summaryrefslogtreecommitdiffstats
path: root/kernel
diff options
context:
space:
mode:
Diffstat (limited to 'kernel')
-rw-r--r--kernel/Makefile1
-rw-r--r--kernel/bpf/verifier.c4
-rw-r--r--kernel/dma/contiguous.c8
-rw-r--r--kernel/dma/direct.c10
-rw-r--r--kernel/dma/mapping.c32
-rw-r--r--kernel/dma/remap.c2
-rw-r--r--kernel/exit.c5
-rw-r--r--kernel/irq/affinity.c6
-rw-r--r--kernel/memremap.c405
-rw-r--r--kernel/sched/cpufreq_schedutil.c14
-rw-r--r--kernel/sched/deadline.c8
-rw-r--r--kernel/sched/psi.c4
-rw-r--r--kernel/signal.c3
-rw-r--r--kernel/trace/trace_functions_graph.c17
14 files changed, 68 insertions, 451 deletions
diff --git a/kernel/Makefile b/kernel/Makefile
index a8d923b5481b..ef0d95a190b4 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -111,7 +111,6 @@ obj-$(CONFIG_CONTEXT_TRACKING) += context_tracking.o
obj-$(CONFIG_TORTURE_TEST) += torture.o
obj-$(CONFIG_HAS_IOMEM) += iomem.o
-obj-$(CONFIG_ZONE_DEVICE) += memremap.o
obj-$(CONFIG_RSEQ) += rseq.o
obj-$(CONFIG_GCC_PLUGIN_STACKLEAK) += stackleak.o
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 5900cbb966b1..c84d83f86141 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -8616,8 +8616,8 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env)
}
if (is_narrower_load && size < target_size) {
- u8 shift = (off & (size_default - 1)) * 8;
-
+ u8 shift = bpf_ctx_narrow_load_shift(off, size,
+ size_default);
if (ctx_field_size <= 4) {
if (shift)
insn_buf[cnt++] = BPF_ALU32_IMM(BPF_RSH,
diff --git a/kernel/dma/contiguous.c b/kernel/dma/contiguous.c
index bfc0c17f2a3d..2bd410f934b3 100644
--- a/kernel/dma/contiguous.c
+++ b/kernel/dma/contiguous.c
@@ -243,8 +243,9 @@ struct page *dma_alloc_contiguous(struct device *dev, size_t size, gfp_t gfp)
/* CMA can be used only in the context which permits sleeping */
if (cma && gfpflags_allow_blocking(gfp)) {
- align = min_t(size_t, align, CONFIG_CMA_ALIGNMENT);
- page = cma_alloc(cma, count, align, gfp & __GFP_NOWARN);
+ size_t cma_align = min_t(size_t, align, CONFIG_CMA_ALIGNMENT);
+
+ page = cma_alloc(cma, count, cma_align, gfp & __GFP_NOWARN);
}
/* Fallback allocation of normal pages */
@@ -266,7 +267,8 @@ struct page *dma_alloc_contiguous(struct device *dev, size_t size, gfp_t gfp)
*/
void dma_free_contiguous(struct device *dev, struct page *page, size_t size)
{
- if (!cma_release(dev_get_cma_area(dev), page, size >> PAGE_SHIFT))
+ if (!cma_release(dev_get_cma_area(dev), page,
+ PAGE_ALIGN(size) >> PAGE_SHIFT))
__free_pages(page, get_order(size));
}
diff --git a/kernel/dma/direct.c b/kernel/dma/direct.c
index 59bdceea3737..795c9b095d75 100644
