ static ssize_t nv_c2c_pmu_cpumask_show(struct device *dev,
 	default:
 		return 0;
 	}
-	return cpumap_print_to_pagebuf(true, buf, cpumask);
+	return sysfs_emit(buf, "%*pbl\n", cpumask_pr_args(cpumask));
 }
 
 #define NV_C2C_PMU_CPUMASK_ATTR(_name, _config)			\

drivers/perf/nvidia_t410_cmem_latency_pmu.c

@@ -501,7 +501,7 @@ static ssize_t cmem_lat_pmu_cpumask_show(struct device *dev,
 	default:
 		return 0;
 	}
-	return cpumap_print_to_pagebuf(true, buf, cpumask);
+	return sysfs_emit(buf, "%*pbl\n", cpumask_pr_args(cpumask));
 }
 
 #define NV_PMU_CPUMASK_ATTR(_name, _config)			\

drivers/perf/qcom_l2_pmu.c

@@ -638,7 +638,7 @@ static ssize_t l2_cache_pmu_cpumask_show(struct device *dev,
 {
 	struct l2cache_pmu *l2cache_pmu = to_l2cache_pmu(dev_get_drvdata(dev));
 
-	return cpumap_print_to_pagebuf(true, buf, &l2cache_pmu->cpumask);
+	return sysfs_emit(buf, "%*pbl\n", cpumask_pr_args(&l2cache_pmu->cpumask));
 }
 
 static struct device_attribute l2_cache_pmu_cpumask_attr =

drivers/perf/qcom_l3_pmu.c

@@ -663,7 +663,7 @@ static ssize_t cpumask_show(struct device *dev,
 {
 	struct l3cache_pmu *l3pmu = to_l3cache_pmu(dev_get_drvdata(dev));
 
-	return cpumap_print_to_pagebuf(true, buf, &l3pmu->cpumask);
+	return sysfs_emit(buf, "%*pbl\n", cpumask_pr_args(&l3pmu->cpumask));
 }
 
 static DEVICE_ATTR_RO(cpumask);

drivers/perf/starfive_starlink_pmu.c

@@ -130,7 +130,7 @@ cpumask_show(struct device *dev, struct device_attribute *attr, char *buf)
 {
 	struct starlink_pmu *starlink_pmu = to_starlink_pmu(dev_get_drvdata(dev));
 
-	return cpumap_print_to_pagebuf(true, buf, &starlink_pmu->cpumask);
+	return sysfs_emit(buf, "%*pbl\n", cpumask_pr_args(&starlink_pmu->cpumask));
 }
 
 static DEVICE_ATTR_RO(cpumask);

drivers/perf/thunderx2_pmu.c

@@ -254,7 +254,7 @@ static ssize_t cpumask_show(struct device *dev, struct device_attribute *attr,
 	struct tx2_uncore_pmu *tx2_pmu;
 
 	tx2_pmu = pmu_to_tx2_pmu(dev_get_drvdata(dev));
-	return cpumap_print_to_pagebuf(true, buf, cpumask_of(tx2_pmu->cpu));
+	return sysfs_emit(buf, "%*pbl\n", cpumask_pr_args(cpumask_of(tx2_pmu->cpu)));
 }
 static DEVICE_ATTR_RO(cpumask);
 

drivers/perf/xgene_pmu.c

@@ -595,7 +595,7 @@ static ssize_t cpumask_show(struct device *dev,
 {
 	struct xgene_pmu_dev *pmu_dev = to_pmu_dev(dev_get_drvdata(dev));
 
-	return cpumap_print_to_pagebuf(true, buf, &pmu_dev->parent->cpu);
+	return sysfs_emit(buf, "%*pbl\n", cpumask_pr_args(&pmu_dev->parent->cpu));
 }
 
 static DEVICE_ATTR_RO(cpumask);

include/asm-generic/bitops/le.h

@@ -16,47 +16,47 @@
 #endif
 
 
-static inline int test_bit_le(int nr, const void *addr)
+static inline int test_bit_le(unsigned long nr, const void *addr)
 {
 	return test_bit(nr ^ BITOP_LE_SWIZZLE, addr);
 }
 
