diff options
| -rw-r--r-- | .mailmap | 5 | ||||
| -rw-r--r-- | MAINTAINERS | 30 | ||||
| -rw-r--r-- | include/linux/maple_tree.h | 2 | ||||
| -rw-r--r-- | include/linux/mm.h | 2 | ||||
| -rw-r--r-- | kernel/liveupdate/kexec_handover.c | 21 | ||||
| -rw-r--r-- | kernel/liveupdate/luo_session.c | 15 | ||||
| -rw-r--r-- | lib/maple_tree.c | 2 | ||||
| -rw-r--r-- | lib/test_maple_tree.c | 4 | ||||
| -rw-r--r-- | mm/damon/lru_sort.c | 85 | ||||
| -rw-r--r-- | mm/damon/reclaim.c | 85 | ||||
| -rw-r--r-- | mm/damon/stat.c | 30 | ||||
| -rw-r--r-- | mm/damon/sysfs-schemes.c | 24 | ||||
| -rw-r--r-- | mm/hugetlb_cma.c | 1 | ||||
| -rw-r--r-- | mm/memcontrol.c | 29 | ||||
| -rw-r--r-- | mm/page-writeback.c | 16 | ||||
| -rw-r--r-- | mm/userfaultfd.c | 12 | ||||
| -rw-r--r-- | mm/util.c | 26 | ||||
| -rw-r--r-- | mm/vma.c | 3 | ||||
| -rw-r--r-- | mm/vmalloc.c | 2 | ||||
| -rw-r--r-- | tools/testing/radix-tree/maple.c | 2 | ||||
| -rw-r--r-- | tools/testing/selftests/mm/config | 1 | ||||
| -rw-r--r-- | tools/testing/vma/include/dup.h | 2 | ||||
| -rw-r--r-- | tools/testing/vma/include/stubs.h | 3 |
23 files changed, 262 insertions, 140 deletions
@@ -207,6 +207,7 @@ Claudiu Beznea <claudiu.beznea@tuxon.dev> <claudiu.beznea@microchip.com> Colin Ian King <colin.i.king@gmail.com> <colin.king@canonical.com> Corey Minyard <minyard@acm.org> Damian Hobson-Garcia <dhobsong@igel.co.jp> +Dan Carpenter <error27@gmail.com> <dan.carpenter@linaro.org> Dan Carpenter <error27@gmail.com> <dan.carpenter@oracle.com> Dan Williams <djbw@kernel.org> <dan.j.williams@intel.com> Daniel Borkmann <daniel@iogearbox.net> <danborkmann@googlemail.com> @@ -495,6 +496,7 @@ Leon Romanovsky <leon@kernel.org> <leon@leon.nu> Leon Romanovsky <leon@kernel.org> <leonro@mellanox.com> Leon Romanovsky <leon@kernel.org> <leonro@nvidia.com> Leo Yan <leo.yan@linux.dev> <leo.yan@linaro.org> +Liam R. Howlett <liam@infradead.org> <Liam.Howlett@oracle.com> Liam Mark <quic_lmark@quicinc.com> <lmark@codeaurora.org> Linas Vepstas <linas@austin.ibm.com> Linus Lüssing <linus.luessing@c0d3.blue> <linus.luessing@ascom.ch> @@ -505,6 +507,8 @@ Linus Walleij <linusw@kernel.org> <linus.walleij@stericsson.com> Linus Walleij <linusw@kernel.org> <linus.walleij@linaro.org> Linus Walleij <linusw@kernel.org> <triad@df.lth.se> <linux-hardening@vger.kernel.org> <kernel-hardening@lists.openwall.com> +Li Wang <li.wang@linux.dev> <liwang@redhat.com> +Li Wang <li.wang@linux.dev> <wangli.ahau@gmail.com> Li Yang <leoyang.li@nxp.com> <leoli@freescale.com> Li Yang <leoyang.li@nxp.com> <leo@zh-kernel.org> Lior David <quic_liord@quicinc.com> <liord@codeaurora.org> @@ -687,6 +691,7 @@ Punit Agrawal <punitagrawal@gmail.com> <punit.agrawal@arm.com> Puranjay Mohan <puranjay@kernel.org> <puranjay12@gmail.com> Qais Yousef <qyousef@layalina.io> <qais.yousef@imgtec.com> Qais Yousef <qyousef@layalina.io> <qais.yousef@arm.com> +Qi Zheng <qi.zheng@linux.dev> <zhengqi.arch@bytedance.com> Quentin Monnet <qmo@kernel.org> <quentin.monnet@netronome.com> Quentin Monnet <qmo@kernel.org> <quentin@isovalent.com> Quentin Perret <qperret@qperret.net> <quentin.perret@arm.com> diff --git a/MAINTAINERS b/MAINTAINERS index 27a073f53cea..82db3e6722bf 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -13860,7 +13860,6 @@ M: Pratyush Yadav <pratyush@kernel.org> R: Dave Young <ruirui.yang@linux.dev> L: kexec@lists.infradead.org S: Maintained -W: http://lse.sourceforge.net/kdump/ F: Documentation/admin-guide/kdump/ F: fs/proc/vmcore.c F: include/linux/crash_core.h @@ -15252,7 +15251,7 @@ M: Andrea Cervesato <andrea.cervesato@suse.com> M: Cyril Hrubis <chrubis@suse.cz> M: Jan Stancek <jstancek@redhat.com> M: Petr Vorel <pvorel@suse.cz> -M: Li Wang <liwang@redhat.com> +M: Li Wang <li.wang@linux.dev> M: Yang Xu <xuyang2018.jy@fujitsu.com> M: Xiao Yang <yangx.jy@fujitsu.com> L: ltp@lists.linux.it (subscribers-only) @@ -15399,7 +15398,7 @@ F: include/net/netns/mctp.h F: net/mctp/ MAPLE TREE -M: Liam R. Howlett <Liam.Howlett@oracle.com> +M: Liam R. Howlett <liam@infradead.org> R: Alice Ryhl <aliceryhl@google.com> R: Andrew Ballance <andrewjballance@gmail.com> L: maple-tree@lists.infradead.org @@ -16759,7 +16758,7 @@ MEMORY MANAGEMENT - CORE M: