From d9b8aadaffa65809d146cf0f8632a22a946367d7 Mon Sep 17 00:00:00 2001 From: Ilya Leoshkevich Date: Fri, 19 Jul 2019 11:18:15 +0200 Subject: bpf: fix narrower loads on s390 The very first check in test_pkt_md_access is failing on s390, which happens because loading a part of a struct __sk_buff field produces an incorrect result. The preprocessed code of the check is: { __u8 tmp = *((volatile __u8 *)&skb->len + ((sizeof(skb->len) - sizeof(__u8)) / sizeof(__u8))); if (tmp != ((*(volatile __u32 *)&skb->len) & 0xFF)) return 2; }; clang generates the following code for it: 0: 71 21 00 03 00 00 00 00 r2 = *(u8 *)(r1 + 3) 1: 61 31 00 00 00 00 00 00 r3 = *(u32 *)(r1 + 0) 2: 57 30 00 00 00 00 00 ff r3 &= 255 3: 5d 23 00 1d 00 00 00 00 if r2 != r3 goto +29 Finally, verifier transforms it to: 0: (61) r2 = *(u32 *)(r1 +104) 1: (bc) w2 = w2 2: (74) w2 >>= 24 3: (bc) w2 = w2 4: (54) w2 &= 255 5: (bc) w2 = w2 The problem is that when verifier emits the code to replace a partial load of a struct __sk_buff field (*(u8 *)(r1 + 3)) with a full load of struct sk_buff field (*(u32 *)(r1 + 104)), an optional shift and a bitwise AND, it assumes that the machine is little endian and incorrectly decides to use a shift. Adjust shift count calculation to account for endianness. Fixes: 31fd85816dbe ("bpf: permits narrower load from bpf program context fields") Signed-off-by: Ilya Leoshkevich Signed-off-by: Alexei Starovoitov --- kernel/bpf/verifier.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'kernel') 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, -- cgit v1.2.3 From 66d7780f18eae0232827fcffeaded39a6a168236 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 8 Jul 2019 11:51:56 -0700 Subject: dma-mapping: check pfn validity in dma_common_{mmap,get_sgtable} Check that the pfn returned from arch_dma_coherent_to_pfn refers to a valid page and reject the mmap / get_sgtable requests otherwise. Based on the arm implementation of the mmap and get_sgtable methods. Signed-off-by: Christoph Hellwig Tested-by: Vignesh Raghavendra --- kernel/dma/mapping.c | 13 +++++++++++-- 1 file changed, 11 insertions(+), 2 deletions(-) (limited to 'kernel') diff --git a/kernel/dma/mapping.c b/kernel/dma/mapping.c index 1f628e7ac709..b945239621d8 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); } @@ -170,7 +175,11 @@ 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)); } -- cgit v1.2.3 From c6622a425acd1d2f3a443cd39b490a8777b622d7 Mon Sep 17 00:00:00 2001 From: Nicolin Chen Date: Fri, 26 Jul 2019 12:34:32 -0700 Subject: dma-contiguous: do not overwrite align in dma_alloc_contiguous() The dma_alloc_contiguous() limits align at CONFIG_CMA_ALIGNMENT for cma_alloc() however it does not restore it for the fallback routine. This will result in a size mismatch between the allocation and free when running into the fallback routines after cma_alloc() fails, if the align is larger than CONFIG_CMA_ALIGNMENT. This patch adds a cma_align to take care of cma_alloc() and prevent the align from being overwritten. Fixes: fdaeec198ada ("dma-contiguous: add dma_{alloc,free}_contiguous() helpers") Reported-by: Dafna Hirschfeld Signed-off-by: Nicolin Chen Signed-off-by: Christoph Hellwig --- kernel/dma/contiguous.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'kernel') diff --git a/kernel/dma/contiguous.c b/kernel/dma/contiguous.c index bfc0c17f2a3d..ea8259f53eda 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 */ -- cgit v1.2.3 From f46cc0152501e46d1b3aa5e7eade61145070eab0 Mon Sep 17 00:00:00 2001 From: Nicolin Chen Date: Fri, 26 Jul 2019 12:34:33 -0700 Subject: dma-contiguous: page-align the size in dma_free_contiguous() According to the original dma_direct_alloc_pages() code: { unsigned int count = PAGE_ALIGN(size) >> PAGE_SHIFT; if (!dma_release_from_contiguous(dev, page, count)) __free_pages(page, get_order(size)); } The count parameter for dma_release_from_contiguous() was page aligned before the right-shifting operation, while the new API dma_free_contiguous() forgets to have PAGE_ALIGN() at the size. So this patch simply adds it to prevent any corner case. Fixes: fdaeec198ada ("dma-contiguous: add dma_{alloc,free}_contiguous() helpers") Signed-off-by: Nicolin Chen Reviewed-by: Christoph Hellwig Signed-off-by: Christoph Hellwig --- kernel/dma/contiguous.