ppc64/cell: local TLB flush with active SPEs
I'm looking for a clean solution to detect the need for global TLB flush when an mm_struct is only used on one logical PowerPC CPU (PPE) and also mapped with the memory flow controller of an SPE on the Cell CPU.
Normally, we set bits in mm_struct:cpu_vm_mask for each CPU that accesses the mm and then do global flushes instead of local flushes when CPUs other than the currently running one are marked as used in that mask. When an SPE does DMA to that mm, it also gets local TLB entries that are only flushed with a global tlbie broadcast.
The current hack is to always set cpu_vm_mask to all bits set when we map an mm into an SPE to ensure receiving the broadcast, but that is obviously not how it's meant to be used. In particular, it doesn't work in UP configurations where the cpumask contains only one bit.
One solution that might be better could be to introduce a new special flag in addition to cpu_vm_mask for this purpose. We already have a bit field in mm_struct for dumpable, so adding another bit there at least does not waste space for other platforms, and it's likely to be in the same cache line as cpu_vm_mask. However, I'm reluctant to add more bit fields to such a prominent place, because it might encourage other people to add more bit fields or thing that they are accepted coding practice.
Another idea would be to add a new field to mm_context_t, so it stays in the architecture specific code. Again, adding an int here does not waste space because there is currently padding in that place on ppc64.
Or maybe there is a completely different solution.
Suggestions?
Arnd <><
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in the body to [email protected]. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"[email protected]"> [email protected] </a>
Quoted 5 lines · Arnd Bergmann
Another idea would be to add a new field to
mm_context_t, so it stays in the architecture specific code. Again, adding an int here does not waste space because there is currently padding in tha place on ppc64.
mm_context_t sounds like the right place for this to me.
-Andi
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in the body to [email protected]. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"[email protected]"> [email protected] </a>
For reference, the 2.6.3 bring-up kernel always issued global TLBIE. This was a hack, and we very much wanted to improve performance if possible, particularly for the vast majority of PPC applications out there that don't use SPEs.
As long as we are thinking about a proper solution, the whole mm->cpu_vm_mask thing is broken, at least as a selector for local -vs- global TLBIE. The problem, as I see it, is that memory regions can shared among processes (via mmap/shmat), with each task bound to different processors. If we are to continue using a cpumask as selector for TLBIE, then we really need a vma->cpu_vma_mask.
---
Mark Nutter
STI Design Center / IBM
email: [email protected]
voice: 512-838-1612
fax: 512-838-1927
11400 Burnet Road
Mail Stop 906/3003B
Austin, TX 78758
Arnd Bergmann <[email protected]>
10/12/2005 01:03 PM
To: [email protected], [email protected]
cc: Benjamin Herrenschmidt <[email protected]>, Paul
Mackerras <[email protected]>, Mark Nutter/Austin/IBM@IBMUS, Michael Day/Austin/IBM@IBMUS, Ulrich Weigand <[email protected]>
Subject: ppc64/cell: local TLB flush with active SPEs
I'm looking for a clean solution to detect the need for global TLB flush when an mm_struct is only used on one logical PowerPC CPU (PPE) and also mapped with the memory flow controller of an SPE on the Cell CPU.
Normally, we set bits in mm_struct:cpu_vm_mask for each CPU that accesses the mm and then do global flushes instead of local flushes when CPUs other than the currently running one are marked as used in that mask. When an SPE does DMA to that mm, it also gets local TLB entries that are only flushed with a global tlbie broadcast.
The current hack is to always set cpu_vm_mask to all bits set when we map an mm into an SPE to ensure receiving the broadcast, but that is obviously not how it's meant to be used. In particular, it doesn't work in UP configurations where the cpumask contains only one bit.
One solution that might be better could be to introduce a new special flag in addition to cpu_vm_mask for this purpose. We already have a bit field in mm_struct for dumpable, so adding another bit there at least does not waste space for other platforms, and it's likely to be in the same cache line as cpu_vm_mask. However, I'm reluctant to add more bit fields to such a prominent place, because it might encourage other people to add more bit fields or thing that they are accepted coding practice.
Another idea would be to add a new field to mm_context_t, so it stays in the architecture specific code. Again, adding an int here does not waste space because there is currently padding in that place on ppc64.
Or maybe there is a completely different solution.
Suggestions?
Arnd <><
_______________________________________________
Linuxppc64-dev mailing list
[email protected]
https://ozlabs.org/mailman/listinfo/linuxppc64-dev
Quoted 7 lines · Mark Nutter
As long as we are thinking about a proper solution, the whole
mm->cpu_vm_maskthing is broken, at least as a selector for local -vs- global TLBIE. The problem, as I see it, is that memory regions can shared among processes (via mmap/shmat), with each task bound to different processors. If we are to continue using a cpumask as selector for TLBIE, then we really need avma->cpu_vma_mask.
No, because different tasks mapping the same address_space result in distinct virtual (though not necessarily effective) addresses, so the TLB entries are never shared across processes. A TLB entry on ppc64 always maps between the (mm_struct,effective address) tuple and the real address and is local to one CPU or SPU.
If we want to be clever, we could optimize the case where an mm_struct has been used on exactly on CPU (the currently running one) and at least one SPU. In that case, doing a TLBIEL plus a separate flush of each of the MFCs that were used (by writing to their TLB_Invalidate_Entry registers) is probably better than a global TLBIE.
Arnd <><
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in the body to [email protected]. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"[email protected]"> [email protected] </a>