[PATCH 3/7] x86/pv: use populate_perdomain_mapping() to map the Xen GDT
George Dunlap <[email protected]>
| Newsgroups | org.xenproject.lists.xen-devel |
|---|---|
| Message-ID | <[email protected]> |
From: Roger Pau Monné <[email protected]> Currently, update_xen_slot_in_full_gdt() uses the stashed pointer in d->arch.pv.gdt_ldt_l1tab to update the incoming vcpu's page-tables with Xen's GDT, by writing a stashed per-cpu copy of a pre-baked L1 entry (either 64-bit or compat version). Now that all perdomain pagetables are allocated from the xenheap and their root L3 stashed in d->arch.perdomain_l3, d->arch.pv.gdt_ldt_l1tab is redundant. Remove one user by switching update_xen_slot_in_full_gdt() to using populate_perdomain_mapping(). Since populate_perdomain_mapping() takes an mfn rather than an l1e, cache the mfn of the per-cpu page instead. As a side effect, this consolidates the setting of the flags into a single place. Continue to check that the per-cpu value we're using has been initialized: per-CPU data starts out zeroed, and no GDT can live at MFN 0. What was one store through a cached pointer is now an out-of-line walk (L3 pointer, L3e, L2e, then the L1e) on every PV context switch: three dependent loads, negligible next to the CR3 write that follows. Signed-off-by: Roger Pau Monné <[email protected]> Assisted-by: Claude Code:claude-fable-5, Claude Code:claude-opus-4-8 Signed-off-by: George Dunlap <[email protected]> --- Changes since the previously posted version: - populate_perdomain_mapping() introduction split into the previous patch; this patch is now just the Xen GDT conversion. - Retain the "GDT MFN cached" check as ASSERT(mfn_x(mfn)). --- xen/arch/x86/domain.c | 13 +++++++++---- xen/arch/x86/include/asm/desc.h | 6 ++++-- xen/arch/x86/smpboot.c | 14 +++++--------- xen/arch/x86/traps.c | 4 ++-- 4 files changed, 20 insertions(+), 17 deletions(-) diff --git a/xen/arch/x86/domain.c b/xen/arch/x86/domain.c index 163a2c97ae..f5b2eef95a 100644 --- a/xen/arch/x86/domain.c +++ b/xen/arch/x86/domain.c @@ -2062,11 +2062,16 @@ static always_inline bool need_full_gdt(const struct domain *d) static void update_xen_slot_in_full_gdt(const struct vcpu *v, unsigned int cpu) { - ASSERT(per_cpu(gdt_l1e, cpu).l1); /* Confirm these have been cached. */ + mfn_t mfn = !is_pv_32bit_vcpu(v) ? per_cpu(gdt_mfn, cpu) + : per_cpu(compat_gdt_mfn, cpu); - l1e_write(pv_gdt_ptes(v) + FIRST_RESERVED_GDT_PAGE, - !is_pv_32bit_vcpu(v) ? per_cpu(gdt_l1e, cpu) - : per_cpu(compat_gdt_l1e, cpu)); + /* Confirm the GDT MFNs have been cached (MFN 0 is never a GDT). */ + ASSERT(mfn_x(mfn)); + + populate_perdomain_mapping(v, + GDT_VIRT_START(v) + + (FIRST_RESERVED_GDT_PAGE << PAGE_SHIFT), + &mfn, 1, __PAGE_HYPERVISOR_RW); } static void load_full_gdt(const struct vcpu *v, unsigned int cpu) diff --git a/xen/arch/x86/include/asm/desc.h b/xen/arch/x86/include/asm/desc.h index dcbdac3ff7..a26df9fbe9 100644 --- a/xen/arch/x86/include/asm/desc.h +++ b/xen/arch/x86/include/asm/desc.h @@ -44,6 +44,8 @@ #ifndef __ASSEMBLER__ +#include <xen/mm-frame.h> + #define GUEST_KERNEL_RPL(d) (is_pv_32bit_domain(d) ? 