Page MenuHomeFreeBSD

kib (Konstantin Belousov)
User

Projects

User Details

User Since
May 16 2014, 7:35 PM (278 w, 6 d)

Recent Activity

Today

kib committed rS352549: MFC r352303:.
MFC r352303:
Fri, Sep 20, 7:24 AM

Yesterday

kib added a comment to D21592: (vm object 3) Add a shared object busy synchronization mechanism that blocks new page busy acquires while held..
In D21592#473571, @jeff wrote:

I think I've brought this up before, but I would like it if the VM had a generic per-2MB page structure. We already have several in vm_reserv and the pmap, and IMO it would be a good place to maintain a "compound" busy state, rather than in the object. I worry that a mechanism to block the busying of all pages in an object will inhibit concurrency and lead to transient latency spikes. I don't object to the current approach though.

Right now the object lock is the mechanism that blocks busying of all pages and creates transient latency spikes. This at least narrows it a level and allows other object operations to proceed. If you had a per-superpage object you would have to be able to very quickly look it up and acquire in tryxbusy/sbusy.
Ultimately I would like to see a generic mechanism that can treat pages as groups with a single set of state. A variable page size.

Thu, Sep 19, 1:55 PM
kib added inline comments to D21592: (vm object 3) Add a shared object busy synchronization mechanism that blocks new page busy acquires while held..
Thu, Sep 19, 1:47 PM
kib accepted D21706: truss and ktrace should decode PROT_MAX allocations.
Thu, Sep 19, 1:05 PM
kib accepted D21703: o Unify all <machine>/resource.h, unhide PCI_RES_BUS, add CLK and PWR..
Thu, Sep 19, 7:09 AM
kib added a reviewer for D21703: o Unify all <machine>/resource.h, unhide PCI_RES_BUS, add CLK and PWR.: jhb.
Thu, Sep 19, 7:08 AM
kib added a comment to D21703: o Unify all <machine>/resource.h, unhide PCI_RES_BUS, add CLK and PWR..

This looks fine to me, but I have no idea why John put PCI_RES_BUS under #ifdef NEW_PCIB instead of defining it always. Also, would it be reasonable to do a separate pass to rename PCI_RES_BUS to SYS_RES_PCIBUS ?

Thu, Sep 19, 7:08 AM
kib added inline comments to D21706: truss and ktrace should decode PROT_MAX allocations.
Thu, Sep 19, 6:47 AM
kib added a comment to D21703: o Unify all <machine>/resource.h, unhide PCI_RES_BUS, add CLK and PWR..

I think it would be fair to remove copyrights from machine/resource.h, instead put the trivial header files into public domain or assign to yourself.

Thu, Sep 19, 6:42 AM

Wed, Sep 18

kib committed rS352494: Release dougm..
Release dougm.
Wed, Sep 18, 7:54 PM
kib added inline comments to D21706: truss and ktrace should decode PROT_MAX allocations.
Wed, Sep 18, 7:40 PM
kib committed rS352488: truss: decode sysctl names..
truss: decode sysctl names.
Wed, Sep 18, 4:15 PM
kib closed D21688: make truss decode sysctl names.
Wed, Sep 18, 4:15 PM
kib closed D21693: sysctl: use names instead of magic numbers.
Wed, Sep 18, 4:13 PM
kib committed rS352486: sysctl: use names instead of magic numbers..
sysctl: use names instead of magic numbers.
Wed, Sep 18, 4:13 PM
kib accepted D21688: make truss decode sysctl names.
Wed, Sep 18, 2:06 PM
kib added inline comments to D21688: make truss decode sysctl names.
Wed, Sep 18, 10:22 AM
kib added inline comments to D21688: make truss decode sysctl names.
Wed, Sep 18, 6:37 AM
kib accepted D21693: sysctl: use names instead of magic numbers.
Wed, Sep 18, 6:33 AM
kib added inline comments to D21592: (vm object 3) Add a shared object busy synchronization mechanism that blocks new page busy acquires while held..
Wed, Sep 18, 6:24 AM