--- a/kernel/dma/direct.c
+++ b/kernel/dma/direct.c
@@ -47,9 +47,6 @@ u64 dma_direct_get_required_mask(struct device *dev)
{
u64 max_dma = phys_to_dma_direct(dev, (max_pfn - 1) << PAGE_SHIFT);
- if (dev->bus_dma_mask && dev->bus_dma_mask < max_dma)
- max_dma = dev->bus_dma_mask;
-
return (1ULL << (fls64(max_dma) - 1)) * 2 - 1;
}
@@ -130,10 +127,12 @@ void *dma_direct_alloc_pages(struct device *dev, size_t size,
if (!page)
return NULL;
- if (attrs & DMA_ATTR_NO_KERNEL_MAPPING) {
+ if ((attrs & DMA_ATTR_NO_KERNEL_MAPPING) &&
+ !force_dma_unencrypted(dev)) {
/* remove any dirty cache lines on the kernel alias */
if (!PageHighMem(page))
arch_dma_prep_coherent(page, size);
+ *dma_handle = phys_to_dma(dev, page_to_phys(page));
/* return the page pointer as the opaque cookie */
return page;
}
@@ -178,7 +177,8 @@ void dma_direct_free_pages(struct device *dev, size_t size, void *cpu_addr,
{
unsigned int page_order = get_order(size);
- if (attrs & DMA_ATTR_NO_KERNEL_MAPPING) {
+ if ((attrs & DMA_ATTR_NO_KERNEL_MAPPING) &&
+ !force_dma_unencrypted(dev)) {
/* cpu_addr is a struct page cookie, not a kernel address */
__dma_direct_free_pages(dev, size, cpu_addr);
return;
diff --git a/kernel/dma/mapping.c b/kernel/dma/mapping.c
index 1f628e7ac709..b0038ca3aa92 100644
--- a/kernel/dma/mapping.c
+++ b/kernel/dma/mapping.c
@@ -116,11 +116,16 @@ int dma_common_get_sgtable(struct device *dev, struct sg_table *sgt,
int ret;
if (!dev_is_dma_coherent(dev)) {
+ unsigned long pfn;
+
if (!IS_ENABLED(CONFIG_ARCH_HAS_DMA_COHERENT_TO_PFN))
return -ENXIO;
- page = pfn_to_page(arch_dma_coherent_to_pfn(dev, cpu_addr,
- dma_addr));
+ /* If the PFN is not valid, we do not have a struct page */
+ pfn = arch_dma_coherent_to_pfn(dev, cpu_addr, dma_addr);
+ if (!pfn_valid(pfn))
+ return -ENXIO;
+ page = pfn_to_page(pfn);
} else {
page = virt_to_page(cpu_addr);
}
@@ -145,6 +150,23 @@ int dma_get_sgtable_attrs(struct device *dev, struct sg_table *sgt,
}
EXPORT_SYMBOL(dma_get_sgtable_attrs);
+#ifdef CONFIG_MMU
+/*
+ * Return the page attributes used for mapping dma_alloc_* memory, either in
+ * kernel space if remapping is needed, or to userspace through dma_mmap_*.
+ */
+pgprot_t dma_pgprot(struct device *dev, pgprot_t prot, unsigned long attrs)
+{
+ if (dev_is_dma_coherent(dev) ||
+ (IS_ENABLED(CONFIG_DMA_NONCOHERENT_CACHE_SYNC) &&
+ (attrs & DMA_ATTR_NON_CONSISTENT)))
+ return prot;
+ if (IS_ENABLED(CONFIG_ARCH_HAS_DMA_MMAP_PGPROT))
+ return arch_dma_mmap_pgprot(dev, prot, attrs);
+ return pgprot_noncached(prot);
+}
+#endif /* CONFIG_MMU */
+
/*
* Create userspace mapping for the DMA-coherent memory.
