src/lib/libc/sys/sigfastblock.2, branch stable/13 FreeBSD source tree Canonicalize the name of the FreeBSD Foundation 2025-02-19T19:52:36+00:00 Li-Wen Hsu lwhsu@FreeBSD.org 2024-10-23T21:03:07+00:00 fd3016b17efbfb351c62921e4ec1ac3812baffab Reviewed by: emaste Sponsored by: The FreeBSD Foundation (cherry picked from commit dab59af3bcc7cb7ba01569d3044894b3e860ad56) (cherry picked from commit ef3ed0726f2230e38df76a32a3b9ff145147af65) 
Reviewed by:	emaste
Sponsored by:	The FreeBSD Foundation

(cherry picked from commit dab59af3bcc7cb7ba01569d3044894b3e860ad56)
(cherry picked from commit ef3ed0726f2230e38df76a32a3b9ff145147af65)
sigfastblock.2: Fix a typo in the manual page 2024-01-23T06:45:41+00:00 Gordon Bergling gbe@FreeBSD.org 2024-01-20T18:54:33+00:00 4bd2aee6120edb8979bb57211a06f06406ad6407 - s/successfull/successful/ (cherry picked from commit a70008e95b907336bddbcc2aa9d567df6e3a41b6) 
- s/successfull/successful/

(cherry picked from commit a70008e95b907336bddbcc2aa9d567df6e3a41b6)
Remove $FreeBSD$: two-line nroff pattern 2023-08-23T17:43:31+00:00 Warner Losh imp@FreeBSD.org 2023-08-22T01:32:08+00:00 b144e70a3325e033163aa4e6e15d0446e245702d Remove /^\.\\"\n\.\\"\s*\$FreeBSD\$$\n/ Similar commit in main: (cherry picked from commit fa9896e082a1) 
Remove /^\.\\"\n\.\\"\s*\$FreeBSD\$$\n/

Similar commit in main:
(cherry picked from commit fa9896e082a1)
Add a way to manage thread signal mask using shared word, instead of syscall. 2020-02-09T11:53:12+00:00 Konstantin Belousov kib@FreeBSD.org 2020-02-09T11:53:12+00:00 146fc63fce9b46ab77ba7959cf69429d9bd88d2a A new syscall sigfastblock(2) is added which registers a uint32_t variable as containing the count of blocks for signal delivery. Its content is read by kernel on each syscall entry and on AST processing, non-zero count of blocks is interpreted same as the signal mask blocking all signals. The biggest downside of the feature that I see is that memory corruption that affects the registered fast sigblock location, would cause quite strange application misbehavior. For instance, the process would be immune to ^C (but killable by SIGKILL). With consumers (rtld and libthr added), benchmarks do not show a slow-down of the syscalls in micro-measurements, and macro benchmarks like buildworld do not demonstrate a difference. Part of the reason is that buildworld time is dominated by compiler, and clang already links to libthr. On the other hand, small utilities typically used by shell scripts have the total number of syscalls cut by half. The syscall is not exported from the stable libc version namespace on purpose. It is intended to be used only by our C runtime implementation internals. Tested by: pho Disscussed with: cem, emaste, jilles Sponsored by: The FreeBSD Foundation Differential revision: https://reviews.freebsd.org/D12773 
A new syscall sigfastblock(2) is added which registers a uint32_t
variable as containing the count of blocks for signal delivery.  Its
content is read by kernel on each syscall entry and on AST processing,
non-zero count of blocks is interpreted same as the signal mask
blocking all signals.

The biggest downside of the feature that I see is that memory
corruption that affects the registered fast sigblock location, would
cause quite strange application misbehavior. For instance, the process
would be immune to ^C (but killable by SIGKILL).

With consumers (rtld and libthr added), benchmarks do not show a
slow-down of the syscalls in micro-measurements, and macro benchmarks
like buildworld do not demonstrate a difference. Part of the reason is
that buildworld time is dominated by compiler, and clang already links
to libthr. On the other hand, small utilities typically used by shell
scripts have the total number of syscalls cut by half.

The syscall is not exported from the stable libc version namespace on
purpose.  It is intended to be used only by our C runtime
implementation internals.

Tested by:	pho
Disscussed with:	cem, emaste, jilles
Sponsored by:	The FreeBSD Foundation
Differential revision:	https://reviews.freebsd.org/D12773