-static inline void set_bit_le(int nr, void *addr)
+static inline void set_bit_le(unsigned long nr, void *addr)
 {
 	set_bit(nr ^ BITOP_LE_SWIZZLE, addr);
 }
 
-static inline void clear_bit_le(int nr, void *addr)
+static inline void clear_bit_le(unsigned long nr, void *addr)
 {
 	clear_bit(nr ^ BITOP_LE_SWIZZLE, addr);
 }
 
-static inline void __set_bit_le(int nr, void *addr)
+static inline void __set_bit_le(unsigned long nr, void *addr)
 {
 	__set_bit(nr ^ BITOP_LE_SWIZZLE, addr);
 }
 
-static inline void __clear_bit_le(int nr, void *addr)
+static inline void __clear_bit_le(unsigned long nr, void *addr)
 {
 	__clear_bit(nr ^ BITOP_LE_SWIZZLE, addr);
 }
 
-static inline int test_and_set_bit_le(int nr, void *addr)
+static inline int test_and_set_bit_le(unsigned long nr, void *addr)
 {
 	return test_and_set_bit(nr ^ BITOP_LE_SWIZZLE, addr);
 }
 
-static inline int test_and_clear_bit_le(int nr, void *addr)
+static inline int test_and_clear_bit_le(unsigned long nr, void *addr)
 {
 	return test_and_clear_bit(nr ^ BITOP_LE_SWIZZLE, addr);
 }
 
-static inline int __test_and_set_bit_le(int nr, void *addr)
+static inline int __test_and_set_bit_le(unsigned long nr, void *addr)
 {
 	return __test_and_set_bit(nr ^ BITOP_LE_SWIZZLE, addr);
 }
 
-static inline int __test_and_clear_bit_le(int nr, void *addr)
+static inline int __test_and_clear_bit_le(unsigned long nr, void *addr)
 {
 	return __test_and_clear_bit(nr ^ BITOP_LE_SWIZZLE, addr);
 }

include/linux/bitmap.h

@@ -2,7 +2,7 @@
 #ifndef __LINUX_BITMAP_H
 #define __LINUX_BITMAP_H
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 #include <linux/align.h>
 #include <linux/bitops.h>
@@ -209,6 +209,9 @@ unsigned long bitmap_find_next_zero_area_off(unsigned long *map,
  * The @align_mask should be one less than a power of 2; the effect is that
  * the bit offset of all zero areas this function finds is multiples of that
  * power of 2. A @align_mask of 0 means no alignment is required.
+ *
+ * Return: The bit offset of the found area or a value >= @size
+ * if no area is found.
  */
 static __always_inline
 unsigned long bitmap_find_next_zero_area(unsigned long *map,
@@ -697,14 +700,6 @@ void bitmap_gather(unsigned long *dst, const unsigned long *src,
 		__assign_bit(n++, dst, test_bit(bit, src));
 }
 
-static __always_inline
-void bitmap_next_set_region(unsigned long *bitmap, unsigned int *rs,
-			    unsigned int *re, unsigned int end)
-{
-	*rs = find_next_bit(bitmap, end, *rs);
-	*re = find_next_zero_bit(bitmap, end, *rs + 1);
-}
-
 /**
  * bitmap_release_region - release allocated bitmap region
  *	@bitmap: array of unsigned longs corresponding to the bitmap
@@ -894,6 +889,6 @@ void bitmap_write(unsigned long *map, unsigned long value,
 #define bitmap_set_value8(map, value, start)		\
 	bitmap_write(map, value, start, BITS_PER_BYTE)
 
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 
 #endif /* __LINUX_BITMAP_H */

include/linux/bits.h

@@ -17,7 +17,7 @@
  * position @h. For example
  * GENMASK_ULL(39, 21) gives us the 64bit vector 0x000000ffffe00000.
  */
-#if !defined(__ASSEMBLY__)
+#if !defined(__ASSEMBLER__)
 
