From: Fangyu Yu <fangyu.yu@linux.alibaba.com>
Gstage page-table helpers frequently chase gstage->kvm->arch to
fetch pgd_levels. This adds noise and repeats the same dereference
chain in hot paths.
Add pgd_levels to struct kvm_gstage and initialize it from kvm->arch
when setting up a gstage instance. Introduce kvm_riscv_gstage_init()
to centralize initialization and switch gstage code to use
gstage->pgd_levels.
Suggested-by: Anup Patel <anup@brainfault.org>
Signed-off-by: Fangyu Yu <fangyu.yu@linux.alibaba.com>
---
arch/riscv/include/asm/kvm_gstage.h | 10 ++++++
arch/riscv/kvm/gstage.c | 10 +++---
arch/riscv/kvm/mmu.c | 50 ++++++-----------------------
3 files changed, 25 insertions(+), 45 deletions(-)
diff --git a/arch/riscv/include/asm/kvm_gstage.h b/arch/riscv/include/asm/kvm_gstage.h
index 5aa58d1f692a..70d9d483365e 100644
--- a/arch/riscv/include/asm/kvm_gstage.h
+++ b/arch/riscv/include/asm/kvm_gstage.h
@@ -15,6 +15,7 @@ struct kvm_gstage {
#define KVM_GSTAGE_FLAGS_LOCAL BIT(0)
unsigned long vmid;
pgd_t *pgd;
+ unsigned long pgd_levels;
};
struct kvm_gstage_mapping {
@@ -92,4 +93,13 @@ static inline unsigned long kvm_riscv_gstage_mode(unsigned long pgd_levels)
}
}
+static inline void kvm_riscv_gstage_init(struct kvm_gstage *gstage, struct kvm *kvm)
+{
+ gstage->kvm = kvm;
+ gstage->flags = 0;
+ gstage->vmid = READ_ONCE(kvm->arch.vmid.vmid);
+ gstage->pgd = kvm->arch.pgd;
+ gstage->pgd_levels = kvm->arch.pgd_levels;
+}
+
#endif
diff --git a/arch/riscv/kvm/gstage.c b/arch/riscv/kvm/gstage.c
index 4beb9322fe76..7c4c34bc191b 100644
--- a/arch/riscv/kvm/gstage.c
+++ b/arch/riscv/kvm/gstage.c
@@ -26,7 +26,7 @@ static inline unsigned long gstage_pte_index(struct kvm_gstage *gstage,
unsigned long mask;
unsigned long shift = HGATP_PAGE_SHIFT + (kvm_riscv_gstage_index_bits * level);
- if (level == gstage->kvm->arch.pgd_levels - 1)
+ if (level == gstage->pgd_levels - 1)
mask = (PTRS_PER_PTE * (1UL << kvm_riscv_gstage_pgd_xbits)) - 1;
else
mask = PTRS_PER_PTE - 1;
@@ -45,7 +45,7 @@ static int gstage_page_size_to_level(struct kvm_gstage *gstage, unsigned long pa
u32 i;
unsigned long psz = 1UL << 12;
- for (i = 0; i < gstage->kvm->arch.pgd_levels; i++) {
+ for (i = 0; i < gstage->pgd_levels; i++) {
if (page_size == (psz << (i * kvm_riscv_gstage_index_bits))) {
*out_level = i;
return 0;
@@ -58,7 +58,7 @@ static int gstage_page_size_to_level(struct kvm_gstage *gstage, unsigned long pa
static int gstage_level_to_page_order(struct kvm_gstage *gstage, u32 level,
unsigned long *out_pgorder)
{
- if (gstage->kvm->arch.pgd_levels < level)
+ if (gstage->pgd_levels < level)
