search for: arch_leave_lazy_mmu_mode

...a/drivers/xen/grant-table.c +++ b/drivers/xen/grant-table.c @@ -930,9 +930,10 @@ int gnttab_map_refs(struct gnttab_map_grant_ref *map_ops, ret = m2p_add_override(mfn, pages[i], kmap_ops ? &kmap_ops[i] : NULL); if (ret) - return ret; + goto out; } + out: if (lazy) arch_leave_lazy_mmu_mode(); @@ -969,9 +970,10 @@ int gnttab_unmap_refs(struct gnttab_unmap_grant_ref *unmap_ops, ret = m2p_remove_override(pages[i], kmap_ops ? &kmap_ops[i] : NULL); if (ret) - return ret; + goto out; } + out: if (lazy) arch_leave_lazy_mmu_mode(); -- 1.7.9.5

...calls together is a great performance benefit because it means issuing one hypercall total rather than two hypercall per page. If paravirt_lazy_mode is set PARAVIRT_LAZY_MMU, all these calls are going to be batched together, otherwise they are issued one at a time. Adding arch_enter_lazy_mmu_mode/arch_leave_lazy_mmu_mode around the m2p_add/remove_override calls forces paravirt_lazy_mode to PARAVIRT_LAZY_MMU, therefore makes sure that they are always batched. Changes in v3: - do not call arch_enter/leave_lazy_mmu_mode in xen_blkbk_unmap, that can be called in interrupt context. Signed-off-by: Stefano Stabellini...

...which may be modified. In the UP + * case, this is required so that preemption is disabled, and in the SMP case, + * it must synchronize the delayed page table writes properly on other CPUs. + */ +#ifndef __HAVE_ARCH_ENTER_LAZY_MMU_MODE +#define arch_enter_lazy_mmu_mode() do {} while (0) +#define arch_leave_lazy_mmu_mode() do {} while (0) +#endif + +/* * When walking page tables, get the address of the next boundary, * or the end address of the range if that comes earlier. Although no * vma end wraps to 0, rounded up __boundary may wrap to 0 throughout. =======================================================...

...[i], mfn); + pages[i]->index = pfn_to_mfn(pfn); + + if (unlikely(!set_phys_to_machine(pfn, FOREIGN_FRAME(mfn)))) { + ret = -ENOMEM; + goto out; + } + + if (kmap_ops) { + ret = m2p_add_override(mfn, pages[i], &kmap_ops[i]); + if (ret) + goto out; + } + } + +out: + if (lazy) + arch_leave_lazy_mmu_mode(); + + return ret; +} +EXPORT_SYMBOL_GPL(set_foreign_p2m_mapping); + /* Add an MFN override for a particular page */ int m2p_add_override(unsigned long mfn, struct page *page, struct gnttab_map_grant_ref *kmap_op) @@ -899,13 +958,6 @@ int m2p_add_override(unsigned long mfn, struct page *page,...

...[i], mfn); + pages[i]->index = pfn_to_mfn(pfn); + + if (unlikely(!set_phys_to_machine(pfn, FOREIGN_FRAME(mfn)))) { + ret = -ENOMEM; + goto out; + } + + if (kmap_ops) { + ret = m2p_add_override(mfn, pages[i], &kmap_ops[i]); + if (ret) + goto out; + } + } + +out: + if (lazy) + arch_leave_lazy_mmu_mode(); + + return ret; +} +EXPORT_SYMBOL_GPL(set_foreign_p2m_mapping); + /* Add an MFN override for a particular page */ int m2p_add_override(unsigned long mfn, struct page *page, struct gnttab_map_grant_ref *kmap_op) @@ -899,13 +958,6 @@ int m2p_add_override(unsigned long mfn, struct page *page,...

...a relatively minor corner case. It seems to me that it would be better to define kpte_clear_flush as: #define kpte_clear_flush(ptep, vaddr) \ do { \ arch_enter_lazy_mmu_mode(); \ pte_clear(&init_mm, vaddr, ptep); \ __flush_tlb_one(vaddr); \ arch_leave_lazy_mmu_mode(); \ } while (0) and take advantage of mmu batching to make this operation efficient. But I'm not sure if this is safe. (Also, kmap_atomic could use set_pte_at rather than set_pte.) What do you think? J

...a relatively minor corner case. It seems to me that it would be better to define kpte_clear_flush as: #define kpte_clear_flush(ptep, vaddr) \ do { \ arch_enter_lazy_mmu_mode(); \ pte_clear(&init_mm, vaddr, ptep); \ __flush_tlb_one(vaddr); \ arch_leave_lazy_mmu_mode(); \ } while (0) and take advantage of mmu batching to make this operation efficient. But I'm not sure if this is safe. (Also, kmap_atomic could use set_pte_at rather than set_pte.) What do you think? J