 /*
  * Missing asm support
@@ -75,7 +75,7 @@
 #define BIT_U32(nr)	BIT_TYPE(u32, nr)
 #define BIT_U64(nr)	BIT_TYPE(u64, nr)
 
-#else /* defined(__ASSEMBLY__) */
+#else /* defined(__ASSEMBLER__) */
 
 /*
  * BUILD_BUG_ON_ZERO is not available in h files included from asm files,
@@ -84,6 +84,6 @@
 #define GENMASK(h, l)		__GENMASK(h, l)
 #define GENMASK_ULL(h, l)	__GENMASK_ULL(h, l)
 
-#endif /* !defined(__ASSEMBLY__) */
+#endif /* !defined(__ASSEMBLER__) */
 
 #endif	/* __LINUX_BITS_H */

include/linux/cpumask.h

@@ -13,7 +13,6 @@
 #include <linux/cpumask_types.h>
 #include <linux/gfp_types.h>
 #include <linux/numa.h>
-#include <linux/sprintf.h>
 #include <linux/threads.h>
 #include <linux/types.h>
 #include <vdso/page.h>
@@ -1315,24 +1314,6 @@ static __always_inline bool cpu_dying(unsigned int cpu)
 }
 #endif /* NR_CPUS > BITS_PER_LONG */
 
-/**
- * cpumap_print_to_pagebuf  - copies the cpumask into the buffer either
- *	as comma-separated list of cpus or hex values of cpumask
- * @list: indicates whether the cpumap must be list
- * @mask: the cpumask to copy
- * @buf: the buffer to copy into
- *
- * Return: the length of the (null-terminated) @buf string, zero if
- * nothing is copied.
- */
-static __always_inline ssize_t
-cpumap_print_to_pagebuf(bool list, char *buf, const struct cpumask *mask)
-{
-	/* Opencode offset_in_page(buf) to not include linux/mm.h */
-	return scnprintf(buf, PAGE_SIZE - ((unsigned long)buf & ~PAGE_MASK),
-			 list ? "%*pbl\n" : "%*pb\n", cpumask_pr_args(mask));
-}
-
 /**
  * cpumap_print_bitmask_to_buf  - copies the cpumask into the buffer as
  *	hex values of cpumask

include/linux/nodemask.h

@@ -95,6 +95,14 @@
 
 extern nodemask_t _unused_nodemask_arg_;
 
+#if MAX_NUMNODES > 1
+extern unsigned int nr_node_ids;
+extern unsigned int nr_online_nodes;
+#else
+#define nr_node_ids		1U
+#define nr_online_nodes		1U
+#endif
+
 /**
  * nodemask_pr_args - printf args to output a nodemask
  * @maskp: nodemask to be printed
@@ -105,7 +113,7 @@ extern nodemask_t _unused_nodemask_arg_;
 				__nodemask_pr_bits(maskp)
 static __always_inline unsigned int __nodemask_pr_numnodes(const nodemask_t *m)
 {
-	return m ? MAX_NUMNODES : 0;
+	return m ? nr_node_ids : 0;
 }
 static __always_inline const unsigned long *__nodemask_pr_bits(const nodemask_t *m)
 {
@@ -438,9 +446,6 @@ static __always_inline unsigned int next_memory_node(int nid)
 	return next_node(nid, node_states[N_MEMORY]);
 }
 
-extern unsigned int nr_node_ids;
-extern unsigned int nr_online_nodes;
-
 static __always_inline void node_set_online(int nid)
 {
 	node_set_state(nid, N_ONLINE);
@@ -480,8 +485,6 @@ static __always_inline int num_node_state(enum node_states state)
 #define first_memory_node	0
 #define next_online_node(nid)	(MAX_NUMNODES)
 #define next_memory_node(nid)	(MAX_NUMNODES)
-#define nr_node_ids		1U
-#define nr_online_nodes		1U
 