Tue, Sep 17

kib accepted D21667: vfs: fix incorrect hold in vtryrecycle.
Tue, Sep 17, 8:19 PM
kib accepted D21393: [3/3] Add linux-compatible memfd_create.
Tue, Sep 17, 8:15 PM
kib committed rS352459: ifconfig: add report of the string from SIOCGIFDOWNREASON..
ifconfig: add report of the string from SIOCGIFDOWNREASON.
Tue, Sep 17, 6:51 PM
kib committed rS352458: Add SIOCGIFDOWNREASON..
Add SIOCGIFDOWNREASON.
Tue, Sep 17, 6:49 PM
kib closed D21527: Add SIOCGIFDOWNREASON.
Tue, Sep 17, 6:49 PM
kib committed rS352457: Further refine r352393, only call vnode_pager_setsize() outside the.
Further refine r352393, only call vnode_pager_setsize() outside the
Tue, Sep 17, 6:41 PM
kib closed D21632: realloc(x, 0) should not return NULL.
Tue, Sep 17, 6:36 PM
kib committed rS352456: realloc(x, 0) should not return NULL..
realloc(x, 0) should not return NULL.
Tue, Sep 17, 6:36 PM
kib committed rS352455: Return EISDIR when directory is opened with O_CREAT without O_DIRECTORY..
Return EISDIR when directory is opened with O_CREAT without O_DIRECTORY.
Tue, Sep 17, 6:32 PM
kib closed D21634: Return EISDIR when directory is opened with O_CREAT without O_DIRECTORY..
Tue, Sep 17, 6:32 PM
kib added a comment to D21646: vfs: add root vnode caching for mount points.

I think it is fine.

Tue, Sep 17, 2:48 PM
kib added inline comments to D21688: make truss decode sysctl names.
Tue, Sep 17, 2:37 PM
kib added a comment to D21667: vfs: fix incorrect hold in vtryrecycle.
In D21667#472964, @mjg wrote:

I think it's cleaner to handle this separately mostly because this function cannot do any clean up so it behaves quite differently compared to vn_start_write. If you insist I can fold it in.

Tue, Sep 17, 2:27 PM
kib accepted D21206: libc: add fdwalk.
Tue, Sep 17, 2:18 PM
kib added inline comments to D21206: libc: add fdwalk.
Tue, Sep 17, 12:32 PM
kib added a comment to D21667: vfs: fix incorrect hold in vtryrecycle.

Why do you need vn_start_write_nb() when vn_start_write() already takes the flag argument ?

Tue, Sep 17, 8:54 AM
kib added inline comments to D21393: [3/3] Add linux-compatible memfd_create.
Tue, Sep 17, 8:44 AM
kib accepted D21624: Add some tests for page fault signals and codes.
Tue, Sep 17, 7:43 AM

Mon, Sep 16

kib added a comment to D21678: Use AMD CLZERO instruction for pagezero..
In D21678#472744, @mjg wrote:
Mon, Sep 16, 6:57 PM
kib created D21678: Use AMD CLZERO instruction for pagezero..
Mon, Sep 16, 6:14 PM
kib accepted D21637: vfs: convert struct mount counters to per-cpu.
Mon, Sep 16, 6:10 PM
kib added a comment to D21642: Remove more unused identifiers from r351198..
In D21642#472503, @alc wrote:

Yes, I put the const in the wrong place. So, code within vm_page.c will avoid the dereference, but code outside vm_page.c that uses the declaration from vm_page.h will still perform the dereference. Declaring vm_page_array as an array would deal with both cases.

I'm still missing something. vm_page_array cannot be defined in vm_page.h, and if it is not defined there I do not see how the compiler can elide a memory dereference.

It cannot be defined, but can be declared, same as now. Or I do not understand what you are trying to say.