return -EINVAL;
*out_pgorder = 12 + (level * kvm_riscv_gstage_index_bits);
@@ -83,7 +83,7 @@ bool kvm_riscv_gstage_get_leaf(struct kvm_gstage *gstage, gpa_t addr,
pte_t **ptepp, u32 *ptep_level)
{
pte_t *ptep;
- u32 current_level = gstage->kvm->arch.pgd_levels - 1;
+ u32 current_level = gstage->pgd_levels - 1;
*ptep_level = current_level;
ptep = (pte_t *)gstage->pgd;
@@ -127,7 +127,7 @@ int kvm_riscv_gstage_set_pte(struct kvm_gstage *gstage,
struct kvm_mmu_memory_cache *pcache,
const struct kvm_gstage_mapping *map)
{
- u32 current_level = gstage->kvm->arch.pgd_levels - 1;
+ u32 current_level = gstage->pgd_levels - 1;
pte_t *next_ptep = (pte_t *)gstage->pgd;
pte_t *ptep = &next_ptep[gstage_pte_index(gstage, map->addr, current_level)];
diff --git a/arch/riscv/kvm/mmu.c b/arch/riscv/kvm/mmu.c
index fbcdd75cb9af..2d3def024270 100644
--- a/arch/riscv/kvm/mmu.c
+++ b/arch/riscv/kvm/mmu.c
@@ -24,10 +24,7 @@ static void mmu_wp_memory_region(struct kvm *kvm, int slot)
phys_addr_t end = (memslot->base_gfn + memslot->npages) << PAGE_SHIFT;
struct kvm_gstage gstage;
- gstage.kvm = kvm;
- gstage.flags = 0;
- gstage.vmid = READ_ONCE(kvm->arch.vmid.vmid);
- gstage.pgd = kvm->arch.pgd;
+ kvm_riscv_gstage_init(&gstage, kvm);
spin_lock(&kvm->mmu_lock);
kvm_riscv_gstage_wp_range(&gstage, start, end);
@@ -49,10 +46,7 @@ int kvm_riscv_mmu_ioremap(struct kvm *kvm, gpa_t gpa, phys_addr_t hpa,
struct kvm_gstage_mapping map;
struct kvm_gstage gstage;
- gstage.kvm = kvm;
- gstage.flags = 0;
- gstage.vmid = READ_ONCE(kvm->arch.vmid.vmid);
- gstage.pgd = kvm->arch.pgd;
+ kvm_riscv_gstage_init(&gstage, kvm);
end = (gpa + size + PAGE_SIZE - 1) & PAGE_MASK;
pfn = __phys_to_pfn(hpa);
@@ -89,10 +83,7 @@ void kvm_riscv_mmu_iounmap(struct kvm *kvm, gpa_t gpa, unsigned long size)
{
struct kvm_gstage gstage;
- gstage.kvm = kvm;
- gstage.flags = 0;
- gstage.vmid = READ_ONCE(kvm->arch.vmid.vmid);
- gstage.pgd = kvm->arch.pgd;
+ kvm_riscv_gstage_init(&gstage, kvm);
spin_lock(&kvm->mmu_lock);
kvm_riscv_gstage_unmap_range(&gstage, gpa, size, false);
@@ -109,10 +100,7 @@ void kvm_arch_mmu_enable_log_dirty_pt_masked(struct kvm *kvm,
phys_addr_t end = (base_gfn + __fls(mask) + 1) << PAGE_SHIFT;
struct kvm_gstage gstage;
- gstage.kvm = kvm;
- gstage.flags = 0;
- gstage.vmid = READ_ONCE(kvm->arch.vmid.vmid);
- gstage.pgd = kvm->arch.pgd;
+ kvm_riscv_gstage_init(&gstage, kvm);
kvm_riscv_gstage_wp_range(&gstage, start, end);
}
@@ -141,10 +129,7 @@ void kvm_arch_flush_shadow_memslot(struct kvm *kvm,
phys_addr_t size = slot->npages << PAGE_SHIFT;
struct kvm_gstage gstage;