 #define node_set_online(node)	   node_set_state((node), N_ONLINE)
 #define node_set_offline(node)	   node_clear_state((node), N_ONLINE)

kernel/events/core.c

@@ -12726,7 +12726,7 @@ static ssize_t cpumask_show(struct device *dev, struct device_attribute *attr,
 	struct cpumask *mask = perf_scope_cpumask(pmu->scope);
 
 	if (mask)
-		return cpumap_print_to_pagebuf(true, buf, mask);
+		return sysfs_emit(buf, "%*pbl\n", cpumask_pr_args(mask));
 	return 0;
 }
 

lib/Kconfig.debug

@@ -2683,6 +2683,19 @@ config FIND_BIT_BENCHMARK
 
 	  If unsure, say N.
 
+config REGION_ALLOC_BENCHMARK
+	tristate "Benchmark bitmap, IDA and Maple Tree region allocation"
+	help
+	  This builds a microbenchmark comparing variable-sized region
+	  allocation using bitmaps, IDA and Maple Tree. The benchmark
+	  runs at initialization time.
+
+	  Usage:
+	    insmod region_alloc_benchmark.ko
+	    insmod region_alloc_benchmark.ko capacities=1024,2048,4096,65536
+
+	  If unsure, say N.
+
 config FIND_BIT_BENCHMARK_RUST
 	tristate "Test find_bit functions in Rust"
 	depends on RUST

lib/Makefile

@@ -64,6 +64,7 @@ obj-y += hexdump.o
 obj-$(CONFIG_TEST_HEXDUMP) += test_hexdump.o
 obj-y += kstrtox.o
 obj-$(CONFIG_FIND_BIT_BENCHMARK) += find_bit_benchmark.o
+obj-$(CONFIG_REGION_ALLOC_BENCHMARK) += region_alloc_benchmark.o
 obj-$(CONFIG_FIND_BIT_BENCHMARK_RUST) += find_bit_benchmark_rust.o
 obj-$(CONFIG_TEST_BPF) += test_bpf.o
 test_dhry-objs := dhry_1.o dhry_2.o dhry_run.o

lib/bitmap-str.c

@@ -75,8 +75,7 @@ static int bitmap_print_to_buf(bool list, char *buf, const unsigned long *maskp,
  * @off: in the string from which we are copying, We copy to @buf
  * @count: the maximum number of bytes to print
  *
- * The sprintf("%*pb[l]") is used indirectly via its cpumap wrapper
- * cpumap_print_to_pagebuf() or directly by drivers to export hexadecimal
+ * The sprintf("%*pb[l]") format is used by drivers to export hexadecimal
  * bitmask and decimal list to userspace by sysfs ABI.
  * Drivers might be using a normal attribute for this kind of ABIs. A
  * normal attribute typically has show entry as below::
@@ -115,9 +114,9 @@ static int bitmap_print_to_buf(bool list, char *buf, const unsigned long *maskp,
  * parameters such as off, count from bin_attribute show entry to this API.
  *
  * The role of cpumap_print_bitmask_to_buf() and cpumap_print_list_to_buf()
- * is similar with cpumap_print_to_pagebuf(),  the difference is that
- * scnprintf("%*pb[l]") mainly serves sysfs attribute with the assumption
- * the destination buffer is exactly one page and won't be more than one page.
+ * is similar to direct sysfs_emit("%*pb[l]") formatting, but the latter
+ * assumes the destination buffer is exactly one page and won't be more than
+ * one page.
  * cpumap_print_bitmask_to_buf() and cpumap_print_list_to_buf(), on the other
  * hand, mainly serves bin_attribute which doesn't work with exact one page,
  * and it can break the size limit of converted decimal list and hexadecimal

lib/bitmap.c

@@ -424,6 +424,9 @@ EXPORT_SYMBOL(__bitmap_clear);
  * The @align_mask should be one less than a power of 2; the effect is that
  * the bit offset of all zero areas this function finds plus @align_offset
  * is multiple of that power of 2.
+ *
+ * Return: The bit offset of the found area or a value greater than or equal
+ * to @size if no area is found.
  */
 unsigned long bitmap_find_next_zero_area_off(unsigned long *map,
 					     unsigned long size,
@@ -432,22 +435,23 @@ unsigned long bitmap_find_next_zero_area_off(unsigned long *map,
 					     unsigned long align_mask,
 					     unsigned long align_offset)
 {
-	unsigned long index, end, i;
-again:
-	index = find_next_zero_bit(map, size, start);
+	unsigned long end, i, off;
 