Andrew Morton <akpm@linux-foundation.org> M: David Hildenbrand <david@kernel.org> R: Lorenzo Stoakes <ljs@kernel.org> -R: Liam R. Howlett <Liam.Howlett@oracle.com> +R: Liam R. Howlett <liam@infradead.org> R: Vlastimil Babka <vbabka@kernel.org> R: Mike Rapoport <rppt@kernel.org> R: Suren Baghdasaryan <surenb@google.com> @@ -16805,7 +16804,7 @@ F: mm/sparse.c F: mm/util.c F: mm/vmpressure.c F: mm/vmstat.c -N: include/linux/page[-_]* +N: include\/linux\/page[-_][a-zA-Z]* MEMORY MANAGEMENT - EXECMEM M: Andrew Morton <akpm@linux-foundation.org> @@ -16895,7 +16894,7 @@ MEMORY MANAGEMENT - MISC M: Andrew Morton <akpm@linux-foundation.org> M: David Hildenbrand <david@kernel.org> R: Lorenzo Stoakes <ljs@kernel.org> -R: Liam R. Howlett <Liam.Howlett@oracle.com> +R: Liam R. Howlett <liam@infradead.org> R: Vlastimil Babka <vbabka@kernel.org> R: Mike Rapoport <rppt@kernel.org> R: Suren Baghdasaryan <surenb@google.com> @@ -16962,6 +16961,7 @@ S: Maintained F: include/linux/compaction.h F: include/linux/gfp.h F: include/linux/page-isolation.h +F: include/linux/pageblock-flags.h F: mm/compaction.c F: mm/debug_page_alloc.c F: mm/debug_page_ref.c @@ -16983,7 +16983,7 @@ M: Andrew Morton <akpm@linux-foundation.org> M: Johannes Weiner <hannes@cmpxchg.org> R: David Hildenbrand <david@kernel.org> R: Michal Hocko <mhocko@kernel.org> -R: Qi Zheng <zhengqi.arch@bytedance.com> +R: Qi Zheng <qi.zheng@linux.dev> R: Shakeel Butt <shakeel.butt@linux.dev> R: Lorenzo Stoakes <ljs@kernel.org> L: linux-mm@kvack.org @@ -16996,7 +16996,7 @@ M: Andrew Morton <akpm@linux-foundation.org> M: David Hildenbrand <david@kernel.org> M: Lorenzo Stoakes <ljs@kernel.org> R: Rik van Riel <riel@surriel.com> -R: Liam R. Howlett <Liam.Howlett@oracle.com> +R: Liam R. Howlett <liam@infradead.org> R: Vlastimil Babka <vbabka@kernel.org> R: Harry Yoo <harry@kernel.org> R: Jann Horn <jannh@google.com> @@ -17043,7 +17043,7 @@ M: David Hildenbrand <david@kernel.org> M: Lorenzo Stoakes <ljs@kernel.org> R: Zi Yan <ziy@nvidia.com> R: Baolin Wang <baolin.wang@linux.alibaba.com> -R: Liam R. Howlett <Liam.Howlett@oracle.com> +R: Liam R. Howlett <liam@infradead.org> R: Nico Pache <npache@redhat.com> R: Ryan Roberts <ryan.roberts@arm.com> R: Dev Jain <dev.jain@arm.com> @@ -17081,7 +17081,7 @@ F: tools/testing/selftests/mm/uffd-*.[ch] MEMORY MANAGEMENT - RUST M: Alice Ryhl <aliceryhl@google.com> R: Lorenzo Stoakes <ljs@kernel.org> -R: Liam R. Howlett <Liam.Howlett@oracle.com> +R: Liam R. Howlett <liam@infradead.org> L: linux-mm@kvack.org L: rust-for-linux@vger.kernel.org S: Maintained @@ -17095,7 +17095,7 @@ F: rust/kernel/page.rs MEMORY MAPPING M: Andrew Morton <akpm@linux-foundation.org> -M: Liam R. Howlett <Liam.Howlett@oracle.com> +M: Liam R. Howlett <liam@infradead.org> M: Lorenzo Stoakes <ljs@kernel.org> R: Vlastimil Babka <vbabka@kernel.org> R: Jann Horn <jannh@google.com> @@ -17127,7 +17127,7 @@ F: tools/testing/vma/ MEMORY MAPPING - LOCKING M: Andrew Morton <akpm@linux-foundation.org> M: Suren Baghdasaryan <surenb@google.com> -M: Liam R. Howlett <Liam.Howlett@oracle.com> +M: Liam R. Howlett <liam@infradead.org> M: Lorenzo Stoakes <ljs@kernel.org> R: Vlastimil Babka <vbabka@kernel.org> R: Shakeel Butt <shakeel.butt@linux.dev> @@ -17142,7 +17142,7 @@ F: mm/mmap_lock.c MEMORY MAPPING - MADVISE (MEMORY ADVICE) M: Andrew Morton <akpm@linux-foundation.org> -M: Liam R. Howlett <Liam.Howlett@oracle.com> +M: Liam R. Howlett <liam@infradead.org> M: Lorenzo Stoakes <ljs@kernel.org> M: David Hildenbrand <david@kernel.org> R: Vlastimil Babka <vbabka@kernel.org> @@ -23403,7 +23403,7 @@ RUST [ALLOC] M: Danilo Krummrich <dakr@kernel.org> R: Lorenzo Stoakes <ljs@kernel.org> R: Vlastimil Babka <vbabka@kernel.org> -R: Liam R. Howlett <Liam.Howlett@oracle.com> +R: Liam R. Howlett <liam@infradead.org> R: Uladzislau Rezki <urezki@gmail.com> L: rust-for-linux@vger.kernel.org S: Maintained @@ -24348,7 +24348,7 @@ F: include/media/i2c/rj54n1cb0c.h SHRINKER M: Andrew Morton <akpm@linux-foundation.org> M: Dave Chinner <david@fromorbit.com> -R: Qi Zheng <zhengqi.arch@bytedance.com> +R: Qi Zheng <qi.zheng@linux.dev> R: Roman Gushchin <roman.gushchin@linux.dev> R: Muchun Song <muchun.song@linux.dev> L: