Re: [PATCH 10/15] powerpc/mm: Add hooks for cxl
Michael Neuling mi...@neuling.org writes: From: Ian Munsie imun...@au1.ibm.com This add a hook into tlbie() so that we use global invalidations when there are cxl contexts active. Normally cxl snoops broadcast tlbie. cxl can have TLB entries invalidated via MMIO, but we aren't doing that yet. So for now we are just disabling local tlbies when cxl contexts are active. In future we can make tlbie() local mode smarter so that it invalidates cxl contexts explicitly when it needs to. This also adds a hooks for when SLBs are invalidated to ensure any corresponding SLBs in cxl are also invalidated at the same time. We are not really invalidating cx1 SLB's when we are doing slb_flush_and_rebolt(). May be add some code documentation around to explain when we are invalidating cx1 slb here. ? Signed-off-by: Ian Munsie imun...@au1.ibm.com Signed-off-by: Michael Neuling mi...@neuling.org --- arch/powerpc/mm/hash_native_64.c | 6 +- arch/powerpc/mm/hash_utils_64.c | 3 +++ arch/powerpc/mm/slice.c | 3 +++ 3 files changed, 11 insertions(+), 1 deletion(-) diff --git a/arch/powerpc/mm/hash_native_64.c b/arch/powerpc/mm/hash_native_64.c index afc0a82..ae4962a 100644 --- a/arch/powerpc/mm/hash_native_64.c +++ b/arch/powerpc/mm/hash_native_64.c @@ -29,6 +29,8 @@ #include asm/kexec.h #include asm/ppc-opcode.h +#include misc/cxl.h + #ifdef DEBUG_LOW #define DBG_LOW(fmt...) udbg_printf(fmt) #else @@ -149,9 +151,11 @@ static inline void __tlbiel(unsigned long vpn, int psize, int apsize, int ssize) static inline void tlbie(unsigned long vpn, int psize, int apsize, int ssize, int local) { - unsigned int use_local = local mmu_has_feature(MMU_FTR_TLBIEL); + unsigned int use_local; int lock_tlbie = !mmu_has_feature(MMU_FTR_LOCKLESS_TLBIE); + use_local = local mmu_has_feature(MMU_FTR_TLBIEL) !cxl_ctx_in_use(); + if (use_local) use_local = mmu_psize_defs[psize].tlbiel; if (lock_tlbie !use_local) diff --git a/arch/powerpc/mm/hash_utils_64.c b/arch/powerpc/mm/hash_utils_64.c index 66071af..be40ff7 100644 --- a/arch/powerpc/mm/hash_utils_64.c +++ b/arch/powerpc/mm/hash_utils_64.c @@ -34,6 +34,7 @@ #include linux/signal.h #include linux/memblock.h #include linux/context_tracking.h +#include misc/cxl.h #include asm/processor.h #include asm/pgtable.h @@ -906,6 +907,7 @@ void demote_segment_4k(struct mm_struct *mm, unsigned long addr) #ifdef CONFIG_SPU_BASE spu_flush_all_slbs(mm); #endif + cxl_slbia(mm); if (get_paca_psize(addr) != MMU_PAGE_4K) { get_paca()-context = mm-context; slb_flush_and_rebolt(); @@ -1145,6 +1147,7 @@ int hash_page_mm(struct mm_struct *mm, unsigned long ea, unsigned long access, u #ifdef CONFIG_SPU_BASE spu_flush_all_slbs(mm); #endif + cxl_slbia(mm); } } diff --git a/arch/powerpc/mm/slice.c b/arch/powerpc/mm/slice.c index b0c75cc..4d3a34b 100644 --- a/arch/powerpc/mm/slice.c +++ b/arch/powerpc/mm/slice.c @@ -30,6 +30,7 @@ #include linux/err.h #include linux/spinlock.h #include linux/export.h +#include misc/cxl.h #include asm/mman.h #include asm/mmu.h #include asm/spu.h @@ -235,6 +236,7 @@ static void slice_convert(struct mm_struct *mm, struct slice_mask mask, int psiz #ifdef CONFIG_SPU_BASE spu_flush_all_slbs(mm); #endif + cxl_slbia(mm); } /* @@ -674,6 +676,7 @@ void slice_set_psize(struct mm_struct *mm, unsigned long address, #ifdef CONFIG_SPU_BASE spu_flush_all_slbs(mm); #endif + cxl_slbia(mm); } void slice_set_range_psize(struct mm_struct *mm, unsigned long start, -- 1.9.1 -- To unsubscribe from this list: send the line unsubscribe linux-kernel in the body of a message to majord...@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/ ___ Linuxppc-dev mailing list Linuxppc-dev@lists.ozlabs.org https://lists.ozlabs.org/listinfo/linuxppc-dev
Re: [PATCH 10/15] powerpc/mm: Add hooks for cxl
