Re: [Qemu-devel] [PATCH 2/3] softmmu: support up to 12 MMU modes

2015-02-20 Thread Richard Henderson
On 02/20/2015 09:57 AM, Paolo Bonzini wrote: > + * TCG will have to generate an operand as large as the distance between > + * tlb_table[0][0] and the tlb_table[NB_MMU_MODES - 1][0].addend. For Nit: the distance is from the start of env, i.e. offsetof(CPUArchState, tlb_table[mem_index][0].adde

[Qemu-devel] [PATCH 2/3] softmmu: support up to 12 MMU modes

2015-02-20 Thread Paolo Bonzini
At 8k per TLB (for 64-bit host or target), 8 or more modes make the TLBs bigger than 64k, and some RISC TCG backends do not like that. On the affected hosts, cut the TLB size in half---there is still a measurable speedup on PPC with the next patch. Signed-off-by: Paolo Bonzini --- include/exec/

[Qemu-devel] [PATCH 2/3] softmmu: support up to 12 MMU modes

2015-02-20 Thread Paolo Bonzini
At 8k per TLB (for 64-bit host or target), 8 or more modes make the TLBs bigger than 64k, and some RISC TCG backends do not like that. On the affected hosts, cut the TLB size in half---there is still a measurable speedup on PPC with the next patch. Signed-off-by: Paolo Bonzini --- include/exec/