-	/* Align allocation */
-	index = __ALIGN_MASK(index + align_offset, align_mask) - align_offset;
+	for_each_clear_bit_from(start, map, size) {
+		start = __ALIGN_MASK(start + align_offset, align_mask) - align_offset;
+		end = start + nr;
+		if (end > size)
+			break;
 
-	end = index + nr;
-	if (end > size)
-		return end;
-	i = find_next_bit(map, end, index);
-	if (i < end) {
-		start = i + 1;
-		goto again;
+		off = round_down(start, BITS_PER_LONG);
+		i = find_last_bit(map + start / BITS_PER_LONG, end - off) + off;
+		if (i >= end || i < start)
+			return start;
+
+		start = i;
 	}
-	return index;
+
+	return size;
 }
 EXPORT_SYMBOL(bitmap_find_next_zero_area_off);
 

lib/find_bit_benchmark.c

@@ -149,6 +149,21 @@ static int __init test_find_next_and_bit(const void *bitmap,
 	return 0;
 }
 
+static int __init
+test_bitmap_find_next_zero_area_off(unsigned long *bitmap, unsigned long len)
+{
+	unsigned long i, cnt;
+	ktime_t time;
+
+	time = ktime_get();
+	for (cnt = i = 0; i < BITMAP_LEN; cnt++)
+		i = bitmap_find_next_zero_area_off(bitmap, BITMAP_LEN, i, 8, 0, 0) + 1;
+	time = ktime_get() - time;
+	pr_err("bitmap_find_next_zero_area_off:%7llu ns, %6ld iterations\n", time, cnt);
+
+	return 0;
+}
+
 static int __init find_bit_test(void)
 {
 	unsigned long nbits = BITMAP_LEN / SPARSE;
@@ -158,6 +173,7 @@ static int __init find_bit_test(void)
 	get_random_bytes(bitmap, sizeof(bitmap));
 	get_random_bytes(bitmap2, sizeof(bitmap2));
 
+	test_bitmap_find_next_zero_area_off(bitmap, BITMAP_LEN);
 	test_find_next_bit(bitmap, BITMAP_LEN);
 	test_find_next_zero_bit(bitmap, BITMAP_LEN);
 	test_find_last_bit(bitmap, BITMAP_LEN);
@@ -181,6 +197,7 @@ static int __init find_bit_test(void)
 		__set_bit(get_random_u32_below(BITMAP_LEN), bitmap2);
 	}
 
+	test_bitmap_find_next_zero_area_off(bitmap, BITMAP_LEN);
 	test_find_next_bit(bitmap, BITMAP_LEN);
 	test_find_next_zero_bit(bitmap, BITMAP_LEN);
 	test_find_last_bit(bitmap, BITMAP_LEN);

