linux.git/include/linux, branch bh1745

cpumask: be more careful with 'cpumask_setall()'

2023-03-07T20:16:18+00:00

Commit 596ff4a09b89 ("cpumask: re-introduce constant-sized cpumask optimizations") changed cpumask_setall() to use "bitmap_set()" instead of "bitmap_fill()", because bitmap_fill() would explicitly set all the bits of a constant sized small bitmap, and that's exactly what we don't want: we want to only set bits up to 'nr_cpu_ids', which is what "bitmap_set()" does. However, Yury correctly points out that while "bitmap_set()" does indeed only set bits up to the required bitmap size, it doesn't _clear_ bits above that size, so the upper bits would still not have well-defined values. Now, none of this should really matter, since any bits set past 'nr_cpu_ids' should always be ignored in the first place. Yes, the bit scanning functions might return them as a result, but since users should always consider the ">= nr_cpu_ids" condition to mean "no more bits", that shouldn't have any actual effect (see previous commit 8ca09d5fa354 "cpumask: fix incorrect cpumask scanning result checks"). But let's just do it right, the way the code was _intended_ to work. We have had enough lazy code that works but bites us in the *rse later (again, see previous commit) that there's no reason to not just do this properly. It turns out that "bitmap_fill()" gets this all right for the complex case, and really only fails for the inlined optimized case that just fills the whole word. And while we could just fix bitmap_fill() to use the proper last word mask, there's two issues with that: - the cpumask case wants to do the _optimization_ based on "NR_CPUS is a small constant", but then wants to do the actual bit _fill_ based on "nr_cpu_ids" that isn't necessarily that same constant - we have lots of non-cpumask users of bitmap_fill(), and while they hopefully don't care, and probably would want the proper semantics anyway ("only set bits up to the limit"), I do not want the cpumask changes to impact other parts So this ends up just doing the single-word optimization by hand in the cpumask code. If our cpumask is fundamentally limited to a single word, just do the proper "fill in that word" exactly. And if it's the more complex multi-word case, then the generic bitmap_fill() will DTRT. This is all an example of how our bitmap function optimizations really are somewhat broken. They conflate the "this is size of the bitmap" optimizations with the actual bit(s) we want to set. In many cases we really want to have the two be separate things: sometimes we base our optimizations on the size of the whole bitmap ("I know this whole bitmap fits in a single word, so I'll just use single-word accesses"), and sometimes we base them on the bit we are looking at ("this is just acting on bits that are in the first word, so I'll use single-word accesses"). Notice how the end result of the two optimizations are the same, but the way we get to them are quite different. And all our cpumask optimization games are really about that fundamental distinction, and we'd often really want to pass in both the "this is the bit I'm working on" (which _can_ be a small constant but might be variable), and "I know it's in this range even if it's variable" (based on CONFIG_NR_CPUS). So this cpumask_setall() implementation just makes that explicit. It checks the "I statically know the size is small" using the known static size of the cpumask (which is what that 'small_cpumask_bits' is all about), but then sets the actual bits using the exact number of cpus we have (ie 'nr_cpumask_bits') Of course, in a perfect world, the compiler would have done all the range analysis (possibly with help from us just telling it that "this value is always in this range"), and would do all of this for us. But that is not the world we live in. While we dream of that perfect world, this does that manual logic to make it all work out. And this was a very long explanation for a small code change that shouldn't even matter. Reported-by: Yury Norov Link: https://lore.kernel.org/lkml/ZAV9nGG9e1%2FrV+L%2F@yury-laptop/ Signed-off-by: Linus Torvalds

cpumask: Fix typo nr_cpumask_size --> nr_cpumask_bits

2023-03-06T18:58:04+00:00

The never used nr_cpumask_size is just a typo, hence use existing redefinition that's called nr_cpumask_bits. Signed-off-by: Andy Shevchenko Signed-off-by: Linus Torvalds

