fdb987bebd
Currently we use a single hash table per PCB database for connected and bound PCBs. Since we started using net_epoch to synchronize hash table lookups, there's been a bug, noted in a comment above in_pcbrehash(): connecting a socket can cause an inpcb to move between hash chains, and this can cause a concurrent lookup to follow the wrong linkage pointers. I believe this could cause rare, spurious ECONNREFUSED errors in the worse case. Address the problem by introducing a second hash table and adding more linkage pointers to struct inpcb. Now the database has one table each for connected and unconnected sockets. When inserting an inpcb into the hash table, in_pcbinhash() now looks at the foreign address of the inpcb to figure out which table to use. This ensures that queue linkage pointers are stable until the socket is disconnected, so the problem described above goes away. There is also a small benefit in that in_pcblookup_*() can now search just one of the two possible hash buckets. I also made the "rehash" parameter of in(6)_pcbconnect() unused. This parameter seems confusing and it is simpler to let the inpcb code figure out what to do using the existing INP_INHASHLIST flag. UDP sockets pose a special problem since they can be connected and disconnected multiple times during their lifecycle. To handle this, the patch plugs a hole in the inpcb structure and uses it to store an SMR sequence number. When an inpcb is disconnected - an operation which requires the global PCB database hash lock - the write sequence number is advanced, and in order to reconnect, the connecting thread must wait for readers to drain before reusing the inpcb's hash chain linkage pointers. raw_ip (ab)uses the hash table without using the corresponding accessors. Since there are now two hash tables, it arbitrarily uses the "connected" table for all of its PCBs. This will be addressed in some way in the future. inp interators which specify a hash bucket will only visit connected PCBs. This is not really correct, but nothing in the tree uses that functionality except raw_ip, which as mentioned above places all of its PCBs in the "connected" table and so is unaffected. Discussed with: glebius Tested by: glebius Sponsored by: Klara, Inc. Sponsored by: Modirum MDPay Differential Revision: https://reviews.freebsd.org/D38569 |
||
|---|---|---|
| .. | ||
| amd64 | ||
| arm | ||
| arm64 | ||
| bsm | ||
| cam | ||
| cddl | ||
| compat | ||
| conf | ||
| contrib | ||
| crypto | ||
| ddb | ||
| dev | ||
| dts | ||
| fs | ||
| gdb | ||
| geom | ||
| gnu | ||
| i386 | ||
| isa | ||
| kern | ||
| kgssapi | ||
| libkern | ||
| modules | ||
| net | ||
| net80211 | ||
| netgraph | ||
| netinet | ||
| netinet6 | ||
| netipsec | ||
| netlink | ||
| netpfil | ||
| netsmb | ||
| nfs | ||
| nfsclient | ||
| nfsserver | ||
| nlm | ||
| ofed | ||
| opencrypto | ||
| powerpc | ||
| riscv | ||
| rpc | ||
| security | ||
| sys | ||
| teken | ||
| tests | ||
| tools | ||
| ufs | ||
| vm | ||
| x86 | ||
| xdr | ||
| xen | ||
| Makefile | ||
| README.md | ||
FreeBSD Kernel Source:
This directory contains the source files and build glue that make up the FreeBSD kernel and its modules, including both original and contributed software.
Kernel configuration files are located in the conf/ subdirectory of each
architecture. GENERIC is the configuration used in release builds. NOTES
contains documentation of all possible entries. LINT is a compile-only
configuration used to maximize build coverage and detect regressions.
Source Roadmap:
| Directory | Description |
|---|---|
| amd64 | AMD64 (64-bit x86) architecture support |
| arm | 32-bit ARM architecture support |
| arm64 | 64-bit ARM (AArch64) architecture support |
| cam | Common Access Method storage subsystem - cam(4) and ctl(4) |
| cddl | CDDL-licensed optional sources such as DTrace |
| conf | kernel build glue |
| compat | Linux compatibility layer, FreeBSD 32-bit compatibility |
| contrib | 3rd-party imported software such as OpenZFS |
| crypto | crypto drivers |
| ddb | interactive kernel debugger - ddb(4) |
| fs | most filesystems, excluding UFS, NFS, and ZFS |
| dev | device drivers and other arch independent code |
| gdb | kernel remote GDB stub - gdb(4) |
| geom | GEOM framework - geom(4) |
| i386 | i386 (32-bit x86) architecture support |
| kern | main part of the kernel |
| libkern | libc-like and other support functions for kernel use |
| modules | kernel module infrastructure |
| net | core networking code |
| net80211 | wireless networking (IEEE 802.11) - net80211(4) |
| netgraph | graph-based networking subsystem - netgraph(4) |
| netinet | IPv4 protocol implementation - inet(4) |
| netinet6 | IPv6 protocol implementation - inet6(4) |
| netipsec | IPsec protocol implementation - ipsec(4) |
| netpfil | packet filters - ipfw(4), pf(4), and ipfilter(4) |
| opencrypto | OpenCrypto framework - crypto(7) |
| powerpc | PowerPC/POWER (32 and 64-bit) architecture support |
| riscv | 64-bit RISC-V architecture support |
| security | security facilities - audit(4) and mac(4) |
| sys | kernel headers |
| tests | kernel unit tests |
| ufs | Unix File System - ffs(7) |
| vm | virtual memory system |
| x86 | code shared by AMD64 and i386 architectures |