IABSD.fr/src/sys
Branch :
Log
| Author | Commit | Date | CI | Message |
|---|---|---|---|---|
 |
2293e682 | 2024-08-05 23:56:10 | restrict the maximum wait time you can set via BIOCSWTIMEOUT to 5 minutes. this is avoids passing excessively large values to timeout_add_nsec. Reported-by: syzbot+f650785d4f2b3fe28284@syzkaller.appspotmail.com | |
|
e7251812 | 2024-08-05 23:51:11 | change the nsec argument to timeout_add_nsec from int to uint64_t you can only fit a couple of nanonseconds into an int, which limited the usefulness of the api. worse, if a large nsec value was passed in it could be cast to a negative int value which tripped over a KASSERT at the top of timeout_add that ends up being called. avoid this footgun by working in the bigger type and doing the same range checks/fixes for other timeout_add wrappers. ok claudio@ mvs@ | |
 |
438cc182 | 2024-08-05 18:47:29 | Unlock KERN_BOOTTIME. microboottime() and following binboottime() are mp-safe and `mb' is local data. ok bluhm | |
 |
a4f9b83f | 2024-08-05 18:39:34 | Adjust for arm64_intr_get_parent() changes. ok patrick@ | |
|
4ad77004 | 2024-08-05 18:37:29 | Fix reporting if critical battery state. ok jca@, mlarkin@ | |
|
1f1fa3f3 | 2024-08-05 18:36:28 | Add battery sensors. ok phessler@ | |
 |
270a6ceb | 2024-08-05 17:47:29 | Fix bridging IPv6 fragments with pf reassembly. Sending IPv6 fragments over a bridge with pf did not work. During input pf reassembles the packet, and at bridge output it should be refragmented. This is only done for PF_FWD direction, but bridge(4) and veb(4) called pf_test() with PF_OUT argument. OK sashan@ | |
|
ad534f18 | 2024-08-05 15:43:58 | Unlock most of `kern_vars' variables. Add corresponding cases to the kern_sysctl() switch and unlock read-only variables from `kern_vars'. Unlock KERN_SOMAXCONN and KERN_SOMINCONN which are atomically read-only accessed only from solisten(). ok kettenis | |
|
d5cabab1 | 2024-08-05 13:55:34 | The devicetree spec says in section 2.4: If an interrupt-generating device does not have an interrupt-parent property, its interrupt parent is assumed to be its devicetree parent. Implement this aspect of the spec in the same way as Linux does by not just looking at the immediate parent but keep on walking up the tree until we hit a node with an "interrupt-controller" property or a node that has an "interrupt-parent" property. same diff as committed for arm64 yesterday ok patrick@ | |
|
522bbe49 | 2024-08-05 13:46:16 | Take `sysctl_lock' before kernel lock. ok bluhm | |
 |
2adb8ed0 | 2024-08-05 09:43:26 | sync with base | |
 |
5f1cde00 | 2024-08-05 02:54:42 | drm/i915/dp: Don't switch the LTTPR mode on an active link From Imre Deak 12880cc086deef91e62e2f010750087a3c23fae3 in linux-6.6.y/6.6.44 509580fad7323b6a5da27e8365cd488f3b57210e in mainline linux | |
|
aa0c546b | 2024-08-05 02:52:34 | drm/i915/dp: Reset intel_dp->link_trained before retraining the link From Imre Deak a90e900f71da23a354e9d17f1dc0c654d0ae9ceb in linux-6.6.y/6.6.44 d13e2a6e95e6b87f571c837c71a3d05691def9bb in mainline linux | |
|
cd8dd4c7 | 2024-08-05 02:50:36 | drm/amd/amdgpu: Fix uninitialized variable warnings From Ma Ke e150f0171c0c0c45a373a658358c51c940ed4fd9 in linux-6.6.y/6.6.44 df65aabef3c0327c23b840ab5520150df4db6b5f in mainline linux | |
|
26d6e9f7 | 2024-08-05 02:47:58 | drm/amdgpu: reset vm state machine after gpu reset(vram lost) From ZhenGuo Yin 323790535237927e1b6a7bc35ddf662c6e7c25cc in linux-6.6.y/6.6.44 5659b0c93a1ea02c662a030b322093203f299185 in mainline linux | |