*/
@@ -159,7 +181,7 @@ int dma_common_mmap(struct device *dev, struct vm_area_struct *vma,
unsigned long pfn;
int ret = -ENXIO;
- vma->vm_page_prot = arch_dma_mmap_pgprot(dev, vma->vm_page_prot, attrs);
+ vma->vm_page_prot = dma_pgprot(dev, vma->vm_page_prot, attrs);
if (dma_mmap_from_dev_coherent(dev, vma, cpu_addr, size, &ret))
return ret;
@@ -170,7 +192,11 @@ int dma_common_mmap(struct device *dev, struct vm_area_struct *vma,
if (!dev_is_dma_coherent(dev)) {
if (!IS_ENABLED(CONFIG_ARCH_HAS_DMA_COHERENT_TO_PFN))
return -ENXIO;
+
+ /* If the PFN is not valid, we do not have a struct page */
pfn = arch_dma_coherent_to_pfn(dev, cpu_addr, dma_addr);
+ if (!pfn_valid(pfn))
+ return -ENXIO;
} else {
pfn = page_to_pfn(virt_to_page(cpu_addr));
}
diff --git a/kernel/dma/remap.c b/kernel/dma/remap.c
index a594aec07882..ffe78f0b2fe4 100644
--- a/kernel/dma/remap.c
+++ b/kernel/dma/remap.c
@@ -218,7 +218,7 @@ void *arch_dma_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle,
/* create a coherent mapping */
ret = dma_common_contiguous_remap(page, size, VM_USERMAP,
- arch_dma_mmap_pgprot(dev, PAGE_KERNEL, attrs),
+ dma_pgprot(dev, PAGE_KERNEL, attrs),
__builtin_return_address(0));
if (!ret) {
__dma_direct_free_pages(dev, size, page);
diff --git a/kernel/exit.c b/kernel/exit.c
index 4436158a6d30..5b4a5dcce8f8 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -734,9 +734,10 @@ static void exit_notify(struct task_struct *tsk, int group_dead)
autoreap = true;
}
- tsk->exit_state = autoreap ? EXIT_DEAD : EXIT_ZOMBIE;
- if (tsk->exit_state == EXIT_DEAD)
+ if (autoreap) {
+ tsk->exit_state = EXIT_DEAD;
list_add(&tsk->ptrace_entry, &dead);
+ }
/* mt-exec, de_thread() is waiting for group leader */
if (unlikely(tsk->signal->notify_count < 0))
diff --git a/kernel/irq/affinity.c b/kernel/irq/affinity.c
index 4352b08ae48d..6fef48033f96 100644
--- a/kernel/irq/affinity.c
+++ b/kernel/irq/affinity.c
@@ -251,11 +251,9 @@ irq_create_affinity_masks(unsigned int nvecs, struct irq_affinity *affd)
* Determine the number of vectors which need interrupt affinities
* assigned. If the pre/post request exhausts the available vectors
* then nothing to do here except for invoking the calc_sets()
- * callback so the device driver can adjust to the situation. If there
- * is only a single vector, then managing the queue is pointless as
- * well.
+ * callback so the device driver can adjust to the situation.
*/
- if (nvecs > 1 && nvecs > affd->pre_vectors + affd->post_vectors)
+ if (nvecs > affd->pre_vectors + affd->post_vectors)
affvecs = nvecs - affd->pre_vectors - affd->post_vectors;
else
affvecs = 0;
diff --git a/kernel/memremap.c b/kernel/memremap.c
deleted file mode 100644
index 6ee03a816d67..000000000000
--- a/kernel/memremap.c
+++ /dev/null
@@ -1,405 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-/* Copyright(c) 2015 Intel Corporation. All rights reserved. */
-#include <linux/device.h>
-#include <linux/io.h>
-#include <linux/kasan.h>
-#include <linux/memory_hotplug.h>
-#include <linux/mm.h>
-#include <linux/pfn_t.h>
-#include <linux/swap.h>
-#include <linux/swapops.h>
-#include <linux/types.h>
-#include <linux/wait_bit.h>
-#include <linux/xarray.h>
-
-static DEFINE_XARRAY(pgmap_array);
-#define SECTION_MASK ~((1UL << PA_SECTION_SHIFT) - 1)
-#define SECTION_SIZE (1UL << PA_SECTION_SHIFT)
-
-#ifdef CONFIG_DEV_PAGEMAP_OPS
-DEFINE_STATIC_KEY_FALSE(devmap_managed_key);
-EXPORT_SYMBOL(devmap_managed_key);