- gstage.kvm = kvm;
- gstage.flags = 0;
- gstage.vmid = READ_ONCE(kvm->arch.vmid.vmid);
- gstage.pgd = kvm->arch.pgd;
+ kvm_riscv_gstage_init(&gstage, kvm);
spin_lock(&kvm->mmu_lock);
kvm_riscv_gstage_unmap_range(&gstage, gpa, size, false);
@@ -250,10 +235,7 @@ bool kvm_unmap_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range)
if (!kvm->arch.pgd)
return false;
- gstage.kvm = kvm;
- gstage.flags = 0;
- gstage.vmid = READ_ONCE(kvm->arch.vmid.vmid);
- gstage.pgd = kvm->arch.pgd;
+ kvm_riscv_gstage_init(&gstage, kvm);
mmu_locked = spin_trylock(&kvm->mmu_lock);
kvm_riscv_gstage_unmap_range(&gstage, range->start << PAGE_SHIFT,
(range->end - range->start) << PAGE_SHIFT,
@@ -275,10 +257,7 @@ bool kvm_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range)
WARN_ON(size != PAGE_SIZE && size != PMD_SIZE && size != PUD_SIZE);
- gstage.kvm = kvm;
- gstage.flags = 0;
- gstage.vmid = READ_ONCE(kvm->arch.vmid.vmid);
- gstage.pgd = kvm->arch.pgd;
+ kvm_riscv_gstage_init(&gstage, kvm);
if (!kvm_riscv_gstage_get_leaf(&gstage, range->start << PAGE_SHIFT,
&ptep, &ptep_level))
return false;
@@ -298,10 +277,7 @@ bool kvm_test_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range)
WARN_ON(size != PAGE_SIZE && size != PMD_SIZE && size != PUD_SIZE);
- gstage.kvm = kvm;
- gstage.flags = 0;
- gstage.vmid = READ_ONCE(kvm->arch.vmid.vmid);
- gstage.pgd = kvm->arch.pgd;
+ kvm_riscv_gstage_init(&gstage, kvm);
if (!kvm_riscv_gstage_get_leaf(&gstage, range->start << PAGE_SHIFT,
&ptep, &ptep_level))
return false;
@@ -463,10 +439,7 @@ int kvm_riscv_mmu_map(struct kvm_vcpu *vcpu, struct kvm_memory_slot *memslot,
struct kvm_gstage gstage;
struct page *page;
- gstage.kvm = kvm;
- gstage.flags = 0;
- gstage.vmid = READ_ONCE(kvm->arch.vmid.vmid);
- gstage.pgd = kvm->arch.pgd;
+ kvm_riscv_gstage_init(&gstage, kvm);
/* Setup initial state of output mapping */
memset(out_map, 0, sizeof(*out_map));
@@ -587,10 +560,7 @@ void kvm_riscv_mmu_free_pgd(struct kvm *kvm)
spin_lock(&kvm->mmu_lock);
if (kvm->arch.pgd) {
- gstage.kvm = kvm;
- gstage.flags = 0;
- gstage.vmid = READ_ONCE(kvm->arch.vmid.vmid);
- gstage.pgd = kvm->arch.pgd;
+ kvm_riscv_gstage_init(&gstage, kvm);
kvm_riscv_gstage_unmap_range(&gstage, 0UL,
kvm_riscv_gstage_gpa_size(kvm->arch.pgd_levels), false);
pgd = READ_ONCE(kvm->arch.pgd);
--
2.50.1On Mon, Mar 30, 2026 at 5:56 PM <fangyu.yu@linux.alibaba.com> wrote:
>
> From: Fangyu Yu <fangyu.yu@linux.alibaba.com>
>
> Gstage page-table helpers frequently chase gstage->kvm->arch to
> fetch pgd_levels. This adds noise and repeats the same dereference
> chain in hot paths.