linux-mm@kvack.org diff --git a/include/linux/maple_tree.h b/include/linux/maple_tree.h index 0c464eade1d6..4a5631906aff 100644 --- a/include/linux/maple_tree.h +++ b/include/linux/maple_tree.h @@ -4,7 +4,7 @@ /* * Maple Tree - An RCU-safe adaptive tree for storing ranges * Copyright (c) 2018-2022 Oracle - * Authors: Liam R. Howlett <Liam.Howlett@Oracle.com> + * Authors: Liam R. Howlett <liam@infradead.org> * Matthew Wilcox <willy@infradead.org> */ diff --git a/include/linux/mm.h b/include/linux/mm.h index 0b776907152e..af23453e9dbd 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -4391,7 +4391,7 @@ static inline void mmap_action_map_kernel_pages_full(struct vm_area_desc *desc, int mmap_action_prepare(struct vm_area_desc *desc); int mmap_action_complete(struct vm_area_struct *vma, - struct mmap_action *action); + struct mmap_action *action, bool is_compat); /* Look up the first VMA which exactly match the interval vm_start ... vm_end */ static inline struct vm_area_struct *find_exact_vma(struct mm_struct *mm, diff --git a/kernel/liveupdate/kexec_handover.c b/kernel/liveupdate/kexec_handover.c index 94762de1fe5f..18509d8082ea 100644 --- a/kernel/liveupdate/kexec_handover.c +++ b/kernel/liveupdate/kexec_handover.c @@ -762,19 +762,24 @@ int kho_add_subtree(const char *name, void *blob, size_t size) goto out_pack; } - err = fdt_setprop(root_fdt, off, KHO_SUB_TREE_PROP_NAME, - &phys, sizeof(phys)); - if (err < 0) - goto out_pack; + fdt_err = fdt_setprop(root_fdt, off, KHO_SUB_TREE_PROP_NAME, + &phys, sizeof(phys)); + if (fdt_err < 0) + goto out_del_node; - err = fdt_setprop(root_fdt, off, KHO_SUB_TREE_SIZE_PROP_NAME, - &size_u64, sizeof(size_u64)); - if (err < 0) - goto out_pack; + fdt_err = fdt_setprop(root_fdt, off, KHO_SUB_TREE_SIZE_PROP_NAME, + &size_u64, sizeof(size_u64)); + if (fdt_err < 0) + goto out_del_node; WARN_ON_ONCE(kho_debugfs_blob_add(&kho_out.dbg, name, blob, size, false)); + err = 0; + goto out_pack; + +out_del_node: + fdt_del_node(root_fdt, off); out_pack: fdt_pack(root_fdt); diff --git a/kernel/liveupdate/luo_session.c b/kernel/liveupdate/luo_session.c index a3327a28fc1f..7a42385dabe2 100644 --- a/kernel/liveupdate/luo_session.c +++ b/kernel/liveupdate/luo_session.c @@ -514,11 +514,12 @@ int luo_session_deserialize(void) { struct luo_session_header *sh = &luo_session_global.incoming; static bool is_deserialized; - static int err; + static int saved_err; + int err; /* If has been deserialized, always return the same error code */ if (is_deserialized) - return err; + return saved_err; is_deserialized = true; if (!sh->active) @@ -547,7 +548,8 @@ int luo_session_deserialize(void) pr_warn("Failed to allocate session [%.*s] during deserialization %pe\n", (int)sizeof(sh->ser[i].name), sh->ser[i].name, session); - return PTR_ERR(session); + err = PTR_ERR(session); + goto save_err; } err = luo_session_insert(sh, session); @@ -555,7 +557,7 @@ int luo_session_deserialize(void) pr_warn("Failed to insert session [%s] %pe\n", session->name, ERR_PTR(err)); luo_session_free(session); - return err; + goto save_err; } scoped_guard(mutex, &session->mutex) { @@ -565,7 +567,7 @@ int luo_session_deserialize(void) if (err) { pr_warn("Failed to deserialize files for session [%s] %pe\n", session->name, ERR_PTR(err)); - return err; + goto save_err; } } @@ -574,6 +576,9 @@ int luo_session_deserialize(void) sh->ser = NULL; return 0; +save_err: + saved_err = err; + return err; } int luo_session_serialize(void) diff --git a/lib/maple_tree.c b/lib/maple_tree.c index d18d7ed9ab67..60ae5e6fc1ee 100644 --- a/lib/maple_tree.c +++ b/lib/maple_tree.c @@ -2,7 +2,7 @@ /* * Maple Tree implementation * Copyright (c) 2018-2022 Oracle Corporation - * Authors: Liam R. Howlett <Liam.Howlett@oracle.com> + * Authors: Liam R. Howlett <liam@infradead.org> * Matthew Wilcox <willy@infradead.org> * Copyright (c) 2023 ByteDance * Author: Peng Zhang <zhangpeng.00@bytedance.com> diff --git a/lib/test_maple_tree.c b/lib/test_maple_tree.c index 434d8a2fdd99..b9367c61e8b5 100644 --- a/lib/test_maple_tree.c +++ b/lib/test_maple_tree.c @@ -2,7 +2,7 @@ /* * test_maple_tree.c: Test the maple tree API * Copyright (c) 2018-2022 Oracle Corporation - * Author: Liam R. Howlett <Liam.Howlett@Oracle.com> + * Author: Liam R. Howlett <liam@infradead.org> * * Any tests that only require the interface of the tree. */ @@ -4021,6 +4021,6 @@ static void __exit maple_tree_harvest(void) module_init(maple_tree_seed); module_exit(maple_tree_harvest); -MODULE_AUTHOR("Liam R. Howlett <Liam.Howlett@Oracle.com>"); +MODULE_AUTHOR("Liam R. Howlett <liam@infradead.org>"); MODULE_DESCRIPTION("maple tree API test module"); MODULE_LICENSE("GPL"); diff --git a/mm/damon/lru_sort.c b/mm/damon/lru_sort.c index 554559d72976..8494040b1ee4 100644 --- a/mm/damon/lru_sort.c +++ b/mm/damon/lru_sort.c @@ -161,15 +161,6 @@ module_param(monitor_region_end, ulong, 0600); */ static unsigned long addr_unit __read_mostly = 1; -/* - * PID of the DAMON thread - * - * If DAMON_LRU_SORT is enabled, this becomes the PID of the worker thread. - * Else, -1. - */ -static int kdamond_pid __read_mostly = -1; -module_param(kdamond_pid, int, 0400); - static struct damos_stat damon_lru_sort_hot_stat; DEFINE_DAMON_MODULES_DAMOS_STATS_PARAMS(damon_lru_sort_hot_stat, lru_sort_tried_hot_regions, lru_sorted_hot_regions, @@ -386,12 +377,8 @@ static int damon_lru_sort_turn(bool on) { int err; - if (!on) { - err = damon_stop(&ctx, 1); - if (!err) - kdamond_pid = -1; - return err; - } + if (!on) + return damon_stop(&ctx, 1); err = damon_lru_sort_apply_parameters(); if (err) @@ -400,9 +387,6 @@ static int damon_lru_sort_turn(bool on) err = damon_start(&ctx, 1, true); if (err) return err; - kdamond_pid = damon_kdamond_pid(ctx); - if (kdamond_pid < 0) - return kdamond_pid; return damon_call(ctx, &call_control); } @@ -430,42 +414,83 @@ module_param_cb(addr_unit, &addr_unit_param_ops, &addr_unit, 0600); MODULE_PARM_DESC(addr_unit, "Scale factor for DAMON_LRU_SORT to ops address conversion (default: 1)"); +static bool damon_lru_sort_enabled(void) +{ + if (!ctx) + return false; + return damon_is_running(ctx); +} + static int damon_lru_sort_enabled_store(const char *val, const struct kernel_param *kp) { - bool is_enabled = enabled; - bool enable; int err; - err = kstrtobool(val, &enable); + err = kstrtobool(val, &enabled); if (err) return err; - if (is_enabled == enable) + if (damon_lru_sort_enabled() == enabled) return 0; /* Called before init function. The function will handle this. */ if (!damon_initialized()) - goto set_param_out; + return 0; - err = damon_lru_sort_turn(enable); - if (err) - return err; + return damon_lru_sort_turn(enabled); +} -set_param_out: - enabled = enable; - return err; +static int damon_lru_sort_enabled_load(char *buffer, + const struct kernel_param *kp) +{ + return sprintf(buffer, "%c\n", damon_lru_sort_enabled() ? 'Y' : 'N'); } static const struct kernel_param_ops enabled_param_ops = { .set = damon_lru_sort_enabled_store, - .get = param_get_bool, + .get = damon_lru_sort_enabled_load, }; module_param_cb(enabled, &enabled_param_ops, &enabled, 0600); MODULE_PARM_DESC(enabled, "Enable or disable DAMON_LRU_SORT (default: disabled)"); +static int damon_lru_sort_kdamond_pid_store(const char *val, + const struct kernel_param *kp) +{ + /* + * kdamond_pid is read-only, but kernel command line could write it. + * Do nothing here. + */ + return 0; +} + +static int damon_lru_sort_kdamond_pid_load(char *buffer, + const struct kernel_param *kp) +{ + int kdamond_pid = -1; + + if (ctx) { + kdamond_pid = damon_kdamond_pid(ctx); + if (kdamond_pid < 0) + kdamond_pid = -1; + } + return sprintf(buffer, "%d\n", kdamond_pid); +} + +static const struct kernel_param_ops kdamond_pid_param_ops = { + .set = damon_lru_sort_kdamond_pid_store, + .get = damon_lru_sort_kdamond_pid_load, +}; + +/* + * PID of the DAMON thread + * + * If DAMON_LRU_SORT is enabled, this becomes the PID of the worker thread. + * Else, -1. + */ +module_param_cb(kdamond_pid, &kdamond_pid_param_ops, NULL, 0400); + static int __init damon_lru_sort_init(void) { int err; diff --git a/mm/damon/reclaim.c b/mm/damon/reclaim.c index 86da14778658..fe7fce26cf6c 100644 --- a/mm/damon/reclaim.c +++ b/mm/damon/reclaim.c @@ -144,15 +144,6 @@ static unsigned long addr_unit __read_mostly = 1; static bool skip_anon __read_mostly; module_param(skip_anon, bool, 0600); -/* - * PID of the DAMON thread - * - * If DAMON_RECLAIM is enabled, this becomes the PID of the worker thread. - * Else, -1. - */ -static int kdamond_pid __read_mostly = -1; -module_param(kdamond_pid, int, 0400); - static struct damos_stat damon_reclaim_stat; DEFINE_DAMON_MODULES_DAMOS_STATS_PARAMS(damon_reclaim_stat, reclaim_tried_regions, reclaimed_regions, quota_exceeds); @@ -288,12 +279,8 @@ static int damon_reclaim_turn(bool on) { int err; - if (!on) { - err = damon_stop(&ctx, 1); - if (!err) - kdamond_pid = -1; - return err; - } + if (!on) + return damon_stop(&ctx, 1); err = damon_reclaim_apply_parameters(); if (err) @@ -302,9 +289,6 @@ static int damon_reclaim_turn(bool on) err = damon_start(&ctx, 1, true); if (err) return err; - kdamond_pid = damon_kdamond_pid(ctx); - if (kdamond_pid < 0) - return kdamond_pid; return damon_call(ctx, &call_control); } @@ -332,42 +316,83 @@ module_param_cb(addr_unit, &addr_unit_param_ops, &addr_unit, 0600); MODULE_PARM_DESC(addr_unit, "Scale factor for DAMON_RECLAIM to ops address conversion (default: 1)"); +static bool damon_reclaim_enabled(void) +{ + if (!ctx) + return false; + return damon_is_running(ctx); +} + static int damon_reclaim_enabled_store(const char *val, const struct kernel_param *kp) { - bool is_enabled = enabled; - bool enable; int err; - err = kstrtobool(val, &enable); + err = kstrtobool(val, &enabled); if (err) return err; - if (is_enabled == enable) + if (damon_reclaim_enabled() == enabled) return 0; /* Called before init function. The function will handle this. */ if (!damon_initialized()) - goto set_param_out; + return 0; - err = damon_reclaim_turn(enable); - if (err) - return err; + return damon_reclaim_turn(enabled); +} -set_param_out: - enabled = enable; - return err; +static int damon_reclaim_enabled_load(char *buffer, + const struct kernel_param *kp) +{ + return sprintf(buffer, "%c\n", damon_reclaim_enabled() ? 'Y' : 'N'); } static const struct kernel_param_ops enabled_param_ops = { .set = damon_reclaim_enabled_store, - .get = param_get_bool, + .get = damon_reclaim_enabled_load, }; module_param_cb(enabled, &enabled_param_ops, &enabled, 0600); MODULE_PARM_DESC(enabled, "Enable or disable DAMON_RECLAIM (default: disabled)"); +static int damon_reclaim_kdamond_pid_store(const char *val, + const struct kernel_param *kp) +{ + /* + * kdamond_pid is read-only, but kernel command line could write it. + * Do nothing here. + */ + return 0; +} + +static int damon_reclaim_kdamond_pid_load(char *buffer, + const struct kernel_param *kp) +{ + int kdamond_pid = -1; + + if (ctx) { + kdamond_pid = damon_kdamond_pid(ctx); + if (kdamond_pid < 0) + kdamond_pid = -1; + } + return sprintf(buffer, "%d\n", kdamond_pid); +} + +static const struct kernel_param_ops kdamond_pid_param_ops = { + .set = damon_reclaim_kdamond_pid_store, + .get = damon_reclaim_kdamond_pid_load, +}; + +/* + * PID of the DAMON thread + * + * If DAMON_RECLAIM is enabled, this becomes the PID of the worker thread. + * Else, -1. + */ +module_param_cb(kdamond_pid, &kdamond_pid_param_ops, NULL, 0400); + static int __init damon_reclaim_init(void) { int err; diff --git a/mm/damon/stat.c b/mm/damon/stat.c index 99ba346f9e32..3951b762cbdd 100644 --- a/mm/damon/stat.c +++ b/mm/damon/stat.c @@ -19,14 +19,17 @@ static int damon_stat_enabled_store( const char *val, const struct kernel_param *kp); +static int damon_stat_enabled_load(char *buffer, + const struct kernel_param *kp); + static const struct kernel_param_ops enabled_param_ops = { .set = damon_stat_enabled_store, - .get = param_get_bool, + .get = damon_stat_enabled_load, }; static bool enabled __read_mostly = IS_ENABLED( CONFIG_DAMON_STAT_ENABLED_DEFAULT); -module_param_cb(enabled, &enabled_param_ops, &enabled, 0600); +module_param_cb(enabled, &enabled_param_ops, NULL, 0600); MODULE_PARM_DESC(enabled, "Enable of disable DAMON_STAT"); static unsigned long estimated_memory_bandwidth __read_mostly; @@ -273,17 +276,23 @@ static void damon_stat_stop(void) damon_stat_context = NULL; } +static bool damon_stat_enabled(void) +{ + if (!damon_stat_context) + return false; + return damon_is_running(damon_stat_context); +} + static int damon_stat_enabled_store( const char *val, const struct kernel_param *kp) { - bool is_enabled = enabled; int err; err = kstrtobool(val, &enabled); if (err) return err; - if (is_enabled == enabled) + if (damon_stat_enabled() == enabled) return 0; if (!damon_initialized()) @@ -293,16 +302,17 @@ static int damon_stat_enabled_store( */ return 0; - if (enabled) { - err = damon_stat_start(); - if (err) - enabled = false; - return err; - } + if (enabled) + return damon_stat_start(); damon_stat_stop(); return 0; } +static int damon_stat_enabled_load(char *buffer, const struct kernel_param *kp) +{ + return sprintf(buffer, "%c\n", damon_stat_enabled() ? 