-static atomic_t devmap_managed_enable;
-
-static void devmap_managed_enable_put(void *data)
-{
- if (atomic_dec_and_test(&devmap_managed_enable))
- static_branch_disable(&devmap_managed_key);
-}
-
-static int devmap_managed_enable_get(struct device *dev, struct dev_pagemap *pgmap)
-{
- if (!pgmap->ops || !pgmap->ops->page_free) {
- WARN(1, "Missing page_free method\n");
- return -EINVAL;
- }
-
- if (atomic_inc_return(&devmap_managed_enable) == 1)
- static_branch_enable(&devmap_managed_key);
- return devm_add_action_or_reset(dev, devmap_managed_enable_put, NULL);
-}
-#else
-static int devmap_managed_enable_get(struct device *dev, struct dev_pagemap *pgmap)
-{
- return -EINVAL;
-}
-#endif /* CONFIG_DEV_PAGEMAP_OPS */
-
-static void pgmap_array_delete(struct resource *res)
-{
- xa_store_range(&pgmap_array, PHYS_PFN(res->start), PHYS_PFN(res->end),
- NULL, GFP_KERNEL);
- synchronize_rcu();
-}
-
-static unsigned long pfn_first(struct dev_pagemap *pgmap)
-{
- return PHYS_PFN(pgmap->res.start) +
- vmem_altmap_offset(pgmap_altmap(pgmap));
-}
-
-static unsigned long pfn_end(struct dev_pagemap *pgmap)
-{
- const struct resource *res = &pgmap->res;
-
- return (res->start + resource_size(res)) >> PAGE_SHIFT;
-}
-
-static unsigned long pfn_next(unsigned long pfn)
-{
- if (pfn % 1024 == 0)
- cond_resched();
- return pfn + 1;
-}
-
-#define for_each_device_pfn(pfn, map) \
- for (pfn = pfn_first(map); pfn < pfn_end(map); pfn = pfn_next(pfn))
-
-static void dev_pagemap_kill(struct dev_pagemap *pgmap)
-{
- if (pgmap->ops && pgmap->ops->kill)
- pgmap->ops->kill(pgmap);
- else
- percpu_ref_kill(pgmap->ref);
-}
-
-static void dev_pagemap_cleanup(struct dev_pagemap *pgmap)
-{
- if (pgmap->ops && pgmap->ops->cleanup) {
- pgmap->ops->cleanup(pgmap);
- } else {
- wait_for_completion(&pgmap->done);
- percpu_ref_exit(pgmap->ref);
- }
-}
-
-static void devm_memremap_pages_release(void *data)
-{
- struct dev_pagemap *pgmap = data;
- struct device *dev = pgmap->dev;
- struct resource *res = &pgmap->res;
- unsigned long pfn;
- int nid;
-
- dev_pagemap_kill(pgmap);
- for_each_device_pfn(pfn, pgmap)
- put_page(pfn_to_page(pfn));
- dev_pagemap_cleanup(pgmap);
-
- /* pages are dead and unused, undo the arch mapping */
- nid = page_to_nid(pfn_to_page(PHYS_PFN(res->start)));
-
- mem_hotplug_begin();
- if (pgmap->type == MEMORY_DEVICE_PRIVATE) {
- pfn = PHYS_PFN(res->start);
- __remove_pages(page_zone(pfn_to_page(pfn)), pfn,
- PHYS_PFN(resource_size(res)), NULL);
- } else {
- arch_remove_memory(nid, res->start, resource_size(res),
- pgmap_altmap(pgmap));
- kasan_remove_zero_shadow(__va(res->start), resource_size(res));
- }
- mem_hotplug_done();
-
- untrack_pfn(NULL, PHYS_PFN(res->start), resource_size(res));
- pgmap_array_delete(res);
- dev_WARN_ONCE(dev, pgmap->altmap.alloc,
- "%s: failed to free all reserved pages\n", __func__);
-}
-
-static void dev_pagemap_percpu_release(struct percpu_ref *ref)
-{
- struct dev_pagemap *pgmap =
- container_of(ref, struct dev_pagemap, internal_ref);
-
- complete(&pgmap->done);
-}
-
-/**
- * devm_memremap_pages - remap and provide memmap backing for the given resource
- * @dev: hosting device for @res
- * @pgmap: pointer to a struct dev_pagemap
- *
- * Notes:
- * 1/ At a minimum the res and type members of @pgmap must be initialized
- * by the caller before passing it to this function
- *
- * 2/ The altmap field may optionally be initialized, in which case
- * PGMAP_ALTMAP_VALID must be set in pgmap->flags.
