diff options
| author | Richard Henderson <richard.henderson@linaro.org> | 2023-04-22 06:10:51 +0100 |
|---|---|---|
| committer | Richard Henderson <richard.henderson@linaro.org> | 2023-04-22 06:10:51 +0100 |
| commit | 1cc6e1a20144c0ae360cbeb0e035fdee1bd80609 (patch) | |
| tree | f2e873608f5e982206b52d4a3c8d6d0644abc56c /docs | |
| parent | 45608654aa63ca2b311d6cb761e1522f2128e00e (diff) | |
| parent | 5f9efbbcf6fc77e583254389124437d981ad76b9 (diff) | |
Merge tag 'for-upstream' of https://gitlab.com/bonzini/qemu into staging
* Optional use of Meson wrap for slirp
* Coverity fixes
* Avoid -Werror=maybe-uninitialized
* Mark coroutine QMP command functions as coroutine_fn
* Mark functions that suspend as coroutine_mixed_fn
* target/i386: Fix SGX CPUID leaf
* First batch of qatomic_mb_read() removal
* Small atomic.rst improvement
* NBD cleanup
* Update libvirt-ci submodule
# -----BEGIN PGP SIGNATURE-----
#
# iQFIBAABCAAyFiEE8TM4V0tmI4mGbHaCv/vSX3jHroMFAmRBAzwUHHBib256aW5p
# QHJlZGhhdC5jb20ACgkQv/vSX3jHroP64gf+NzLW95tylCfhKuuLq/TjuOTQqHCD
# KVLlA1I3pwJfk4SUuigrnaJtwfa/tBiWxfaivUdPAzPzeXyxcVSOps0neohrmFBh
# 2e3ylBWWz22K0gkLtrFwJT99TVy6w6Xhj9SX8HPRfxl4k8yMPrUJNW78hh6APAwq
# /etZY6+ieHC7cwG4xluhxsHnxnBYBYD+18hUd+b5LchD/yvCSCNNiursutpa0Ar/
# r/HtDwNFKlaApO3sU4R3yYgdS1Fvcas4tDZaumADsQlSG5z+UeJldc98LiRlFrAA
# gnskBSaaly/NgWqY3hVCYaBGyjD4lWPkX/FEChi0XX6Fl1P0umQAv/7z3w==
# =XSAs
# -----END PGP SIGNATURE-----
# gpg: Signature made Thu 20 Apr 2023 10:17:48 AM BST
# gpg: using RSA key F13338574B662389866C7682BFFBD25F78C7AE83
# gpg: issuer "pbonzini@redhat.com"
# gpg: Good signature from "Paolo Bonzini <bonzini@gnu.org>" [undefined]
# gpg: aka "Paolo Bonzini <pbonzini@redhat.com>" [undefined]
# gpg: WARNING: This key is not certified with a trusted signature!
# gpg: There is no indication that the signature belongs to the owner.
# Primary key fingerprint: 46F5 9FBD 57D6 12E7 BFD4 E2F7 7E15 100C CD36 69B1
# Subkey fingerprint: F133 3857 4B66 2389 866C 7682 BFFB D25F 78C7 AE83
* tag 'for-upstream' of https://gitlab.com/bonzini/qemu: (25 commits)
tests: lcitool: Switch to OpenSUSE Leap 15.4
tests: libvirt-ci: Update to commit '2fa24dce8bc'
configure: Honour cross-prefix when finding ObjC compiler
coverity: unify Fedora dockerfiles
nbd: a BlockExport always has a BlockBackend
docs: explain effect of smp_read_barrier_depends() on modern architectures
qemu-coroutine: remove qatomic_mb_read()
postcopy-ram: do not use qatomic_mb_read
block-backend: remove qatomic_mb_read()
target/i386: Change wrong XFRM value in SGX CPUID leaf
monitor: mark mixed functions that can suspend
migration: mark mixed functions that can suspend
io: mark mixed functions that can suspend
qapi-gen: mark coroutine QMP command functions as coroutine_fn
target/mips: tcg: detect out-of-bounds accesses to cpu_gpr and cpu_gpr_hi
coverity: update COMPONENTS.md
lasi: fix RTC migration
target/i386: Avoid unreachable variable declaration in mmu_translate()
configure: Avoid -Werror=maybe-uninitialized
tests: bios-tables-test: replace memset with initializer
...
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Diffstat (limited to 'docs')
| -rw-r--r-- | docs/devel/atomics.rst | 11 |
1 files changed, 7 insertions, 4 deletions
diff --git a/docs/devel/atomics.rst b/docs/devel/atomics.rst index 81ec26be17..248076375b 100644 --- a/docs/devel/atomics.rst +++ b/docs/devel/atomics.rst @@ -220,10 +220,9 @@ They come in six kinds: retrieves the address to which the second load will be directed), the processor will guarantee that the first LOAD will appear to happen before the second with respect to the other components of the system. - However, this is not always true---for example, it was not true on - Alpha processors. Whenever this kind of access happens to shared - memory (that is not protected by a lock), a read barrier is needed, - and ``smp_read_barrier_depends()`` can be used instead of ``smp_rmb()``. + Therefore, unlike ``smp_rmb()`` or ``qatomic_load_acquire()``, + ``smp_read_barrier_depends()`` can be just a compiler barrier on + weakly-ordered architectures such as Arm or PPC[#]_. Note that the first load really has to have a _data_ dependency and not a control dependency. If the address for the second load is dependent @@ -231,6 +230,10 @@ They come in six kinds: than actually loading the address itself, then it's a _control_ dependency and a full read barrier or better is required. +.. [#] The DEC Alpha is an exception, because ``smp_read_barrier_depends()`` + needs a processor barrier. On strongly-ordered architectures such + as x86 or s390, ``smp_rmb()`` and ``qatomic_load_acquire()`` can + also be compiler barriers only. Memory barriers and ``qatomic_load_acquire``/``qatomic_store_release`` are mostly used when a data structure has one thread that is always a writer |