'Y' : 'N'); +} + static int __init damon_stat_init(void) { int err = 0; diff --git a/mm/damon/sysfs-schemes.c b/mm/damon/sysfs-schemes.c index 5186966dafb3..245d63808411 100644 --- a/mm/damon/sysfs-schemes.c +++ b/mm/damon/sysfs-schemes.c @@ -533,9 +533,14 @@ static ssize_t memcg_path_show(struct kobject *kobj, { struct damon_sysfs_scheme_filter *filter = container_of(kobj, struct damon_sysfs_scheme_filter, kobj); + int len; - return sysfs_emit(buf, "%s\n", + if (!mutex_trylock(&damon_sysfs_lock)) + return -EBUSY; + len = sysfs_emit(buf, "%s\n", filter->memcg_path ? filter->memcg_path : ""); + mutex_unlock(&damon_sysfs_lock); + return len; } static ssize_t memcg_path_store(struct kobject *kobj, @@ -550,8 +555,13 @@ static ssize_t memcg_path_store(struct kobject *kobj, return -ENOMEM; strscpy(path, buf, count + 1); + if (!mutex_trylock(&damon_sysfs_lock)) { + kfree(path); + return -EBUSY; + } kfree(filter->memcg_path); filter->memcg_path = path; + mutex_unlock(&damon_sysfs_lock); return count; } @@ -1187,8 +1197,13 @@ static ssize_t path_show(struct kobject *kobj, { struct damos_sysfs_quota_goal *goal = container_of(kobj, struct damos_sysfs_quota_goal, kobj); + int len; - return sysfs_emit(buf, "%s\n", goal->path ? goal->path : ""); + if (!mutex_trylock(&damon_sysfs_lock)) + return -EBUSY; + len = sysfs_emit(buf, "%s\n", goal->path ? goal->path : ""); + mutex_unlock(&damon_sysfs_lock); + return len; } static ssize_t path_store(struct kobject *kobj, @@ -1203,8 +1218,13 @@ static ssize_t path_store(struct kobject *kobj, return -ENOMEM; strscpy(path, buf, count + 1); + if (!mutex_trylock(&damon_sysfs_lock)) { + kfree(path); + return -EBUSY; + } kfree(goal->path); goal->path = path; + mutex_unlock(&damon_sysfs_lock); return count; } diff --git a/mm/hugetlb_cma.c b/mm/hugetlb_cma.c index f83ae4998990..7693ccefd0c6 100644 --- a/mm/hugetlb_cma.c +++ b/mm/hugetlb_cma.c @@ -204,6 +204,7 @@ void __init hugetlb_cma_reserve(void) */ per_node = DIV_ROUND_UP(hugetlb_cma_size, nodes_weight(hugetlb_bootmem_nodes)); + per_node = round_up(per_node, PAGE_SIZE << order); pr_info("hugetlb_cma: reserve %lu MiB, up to %lu MiB per node\n", hugetlb_cma_size / SZ_1M, per_node / SZ_1M); } diff --git a/mm/memcontrol.c b/mm/memcontrol.c index c3d98ab41f1f..c03d4787d466 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -805,12 +805,17 @@ static long memcg_state_val_in_pages(int idx, long val) * Used in mod_memcg_state() and mod_memcg_lruvec_state() to avoid race with * reparenting of non-hierarchical state_locals. */ -static inline struct mem_cgroup *get_non_dying_memcg_start(struct mem_cgroup *memcg) +static inline struct mem_cgroup *get_non_dying_memcg_start(struct mem_cgroup *memcg, + bool *rcu_locked) { - if (cgroup_subsys_on_dfl(memory_cgrp_subsys)) + /* Rebinding can cause this value to be changed at runtime */ + if (cgroup_subsys_on_dfl(memory_cgrp_subsys)) { + *rcu_locked = false; return memcg; + } rcu_read_lock(); + *rcu_locked = true; while (memcg_is_dying(memcg)) memcg = parent_mem_cgroup(memcg); @@ -818,20 +823,21 @@ static inline struct mem_cgroup *get_non_dying_memcg_start(struct mem_cgroup *me return memcg; } -static inline void get_non_dying_memcg_end(void) +static inline void get_non_dying_memcg_end(bool rcu_locked) { - if (cgroup_subsys_on_dfl(memory_cgrp_subsys)) + if (!rcu_locked) return; rcu_read_unlock(); } #else -static inline struct mem_cgroup *get_non_dying_memcg_start(struct mem_cgroup *memcg) +static inline struct mem_cgroup *get_non_dying_memcg_start(struct mem_cgroup *memcg, + bool *rcu_locked) { return memcg; } -static inline void get_non_dying_memcg_end(void) +static