- *
- * 3/ The ref field may optionally be provided, in which pgmap->ref must be
- * 'live' on entry and will be killed and reaped at
- * devm_memremap_pages_release() time, or if this routine fails.
- *
- * 4/ res is expected to be a host memory range that could feasibly be
- * treated as a "System RAM" range, i.e. not a device mmio range, but
- * this is not enforced.
- */
-void *devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap)
-{
- struct resource *res = &pgmap->res;
- struct dev_pagemap *conflict_pgmap;
- struct mhp_restrictions restrictions = {
- /*
- * We do not want any optional features only our own memmap
- */
- .altmap = pgmap_altmap(pgmap),
- };
- pgprot_t pgprot = PAGE_KERNEL;
- int error, nid, is_ram;
- bool need_devmap_managed = true;
-
- switch (pgmap->type) {
- case MEMORY_DEVICE_PRIVATE:
- if (!IS_ENABLED(CONFIG_DEVICE_PRIVATE)) {
- WARN(1, "Device private memory not supported\n");
- return ERR_PTR(-EINVAL);
- }
- if (!pgmap->ops || !pgmap->ops->migrate_to_ram) {
- WARN(1, "Missing migrate_to_ram method\n");
- return ERR_PTR(-EINVAL);
- }
- break;
- case MEMORY_DEVICE_FS_DAX:
- if (!IS_ENABLED(CONFIG_ZONE_DEVICE) ||
- IS_ENABLED(CONFIG_FS_DAX_LIMITED)) {
- WARN(1, "File system DAX not supported\n");
- return ERR_PTR(-EINVAL);
- }
- break;
- case MEMORY_DEVICE_DEVDAX:
- case MEMORY_DEVICE_PCI_P2PDMA:
- need_devmap_managed = false;
- break;
- default:
- WARN(1, "Invalid pgmap type %d\n", pgmap->type);
- break;
- }
-
- if (!pgmap->ref) {
- if (pgmap->ops && (pgmap->ops->kill || pgmap->ops->cleanup))
- return ERR_PTR(-EINVAL);
-
- init_completion(&pgmap->done);
- error = percpu_ref_init(&pgmap->internal_ref,
- dev_pagemap_percpu_release, 0, GFP_KERNEL);
- if (error)
- return ERR_PTR(error);
- pgmap->ref = &pgmap->internal_ref;
- } else {
- if (!pgmap->ops || !pgmap->ops->kill || !pgmap->ops->cleanup) {
- WARN(1, "Missing reference count teardown definition\n");
- return ERR_PTR(-EINVAL);
- }
- }
-
- if (need_devmap_managed) {
- error = devmap_managed_enable_get(dev, pgmap);
- if (error)
- return ERR_PTR(error);
- }
-
- conflict_pgmap = get_dev_pagemap(PHYS_PFN(res->start), NULL);
- if (conflict_pgmap) {
- dev_WARN(dev, "Conflicting mapping in same section\n");
- put_dev_pagemap(conflict_pgmap);
- error = -ENOMEM;
- goto err_array;
- }
-
- conflict_pgmap = get_dev_pagemap(PHYS_PFN(res->end), NULL);
- if (conflict_pgmap) {
- dev_WARN(dev, "Conflicting mapping in same section\n");
- put_dev_pagemap(conflict_pgmap);
- error = -ENOMEM;
- goto err_array;
- }
-
- is_ram = region_intersects(res->start, resource_size(res),
- IORESOURCE_SYSTEM_RAM, IORES_DESC_NONE);
-
- if (is_ram != REGION_DISJOINT) {
- WARN_ONCE(1, "%s attempted on %s region %pr\n", __func__,
- is_ram == REGION_MIXED ? "mixed" : "ram", res);
- error = -ENXIO;
- goto err_array;
- }
-
- pgmap->dev = dev;
-
- error = xa_err(xa_store_range(&pgmap_array, PHYS_PFN(res->start),
- PHYS_PFN(res->end), pgmap, GFP_KERNEL));
- if (error)
- goto err_array;
-
- nid = dev_to_node(dev);
- if (nid < 0)
- nid = numa_mem_id();
-
- error = track_pfn_remap(NULL, &pgprot, PHYS_PFN(res->start), 0,
- resource_size(res));
- if (error)
- goto err_pfn_remap;
-
- mem_hotplug_begin();
-
- /*
- * For device private memory we call add_pages() as we only need to
- * allocate and initialize struct page for the device memory. More-
- * over the device memory is un-accessible thus we do not want to
- * create a linear mapping for the memory like arch_add_memory()
- * would do.