|
cb2f7175 | 2024-08-05 02:44:55 | drm/dp_mst: Fix all mstb marked as not probed after suspend/resume From Wayne Lin e290feb8b749a06b93ed01d4cf66567cbdf0e85d in linux-6.6.y/6.6.44 d63d81094d208abb20fc444514b2d9ec2f4b7c4e in mainline linux | |
|
f61f9b4d | 2024-08-05 02:42:47 | drm/amdgpu/sdma5.2: Update wptr registers as well as doorbell From Alex Deucher 9d74e50098492e89f319ac6922db3c2062f69340 in linux-6.6.y/6.6.44 a03ebf116303e5d13ba9a2b65726b106cb1e96f6 in mainline linux | |
|
4d9ba5d1 | 2024-08-05 02:40:00 | drm/i915/gt: Do not consider preemption during execlists_dequeue for gen8 From Nitin Gote 05c0fb20ca3e000a7e966584845731ba4fc950da in linux-6.6.y/6.6.44 65564157ae64cec0f527583f96e32f484f730f92 in mainline linux | |
|
180eb82d | 2024-08-05 02:37:12 | drm/amd/display: Check for NULL pointer From Sung Joon Kim 4ccd37085976ea5d3c499b1e6d0b3f4deaf2cd5a in linux-6.6.y/6.6.44 4ab68e168ae1695f7c04fae98930740aaf7c50fa in mainline linux | |
|
d7388dee | 2024-08-05 02:35:12 | drm/amdgpu: Remove GC HW IP 9.3.0 from noretry=1 From Tim Van Patten 6d72626808325c1986cbf90b0ce27a59b4291876 in linux-6.6.y/6.6.44 1446226d32a45bb7c4f63195a59be8c08defe658 in mainline linux | |
|
d98eb4da | 2024-08-05 02:33:42 | drm/amdgpu: Check if NBIO funcs are NULL in amdgpu_device_baco_exit From Friedrich Vock 67b4592a7d74e57a5a0929eaf3ae30414ebd39ae in linux-6.6.y/6.6.44 0cdb3f9740844b9d95ca413e3fcff11f81223ecf in mainline linux | |
|
9456895c | 2024-08-05 02:31:14 | drm/amdgpu: Fix memory range calculation From Lijo Lazar ae1dd0a379e41db7d4773880e6918948668ef3ad in linux-6.6.y/6.6.44 ce798376ef6764de51d8f4684ae525b55df295fa in mainline linux | |
|
6216c052 | 2024-08-05 02:28:52 | drm/amd/pm: Fix aldebaran pcie speed reporting From Lijo Lazar 0af2e5cb74514877326448becf40365b073b44e2 in linux-6.6.y/6.6.44 b6420021e17e262c57bb289d0556ee181b014f9c in mainline linux | |
|
5e55c4ed | 2024-08-05 02:26:35 | drm/amdkfd: Fix CU Masking for GFX 9.4.3 From Mukul Joshi cd1885ae4cbf191332ae66f8a214e52fb226ba43 in linux-6.6.y/6.6.44 85cf43c554e438e2e12b0fe109688c9533e4d93f in mainline linux | |
 |
8d1d79aa | 2024-08-04 22:28:08 | ppoll() is in POSIX-2024. Update #include visibility and manpages and add restrict qualifiers. While here, rename the BUGS section to CAVEATS since they're really "these probably don't do what you want" notes and not things that need fixing. ok millert@ | |
 |
f4fd31f8 | 2024-08-04 20:10:38 | Fix typo. ok kettenis@ | |
|
5dbfd905 | 2024-08-04 15:30:08 | Add battery status support for the x1e80100. This SoC needs a second firmware and requires us to shut down an initial "light" firmware that was presumably loaded bu the system firmware. For now the required firmwares are not packaged and need to be copied from the Windows install. ok patrick@ | |
|
fa6a043a | 2024-08-04 12:01:18 | The devicetree spec says in section 2.4: If an interrupt-generating device does not have an interrupt-parent property, its interrupt parent is assumed to be its devicetree parent. Implement this aspect of the spec in the same way as Linux does by not just looking at the immediate parent but keep on walking up the tree until we hit a node with an "interrupt-controller" property or a node that has an "interrupt-parent" property. ok patrick@ | |
|