>
> Add pgd_levels to struct kvm_gstage and initialize it from kvm->arch
> when setting up a gstage instance. Introduce kvm_riscv_gstage_init()
> to centralize initialization and switch gstage code to use
> gstage->pgd_levels.
>
> Suggested-by: Anup Patel <anup@brainfault.org>
> Signed-off-by: Fangyu Yu <fangyu.yu@linux.alibaba.com>
LGTM.
Reviewed-by: Anup Patel <anup@brainfault.org>
Thanks,
Anup
> ---
> arch/riscv/include/asm/kvm_gstage.h | 10 ++++++
> arch/riscv/kvm/gstage.c | 10 +++---
> arch/riscv/kvm/mmu.c | 50 ++++++-----------------------
> 3 files changed, 25 insertions(+), 45 deletions(-)
>
> diff --git a/arch/riscv/include/asm/kvm_gstage.h b/arch/riscv/include/asm/kvm_gstage.h
> index 5aa58d1f692a..70d9d483365e 100644
> --- a/arch/riscv/include/asm/kvm_gstage.h
> +++ b/arch/riscv/include/asm/kvm_gstage.h
> @@ -15,6 +15,7 @@ struct kvm_gstage {
> #define KVM_GSTAGE_FLAGS_LOCAL BIT(0)
> unsigned long vmid;
> pgd_t *pgd;
> + unsigned long pgd_levels;
> };
>
> struct kvm_gstage_mapping {
> @@ -92,4 +93,13 @@ static inline unsigned long kvm_riscv_gstage_mode(unsigned long pgd_levels)
> }
> }
>
> +static inline void kvm_riscv_gstage_init(struct kvm_gstage *gstage, struct kvm *kvm)
> +{
> + gstage->kvm = kvm;
> + gstage->flags = 0;
> + gstage->vmid = READ_ONCE(kvm->arch.vmid.vmid);
> + gstage->pgd = kvm->arch.pgd;
> + gstage->pgd_levels = kvm->arch.pgd_levels;
> +}
> +
> #endif
> diff --git a/arch/riscv/kvm/gstage.c b/arch/riscv/kvm/gstage.c
> index 4beb9322fe76..7c4c34bc191b 100644
> --- a/arch/riscv/kvm/gstage.c
> +++ b/arch/riscv/kvm/gstage.c
> @@ -26,7 +26,7 @@ static inline unsigned long gstage_pte_index(struct kvm_gstage *gstage,
> unsigned long mask;
> unsigned long shift = HGATP_PAGE_SHIFT + (kvm_riscv_gstage_index_bits * level);
>
> - if (level == gstage->kvm->arch.pgd_levels - 1)
> + if (level == gstage->pgd_levels - 1)
> mask = (PTRS_PER_PTE * (1UL << kvm_riscv_gstage_pgd_xbits)) - 1;
> else
> mask = PTRS_PER_PTE - 1;
> @@ -45,7 +45,7 @@ static int gstage_page_size_to_level(struct kvm_gstage *gstage, unsigned long pa
> u32 i;
> unsigned long psz = 1UL << 12;
>
> - for (i = 0; i < gstage->kvm->arch.pgd_levels; i++) {
> + for (i = 0; i < gstage->pgd_levels; i++) {
> if (page_size == (psz << (i * kvm_riscv_gstage_index_bits))) {
> *out_level = i;
> return 0;
> @@ -58,7 +58,7 @@ static int gstage_page_size_to_level(struct kvm_gstage *gstage, unsigned long pa
> static int gstage_level_to_page_order(struct kvm_gstage *gstage, u32 level,
> unsigned long *out_pgorder)
> {
> - if (gstage->kvm->arch.pgd_levels < level)
> + if (gstage->pgd_levels < level)
