diff options
author | Andrew Morton <akpm@linux-foundation.org> | 2023-06-24 01:58:19 +0200 |
---|---|---|
committer | Andrew Morton <akpm@linux-foundation.org> | 2023-06-24 01:58:19 +0200 |
commit | 63773d2b593d86440c3b96fd300ed80d00cd06ef (patch) | |
tree | ebc7b1e8f1c0ce535ef9c6120209d0e87d8d4b16 | |
parent | mm: page_alloc: make compound_page_dtors static (diff) | |
parent | mm/mglru: make memcg_lru->lock irq safe (diff) | |
download | linux-63773d2b593d86440c3b96fd300ed80d00cd06ef.tar.xz linux-63773d2b593d86440c3b96fd300ed80d00cd06ef.zip |
Merge mm-hotfixes-stable into mm-stable to pick up depended-upon changes.
63 files changed, 599 insertions, 364 deletions
@@ -70,6 +70,8 @@ Baolin Wang <baolin.wang@linux.alibaba.com> <baolin.wang@unisoc.com> Baolin Wang <baolin.wang@linux.alibaba.com> <baolin.wang7@gmail.com> Bart Van Assche <bvanassche@acm.org> <bart.vanassche@sandisk.com> Bart Van Assche <bvanassche@acm.org> <bart.vanassche@wdc.com> +Ben Dooks <ben-linux@fluff.org> <ben.dooks@simtec.co.uk> +Ben Dooks <ben-linux@fluff.org> <ben.dooks@sifive.com> Ben Gardner <bgardner@wabtec.com> Ben M Cahill <ben.m.cahill@intel.com> Ben Widawsky <bwidawsk@kernel.org> <ben@bwidawsk.net> @@ -233,6 +235,7 @@ Jisheng Zhang <jszhang@kernel.org> <Jisheng.Zhang@synaptics.com> Johan Hovold <johan@kernel.org> <jhovold@gmail.com> Johan Hovold <johan@kernel.org> <johan@hovoldconsulting.com> John Crispin <john@phrozen.org> <blogic@openwrt.org> +John Keeping <john@keeping.me.uk> <john@metanate.com> John Paul Adrian Glaubitz <glaubitz@physik.fu-berlin.de> John Stultz <johnstul@us.ibm.com> <jon.toppins+linux@gmail.com> <jtoppins@cumulusnetworks.com> diff --git a/Documentation/trace/histogram.rst b/Documentation/trace/histogram.rst index 479c9eac6335..3c9b263de9c2 100644 --- a/Documentation/trace/histogram.rst +++ b/Documentation/trace/histogram.rst @@ -35,7 +35,7 @@ Documentation written by Tom Zanussi in place of an explicit value field - this is simply a count of event hits. If 'values' isn't specified, an implicit 'hitcount' value will be automatically created and used as the only value. - Keys can be any field, or the special string 'stacktrace', which + Keys can be any field, or the special string 'common_stacktrace', which will use the event's kernel stacktrace as the key. The keywords 'keys' or 'key' can be used to specify keys, and the keywords 'values', 'vals', or 'val' can be used to specify values. Compound @@ -54,7 +54,7 @@ Documentation written by Tom Zanussi 'compatible' if the fields named in the trigger share the same number and type of fields and those fields also have the same names. Note that any two events always share the compatible 'hitcount' and - 'stacktrace' fields and can therefore be combined using those + 'common_stacktrace' fields and can therefore be combined using those fields, however pointless that may be. 'hist' triggers add a 'hist' file to each event's subdirectory. @@ -547,9 +547,9 @@ Extended error information the hist trigger display symbolic call_sites, we can have the hist trigger additionally display the complete set of kernel stack traces that led to each call_site. To do that, we simply use the special - value 'stacktrace' for the key parameter:: + value 'common_stacktrace' for the key parameter:: - # echo 'hist:keys=stacktrace:values=bytes_req,bytes_alloc:sort=bytes_alloc' > \ + # echo 'hist:keys=common_stacktrace:values=bytes_req,bytes_alloc:sort=bytes_alloc' > \ /sys/kernel/tracing/events/kmem/kmalloc/trigger The above trigger will use the kernel stack trace in effect when an @@ -561,9 +561,9 @@ Extended error information every callpath to a kmalloc for a kernel compile):: # cat /sys/kernel/tracing/events/kmem/kmalloc/hist - # trigger info: hist:keys=stacktrace:vals=bytes_req,bytes_alloc:sort=bytes_alloc:size=2048 [active] + # trigger info: hist:keys=common_stacktrace:vals=bytes_req,bytes_alloc:sort=bytes_alloc:size=2048 [active] - { stacktrace: + { common_stacktrace: __kmalloc_track_caller+0x10b/0x1a0 kmemdup+0x20/0x50 hidraw_report_event+0x8a/0x120 [hid] @@ -581,7 +581,7 @@ Extended error information cpu_startup_entry+0x315/0x3e0 rest_init+0x7c/0x80 } hitcount: 3 bytes_req: 21 bytes_alloc: 24 - { stacktrace: + { common_stacktrace: __kmalloc_track_caller+0x10b/0x1a0 kmemdup+0x20/0x50 hidraw_report_event+0x8a/0x120 [hid] @@ -596,7 +596,7 @@ Extended error information do_IRQ+0x5a/0xf0 ret_from_intr+0x0/0x30 } hitcount: 3 bytes_req: 21 bytes_alloc: 24 - { stacktrace: + { common_stacktrace: kmem_cache_alloc_trace+0xeb/0x150 aa_alloc_task_context+0x27/0x40 apparmor_cred_prepare+0x1f/0x50 @@ -608,7 +608,7 @@ Extended error information . . . - { stacktrace: + { common_stacktrace: __kmalloc+0x11b/0x1b0 i915_gem_execbuffer2+0x6c/0x2c0 [i915] drm_ioctl+0x349/0x670 [drm] @@ -616,7 +616,7 @@ Extended error information SyS_ioctl+0x81/0xa0 system_call_fastpath+0x12/0x6a } hitcount: 17726 bytes_req: 13944120 bytes_alloc: 19593808 - { stacktrace: + { common_stacktrace: __kmalloc+0x11b/0x1b0 load_elf_phdrs+0x76/0xa0 load_elf_binary+0x102/0x1650 @@ -625,7 +625,7 @@ Extended error information SyS_execve+0x3a/0x50 return_from_execve+0x0/0x23 } hitcount: 33348 bytes_req: 17152128 bytes_alloc: 20226048 - { stacktrace: + { common_stacktrace: kmem_cache_alloc_trace+0xeb/0x150 apparmor_file_alloc_security+0x27/0x40 security_file_alloc+0x16/0x20 @@ -636,7 +636,7 @@ Extended error information SyS_open+0x1e/0x20 system_call_fastpath+0x12/0x6a } hitcount: 4766422 bytes_req: 9532844 bytes_alloc: 38131376 - { stacktrace: + { common_stacktrace: __kmalloc+0x11b/0x1b0 seq_buf_alloc+0x1b/0x50 seq_read+0x2cc/0x370 @@ -1026,7 +1026,7 @@ Extended error information First we set up an initially paused stacktrace trigger on the netif_receive_skb event:: - # echo 'hist:key=stacktrace:vals=len:pause' > \ + # echo 'hist:key=common_stacktrace:vals=len:pause' > \ /sys/kernel/tracing/events/net/netif_receive_skb/trigger Next, we set up an 'enable_hist' trigger on the sched_process_exec @@ -1060,9 +1060,9 @@ Extended error information $ wget https://www.kernel.org/pub/linux/kernel/v3.x/patch-3.19.xz # cat /sys/kernel/tracing/events/net/netif_receive_skb/hist - # trigger info: hist:keys=stacktrace:vals=len:sort=hitcount:size=2048 [paused] + # trigger info: hist:keys=common_stacktrace:vals=len:sort=hitcount:size=2048 [paused] - { stacktrace: + { common_stacktrace: __netif_receive_skb_core+0x46d/0x990 __netif_receive_skb+0x18/0x60 netif_receive_skb_internal+0x23/0x90 @@ -1079,7 +1079,7 @@ Extended error information kthread+0xd2/0xf0 ret_from_fork+0x42/0x70 } hitcount: 85 len: 28884 - { stacktrace: + { common_stacktrace: __netif_receive_skb_core+0x46d/0x990 __netif_receive_skb+0x18/0x60 netif_receive_skb_internal+0x23/0x90 @@ -1097,7 +1097,7 @@ Extended error information irq_thread+0x11f/0x150 kthread+0xd2/0xf0 } hitcount: 98 len: 664329 - { stacktrace: + { common_stacktrace: __netif_receive_skb_core+0x46d/0x990 __netif_receive_skb+0x18/0x60 process_backlog+0xa8/0x150 @@ -1115,7 +1115,7 @@ Extended error information inet_sendmsg+0x64/0xa0 sock_sendmsg+0x3d/0x50 } hitcount: 115 len: 13030 - { stacktrace: + { common_stacktrace: __netif_receive_skb_core+0x46d/0x990 __netif_receive_skb+0x18/0x60 netif_receive_skb_internal+0x23/0x90 @@ -1142,14 +1142,14 @@ Extended error information into the histogram. In order to avoid having to set everything up again, we can just clear the histogram first:: - # echo 'hist:key=stacktrace:vals=len:clear' >> \ + # echo 'hist:key=common_stacktrace:vals=len:clear' >> \ /sys/kernel/tracing/events/net/netif_receive_skb/trigger Just to verify that it is in fact cleared, here's what we now see in the hist file:: # cat /sys/kernel/tracing/events/net/netif_receive_skb/hist - # trigger info: hist:keys=stacktrace:vals=len:sort=hitcount:size=2048 [paused] + # trigger info: hist:keys=common_stacktrace:vals=len:sort=hitcount:size=2048 [paused] Totals: Hits: 0 @@ -1485,12 +1485,12 @@ Extended error information And here's an example that shows how to combine histogram data from any two events even if they don't share any 'compatible' fields - other than 'hitcount' and 'stacktrace'. These commands create a + other than 'hitcount' and 'common_stacktrace'. These commands create a couple of triggers named 'bar' using those fields:: - # echo 'hist:name=bar:key=stacktrace:val=hitcount' > \ + # echo 'hist:name=bar:key=common_stacktrace:val=hitcount' > \ /sys/kernel/tracing/events/sched/sched_process_fork/trigger - # echo 'hist:name=bar:key=stacktrace:val=hitcount' > \ + # echo 'hist:name=bar:key=common_stacktrace:val=hitcount' > \ /sys/kernel/tracing/events/net/netif_rx/trigger And displaying the output of either shows some interesting if @@ -1501,16 +1501,16 @@ Extended error information # event histogram # - # trigger info: hist:name=bar:keys=stacktrace:vals=hitcount:sort=hitcount:size=2048 [active] + # trigger info: hist:name=bar:keys=common_stacktrace:vals=hitcount:sort=hitcount:size=2048 [active] # - { stacktrace: + { common_stacktrace: kernel_clone+0x18e/0x330 kernel_thread+0x29/0x30 kthreadd+0x154/0x1b0 ret_from_fork+0x3f/0x70 } hitcount: 1 - { stacktrace: + { common_stacktrace: netif_rx_internal+0xb2/0xd0 netif_rx_ni+0x20/0x70 dev_loopback_xmit+0xaa/0xd0 @@ -1528,7 +1528,7 @@ Extended error information call_cpuidle+0x3b/0x60 cpu_startup_entry+0x22d/0x310 } hitcount: 1 - { stacktrace: + { common_stacktrace: netif_rx_internal+0xb2/0xd0 netif_rx_ni+0x20/0x70 dev_loopback_xmit+0xaa/0xd0 @@ -1543,7 +1543,7 @@ Extended error information SyS_sendto+0xe/0x10 entry_SYSCALL_64_fastpath+0x12/0x6a } hitcount: 2 - { stacktrace: + { common_stacktrace: netif_rx_internal+0xb2/0xd0 netif_rx+0x1c/0x60 loopback_xmit+0x6c/0xb0 @@ -1561,7 +1561,7 @@ Extended error information sock_sendmsg+0x38/0x50 ___sys_sendmsg+0x14e/0x270 } hitcount: 76 - { stacktrace: + { common_stacktrace: netif_rx_internal+0xb2/0xd0 netif_rx+0x1c/0x60 loopback_xmit+0x6c/0xb0 @@ -1579,7 +1579,7 @@ Extended error information sock_sendmsg+0x38/0x50 ___sys_sendmsg+0x269/0x270 } hitcount: 77 - { stacktrace: + { common_stacktrace: netif_rx_internal+0xb2/0xd0 netif_rx+0x1c/0x60 loopback_xmit+0x6c/0xb0 @@ -1597,7 +1597,7 @@ Extended error information sock_sendmsg+0x38/0x50 SYSC_sendto+0xef/0x170 } hitcount: 88 - { stacktrace: + { common_stacktrace: kernel_clone+0x18e/0x330 SyS_clone+0x19/0x20 entry_SYSCALL_64_fastpath+0x12/0x6a @@ -1949,7 +1949,7 @@ uninterruptible state:: # cd /sys/kernel/tracing # echo 's:block_lat pid_t pid; u64 delta; unsigned long[] stack;' > dynamic_events - # echo 'hist:keys=next_pid:ts=common_timestamp.usecs,st=stacktrace if prev_state == 2' >> events/sched/sched_switch/trigger + # echo 'hist:keys=next_pid:ts=common_timestamp.usecs,st=common_stacktrace if prev_state == 2' >> events/sched/sched_switch/trigger # echo 'hist:keys=prev_pid:delta=common_timestamp.usecs-$ts,s=$st:onmax($delta).trace(block_lat,prev_pid,$delta,$s)' >> events/sched/sched_switch/trigger # echo 1 > events/synthetic/block_lat/enable # cat trace diff --git a/arch/powerpc/purgatory/Makefile b/arch/powerpc/purgatory/Makefile index 6f5e2727963c..78473d69cd2b 100644 --- a/arch/powerpc/purgatory/Makefile +++ b/arch/powerpc/purgatory/Makefile @@ -5,6 +5,11 @@ KCSAN_SANITIZE := n targets += trampoline_$(BITS).o purgatory.ro +# When profile-guided optimization is enabled, llvm emits two different +# overlapping text sections, which is not supported by kexec. Remove profile +# optimization flags. +KBUILD_CFLAGS := $(filter-out -fprofile-sample-use=% -fprofile-use=%,$(KBUILD_CFLAGS)) + LDFLAGS_purgatory.ro := -e purgatory_start -r --no-undefined $(obj)/purgatory.ro: $(obj)/trampoline_$(BITS).o FORCE diff --git a/arch/riscv/purgatory/Makefile b/arch/riscv/purgatory/Makefile