inline void get_non_dying_memcg_end(bool rcu_locked) { } #endif @@ -865,12 +871,14 @@ static void __mod_memcg_state(struct mem_cgroup *memcg, void mod_memcg_state(struct mem_cgroup *memcg, enum memcg_stat_item idx, int val) { + bool rcu_locked = false; + if (mem_cgroup_disabled()) return; - memcg = get_non_dying_memcg_start(memcg); + memcg = get_non_dying_memcg_start(memcg, &rcu_locked); __mod_memcg_state(memcg, idx, val); - get_non_dying_memcg_end(); + get_non_dying_memcg_end(rcu_locked); } #ifdef CONFIG_MEMCG_V1 @@ -933,14 +941,15 @@ static void mod_memcg_lruvec_state(struct lruvec *lruvec, struct pglist_data *pgdat = lruvec_pgdat(lruvec); struct mem_cgroup_per_node *pn; struct mem_cgroup *memcg; + bool rcu_locked = false; pn = container_of(lruvec, struct mem_cgroup_per_node, lruvec); - memcg = get_non_dying_memcg_start(pn->memcg); + memcg = get_non_dying_memcg_start(pn->memcg, &rcu_locked); pn = memcg->nodeinfo[pgdat->node_id]; __mod_memcg_lruvec_state(pn, idx, val); - get_non_dying_memcg_end(); + get_non_dying_memcg_end(rcu_locked); } /** diff --git a/mm/page-writeback.c b/mm/page-writeback.c index 88cd53d4ba09..833f743f309f 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -1835,7 +1835,9 @@ static int balance_dirty_pages(struct bdi_writeback *wb, balance_domain_limits(mdtc, strictlimit); } - if (nr_dirty > gdtc->bg_thresh && !writeback_in_progress(wb)) + if (!writeback_in_progress(wb) && + (nr_dirty > gdtc->bg_thresh || + (strictlimit && gdtc->wb_dirty > gdtc->wb_bg_thresh))) wb_start_background_writeback(wb); /* @@ -1862,15 +1864,9 @@ free_running: * Unconditionally start background writeback if it's not * already in progress. We need to do this because the global * dirty threshold check above (nr_dirty > gdtc->bg_thresh) - * doesn't account for these cases: - * - * a) strictlimit BDIs: throttling is calculated using per-wb - * thresholds. The per-wb threshold can be exceeded even when - * nr_dirty < gdtc->bg_thresh - * - * b) memcg-based throttling: memcg uses its own dirty count and - * thresholds and can trigger throttling even when global - * nr_dirty < gdtc->bg_thresh + * doesn't account for the memcg-based throttling case. memcg + * uses its own dirty count and thresholds and can trigger + * throttling even when global nr_dirty < gdtc->bg_thresh * * Writeback needs to be started else the writer stalls in the * throttle loop waiting for dirty pages to be written back diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c index 885da1e56466..180bad42fc79 100644 --- a/mm/userfaultfd.c +++ b/mm/userfaultfd.c @@ -443,8 +443,10 @@ static int mfill_copy_folio_locked(struct folio *folio, unsigned long src_addr) return ret; } -static int mfill_copy_folio_retry(struct mfill_state *state, struct folio *folio) +static int mfill_copy_folio_retry(struct mfill_state *state, + struct folio *folio) { + const struct vm_uffd_ops *orig_ops = vma_uffd_ops(state->vma); unsigned long src_addr = state->src_addr; void *kaddr; int err; @@ -465,6 +467,14 @@ static int mfill_copy_folio_retry(struct mfill_state *state, struct folio *folio if (err) return err; + /* + * The VMA type may have changed while the lock was dropped + * (e.g. replaced with a hugetlb mapping), making the caller's + * ops pointer stale. + */ + if (vma_uffd_ops(state->vma) != orig_ops) + return -EAGAIN; + err = mfill_establish_pmd(state); if (err) return err; diff --git a/mm/util.c b/mm/util.c index 232c3930a662..3cc949a0b7ed 100644 --- a/mm/util.c +++ b/mm/util.c @@ -1232,7 +1232,7 @@ int __compat_vma_mmap(struct vm_area_desc *desc, /* Update the VMA from the descriptor. */ compat_set_vma_from_desc(vma, desc); /* Complete any specified mmap actions. */ - return mmap_action_complete(vma, &desc->action); + return mmap_action_complete(vma, &desc->action, /*is_compat=*/true); } EXPORT_SYMBOL(__compat_vma_mmap); @@ -1389,7 +1389,8 @@ static int call_vma_mapped(struct vm_area_struct *vma) } static int mmap_action_finish(struct vm_area_struct *vma, - struct mmap_action *action, int err) + struct mmap_action *action, int err, + bool is_compat) { size_t len; @@ -1400,8 +1401,12 @@ static int mmap_action_finish(struct vm_area_struct *vma, /* do_munmap() might