6635b7e6 | 2024-08-04 11:05:18 | Add intelpmc(4), a driver for the power management controller found on various Intel SoCs. The driver takes care of calling the AML methods needed to enter low power idle states during suspend-to-idle (S0i). The driver also implements some debug code that prints the residency of various power states in dmesg. Based on some earlier code by jcs@ ok jcs@ | |
|
f4d0a262 | 2024-08-02 22:24:51 | Code patch out the retpoline in the signal trampoline just like the others. Nudged, test, and ok deraadt@ | |
|
953cd95b | 2024-08-02 14:35:56 | regen | |
|
d800346e | 2024-08-02 14:34:45 | Push kernel lock down to sysctl(2). Unlock few obvious immutable or read-only variables from "kern.*" and "hw.*" paths. Keep the rest variables locked as before, include pages wiring. Use new sysctl_vs{,un}lock() functions introduced for thar purpose. In kern.* path: - KERN_OSTYPE, KERN_OSRELEASE, KERN_OSVERSION, KERN_VERSION - immutable; - KERN_NUMVNODES - read-only access to integer; - KERN_MBSTAT - read-only access to per-CPU counters; In hw.* path: - HW_MACHINE, HW_MODEL, HW_NCPUONLINE, HW_PHYSMEM, HW_VENDOR, HW_PRODUCT, HW_VERSION, HW_SERIALNO, HW_UUID, HW_PHYSMEM64 - immutable; - HW_USERMEM and HW_USERMEM64 - `physmem' is immutable, uvmexp.wired is mutable but integer; read-only access to localy stored difference between `physmem' and uvmexp.wired; - `hw_vars' - read-only access to integers; some of them like HW_BYTEORDER and HW_PAGESIZE are immutable; ok bluhm kettenis | |
|
ce337326 | 2024-08-02 09:28:35 | Switch off unreferenced power resources in DVACT_POWERDOWN instead of DVACT_SUSPEND. Fixes an issue with (un)hibernate where we don't attach xhci(4) controllers, which would make is turn the xhci(4) off inadvertedly because its power resource wasn't referenced. ok mlarkin@ | |
|
c1d8b5d1 | 2024-08-02 01:53:21 | getentropy(2) is in POSIX-2024, so adjust the #include visibility, change the "too much" error to EINVAL, add GETENTROPY_MAX to <limits.h> (via sys/syslimits.h), and update the manpage. ok deraadt@ | |
|
64e5b687 | 2024-08-01 17:19:01 | Run socket splice idle timeout without kernel lock. OK mvs@ | |
|
d83b63cc | 2024-08-01 11:53:03 | Add device tree mapping for Samsung Galaxy Book4 Edge. ok kettenis@ | |
 |
d3638ce2 | 2024-08-01 11:13:19 | virtio: Fix dmamap_sync calls Add some missing bus_dmamap_sync calls, noticed with SEV and based on an earlier diff by hshoexer@. Some of the required syncing is done in virtio_check_vq(). Make sure to use that function instead of calling call the virtqueue done function directly from device specific drivers. For viogpu this means that we cannot poll with virtio_dequeue() but must use virtio_check_vq() instead. To make this more clear, rename viogpu_vq_wait() into viogpu_vq_done(). While there, set the DRIVER_OK flag even earlier. It must be set before using any virtqueue. ok kettenis@ | |
|
df51ca29 | 2024-08-01 06:04:22 | Remove a comment that was committed by accident | |
|
0a218225 | 2024-08-01 04:03:10 | sync with src | |
|
9ae74e5e | 2024-07-31 10:07:33 | Add ufshci(4) at fdt support. This lets me boot the Samsung Galaxy Book4 Edge in DT mode with ufshci(4), based on a WIP DTB file. ok kettenis@ | |
|