...static void flush_lazy(enum paravirt_lazy_mode mode, struct pv_lazy_ops *ops) +{ + if (x86_read_percpu(paravirt_lazy_mode) == mode) { + (*ops->leave)(); + (*ops->enter)(); + } +} + +void arch_enter_lazy_mmu_mode(void) +{ + enter_lazy(PARAVIRT_LAZY_MMU, &pv_mmu_ops.lazy_mode); +} + +void arch_leave_lazy_mmu_mode(void) +{ + leave_lazy(PARAVIRT_LAZY_MMU, &pv_mmu_ops.lazy_mode); +} + +void arch_flush_lazy_mmu_mode(void) +{ + flush_lazy(PARAVIRT_LAZY_MMU, &pv_mmu_ops.lazy_mode); +} + +void arch_enter_lazy_cpu_mode(void) +{ + enter_lazy(PARAVIRT_LAZY_CPU, &pv_cpu_ops.lazy_mode); +} + +void arch_leav...

...static void flush_lazy(enum paravirt_lazy_mode mode, struct pv_lazy_ops *ops) +{ + if (x86_read_percpu(paravirt_lazy_mode) == mode) { + (*ops->leave)(); + (*ops->enter)(); + } +} + +void arch_enter_lazy_mmu_mode(void) +{ + enter_lazy(PARAVIRT_LAZY_MMU, &pv_mmu_ops.lazy_mode); +} + +void arch_leave_lazy_mmu_mode(void) +{ + leave_lazy(PARAVIRT_LAZY_MMU, &pv_mmu_ops.lazy_mode); +} + +void arch_flush_lazy_mmu_mode(void) +{ + flush_lazy(PARAVIRT_LAZY_MMU, &pv_mmu_ops.lazy_mode); +} + +void arch_enter_lazy_cpu_mode(void) +{ + enter_lazy(PARAVIRT_LAZY_CPU, &pv_cpu_ops.lazy_mode); +} + +void arch_leav...

[ REPOST: Apologies to anyone who has seen this before. It didn't make it onto any of the lists it should have. -J ] Hi Andrew, This series of patches lays the basic ground work for the paravirtualized kernel patches coming later on. I think this lot is ready for the rough-and-tumble world of the -mm tree. For the most part, these patches do nothing or very little. The patches should

[ REPOST: Apologies to anyone who has seen this before. It didn't make it onto any of the lists it should have. -J ] Hi Andrew, This series of patches lays the basic ground work for the paravirtualized kernel patches coming later on. I think this lot is ready for the rough-and-tumble world of the -mm tree. For the most part, these patches do nothing or very little. The patches should

...{ + arch_leave_lazy_cpu_mode(); + arch_enter_lazy_cpu_mode(); + } } #define __HAVE_ARCH_ENTER_LAZY_MMU_MODE static inline void arch_enter_lazy_mmu_mode(void) { - PVOP_VCALL1(pv_misc_ops.set_lazy_mode, PARAVIRT_LAZY_MMU); + PVOP_VCALL0(pv_mmu_ops.lazy_mode.enter); } static inline void arch_leave_lazy_mmu_mode(void) { - PVOP_VCALL1(pv_misc_ops.set_lazy_mode, PARAVIRT_LAZY_NONE); + PVOP_VCALL0(pv_mmu_ops.lazy_mode.leave); } static inline void arch_flush_lazy_mmu_mode(void) { - PVOP_VCALL1(pv_misc_ops.set_lazy_mode, PARAVIRT_LAZY_FLUSH); + if (unlikely(paravirt_get_lazy_mode() == PARAVIRT_LAZY_MMU))...

...{ + arch_leave_lazy_cpu_mode(); + arch_enter_lazy_cpu_mode(); + } } #define __HAVE_ARCH_ENTER_LAZY_MMU_MODE static inline void arch_enter_lazy_mmu_mode(void) { - PVOP_VCALL1(pv_misc_ops.set_lazy_mode, PARAVIRT_LAZY_MMU); + PVOP_VCALL0(pv_mmu_ops.lazy_mode.enter); } static inline void arch_leave_lazy_mmu_mode(void) { - PVOP_VCALL1(pv_misc_ops.set_lazy_mode, PARAVIRT_LAZY_NONE); + PVOP_VCALL0(pv_mmu_ops.lazy_mode.leave); } static inline void arch_flush_lazy_mmu_mode(void) { - PVOP_VCALL1(pv_misc_ops.set_lazy_mode, PARAVIRT_LAZY_FLUSH); + if (unlikely(paravirt_get_lazy_mode() == PARAVIRT_LAZY_MMU))...