index 5730797a6b40..bd2e27f82532 100644 --- a/arch/riscv/purgatory/Makefile +++ b/arch/riscv/purgatory/Makefile @@ -35,6 +35,11 @@ CFLAGS_sha256.o := -D__DISABLE_EXPORTS CFLAGS_string.o := -D__DISABLE_EXPORTS CFLAGS_ctype.o := -D__DISABLE_EXPORTS +# When profile-guided optimization is enabled, llvm emits two different +# overlapping text sections, which is not supported by kexec. Remove profile +# optimization flags. +KBUILD_CFLAGS := $(filter-out -fprofile-sample-use=% -fprofile-use=%,$(KBUILD_CFLAGS)) + # When linking purgatory.ro with -r unresolved symbols are not checked, # also link a purgatory.chk binary without -r to check for unresolved symbols. PURGATORY_LDFLAGS := -e purgatory_start -z nodefaultlib diff --git a/arch/x86/crypto/aria-aesni-avx-asm_64.S b/arch/x86/crypto/aria-aesni-avx-asm_64.S index 7c1abc513f34..9556dacd9841 100644 --- a/arch/x86/crypto/aria-aesni-avx-asm_64.S +++ b/arch/x86/crypto/aria-aesni-avx-asm_64.S @@ -773,8 +773,6 @@ .octa 0x3F893781E95FE1576CDA64D2BA0CB204 #ifdef CONFIG_AS_GFNI -.section .rodata.cst8, "aM", @progbits, 8 -.align 8 /* AES affine: */ #define tf_aff_const BV8(1, 1, 0, 0, 0, 1, 1, 0) .Ltf_aff_bitmatrix: diff --git a/arch/x86/purgatory/Makefile b/arch/x86/purgatory/Makefile index 82fec66d46d2..42abd6af1198 100644 --- a/arch/x86/purgatory/Makefile +++ b/arch/x86/purgatory/Makefile @@ -14,6 +14,11 @@ $(obj)/sha256.o: $(srctree)/lib/crypto/sha256.c FORCE CFLAGS_sha256.o := -D__DISABLE_EXPORTS +# When profile-guided optimization is enabled, llvm emits two different +# overlapping text sections, which is not supported by kexec. Remove profile +# optimization flags. +KBUILD_CFLAGS := $(filter-out -fprofile-sample-use=% -fprofile-use=%,$(KBUILD_CFLAGS)) + # When linking purgatory.ro with -r unresolved symbols are not checked, # also link a purgatory.chk binary without -r to check for unresolved symbols. PURGATORY_LDFLAGS := -e purgatory_start -z nodefaultlib diff --git a/drivers/dma-buf/udmabuf.c b/drivers/dma-buf/udmabuf.c index 01f2e86f3f7c..12cf6bb2e3ce 100644 --- a/drivers/dma-buf/udmabuf.c +++ b/drivers/dma-buf/udmabuf.c @@ -12,7 +12,6 @@ #include <linux/shmem_fs.h> #include <linux/slab.h> #include <linux/udmabuf.h> -#include <linux/hugetlb.h> #include <linux/vmalloc.h> #include <linux/iosys-map.h> @@ -207,9 +206,7 @@ static long udmabuf_create(struct miscdevice *device, struct udmabuf *ubuf; struct dma_buf *buf; pgoff_t pgoff, pgcnt, pgidx, pgbuf = 0, pglimit; - struct page *page, *hpage = NULL; - pgoff_t subpgoff, maxsubpgs; - struct hstate *hpstate; + struct page *page; int seals, ret = -EINVAL; u32 i, flags; @@ -245,7 +242,7 @@ static long udmabuf_create(struct miscdevice *device, if (!memfd) goto err; mapping = memfd->f_mapping; - if (!shmem_mapping(mapping) && !is_file_hugepages(memfd)) + if (!shmem_mapping(mapping)) goto err; seals = memfd_fcntl(memfd, F_GET_SEALS, 0); if (seals == -EINVAL) @@ -256,48 +253,16 @@ static long udmabuf_create(struct miscdevice *device, goto err; pgoff = list[i].offset >> PAGE_SHIFT; pgcnt = list[i].size >> PAGE_SHIFT; - if (is_file_hugepages(memfd)) { - hpstate = hstate_file(memfd); - pgoff = list[i].offset >> huge_page_shift(hpstate); - subpgoff = (list[i].offset & - ~huge_page_mask(hpstate)) >> PAGE_SHIFT; - maxsubpgs = huge_page_size(hpstate) >> PAGE_SHIFT; - } for (pgidx = 0; pgidx < pgcnt; pgidx++) { - if (is_file_hugepages(memfd)) { - if (!hpage) { - hpage = find_get_page_flags(mapping, pgoff, - FGP_ACCESSED); - if (!hpage) { - ret = -EINVAL; - goto err; - } - } - page = hpage + subpgoff; - get_page(page); - subpgoff++; - if (subpgoff == maxsubpgs) { - put_page(hpage); - hpage = NULL; - subpgoff = 0; - pgoff++; - } - } else { - page = shmem_read_mapping_page(mapping, - pgoff + pgidx); - if (IS_ERR(page)) { - ret = PTR_ERR(page); - goto err; - } + page = shmem_read_mapping_page(mapping, pgoff + pgidx); + if (IS_ERR(page)) { + ret = PTR_ERR(page); + goto err; } ubuf->pages[pgbuf++] = page; } fput(memfd); memfd = NULL; - if (hpage) { - put_page(hpage); - hpage = NULL; - } } exp_info.ops = &udmabuf_ops; diff --git a/drivers/dma/at_hdmac.c b/drivers/dma/at_hdmac.c index 8858470246e1..ee3a219e3a89 100644 --- a/drivers/dma/at_hdmac.c +++ b/drivers/dma/at_hdmac.c @@ -132,7 +132,7 @@ #define ATC_DST_PIP BIT(12) /* Destination Picture-in-Picture enabled */ #define ATC_SRC_DSCR_DIS BIT(16) /* Src Descriptor fetch disable */ #define ATC_DST_DSCR_DIS BIT(20) /* Dst Descriptor fetch disable */ -#define ATC_FC GENMASK(22, 21) /* Choose Flow Controller */ +#define ATC_FC GENMASK(23, 21) /* Choose Flow Controller */ #define ATC_FC_MEM2MEM 0x0 /* Mem-to-Mem (DMA) */ #define ATC_FC_MEM2PER 0x1 /* Mem-to-Periph (DMA) */ #define ATC_FC_PER2MEM 0x2 /* Periph-to-Mem (DMA) */ @@ -153,8 +153,6 @@ #define ATC_AUTO BIT(31) /* Auto multiple buffer tx enable */ /* Bitfields in CFG */ -#define ATC_PER_MSB(h) ((0x30U & (h)) >> 4) /* Extract most significant bits of a handshaking identifier */ - #define ATC_SRC_PER GENMASK(3, 0) /* Channel src rq associated with periph handshaking ifc h */ #define ATC_DST_PER GENMASK(7, 4) /* Channel dst rq associated with periph handshaking ifc h */ #define ATC_SRC_REP BIT(8) /* Source Replay Mod */ @@ -181,10 +179,15 @@ #define ATC_DPIP_HOLE GENMASK(15, 0) #define ATC_DPIP_BOUNDARY GENMASK(25, 16) -#define ATC_SRC_PER_ID(id) (FIELD_PREP(ATC_SRC_PER_MSB, (id)) | \ - FIELD_PREP(ATC_SRC_PER, (id))) -#define ATC_DST_PER_ID(id) (FIELD_PREP(ATC_DST_PER_MSB, (id)) | \ - FIELD_PREP(ATC_DST_PER, (id))) +#define ATC_PER_MSB GENMASK(5, 4) /* Extract MSBs of a handshaking identifier */ +#define ATC_SRC_PER_ID(id) \ + ({ typeof(id) _id = (id); \ + FIELD_PREP(ATC_SRC_PER_MSB, FIELD_GET(ATC_PER_MSB, _id)) | \ + FIELD_PREP(ATC_SRC_PER, _id); }) +#define ATC_DST_PER_ID(id) \ + ({ typeof(id) _id = (id); \ + FIELD_PREP(ATC_DST_PER_MSB, FIELD_GET(ATC_PER_MSB, _id)) | \ + FIELD_PREP(ATC_DST_PER, _id); }) diff --git a/drivers/dma/at_xdmac.c b/drivers/dma/at_xdmac.c index 7da6d9b6098e..c3b37168b21f 100644 --- a/drivers/dma/at_xdmac.c +++ b/drivers/dma/at_xdmac.c @@ -1102,6 +1102,8 @@ at_xdmac_prep_interleaved(struct dma_chan *chan, NULL, src_addr, dst_addr, xt, xt->sgl); + if (!first) + return NULL; /* Length of the block is (BLEN+1) microblocks. */ for (i = 0; i < xt->numf - 1; i++) @@ -1132,8 +1134,9 @@ at_xdmac_prep_interleaved(struct dma_chan *chan, src_addr, dst_addr, xt, chunk); if (!desc) { - list_splice_tail_init(&first->descs_list, - &atchan->free_descs_list); + if (first) + list_splice_tail_init(&first->descs_list, + &atchan->free_descs_list); return NULL; } diff --git a/drivers/dma/idxd/cdev.c b/drivers/dma/idxd/cdev.c index ecbf67c2ad2b..d32deb9b4e3d 100644 --- a/drivers/dma/idxd/cdev.c +++ b/drivers/dma/idxd/cdev.c @@ -277,7 +277,6 @@ static int idxd_cdev_open(struct inode *inode, struct file *filp) if (wq_dedicated(wq)) { rc = idxd_wq_set_pasid(wq, pasid); if (rc < 0) { - iommu_sva_unbind_device(sva); dev_err(dev, "wq set pasid failed: %d\n", rc); goto failed_set_pasid; } diff --git a/drivers/dma/pl330.c b/drivers/dma/pl330.c index 0d9257fbdfb0..b4731fe6bbc1 100644 --- a/drivers/dma/pl330.c +++ b/drivers/dma/pl330.c @@ -1050,7 +1050,7 @@ static bool _trigger(struct pl330_thread *thrd) return true; } -static bool _start(struct pl330_thread *thrd) +static bool pl330_start_thread(struct pl330_thread *thrd) { switch (_state(thrd)) { case PL330_STATE_FAULT_COMPLETING: @@ -1702,7 +1702,7 @@ static int pl330_update(struct pl330_dmac *pl330) thrd->req_running = -1; /* Get going again ASAP */ - _start(thrd); + pl330_start_thread(thrd); /* For now, just make a list of callbacks to be done */ list_add_tail(&descdone->rqd, &pl330->req_done); @@ -2089,7 +2089,7 @@ static void pl330_tasklet(struct tasklet_struct *t) } else { /* Make sure the PL330 Channel thread is active */ spin_lock(&pch->thread->dmac->lock); - _start(pch->thread); + pl330_start_thread(pch->thread); spin_unlock(&pch->thread->dmac->lock); } @@ -2107,7 +2107,7 @@ static void pl330_tasklet(struct tasklet_struct *t) if (power_down) { pch->active = true; spin_lock(&pch->thread->dmac->lock); - _start(pch->thread); + pl330_start_thread(pch->thread); spin_unlock(&pch->thread->dmac->lock); power_down = false; } diff --git a/drivers/dma/ti/k3-udma.c b/drivers/dma/ti/k3-udma.c index fc3a2a05ab7b..b8329a23728d 100644 --- a/drivers/dma/ti/k3-udma.c +++ b/drivers/dma/ti/k3-udma.c @@ -5527,7 +5527,7 @@ static int udma_probe(struct platform_device *pdev) return ret; } -static int udma_pm_suspend(struct device *dev) +static int __maybe_unused udma_pm_suspend(struct device *dev) { struct udma_dev *ud = dev_get_drvdata(dev); struct dma_device *dma_dev = &ud->ddev; @@ -5549,7 +5549,7 @@ static int udma_pm_suspend(struct device *dev) return 0; } -static int udma_pm_resume(struct device *dev) +static int __maybe_unused udma_pm_resume(struct device *dev) { struct udma_dev *ud = dev_get_drvdata(dev); struct dma_device *dma_dev = &ud->ddev; diff --git a/drivers/md/dm-cache-metadata.c b/drivers/md/dm-cache-metadata.c index 9e0c69958587..acffed750e3e 100644 --- a/drivers/md/dm-cache-metadata.c +++ b/drivers/md/dm-cache-metadata.c @@ -1828,7 +1828,7 @@ int dm_cache_metadata_abort(struct dm_cache_metadata *cmd) * Replacement block manager (new_bm) is created and old_bm destroyed outside of * cmd root_lock to avoid ABBA deadlock that would result (due to life-cycle of * shrinker associated with the block manager's bufio client vs cmd root_lock). - * - must take shrinker_mutex without holding cmd->root_lock + * - must take shrinker_rwsem without holding cmd->root_lock */ new_bm = dm_block_manager_create(cmd->bdev, DM_CACHE_METADATA_BLOCK_SIZE << SECTOR_SHIFT, CACHE_MAX_CONCURRENT_LOCKS); diff --git a/drivers/md/dm-thin-metadata.c b/drivers/md/dm-thin-metadata.c index 9f5cb52c5763..fd464fb024c3 100644 --- a/drivers/md/dm-thin-metadata.c +++ b/drivers/md/dm-thin-metadata.c @@ -1887,7 +1887,7 @@ int dm_pool_abort_metadata(struct dm_pool_metadata *pmd) * Replacement block manager (new_bm) is created and old_bm destroyed outside of * pmd root_lock to avoid ABBA deadlock that would result (due to life-cycle of * shrinker associated with the block manager's bufio client vs pmd root_lock). - * - must take shrinker_mutex without holding pmd->root_lock + * - must take shrinker_rwsem without holding pmd->root_lock */ new_bm = dm_block_manager_create(pmd->bdev, THIN_METADATA_BLOCK_SIZE << SECTOR_SHIFT, THIN_MAX_CONCURRENT_LOCKS); diff --git a/drivers/phy/amlogic/phy-meson-g12a-mipi-dphy-analog.c b/drivers/phy/amlogic/phy-meson-g12a-mipi-dphy-analog.c index c14089fa7db4..cabdddbbabfd 100644 --- a/drivers/phy/amlogic/phy-meson-g12a-mipi-dphy-analog.c +++ b/drivers/phy/amlogic/phy-meson-g12a-mipi-dphy-analog.c @@ -70,7 +70,7 @@ static int phy_g12a_mipi_dphy_analog_power_on(struct phy *phy) HHI_MIPI_CNTL1_BANDGAP); regmap_write(priv->regmap, HHI_MIPI_CNTL2, - FIELD_PREP(HHI_MIPI_CNTL2_DIF_TX_CTL0, 0x459) | + FIELD_PREP(HHI_MIPI_CNTL2_DIF_TX_CTL0, 0x45a) | FIELD_PREP(HHI_MIPI_CNTL2_DIF_TX_CTL1, 0x2680)); reg = DSI_LANE_CLK; diff --git a/drivers/phy/mediatek/phy-mtk-hdmi-mt8195.c b/drivers/phy/mediatek/phy-mtk-hdmi-mt8195.c index caa953780bee..8aa7251de4a9 100644 --- a/drivers/phy/mediatek/phy-mtk-hdmi-mt8195.c +++ b/drivers/phy/mediatek/phy-mtk-hdmi-mt8195.c @@ -237,11 +237,11 @@ static int mtk_hdmi_pll_calc(struct mtk_hdmi_phy *hdmi_phy, struct clk_hw *hw, */ if (tmds_clk < 54 * MEGA) txposdiv = 8; - else if (tmds_clk >= 54 * MEGA && tmds_clk < 148.35 * MEGA) + else if (tmds_clk >= 54 * MEGA && (tmds_clk * 100) < 14835 * MEGA) txposdiv = 4; - else if (tmds_clk >= 148.35 * MEGA && tmds_clk < 296.7 * MEGA) + else if ((tmds_clk * 100) >= 14835 * MEGA && (tmds_clk * 10) < 2967 * MEGA) txposdiv = 2; - else if (tmds_clk >= 296.7 * MEGA && tmds_clk <= 594 * MEGA) + else if ((tmds_clk * 10) >= 2967 * MEGA && tmds_clk <= 594 * MEGA) txposdiv = 1; else return -EINVAL; @@ -324,12 +324,12 @@ static int mtk_hdmi_pll_drv_setting(struct clk_hw *hw) clk_channel_bias = 0x34; /* 20mA */ impedance_en = 0xf; impedance = 0x36; /* 100ohm */ - } else if (pixel_clk >= 74.175 * MEGA && pixel_clk <= 300 * MEGA) { + } else if (((u64)pixel_clk * 1000) >= 74175 * MEGA && pixel_clk <= 300 * MEGA) { data_channel_bias = 0x34; /* 20mA */ clk_channel_bias = 0x2c; /* 16mA */ impedance_en = 0xf; impedance = 0x36; /* 100ohm */ - } else if (pixel_clk >= 27 * MEGA && pixel_clk < 74.175 * MEGA) { + } else if (pixel_clk >= 27 * MEGA && ((u64)pixel_clk * 1000) < 74175 * MEGA) { data_channel_bias = 0x14; /* 10mA */ clk_channel_bias = 0x14; /* 10mA */ impedance_en = 0x0; diff --git a/drivers/phy/qualcomm/phy-qcom-qmp-combo.c b/drivers/phy/qualcomm/phy-qcom-qmp-combo.c index 6850e04c329b..87b17e5877ab 100644 --- a/drivers/phy/qualcomm/phy-qcom-qmp-combo.c +++ b/drivers/phy/qualcomm/phy-qcom-qmp-combo.c @@ -2472,7 +2472,7 @@ static int qmp_combo_com_init(struct qmp_combo *qmp) ret = regulator_bulk_enable(cfg->num_vregs, qmp->vregs); if (ret) { dev_err(qmp->dev, "failed to enable regulators, err=%d\n", ret); - goto err_unlock; + goto err_decrement_count; } ret = reset_control_bulk_assert(cfg->num_resets, qmp->resets); @@ -2522,7 +2522,8 @@ err_assert_reset: reset_control_bulk_assert(cfg->num_resets, qmp->resets); err_disable_regulators: regulator_bulk_disable(cfg->num_vregs, qmp->vregs); -err_unlock: +err_decrement_count: + qmp->init_count--; mutex_unlock(&qmp->phy_mutex); return ret; diff --git a/drivers/phy/qualcomm/phy-qcom-qmp-pcie-msm8996.c b/drivers/phy/qualcomm/phy-qcom-qmp-pcie-msm8996.c index 09824be088c9..0c603bc06e09 100644 --- a/drivers/phy/qualcomm/phy-qcom-qmp-pcie-msm8996.c +++ b/drivers/phy/qualcomm/phy-qcom-qmp-pcie-msm8996.c @@ -379,7 +379,7 @@ static int qmp_pcie_msm8996_com_init(struct qmp_phy *qphy) ret = regulator_bulk_enable(cfg->num_vregs, qmp->vregs); if (ret) { dev_err(qmp->dev, "failed to enable regulators, err=%d\n", ret); - goto err_unlock; + goto err_decrement_count; } ret = reset_control_bulk_assert(cfg->num_resets, qmp->resets); @@ -409,7 +409,8 @@ err_assert_reset: reset_control_bulk_assert(cfg->num_resets, qmp->resets); err_disable_regulators: regulator_bulk_disable(cfg->num_vregs, qmp->vregs); -err_unlock: +err_decrement_count: + qmp->init_count--; mutex_unlock(&qmp->phy_mutex); return ret; diff --git a/drivers/phy/qualcomm/phy-qcom-snps-femto-v2.c b/drivers/phy/qualcomm/phy-qcom-snps-femto-v2.c index a59063596214..6c237f3cc66d 100644 --- a/drivers/phy/qualcomm/phy-qcom-snps-femto-v2.c +++ b/drivers/phy/qualcomm/phy-qcom-snps-femto-v2.c @@ -115,11 +115,11 @@ struct phy_override_seq { * * @cfg_ahb_clk: AHB2PHY interface clock * @ref_clk: phy reference clock - * @iface_clk: phy interface clock * @phy_reset: phy reset control * @vregs: regulator supplies bulk data * @phy_initialized: if PHY has been initialized correctly * @mode: contains the current mode the PHY is in + * @update_seq_cfg: tuning parameters for phy init */ struct qcom_snps_hsphy { struct phy *phy; diff --git a/fs/eventpoll.c b/fs/eventpoll.c index 980483455cc0..266d45c7685b 100644 --- a/fs/eventpoll.c +++ b/fs/eventpoll.c @@ -1805,7 +1805,11 @@ static int ep_autoremove_wake_function(struct wait_queue_entry *wq_entry, { int ret = default_wake_function(wq_entry, mode, sync, key); - list_del_init(&wq_entry->entry); + /* + * Pairs with list_empty_careful in ep_poll, and ensures future loop + * iterations see the cause of this wakeup. + */ + list_del_init_careful(&wq_entry->entry); return ret; } diff --git a/fs/nilfs2/btnode.c b/fs/nilfs2/btnode.c index e956f886a1a1..5710833ac1cc 100644 --- a/fs/nilfs2/btnode.c +++ b/fs/nilfs2/btnode.c @@ -285,6 +285,14 @@ void nilfs_btnode_abort_change_key(struct address_space *btnc, if (nbh == NULL) { /* blocksize == pagesize */ xa_erase_irq(&btnc->i_pages, newkey); unlock_page(ctxt->bh->b_page); - } else - brelse(nbh); + } else { + /* + * When canceling a buffer that a prepare operation has + * allocated to copy a node block to another location, use + * nilfs_btnode_delete() to initialize and release the buffer + * so that the buffer flags will not be in an inconsistent + * state when it is reallocated. + */ + nilfs_btnode_delete(nbh); + } } diff --git a/fs/nilfs2/page.c b/fs/nilfs2/page.c index 5cf30827f244..b4e54d079b7d 100644 --- a/fs/nilfs2/page.c +++ b/fs/nilfs2/page.c @@ -370,7 +370,15 @@ void nilfs_clear_dirty_pages(struct address_space *mapping, bool silent) struct folio *folio = fbatch.folios[i]; folio_lock(folio); - nilfs_clear_dirty_page(&folio->page, silent); + + /* + * This folio may have been removed from the address + * space by truncation or invalidation when the lock + * was acquired. Skip processing in that case. + */ + if (likely(folio->mapping == mapping)) + nilfs_clear_dirty_page(&folio->page, silent); + folio_unlock(folio); } folio_batch_release(&fbatch); diff --git a/fs/nilfs2/segbuf.c b/fs/nilfs2/segbuf.c index 1362ccb64ec7..6e59dc19a732 100644 --- a/fs/nilfs2/segbuf.c +++ b/fs/nilfs2/segbuf.c @@ -101,6 +101,12 @@ int nilfs_segbuf_extend_segsum(struct nilfs_segment_buffer *segbuf) if (unlikely(!bh)) return -ENOMEM; + lock_buffer(bh); + if (!buffer_uptodate(bh)) { + memset(bh->b_data, 0, bh->b_size); + set_buffer_uptodate(bh); + } + unlock_buffer(bh); nilfs_segbuf_add_segsum_buffer(segbuf, bh); return 0; } diff --git a/fs/nilfs2/segment.c b/fs/nilfs2/segment.c index ac949fd7603f..c2553024bd25 100644 --- a/fs/nilfs2/segment.c +++ b/fs/nilfs2/segment.c @@ -981,10 +981,13 @@ static void nilfs_segctor_fill_in_super_root(struct nilfs_sc_info *sci, unsigned int isz, srsz; bh_sr = NILFS_LAST_SEGBUF(&sci->sc_segbufs)->sb_super_root; + + lock_buffer(bh_sr); raw_sr = (struct nilfs_super_root *)bh_sr->b_data; isz = nilfs->ns_inode_size; srsz = NILFS_SR_BYTES(isz); + raw_sr->sr_sum = 0; /* Ensure initialization within this update */ raw_sr->sr_bytes = cpu_to_le16(srsz); raw_sr->sr_nongc_ctime = cpu_to_le64(nilfs_doing_gc() ? @@ -998,6 +1001,8 @@ static void nilfs_segctor_fill_in_super_root(struct nilfs_sc_info *sci, nilfs_write_inode_common(nilfs->ns_sufile, (void *)raw_sr + NILFS_SR_SUFILE_OFFSET(isz), 1); memset((void *)raw_sr + srsz, 0, nilfs->ns_blocksize - srsz); + set_buffer_uptodate(bh_sr); + unlock_buffer(bh_sr); } static void nilfs_redirty_inodes(struct list_head *head) @@ -1780,6 +1785,7 @@ static void nilfs_abort_logs(struct list_head *logs, int err) list_for_each_entry(segbuf, logs, sb_list) { list_for_each_entry(bh, &segbuf->sb_segsum_buffers, b_assoc_buffers) { + clear_buffer_uptodate(bh); if (bh->b_page != bd_page) { if (bd_page) end_page_writeback(bd_page); @@ -1791,6 +1797,7 @@ static void nilfs_abort_logs(struct list_head *logs, int err) b_assoc_buffers) { clear_buffer_async_write(bh); if (bh == segbuf->sb_super_root) { + clear_buffer_uptodate(bh); if (bh->b_page != bd_page) { end_page_writeback(bd_page); bd_page = bh->b_page; diff --git a/fs/nilfs2/sufile.c b/fs/nilfs2/sufile.c index dc359b56fdfa..2c6078a6b8ec 100644 --- a/fs/nilfs2/sufile.c +++ b/fs/nilfs2/sufile.c @@ -779,6 +779,15 @@ int nilfs_sufile_resize(struct inode *sufile, __u64 newnsegs) goto out_header; sui->ncleansegs -= nsegs - newnsegs; + + /* + * If the sufile is successfully truncated, immediately adjust + * the segment allocation space while locking the semaphore + * "mi_sem" so that nilfs_sufile_alloc() never allocates + * segments in the truncated space. + */ + sui->allocmax = newnsegs - 1; + sui->allocmin = 0; } kaddr = kmap_atomic(header_bh->b_page); diff --git a/fs/nilfs2/super.c b/fs/nilfs2/super.c index 77f1e5778d1c..9ba4933087af 100644 --- a/fs/nilfs2/super.c +++ b/fs/nilfs2/super.c @@ -372,10 +372,31 @@ static int nilfs_move_2nd_super(struct super_block *sb, loff_t sb2off) goto out; } nsbp = (void *)nsbh->b_data + offset; - memset(nsbp, 0, nilfs->ns_blocksize); + lock_buffer(nsbh); if (sb2i >= 0) { + /* + * The position of the second superblock only changes by 4KiB, + * which is larger than the maximum superblock data size + * (= 1KiB), so there is no need to use memmove() to allow + * overlap between source and destination. + */ memcpy(nsbp, nilfs->ns_sbp[sb2i], nilfs->ns_sbsize); + + /* + * Zero fill after copy to avoid overwriting in case of move + * within the same block. + */ + memset(nsbh->b_data, 0, offset); + memset((void *)nsbp + nilfs->ns_sbsize, 0, + nsbh->b_size - offset - nilfs->ns_sbsize); + } else { + memset(nsbh->b_data, 0, nsbh->b_size); + } + set_buffer_uptodate(nsbh); + unlock_buffer(nsbh); + + if (sb2i >= 0) { brelse(nilfs->ns_sbh[sb2i]); nilfs->ns_sbh[sb2i] = nsbh; nilfs->ns_sbp[sb2i] = nsbp; diff --git a/fs/nilfs2/the_nilfs.c b/fs/nilfs2/the_nilfs.c index 2894152a6b25..0f0667957c81 100644 --- a/fs/nilfs2/the_nilfs.c +++ b/fs/nilfs2/the_nilfs.c @@ -405,6 +405,18 @@ unsigned long nilfs_nrsvsegs(struct the_nilfs *nilfs, unsigned long nsegs) 100)); } +/** + * nilfs_max_segment_count - calculate the maximum number of segments + * @nilfs: nilfs object + */ +static u64 nilfs_max_segment_count(struct the_nilfs *nilfs) +{ + u64 max_count = U64_MAX; + + do_div(max_count, nilfs->ns_blocks_per_segment); + return min_t(u64, max_count, ULONG_MAX); +} + void nilfs_set_nsegments(struct the_nilfs *nilfs, unsigned long nsegs) { nilfs->ns_nsegments = nsegs; @@ -414,6 +426,8 @@ void nilfs_set_nsegments(struct the_nilfs *nilfs, unsigned long nsegs) static int nilfs_store_disk_layout(struct the_nilfs *nilfs, struct nilfs_super_block *sbp) { + u64 nsegments, nblocks; + if (le32_to_cpu(sbp->s_rev_level) < NILFS_MIN_SUPP_REV) { nilfs_err(nilfs->ns_sb, "unsupported revision (superblock rev.=%d.%d, current rev.=%d.%d). Please check the version of mkfs.nilfs(2).", @@ -457,7 +471,34 @@ static int nilfs_store_disk_layout(struct the_nilfs *nilfs, return -EINVAL; } - nilfs_set_nsegments(nilfs, le64_to_cpu(sbp->s_nsegments)); + nsegments = le64_to_cpu(sbp->s_nsegments); + if (nsegments > nilfs_max_segment_count(nilfs)) { + nilfs_err(nilfs->ns_sb, + "segment count %llu exceeds upper limit (%llu segments)", + (unsigned long long)nsegments, + (unsigned long long)nilfs_max_segment_count(nilfs)); + return -EINVAL; + } + + nblocks = sb_bdev_nr_blocks(nilfs->ns_sb); + if (nblocks) { + u64 min_block_count = nsegments * nilfs->ns_blocks_per_segment; + /* + * To avoid failing to mount early device images without a + * second superblock, exclude that block count from the + * "min_block_count" calculation. + */ + + if (nblocks < min_block_count) { + nilfs_err(nilfs->ns_sb, + "total number of segment blocks %llu exceeds device size (%llu blocks)", + (unsigned long long)min_block_count, + (unsigned long long)nblocks); + return -EINVAL; + } + } + + nilfs_set_nsegments(nilfs, nsegments); nilfs->ns_crc_seed = le32_to_cpu(sbp->s_crc_seed); return 0; } diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c index efb09de4343d..b173c36bcab3 100644 --- a/fs/ocfs2/file.c +++ b/fs/ocfs2/file.c @@ -2100,14 +2100,20 @@ static long ocfs2_fallocate(struct file *file, int mode, loff_t offset, struct ocfs2_space_resv sr; int change_size = 1; int cmd = OCFS2_IOC_RESVSP64; + int ret = 0; if (mode & ~(FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE)) return -EOPNOTSUPP; if (!ocfs2_writes_unwritten_extents(osb)) return -EOPNOTSUPP; - if (mode & FALLOC_FL_KEEP_SIZE) + if (mode & FALLOC_FL_KEEP_SIZE) { change_size = 0; + } else { + ret = inode_newsize_ok(inode, offset + len); + if (ret) + return ret; + } if (mode & FALLOC_FL_PUNCH_HOLE) cmd = OCFS2_IOC_UNRESVSP64; diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c