Re: [PATCH 14/27] Add book3s_64 specific opcode emulation

2009-11-04 Thread Arnd Bergmann
On Tuesday 03 November 2009, Benjamin Herrenschmidt wrote: (Though glibc can be nasty, afaik it might load up optimized variants of some routines with hard wired cache line sizes based on the CPU type) You can also get application with hand-coded cache optimizations that are even harder, if not

Re: [PATCH 14/27] Add book3s_64 specific opcode emulation

2009-11-04 Thread Benjamin Herrenschmidt
On Wed, 2009-11-04 at 09:43 +0100, Arnd Bergmann wrote: On Tuesday 03 November 2009, Benjamin Herrenschmidt wrote: (Though glibc can be nasty, afaik it might load up optimized variants of some routines with hard wired cache line sizes based on the CPU type) You can also get application

Re: [PATCH 14/27] Add book3s_64 specific opcode emulation

2009-11-04 Thread Alexander Graf
On 04.11.2009, at 09:47, Benjamin Herrenschmidt wrote: On Wed, 2009-11-04 at 09:43 +0100, Arnd Bergmann wrote: On Tuesday 03 November 2009, Benjamin Herrenschmidt wrote: (Though glibc can be nasty, afaik it might load up optimized variants of some routines with hard wired cache line sizes

Re: [PATCH 14/27] Add book3s_64 specific opcode emulation

2009-11-04 Thread Segher Boessenkool
+ case OP_31_XOP_EIOIO: + break; Have you always executed an eieio or sync when you get here, or do you just not allow direct access to I/O devices? Other context synchronising insns are not enough, they do not broadcast on the bus. There is no device

Re: [PATCH 14/27] Add book3s_64 specific opcode emulation

2009-11-03 Thread Segher Boessenkool
Nice patchset. Some comments on the emulation part: +#define OP_31_XOP_EIOIO854 You mean EIEIO. + case 19: + switch (get_xop(inst)) { + case OP_19_XOP_RFID: + case OP_19_XOP_RFI: + vcpu-arch.pc =

Re: [PATCH 14/27] Add book3s_64 specific opcode emulation

2009-11-03 Thread Alexander Graf
On 03.11.2009, at 09:47, Segher Boessenkool wrote: Nice patchset. Some comments on the emulation part: Cool, thanks for looking though them! +#define OP_31_XOP_EIOIO854 You mean EIEIO. Probably, yeah. + case 19: + switch (get_xop(inst)) { +

[PATCH 14/27] Add book3s_64 specific opcode emulation

2009-10-30 Thread Alexander Graf
There are generic parts of PowerPC that can be shared across all implementations and specific parts that only apply to BookE or desktop PPCs. This patch adds emulation for desktop specific opcodes that don't apply to BookE CPUs. Signed-off-by: Alexander Graf ag...@suse.de --- v5 - v6: - //

[PATCH 14/27] Add book3s_64 specific opcode emulation

2009-10-30 Thread Alexander Graf
There are generic parts of PowerPC that can be shared across all implementations and specific parts that only apply to BookE or desktop PPCs. This patch adds emulation for desktop specific opcodes that don't apply to BookE CPUs. Signed-off-by: Alexander Graf ag...@suse.de --- v5 - v6: - //

[PATCH 14/27] Add book3s_64 specific opcode emulation

2009-10-21 Thread Alexander Graf
There are generic parts of PowerPC that can be shared across all implementations and specific parts that only apply to BookE or desktop PPCs. This patch adds emulation for desktop specific opcodes that don't apply to BookE CPUs. Signed-off-by: Alexander Graf ag...@suse.de ---

[PATCH 14/27] Add book3s_64 specific opcode emulation

2009-10-21 Thread Alexander Graf
There are generic parts of PowerPC that can be shared across all implementations and specific parts that only apply to BookE or desktop PPCs. This patch adds emulation for desktop specific opcodes that don't apply to BookE CPUs. Signed-off-by: Alexander Graf ag...@suse.de ---