At OLS I gave a talk on some of the Xen scalability inhibitors, and one of these was writable page tables. We went over why the feature does not scale, but just as important, we found that the uniprocessor case does not provide any advantage either. These tests were done on x86_64, so I wanted to run the 1-way test on 32 bit to show the same problem. So, I have run with writable PTs and

...+#define arch_enter_lazy_cpu_mode() paravirt_ops.set_lazy_mode(PARAVIRT_LAZY_CPU) +#define arch_leave_lazy_cpu_mode() paravirt_ops.set_lazy_mode(PARAVIRT_LAZY_NONE) + +#define __HAVE_ARCH_ENTER_LAZY_MMU_MODE +#define arch_enter_lazy_mmu_mode() paravirt_ops.set_lazy_mode(PARAVIRT_LAZY_MMU) +#define arch_leave_lazy_mmu_mode() paravirt_ops.set_lazy_mode(PARAVIRT_LAZY_NONE) + /* These all sit in the .parainstructions section to tell us what to patch. */ struct paravirt_patch { u8 *instr; /* original instructions */ diff -r 01f2e46c1416 kernel/sched.c --- a/kernel/sched.c Thu Dec 14 14:26:24 2006 -0800 +++ b/kernel...

...+#define arch_enter_lazy_cpu_mode() paravirt_ops.set_lazy_mode(PARAVIRT_LAZY_CPU) +#define arch_leave_lazy_cpu_mode() paravirt_ops.set_lazy_mode(PARAVIRT_LAZY_NONE) + +#define __HAVE_ARCH_ENTER_LAZY_MMU_MODE +#define arch_enter_lazy_mmu_mode() paravirt_ops.set_lazy_mode(PARAVIRT_LAZY_MMU) +#define arch_leave_lazy_mmu_mode() paravirt_ops.set_lazy_mode(PARAVIRT_LAZY_NONE) + /* These all sit in the .parainstructions section to tell us what to patch. */ struct paravirt_patch { u8 *instr; /* original instructions */ diff -r 01f2e46c1416 kernel/sched.c --- a/kernel/sched.c Thu Dec 14 14:26:24 2006 -0800 +++ b/kernel...

...+#define arch_enter_lazy_cpu_mode() paravirt_ops.set_lazy_mode(PARAVIRT_LAZY_CPU) +#define arch_leave_lazy_cpu_mode() paravirt_ops.set_lazy_mode(PARAVIRT_LAZY_NONE) + +#define __HAVE_ARCH_ENTER_LAZY_MMU_MODE +#define arch_enter_lazy_mmu_mode() paravirt_ops.set_lazy_mode(PARAVIRT_LAZY_MMU) +#define arch_leave_lazy_mmu_mode() paravirt_ops.set_lazy_mode(PARAVIRT_LAZY_NONE) + /* These all sit in the .parainstructions section to tell us what to patch. */ struct paravirt_patch { u8 *instr; /* original instructions */ diff -r 320f0d4d2280 kernel/sched.c --- a/kernel/sched.c Tue Dec 12 13:50:50 2006 -0800 +++ b/kernel...

...+#define arch_enter_lazy_cpu_mode() paravirt_ops.set_lazy_mode(PARAVIRT_LAZY_CPU) +#define arch_leave_lazy_cpu_mode() paravirt_ops.set_lazy_mode(PARAVIRT_LAZY_NONE) + +#define __HAVE_ARCH_ENTER_LAZY_MMU_MODE +#define arch_enter_lazy_mmu_mode() paravirt_ops.set_lazy_mode(PARAVIRT_LAZY_MMU) +#define arch_leave_lazy_mmu_mode() paravirt_ops.set_lazy_mode(PARAVIRT_LAZY_NONE) + /* These all sit in the .parainstructions section to tell us what to patch. */ struct paravirt_patch { u8 *instr; /* original instructions */ diff -r 320f0d4d2280 kernel/sched.c --- a/kernel/sched.c Tue Dec 12 13:50:50 2006 -0800 +++ b/kernel...

Today paravirtualization is a all-or-nothing game: either a kernel is compiled with no paravirtualization support at all, or it is supporting paravirtualized environments like Xen pv-guests or lguest additionally to some paravirtualized tuning for KVM, Hyperv, VMWare or Xen HVM-guests. As support of pv-guests requires quite intrusive pv-hooks (e.g. all access functions to page table entries,

Today paravirtualization is a all-or-nothing game: either a kernel is compiled with no paravirtualization support at all, or it is supporting paravirtualized environments like Xen pv-guests or lguest additionally to some paravirtualized tuning for KVM, Hyperv, VMWare or Xen HVM-guests. As support of pv-guests requires quite intrusive pv-hooks (e.g. all access functions to page table entries,