index 0b0e6a132101..988d1c076861 100644 --- a/fs/ocfs2/super.c +++ b/fs/ocfs2/super.c @@ -952,8 +952,10 @@ static void ocfs2_disable_quotas(struct ocfs2_super *osb) for (type = 0; type < OCFS2_MAXQUOTAS; type++) { if (!sb_has_quota_loaded(sb, type)) continue; - oinfo = sb_dqinfo(sb, type)->dqi_priv; - cancel_delayed_work_sync(&oinfo->dqi_sync_work); + if (!sb_has_quota_suspended(sb, type)) { + oinfo = sb_dqinfo(sb, type)->dqi_priv; + cancel_delayed_work_sync(&oinfo->dqi_sync_work); + } inode = igrab(sb->s_dquot.files[type]); /* Turn off quotas. This will remove all dquot structures from * memory and so they will be automatically synced to global diff --git a/fs/super.c b/fs/super.c index 34afe411cf2b..04bc62ab7dfe 100644 --- a/fs/super.c +++ b/fs/super.c @@ -54,7 +54,7 @@ static char *sb_writers_name[SB_FREEZE_LEVELS] = { * One thing we have to be careful of with a per-sb shrinker is that we don't * drop the last active reference to the superblock from within the shrinker. * If that happens we could trigger unregistering the shrinker from within the - * shrinker path and that leads to deadlock on the shrinker_mutex. Hence we + * shrinker path and that leads to deadlock on the shrinker_rwsem. Hence we * take a passive reference to the superblock to avoid this from occurring. */ static unsigned long super_cache_scan(struct shrinker *shrink, diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c index 0aa5caac5164..7cecd49e078b 100644 --- a/fs/userfaultfd.c +++ b/fs/userfaultfd.c @@ -1322,6 +1322,7 @@ static int userfaultfd_register(struct userfaultfd_ctx *ctx, bool basic_ioctls; unsigned long start, end, vma_end; struct vma_iterator vmi; + pgoff_t pgoff; user_uffdio_register = (struct uffdio_register __user *) arg; @@ -1449,6 +1450,8 @@ static int userfaultfd_register(struct userfaultfd_ctx *ctx, vma_iter_set(&vmi, start); prev = vma_prev(&vmi); + if (vma->vm_start < start) + prev = vma; ret = 0; for_each_vma_range(vmi, vma, end) { @@ -1472,8 +1475,9 @@ static int userfaultfd_register(struct userfaultfd_ctx *ctx, vma_end = min(end, vma->vm_end); new_flags = (vma->vm_flags & ~__VM_UFFD_FLAGS) | vm_flags; + pgoff = vma->vm_pgoff + ((start - vma->vm_start) >> PAGE_SHIFT); prev = vma_merge(&vmi, mm, prev, start, vma_end, new_flags, - vma->anon_vma, vma->vm_file, vma->vm_pgoff, + vma->anon_vma, vma->vm_file, pgoff, vma_policy(vma), ((struct vm_userfaultfd_ctx){ ctx }), anon_vma_name(vma)); @@ -1553,6 +1557,7 @@ static int userfaultfd_unregister(struct userfaultfd_ctx *ctx, unsigned long start, end, vma_end; const void __user *buf = (void __user *)arg; struct vma_iterator vmi; + pgoff_t pgoff; ret = -EFAULT; if (copy_from_user(&uffdio_unregister, buf, sizeof(uffdio_unregister))) @@ -1615,6 +1620,9 @@ static int userfaultfd_unregister(struct userfaultfd_ctx *ctx, vma_iter_set(&vmi, start); prev = vma_prev(&vmi); + if (vma->vm_start < start) + prev = vma; + ret = 0; for_each_vma_range(vmi, vma, end) { cond_resched(); @@ -1652,8 +1660,9 @@ static int userfaultfd_unregister(struct userfaultfd_ctx *ctx, uffd_wp_range(vma, start, vma_end - start, false); new_flags = vma->vm_flags & ~__VM_UFFD_FLAGS; + pgoff = vma->vm_pgoff + ((start - vma->vm_start) >> PAGE_SHIFT); prev = vma_merge(&vmi, mm, prev, start, vma_end, new_flags, - vma->anon_vma, vma->vm_file, vma->vm_pgoff, + vma->anon_vma, vma->vm_file, pgoff, vma_policy(vma), NULL_VM_UFFD_CTX, anon_vma_name(vma)); if (prev) { diff --git a/include/linux/fs.h b/include/linux/fs.h index c363f8687c7e..6af251375438 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2566,12 +2566,6 @@ static inline int deny_write_access(struct file *file) struct inode *inode = file_inode(file); return atomic_dec_unless_positive(&inode->i_writecount) ? 0 : -ETXTBSY; } -static inline int exclusive_deny_write_access(struct file *file) -{ - int old = 0; - struct inode *inode = file_inode(file); - return atomic_try_cmpxchg(&inode->i_writecount, &old, -1) ? 0 : -ETXTBSY; -} static inline void put_write_access(struct inode * inode) { atomic_dec(&inode->i_writecount); diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h index 0e373222a6df..7c4a0b72334e 100644 --- a/include/linux/trace_events.h +++ b/include/linux/trace_events.h @@ -806,6 +806,7 @@ enum { FILTER_TRACE_FN, FILTER_COMM, FILTER_CPU, + FILTER_STACKTRACE, }; extern int trace_event_raw_init(struct trace_event_call *call); diff --git a/include/linux/user_events.h b/include/linux/user_events.h index 2847f5a18a86..8afa8c3a0973 100644 --- a/include/linux/user_events.h +++ b/include/linux/user_events.h @@ -17,9 +17,10 @@ #ifdef CONFIG_USER_EVENTS struct user_event_mm { - struct list_head link; + struct list_head mms_link; struct list_head enablers; struct mm_struct *mm; + /* Used for one-shot lists, protected by event_mutex */ struct user_event_mm *next; refcount_t refcnt; refcount_t tasks; diff --git a/include/trace/events/writeback.h b/include/trace/events/writeback.h index 86b2a82da546..54e353c9f919 100644 --- a/include/trace/events/writeback.h +++ b/include/trace/events/writeback.h @@ -68,7 +68,7 @@ DECLARE_EVENT_CLASS(writeback_folio_template, strscpy_pad(__entry->name, bdi_dev_name(mapping ? inode_to_bdi(mapping->host) : NULL), 32); - __entry->ino = mapping ? mapping->host->i_ino : 0; + __entry->ino = (mapping && mapping->host) ? mapping->host->i_ino : 0; __entry->index = folio->index; ), diff --git a/kernel/kexec_file.c b/kernel/kexec_file.c index f989f5f1933b..69ee4a29136f 100644 --- a/kernel/kexec_file.c +++ b/kernel/kexec_file.c @@ -901,10 +901,22 @@ static int kexec_purgatory_setup_sechdrs(struct purgatory_info *pi, } offset = ALIGN(offset, align); + + /* + * Check if the segment contains the entry point, if so, + * calculate the value of image->start based on it. + * If the compiler has produced more than one .text section + * (Eg: .text.hot), they are generally after the main .text + * section, and they shall not be used to calculate + * image->start. So do not re-calculate image->start if it + * is not set to the initial value, and warn the user so they + * have a chance to fix their purgatory's linker script. + */ if (sechdrs[i].sh_flags & SHF_EXECINSTR && pi->ehdr->e_entry >= sechdrs[i].sh_addr && pi->ehdr->e_entry < (sechdrs[i].sh_addr - + sechdrs[i].sh_size)) { + + sechdrs[i].sh_size) && + !WARN_ON(kbuf->image->start != pi->ehdr->e_entry)) { kbuf->image->start -= sechdrs[i].sh_addr; kbuf->image->start += kbuf->mem + offset; } diff --git a/kernel/module/main.c b/kernel/module/main.c index b4c7e925fdb0..044aa2c9e3cb 100644 --- a/kernel/module/main.c +++ b/kernel/module/main.c @@ -3057,13 +3057,25 @@ SYSCALL_DEFINE3(init_module, void __user *, umod, return load_module(&info, uargs, 0); } -static int file_init_module(struct file *file, const char __user * uargs, int flags) +SYSCALL_DEFINE3(finit_module, int, fd, const char __user *, uargs, int, flags) { struct load_info info = { }; void *buf = NULL; int len; + int err; + + err = may_init_module(); + if (err) + return err; + + pr_debug("finit_module: fd=%d, uargs=%p, flags=%i\n", fd, uargs, flags); - len = kernel_read_file(file, 0, &buf, INT_MAX, NULL, + if (flags & ~(MODULE_INIT_IGNORE_MODVERSIONS + |MODULE_INIT_IGNORE_VERMAGIC + |MODULE_INIT_COMPRESSED_FILE)) + return -EINVAL; + + len = kernel_read_file_from_fd(fd, 0, &buf, INT_MAX, NULL, READING_MODULE); if (len < 0) { mod_stat_inc(&failed_kreads); @@ -3072,7 +3084,7 @@ static int file_init_module(struct file *file, const char __user * uargs, int fl } if (flags & MODULE_INIT_COMPRESSED_FILE) { - int err = module_decompress(&info, buf, len); + err = module_decompress(&info, buf, len); vfree(buf); /* compressed data is no longer needed */ if (err) { mod_stat_inc(&failed_decompress); @@ -3087,46 +3099,6 @@ static int file_init_module(struct file *file, const char __user * uargs, int fl return load_module(&info, uargs, flags); } -/* - * kernel_read_file() will already deny write access, but module - * loading wants _exclusive_ access to the file, so we do that - * here, along with basic sanity checks. - */ -static int prepare_file_for_module_load(struct file *file) -{ - if (!file || !(file->f_mode & FMODE_READ)) - return -EBADF; - if (!S_ISREG(file_inode(file)->i_mode)) - return -EINVAL; - return exclusive_deny_write_access(file); -} - -SYSCALL_DEFINE3(finit_module, int, fd, const char __user *, uargs, int, flags) -{ - struct fd f; - int err; - - err = may_init_module(); - if (err) - return err; - - pr_debug("finit_module: fd=%d, uargs=%p, flags=%i\n", fd, uargs, flags); - - if (flags & ~(MODULE_INIT_IGNORE_MODVERSIONS - |MODULE_INIT_IGNORE_VERMAGIC - |MODULE_INIT_COMPRESSED_FILE)) - return -EINVAL; - - f = fdget(fd); - err = prepare_file_for_module_load(f.file); - if (!err) { - err = file_init_module(f.file, uargs, flags); - allow_write_access(f.file); - } - fdput(f); - return err; -} - /* Keep in sync with MODULE_FLAGS_BUF_SIZE !!! */ char *module_flags(struct module *mod, char *buf, bool show_state) { diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index ebc59781456a..64a4dde073ef 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -60,6 +60,7 @@ */ bool ring_buffer_expanded; +#ifdef CONFIG_FTRACE_STARTUP_TEST /* * We need to change this state when a selftest is running. * A selftest will lurk into the ring-buffer to count the @@ -75,7 +76,6 @@ static bool __read_mostly tracing_selftest_running; */ bool __read_mostly tracing_selftest_disabled; -#ifdef CONFIG_FTRACE_STARTUP_TEST void __init disable_tracing_selftest(const char *reason) { if (!tracing_selftest_disabled) { @@ -83,6 +83,9 @@ void __init disable_tracing_selftest(const char *reason) pr_info("Ftrace startup test is disabled due to %s\n", reason); } } +#else +#define tracing_selftest_running 0 +#define tracing_selftest_disabled 0 #endif /* Pipe tracepoints to printk */ @@ -1051,7 +1054,10 @@ int __trace_array_puts(struct trace_array *tr, unsigned long ip, if (!(tr->trace_flags & TRACE_ITER_PRINTK)) return 0; - if (unlikely(tracing_selftest_running || tracing_disabled)) + if (unlikely(tracing_selftest_running && tr == &global_trace)) + return 0; + + if (unlikely(tracing_disabled)) return 0; alloc = sizeof(*entry) + size + 2; /* possible \n added */ @@ -2041,6 +2047,24 @@ static int run_tracer_selftest(struct tracer *type) return 0; } +static int do_run_tracer_selftest(struct tracer *type) +{ + int ret; + + /* + * Tests can take a long time, especially if they are run one after the + * other, as does happen during bootup when all the tracers are + * registered. This could cause the soft lockup watchdog to trigger. + */ + cond_resched(); + + tracing_selftest_running = true; + ret = run_tracer_selftest(type); + tracing_selftest_running = false; + + return ret; +} + static __init int init_trace_selftests(void) { struct trace_selftests *p, *n; @@ -2092,6 +2116,10 @@ static inline int run_tracer_selftest(struct tracer *type) { return 0; } +static inline int do_run_tracer_selftest(struct tracer *type) +{ + return 0; +} #endif /* CONFIG_FTRACE_STARTUP_TEST */ static void add_tracer_options(struct trace_array *tr, struct tracer *t); @@ -2127,8 +2155,6 @@ int __init register_tracer(struct tracer *type) mutex_lock(&trace_types_lock); - tracing_selftest_running = true; - for (t = trace_types; t; t = t->next) { if (strcmp(type->name, t->name) == 0) { /* already found */ @@ -2157,7 +2183,7 @@ int __init register_tracer(struct tracer *type) /* store the tracer for __set_tracer_option */ type->flags->trace = type; - ret = run_tracer_selftest(type); + ret = do_run_tracer_selftest(type); if (ret < 0) goto out; @@ -2166,7 +2192,6 @@ int __init register_tracer(struct tracer *type) add_tracer_options(&global_trace, type); out: - tracing_selftest_running = false; mutex_unlock(&trace_types_lock); if (ret || !default_bootup_tracer) @@ -3490,7 +3515,7 @@ __trace_array_vprintk(struct trace_buffer *buffer, unsigned int trace_ctx; char *tbuffer; - if (tracing_disabled || tracing_selftest_running) + if (tracing_disabled) return 0; /* Don't pollute graph traces with trace_vprintk internals */ @@ -3538,6 +3563,9 @@ __printf(3, 0) int trace_array_vprintk(struct trace_array *tr, unsigned long ip, const char *fmt, va_list args) { + if (tracing_selftest_running && tr == &global_trace) + return 0; + return __trace_array_vprintk(tr->array_buffer.buffer, ip, fmt, args); } @@ -5752,7 +5780,7 @@ static const char readme_msg[] = "\t table using the key(s) and value(s) named, and the value of a\n" "\t sum called 'hitcount' is incremented. Keys and values\n" "\t correspond to fields in the event's format description. Keys\n" - "\t can be any field, or the special string 'stacktrace'.