lib/region_alloc_benchmark.c

@@ -0,0 +1,217 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Benchmark bitmap, IDA and Maple Tree allocation of variable-sized regions. */
+
+#include <linux/bitmap.h>
+#include <linux/idr.h>
+#include <linux/kernel.h>
+#include <linux/maple_tree.h>
+#include <linux/module.h>
+#include <linux/printk.h>
+#include <linux/random.h>
+#include <linux/slab.h>
+#include <linux/xarray.h>
+
+#define REGION_MAX_SIZE	32
+
+static unsigned long *bitmap __initdata;
+/* One more request guarantees that even an all-ones trace reaches ENOSPC. */
+static u8 *reg_sz __initdata;
+static unsigned long *reg_idx __initdata;
+static unsigned long capacities[64] = { 1000000, 100000, 10000, 1000, 100, 10 };
+static unsigned int cap_cnt = 6;
+
+module_param_array(capacities, ulong, &cap_cnt, 0400);
+MODULE_PARM_DESC(capacities, "Region capacities to benchmark");
+
+static unsigned long __init benchmark_bitmap(unsigned long cap)
+{
+	unsigned long cnt, idx;
+	ktime_t alloc_time, free_time;
+	size_t sz;
+
+	bitmap_zero(bitmap, cap);
+	alloc_time = ktime_get();
+	for (cnt = 0; cnt <= cap; cnt++) {
+		idx = bitmap_find_next_zero_area(bitmap, cap, 0, reg_sz[cnt], 0);
+		if (idx >= cap)
+			break;
+
+		reg_idx[cnt] = idx;
+		bitmap_set(bitmap, idx, reg_sz[cnt]);
+	}
+	alloc_time = ktime_get() - alloc_time;
+
+	idx = cnt;
+
+	free_time = ktime_get();
+	while (idx--)
+		bitmap_clear(bitmap, reg_idx[idx], reg_sz[idx]);
+	free_time = ktime_get() - free_time;
+
+	WARN_ON(!bitmap_empty(bitmap, cap));
+
+	sz = BITS_TO_LONGS(cap) * sizeof(unsigned long);
+	pr_err("Bitmap  %12llu  %12llu  %8lu  %8lu  %10zu\n",
+	       alloc_time, free_time, cnt, cap, sz);
+
+	return cnt;
+}
+
+static size_t __init ida_size(unsigned long nr_ids)
+{
+	unsigned long entries = DIV_ROUND_UP(nr_ids, IDA_BITMAP_BITS);
+	unsigned long bitmaps = nr_ids / IDA_BITMAP_BITS;
+	unsigned long nodes = 0;
+
+	if (nr_ids % IDA_BITMAP_BITS > BITS_PER_XA_VALUE)
+		bitmaps++;
+
+	while (entries > 1) {
+		entries = DIV_ROUND_UP(entries, XA_CHUNK_SIZE);
+		nodes += entries;
+	}
+
+	return sizeof(struct ida) +
+		bitmaps * sizeof(struct ida_bitmap) +
+		nodes   * sizeof(struct xa_node);
+}
+
+static unsigned long __init benchmark_ida(unsigned long cap)
+{
+	struct ida ida = IDA_INIT(ida);
+	unsigned long cnt, idx, off, nr_ids = 0;
+	ktime_t alloc_time, free_time;
+	int id = -ENOSPC;
+
+	alloc_time = ktime_get();
+	for (cnt = 0; cnt <= cap; cnt++) {
+		for (off = 0; off < reg_sz[cnt]; off++) {
+			id = ida_alloc_max(&ida, cap - 1, GFP_KERNEL);
+			if (id < 0)
+				break;
+
+			if (!off)
+				reg_idx[cnt] = id;
+		}
+		if (id < 0) {
+			while (off--)
+				ida_free(&ida, reg_idx[cnt] + off);
+			break;
+		}
+		WARN_ON(id != reg_idx[cnt] + reg_sz[cnt] - 1);
+		nr_ids += reg_sz[cnt];
+	}
+	alloc_time = ktime_get() - alloc_time;
+
+	WARN_ON(id != -ENOSPC);
+
+	idx = cnt;
+
+	free_time = ktime_get();
+	while (idx--) {
+		for (off = 0; off < reg_sz[idx]; off++)