- *
- * For all other device memory types, which are accessible by
- * the CPU, we do want the linear mapping and thus use
- * arch_add_memory().
- */
- if (pgmap->type == MEMORY_DEVICE_PRIVATE) {
- error = add_pages(nid, PHYS_PFN(res->start),
- PHYS_PFN(resource_size(res)), &restrictions);
- } else {
- error = kasan_add_zero_shadow(__va(res->start), resource_size(res));
- if (error) {
- mem_hotplug_done();
- goto err_kasan;
- }
-
- error = arch_add_memory(nid, res->start, resource_size(res),
- &restrictions);
- }
-
- if (!error) {
- struct zone *zone;
-
- zone = &NODE_DATA(nid)->node_zones[ZONE_DEVICE];
- move_pfn_range_to_zone(zone, PHYS_PFN(res->start),
- PHYS_PFN(resource_size(res)), restrictions.altmap);
- }
-
- mem_hotplug_done();
- if (error)
- goto err_add_memory;
-
- /*
- * Initialization of the pages has been deferred until now in order
- * to allow us to do the work while not holding the hotplug lock.
- */
- memmap_init_zone_device(&NODE_DATA(nid)->node_zones[ZONE_DEVICE],
- PHYS_PFN(res->start),
- PHYS_PFN(resource_size(res)), pgmap);
- percpu_ref_get_many(pgmap->ref, pfn_end(pgmap) - pfn_first(pgmap));
-
- error = devm_add_action_or_reset(dev, devm_memremap_pages_release,
- pgmap);
- if (error)
- return ERR_PTR(error);
-
- return __va(res->start);
-
- err_add_memory:
- kasan_remove_zero_shadow(__va(res->start), resource_size(res));
- err_kasan:
- untrack_pfn(NULL, PHYS_PFN(res->start), resource_size(res));
- err_pfn_remap:
- pgmap_array_delete(res);
- err_array:
- dev_pagemap_kill(pgmap);
- dev_pagemap_cleanup(pgmap);
- return ERR_PTR(error);
-}
-EXPORT_SYMBOL_GPL(devm_memremap_pages);
-
-void devm_memunmap_pages(struct device *dev, struct dev_pagemap *pgmap)
-{
- devm_release_action(dev, devm_memremap_pages_release, pgmap);
-}
-EXPORT_SYMBOL_GPL(devm_memunmap_pages);
-
-unsigned long vmem_altmap_offset(struct vmem_altmap *altmap)
-{
- /* number of pfns from base where pfn_to_page() is valid */
- if (altmap)
- return altmap->reserve + altmap->free;
- return 0;
-}
-
-void vmem_altmap_free(struct vmem_altmap *altmap, unsigned long nr_pfns)
-{
- altmap->alloc -= nr_pfns;
-}
-
-/**
- * get_dev_pagemap() - take a new live reference on the dev_pagemap for @pfn
- * @pfn: page frame number to lookup page_map
- * @pgmap: optional known pgmap that already has a reference
- *
- * If @pgmap is non-NULL and covers @pfn it will be returned as-is. If @pgmap
- * is non-NULL but does not cover @pfn the reference to it will be released.
- */
-struct dev_pagemap *get_dev_pagemap(unsigned long pfn,
- struct dev_pagemap *pgmap)
-{
- resource_size_t phys = PFN_PHYS(pfn);
-
- /*
- * In the cached case we're already holding a live reference.