> return -EINVAL;
>
> *out_pgorder = 12 + (level * kvm_riscv_gstage_index_bits);
> @@ -83,7 +83,7 @@ bool kvm_riscv_gstage_get_leaf(struct kvm_gstage *gstage, gpa_t addr,
> pte_t **ptepp, u32 *ptep_level)
> {
> pte_t *ptep;
> - u32 current_level = gstage->kvm->arch.pgd_levels - 1;
> + u32 current_level = gstage->pgd_levels - 1;
>
> *ptep_level = current_level;
> ptep = (pte_t *)gstage->pgd;
> @@ -127,7 +127,7 @@ int kvm_riscv_gstage_set_pte(struct kvm_gstage *gstage,
> struct kvm_mmu_memory_cache *pcache,
> const struct kvm_gstage_mapping *map)
> {
> - u32 current_level = gstage->kvm->arch.pgd_levels - 1;
> + u32 current_level = gstage->pgd_levels - 1;
> pte_t *next_ptep = (pte_t *)gstage->pgd;
> pte_t *ptep = &next_ptep[gstage_pte_index(gstage, map->addr, current_level)];
>
> diff --git a/arch/riscv/kvm/mmu.c b/arch/riscv/kvm/mmu.c
> index fbcdd75cb9af..2d3def024270 100644
> --- a/arch/riscv/kvm/mmu.c
> +++ b/arch/riscv/kvm/mmu.c
> @@ -24,10 +24,7 @@ static void mmu_wp_memory_region(struct kvm *kvm, int slot)
> phys_addr_t end = (memslot->base_gfn + memslot->npages) << PAGE_SHIFT;
> struct kvm_gstage gstage;
>
> - gstage.kvm = kvm;
> - gstage.flags = 0;
> - gstage.vmid = READ_ONCE(kvm->arch.vmid.vmid);
> - gstage.pgd = kvm->arch.pgd;
> + kvm_riscv_gstage_init(&gstage, kvm);
>
> spin_lock(&kvm->mmu_lock);
> kvm_riscv_gstage_wp_range(&gstage, start, end);
> @@ -49,10 +46,7 @@ int kvm_riscv_mmu_ioremap(struct kvm *kvm, gpa_t gpa, phys_addr_t hpa,
> struct kvm_gstage_mapping map;
> struct kvm_gstage gstage;
>
> - gstage.kvm = kvm;
> - gstage.flags = 0;
> - gstage.vmid = READ_ONCE(kvm->arch.vmid.vmid);
> - gstage.pgd = kvm->arch.pgd;
> + kvm_riscv_gstage_init(&gstage, kvm);
>
> end = (gpa + size + PAGE_SIZE - 1) & PAGE_MASK;
> pfn = __phys_to_pfn(hpa);
> @@ -89,10 +83,7 @@ void kvm_riscv_mmu_iounmap(struct kvm *kvm, gpa_t gpa, unsigned long size)
> {
> struct kvm_gstage gstage;
>
> - gstage.kvm = kvm;
> - gstage.flags = 0;
> - gstage.vmid = READ_ONCE(kvm->arch.vmid.vmid);
> - gstage.pgd = kvm->arch.pgd;
> + kvm_riscv_gstage_init(&gstage, kvm);
>
> spin_lock(&kvm->mmu_lock);
> kvm_riscv_gstage_unmap_range(&gstage, gpa, size, false);
> @@ -109,10 +100,7 @@ void kvm_arch_mmu_enable_log_dirty_pt_masked(struct kvm *kvm,
> phys_addr_t end = (base_gfn + __fls(mask) + 1) << PAGE_SHIFT;
> struct kvm_gstage gstage;
>
> - gstage.kvm = kvm;
> - gstage.flags = 0;
> - gstage.vmid = READ_ONCE(kvm->arch.vmid.vmid);
> - gstage.pgd = kvm->arch.pgd;
> + kvm_riscv_gstage_init(&gstage, kvm);
>
> kvm_riscv_gstage_wp_range(&gstage, start, end);
> }