\n" + "\t can be any field, or the special string 'common_stacktrace'.\n" "\t Compound keys consisting of up to two fields can be specified\n" "\t by the 'keys' keyword. Values must correspond to numeric\n" "\t fields. Sort keys consisting of up to two fields can be\n" diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index 654ffa40457a..57e539d47989 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -194,6 +194,8 @@ static int trace_define_generic_fields(void) __generic_field(int, common_cpu, FILTER_CPU); __generic_field(char *, COMM, FILTER_COMM); __generic_field(char *, comm, FILTER_COMM); + __generic_field(char *, stacktrace, FILTER_STACKTRACE); + __generic_field(char *, STACKTRACE, FILTER_STACKTRACE); return ret; } diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c index 486cca3c2b75..b97d3ad832f1 100644 --- a/kernel/trace/trace_events_hist.c +++ b/kernel/trace/trace_events_hist.c @@ -1364,7 +1364,7 @@ static const char *hist_field_name(struct hist_field *field, if (field->field) field_name = field->field->name; else - field_name = "stacktrace"; + field_name = "common_stacktrace"; } else if (field->flags & HIST_FIELD_FL_HITCOUNT) field_name = "hitcount"; @@ -2367,7 +2367,7 @@ parse_field(struct hist_trigger_data *hist_data, struct trace_event_file *file, hist_data->enable_timestamps = true; if (*flags & HIST_FIELD_FL_TIMESTAMP_USECS) hist_data->attrs->ts_in_usecs = true; - } else if (strcmp(field_name, "stacktrace") == 0) { + } else if (strcmp(field_name, "common_stacktrace") == 0) { *flags |= HIST_FIELD_FL_STACKTRACE; } else if (strcmp(field_name, "common_cpu") == 0) *flags |= HIST_FIELD_FL_CPU; @@ -2378,11 +2378,15 @@ parse_field(struct hist_trigger_data *hist_data, struct trace_event_file *file, if (!field || !field->size) { /* * For backward compatibility, if field_name - * was "cpu", then we treat this the same as - * common_cpu. This also works for "CPU". + * was "cpu" or "stacktrace", then we treat this + * the same as common_cpu and common_stacktrace + * respectively. This also works for "CPU", and + * "STACKTRACE". */ if (field && field->filter_type == FILTER_CPU) { *flags |= HIST_FIELD_FL_CPU; + } else if (field && field->filter_type == FILTER_STACKTRACE) { + *flags |= HIST_FIELD_FL_STACKTRACE; } else { hist_err(tr, HIST_ERR_FIELD_NOT_FOUND, errpos(field_name)); @@ -4238,13 +4242,19 @@ static int __create_val_field(struct hist_trigger_data *hist_data, goto out; } - /* Some types cannot be a value */ - if (hist_field->flags & (HIST_FIELD_FL_GRAPH | HIST_FIELD_FL_PERCENT | - HIST_FIELD_FL_BUCKET | HIST_FIELD_FL_LOG2 | - HIST_FIELD_FL_SYM | HIST_FIELD_FL_SYM_OFFSET | - HIST_FIELD_FL_SYSCALL | HIST_FIELD_FL_STACKTRACE)) { - hist_err(file->tr, HIST_ERR_BAD_FIELD_MODIFIER, errpos(field_str)); - ret = -EINVAL; + /* values and variables should not have some modifiers */ + if (hist_field->flags & HIST_FIELD_FL_VAR) { + /* Variable */ + if (hist_field->flags & (HIST_FIELD_FL_GRAPH | HIST_FIELD_FL_PERCENT | + HIST_FIELD_FL_BUCKET | HIST_FIELD_FL_LOG2)) + goto err; + } else { + /* Value */ + if (hist_field->flags & (HIST_FIELD_FL_GRAPH | HIST_FIELD_FL_PERCENT | + HIST_FIELD_FL_BUCKET | HIST_FIELD_FL_LOG2 | + HIST_FIELD_FL_SYM | HIST_FIELD_FL_SYM_OFFSET | + HIST_FIELD_FL_SYSCALL | HIST_FIELD_FL_STACKTRACE)) + goto err; } hist_data->fields[val_idx] = hist_field; @@ -4256,6 +4266,9 @@ static int __create_val_field(struct hist_trigger_data *hist_data, ret = -EINVAL; out: return ret; + err: + hist_err(file->tr, HIST_ERR_BAD_FIELD_MODIFIER, errpos(field_str)); + return -EINVAL; } static int create_val_field(struct hist_trigger_data *hist_data, @@ -5385,7 +5398,7 @@ static void hist_trigger_print_key(struct seq_file *m, if (key_field->field) seq_printf(m, "%s.stacktrace", key_field->field->name); else - seq_puts(m, "stacktrace:\n"); + seq_puts(m, "common_stacktrace:\n"); hist_trigger_stacktrace_print(m, key + key_field->offset, HIST_STACKTRACE_DEPTH); @@ -5968,7 +5981,7 @@ static int event_hist_trigger_print(struct seq_file *m, if (field->field) seq_printf(m, "%s.stacktrace", field->field->name); else - seq_puts(m, "stacktrace"); + seq_puts(m, "common_stacktrace"); } else hist_field_print(m, field); } diff --git a/kernel/trace/trace_events_user.c b/kernel/trace/trace_events_user.c index bdc2666e8d39..8e196bace108 100644 --- a/kernel/trace/trace_events_user.c +++ b/kernel/trace/trace_events_user.c @@ -96,12 +96,12 @@ struct user_event { * these to track enablement sites that are tied to an event. */ struct user_event_enabler { - struct list_head link; + struct list_head mm_enablers_link; struct user_event *event; unsigned long addr; /* Track enable bit, flags, etc. Aligned for bitops. */ - unsigned int values; + unsigned long values; }; /* Bits 0-5 are for the bit to update upon enable/disable (0-63 allowed) */ @@ -116,7 +116,9 @@ struct user_event_enabler { /* Only duplicate the bit value */ #define ENABLE_VAL_DUP_MASK ENABLE_VAL_BIT_MASK -#define ENABLE_BITOPS(e) ((unsigned long *)&(e)->values) +#define ENABLE_BITOPS(e) (&(e)->values) + +#define ENABLE_BIT(e) ((int)((e)->values & ENABLE_VAL_BIT_MASK)) /* Used for asynchronous faulting in of pages */ struct user_event_enabler_fault { @@ -153,7 +155,7 @@ struct user_event_file_info { #define VALIDATOR_REL (1 << 1) struct user_event_validator { - struct list_head link; + struct list_head user_event_link; int offset; int flags; }; @@ -259,7 +261,7 @@ error: static void user_event_enabler_destroy(struct user_event_enabler *enabler) { - list_del_rcu(&enabler->link); + list_del_rcu(&enabler->mm_enablers_link); /* No longer tracking the event via the enabler */ refcount_dec(&enabler->event->refcnt); @@ -423,9 +425,9 @@ static int user_event_enabler_write(struct user_event_mm *mm, /* Update bit atomically, user tracers must be atomic as well */ if (enabler->event && enabler->event->status) - set_bit(enabler->values & ENABLE_VAL_BIT_MASK, ptr); + set_bit(ENABLE_BIT(enabler), ptr); else - clear_bit(enabler->values & ENABLE_VAL_BIT_MASK, ptr); + clear_bit(ENABLE_BIT(enabler), ptr); kunmap_local(kaddr); unpin_user_pages_dirty_lock(&page, 1, true); @@ -437,11 +439,9 @@ static bool user_event_enabler_exists(struct user_event_mm *mm, unsigned long uaddr, unsigned char bit) { struct user_event_enabler *enabler; - struct user_event_enabler *next; - list_for_each_entry_safe(enabler, next, &mm->enablers, link) { - if (enabler->addr == uaddr && - (enabler->values & ENABLE_VAL_BIT_MASK) == bit) + list_for_each_entry(enabler, &mm->enablers, mm_enablers_link) { + if (enabler->addr == uaddr && ENABLE_BIT(enabler) == bit) return true; } @@ -451,23 +451,36 @@ static bool user_event_enabler_exists(struct user_event_mm *mm, static void user_event_enabler_update(struct user_event *user) { struct user_event_enabler *enabler; - struct user_event_mm *mm = user_event_mm_get_all(user); struct user_event_mm *next; + struct user_event_mm *mm; int attempt; + lockdep_assert_held(&event_mutex); + + /* + * We need to build a one-shot list of all the mms that have an + * enabler for the user_event passed in. This list is only valid + * while holding the event_mutex. The only reason for this is due + * to the global mm list being RCU protected and we use methods + * which can wait (mmap_read_lock and pin_user_pages_remote). + * + * NOTE: user_event_mm_get_all() increments the ref count of each + * mm that is added to the list to prevent removal timing windows. + * We must always put each mm after they are used, which may wait. + */ + mm = user_event_mm_get_all(user); + while (mm) { next = mm->next; mmap_read_lock(mm->mm); - rcu_read_lock(); - list_for_each_entry_rcu(enabler, &mm->enablers, link) { + list_for_each_entry(enabler, &mm->enablers, mm_enablers_link) { if (enabler->event == user) { attempt = 0; user_event_enabler_write(mm, enabler, true, &attempt); } } - rcu_read_unlock(); mmap_read_unlock(mm->mm); user_event_mm_put(mm); mm = next; @@ -495,7 +508,9 @@ static bool user_event_enabler_dup(struct user_event_enabler *orig, enabler->values = orig->values & ENABLE_VAL_DUP_MASK; refcount_inc(&enabler->event->refcnt); - list_add_rcu(&enabler->link, &mm->enablers); + + /* Enablers not exposed yet, RCU not required */ + list_add(&enabler->mm_enablers_link, &mm->enablers); return true; } @@ -514,6 +529,14 @@ static struct user_event_mm *user_event_mm_get_all(struct user_event *user) struct user_event_mm *mm; /* + * We use the mm->next field to build a one-shot list from the global + * RCU protected list. To build this list the event_mutex must be held. + * This lets us build a list without requiring allocs that could fail + * when user based events are most wanted for diagnostics. + */ + lockdep_assert_held(&event_mutex); + + /* * We do not want to block fork/exec while enablements are being * updated, so we use RCU to walk the current tasks that have used * user_events ABI for 1 or more events. Each enabler found in each @@ -525,23 +548,24 @@ static struct user_event_mm *user_event_mm_get_all(struct user_event *user) */ rcu_read_lock(); - list_for_each_entry_rcu(mm, &user_event_mms, link) - list_for_each_entry_rcu(enabler, &mm->enablers, link) + list_for_each_entry_rcu(mm, &user_event_mms, mms_link) { + list_for_each_entry_rcu(enabler, &mm->enablers, mm_enablers_link) { if (enabler->event == user) { mm->next = found; found = user_event_mm_get(mm); break; } + } + } rcu_read_unlock(); return found; } -static struct user_event_mm *user_event_mm_create(struct task_struct *t) +static struct user_event_mm *user_event_mm_alloc(struct task_struct *t) { struct user_event_mm *user_mm; - unsigned long flags; user_mm = kzalloc(sizeof(*user_mm), GFP_KERNEL_ACCOUNT); @@ -553,12 +577,6 @@ static struct user_event_mm *user_event_mm_create(struct task_struct *t) refcount_set(&user_mm->refcnt, 1); refcount_set(&user_mm->tasks, 1); - spin_lock_irqsave(&user_event_mms_lock, flags); - list_add_rcu(&user_mm->link, &user_event_mms); - spin_unlock_irqrestore(&user_event_mms_lock, flags); - - t->user_event_mm = user_mm; - /* * The lifetime of the memory descriptor can slightly outlast * the task lifetime if a ref to the user_event_mm is taken @@ -572,6 +590,17 @@ static struct user_event_mm *user_event_mm_create(struct task_struct *t) return user_mm; } +static void user_event_mm_attach(struct user_event_mm *user_mm, struct task_struct *t) +{ + unsigned long flags; + + spin_lock_irqsave(&user_event_mms_lock, flags); + list_add_rcu(&user_mm->mms_link, &user_event_mms); + spin_unlock_irqrestore(&user_event_mms_lock, flags); + + t->user_event_mm = user_mm; +} + static struct user_event_mm *current_user_event_mm(void) { struct user_event_mm *user_mm = current->user_event_mm; @@ -579,10 +608,12 @@ static struct user_event_mm *current_user_event_mm(void) if (user_mm) goto inc; - user_mm = user_event_mm_create(current); + user_mm = user_event_mm_alloc(current); if (!user_mm) goto error; + + user_event_mm_attach(user_mm, current); inc: refcount_inc(&user_mm->refcnt); error: @@ -593,7 +624,7 @@ static void user_event_mm_destroy(struct user_event_mm *mm) { struct user_event_enabler *enabler, *next; - list_for_each_entry_safe(enabler, next, &mm->enablers, link) + list_for_each_entry_safe(enabler, next, &mm->enablers, mm_enablers_link) user_event_enabler_destroy(enabler); mmdrop(mm->mm); @@ -630,7 +661,7 @@ void user_event_mm_remove(struct task_struct *t) /* Remove the mm from the list, so it can no longer be enabled */ spin_lock_irqsave(&user_event_mms_lock, flags); - list_del_rcu(&mm->link); + list_del_rcu(&mm->mms_link); spin_unlock_irqrestore(&user_event_mms_lock, flags); /* @@ -670,7 +701,7 @@ void user_event_mm_remove(struct task_struct *t) void user_event_mm_dup(struct task_struct *t, struct user_event_mm *old_mm) { - struct user_event_mm *mm = user_event_mm_create(t); + struct user_event_mm *mm = user_event_mm_alloc(t); struct user_event_enabler *enabler; if (!mm) @@ -678,16 +709,18 @@ void user_event_mm_dup(struct task_struct *t, struct user_event_mm *old_mm) rcu_read_lock(); - list_for_each_entry_rcu(enabler, &old_mm->enablers, link) + list_for_each_entry_rcu(enabler, &old_mm->enablers, mm_enablers_link) { if (!user_event_enabler_dup(enabler, mm)) goto error; + } rcu_read_unlock(); + user_event_mm_attach(mm, t); return; error: rcu_read_unlock(); - user_event_mm_remove(t); + user_event_mm_destroy(mm); } static bool current_user_event_enabler_exists(unsigned long uaddr, @@ -748,7 +781,7 @@ retry: */ if (!