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/dma/contiguous.c b/kernel/dma/contiguous.c index ea8259f53eda..2bd410f934b3 100644 --- a/kernel/dma/contiguous.c +++ b/kernel/dma/contiguous.c @@ -267,7 +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)); } -- cgit v1.2.3 From 1caf7d50f46bd0388e38e653b146aa81700e8eb8 Mon Sep 17 00:00:00 2001 From: "Joel Fernandes (Google)" Date: Wed, 24 Jul 2019 12:48:16 -0400 Subject: pidfd: Add warning if exit_state is 0 during notification Previously a condition got missed where the pidfd waiters are awakened before the exit_state gets set. This can result in a missed notification [1] and the polling thread waiting forever. It is fixed now, however it would be nice to avoid this kind of issue going unnoticed in the future. So just add a warning to catch it in the future. /* References */ [1]: https://lore.kernel.org/lkml/20190717172100.261204-1-joel@joelfernandes.org/ Signed-off-by: Joel Fernandes (Google) Link: https://lore.kernel.org/r/20190724164816.201099-1-joel@joelfernandes.org Signed-off-by: Christian Brauner --- kernel/signal.c | 1 + 1 file changed, 1 insertion(+) (limited to 'kernel') diff --git a/kernel/signal.c b/kernel/signal.c index 91b789dd6e72..349f5a67f100 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -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); } -- cgit v1.2.3 From 30b692d3b390c6fe78a5064be0c4bbd44a41be59 Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Mon, 29 Jul 2019 17:48:24 +0200 Subject: exit: make setting exit_state consistent Since commit b191d6491be6 ("pidfd: fix a poll race when setting exit_state") we unconditionally set exit_state to EXIT_ZOMBIE before calling into do_notify_parent(). This was done to eliminate a race when querying exit_state in do_notify_pidfd(). Back then we decided to do the absolute minimal thing to fix this and not touch the rest of the exit_notify() function where exit_state is set. Since this fix has not caused any issues change the setting of exit_state to EXIT_DEAD in the autoreap case to account for the fact hat exit_state is set to EXIT_ZOMBIE unconditionally. This fix was planned but also explicitly requested in [1] and makes the whole code more consistent. /* References */ [1]: https://lore.kernel.org/lkml/CAHk-=wigcxGFR2szue4wavJtH5cYTTeNES=toUBVGsmX0rzX+g@mail.gmail.com Signed-off-by: Christian Brauner Acked-by: Oleg Nesterov Cc: Linus Torvalds --- kernel/exit.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'kernel') 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)) -- cgit v1.2.3 From 6c77221df96177da0520847ce91e33f539fb8b2d Mon Sep 17 00:00:00 2001 From: Changbin Du Date: Tue, 30 Jul 2019 22:08:50 +0800 Subject: fgraph: Remove redundant ftrace_graph_notrace_addr() test We already have tested it before. The second one should be removed. With this change, the performance should have little improvement. Link: http://lkml.kernel.org/r/20190730140850.7927-1-changbin.du@gmail.com Cc: stable@vger.kernel.org Fixes: 9cd2992f2d6c ("fgraph: Have set_graph_notrace only affect function_graph tracer") Signed-off-by: Changbin Du Signed-off-by: Steven Rostedt (VMware) --- kernel/trace/trace_functions_graph.c | 17 +++++++---------- 1 file changed, 7 insertions(+), 10 deletions(-) (limited to 'kernel') 