Re: [PATCH RFC v8 02/56] KVM: x86: Add 'update_mem_attr' x86 op

[Michael Roth <michael.roth@amd.com>]

On Fri, Mar 17, 2023 at 09:56:11PM -0700, Isaku Yamahata wrote:
> On Mon, Feb 20, 2023 at 12:37:53PM -0600,
> Michael Roth <michael.roth@amd.com> wrote:
> 
> > This callback will do any platform-specific handling needed for
> > converting pages between shared/private.
> > 
> > Signed-off-by: Michael Roth <michael.roth@amd.com>
> > ---
> >  arch/x86/include/asm/kvm-x86-ops.h |  1 +
> >  arch/x86/include/asm/kvm_host.h    |  2 ++
> >  arch/x86/kvm/mmu/mmu.c             | 13 +++++++++++++
> >  include/linux/kvm_host.h           |  4 ++++
> >  virt/kvm/kvm_main.c                | 29 +++++++++++++++++++++++++++++
> >  5 files changed, 49 insertions(+)
> > 
> > diff --git a/arch/x86/include/asm/kvm-x86-ops.h b/arch/x86/include/asm/kvm-x86-ops.h
> > index 72183da010b8..a8aaf532c2ab 100644
> > --- a/arch/x86/include/asm/kvm-x86-ops.h
> > +++ b/arch/x86/include/asm/kvm-x86-ops.h
> > @@ -132,6 +132,7 @@ KVM_X86_OP(complete_emulated_msr)
> >  KVM_X86_OP(vcpu_deliver_sipi_vector)
> >  KVM_X86_OP_OPTIONAL_RET0(vcpu_get_apicv_inhibit_reasons);
> >  KVM_X86_OP_OPTIONAL_RET0(fault_is_private);
> > +KVM_X86_OP_OPTIONAL_RET0(update_mem_attr)
> >  
> >  #undef KVM_X86_OP
> >  #undef KVM_X86_OP_OPTIONAL
> > diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
> > index f856d689dda0..2da3fb2d5d1b 100644
> > --- a/arch/x86/include/asm/kvm_host.h
> > +++ b/arch/x86/include/asm/kvm_host.h
> > @@ -1644,6 +1644,8 @@ struct kvm_x86_ops {
> >  	void (*load_mmu_pgd)(struct kvm_vcpu *vcpu, hpa_t root_hpa,
> >  			     int root_level);
> >  	bool (*fault_is_private)(struct kvm *kvm, gpa_t gpa, u64 error_code, bool *private_fault);
> > +	int (*update_mem_attr)(struct kvm_memory_slot *slot, unsigned int attr,
> > +			       gfn_t start, gfn_t end);
> >  
> >  	bool (*has_wbinvd_exit)(void);
> >  
> > diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
> > index fb3f34b7391c..053bd77bbf52 100644
> > --- a/arch/x86/kvm/mmu/mmu.c
> > +++ b/arch/x86/kvm/mmu/mmu.c
> > @@ -7251,4 +7251,17 @@ void kvm_arch_set_memory_attributes(struct kvm *kvm,
> >  		linfo_update_mixed(gfn, slot, level, mixed);
> >  	}
> >  }
> > +
> > +void kvm_arch_post_set_memory_attributes(struct kvm *kvm,
> > +					 struct kvm_memory_slot *slot,
> > +					 unsigned long attrs,
> > +					 gfn_t start, gfn_t end)
> > +{
> > +	int ret;
> > +
> > +	ret = static_call(kvm_x86_update_mem_attr)(slot, attrs, start, end);
> > +	if (ret)
> > +		pr_warn_ratelimited("Failed to update GFN range 0x%llx-0x%llx with attributes 0x%lx. Ret: %d\n",
> > +				    start, end, attrs, ret);
> > +}
> >  #endif
> > diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
> > index fdc59479b3e2..d200b8f45583 100644
> > --- a/include/linux/kvm_host.h
> > +++ b/include/linux/kvm_host.h
> > @@ -2330,6 +2330,10 @@ void kvm_arch_set_memory_attributes(struct kvm *kvm,
> >  				    struct kvm_memory_slot *slot,
> >  				    unsigned long attrs,
> >  				    gfn_t start, gfn_t end);
> > +void kvm_arch_post_set_memory_attributes(struct kvm *kvm,
> > +					 struct kvm_memory_slot *slot,
> > +					 unsigned long attrs,
> > +					 gfn_t start, gfn_t end);
> >  
> >  static inline bool kvm_mem_is_private(struct kvm *kvm, gfn_t gfn)
> >  {
> > diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
> > index b68574ff6c30..8ec985f1c57d 100644
> > --- a/virt/kvm/kvm_main.c
> > +++ b/virt/kvm/kvm_main.c
> > @@ -2561,6 +2561,32 @@ static void kvm_mem_attrs_changed(struct kvm *kvm, unsigned long attrs,
> >  		kvm_flush_remote_tlbs(kvm);
> >  }
> >  
> > +static void kvm_post_mem_attrs_changed(struct kvm *kvm, unsigned long attrs,
> > +				       gfn_t start_orig, gfn_t end_orig)
> > +{
> > +	struct kvm_memory_slot *slot;
> > +	struct kvm_memslots *slots;
> > +	struct kvm_memslot_iter iter;
> > +	int i;
> > +
> > +	for (i = 0; i < kvm_arch_nr_memslot_as_ids(kvm); i++) {
> > +		slots = __kvm_memslots(kvm, i);
> > +
> > +		kvm_for_each_memslot_in_gfn_range(&iter, slots, start_orig, end_orig) {
> > +			gfn_t start, end;
> > +
> > +			slot = iter.slot;
> > +			start = max(start_orig, slot->base_gfn);
> > +			end = min(end_orig, slot->base_gfn + slot->npages);
> > +
> > +			if (start >= end)
> > +				continue;
> > +
> > +			kvm_arch_post_set_memory_attributes(kvm, slot, attrs, start, end);
> > +		}
> > +	}
> > +}
> > +
> >  static int kvm_vm_ioctl_set_mem_attributes(struct kvm *kvm,
> >  					   struct kvm_memory_attributes *attrs)
> >  {
> > @@ -2602,6 +2628,9 @@ static int kvm_vm_ioctl_set_mem_attributes(struct kvm *kvm,
> >  	kvm_mmu_invalidate_end(kvm);
> >  	KVM_MMU_UNLOCK(kvm);
> >  
> > +	if (i > start)
> > +		kvm_post_mem_attrs_changed(kvm, attrs->attributes, start, i);
> > +
> 
> Doesn't kvm_arch_set_memory_attributes() work for you? i.e the following patch.
> The error check and pr_warn_ratelimited() can be pushed down into the callback.