- */
- if (pgmap) {
- if (phys >= pgmap->res.start && phys <= pgmap->res.end)
- return pgmap;
- put_dev_pagemap(pgmap);
- }
-
- /* fall back to slow path lookup */
- rcu_read_lock();
- pgmap = xa_load(&pgmap_array, PHYS_PFN(phys));
- if (pgmap && !percpu_ref_tryget_live(pgmap->ref))
- pgmap = NULL;
- rcu_read_unlock();
-
- return pgmap;
-}
-EXPORT_SYMBOL_GPL(get_dev_pagemap);
-
-#ifdef CONFIG_DEV_PAGEMAP_OPS
-void __put_devmap_managed_page(struct page *page)
-{
- int count = page_ref_dec_return(page);
-
- /*
- * If refcount is 1 then page is freed and refcount is stable as nobody
- * holds a reference on the page.
- */
- if (count == 1) {
- /* Clear Active bit in case of parallel mark_page_accessed */
- __ClearPageActive(page);
- __ClearPageWaiters(page);
-
- mem_cgroup_uncharge(page);
-
- page->pgmap->ops->page_free(page);
- } else if (!count)
- __put_page(page);
-}
-EXPORT_SYMBOL(__put_devmap_managed_page);
-#endif /* CONFIG_DEV_PAGEMAP_OPS */
diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c
index 636ca6f88c8e..867b4bb6d4be 100644
--- a/kernel/sched/cpufreq_schedutil.c
+++ b/kernel/sched/cpufreq_schedutil.c
@@ -40,6 +40,7 @@ struct sugov_policy {
struct task_struct *thread;
bool work_in_progress;
+ bool limits_changed;
bool need_freq_update;
};
@@ -89,8 +90,11 @@ static bool sugov_should_update_freq(struct sugov_policy *sg_policy, u64 time)
!cpufreq_this_cpu_can_update(sg_policy->policy))
return false;
- if (unlikely(sg_policy->need_freq_update))
+ if (unlikely(sg_policy->limits_changed)) {
+ sg_policy->limits_changed = false;
+ sg_policy->need_freq_update = true;
return true;
+ }
delta_ns = time - sg_policy->last_freq_update_time;
@@ -437,7 +441,7 @@ static inline bool sugov_cpu_is_busy(struct sugov_cpu *sg_cpu) { return false; }
static inline void ignore_dl_rate_limit(struct sugov_cpu *sg_cpu, struct sugov_policy *sg_policy)
{
if (cpu_bw_dl(cpu_rq(sg_cpu->cpu)) > sg_cpu->bw_dl)
- sg_policy->need_freq_update = true;
+ sg_policy->limits_changed = true;
}
static void sugov_update_single(struct update_util_data *hook, u64 time,
@@ -457,7 +461,8 @@ static void sugov_update_single(struct update_util_data *hook, u64 time,
if (!sugov_should_update_freq(sg_policy, time))
return;
- busy = sugov_cpu_is_busy(sg_cpu);
+ /* Limits may have changed, don't skip frequency update */
+ busy = !sg_policy->need_freq_update && sugov_cpu_is_busy(sg_cpu);
util = sugov_get_util(sg_cpu);
max = sg_cpu->max;
@@ -831,6 +836,7 @@ static int sugov_start(struct cpufreq_policy *policy)
sg_policy->last_freq_update_time = 0;
sg_policy->next_freq = 0;
sg_policy->work_in_progress = false;
+ sg_policy->limits_changed = false;
sg_policy->need_freq_update = false;
sg_policy->cached_raw_freq = 0;
@@ -879,7 +885,7 @@ static void sugov_limits(struct cpufreq_policy *policy)
mutex_unlock(&sg_policy->work_lock);
}
- sg_policy->need_freq_update = true;
+ sg_policy->limits_changed = true;
}
struct cpufreq_governor schedutil_gov = {
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index ef5b9f6b1d42..46122edd8552 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -2088,17 +2088,13 @@ retry:
}
deactivate_task(rq, next_task, 0);
- sub_running_bw(&next_task->dl, &rq->dl);
- sub_rq_bw(&next_task->dl, &rq->dl);
set_task_cpu(next_task, later_rq->cpu);
- add_rq_bw(&next_task->dl, &later_rq->dl);
/*
* Update the later_rq clock here, because the clock is used
* by the cpufreq_update_util() inside __add_running_bw().