On Fri, 2014-09-26 at 14:33 +1000, Anton Blanchard wrote: From: Ian Munsie imun...@au1.ibm.com This add a hook into tlbie() so that we use global invalidations when there are cxl contexts active. Normally cxl snoops broadcast tlbie. cxl can have TLB entries invalidated via MMIO, but we aren't doing that yet. So for now we are just disabling local tlbies when cxl contexts are active. In future we can make tlbie() local mode smarter so that it invalidates cxl contexts explicitly when it needs to. This also adds a hooks for when SLBs are invalidated to ensure any corresponding SLBs in cxl are also invalidated at the same time. Signed-off-by: Ian Munsie imun...@au1.ibm.com Signed-off-by: Michael Neuling mi...@neuling.org + use_local = local mmu_has_feature(MMU_FTR_TLBIEL) !cxl_ctx_in_use(); Seems reasonable until we can get the MMIO based optimisation in. Will all CAPI cached translations be invalidated before we finish using a CAPI context? I'm not sure I understand. Can you elaborate? And conversely, could CAPI cache any translations when a context isn't active? The kernel invalidates all translations when the file descriptor is closed. So no, unless the PSL was badly behaving and ignoring the invalidations but if we can't trust the PSL we're screwed. I'm mostly concerned that we can't have a situation where badly behaving userspace could result in a stale translation. We only map what a user processes maps and we tear it down when the process is teared down (on the file descriptor release). So I think we are ok. Unless there's some lazy teardown you're alluding to that I'm missing? spu_flush_all_slbs(mm); #endif + cxl_slbia(mm); spu_flush_all_slbs(mm); #endif + cxl_slbia(mm); spu_flush_all_slbs(mm); #endif + cxl_slbia(mm); spu_flush_all_slbs(mm); #endif + cxl_slbia(mm); Should we combine the SPU vs CXL callouts into something common - perhaps copro_flush_all_slbs()? Sounds good. I'll update. Mikey ___ Linuxppc-dev mailing list Linuxppc-dev@lists.ozlabs.org https://lists.ozlabs.org/listinfo/linuxppc-dev
Re: [PATCH 10/15] powerpc/mm: Add hooks for cxl
Hi Mikey, We only map what a user processes maps and we tear it down when the process is teared down (on the file descriptor release). So I think we are ok. Unless there's some lazy teardown you're alluding to that I'm missing? I was trying to make sure things like the TLB batching code won't allow a tlbie to be postponed until after a CAPI mapping is destroyed. It's been ages since I looked at that part of the mm code. Anton ___ Linuxppc-dev mailing list Linuxppc-dev@lists.ozlabs.org https://lists.ozlabs.org/listinfo/linuxppc-dev
Re: [PATCH 10/15] powerpc/mm: Add hooks for cxl
From: Ian Munsie imun...@au1.ibm.com This add a hook into tlbie() so that we use global invalidations when there are cxl contexts active. Normally cxl snoops broadcast tlbie. cxl can have TLB entries invalidated via MMIO, but we aren't doing that yet. So for now we are just disabling local tlbies when cxl contexts are active. In future we can make tlbie() local mode smarter so that it invalidates cxl contexts explicitly when it needs to. This also adds a hooks for when SLBs are invalidated to ensure any corresponding SLBs in cxl are also invalidated at the same time. Signed-off-by: Ian Munsie imun...@au1.ibm.com Signed-off-by: Michael Neuling mi...@neuling.org + use_local = local mmu_has_feature(MMU_FTR_TLBIEL) !cxl_ctx_in_use(); Seems reasonable until we can get the MMIO based optimisation in. Will all CAPI cached translations be invalidated before we finish using a CAPI context? And conversely, could CAPI cache any translations when a context isn't active? I'm mostly concerned that we can't have a situation where badly behaving userspace could result in a stale translation. spu_flush_all_slbs(mm); #endif + cxl_slbia(mm); spu_flush_all_slbs(mm); #endif + cxl_slbia(mm); spu_flush_all_slbs(mm); #endif + cxl_slbia(mm); spu_flush_all_slbs(mm); #endif + cxl_slbia(mm); Should we combine the SPU vs CXL callouts into something common - perhaps copro_flush_all_slbs()? Anton ___ Linuxppc-dev mailing list Linuxppc-dev@lists.ozlabs.org https://lists.ozlabs.org/listinfo/linuxppc-dev