take rmap lock, so release if held. */ maybe_rmap_unlock_action(vma, action); - if (!err) - return 0; + /* + * If this is invoked from the compatibility layer, post-mmap() hook + * logic will handle cleanup for us. + */ + if (!err || is_compat) + return err; /* * If an error occurs, unmap the VMA altogether and return an error. We @@ -1451,13 +1456,15 @@ EXPORT_SYMBOL(mmap_action_prepare); * mmap_action_complete - Execute VMA descriptor action. * @vma: The VMA to perform the action upon. * @action: The action to perform. + * @is_compat: Is this being invoked from the compatibility layer? * * Similar to mmap_action_prepare(). * - * Return: 0 on success, or error, at which point the VMA will be unmapped. + * Return: 0 on success, or error, at which point the VMA will be unmapped if + * !@is_compat. */ int mmap_action_complete(struct vm_area_struct *vma, - struct mmap_action *action) + struct mmap_action *action, bool is_compat) { int err = 0; @@ -1478,7 +1485,7 @@ int mmap_action_complete(struct vm_area_struct *vma, break; } - return mmap_action_finish(vma, action, err); + return mmap_action_finish(vma, action, err, is_compat); } EXPORT_SYMBOL(mmap_action_complete); #else @@ -1500,7 +1507,8 @@ int mmap_action_prepare(struct vm_area_desc *desc) EXPORT_SYMBOL(mmap_action_prepare); int mmap_action_complete(struct vm_area_struct *vma, - struct mmap_action *action) + struct mmap_action *action, + bool is_compat) { int err = 0; @@ -1517,7 +1525,7 @@ int mmap_action_complete(struct vm_area_struct *vma, break; } - return mmap_action_finish(vma, action, err); + return mmap_action_finish(vma, action, err, is_compat); } EXPORT_SYMBOL(mmap_action_complete); #endif @@ -2780,7 +2780,8 @@ static unsigned long __mmap_region(struct file *file, unsigned long addr, __mmap_complete(&map, vma); if (have_mmap_prepare && allocated_new) { - error = mmap_action_complete(vma, &desc.action); + error = mmap_action_complete(vma, &desc.action, + /*is_compat=*/false); if (error) return error; } diff --git a/mm/vmalloc.c b/mm/vmalloc.c index aa08651ec0df..c31a8615a832 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -4361,7 +4361,7 @@ need_realloc: return NULL; if (p) { - memcpy(n, p, old_size); + memcpy(n, p, min(size, old_size)); vfree(p); } diff --git a/tools/testing/radix-tree/maple.c b/tools/testing/radix-tree/maple.c index feedd5ab7058..0607913a3022 100644 --- a/tools/testing/radix-tree/maple.c +++ b/tools/testing/radix-tree/maple.c @@ -2,7 +2,7 @@ /* * maple_tree.c: Userspace testing for maple tree test-suite * Copyright (c) 2018-2022 Oracle Corporation - * Author: Liam R. Howlett <Liam.Howlett@Oracle.com> + * Author: Liam R. Howlett <liam@infradead.org> * * Any tests that require internal knowledge of the tree or threads and other * difficult to handle in kernel tests. diff --git a/tools/testing/selftests/mm/config b/tools/testing/selftests/mm/config index 1dbe2b4558ab..06f78bd232e2 100644 --- a/tools/testing/selftests/mm/config +++ b/tools/testing/selftests/mm/config @@ -13,3 +13,4 @@ CONFIG_PROFILING=y CONFIG_UPROBES=y CONFIG_MEMORY_FAILURE=y CONFIG_HWPOISON_INJECT=m +CONFIG_PROC_MEM_ALWAYS_FORCE=y diff --git a/tools/testing/vma/include/dup.h b/tools/testing/vma/include/dup.h index b4864aad2db0..9e0dfd3a85b0 100644 --- a/tools/testing/vma/include/dup.h +++ b/tools/testing/vma/include/dup.h @@ -1330,7 +1330,7 @@ static inline int __compat_vma_mmap(struct vm_area_desc *desc, /* Update the VMA from the descriptor. */ compat_set_vma_from_desc(vma, desc); /* Complete any specified mmap actions. */ - return mmap_action_complete(vma, &desc->action); + return mmap_action_complete(vma, &desc->action, /*is_compat=*/true); } static inline int compat_vma_mmap(struct file *file, struct vm_area_struct *vma) diff --git a/tools/testing/vma/include/stubs.h b/tools/testing/vma/include/stubs.h index a30b8bc84955..64164e25658f 100644 --- a/tools/testing/vma/include/stubs.h +++ b/tools/testing/vma/include/stubs.h @@ -87,7 +87,8 @@ static inline int mmap_action_prepare(struct vm_area_desc *desc) } static inline int mmap_action_complete(struct vm_area_struct *vma, - struct mmap_action *action) + struct mmap_action *action, + bool is_compat) { return 0; } |