Message ID | 1375788674-13140-7-git-send-email-Bharat.Bhushan@freescale.com (mailing list archive) |
---|---|
State | Not Applicable |
Headers | show |
On Tue, 2013-08-06 at 17:01 +0530, Bharat Bhushan wrote: > @@ -449,7 +446,16 @@ static inline int kvmppc_e500_shadow_map(struct kvmppc_vcpu_e500 *vcpu_e500, > gvaddr &= ~((tsize_pages << PAGE_SHIFT) - 1); > } > > - kvmppc_e500_ref_setup(ref, gtlbe, pfn); > + pgdir = vcpu_e500->vcpu.arch.pgdir; > + ptep = lookup_linux_pte(pgdir, hva, &tsize_pages); > + if (pte_present(*ptep)) { > + wimg = (pte_val(*ptep) >> PTE_WIMGE_SHIFT) & MAS2_WIMGE_MASK; > + } else { > + printk(KERN_ERR "pte not present: gfn %lx, pfn %lx\n", > + (long)gfn, pfn); > + return -EINVAL; Don't let the guest spam the host kernel console by repeatedly accessing bad mappings (even if it requires host userspace to assist by pointing a memslot at a bad hva). This should at most be printk_ratelimited(), and probably just pr_debug(). It should also have __func__ context. Also, I don't see the return value getting checked (the immediate callers check it and propogate the error, but kvmppc_mmu_map() doesn't). We want to send a machine check to the guest if this happens (or possibly exit to userspace since it indicates a bad memslot, not just a guest bug). We don't want to just silently retry over and over. Otherwise, this series looks good to me. -Scott
> -----Original Message----- > From: Wood Scott-B07421 > Sent: Saturday, August 10, 2013 6:35 AM > To: Bhushan Bharat-R65777 > Cc: benh@kernel.crashing.org; agraf@suse.de; paulus@samba.org; > kvm@vger.kernel.org; kvm-ppc@vger.kernel.org; linuxppc-dev@lists.ozlabs.org; > Bhushan Bharat-R65777 > Subject: Re: [PATCH 6/6 v3] kvm: powerpc: use caching attributes as per linux > pte > > On Tue, 2013-08-06 at 17:01 +0530, Bharat Bhushan wrote: > > @@ -449,7 +446,16 @@ static inline int kvmppc_e500_shadow_map(struct > kvmppc_vcpu_e500 *vcpu_e500, > > gvaddr &= ~((tsize_pages << PAGE_SHIFT) - 1); > > } > > > > - kvmppc_e500_ref_setup(ref, gtlbe, pfn); > > + pgdir = vcpu_e500->vcpu.arch.pgdir; > > + ptep = lookup_linux_pte(pgdir, hva, &tsize_pages); > > + if (pte_present(*ptep)) { > > + wimg = (pte_val(*ptep) >> PTE_WIMGE_SHIFT) & MAS2_WIMGE_MASK; > > + } else { > > + printk(KERN_ERR "pte not present: gfn %lx, pfn %lx\n", > > + (long)gfn, pfn); > > + return -EINVAL; > > Don't let the guest spam the host kernel console by repeatedly accessing bad > mappings (even if it requires host userspace to assist by pointing a memslot at > a bad hva). This should at most be printk_ratelimited(), and probably just > pr_debug(). It should also have __func__ context. Very good point, I will make this printk_ratelimited() in this patch. And convert this and other error prints to pr_debug() when we will send machine check on error in this flow. > > Also, I don't see the return value getting checked (the immediate callers check > it and propogate