cpumask: re-introduce constant-sized cpumask optimizations

2023-03-05T22:30:34+00:00

Commit aa47a7c215e7 ("lib/cpumask: deprecate nr_cpumask_bits") resulted in the cpumask operations potentially becoming hugely less efficient, because suddenly the cpumask was always considered to be variable-sized. The optimization was then later added back in a limited form by commit 6f9c07be9d02 ("lib/cpumask: add FORCE_NR_CPUS config option"), but that FORCE_NR_CPUS option is not useful in a generic kernel and more of a special case for embedded situations with fixed hardware. Instead, just re-introduce the optimization, with some changes. Instead of depending on CPUMASK_OFFSTACK being false, and then always using the full constant cpumask width, this introduces three different cpumask "sizes": - the exact size (nr_cpumask_bits) remains identical to nr_cpu_ids. This is used for situations where we should use the exact size. - the "small" size (small_cpumask_bits) is the NR_CPUS constant if it fits in a single word and the bitmap operations thus end up able to trigger the "small_const_nbits()" optimizations. This is used for the operations that have optimized single-word cases that get inlined, notably the bit find and scanning functions. - the "large" size (large_cpumask_bits) is the NR_CPUS constant if it is an sufficiently small constant that makes simple "copy" and "clear" operations more efficient. This is arbitrarily set at four words or less. As a an example of this situation, without this fixed size optimization, cpumask_clear() will generate code like movl nr_cpu_ids(%rip), %edx addq $63, %rdx shrq $3, %rdx andl $-8, %edx callq memset@PLT on x86-64, because it would calculate the "exact" number of longwords that need to be cleared. In contrast, with this patch, using a MAX_CPU of 64 (which is quite a reasonable value to use), the above becomes a single movq $0,cpumask instruction instead, because instead of caring to figure out exactly how many CPU's the system has, it just knows that the cpumask will be a single word and can just clear it all. Note that this does end up tightening the rules a bit from the original version in another way: operations that set bits in the cpumask are now limited to the actual nr_cpu_ids limit, whereas we used to do the nr_cpumask_bits thing almost everywhere in the cpumask code. But if you just clear bits, or scan for bits, we can use the simpler compile-time constants. In the process, remove 'cpumask_complement()' and 'for_each_cpu_not()' which were not useful, and which fundamentally have to be limited to 'nr_cpu_ids'. Better remove them now than have somebody introduce use of them later. Of course, on x86-64 with MAXSMP there is no sane small compile-time constant for the cpumask sizes, and we end up using the actual CPU bits, and will generate the above kind of horrors regardless. Please don't use MAXSMP unless you really expect to have machines with thousands of cores. Signed-off-by: Linus Torvalds

Merge tag 'irq-urgent-2023-03-05' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

2023-03-05T19:19:16+00:00

Pull irq updates from Thomas Gleixner: "A set of updates for the interrupt susbsystem: - Prevent possible NULL pointer derefences in irq_data_get_affinity_mask() and irq_domain_create_hierarchy() - Take the per device MSI lock before invoking code which relies on it being hold - Make sure that MSI descriptors are unreferenced before freeing them. This was overlooked when the platform MSI code was converted to use core infrastructure and results in a fals positive warning - Remove dead code in the MSI subsystem - Clarify the documentation for pci_msix_free_irq() - More kobj_type constification" * tag 'irq-urgent-2023-03-05' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: genirq/msi, platform-msi: Ensure that MSI descriptors are unreferenced genirq/msi: Drop dead domain name assignment irqdomain: Add missing NULL pointer check in irq_domain_create_hierarchy() genirq/irqdesc: Make kobj_type structures constant PCI/MSI: Clarify usage of pci_msix_free_irq() genirq/msi: Take the per-device MSI lock before validating the control structure genirq/ipi: Fix NULL pointer deref in irq_data_get_affinity_mask()

Remove Intel compiler support

2023-03-05T18:49:37+00:00

include/linux/compiler-intel.h had no update in the past 3 years. We often forget about the third C compiler to build the kernel. For example, commit a0a12c3ed057 ("asm goto: eradicate CC_HAS_ASM_GOTO") only mentioned GCC and Clang. init/Kconfig defines CC_IS_GCC and CC_IS_CLANG but not CC_IS_ICC, and nobody has reported any issue. I guess the Intel Compiler support is broken, and nobody is caring about it. Harald Arnesen pointed out ICC (classic Intel C/C++ compiler) is deprecated: $ icc -v icc: remark #10441: The Intel(R) C++ Compiler Classic (ICC) is deprecated and will be removed from product release in the second half of 2023. The Intel(R) oneAPI DPC++/C++ Compiler (ICX) is the recommended compiler moving forward. Please transition to use this compiler. Use '-diag-disable=10441' to disable this message. icc version 2021.7.0 (gcc version 12.1.0 compatibility) Arnd Bergmann provided a link to the article, "Intel C/C++ compilers complete adoption of LLVM". lib/zstd/common/compiler.h and lib/zstd/compress/zstd_fast.c were kept untouched for better sync with https://github.com/facebook/zstd Link: https://www.intel.com/content/www/us/en/developer/articles/technical/adoption-of-llvm-complete-icx.html Signed-off-by: Masahiro Yamada Acked-by: Arnd Bergmann Reviewed-by: Nick Desaulniers Reviewed-by: Nathan Chancellor Reviewed-by: Miguel Ojeda Signed-off-by: Linus Torvalds