Mon, Sep 16, 4:01 PM
kib committed rS352393: nfscl_loadattrcache: fix rest of the cases to not call.
nfscl_loadattrcache: fix rest of the cases to not call
Mon, Sep 16, 1:26 PM
kib added inline comments to D21637: vfs: convert struct mount counters to per-cpu.
Mon, Sep 16, 8:29 AM
kib updated the summary of D21527: Add SIOCGIFDOWNREASON.
Mon, Sep 16, 8:12 AM
kib updated the summary of D21527: Add SIOCGIFDOWNREASON.
Mon, Sep 16, 8:12 AM
kib updated the summary of D21527: Add SIOCGIFDOWNREASON.
Mon, Sep 16, 8:07 AM
kib added reviewers for D21527: Add SIOCGIFDOWNREASON: network, transport.
Mon, Sep 16, 7:36 AM
kib accepted D21575: vfs: manage mnt_writeopcount with atomics.
Mon, Sep 16, 7:29 AM
kib committed rS352384: Increase the size of the send and receive buffers for YP client rpc.
Increase the size of the send and receive buffers for YP client rpc
Mon, Sep 16, 6:42 AM
kib closed D21586: Increase the size of the send and receive buffers for YP client rpc calls to max allowed UDP datagram size..
Mon, Sep 16, 6:42 AM
kib committed rS352383: MFC r352059, r352060:.
MFC r352059, r352060:
Mon, Sep 16, 6:24 AM
kib committed rS352382: MFC r352056:.
MFC r352056:
Mon, Sep 16, 6:23 AM
kib committed rS352381: MFC r352058:.
MFC r352058:
Mon, Sep 16, 6:22 AM
kib committed rS352380: MFC r352059, r352060:.
MFC r352059, r352060:
Mon, Sep 16, 6:15 AM
kib committed rS352379: MFC r352056:.
MFC r352056:
Mon, Sep 16, 6:13 AM
kib committed rS352378: MFC r352058:.
MFC r352058:
Mon, Sep 16, 6:12 AM

Sun, Sep 15

kib accepted D21392: [2/3] Add an initial seal argument to kern_shm_open() .
Sun, Sep 15, 5:08 PM

Sat, Sep 14

kib accepted D21575: vfs: manage mnt_writeopcount with atomics.
Sat, Sep 14, 9:35 PM
kib accepted D21574: vfs: manage mnt_lockref with atomics.
Sat, Sep 14, 9:29 PM
kib added a comment to D21574: vfs: manage mnt_lockref with atomics.

This is not yet updated to pcpu counters, right ?

Sat, Sep 14, 8:58 PM
kib accepted D21425: vfs: manage mnt_ref with atomics.
Sat, Sep 14, 8:55 PM
kib added inline comments to D21425: vfs: manage mnt_ref with atomics.
Sat, Sep 14, 8:17 PM
kib added inline comments to D21458: Add mount options to prevent covering.
Sat, Sep 14, 8:06 PM
kib accepted D21548: (vm object 1) Replace busy checks and sleeps with acquires where it is trivial to do so..
Sat, Sep 14, 7:39 PM
kib added inline comments to D21458: Add mount options to prevent covering.
Sat, Sep 14, 7:37 PM
kib accepted D19058: posix_spawn(3): handle potential signal issues with vfork.
Sat, Sep 14, 5:33 PM
kib added inline comments to D21548: (vm object 1) Replace busy checks and sleeps with acquires where it is trivial to do so..
Sat, Sep 14, 5:30 PM
kib added inline comments to D21425: vfs: manage mnt_ref with atomics.
Sat, Sep 14, 5:10 PM
kib added inline comments to D21425: vfs: manage mnt_ref with atomics.
Sat, Sep 14, 5:07 PM
kib updated the diff for D21566: Improve MD page fault handlers..

Build fixes: tb passes.