1 : 3) /* Fix up the RPL of a guest segment selector. */ @@ -136,10 +138,10 @@ struct __packed desc_ptr { extern seg_desc_t boot_gdt[]; DECLARE_PER_CPU(seg_desc_t *, gdt); -DECLARE_PER_CPU(l1_pgentry_t, gdt_l1e); +DECLARE_PER_CPU(mfn_t, gdt_mfn); extern seg_desc_t boot_compat_gdt[]; DECLARE_PER_CPU(seg_desc_t *, compat_gdt); -DECLARE_PER_CPU(l1_pgentry_t, compat_gdt_l1e); +DECLARE_PER_CPU(mfn_t, compat_gdt_mfn); DECLARE_PER_CPU(bool, full_gdt_loaded); static inline void lgdt(const struct desc_ptr *gdtr) diff --git a/xen/arch/x86/smpboot.c b/xen/arch/x86/smpboot.c index 84e9e4beed..9246945506 100644 --- a/xen/arch/x86/smpboot.c +++ b/xen/arch/x86/smpboot.c @@ -1085,8 +1085,7 @@ static int cpu_smpboot_alloc(unsigned int cpu) if ( gdt == NULL ) goto out; per_cpu(gdt, cpu) = gdt; - per_cpu(gdt_l1e, cpu) = - l1e_from_pfn(virt_to_mfn(gdt), __PAGE_HYPERVISOR_RW); + per_cpu(gdt_mfn, cpu) = _mfn(virt_to_mfn(gdt)); memcpy(gdt, boot_gdt, NR_RESERVED_GDT_PAGES * PAGE_SIZE); BUILD_BUG_ON(NR_CPUS > 0x10000); gdt[PER_CPU_GDT_ENTRY - FIRST_RESERVED_GDT_ENTRY].a = cpu; @@ -1095,8 +1094,7 @@ static int cpu_smpboot_alloc(unsigned int cpu) per_cpu(compat_gdt, cpu) = gdt = alloc_xenheap_pages(0, memflags); if ( gdt == NULL ) goto out; - per_cpu(compat_gdt_l1e, cpu) = - l1e_from_pfn(virt_to_mfn(gdt), __PAGE_HYPERVISOR_RW); + per_cpu(compat_gdt_mfn, cpu) = _mfn(virt_to_mfn(gdt)); memcpy(gdt, boot_compat_gdt, NR_RESERVED_GDT_PAGES * PAGE_SIZE); gdt[PER_CPU_GDT_ENTRY - FIRST_RESERVED_GDT_ENTRY].a = cpu; #endif @@ -1174,15 +1172,13 @@ void __init smp_prepare_cpus(void) print_cpu_info(0); /* - * Cache {,compat_}gdt_l1e for the BSP now that physically relocation is + * Cache {,compat_}gdt_mfn for the BSP now that physically relocation is * done. It must be after physical relocation of Xen, and before the * first context_switch(). */ - this_cpu(gdt_l1e) = - l1e_from_pfn(virt_to_mfn(boot_gdt), __PAGE_HYPERVISOR_RW); + this_cpu(gdt_mfn) = _mfn(virt_to_mfn(boot_gdt)); if ( IS_ENABLED(CONFIG_PV32) ) - this_cpu(compat_gdt_l1e) = - l1e_from_pfn(virt_to_mfn(boot_compat_gdt), __PAGE_HYPERVISOR_RW); + this_cpu(compat_gdt_mfn) = _mfn(virt_to_mfn(boot_compat_gdt)); boot_cpu_physical_apicid = get_apic_id(); x86_cpu_to_apicid[0] = boot_cpu_physical_apicid; diff --git a/xen/arch/x86/traps.c b/xen/arch/x86/traps.c index 1774966305..2fcaa413f7 100644 --- a/xen/arch/x86/traps.c +++ b/xen/arch/x86/traps.c @@ -71,10 +71,10 @@ DEFINE_PER_CPU(uint64_t, efer); static DEFINE_PER_CPU(unsigned long, last_extable_addr); DEFINE_PER_CPU_READ_MOSTLY(seg_desc_t *, gdt); -DEFINE_PER_CPU_READ_MOSTLY(l1_pgentry_t, gdt_l1e); +DEFINE_PER_CPU_READ_MOSTLY(mfn_t, gdt_mfn); #ifdef CONFIG_PV32 DEFINE_PER_CPU_READ_MOSTLY(seg_desc_t *, compat_gdt); -DEFINE_PER_CPU_READ_MOSTLY(l1_pgentry_t, compat_gdt_l1e); +DEFINE_PER_CPU_READ_MOSTLY(mfn_t, compat_gdt_mfn); #endif /* -- 2.55.0