David Brazdil | 0f672f6 | 2019-12-10 10:32:29 +0000 | [diff] [blame^] | 1 | .. SPDX-License-Identifier: GPL-2.0 |
| 2 | |
| 3 | ======= |
| 4 | IO-APIC |
| 5 | ======= |
| 6 | |
| 7 | :Author: Ingo Molnar <mingo@kernel.org> |
| 8 | |
| 9 | Most (all) Intel-MP compliant SMP boards have the so-called 'IO-APIC', |
| 10 | which is an enhanced interrupt controller. It enables us to route |
| 11 | hardware interrupts to multiple CPUs, or to CPU groups. Without an |
| 12 | IO-APIC, interrupts from hardware will be delivered only to the |
| 13 | CPU which boots the operating system (usually CPU#0). |
| 14 | |
| 15 | Linux supports all variants of compliant SMP boards, including ones with |
| 16 | multiple IO-APICs. Multiple IO-APICs are used in high-end servers to |
| 17 | distribute IRQ load further. |
| 18 | |
| 19 | There are (a few) known breakages in certain older boards, such bugs are |
| 20 | usually worked around by the kernel. If your MP-compliant SMP board does |
| 21 | not boot Linux, then consult the linux-smp mailing list archives first. |
| 22 | |
| 23 | If your box boots fine with enabled IO-APIC IRQs, then your |
| 24 | /proc/interrupts will look like this one:: |
| 25 | |
| 26 | hell:~> cat /proc/interrupts |
| 27 | CPU0 |
| 28 | 0: 1360293 IO-APIC-edge timer |
| 29 | 1: 4 IO-APIC-edge keyboard |
| 30 | 2: 0 XT-PIC cascade |
| 31 | 13: 1 XT-PIC fpu |
| 32 | 14: 1448 IO-APIC-edge ide0 |
| 33 | 16: 28232 IO-APIC-level Intel EtherExpress Pro 10/100 Ethernet |
| 34 | 17: 51304 IO-APIC-level eth0 |
| 35 | NMI: 0 |
| 36 | ERR: 0 |
| 37 | hell:~> |
| 38 | |
| 39 | Some interrupts are still listed as 'XT PIC', but this is not a problem; |
| 40 | none of those IRQ sources is performance-critical. |
| 41 | |
| 42 | |
| 43 | In the unlikely case that your board does not create a working mp-table, |
| 44 | you can use the pirq= boot parameter to 'hand-construct' IRQ entries. This |
| 45 | is non-trivial though and cannot be automated. One sample /etc/lilo.conf |
| 46 | entry:: |
| 47 | |
| 48 | append="pirq=15,11,10" |
| 49 | |
| 50 | The actual numbers depend on your system, on your PCI cards and on their |
| 51 | PCI slot position. Usually PCI slots are 'daisy chained' before they are |
| 52 | connected to the PCI chipset IRQ routing facility (the incoming PIRQ1-4 |
| 53 | lines):: |
| 54 | |
| 55 | ,-. ,-. ,-. ,-. ,-. |
| 56 | PIRQ4 ----| |-. ,-| |-. ,-| |-. ,-| |--------| | |
| 57 | |S| \ / |S| \ / |S| \ / |S| |S| |
| 58 | PIRQ3 ----|l|-. `/---|l|-. `/---|l|-. `/---|l|--------|l| |
| 59 | |o| \/ |o| \/ |o| \/ |o| |o| |
| 60 | PIRQ2 ----|t|-./`----|t|-./`----|t|-./`----|t|--------|t| |
| 61 | |1| /\ |2| /\ |3| /\ |4| |5| |
| 62 | PIRQ1 ----| |- `----| |- `----| |- `----| |--------| | |
| 63 | `-' `-' `-' `-' `-' |
| 64 | |
| 65 | Every PCI card emits a PCI IRQ, which can be INTA, INTB, INTC or INTD:: |
| 66 | |
| 67 | ,-. |
| 68 | INTD--| | |
| 69 | |S| |
| 70 | INTC--|l| |
| 71 | |o| |
| 72 | INTB--|t| |
| 73 | |x| |
| 74 | INTA--| | |
| 75 | `-' |
| 76 | |
| 77 | These INTA-D PCI IRQs are always 'local to the card', their real meaning |
| 78 | depends on which slot they are in. If you look at the daisy chaining diagram, |
| 79 | a card in slot4, issuing INTA IRQ, it will end up as a signal on PIRQ4 of |
| 80 | the PCI chipset. Most cards issue INTA, this creates optimal distribution |
| 81 | between the PIRQ lines. (distributing IRQ sources properly is not a |
| 82 | necessity, PCI IRQs can be shared at will, but it's a good for performance |
| 83 | to have non shared interrupts). Slot5 should be used for videocards, they |
| 84 | do not use interrupts normally, thus they are not daisy chained either. |
| 85 | |
| 86 | so if you have your SCSI card (IRQ11) in Slot1, Tulip card (IRQ9) in |
| 87 | Slot2, then you'll have to specify this pirq= line:: |
| 88 | |
| 89 | append="pirq=11,9" |
| 90 | |
| 91 | the following script tries to figure out such a default pirq= line from |
| 92 | your PCI configuration:: |
| 93 | |
| 94 | echo -n pirq=; echo `scanpci | grep T_L | cut -c56-` | sed 's/ /,/g' |
| 95 | |
| 96 | note that this script won't work if you have skipped a few slots or if your |
| 97 | board does not do default daisy-chaining. (or the IO-APIC has the PIRQ pins |
| 98 | connected in some strange way). E.g. if in the above case you have your SCSI |
| 99 | card (IRQ11) in Slot3, and have Slot1 empty:: |
| 100 | |
| 101 | append="pirq=0,9,11" |
| 102 | |
| 103 | [value '0' is a generic 'placeholder', reserved for empty (or non-IRQ emitting) |
| 104 | slots.] |
| 105 | |
| 106 | Generally, it's always possible to find out the correct pirq= settings, just |
| 107 | permute all IRQ numbers properly ... it will take some time though. An |
| 108 | 'incorrect' pirq line will cause the booting process to hang, or a device |
| 109 | won't function properly (e.g. if it's inserted as a module). |
| 110 | |
| 111 | If you have 2 PCI buses, then you can use up to 8 pirq values, although such |
| 112 | boards tend to have a good configuration. |
| 113 | |
| 114 | Be prepared that it might happen that you need some strange pirq line:: |
| 115 | |
| 116 | append="pirq=0,0,0,0,0,0,9,11" |
| 117 | |
| 118 | Use smart trial-and-error techniques to find out the correct pirq line ... |
| 119 | |
| 120 | Good luck and mail to linux-smp@vger.kernel.org or |
| 121 | linux-kernel@vger.kernel.org if you have any problems that are not covered |
| 122 | by this document. |
| 123 | |