Carles Cufi dc006e6b5f arch: arm: cortex-m: Reduce ZLI latency by not disabling them in wrapper ... The difference between __irq_disable() and irq_lock() is that the former essentially translates to `cpsid i`, whereas `irq_lock()` translates to setting BASEPRI (on cores with BASEPRI). This means that using irq_lock() does not disable zero-latency interrupts (ZLIs), which reduces the potential execution latency of ZLIs. In both isr_wrapper and _arch_isr_direct_pm() (which is just really an implementation of ISR_DIRECT_PM()), we were using __irq_disable() to disable all interrups, including ZLIs. But the code executed with interrupts disabled handles waking up from idle, and so must only be protected against regular interrupts being executed, not ZLIs, which should have no effect on the correct execution of the code. Signed-off-by: Carles Cufi <carles.cufi@nordicsemi.no>		2025-06-06 20:11:18 +01:00
..
cortex_a_r	arch: arm: cortex_a_r: use correct name for TLB Conflict Abort	2025-05-31 07:01:36 -04:00
cortex_m	arch: arm: cortex-m: Reduce ZLI latency by not disabling them in wrapper	2025-06-06 20:11:18 +01:00
mmu	arch: arm: Replaced __volatile__ with volatile	2025-03-17 16:24:51 +01:00
mpu	Revert "arch: arm: mpu: fix erratum 1013783-B"	2025-05-31 05:57:18 -04:00
offsets	arch: arm: cortex_m: pm_s2ram: add support for all architectures	2024-11-16 14:00:44 -05:00
__aeabi_atexit.c
CMakeLists.txt
elf.c	llext: Add parameters to arch_elf_relocate	2025-03-07 19:44:54 +01:00
fatal.c	coredump: ARM: Ensure sp in dump is set as gdb expects	2024-11-06 10:17:59 -08:00
gdbstub.c	arch: define struct arch_esf and deprecate z_arch_esf_t	2024-06-04 14:02:51 -05:00
header.S
irq_offload.c	arch: initialize irq_offload during boot, do not use SYS_INIT	2024-09-17 20:05:22 -04:00
Kconfig	arch: add dependencie for CONFIG_SRAM_VECTOR_TABLE	2025-04-25 11:03:54 +02:00
Kconfig.vfp
nmi_on_reset.S
nmi.c
swi_tables.ld
tls.c	toolchain: iar: tls: no tls pointer offset in IAR	2025-02-14 19:12:44 +00:00
userspace.S
vector_table.ld
zimage_header.ld