075c50c2 | 2024-07-30 19:47:05 | Make the Samsung Galaxy Book4 Edge (x1e80100) boot in ACPI mode; Until now the kernel did panic during early boot because we couldn't respond to the battery requests sent to the 0xa1 "bus". This (dummy) driver registers a 0xa1 region space very early, and responds with a static zero value to satisfy the battery requests on 0xa1, which let us boot successfully to multi-user. In the future this machine should be operated in FDT mode, and an improved AML parsing interface might make this workaround obsolete also for RAMDISK. Help and OK kettenis@, deraadt@ | |
 |
5e1af158 | 2024-07-30 13:41:15 | Exports the statistics when PIPEXDSESSION. Found by ymatsui at iij. ok mvs | |
|
ab617a20 | 2024-07-30 08:59:33 | Populate most of the remaining hwcap and hwcap2 flags based on the detected CPU features. ok naddy@ | |
|
ad4b79de | 2024-07-30 05:57:31 | Recognize the features defines for POSIX 1003.1-2024, giving new values for __POSIX_VISIBLE and __XPG_VISIBLE. ok millert@ | |
|
42d82ebc | 2024-07-29 18:43:11 | Set the target ACPI to S5 when we're powering down the machine. Prevents us from trying to put devices into the D3 power state which some hardware doesn't appreciate. ok ratchov@, deraadt@ | |
 |
235013eb | 2024-07-29 12:42:53 | Move the signal related kqueue filters to kern_event.c. Since proc and signal filters share the same klist it makes sense to keep them together. OK mvs@ | |
|
4eca214d | 2024-07-29 12:41:30 | Use shared net lock instead of exclusive when frag6 calls icmp6_error(). OK mvs@ a while ago as part of a larger diff | |
|
984616ac | 2024-07-29 10:35:22 | Remove `sb_sel' from sobuf_print() output, no sense to print "...". ok bluhm | |
|
c4fac757 | 2024-07-29 09:49:49 | Replace per thread P_CONTINUED with per process PS_CONTINUED flag dowait6() can only look at per process state so switch this over. Right now SIGCONT handling in ptsignal is recursive and not quite right but this is a step in the right direction. It fixes dowait6() handling for multithreaded processes where the main thread exited. OK mpi@ | |
|
fc16a34e | 2024-07-29 01:26:15 | drm/amdgpu: Fix signedness bug in sdma_v4_0_process_trap_irq() From Dan Carpenter 4edb0a84e6b32e75dc9bd6dd085b2c2ff19ec287 in linux-6.6.y/6.6.43 6769a23697f17f9bf9365ca8ed62fe37e361a05a in mainline linux | |
|
b83e847d | 2024-07-29 01:18:32 | regen | |
|
dadec1e3 | 2024-07-29 01:17:53 | add "Strix Point" APU device id, and another Navi 31 150e rev c1 is Radeon 880M/890M 150e rev c4 is Radeon 880M/890M 150e rev c6 is Radeon 890M 744a rev 00 is Radeon Pro W7900 Dual Slot found in AMD Software: Adrenalin Edition 24.7.1 | |
 |
6bc6e70e | 2024-07-27 17:31:49 | Allow for another TEMPerHUM version. From Sebastiaan Indesteege. | |
|
5ccef584 | 2024-07-27 13:31:26 | Use ".arch_extension fp" for the signal trampoline since it saves and restores the FPU registers (running in userland). And add an ".arch_extension nofp" afterwards such that the remaining kernel code can't touch the FPU. Needed to build with clang18 ok jsg@ | |
 |
8c144870 | 2024-07-27 03:26:12 | sync | |
|
25a0d4ae | 2024-07-27 03:26:04 | shorten strings by removing pointless information ok jsg | |
|
247cf2e3 | 2024-07-27 02:10:26 | Sort and regularize all the ktrstruct() macros ok deraadt@ | |
|
a984a0c3 | 2024-07-26 19:16:31 | Trace struct itimerval ok deraadt@ claudio@ | |
|