Sat, Sep 14, 4:50 PM
kib added inline comments to D21566: Improve MD page fault handlers..
Sat, Sep 14, 1:45 PM
kib committed rS352331: MFC r352013:.
MFC r352013:
Sat, Sep 14, 1:35 PM
kib committed rS352329: MFC r352017:.
MFC r352017:
Sat, Sep 14, 1:33 PM
kib committed rS352327: MFC r352016:.
MFC r352016:
Sat, Sep 14, 1:32 PM
kib committed rS352325: MFC r352015:.
MFC r352015:
Sat, Sep 14, 1:31 PM
kib committed rS352323: MFC r352014:.
MFC r352014:
Sat, Sep 14, 1:29 PM
kib committed rS352322: MFC r352013:.
MFC r352013:
Sat, Sep 14, 1:27 PM
kib committed rS352321: MFC r352012:.
MFC r352012:
Sat, Sep 14, 1:26 PM
kib accepted D21391: [1/3] Add mostly Linux-compatible file sealing support.
Sat, Sep 14, 9:03 AM
kib added inline comments to D19058: posix_spawn(3): handle potential signal issues with vfork.
Sat, Sep 14, 9:01 AM
kib accepted D21458: Add mount options to prevent covering.
Sat, Sep 14, 9:00 AM
kib accepted D21628: rangelock: add rangelock_cookie_assert.
Sat, Sep 14, 8:57 AM
kib accepted D21656: Fix aux_info corruption in rtld direct execution mode.
Sat, Sep 14, 8:27 AM

Fri, Sep 13

kib updated the diff for D21566: Improve MD page fault handlers..

Rebase after riscv commit.

Fri, Sep 13, 8:21 PM
kib committed rS352303: riscv trap_pfault: remove unneeded hold of the process around vm_fault() call..
riscv trap_pfault: remove unneeded hold of the process around vm_fault() call.
Fri, Sep 13, 8:17 PM
kib closed D21645: riscv trap_pfault: remove unneeded hold of the process around vm_fault() call..
Fri, Sep 13, 8:17 PM
kib added inline comments to D21645: riscv trap_pfault: remove unneeded hold of the process around vm_fault() call..
Fri, Sep 13, 8:05 PM
kib added inline comments to D21458: Add mount options to prevent covering.
Fri, Sep 13, 7:50 PM
kib created D21645: riscv trap_pfault: remove unneeded hold of the process around vm_fault() call..
Fri, Sep 13, 7:22 PM
kib added inline comments to D21638: Add kqueue support for ZFS..
Fri, Sep 13, 7:02 PM
kib added inline comments to D21458: Add mount options to prevent covering.
Fri, Sep 13, 6:28 PM
kib accepted D21642: Remove more unused identifiers from r351198..
Fri, Sep 13, 6:09 PM
kib added inline comments to D21628: rangelock: add rangelock_cookie_assert.
Fri, Sep 13, 6:06 PM
kib added a comment to D21626: vfs: scale foffset_lock.

I am fine with this version modulo atomic_short.

Fri, Sep 13, 6:03 PM
kib accepted D21627: Implement a close_range(2) syscall.
Fri, Sep 13, 6:02 PM
kib accepted D21639: Fix some issues with r352110..
Fri, Sep 13, 5:58 PM
kib created D21634: Return EISDIR when directory is opened with O_CREAT without O_DIRECTORY..
Fri, Sep 13, 10:38 AM
kib updated the diff for D21566: Improve MD page fault handlers..
  • Stop overloading KERN_INVALID_ADDRESS for out-of-object error. This breaks other situations, it seems that the best route is to add a new Mach-style error.
  • Switch to use switch in signal decoding in vm_fault_trap().
  • Do not assume that map == kernel_map implies signo != NULL. copyin faults on user address, but in kernel mode.
Fri, Sep 13, 9:47 AM
kib created D21632: realloc(x, 0) should not return NULL.
Fri, Sep 13, 9:21 AM