Merge tag 'mm-hotfixes-stable-2023-03-04-13-12' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm

2023-03-04T21:32:50+00:00

Pull misc fixes from Andrew Morton: "17 hotfixes. Eight are for MM and seven are for other parts of the kernel. Seven are cc:stable and eight address post-6.3 issues or were judged unsuitable for -stable backporting" * tag 'mm-hotfixes-stable-2023-03-04-13-12' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm: mailmap: map Dikshita Agarwal's old address to his current one mailmap: map Vikash Garodia's old address to his current one fs/cramfs/inode.c: initialize file_ra_state fs: hfsplus: fix UAF issue in hfsplus_put_super panic: fix the panic_print NMI backtrace setting lib: parser: update documentation for match_NUMBER functions kasan, x86: don't rename memintrinsics in uninstrumented files kasan: test: fix test for new meminstrinsic instrumentation kasan: treat meminstrinsic as builtins in uninstrumented files kasan: emit different calls for instrumentable memintrinsics ocfs2: fix non-auto defrag path not working issue ocfs2: fix defrag path triggering jbd2 ASSERT mailmap: map Georgi Djakov's old Linaro address to his current one mm/hwpoison: convert TTU_IGNORE_HWPOISON to TTU_HWPOISON lib/zlib: DFLTCC deflate does not write all available bits for Z_NO_FLUSH mm/damon/paddr: fix missing folio_put() mm/mremap: fix dup_anon_vma() in vma_merge() case 4

Merge tag 'io_uring-6.3-2023-03-03' of git://git.kernel.dk/linux

2023-03-03T18:25:29+00:00

Pull more io_uring updates from Jens Axboe: "Here's a set of fixes/changes that didn't make the first cut, either because they got queued before I sent the early merge request, or fixes that came in afterwards. In detail: - Don't set MSG_NOSIGNAL on recv/recvmsg opcodes, as AF_PACKET will error out (David) - Fix for spurious poll wakeups (me) - Fix for a file leak for buffered reads in certain conditions (Joseph) - Don't allow registered buffers of mixed types (Pavel) - Improve handling of huge pages for registered buffers (Pavel) - Provided buffer ring size calculation fix (Wojciech) - Minor cleanups (me)" * tag 'io_uring-6.3-2023-03-03' of git://git.kernel.dk/linux: io_uring/poll: don't pass in wake func to io_init_poll_iocb() io_uring: fix fget leak when fs don't support nowait buffered read io_uring/poll: allow some retries for poll triggering spuriously io_uring: remove MSG_NOSIGNAL from recvmsg io_uring/rsrc: always initialize 'folio' to NULL io_uring/rsrc: optimise registered huge pages io_uring/rsrc: optimise single entry advance io_uring/rsrc: disallow multi-source reg buffers io_uring: remove unused wq_list_merge io_uring: fix size calculation when registering buf ring io_uring/rsrc: fix a comment in io_import_fixed() io_uring: rename 'in_idle' to 'in_cancel' io_uring: consolidate the put_ref-and-return section of adding work

Merge tag 'block-6.3-2023-03-03' of git://git.kernel.dk/linux

2023-03-03T18:21:39+00:00

Pull block fixes from Jens Axboe: - NVMe pull request via Christoph: - Don't access released socket during error recovery (Akinobu Mita) - Bring back auto-removal of deleted namespaces during sequential scan (Christoph Hellwig) - Fix an error code in nvme_auth_process_dhchap_challenge (Dan Carpenter) - Show well known discovery name (Daniel Wagner) - Add a missing endianess conversion in effects masking (Keith Busch) - Fix for a regression introduced in blk-rq-qos during init in this merge window (Breno) - Reorder a few fields in struct blk_mq_tag_set, eliminating a few holes and shrinking it (Christophe) - Remove redundant bdev_get_queue() NULL checks (Juhyung) - Add sed-opal single user mode support flag (Luca) - Remove SQE128 check in ublk as it isn't needed, saving some memory (Ming) - Op specific segment checking for cloned requests (Uday) - Exclusive open partition scan fixes (Yu) - Loop offset/size checking before assigning them in the device (Zhong) - Bio polling fixes (me) * tag 'block-6.3-2023-03-03' of git://git.kernel.dk/linux: blk-mq: enforce op-specific segment limits in blk_insert_cloned_request nvme-fabrics: show well known discovery name nvme-tcp: don't access released socket during error recovery nvme-auth: fix an error code in nvme_auth_process_dhchap_challenge() nvme: bring back auto-removal of deleted namespaces during sequential scan blk-iocost: Pass gendisk to ioc_refresh_params nvme: fix sparse warning on effects masking block: be a bit more careful in checking for NULL bdev while polling block: clear bio->bi_bdev when putting a bio back in the cache loop: loop_set_status_from_info() check before assignment ublk: remove check IO_URING_F_SQE128 in ublk_ch_uring_cmd block: remove more NULL checks after bdev_get_queue() blk-mq: Reorder fields in 'struct blk_mq_tag_set' block: fix scan partition for exclusively open device again block: Revert "block: Do not reread partition table on exclusively open device" sed-opal: add support flag for SUM in status ioctl