*/
update_rq_clock(later_rq);
- add_running_bw(&next_task->dl, &later_rq->dl);
activate_task(later_rq, next_task, ENQUEUE_NOCLOCK);
ret = 1;
@@ -2186,11 +2182,7 @@ static void pull_dl_task(struct rq *this_rq)
resched = true;
deactivate_task(src_rq, p, 0);
- sub_running_bw(&p->dl, &src_rq->dl);
- sub_rq_bw(&p->dl, &src_rq->dl);
set_task_cpu(p, this_cpu);
- add_rq_bw(&p->dl, &this_rq->dl);
- add_running_bw(&p->dl, &this_rq->dl);
activate_task(this_rq, p, 0);
dmin = p->dl.deadline;
diff --git a/kernel/sched/psi.c b/kernel/sched/psi.c
index 7acc632c3b82..23fbbcc414d5 100644
--- a/kernel/sched/psi.c
+++ b/kernel/sched/psi.c
@@ -1051,7 +1051,7 @@ struct psi_trigger *psi_trigger_create(struct psi_group *group,
if (!rcu_access_pointer(group->poll_kworker)) {
struct sched_param param = {
- .sched_priority = MAX_RT_PRIO - 1,
+ .sched_priority = 1,
};
struct kthread_worker *kworker;
@@ -1061,7 +1061,7 @@ struct psi_trigger *psi_trigger_create(struct psi_group *group,
mutex_unlock(&group->trigger_lock);
return ERR_CAST(kworker);
}
- sched_setscheduler(kworker->task, SCHED_FIFO, &param);
+ sched_setscheduler_nocheck(kworker->task, SCHED_FIFO, &param);
kthread_init_delayed_work(&group->poll_work,
psi_poll_work);
rcu_assign_pointer(group->poll_kworker, kworker);
diff --git a/kernel/signal.c b/kernel/signal.c
index 91b789dd6e72..e667be6907d7 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -349,7 +349,7 @@ void task_clear_jobctl_pending(struct task_struct *task, unsigned long mask)
* @task has %JOBCTL_STOP_PENDING set and is participating in a group stop.
* Group stop states are cleared and the group stop count is consumed if
* %JOBCTL_STOP_CONSUME was set. If the consumption completes the group
- * stop, the appropriate %SIGNAL_* flags are set.
+ * stop, the appropriate `SIGNAL_*` flags are set.
*
* CONTEXT:
* Must be called with @task->sighand->siglock held.
@@ -1885,6 +1885,7 @@ static void do_notify_pidfd(struct task_struct *task)
{
struct pid *pid;
+ WARN_ON(task->exit_state == 0);
pid = task_pid(task);
wake_up_all(&pid->wait_pidfd);
}
diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c
index 69ebf3c2f1b5..78af97163147 100644
--- a/kernel/trace/trace_functions_graph.c
+++ b/kernel/trace/trace_functions_graph.c
@@ -137,6 +137,13 @@ int trace_graph_entry(struct ftrace_graph_ent *trace)
if (trace_recursion_test(TRACE_GRAPH_NOTRACE_BIT))
return 0;
+ /*
+ * Do not trace a function if it's filtered by set_graph_notrace.
+ * Make the index of ret stack negative to indicate that it should
+ * ignore further functions. But it needs its own ret stack entry
+ * to recover the original index in order to continue tracing after
+ * returning from the function.
+ */
if (ftrace_graph_notrace_addr(trace->func)) {
trace_recursion_set(TRACE_GRAPH_NOTRACE_BIT);
/*
@@ -156,16 +163,6 @@ int trace_graph_entry(struct ftrace_graph_ent *trace)
return 0;
/*
- * Do not trace a function if it's filtered by set_graph_notrace.
- * Make the index of ret stack negative to indicate that it should
- * ignore further functions. But it needs its own ret stack entry
- * to recover the original index in order to continue tracing after
- * returning from the function.
- */
- if (ftrace_graph_notrace_addr(trace->func))
- return 1;
-
- /*
* Stop here if tracing_threshold is set. We only write function return
* events to the ring buffer.
*/
generated by cgit v1.2.3 (git 2.39.1) at 2025-02-03 16:00:30 +0100