+			ida_free(&ida, reg_idx[idx] + off);
+	}
+	free_time = ktime_get() - free_time;
+
+	WARN_ON(!ida_is_empty(&ida));
+
+	pr_err("IDA     %12llu  %12llu  %8lu  %8lu  %10zu\n",
+	       alloc_time, free_time, cnt, cap, ida_size(nr_ids));
+
+	ida_destroy(&ida);
+	return cnt;
+}
+
+static unsigned long __init benchmark_maple_tree(unsigned long cap)
+{
+	struct maple_tree mt = MTREE_INIT(mt, MT_FLAGS_ALLOC_RANGE);
+	unsigned long cnt, idx;
+	ktime_t alloc_time, free_time;
+	size_t sz;
+	int ret;
+
+	alloc_time = ktime_get();
+	for (cnt = 0; cnt <= cap; cnt++) {
+		ret = mtree_alloc_range(&mt, &idx, xa_mk_value(cnt + 1),
+					reg_sz[cnt], 0, cap - 1, GFP_KERNEL);
+		if (ret)
+			break;
+
+		reg_idx[cnt] = idx;
+	}
+	alloc_time = ktime_get() - alloc_time;
+
+	WARN_ON(ret != -EBUSY);
+
+	idx = cnt;
+
+	free_time = ktime_get();
+	while (idx--)
+		mtree_erase(&mt, reg_idx[idx]);
+	free_time = ktime_get() - free_time;
+
+	WARN_ON(!mtree_empty(&mt));
+
+	/* Minimum storage assuming fully occupied allocation-range leaf nodes. */
+	sz = sizeof(mt) + DIV_ROUND_UP(cnt, MAPLE_ARANGE64_SLOTS) * sizeof(struct maple_node);
+	pr_err("Maple   %12llu  %12llu  %8lu  %8lu  %10zu\n",
+	       alloc_time, free_time, cnt, cap, sz);
+
+	mtree_destroy(&mt);
+	return cnt;
+}
+
+static int __init region_alloc_benchmark(void)
+{
+	unsigned long bitmap_count, ida_count, maple_count;
+	unsigned long i, max_cap = 0;
+	int ret = -ENOMEM;
+
+	for (i = 0; i < cap_cnt; i++) {
+		if (capacities[i] == 0) {
+			pr_err("capacity must be nonzero\n");
+			return -EINVAL;
+		}
+		max_cap = max(max_cap, capacities[i]);
+	}
+
+	bitmap = kvmalloc_array(BITS_TO_LONGS(max_cap), sizeof(*bitmap), GFP_KERNEL);
+	reg_sz = kvmalloc_array(max_cap + 1, sizeof(*reg_sz), GFP_KERNEL);
+	reg_idx = kvmalloc_array(max_cap, sizeof(*reg_idx), GFP_KERNEL);
+	if (!bitmap || !reg_sz || !reg_idx)
+		goto out;
+
+	pr_err("\nStart testing bitmap vs IDA vs Maple Tree region allocation\n");
+	pr_err("memory: bitmap is exact; IDA and Maple Tree are lower bounds\n");
+	pr_err("Type      alloc (ns)     free (ns)   regions  capacity  memory (B)\n");
+
+	for (i = 0; i < cap_cnt; i++) {
+		unsigned long idx, max_size;
+
+		max_size = min(REGION_MAX_SIZE, capacities[i] / 10) ? : 1;
+		for (idx = 0; idx <= capacities[i]; idx++)
+			reg_sz[idx] = get_random_u32_below(max_size) + 1;
+
+		bitmap_count = benchmark_bitmap(capacities[i]);
+		maple_count  = benchmark_maple_tree(capacities[i]);
+		ida_count    = benchmark_ida(capacities[i]);
+
+		WARN_ON(bitmap_count != ida_count);
+		WARN_ON(bitmap_count != maple_count);
+	}
+
+	/* Return an error so the benchmark can run repeatedly without rmmod. */
+	pr_info("Region allocation benchmark complete\n");
+	ret = -EAGAIN;
+out:
+	kvfree(reg_idx);
+	kvfree(reg_sz);
+	kvfree(bitmap);
+	return ret;
+}
+module_init(region_alloc_benchmark);
+
+MODULE_AUTHOR("Yury Norov <ynorov@nvidia.com>");
+MODULE_DESCRIPTION("Benchmark bitmap, IDA and Maple Tree region allocation");
+MODULE_LICENSE("GPL");