[PATCH 10/15] powerpc/mm: Add hooks for cxl
From: Ian Munsie imun...@au1.ibm.com This add a hook into tlbie() so that we use global invalidations when there are cxl contexts active. Normally cxl snoops broadcast tlbie. cxl can have TLB entries invalidated via MMIO, but we aren't doing that yet. So for now we are just disabling local tlbies when cxl contexts are active. In future we can make tlbie() local mode smarter so that it invalidates cxl contexts explicitly when it needs to. This also adds a hooks for when SLBs are invalidated to ensure any corresponding SLBs in cxl are also invalidated at the same time. Signed-off-by: Ian Munsie imun...@au1.ibm.com Signed-off-by: Michael Neuling mi...@neuling.org --- arch/powerpc/mm/hash_native_64.c | 6 +- arch/powerpc/mm/hash_utils_64.c | 3 +++ arch/powerpc/mm/slice.c | 3 +++ 3 files changed, 11 insertions(+), 1 deletion(-) diff --git a/arch/powerpc/mm/hash_native_64.c b/arch/powerpc/mm/hash_native_64.c index afc0a82..ae4962a 100644 --- a/arch/powerpc/mm/hash_native_64.c +++ b/arch/powerpc/mm/hash_native_64.c @@ -29,6 +29,8 @@ #include asm/kexec.h #include asm/ppc-opcode.h +#include misc/cxl.h + #ifdef DEBUG_LOW #define DBG_LOW(fmt...) udbg_printf(fmt) #else @@ -149,9 +151,11 @@ static inline void __tlbiel(unsigned long vpn, int psize, int apsize, int ssize) static inline void tlbie(unsigned long vpn, int psize, int apsize, int ssize, int local) { - unsigned int use_local = local mmu_has_feature(MMU_FTR_TLBIEL); + unsigned int use_local; int lock_tlbie = !mmu_has_feature(MMU_FTR_LOCKLESS_TLBIE); + use_local = local mmu_has_feature(MMU_FTR_TLBIEL) !cxl_ctx_in_use(); + if (use_local) use_local = mmu_psize_defs[psize].tlbiel; if (lock_tlbie !use_local) diff --git a/arch/powerpc/mm/hash_utils_64.c b/arch/powerpc/mm/hash_utils_64.c index 66071af..be40ff7 100644 --- a/arch/powerpc/mm/hash_utils_64.c +++ b/arch/powerpc/mm/hash_utils_64.c @@ -34,6 +34,7 @@ #include linux/signal.h #include linux/memblock.h #include linux/context_tracking.h +#include misc/cxl.h #include asm/processor.h #include asm/pgtable.h @@ -906,6 +907,7 @@ void demote_segment_4k(struct mm_struct *mm, unsigned long addr) #ifdef CONFIG_SPU_BASE spu_flush_all_slbs(mm); #endif + cxl_slbia(mm); if (get_paca_psize(addr) != MMU_PAGE_4K) { get_paca()-context = mm-context; slb_flush_and_rebolt(); @@ -1145,6 +1147,7 @@ int hash_page_mm(struct mm_struct *mm, unsigned long ea, unsigned long access, u #ifdef CONFIG_SPU_BASE spu_flush_all_slbs(mm); #endif + cxl_slbia(mm); } } diff --git a/arch/powerpc/mm/slice.c b/arch/powerpc/mm/slice.c index b0c75cc..4d3a34b 100644 --- a/arch/powerpc/mm/slice.c +++ b/arch/powerpc/mm/slice.c @@ -30,6 +30,7 @@ #include linux/err.h #include linux/spinlock.h #include linux/export.h +#include misc/cxl.h #include asm/mman.h #include asm/mmu.h #include asm/spu.h @@ -235,6 +236,7 @@ static void slice_convert(struct mm_struct *mm, struct slice_mask mask, int psiz #ifdef CONFIG_SPU_BASE spu_flush_all_slbs(mm); #endif + cxl_slbia(mm); } /* @@ -674,6 +676,7 @@ void slice_set_psize(struct mm_struct *mm, unsigned long address, #ifdef CONFIG_SPU_BASE spu_flush_all_slbs(mm); #endif + cxl_slbia(mm); } void slice_set_range_psize(struct mm_struct *mm, unsigned long start, -- 1.9.1 ___ Linuxppc-dev mailing list Linuxppc-dev@lists.ozlabs.org https://lists.ozlabs.org/listinfo/linuxppc-dev