*write_result) { refcount_inc(&enabler->event->refcnt); - list_add_rcu(&enabler->link, &user_mm->enablers); + list_add_rcu(&enabler->mm_enablers_link, &user_mm->enablers); } mutex_unlock(&event_mutex); @@ -904,8 +937,8 @@ static void user_event_destroy_validators(struct user_event *user) struct user_event_validator *validator, *next; struct list_head *head = &user->validators; - list_for_each_entry_safe(validator, next, head, link) { - list_del(&validator->link); + list_for_each_entry_safe(validator, next, head, user_event_link) { + list_del(&validator->user_event_link); kfree(validator); } } @@ -959,7 +992,7 @@ add_validator: validator->offset = offset; /* Want sequential access when validating */ - list_add_tail(&validator->link, &user->validators); + list_add_tail(&validator->user_event_link, &user->validators); add_field: field->type = type; @@ -1349,7 +1382,7 @@ static int user_event_validate(struct user_event *user, void *data, int len) void *pos, *end = data + len; u32 loc, offset, size; - list_for_each_entry(validator, head, link) { + list_for_each_entry(validator, head, user_event_link) { pos = data + validator->offset; /* Already done min_size check, no bounds check here */ @@ -2270,9 +2303,9 @@ static long user_events_ioctl_unreg(unsigned long uarg) */ mutex_lock(&event_mutex); - list_for_each_entry_safe(enabler, next, &mm->enablers, link) + list_for_each_entry_safe(enabler, next, &mm->enablers, mm_enablers_link) { if (enabler->addr == reg.disable_addr && - (enabler->values & ENABLE_VAL_BIT_MASK) == reg.disable_bit) { + ENABLE_BIT(enabler) == reg.disable_bit) { set_bit(ENABLE_VAL_FREEING_BIT, ENABLE_BITOPS(enabler)); if (!test_bit(ENABLE_VAL_FAULTING_BIT, ENABLE_BITOPS(enabler))) @@ -2281,6 +2314,7 @@ static long user_events_ioctl_unreg(unsigned long uarg) /* Removed at least one */ ret = 0; } + } mutex_unlock(&event_mutex); diff --git a/kernel/trace/trace_osnoise.c b/kernel/trace/trace_osnoise.c index efbbec2caff8..e97e3fa5cbed 100644 --- a/kernel/trace/trace_osnoise.c +++ b/kernel/trace/trace_osnoise.c @@ -1652,6 +1652,8 @@ static enum hrtimer_restart timerlat_irq(struct hrtimer *timer) osnoise_stop_tracing(); notify_new_max_latency(diff); + wake_up_process(tlat->kthread); + return HRTIMER_NORESTART; } } diff --git a/kernel/trace/trace_selftest.c b/kernel/trace/trace_selftest.c index a931d9aaea26..529590499b1f 100644 --- a/kernel/trace/trace_selftest.c +++ b/kernel/trace/trace_selftest.c @@ -848,6 +848,12 @@ trace_selftest_startup_function_graph(struct tracer *trace, } #ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS + /* + * These tests can take some time to run. Make sure on non PREEMPT + * kernels, we do not trigger the softlockup detector. + */ + cond_resched(); + tracing_reset_online_cpus(&tr->array_buffer); set_graph_array(tr); @@ -869,6 +875,8 @@ trace_selftest_startup_function_graph(struct tracer *trace, if (ret) goto out; + cond_resched(); + ret = register_ftrace_graph(&fgraph_ops); if (ret) { warn_failed_init_tracer(trace, ret); @@ -891,6 +899,8 @@ trace_selftest_startup_function_graph(struct tracer *trace, if (ret) goto out; + cond_resched(); + tracing_start(); if (!ret && !count) { diff --git a/lib/radix-tree.c b/lib/radix-tree.c index 049ba132f7ef..1a31065b2036 100644 --- a/lib/radix-tree.c +++ b/lib/radix-tree.c @@ -27,6 +27,8 @@ #include <linux/string.h> #include <linux/xarray.h> +#include "radix-tree.h" + /* * Radix tree node cache. */ diff --git a/lib/radix-tree.h b/lib/radix-tree.h new file mode 100644 index 000000000000..40d5c03e2b09 --- /dev/null +++ b/lib/radix-tree.h @@ -0,0 +1,8 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* radix-tree helpers that are only shared with xarray */ + +struct kmem_cache; +struct rcu_head; + +extern struct kmem_cache *radix_tree_node_cachep; +extern void radix_tree_node_rcu_free(struct rcu_head *head); diff --git a/lib/test_vmalloc.c b/lib/test_vmalloc.c index 9dd9745d365f..3718d9886407 100644 --- a/lib/test_vmalloc.c +++ b/lib/test_vmalloc.c @@ -369,7 +369,7 @@ vm_map_ram_test(void) int i; map_nr_pages = nr_pages > 0 ? nr_pages:1; - pages = kmalloc(map_nr_pages * sizeof(struct page), GFP_KERNEL); + pages = kcalloc(map_nr_pages, sizeof(struct page *), GFP_KERNEL); if (!pages) return -1; diff --git a/lib/xarray.c b/lib/xarray.c index ea9ce1f0b386..2071a3718f4e 100644 --- a/lib/xarray.c +++ b/lib/xarray.c @@ -12,6 +12,8 @@ #include <linux/slab.h> #include <linux/xarray.h> +#include "radix-tree.h" + /* * Coding conventions in this file: * @@ -247,10 +249,6 @@ void *xas_load(struct xa_state *xas) } EXPORT_SYMBOL_GPL(xas_load); -/* Move the radix tree node cache here */ -extern struct kmem_cache *radix_tree_node_cachep; -extern void radix_tree_node_rcu_free(struct rcu_head *head); - #define XA_RCU_FREE ((struct xarray *)1) static void xa_node_free(struct xa_node *node) diff --git a/mm/damon/core.c b/mm/damon/core.c index d9ef62047bf5..91cff7f2997e 100644 --- a/mm/damon/core.c +++ b/mm/damon/core.c @@ -551,6 +551,8 @@ int damon_set_attrs(struct damon_ctx *ctx, struct damon_attrs *attrs) return -EINVAL; if (attrs->min_nr_regions > attrs->max_nr_regions) return -EINVAL; + if (attrs->sample_interval > attrs->aggr_interval) + return -EINVAL; damon_update_monitoring_results(ctx, attrs); ctx->attrs = *attrs; diff --git a/mm/filemap.c b/mm/filemap.c index 758bbdf300e7..c20e0b1997e8 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -1728,7 +1728,9 @@ bool __folio_lock_or_retry(struct folio *folio, struct mm_struct *mm, * * Return: The index of the gap if found, otherwise an index outside the * range specified (in which case 'return - index >= max_scan' will be true). - * In the rare case of index wrap-around, 0 will be returned. + * In the rare case of index wrap-around, 0 will be returned. 0 will also + * be returned if index == 0 and there is a gap at the index. We can not + * wrap-around if passed index == 0. */ pgoff_t page_cache_next_miss(struct address_space *mapping, pgoff_t index, unsigned long max_scan) @@ -1738,12 +1740,13 @@ pgoff_t page_cache_next_miss(struct address_space *mapping, while (max_scan--) { void *entry = xas_next(&xas); if (!entry || xa_is_value(entry)) - break; - if (xas.xa_index == 0) - break; + return xas.xa_index; + if (xas.xa_index == 0 && index != 0) + return xas.xa_index; } - return xas.xa_index; + /* No gaps in range and no wrap-around, return index beyond range */ + return xas.xa_index + 1; } EXPORT_SYMBOL(page_cache_next_miss); @@ -1764,7 +1767,9 @@ EXPORT_SYMBOL(page_cache_next_miss); * * Return: The index of the gap if found, otherwise an index outside the * range specified (in which case 'index - return >= max_scan' will be true). - * In the rare case of wrap-around, ULONG_MAX will be returned. + * In the rare case of wrap-around, ULONG_MAX will be returned. ULONG_MAX + * will also be returned if index == ULONG_MAX and there is a gap at the + * index. We can not wrap-around if passed index == ULONG_MAX. */ pgoff_t page_cache_prev_miss(struct address_space *mapping, pgoff_t index, unsigned long max_scan) @@ -1774,12 +1779,13 @@ pgoff_t page_cache_prev_miss(struct address_space *mapping, while (max_scan--) { void *entry = xas_prev(&xas); if (!entry || xa_is_value(entry)) - break; - if (xas.xa_index == ULONG_MAX) - break; + return xas.xa_index; + if (xas.xa_index == ULONG_MAX && index != ULONG_MAX) + return xas.xa_index; } - return xas.xa_index; + /* No gaps in range and no wrap-around, return index beyond range */ + return xas.xa_index - 1; } EXPORT_SYMBOL(page_cache_prev_miss); diff --git a/mm/gup_test.c b/mm/gup_test.c index 26f45fe45c48..eeb3f4d87c51 100644 --- a/mm/gup_test.c +++ b/mm/gup_test.c @@ -380,6 +380,7 @@ static int gup_test_release(struct inode *inode, struct file *file) static const struct file_operations gup_test_fops = { .open = nonseekable_open, .unlocked_ioctl = gup_test_ioctl, + .compat_ioctl = compat_ptr_ioctl, .release = gup_test_release, }; diff --git a/mm/khugepaged.c b/mm/khugepaged.c index 87e962c79a52..5ef1e08b2a06 100644 --- a/mm/khugepaged.c +++ b/mm/khugepaged.c @@ -2089,7 +2089,6 @@ static int collapse_file(struct mm_struct *mm, unsigned long addr, TTU_IGNORE_MLOCK | TTU_BATCH_FLUSH); xas_lock_irq(&xas); - xas_set(&xas, index); VM_BUG_ON_PAGE(page != xas_load(&xas), page); diff --git a/mm/memfd.c b/mm/memfd.c index 69b90c31d38c..e763e76f1106 100644 --- a/mm/memfd.c +++ b/mm/memfd.c @@ -371,12 +371,15 @@ SYSCALL_DEFINE2(memfd_create, inode->i_mode &= ~0111; file_seals = memfd_file_seals_ptr(file); - *file_seals &= ~F_SEAL_SEAL; - *file_seals |= F_SEAL_EXEC; + if (file_seals) { + *file_seals &= ~F_SEAL_SEAL; + *file_seals |= F_SEAL_EXEC; + } } else if (flags & MFD_ALLOW_SEALING) { /* MFD_EXEC and MFD_ALLOW_SEALING are set */ file_seals = memfd_file_seals_ptr(file); - *file_seals &= ~F_SEAL_SEAL; + if (file_seals) + *file_seals &= ~F_SEAL_SEAL; } fd_install(fd, file); diff --git a/mm/mprotect.c b/mm/mprotect.c index 327a6eb90afb..6f658d483704 100644 --- a/mm/mprotect.c +++ b/mm/mprotect.c @@ -824,7 +824,7 @@ static int do_mprotect_pkey(unsigned long start, size_t len, } tlb_finish_mmu(&tlb); - if (!error && vma_iter_end(&vmi) < end) + if (!error && tmp < end) error = -ENOMEM; out: diff --git a/mm/shrinker_debug.c b/mm/shrinker_debug.c index fe10436d9911..3ab53fad8876 100644 --- a/mm/shrinker_debug.c +++ b/mm/shrinker_debug.c @@ -5,12 +5,10 @@ #include <linux/seq_file.h> #include <linux/shrinker.h> #include <linux/memcontrol.h> -#include <linux/srcu.h> /* defined in vmscan.c */ -extern struct mutex shrinker_mutex; +extern struct rw_semaphore shrinker_rwsem; extern struct list_head shrinker_list; -extern struct srcu_struct shrinker_srcu; static DEFINE_IDA(shrinker_debugfs_ida); static struct dentry *shrinker_debugfs_root; @@ -51,13 +49,18 @@ static int shrinker_debugfs_count_show(struct seq_file *m, void *v) struct mem_cgroup *memcg; unsigned long total; bool memcg_aware; - int ret = 0, nid, srcu_idx; + int ret, nid; count_per_node = kcalloc(nr_node_ids, sizeof(unsigned long), GFP_KERNEL); if (!count_per_node) return -ENOMEM; - srcu_idx = srcu_read_lock(&shrinker_srcu); + ret = down_read_killable(&shrinker_rwsem); + if (ret) { + kfree(count_per_node); + return ret; + } + rcu_read_lock(); memcg_aware = shrinker->flags & SHRINKER_MEMCG_AWARE; @@ -88,7 +91,8 @@ static int shrinker_debugfs_count_show(struct seq_file *m, void *v) } } while ((memcg = mem_cgroup_iter(NULL, memcg, NULL)) != NULL); - srcu_read_unlock(&shrinker_srcu, srcu_idx); + rcu_read_unlock(); + up_read(&shrinker_rwsem); kfree(count_per_node); return ret; @@ -111,8 +115,9 @@ static ssize_t shrinker_debugfs_scan_write(struct file *file, .gfp_mask = GFP_KERNEL, }; struct mem_cgroup *memcg = NULL; - int nid, srcu_idx; + int nid; char kbuf[72]; + ssize_t ret; read_len = size < (sizeof(kbuf) - 1) ? size : (sizeof(kbuf) - 1); if (copy_from_user(kbuf, buf, read_len)) @@ -141,7 +146,11 @@ static ssize_t shrinker_debugfs_scan_write(struct file *file, return -EINVAL; } - srcu_idx = srcu_read_lock(&shrinker_srcu); + ret = down_read_killable(&shrinker_rwsem); + if (ret) { + mem_cgroup_put(memcg); + return ret; + } sc.nid = nid; sc.memcg = memcg; @@ -150,7 +159,7 @@ static ssize_t shrinker_debugfs_scan_write(struct file *file, shrinker->scan_objects(shrinker, &sc); - srcu_read_unlock(&shrinker_srcu, srcu_idx); + up_read(&shrinker_rwsem); mem_cgroup_put(memcg); return size; @@ -168,7 +177,7 @@ int shrinker_debugfs_add(struct shrinker *shrinker) char buf[128]; int id; - lockdep_assert_held(&shrinker_mutex); + lockdep_assert_held(&shrinker_rwsem); /* debugfs isn't initialized yet, add debugfs entries later. */ if (!shrinker_debugfs_root) @@ -211,7 +220,7 @@ int shrinker_debugfs_rename(struct shrinker *shrinker, const char *fmt, ...) if (!new) return -ENOMEM; - mutex_lock(&shrinker_mutex); + down_write(&shrinker_rwsem); old = shrinker->name; shrinker->name = new; @@ -229,7 +238,7 @@ int shrinker_debugfs_rename(struct shrinker *shrinker, const char *fmt, ...) shrinker->debugfs_entry = entry; } - mutex_unlock(&shrinker_mutex); + up_write(&shrinker_rwsem); kfree_const(old); @@ -242,7 +251,7 @@ struct dentry *shrinker_debugfs_detach(struct shrinker *shrinker, { struct dentry *entry = shrinker->debugfs_entry; - lockdep_assert_held(&shrinker_mutex); + lockdep_assert_held(&shrinker_rwsem); kfree_const(shrinker->name); shrinker->name = NULL; @@ -271,14 +280,14 @@ static int __init shrinker_debugfs_init(void) shrinker_debugfs_root = dentry; /* Create debugfs entries for shrinkers registered at boot */ - mutex_lock(&shrinker_mutex); + down_write(&shrinker_rwsem); list_for_each_entry(shrinker, &shrinker_list, list) if (!shrinker->debugfs_entry) { ret = shrinker_debugfs_add(shrinker); if (ret) break; } - mutex_unlock(&shrinker_mutex); + up_write(&shrinker_rwsem); return ret; } diff --git a/mm/vmalloc.c b/mm/vmalloc.c index 5a3bf408251b..93cf99aba335 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -3148,11 +3148,20 @@ static void *__vmalloc_area_node(struct vm_struct *area, gfp_t gfp_mask, * allocation request, free them via vfree() if any. */ if (area->nr_pages != nr_small_pages) { - /* vm_area_alloc_pages() can also fail due to a fatal signal */ - if (!fatal_signal_pending(current)) + /* + * vm_area_alloc_pages() can fail due to insufficient memory but + * also:- + * + * - a pending fatal signal + * - insufficient huge page-order pages + * + * Since we always retry allocations at order-0 in the huge page + * case a warning for either is spurious. + */ + if (!fatal_signal_pending(current) && page_order == 0) warn_alloc(gfp_mask, NULL, - "vmalloc error: size %lu, page order %u, failed to allocate pages", - area->nr_pages * PAGE_SIZE, page_order); + "vmalloc error: size %lu, failed to allocate pages", + area->nr_pages * PAGE_SIZE); goto fail; } diff --git a/mm/vmscan.c b/mm/vmscan.c index e305c11ec8fc..27f90896f789 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -35,7 +35,7 @@ #include <linux/cpuset.h> #include <linux/compaction.h> #include <linux/notifier.h> -#include <linux/mutex.h> +#include <linux/rwsem.h> #include <linux/delay.h> #include <linux/kthread.h> #include <linux/freezer.h> @@ -57,7 +57,6 @@ #include <linux/khugepaged.h> #include <linux/rculist_nulls.h> #include <linux/random.h> -#include <linux/srcu.h> #include <asm/tlbflush.h> #include <asm/div64.h> @@ -190,9 +189,7 @@ struct scan_control { int vm_swappiness = 60; LIST_HEAD(shrinker_list); -DEFINE_MUTEX(shrinker_mutex); -DEFINE_SRCU(shrinker_srcu); -static atomic_t shrinker_srcu_generation = ATOMIC_INIT(0); +DECLARE_RWSEM(shrinker_rwsem); #ifdef CONFIG_MEMCG static int shrinker_nr_max; @@ -211,21 +208,8 @@ static inline int shrinker_defer_size(int nr_items) static struct shrinker_info *shrinker_info_protected(struct mem_cgroup *memcg, int nid) { - return srcu_dereference_check(memcg->nodeinfo[nid]->shrinker_info, - &shrinker_srcu, - lockdep_is_held(&shrinker_mutex)); -} - -static struct shrinker_info *shrinker_info_srcu(struct mem_cgroup *memcg, - int nid) -{ - return srcu_dereference(memcg->nodeinfo[nid]->shrinker_info, - &shrinker_srcu); -} - -static void free_shrinker_info_rcu(struct rcu_head *head) -{ - kvfree(container_of(head, struct shrinker_info, rcu)); + return rcu_dereference_protected(memcg->nodeinfo[nid]->shrinker_info, + lockdep_is_held(&shrinker_rwsem)); } static int expand_one_shrinker_info(struct mem_cgroup *memcg, @@ -266,7 +250,7 @@ static int expand_one_shrinker_info(struct mem_cgroup *memcg, defer_size - old_defer_size); rcu_assign_pointer(pn->shrinker_info, new); - call_srcu(&shrinker_srcu, &old->rcu, free_shrinker_info_rcu); + kvfree_rcu(old, rcu); } return 0; @@ -292,7 +276,7 @@ int alloc_shrinker_info(struct mem_cgroup *memcg) int nid, size, ret = 0; int map_size, defer_size = 0; - mutex_lock(&shrinker_mutex); + down_write(&shrinker_rwsem); map_size = shrinker_map_size(shrinker_nr_max); defer_size = shrinker_defer_size(shrinker_nr_max); size = map_size + defer_size; @@ -308,7 +292,7 @@ int alloc_shrinker_info(struct mem_cgroup *memcg) info->map_nr_max = shrinker_nr_max; rcu_assign_pointer(memcg->nodeinfo[nid]->shrinker_info, info); } - mutex_unlock(&shrinker_mutex); + up_write(&shrinker_rwsem); return ret; } @@ -324,7 +308,7 @@ static int expand_shrinker_info(int new_id) if (!root_mem_cgroup) goto out; - lockdep_assert_held(&shrinker_mutex); + lockdep_assert_held(&shrinker_rwsem); map_size = shrinker_map_size(new_nr_max); defer_size = shrinker_defer_size(new_nr_max); @@ -352,16 +336,15 @@ void set_shrinker_bit(struct mem_cgroup *memcg, int nid, int shrinker_id) { if (shrinker_id >= 0 && memcg && !mem_cgroup_is_root(memcg)) { struct shrinker_info *info; - int srcu_idx; - srcu_idx = srcu_read_lock(&shrinker_srcu); - info = shrinker_info_srcu(memcg, nid); + rcu_read_lock(); + info = rcu_dereference(memcg->nodeinfo[nid]->shrinker_info); if (!WARN_ON_ONCE(shrinker_id >= info->map_nr_max)) { /* Pairs with smp mb in shrink_slab() */ smp_mb__before_atomic(); set_bit(shrinker_id, info->map); } - srcu_read_unlock(&shrinker_srcu, srcu_idx); + rcu_read_unlock(); } } @@ -374,7 +357,8 @@ static int prealloc_memcg_shrinker(struct shrinker *shrinker) if (mem_cgroup_disabled()) return -ENOSYS; - mutex_lock(&shrinker_mutex); + down_write(&shrinker_rwsem); + /* This may call shrinker, so it must use down_read_trylock() */ id = idr_alloc(&shrinker_idr, shrinker, 0, 0, GFP_KERNEL); if (id < 0) goto unlock; @@ -388,7 +372,7 @@ static int prealloc_memcg_shrinker(struct shrinker *shrinker) shrinker->id = id; ret = 0; unlock: - mutex_unlock(&shrinker_mutex); + up_write(&shrinker_rwsem); return ret; } @@ -398,7 +382,7 @@ static void unregister_memcg_shrinker(struct shrinker *shrinker) BUG_ON(id < 0); - lockdep_assert_held(&shrinker_mutex); + lockdep_assert_held(&shrinker_rwsem); idr_remove(&shrinker_idr, id); } @@ -408,7 +392,7 @@ static long xchg_nr_deferred_memcg(int nid, struct shrinker *shrinker, { struct shrinker_info *info; - info = shrinker_info_srcu(memcg, nid); + info = shrinker_info_protected(memcg, nid); return atomic_long_xchg(&info->nr_deferred[shrinker->id], 0); } @@ -417,7 +401,7 @@ static long add_nr_deferred_memcg(long nr, int nid, struct shrinker *shrinker, { struct shrinker_info *info; - info = shrinker_info_srcu(memcg, nid); + info = shrinker_info_protected(memcg, nid); return atomic_long_add_return(nr, &info->nr_deferred[shrinker->id]); } @@ -433,7 +417,7 @@ void reparent_shrinker_deferred(struct mem_cgroup *memcg) parent = root_mem_cgroup; /* Prevent from concurrent shrinker_info expand */ - mutex_lock(&shrinker_mutex); + down_read(&shrinker_rwsem); for_each_node(nid) { child_info = shrinker_info_protected(memcg, nid); parent_info = shrinker_info_protected(parent, nid); @@ -442,7 +426,7 @@ void reparent_shrinker_deferred(struct mem_cgroup *memcg) atomic_long_add(nr, &parent_info->nr_deferred[i]); } } - mutex_unlock(&shrinker_mutex); + up_read(&shrinker_rwsem); } static bool cgroup_reclaim(struct scan_control *sc) @@ -743,9 +727,9 @@ void free_prealloced_shrinker(struct shrinker *shrinker) shrinker->name = NULL; #endif if (shrinker->flags & SHRINKER_MEMCG_AWARE) { - mutex_lock(&shrinker_mutex); + down_write(&shrinker_rwsem); unregister_memcg_shrinker(shrinker); - mutex_unlock(&shrinker_mutex); + up_write(&shrinker_rwsem); return; } @@ -755,11 +739,11 @@ void free_prealloced_shrinker(struct shrinker *shrinker) void register_shrinker_prepared(struct shrinker *shrinker) { - mutex_lock(&shrinker_mutex); - list_add_tail_rcu(&shrinker->list, &shrinker_list); + down_write(&shrinker_rwsem); + list_add_tail(&shrinker->list, &shrinker_list); shrinker->flags |= SHRINKER_REGISTERED; shrinker_debugfs_add(shrinker); - mutex_unlock(&shrinker_mutex); + up_write(&shrinker_rwsem); } static int __register_shrinker(struct shrinker *shrinker) @@ -810,16 +794,13 @@ void unregister_shrinker(struct shrinker *shrinker) if (!(shrinker->flags & SHRINKER_REGISTERED)) return; - mutex_lock(&shrinker_mutex); - list_del_rcu(&shrinker->list); + down_write(&shrinker_rwsem); + list_del(&shrinker->list); shrinker->flags &= ~SHRINKER_REGISTERED; if (shrinker->flags & SHRINKER_MEMCG_AWARE) unregister_memcg_shrinker(shrinker); debugfs_entry = shrinker_debugfs_detach(shrinker, &debugfs_id); - mutex_unlock(&shrinker_mutex); - - atomic_inc(&shrinker_srcu_generation); - synchronize_srcu(&shrinker_srcu); + up_write(&shrinker_rwsem); shrinker_debugfs_remove(debugfs_entry, debugfs_id); @@ -831,13 +812,15 @@ EXPORT_SYMBOL(unregister_shrinker); /** * synchronize_shrinkers - Wait for all running shrinkers to complete. * - * This is useful to guarantee that all shrinker invocations have seen an - * update, before freeing memory. + * This is equivalent to calling unregister_shrink() and register_shrinker(), + * but atomically and with less overhead. This is useful to guarantee that all + * shrinker invocations have seen an update, before freeing memory, similar to + * rcu. */ void synchronize_shrinkers(void) { - atomic_inc(&shrinker_srcu_generation); - synchronize_srcu(&shrinker_srcu); + down_write(&shrinker_rwsem); + up_write(&shrinker_rwsem); } EXPORT_SYMBOL(synchronize_shrinkers); @@ -946,20 +929,19 @@ static unsigned long shrink_slab_memcg(gfp_t gfp_mask, int nid, { struct shrinker_info *info; unsigned long ret, freed = 0; - int srcu_idx, generation; - int i = 0; + int i; if (!mem_cgroup_online(memcg)) return 0; -again: - srcu_idx = srcu_read_lock(&shrinker_srcu); - info = shrinker_info_srcu(memcg, nid); + if (!down_read_trylock(&shrinker_rwsem)) + return 0; + + info = shrinker_info_protected(memcg, nid); if (unlikely(!info)) goto unlock; - generation = atomic_read(&shrinker_srcu_generation); - for_each_set_bit_from(i, info->map, info->map_nr_max) { + for_each_set_bit(i, info->map, info->map_nr_max) { struct