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); /* @@ -155,16 +162,6 @@ int trace_graph_entry(struct ftrace_graph_ent *trace) if (ftrace_graph_ignore_irqs()) 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. -- cgit v1.2.3 From 68d8681e97bd1c90259f341c1695af05002070ef Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Fri, 2 Aug 2019 21:48:33 -0700 Subject: kernel/signal.c: fix a kernel-doc markup The kernel-doc parser doesn't handle expressions with %foo*. Instead, when an asterisk should be part of a constant, it uses an alternative notation: `foo*`. Link: http://lkml.kernel.org/r/7f18c2e0b5e39e6b7eb55ddeb043b8b260b49f2d.1563361575.git.mchehab+samsung@kernel.org Signed-off-by: Mauro Carvalho Chehab Cc: Deepa Dinamani Cc: Jonathan Corbet Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/signal.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/signal.c b/kernel/signal.c index 349f5a67f100..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. -- cgit v1.2.3 From 14c5cebad510c2875ca525f36605b47058769670 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 2 Aug 2019 21:49:26 -0700 Subject: memremap: move from kernel/ to mm/ memremap.c implements MM functionality for ZONE_DEVICE, so it really should be in the mm/ directory, not the kernel/ one. Link: http://lkml.kernel.org/r/20190722094143.18387-1-hch@lst.de Signed-off-by: Christoph Hellwig Reviewed-by: Anshuman Khandual Acked-by: Dan Williams Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/Makefile | 1 - kernel/memremap.c | 405 ------------------------------------------------------ mm/Makefile | 1 + mm/memremap.c | 405 ++++++++++++++++++++++++++++++++++++++++++++++++++++++ 4 files changed, 406 insertions(+), 406 deletions(-) delete mode 100644 kernel/memremap.c create mode 100644 mm/memremap.c (limited to 'kernel') 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/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 -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include - -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/mm/Makefile b/mm/Makefile index 338e528ad436..d0b295c3b764 100644 --- a/mm/Makefile +++ b/mm/Makefile @@ -102,5 +102,6 @@ obj-$(CONFIG_FRAME_VECTOR) += frame_vector.o obj-$(CONFIG_DEBUG_PAGE_REF) += debug_page_ref.o obj-$(CONFIG_HARDENED_USERCOPY) += usercopy.o obj-$(CONFIG_PERCPU_STATS) += percpu-stats.o +obj-$(CONFIG_ZONE_DEVICE) += memremap.o obj-$(CONFIG_HMM_MIRROR) += hmm.o obj-$(CONFIG_MEMFD_CREATE) += memfd.o diff --git a/mm/memremap.c b/mm/memremap.c new file mode 100644 index 000000000000..6ee03a816d67 --- /dev/null +++ b/mm/memremap.c @@ -0,0 +1,405 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright(c) 2015 Intel Corporation. All rights reserved. */ +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +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 */ -- cgit v1.2.3 From f4904815f97a934258445a8f763f6b6c48f007e7 Mon Sep 17 00:00:00 2001 From: Dietmar Eggemann Date: Fri, 2 Aug 2019 15:59:43 +0100 Subject: sched/deadline: Fix double accounting of rq/running bw in push & pull {push,pull}_dl_task() always calls {de,}activate_task() with .flags=0 which sets p->on_rq=TASK_ON_RQ_MIGRATING. {push,pull}_dl_task()->{de,}activate_task()->{de,en}queue_task()-> {de,en}queue_task_dl() calls {sub,add}_{running,rq}_bw() since p->on_rq==TASK_ON_RQ_MIGRATING. So {sub,add}_{running,rq}_bw() in {push,pull}_dl_task() is double-accounting for that task. Fix it by removing rq/running bw accounting in [push/pull]_dl_task(). Fixes: 7dd778841164 ("sched/core: Unify p->on_rq updates") Signed-off-by: Dietmar Eggemann Signed-off-by: Peter Zijlstra (Intel) Cc: Valentin Schneider Cc: Ingo Molnar Cc: Luca Abeni Cc: Daniel Bristot de Oliveira Cc: Juri Lelli Cc: Qais Yousef Link: https://lkml.kernel.org/r/20190802145945.18702-2-dietmar.eggemann@arm.com --- kernel/sched/deadline.c | 8 -------- 1 file changed, 8 deletions(-) (limited to 'kernel') 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; -- cgit v1.2.3 From 14f5c7b46a41a595fc61db37f55721714729e59e Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Thu, 1 Aug 2019 12:41:31 +0200 Subject: sched/psi: Reduce psimon FIFO priority PSI defaults to a FIFO-99 thread, reduce this to FIFO-1. FIFO-99 is the very highest priority available to SCHED_FIFO and it not a suitable default; it would indicate the psi work is the most important work on the machine. Since Real-Time tasks will have pre-allocated memory and locked it in place, Real-Time tasks do not care about PSI. All it needs is to be above OTHER. Signed-off-by: Peter Zijlstra (Intel) Acked-by: Johannes Weiner Tested-by: Suren Baghdasaryan Cc: Thomas Gleixner --- kernel/sched/psi.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/sched/psi.c b/kernel/sched/psi.c index 7acc632c3b82..7fe2c5fd26b5 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; -- cgit v1.2.3 From 04e048cf09d7b5fc995817cdc5ae1acd4482429c Mon Sep 17 00:00:00 2001 From: Suren Baghdasaryan Date: Mon, 29 Jul 2019 18:33:10 -0700 Subject: sched/psi: Do not require setsched permission from the trigger creator When a process creates a new trigger by writing into /proc/pressure/* files, permissions to write such a file should be used to determine whether the process is allowed to do so or not. Current implementation would also require such a process to have setsched capability. Setting of psi trigger thread's scheduling policy is an implementation detail and should not be exposed to the user level. Remove the permission check by using _nocheck version of the function. Suggested-by: Nick Kralevich Signed-off-by: Suren Baghdasaryan Signed-off-by: Peter Zijlstra (Intel) Cc: lizefan@huawei.com Cc: mingo@redhat.com Cc: akpm@linux-foundation.org Cc: kernel-team@android.com Cc: dennisszhou@gmail.com Cc: dennis@kernel.org Cc: hannes@cmpxchg.org Cc: axboe@kernel.dk Link: https://lkml.kernel.org/r/20190730013310.162367-1-surenb@google.com --- kernel/sched/psi.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/sched/psi.c b/kernel/sched/psi.c index 7fe2c5fd26b5..23fbbcc414d5 100644 --- a/kernel/sched/psi.c +++ b/kernel/sched/psi.c @@ -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, ¶m); + sched_setscheduler_nocheck(kworker->task, SCHED_FIFO, ¶m); kthread_init_delayed_work(&group->poll_work, psi_poll_work); rcu_assign_pointer(group->poll_kworker, kworker); -- cgit v1.2.3 From 491beed3b102b6e6c0e7734200661242226e3933 Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Mon, 5 Aug 2019 09:19:06 +0800 Subject: genirq/affinity: Create affinity mask for single vector Since commit c66d4bd110a1f8 ("genirq/affinity: Add new callback for (re)calculating interrupt sets"), irq_create_affinity_masks() returns NULL in case of single vector. This change has caused regression on some drivers, such as lpfc. The problem is that single vector requests can happen in some generic cases: 1) kdump kernel 2) irq vectors resource is close to exhaustion. If in that situation the affinity mask for a single vector is not created, every caller has to handle the special case. There is no reason why the mask cannot be created, so remove the check for a single vector and create the mask. Fixes: c66d4bd110a1f8 ("genirq/affinity: Add new callback for (re)calculating interrupt sets") Signed-off-by: Ming Lei Signed-off-by: Thomas Gleixner Cc: stable@vger.kernel.org Link: https://lkml.kernel.org/r/20190805011906.5020-1-ming.lei@redhat.com --- kernel/irq/affinity.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) (limited to 'kernel') 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; -- cgit v1.2.3