lib/test_bitmap.c

@@ -234,6 +234,43 @@ static void __init test_find_nth_bit(void)
 	}
 }
 
+static void __init
+test_bitmap_find_next_zero_area_off(void)
+{
+	DECLARE_BITMAP(bmap, 192);
+
+	bitmap_set(bmap, 0, 192);
+
+	bitmap_clear(bmap, 0, 8);
+	__clear_bit(50, bmap);
+	bitmap_clear(bmap, 60, 18);
+	__set_bit(69, bmap);
+	__clear_bit(80, bmap);
+	bitmap_clear(bmap, 100, 10);
+	__clear_bit(120, bmap);
+	bitmap_clear(bmap, 145, 8);
+	bitmap_clear(bmap, 160, 32);
+
+	expect_eq_uint(0,
+		bitmap_find_next_zero_area_off(bmap, 192, 0, 8, 0, 0));
+	expect_eq_uint(0,
+		bitmap_find_next_zero_area_off(bmap, 192, 0, 8, 3, 0));
+	expect_eq_uint(163,
+		bitmap_find_next_zero_area_off(bmap, 192, 0, 8, 3, 1));
+	expect_eq_uint(60,
+		bitmap_find_next_zero_area_off(bmap, 192, 1, 8, 0, 0));
+	expect_eq_uint(160,
+		bitmap_find_next_zero_area_off(bmap, 192, 1, 8, 7, 0));
+	expect_eq_uint(60,
+		bitmap_find_next_zero_area_off(bmap, 192, 1, 8, 7, 4));
+	expect_eq_uint(100,
+		bitmap_find_next_zero_area_off(bmap, 192, 0, 10, 0, 0));
+	expect_eq_uint(160,
+		bitmap_find_next_zero_area_off(bmap, 192, 0, 32, 0, 0));
+	expect_eq_uint(1,
+		!!(bitmap_find_next_zero_area_off(bmap, 192, 0, 33, 0, 0) >= 192));
+}
+
 static void __init test_fill_set(void)
 {
 	DECLARE_BITMAP(bmap, 1024);
@@ -392,6 +429,7 @@ static void __init test_bitmap_sg(void)
 
 	/* Scatter/gather relationship */
 	bitmap_zero(bmap_tmp, 100);
+	bitmap_zero(bmap_res, 100);
 	bitmap_gather(bmap_tmp, bmap_scatter, sg_mask, nbits);
 	bitmap_scatter(bmap_res, bmap_tmp, sg_mask, nbits);
 	expect_eq_bitmap(bmap_scatter, bmap_res, 100);
@@ -1559,6 +1597,7 @@ static void __init selftest(void)
 	test_for_each_clear_bitrange_from();
 	test_for_each_set_clump8();
 	test_for_each_set_bit_wrap();
+	test_bitmap_find_next_zero_area_off();
 }
 
 KSTM_MODULE_LOADERS(test_bitmap);

tools/include/linux/bits.h

@@ -17,7 +17,7 @@
  * position @h. For example
  * GENMASK_ULL(39, 21) gives us the 64bit vector 0x000000ffffe00000.
  */
-#if !defined(__ASSEMBLY__)
+#if !defined(__ASSEMBLER__)
 
 /*
  * Missing asm support
@@ -75,7 +75,7 @@
 #define BIT_U32(nr)	BIT_TYPE(u32, nr)
 #define BIT_U64(nr)	BIT_TYPE(u64, nr)
 
-#else /* defined(__ASSEMBLY__) */
+#else /* defined(__ASSEMBLER__) */
 
 /*
  * BUILD_BUG_ON_ZERO is not available in h files included from asm files,
@@ -84,6 +84,6 @@
 #define GENMASK(h, l)		__GENMASK(h, l)
 #define GENMASK_ULL(h, l)	__GENMASK_ULL(h, l)
 
-#endif /* !defined(__ASSEMBLY__) */
+#endif /* !defined(__ASSEMBLER__) */
 
 #endif	/* __LINUX_BITS_H */