> @@ -141,10 +129,7 @@ void kvm_arch_flush_shadow_memslot(struct kvm *kvm,
> phys_addr_t size = slot->npages << PAGE_SHIFT;
> struct kvm_gstage gstage;
>
> - gstage.kvm = kvm;
> - gstage.flags = 0;
> - gstage.vmid = READ_ONCE(kvm->arch.vmid.vmid);
> - gstage.pgd = kvm->arch.pgd;
> + kvm_riscv_gstage_init(&gstage, kvm);
>
> spin_lock(&kvm->mmu_lock);
> kvm_riscv_gstage_unmap_range(&gstage, gpa, size, false);
> @@ -250,10 +235,7 @@ bool kvm_unmap_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range)
> if (!kvm->arch.pgd)
> return false;
>
> - gstage.kvm = kvm;
> - gstage.flags = 0;
> - gstage.vmid = READ_ONCE(kvm->arch.vmid.vmid);
> - gstage.pgd = kvm->arch.pgd;
> + kvm_riscv_gstage_init(&gstage, kvm);
> mmu_locked = spin_trylock(&kvm->mmu_lock);
> kvm_riscv_gstage_unmap_range(&gstage, range->start << PAGE_SHIFT,
> (range->end - range->start) << PAGE_SHIFT,
> @@ -275,10 +257,7 @@ bool kvm_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range)
>
> WARN_ON(size != PAGE_SIZE && size != PMD_SIZE && size != PUD_SIZE);
>
> - gstage.kvm = kvm;
> - gstage.flags = 0;
> - gstage.vmid = READ_ONCE(kvm->arch.vmid.vmid);
> - gstage.pgd = kvm->arch.pgd;
> + kvm_riscv_gstage_init(&gstage, kvm);
> if (!kvm_riscv_gstage_get_leaf(&gstage, range->start << PAGE_SHIFT,
> &ptep, &ptep_level))
> return false;
> @@ -298,10 +277,7 @@ bool kvm_test_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range)
>
> WARN_ON(size != PAGE_SIZE && size != PMD_SIZE && size != PUD_SIZE);
>
> - gstage.kvm = kvm;
> - gstage.flags = 0;
> - gstage.vmid = READ_ONCE(kvm->arch.vmid.vmid);
> - gstage.pgd = kvm->arch.pgd;
> + kvm_riscv_gstage_init(&gstage, kvm);
> if (!kvm_riscv_gstage_get_leaf(&gstage, range->start << PAGE_SHIFT,
> &ptep, &ptep_level))
> return false;
> @@ -463,10 +439,7 @@ int kvm_riscv_mmu_map(struct kvm_vcpu *vcpu, struct kvm_memory_slot *memslot,
> struct kvm_gstage gstage;
> struct page *page;
>
> - gstage.kvm = kvm;
> - gstage.flags = 0;
> - gstage.vmid = READ_ONCE(kvm->arch.vmid.vmid);
> - gstage.pgd = kvm->arch.pgd;
> + kvm_riscv_gstage_init(&gstage, kvm);
>
> /* Setup initial state of output mapping */
> memset(out_map, 0, sizeof(*out_map));
> @@ -587,10 +560,7 @@ void kvm_riscv_mmu_free_pgd(struct kvm *kvm)
>
> spin_lock(&kvm->mmu_lock);
> if (kvm->arch.pgd) {
> - gstage.kvm = kvm;
> - gstage.flags = 0;
> - gstage.vmid = READ_ONCE(kvm->arch.vmid.vmid);
> - gstage.pgd = kvm->arch.pgd;
> + kvm_riscv_gstage_init(&gstage, kvm);
> kvm_riscv_gstage_unmap_range(&gstage, 0UL,
> kvm_riscv_gstage_gpa_size(kvm->arch.pgd_levels), false);
> pgd = READ_ONCE(kvm->arch.pgd);
> --
> 2.50.1
>
© 2016 - 2026 Red Hat, Inc.