- User Since
- May 19 2014, 3:05 PM (360 w, 2 d)
Thu, Apr 8
am I ok to proceed with this cleanup?
Wed, Apr 7
Thu, Apr 1
The case I am thinking of, there are 4 NUMA domains, but memory access is equal cost to all four, so there may be better performance to be had by having the default policy be INTERLEAVE instead of FIRST_TOUCH (use the bandwidth of all 4 memory controllers). So I wasn't thinking to override those that request FIRST_TOUCH, but just set the default policy for zones that don't request a specific policy.
For modules that have tunables, you need to set them via kenv (or have them set at boot via loader.conf) BEFORE you load the module.
Would it make sense to have a tunable to control the default policy for UMA? If I wanted to have zones that don't declare themselves UMA_ZONE_FIRSTTOUCH, but interleaved, or something to that effect?
Mon, Mar 29
Fri, Mar 26
Reviewed By: allanjude
Approved By: allanjude
Mar 15 2021
Mar 14 2021
Mar 11 2021
Mar 10 2021
Mar 4 2021
Mar 2 2021
Feb 25 2021
Feb 24 2021
Feb 23 2021
I had to revert this, as it depends on https://reviews.freebsd.org/D28739 which isn't ready to land yet
Fix a typo
Switch to Scott's newer suggested code that is much cleaner
Add the new code to sys/conf/files.arm64 as well, so IPMI works when built into the kernel
Feb 20 2021
I tested this recently on an ARM64 ACPI box, and ran into a panic at boot:
pmu0: <Performance Monitoring Unit> on acpi0 pmu0: MADT: cpu 0 (mpidr 1179648) irq 23 level-triggered pmu0: MADT: cpu 1 (mpidr 1703936) irq 23 level-triggered pmu0: MADT: cpu 2 (mpidr 1310720) irq 23 level-triggered pmu0: MADT: cpu 3 (mpidr 1835008) irq 23 level-triggered pmu0: MADT: cpu 4 (mpidr 1048576) irq 23 level-triggered pmu0: MADT: cpu 5 (mpidr 1572864) irq 23 level-triggered pmu0: MADT: cpu 6 (mpidr 1441792) irq 23 level-triggered pmu0: MADT: cpu 7 (mpidr 1966080) irq 23 level-triggered pmu0: MADT: cpu 8 (mpidr 655360) irq 23 level-triggered pmu0: MADT: cpu 9 (mpidr 2228224) irq 23 level-triggered pmu0: MADT: cpu 10 (mpidr 786432) irq 23 level-triggered pmu0: MADT: cpu 11 (mpidr 2359296) irq 23 level-triggered pmu0: MADT: cpu 12 (mpidr 524288) irq 23 level-triggered pmu0: MADT: cpu 13 (mpidr 2097152) irq 23 level-triggered Fatal data abort: x0: 0 x1: ffffa0001d8103a8 x2: 0 x3: a x4: ffff000000721fc0 x5: 10 x6: f x7: 254 x8: ffffa0001d80fe00 x9: ffff000000aad928 x10: 1 x11: 0 x12: 0 x13: 4 x14: 80 x15: 1 x16: 700 x17: 3 x18: ffff000000f277e0 x19: ffff000000f27870 x20: ffff0002023fd43c x21: d x22: ffffa0001d80fe00 x23: ffffa0001d80bc00 x24: 17 x25: ffff000000823cd6 x26: ffffa0001d80bb00 x27: ffffa0001d805af0 x28: 1 x29: ffff000000f277f0 sp: ffff000000f277e0 lr: ffff000000720860 elr: ffff000000720888 spsr: 604001c5 far: 0 esr: 96000004 panic: vm_fault failed: ffff000000720888 cpuid = 0 time = 1 KDB: stack backtrace: db_trace_self() at db_trace_self db_trace_self_wrapper() at db_trace_self_wrapper+0x30 vpanic() at vpanic+0x184 panic() at panic+0x44 data_abort() at data_abort+0x1d8 handle_el1h_sync() at handle_el1h_sync+0x74 --- exception, esr 0x96000004 madt_handler() at madt_handler+0xe8 acpi_walk_subtables() at acpi_walk_subtables+0x3c pmu_acpi_attach() at pmu_acpi_attach+0x64 device_attach() at device_attach+0x400 bus_generic_new_pass() at bus_generic_new_pass+0x11c bus_generic_new_pass() at bus_generic_new_pass+0xac bus_generic_new_pass() at bus_generic_new_pass+0xac root_bus_configure() at root_bus_configure+0x40 mi_startup() at mi_startup+0x22c virtdone() at virtdone+0x6c KDB: enter: panic [ thread pid 0 tid 100000 ] Stopped at kdb_enter+0x40: undefined d4200000
Feb 19 2021
Feb 18 2021
Do we want to put this link and section reference in the commit message?
Feb 17 2021
Should https://reviews.freebsd.org/D28745 be squashed into this review?
It likely makes sense to squash this with https://reviews.freebsd.org/D28738
Ok, I think I've gotten a handle on the git-arc tool.
No, having only one loop that set both kenv is what we need.
Feb 16 2021
- stand: Support (and prefer) the SMBIOS 64-bit Entry Point Structure
- smbios: Move smbios driver out from x86 machdep code
- smbios: Support (and prefer) the SMBIOS 64-bit Entry Point Structure
- smbios: Use loader provided adddress for SMBIOS entry point
- acpi: Add workaround for Altra I2C memory resource
- iicsmb: Request the bus recursively in bread()
- ipmi_smbios: Deduplicate smbios entry point discovery logic
- Enable smbios in ARM64 GENERIC
- ipmi: Add smbus and pci ipmi types to aarch64 build
- ig4(4): Add an EMAG device type
- ig4(4): Increase timeout to about 1 second
- ig4(4): Use calculated value when sda_hold is zero in ACPI
- ipmi_ssif: Fix inverted for the end of multi-part reads
- smbios: update makefile for new location of smbios.c
- ipmi: on aarch64, load dependancies to increase chance of finding ipmi device
- ipmi_smbios: remove unused smbios_cksum function
- [squashme] Address feedback from manu and andrew