This is originally how I had but when CONFIG_PREEMPT_COUNT is set this
will generate warnings for this callback as well as the invalidation
callback as reported in v7 here:

  https://lore.kernel.org/lkml/Y80vhKwQyw8hS%2F22@notebook/

The main issue is that kvm_mem_attrs_changed() is called while holding
the KVM MMU lock, which disables preemption. But when updating
attributes for SNP, we also need to remove private pages from kernel
directmap, which involves acquiring a mutex which results in
"BUG: scheduling while atomic" warnings.

So that's why we ended up somewhat duplicating some of the logic and
using a separate callback chain that happens out of KVM MMU lock.

-Mike

> 
> From 7c618c1f3c236c382e64680efcbe7d8a672aa870 Mon Sep 17 00:00:00 2001
> Message-Id: <7c618c1f3c236c382e64680efcbe7d8a672aa870.1679114841.git.isaku.yamahata@intel.com>
> In-Reply-To: <428a676face7a06a90e59dca1c32941c9b6ee001.1679114841.git.isaku.yamahata@intel.com>
> References: <428a676face7a06a90e59dca1c32941c9b6ee001.1679114841.git.isaku.yamahata@intel.com>
> From: Isaku Yamahata <isaku.yamahata@intel.com>
> Date: Fri, 17 Mar 2023 12:00:09 -0700
> Subject: [PATCH 4/4] KVM: x86: Add 'set_mem_attr' x86 op
> 
> This callback will do any platform-specific handling needed for
> converting pages between shared/private.
> 
> Originally-by: Michael Roth <michael.roth@amd.com>
> Signed-off-by: Isaku Yamahata <isaku.yamahata@intel.com>
> ---
>  arch/x86/include/asm/kvm-x86-ops.h | 1 +
>  arch/x86/include/asm/kvm_host.h    | 2 ++
>  arch/x86/kvm/mmu/mmu.c             | 1 +
>  3 files changed, 4 insertions(+)
> 
> diff --git a/arch/x86/include/asm/kvm-x86-ops.h b/arch/x86/include/asm/kvm-x86-ops.h
> index dc5f18ac0bd5..956db2ee25a5 100644
> --- a/arch/x86/include/asm/kvm-x86-ops.h
> +++ b/arch/x86/include/asm/kvm-x86-ops.h
> @@ -100,6 +100,7 @@ KVM_X86_OP_OPTIONAL_RET0(set_identity_map_addr)
>  KVM_X86_OP_OPTIONAL_RET0(get_mt_mask)
>  KVM_X86_OP(load_mmu_pgd)
>  KVM_X86_OP(fault_is_private)
> +KVM_X86_OP_OPTIONAL(set_mem_attr)
>  KVM_X86_OP_OPTIONAL(link_private_spt)
>  KVM_X86_OP_OPTIONAL(free_private_spt)
>  KVM_X86_OP_OPTIONAL(split_private_spt)
> diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
> index 0382d236fbf4..88e11dd3afde 100644
> --- a/arch/x86/include/asm/kvm_host.h
> +++ b/arch/x86/include/asm/kvm_host.h
> @@ -1731,6 +1731,8 @@ struct kvm_x86_ops {
>  	void (*load_mmu_pgd)(struct kvm_vcpu *vcpu, hpa_t root_hpa,
>  			     int root_level);
>  	bool (*fault_is_private)(struct kvm *kvm, gpa_t gpa, u64 error_code);
> +	void (*set_mem_attr)(struct kvm *kvm, struct kvm_memory_slot *slot,
> +			     unsigned int attr, gfn_t start, gfn_t end);
>  
>  	int (*link_private_spt)(struct kvm *kvm, gfn_t gfn, enum pg_level level,
>  				void *private_spt);
> diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
> index 0ec94c72895c..329333486e64 100644
> --- a/arch/x86/kvm/mmu/mmu.c
> +++ b/arch/x86/kvm/mmu/mmu.c
> @@ -7908,6 +7908,7 @@ void kvm_arch_set_memory_attributes(struct kvm *kvm,
>  				    gfn_t start, gfn_t end)
>  {
>  	kvm_update_lpage_mixed_flag(kvm, slot, true, attrs, start, end);
> +	static_call(kvm_x86_set_mem_attr)(kvm, slot, attrs, start, end);
>  }
>  
>  void kvm_memory_attributes_create_memslot(struct kvm *kvm,
> -- 
> 2.25.1
> 
> -- 
> Isaku Yamahata <isaku.yamahata@gmail.com>