Merge tag 'rtc-6.3' of git://git.kernel.org/pub/scm/linux/kernel/git/abelloni/linux

2023-03-03T17:15:50+00:00

Pull RTC updates from Alexandre Belloni: "A few drivers got some nice cleanups and a new driver are making the bulk of the changes. Subsystem: - allow rtc_read_alarm without read_alarm callback New driver: - NXP BBNSM module RTC Drivers: - use IRQ flags from fwnode when available - abx80x: nvmem support - brcmstb-waketimer: add non-wake alarm support - ingenic: provide CLK32K clock - isl12022: cleanups - moxart: switch to using gpiod API - pcf85363: allow setting quartz load - pm8xxx: cleanups and support for setting time - rv3028, rv3032: add ACPI support" * tag 'rtc-6.3' of git://git.kernel.org/pub/scm/linux/kernel/git/abelloni/linux: (64 commits) rtc: pm8xxx: add support for nvmem offset dt-bindings: rtc: qcom-pm8xxx: add nvmem-cell offset rtc: abx80x: Add nvmem support rtc: rx6110: Remove unused of_gpio,h rtc: efi: Avoid spamming the log on RTC read failure rtc: isl12022: sort header inclusion alphabetically rtc: isl12022: Join string literals back rtc: isl12022: Drop unneeded OF guards and of_match_ptr() rtc: isl12022: Explicitly use __le16 type for ISL12022_REG_TEMP_L rtc: isl12022: Get rid of unneeded private struct isl12022 rtc: pcf85363: add support for the quartz-load-femtofarads property dt-bindings: rtc: nxp,pcf8563: move pcf85263/pcf85363 to a dedicated binding rtc: allow rtc_read_alarm without read_alarm callback rtc: rv3032: add ACPI support rtc: rv3028: add ACPI support rtc: bbnsm: Add the bbnsm rtc support rtc: jz4740: Register clock provider for the CLK32K pin rtc: jz4740: Use dev_err_probe() rtc: jz4740: Use readl_poll_timeout dt-bindings: rtc: Add #clock-cells property ...

Merge tag 'objtool-core-2023-03-02' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

2023-03-02T17:45:34+00:00

Pull objtool updates from Ingo Molnar: - Shrink 'struct instruction', to improve objtool performance & memory footprint - Other maximum memory usage reductions - this makes the build both faster, and fixes kernel build OOM failures on allyesconfig and similar configs when they try to build the final (large) vmlinux.o - Fix ORC unwinding when a kprobe (INT3) is set on a stack-modifying single-byte instruction (PUSH/POP or LEAVE). This requires the extension of the ORC metadata structure with a 'signal' field - Misc fixes & cleanups * tag 'objtool-core-2023-03-02' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (22 commits) objtool: Fix ORC 'signal' propagation objtool: Remove instruction::list x86: Fix FILL_RETURN_BUFFER objtool: Fix overlapping alternatives objtool: Union instruction::{call_dest,jump_table} objtool: Remove instruction::reloc objtool: Shrink instruction::{type,visited} objtool: Make instruction::alts a single-linked list objtool: Make instruction::stack_ops a single-linked list objtool: Change arch_decode_instruction() signature x86/entry: Fix unwinding from kprobe on PUSH/POP instruction x86/unwind/orc: Add 'signal' field to ORC metadata objtool: Optimize layout of struct special_alt objtool: Optimize layout of struct symbol objtool: Allocate multiple structures with calloc() objtool: Make struct check_options static objtool: Make struct entries[] static and const objtool: Fix HOSTCC flag usage objtool: Properly support make V=1 objtool: Install libsubcmd in build ...