shrink_control sc = { .gfp_mask = gfp_mask, .nid = nid, @@ -1005,14 +987,14 @@ again: set_shrinker_bit(memcg, nid, i); } freed += ret; - if (atomic_read(&shrinker_srcu_generation) != generation) { - srcu_read_unlock(&shrinker_srcu, srcu_idx); - i++; - goto again; + + if (rwsem_is_contended(&shrinker_rwsem)) { + freed = freed ? : 1; + break; } } unlock: - srcu_read_unlock(&shrinker_srcu, srcu_idx); + up_read(&shrinker_rwsem); return freed; } #else /* CONFIG_MEMCG */ @@ -1049,7 +1031,6 @@ static unsigned long shrink_slab(gfp_t gfp_mask, int nid, { unsigned long ret, freed = 0; struct shrinker *shrinker; - int srcu_idx, generation; /* * The root memcg might be allocated even though memcg is disabled @@ -1061,11 +1042,10 @@ static unsigned long shrink_slab(gfp_t gfp_mask, int nid, if (!mem_cgroup_disabled() && !mem_cgroup_is_root(memcg)) return shrink_slab_memcg(gfp_mask, nid, memcg, priority); - srcu_idx = srcu_read_lock(&shrinker_srcu); + if (!down_read_trylock(&shrinker_rwsem)) + goto out; - generation = atomic_read(&shrinker_srcu_generation); - list_for_each_entry_srcu(shrinker, &shrinker_list, list, - srcu_read_lock_held(&shrinker_srcu)) { + list_for_each_entry(shrinker, &shrinker_list, list) { struct shrink_control sc = { .gfp_mask = gfp_mask, .nid = nid, @@ -1076,14 +1056,19 @@ static unsigned long shrink_slab(gfp_t gfp_mask, int nid, if (ret == SHRINK_EMPTY) ret = 0; freed += ret; - - if (atomic_read(&shrinker_srcu_generation) != generation) { + /* + * Bail out if someone want to register a new shrinker to + * prevent the registration from being stalled for long periods + * by parallel ongoing shrinking. + */ + if (rwsem_is_contended(&shrinker_rwsem)) { freed = freed ? : 1; break; } } - srcu_read_unlock(&shrinker_srcu, srcu_idx); + up_read(&shrinker_rwsem); +out: cond_resched(); return freed; } @@ -4774,10 +4759,11 @@ static void lru_gen_rotate_memcg(struct lruvec *lruvec, int op) { int seg; int old, new; + unsigned long flags; int bin = get_random_u32_below(MEMCG_NR_BINS); struct pglist_data *pgdat = lruvec_pgdat(lruvec); - spin_lock(&pgdat->memcg_lru.lock); + spin_lock_irqsave(&pgdat->memcg_lru.lock, flags); VM_WARN_ON_ONCE(hlist_nulls_unhashed(&lruvec->lrugen.list)); @@ -4812,7 +4798,7 @@ static void lru_gen_rotate_memcg(struct lruvec *lruvec, int op) if (!pgdat->memcg_lru.nr_memcgs[old] && old == get_memcg_gen(pgdat->memcg_lru.seq)) WRITE_ONCE(pgdat->memcg_lru.seq, pgdat->memcg_lru.seq + 1); - spin_unlock(&pgdat->memcg_lru.lock); + spin_unlock_irqrestore(&pgdat->memcg_lru.lock, flags); } void lru_gen_online_memcg(struct mem_cgroup *memcg) @@ -4825,7 +4811,7 @@ void lru_gen_online_memcg(struct mem_cgroup *memcg) struct pglist_data *pgdat = NODE_DATA(nid); struct lruvec *lruvec = get_lruvec(memcg, nid); - spin_lock(&pgdat->memcg_lru.lock); + spin_lock_irq(&pgdat->memcg_lru.lock); VM_WARN_ON_ONCE(!hlist_nulls_unhashed(&lruvec->lrugen.list)); @@ -4836,7 +4822,7 @@ void lru_gen_online_memcg(struct mem_cgroup *memcg) lruvec->lrugen.gen = gen; - spin_unlock(&pgdat->memcg_lru.lock); + spin_unlock_irq(&pgdat->memcg_lru.lock); } } @@ -4860,7 +4846,7 @@ void lru_gen_release_memcg(struct mem_cgroup *memcg) struct pglist_data *pgdat = NODE_DATA(nid); struct lruvec *lruvec = get_lruvec(memcg, nid); - spin_lock(&pgdat->memcg_lru.lock); + spin_lock_irq(&pgdat->memcg_lru.lock); VM_WARN_ON_ONCE(hlist_nulls_unhashed(&lruvec->lrugen.list)); @@ -4872,7 +4858,7 @@ void lru_gen_release_memcg(struct mem_cgroup *memcg) if (!pgdat->memcg_lru.nr_memcgs[gen] && gen == get_memcg_gen(pgdat->memcg_lru.seq)) WRITE_ONCE(pgdat->memcg_lru.seq, pgdat->memcg_lru.seq + 1); - spin_unlock(&pgdat->memcg_lru.lock); + spin_unlock_irq(&pgdat->memcg_lru.lock); } } diff --git a/mm/zswap.c b/mm/zswap.c index c122f042a49d..87b204233115 100644 --- a/mm/zswap.c +++ b/mm/zswap.c @@ -1229,9 +1229,16 @@ static int zswap_frontswap_store(unsigned type, pgoff_t offset, goto reject; } + /* + * XXX: zswap reclaim does not work with cgroups yet. Without a + * cgroup-aware entry LRU, we will push out entries system-wide based on + * local cgroup limits. + */ objcg = get_obj_cgroup_from_page(page); - if (objcg && !obj_cgroup_may_zswap(objcg)) - goto shrink; + if (objcg && !obj_cgroup_may_zswap(objcg)) { + ret = -ENOMEM; + goto reject; + } /* reclaim space if needed */ if (zswap_is_full()) { diff --git a/scripts/gdb/linux/constants.py.in b/scripts/gdb/linux/constants.py.in index 471300ba176c..50a92c4e9984 100644 --- a/scripts/gdb/linux/constants.py.in +++ b/scripts/gdb/linux/constants.py.in @@ -48,12 +48,12 @@ if IS_BUILTIN(CONFIG_COMMON_CLK): LX_GDBPARSED(CLK_GET_RATE_NOCACHE) /* linux/fs.h */ -LX_VALUE(SB_RDONLY) -LX_VALUE(SB_SYNCHRONOUS) -LX_VALUE(SB_MANDLOCK) -LX_VALUE(SB_DIRSYNC) -LX_VALUE(SB_NOATIME) -LX_VALUE(SB_NODIRATIME) +LX_GDBPARSED(SB_RDONLY) +LX_GDBPARSED(SB_SYNCHRONOUS) +LX_GDBPARSED(SB_MANDLOCK) +LX_GDBPARSED(SB_DIRSYNC) +LX_GDBPARSED(SB_NOATIME) +LX_GDBPARSED(SB_NODIRATIME) /* linux/htimer.h */ LX_GDBPARSED(hrtimer_resolution) diff --git a/scripts/gfp-translate b/scripts/gfp-translate index b2ce416d944b..6c9aed17cf56 100755 --- a/scripts/gfp-translate +++ b/scripts/gfp-translate @@ -63,11 +63,11 @@ fi # Extract GFP flags from the kernel source TMPFILE=`mktemp -t gfptranslate-XXXXXX` || exit 1 -grep -q ___GFP $SOURCE/include/linux/gfp.h +grep -q ___GFP $SOURCE/include/linux/gfp_types.h if [ $? -eq 0 ]; then - grep "^#define ___GFP" $SOURCE/include/linux/gfp.h | sed -e 's/u$//' | grep -v GFP_BITS > $TMPFILE + grep "^#define ___GFP" $SOURCE/include/linux/gfp_types.h | sed -e 's/u$//' | grep -v GFP_BITS > $TMPFILE else - grep "^#define __GFP" $SOURCE/include/linux/gfp.h | sed -e 's/(__force gfp_t)//' | sed -e 's/u)/)/' | grep -v GFP_BITS | sed -e 's/)\//) \//' > $TMPFILE + grep "^#define __GFP" $SOURCE/include/linux/gfp_types.h | sed -e 's/(__force gfp_t)//' | sed -e 's/u)/)/' | grep -v GFP_BITS | sed -e 's/)\//) \//' > $TMPFILE fi # Parse the flags diff --git a/tools/testing/radix-tree/Makefile b/tools/testing/radix-tree/Makefile index caf32a9b9608..7527f738b4a1 100644 --- a/tools/testing/radix-tree/Makefile +++ b/tools/testing/radix-tree/Makefile @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 -CFLAGS += -I. -I../../include -g -Og -Wall -D_LGPL_SOURCE -fsanitize=address \ - -fsanitize=undefined +CFLAGS += -I. -I../../include -I../../../lib -g -Og -Wall \ + -D_LGPL_SOURCE -fsanitize=address -fsanitize=undefined LDFLAGS += -fsanitize=address -fsanitize=undefined LDLIBS+= -lpthread -lurcu TARGETS = main idr-test multiorder xarray maple @@ -49,6 +49,7 @@ $(OFILES): Makefile *.h */*.h generated/map-shift.h generated/bit-length.h \ ../../../include/linux/xarray.h \ ../../../include/linux/maple_tree.h \ ../../../include/linux/radix-tree.h \ + ../../../lib/radix-tree.h \ ../../../include/linux/idr.h radix-tree.c: ../../../lib/radix-tree.c diff --git a/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-synthetic-event-stack-legacy.tc b/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-synthetic-event-stack-legacy.tc new file mode 100644 index 000000000000..d0cd91a93069 --- /dev/null +++ b/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-synthetic-event-stack-legacy.tc @@ -0,0 +1,24 @@ +#!/bin/sh +# SPDX-License-Identifier: GPL-2.0 +# description: event trigger - test inter-event histogram trigger trace action with dynamic string param (legacy stack) +# requires: set_event synthetic_events events/sched/sched_process_exec/hist "long[] stack' >> synthetic_events":README + +fail() { #msg + echo $1 + exit_fail +} + +echo "Test create synthetic event with stack" + +# Test the old stacktrace keyword (for backward compatibility) +echo 's:wake_lat pid_t pid; u64 delta; unsigned long[] stack;' > dynamic_events +echo 'hist:keys=next_pid:ts=common_timestamp.usecs,st=stacktrace if prev_state == 1||prev_state == 2' >> events/sched/sched_switch/trigger +echo 'hist:keys=prev_pid:delta=common_timestamp.usecs-$ts,s=$st:onmax($delta).trace(wake_lat,prev_pid,$delta,$s)' >> events/sched/sched_switch/trigger +echo 1 > events/synthetic/wake_lat/enable +sleep 1 + +if ! grep -q "=>.*sched" trace; then + fail "Failed to create synthetic event with stack" +fi + +exit 0 diff --git a/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-synthetic-event-stack.tc b/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-synthetic-event-stack.tc index 755dbe94ccf4..8f1cc9a86a06 100644 --- a/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-synthetic-event-stack.tc +++ b/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-synthetic-event-stack.tc @@ -1,7 +1,7 @@ #!/bin/sh # SPDX-License-Identifier: GPL-2.0 # description: event trigger - test inter-event histogram trigger trace action with dynamic string param -# requires: set_event synthetic_events events/sched/sched_process_exec/hist "long[]' >> synthetic_events":README +# requires: set_event synthetic_events events/sched/sched_process_exec/hist "can be any field, or the special string 'common_stacktrace'":README fail() { #msg echo $1 @@ -10,9 +10,8 @@ fail() { #msg echo "Test create synthetic event with stack" - echo 's:wake_lat pid_t pid; u64 delta; unsigned long[] stack;' > dynamic_events -echo 'hist:keys=next_pid:ts=common_timestamp.usecs,st=stacktrace if prev_state == 1||prev_state == 2' >> events/sched/sched_switch/trigger +echo 'hist:keys=next_pid:ts=common_timestamp.usecs,st=common_stacktrace if prev_state == 1||prev_state == 2' >> events/sched/sched_switch/trigger echo 'hist:keys=prev_pid:delta=common_timestamp.usecs-$ts,s=$st:onmax($delta).trace(wake_lat,prev_pid,$delta,$s)' >> events/sched/sched_switch/trigger echo 1 > events/synthetic/wake_lat/enable sleep 1 diff --git a/tools/testing/selftests/mm/Makefile b/tools/testing/selftests/mm/Makefile index e6cd60ca9e48..66d7c07dc177 100644 --- a/tools/testing/selftests/mm/Makefile +++ b/tools/testing/selftests/mm/Makefile @@ -5,12 +5,15 @@ LOCAL_HDRS += $(selfdir)/mm/local_config.h $(top_srcdir)/mm/gup_test.h include local_config.mk +ifeq ($(ARCH),) + ifeq ($(CROSS_COMPILE),) uname_M := $(shell uname -m 2>/dev/null || echo not) else uname_M := $(shell echo $(CROSS_COMPILE) | grep -o '^[a-z0-9]\+') endif -MACHINE ?= $(shell echo $(uname_M) | sed -e 's/aarch64.*/arm64/' -e 's/ppc64.*/ppc64/') +ARCH ?= $(shell echo $(uname_M) | sed -e 's/aarch64.*/arm64/' -e 's/ppc64.*/ppc64/') +endif # Without this, failed build products remain, with up-to-date timestamps, # thus tricking Make (and you!) into believing that All Is Well, in subsequent @@ -66,7 +69,7 @@ TEST_GEN_PROGS += ksm_tests TEST_GEN_PROGS += ksm_functional_tests TEST_GEN_PROGS += mdwe_test -ifeq ($(MACHINE),x86_64) +ifeq ($(ARCH),x86_64) CAN_BUILD_I386 := $(shell ./../x86/check_cc.sh "$(CC)" ../x86/trivial_32bit_program.c -m32) CAN_BUILD_X86_64 := $(shell ./../x86/check_cc.sh "$(CC)" ../x86/trivial_64bit_program.c) CAN_BUILD_WITH_NOPIE := $(shell ./../x86/check_cc.sh "$(CC)" ../x86/trivial_program.c -no-pie) @@ -88,13 +91,13 @@ TEST_GEN_PROGS += $(BINARIES_64) endif else -ifneq (,$(findstring $(MACHINE),ppc64)) +ifneq (,$(findstring $(ARCH),ppc64)) TEST_GEN_PROGS += protection_keys endif endif -ifneq (,$(filter $(MACHINE),arm64 ia64 mips64 parisc64 ppc64 riscv64 s390x sparc64 x86_64)) +ifneq (,$(filter $(ARCH),arm64 ia64 mips64 parisc64 ppc64 riscv64 s390x sparc64 x86_64)) TEST_GEN_PROGS += va_high_addr_switch TEST_GEN_PROGS += virtual_address_range TEST_GEN_PROGS += write_to_hugetlbfs @@ -113,7 +116,7 @@ $(TEST_GEN_PROGS): vm_util.c $(OUTPUT)/uffd-stress: uffd-common.c $(OUTPUT)/uffd-unit-tests: uffd-common.c -ifeq ($(MACHINE),x86_64) +ifeq ($(ARCH),x86_64) BINARIES_32 := $(patsubst %,$(OUTPUT)/%,$(BINARIES_32)) BINARIES_64 := $(patsubst %,$(OUTPUT)/%,$(BINARIES_64)) |