From: Olof Johansson Date: Sat, 3 Sep 2005 22:55:59 +0000 (-0700) Subject: [PATCH] ppc64: Add VMX save flag to VPA X-Git-Tag: v2.6.14-rc1~897 X-Git-Url: https://err.no/cgi-bin/gitweb.cgi?a=commitdiff_plain;h=233ccd0d0452682edb51725410e0f8c0384e8b34;p=linux-2.6 [PATCH] ppc64: Add VMX save flag to VPA We need to indicate to the hypervisor that it needs to save our VMX registers when switching partitions on a shared-processor system, just as it needs to for FP and PMC registers. This could be made to be on-demand when VMX is used, but we don't do that for FP nor PMC right now either so let's not overcomplicate things. Signed-off-by: Olof Johansson Acked-by: Paul Mackerras Cc: Anton Blanchard Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- diff --git a/arch/ppc64/kernel/pSeries_lpar.c b/arch/ppc64/kernel/pSeries_lpar.c index 0a3ddc9227..a1d5fdfea4 100644 --- a/arch/ppc64/kernel/pSeries_lpar.c +++ b/arch/ppc64/kernel/pSeries_lpar.c @@ -266,6 +266,10 @@ void vpa_init(int cpu) /* Register the Virtual Processor Area (VPA) */ flags = 1UL << (63 - 18); + + if (cpu_has_feature(CPU_FTR_ALTIVEC)) + paca[cpu].lppaca.vmxregs_in_use = 1; + ret = register_vpa(flags, hwcpu, __pa(vpa)); if (ret) diff --git a/arch/ppc64/kernel/pacaData.c b/arch/ppc64/kernel/pacaData.c index 6182a2cd90..33a2d8db3f 100644 --- a/arch/ppc64/kernel/pacaData.c +++ b/arch/ppc64/kernel/pacaData.c @@ -59,6 +59,7 @@ extern unsigned long __toc_start; .fpregs_in_use = 1, \ .end_of_quantum = 0xfffffffffffffffful, \ .slb_count = 64, \ + .vmxregs_in_use = 0, \ }, \ #ifdef CONFIG_PPC_ISERIES diff --git a/include/asm-ppc64/lppaca.h b/include/asm-ppc64/lppaca.h index 70766b5f26..9e2a6c0649 100644 --- a/include/asm-ppc64/lppaca.h +++ b/include/asm-ppc64/lppaca.h @@ -108,7 +108,7 @@ struct lppaca volatile u32 virtual_decr; // Virtual DECR for shared procsx78-x7B u16 slb_count; // # of SLBs to maintain x7C-x7D u8 idle; // Indicate OS is idle x7E - u8 reserved5; // Reserved x7F + u8 vmxregs_in_use; // VMX registers in use x7F //=============================================================================