35c0c3c8 | 2024-07-26 15:59:04 | On AMD vmm(4) set SVM_INTERCEPT_INVLPGA in intercept1. According to the AMD64 Architecture Programmer's Manual volume 2 the intercept SVM_INTERCEPT_INVLPGA needs to be set in vmcb.intercept1 (vector 3, offest 00Ch) instead of intercept2 (vector 4, offset 010h). SVM_INTERCEPT_INVLPGA is bit 26, so before vcpu_reset_regs_svm() was actually setting an intercept for CR10, which does not exist. from hshoexer@; OK mlarkin@ | |
|
8fd4ba52 | 2024-07-26 15:51:09 | Mark ipsecflowinfo immutable. ok mvs | |
|
207bd73a | 2024-07-26 15:45:31 | In pipex_l2tp_input(), check if ipsecflowinfo is not changed instead of updating it blindly. ok mvs | |
|
59d5251a | 2024-07-26 14:38:20 | Run UDP input on multiple CPU in parallel. The socket layer of UDP has been made fully MP safe. UDP output is MP safe for a while. mvs@ has fixed the missing pieces in socket splicing recently. This means that complete UDP stack can be processed by multiple threads now. Activate multi processing for udp_input() when called with IPv4 or IPv6 packets. Usually IP processing runs on multiple softnet threads with shared net lock. From there local packets are queued and processed by one thread with exclusive net lock. If the PR_MPINPUT flag is set, protocol input is called directly from IP input on multiple threads, with shared net lock and no additional queueing. tested by Hrvoje Popovski; OK mvs@ | |
|
6354d80b | 2024-07-26 07:55:23 | virtio: add/fix feature bits There was a off-by-one in unused vioblk feature defines. Fix this. Add missing feature bits from virtio 1.2 so that they are displayed with VIRTIO_DEBUG. ok jan@ | |
|
2175e0d6 | 2024-07-26 06:29:01 | vio: Don't request csum offload if not negotiated The standard says "A driver MUST NOT enable an offload for which the appropriate feature has not been negotiated." ok jan@ | |
|
a7c1a79f | 2024-07-26 03:42:02 | drm/radeon: check bo_va->bo is non-NULL before using it From Pierre-Eric Pelloux-Prayer f13c96e0e325a057c03f8a47734adb360e112efe in linux-6.6.y/6.6.42 6fb15dcbcf4f212930350eaee174bb60ed40a536 in mainline linux | |
|
1ff2e760 | 2024-07-26 03:39:34 | drm/amd/display: Fix refresh rate range for some panel From Tom Chung 607731f315d15558696e9b542121d40411df37fd in linux-6.6.y/6.6.42 9ef1548aeaa8858e7aee2152bf95cc71cdcd6dff in mainline linux | |
|
06680a8b | 2024-07-26 03:37:12 | drm/amd/display: Account for cursor prefetch BW in DML1 mode support From Alvin Lee 6ecf239f71ef7f6e9f8ea46b9c7ef4df2afd96c9 in linux-6.6.y/6.6.42 074b3a886713f69d98d30bb348b1e4cb3ce52b22 in mainline linux | |
|
97676e2e | 2024-07-26 03:34:59 | drm/amd/display: Add refresh rate range check From Tom Chung 531e7852fb62bfc6a15cc1df85f62720f704d537 in linux-6.6.y/6.6.42 74ad26b36d303ac233eccadc5c3a8d7ee4709f31 in mainline linux | |
|
f713ee03 | 2024-07-26 03:32:20 | drm/amdgpu: Indicate CU havest info to CP From Harish Kasiviswanathan 86a6a3964f600d458412295ac8d705b6b9a8efdb in linux-6.6.y/6.6.42 49c9ffabde555c841392858d8b9e6cf58998a50c in mainline linux | |
|
0c400691 | 2024-07-26 03:29:47 | drm: panel-orientation-quirks: Add quirk for Aya Neo KUN From Tobias Jakobi 97f71343f794c6ecbb3a2d55b4a04464e924b139 in linux-6.6.y/6.6.42 f74fb5df429ebc6a614dc5aa9e44d7194d402e5a in mainline linux | |
|
84dbb7f9 | 2024-07-26 00:23:57 | use the fp target attribute with fpu_save()/fpu_load() otherwise clang 18 errors when inline assembly uses floating point registers with nofp in -march ok kettenis@ | |
|
5d846028 | 2024-07-25 20:21:40 | Explicitly request for battery status updates as the firmware doesn't seem to send us regular updates itself. Estamate the remaining battery (charge) time by using the reported rate. ok phessler@ | |