the error, but kvmppc_mmu_map() doesn't). > We want to send a machine check to the guest if this happens (or possibly exit > to userspace since it indicates a bad memslot, not just a guest bug). We don't > want to just silently retry over and over. I completely agree with you, but this was something already missing (error return by this function is nothing new added in this patch), So I would like to take that separately. > > Otherwise, this series looks good to me. Thank you. :) -Bharat > > -Scott >
diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h index 3328353..583d405 100644 --- a/arch/powerpc/include/asm/kvm_host.h +++ b/arch/powerpc/include/asm/kvm_host.h @@ -535,6 +535,7 @@ struct kvm_vcpu_arch { #endif gpa_t paddr_accessed; gva_t vaddr_accessed; + pgd_t *pgdir; u8 io_gpr; /* GPR used as IO source/target */ u8 mmio_is_bigendian; @@ -592,7 +593,6 @@ struct kvm_vcpu_arch { struct list_head run_list; struct task_struct *run_task; struct kvm_run *kvm_run; - pgd_t *pgdir; spinlock_t vpa_update_lock; struct kvmppc_vpa vpa; diff --git a/arch/powerpc/kvm/booke.c b/arch/powerpc/kvm/booke.c index 17722d8..0d96d50 100644 --- a/arch/powerpc/kvm/booke.c +++ b/arch/powerpc/kvm/booke.c @@ -696,8 +696,8 @@ int kvmppc_vcpu_run(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu) kvmppc_load_guest_fp(vcpu); #endif + vcpu->arch.pgdir = current->mm->pgd; kvmppc_fix_ee_before_entry(); - ret = __kvmppc_vcpu_run(kvm_run, vcpu); /* No need for kvm_guest_exit. It's done in handle_exit. diff --git a/arch/powerpc/kvm/e500.h b/arch/powerpc/kvm/e500.h index 4fd9650..fc4b2f6 100644 --- a/arch/powerpc/kvm/e500.h +++ b/arch/powerpc/kvm/e500.h @@ -31,11 +31,13 @@ enum vcpu_ftr { #define E500_TLB_NUM 2 /* entry is mapped somewhere in host TLB */ -#define E500_TLB_VALID (1 << 0) +#define E500_TLB_VALID (1 << 31) /* TLB1 entry is mapped by host TLB1, tracked by bitmaps */ -#define E500_TLB_BITMAP (1 << 1) +#define E500_TLB_BITMAP (1 << 30) /* TLB1 entry is mapped by host TLB0 */ -#define E500_TLB_TLB0 (1 << 2) +#define E500_TLB_TLB0 (1 << 29) +/* Lower 5 bits have WIMGE value */ +#define E500_TLB_WIMGE_MASK (0x1f) struct tlbe_ref { pfn_t pfn; /* valid only for TLB0, except briefly */ diff --git a/arch/powerpc/kvm/e500_mmu_host.c b/arch/powerpc/kvm/e500_mmu_host.c index 1c6a9d7..001a2b0 100644 --- a/arch/powerpc/kvm/e500_mmu_host.c +++ b/arch/powerpc/kvm/e500_mmu_host.c @@ -64,15 +64,6 @@ static inline u32 e500_shadow_mas3_attrib(u32 mas3, int usermode) return mas3; } -static inline u32 e500_shadow_mas2_attrib(u32 mas2, int usermode) -{ -#ifdef CONFIG_SMP - return (mas2 & MAS2_ATTRIB_MASK) | MAS2_M; -#else - return mas2 & MAS2_ATTRIB_MASK; -#endif -} - /* * writing shadow tlb entry to host TLB */ @@ -248,10 +239,12 @@ static inline int tlbe_is_writable(struct kvm_book3e_206_tlb_entry *tlbe) static inline void kvmppc_e500_ref_setup(struct tlbe_ref *ref, struct kvm_book3e_206_tlb_entry *gtlbe, - pfn_t pfn) + pfn_t pfn, int wimg) { ref->pfn = pfn; ref->flags |= E500_TLB_VALID; + /* Use guest supplied MAS2_G and MAS2_E */ + ref->flags |= (gtlbe->mas2 & MAS2_ATTRIB_MASK) | wimg; if (tlbe_is_writable(gtlbe)) kvm_set_pfn_dirty(pfn); @@ -312,8 +305,7 @@ static void kvmppc_e500_setup_stlbe( /* Force IPROT=0 for all guest mappings. */ stlbe->mas1 = MAS1_TSIZE(tsize) | get_tlb_sts(gtlbe) | MAS1_VALID; - stlbe->mas2 = (gvaddr & MAS2_EPN) | - e500_shadow_mas2_attrib(gtlbe->mas2, pr); + stlbe->mas2 = (gvaddr & MAS2_EPN) | (ref->flags & E500_TLB_WIMGE_MASK); stlbe->mas7_3 = ((u64)pfn << PAGE_SHIFT) | e500_shadow_mas3_attrib(gtlbe->mas7_3, pr); @@ -332,6 +324,10 @@ static inline int kvmppc_e500_shadow_map(struct kvmppc_vcpu_e500 *vcpu_e500, unsigned long hva; int pfnmap = 0; int tsize = BOOK3E_PAGESZ_4K; + unsigned long tsize_pages = 0; + pte_t *ptep; + int wimg = 0; + pgd_t *pgdir; /* * Translate guest physical to true physical, acquiring @@ -394,7 +390,7 @@ static inline int kvmppc_e500_shadow_map(struct kvmppc_vcpu_e500 *vcpu_e500, */ for (; tsize > BOOK3E_PAGESZ_4K; tsize -= 2) { - unsigned long gfn_start, gfn_end, tsize_pages; + unsigned long gfn_start, gfn_end; tsize_pages = 1 << (tsize - 2); gfn_start = gfn & ~(tsize_pages - 1); @@ -436,7 +432,8 @@ static inline int kvmppc_e500_shadow_map(struct kvmppc_vcpu_e500 *vcpu_e500, } if (likely(!pfnmap)) { - unsigned long tsize_pages = 1 << (tsize + 10 - PAGE_SHIFT); + tsize_pages = 1 << (tsize + 10 - PAGE_SHIFT); + pfn = gfn_to_pfn_memslot(slot, gfn); if (is_error_noslot_pfn(pfn)) { printk(KERN_ERR "Couldn't get real page for gfn %lx!\n", @@ -449,7 +446,16 @@ static inline int kvmppc_e500_shadow_map(struct kvmppc_vcpu_e500 *vcpu_e500, gvaddr &= ~((tsize_pages << PAGE_SHIFT) - 1); } - kvmppc_e500_ref_setup(ref, gtlbe, pfn); + pgdir = vcpu_e500->vcpu.arch.pgdir; + ptep = lookup_linux_pte(pgdir, hva, &tsize_pages); + if (pte_present(*ptep)) { + wimg = (pte_val(*ptep) >> PTE_WIMGE_SHIFT) & MAS2_WIMGE_MASK; + } else { + printk(KERN_ERR "pte not present: gfn %lx, pfn %lx\n", + (long)gfn, pfn); + return -EINVAL; + } + kvmppc_e500_ref_setup(ref, gtlbe, pfn, wimg); kvmppc_e500_setup_stlbe(&vcpu_e500->vcpu, gtlbe, tsize, ref, gvaddr, stlbe);
KVM uses same WIM tlb attributes as the corresponding qemu pte. For this we now search the linux pte for the requested page and get these cache caching/coherency attributes from pte. Signed-off-by: Bharat Bhushan <bharat.bhushan@freescale.com> --- v2->v3 - setting pgdir before kvmppc_fix_ee_before_entry() on vcpu_run - Aligned as per changes in patch 5/6 - setting WIMG for pfnmap pages also v1->v2 - Use Linux pte for wimge rather than RAM/no-RAM mechanism arch/powerpc/include/asm/kvm_host.h | 2 +- arch/powerpc/kvm/booke.c | 2 +- arch/powerpc/kvm/e500.h | 8 ++++-- arch/powerpc/kvm/e500_mmu_host.c | 36 ++++++++++++++++++++-------------- 4 files changed, 28 insertions(+), 20 deletions(-)