|
50bdd322 | 2024-07-25 08:35:40 | virtio: Allow more verbose debugging If VIRTIO_DEBUG is set to 2, dump the whole virtqueues. | |
|
e8331b74 | 2024-07-24 21:24:18 | If the CPU cores implement FEAT_IDST, emulate access to the CPU ID registers from userland and set HWCAP_CPUID. This will allow detection of features to be introduced into the architecture in the future without allocating new HWCAP_xxx or HWCAP2_xxx bits. We provide the same sanitized view of the CPU ID registers as is currently available through sysctl(2). Note that this introduces an unconditional read of ID_AA64MMFR2_EL1. This is known to cause problems on older versions of QEMU. If this turns out to be a problem in cases where updating QEMU is not an option, we'll have to implement a workaround. Also note that since we don't emulate the CPU ID registers on older core, this means that microarchitectural optimizations keyed of reads of MIDR_EL1 are not possible on OpenBSD. I don't think that is a real problem. ok jca@ | |
 |
e06d8e0f | 2024-07-24 21:04:12 | vmm(4): drop checks for EPT or RVI in some functions. vmm(4) only supports using nested paging on Intel or AMD and no longer supports HLAT or shadow paging. ok mlarkin@ | |
|
350ab3c3 | 2024-07-24 15:31:08 | KASSERT that the ps_single proc has P_SUSPSINGLE cleared. Requested by kettenis@ and guenther@ | |
|
8c845098 | 2024-07-24 15:30:17 | Remove the (pr->ps_single->p_flag & P_SUSPSINGLE) == 0 check since it is always true. Also consitently wrap all flag checks into parantheses. OK kettenis@ guenther@ | |
|
97390b9a | 2024-07-24 13:37:05 | Use a different mutex to protect the kqueue klist in logsoftc. knote_locked() will call wakeup() and with it the SCHED_LOCK and by that makes log_mtx no longer a leaf lock. By using an own lock for the klist we can keep log_mtx a leaf lock and with that printf(9) can be used in most contexts again. OK mvs@ | |
 |
8f968f81 | 2024-07-24 12:18:10 | Remove workaround for lock ordering issue in uvm_pseg_get(). Now that uvm_unmap_detach() no longer grab the KERNEL_LOCK() it should be safe to call it with the `uvm_pseg_lck' mutex held via uvm_km_valloc_try(). ok jca@, claudio@ | |
|
8e4f8f34 | 2024-07-24 12:17:31 | Move uvm_exit() outside of the KERNEL_LOCK() in the reaper. Use atomic operations to reference count VM spaces. Tested by claudio@, bluhm@, sthen@, jca@ ok jca@, claudio@ | |
|
a5c1aec3 | 2024-07-24 12:16:21 | Grab the kernel lock in preparation for unlocking most of uvm_unmap_detach(). ok jca@, claudio@ | |
|
d88aa8ff | 2024-07-24 12:15:55 | Remove assertion in udv_detach(), the function is already mpsafe. ok jca@, claudio@ | |
 |
26723e1a | 2024-07-23 20:04:51 | Accept and ignore SADB_X_EXT_REPLAY and SADB_X_EXT_COUNTER payloads for incoming SADB_ADD and SADB_UPDATE message. Since we send them as part of the SADB_GET reply we must also accept them on SADB_ADD/UPDATE as sasyncd will forward payloads previously received in SADB_GET. Fixes a bug where sasync can't restore SAs because pfkey returns EINVAL. From Rafa\xc5\x82 Ramocki ok bluhm@ | |
|
c36fc2a0 | 2024-07-23 19:14:05 | virtio: fix comment | |
 |
ba9ca4db | 2024-07-23 08:59:21 | uaudio: Fix confusion between interface numbers and interface indexes There is rare hardware for which the interface numbers and indexes are not equal. Such devices couldn't attach because the driver claimed the wrong interface. | |
|
a7ffde75 | 2024-07-23 08:38:02 | Pass curproc pointer down from sleep_finish() instead of pulling it in again in sleep_signal_check(). OK dlg@ | |
|
5bf94a72 | 2024-07-22 14:03:22 | remove unneeded prototypes for functions in other files | |
|
2a3093b8 | 2024-07-22 12:05:38 | remove prototype with no matching function | |
|
ba2390ce | 2024-07-22 09:43:47 | Rename PS_STOPPED to PS_STOPPING. I want to use PS_STOPPED to indicate that a process has been stopped so make room for that. OK kettenis@ | |
|
a9d55c5c | 2024-07-22 08:18:53 | Switch proc_finish_wait() to use the process as argument instead of its ps_mainproc. dowait6() needs to stop using ps_mainproc and this is the first step. OK guenther@ | |
|
72a0fbcc | 2024-07-21 19:41:31 | For AMD SEV determine C-bit position and guest mode in locore0. Actually determine the C-bit position if we are running as a guest with SEV enabled. Configure pg_crypt, pg_frame and pg_lgframe accordingly, using the physical address bit reduction provided by cpuid. from hshoexer@; OK mlarkin@ | |
|
d2974a1e | 2024-07-21 18:57:31 | Populate hwcap and hwcap2 based on the sanitized values of the ID register values and the feature bits that we recognize. ok naddy@, jca@ | |
 |
0b0568a1 | 2024-07-21 16:49:26 | Export basic HWCAP bits to let applications detect Altivec & VSX on powerpc64 Input from miod@ and gkoehler@, tests & ok gkoehler@ | |
|
dfc50e6f | 2024-07-21 16:46:56 | Export basic HWCAP bits to let applications detect Altivec on powerpc Input from miod@ and gkoehler@, tests & ok gkoehler@ | |
|
41662a9f | 2024-07-21 16:19:25 | A few manual ret-cleans. Seeing as these pertain to interrupt servicing, the stack utilization ends up near the the deep end of the stack where, retcleans are useful. tested for a while in snaps ok bluhm | |
 |
649d1e2e | 2024-07-21 13:18:15 | Add optimized character rendering case for 6 pixels wide fonts in rasops32_putchar(). From jon (at) elytron (dot) openbsd (dot) amsterdam. | |
|
134de7a2 | 2024-07-20 17:26:19 | Unlock udp(4) somove(). Socket splicing belongs to sockets buffers. udp(4) sockets are fully switched to fine-grained buffers locks, so use them instead of exclusive solock(). Always schedule somove() thread to run as we do for tcp(4) case. This brings delay to packet processing, but it is comparable wit non splicing case where soreceive() threads are always scheduled. So, now spliced udp(4) sockets rely on sb_lock() of `so_rcv' buffer together with `sb_mtx' mutexes of both buffers. Shared solock() only required around pru_send() call, so the most of somove() thread runs simultaneously with network stack. Also document 'sosplice' structure locking. Feedback, tests and OK from bluhm. | |
|
2183e7c2 | 2024-07-20 12:34:52 | UVIDEO_DEBUG needs fcntl.h reported by Peter J. Philipp | |
|
9c4c1a6f | 2024-07-19 16:58:31 | Unlock sysctl net.inet.ip.redirect and net.inet6.ip6.redirect. Variable ip and ip6 sendredirects is only read once during packet processing. Use atomic_load_int() to access the value in exactly one read instruction. No memory barriers needed as there is no correlation with other values. Sort the ip and ip6 checks, so the difference is easier to see. Move access to global variable to the end. OK mvs@ | |
|
18474754 | 2024-07-19 15:41:58 | Relax socket lock assertion in UDP input and send. OK mvs@ |