Instead of using the TSS and stacks of the physical processor allocate
them per vcpu, map them in the per domain area, and use those.
Signed-off-by: Juergen Gross <jgr...@suse.com>
---
xen/arch/x86/domain.c | 45 +++++++++++++++++++++++----
xen/arch/x86/pv/domain.c | 72 +++++++++++++++++++++++++++++++++++++++++---
xen/arch/x86/x86_64/entry.S | 4 +++
xen/include/asm-x86/config.h | 9 +++++-
xen/include/asm-x86/mm.h | 5 +++
5 files changed, 124 insertions(+), 11 deletions(-)
diff --git a/xen/arch/x86/domain.c b/xen/arch/x86/domain.c
index c0cb2cae64..952ed7e121 100644
--- a/xen/arch/x86/domain.c
+++ b/xen/arch/x86/domain.c
@@ -1582,7 +1582,12 @@ static void _update_runstate_area(struct vcpu *v)
static inline bool need_full_gdt(const struct domain *d)
{
- return is_pv_domain(d) && !is_idle_domain(d);
+ return is_pv_32bit_domain(d);
+}
+
+static inline bool need_per_vcpu_data(const struct domain *d)
+{
+ return is_pv_domain(d) && !is_idle_domain(d) && !is_pv_32bit_domain(d);
}
static void __context_switch(void)
@@ -1657,8 +1662,19 @@ static void __context_switch(void)
write_ptbase(n);
- if ( need_full_gdt(nd) &&
- ((p->vcpu_id != n->vcpu_id) || !need_full_gdt(pd)) )
+ if ( need_per_vcpu_data(nd) )
+ {
+ gdt = (struct desc_struct *)GDT_VIRT_START(n);
+ gdt[PER_CPU_GDT_ENTRY].a = cpu;
+
+ gdt_desc.limit = LAST_RESERVED_GDT_BYTE;
+ gdt_desc.base = GDT_VIRT_START(n);
+
+ lgdt(&gdt_desc);
+ ltr(TSS_ENTRY << 3);
+ }
+ else if ( need_full_gdt(nd) &&
+ ((p->vcpu_id != n->vcpu_id) || !need_full_gdt(pd)) )
{
gdt_desc.limit = LAST_RESERVED_GDT_BYTE;
gdt_desc.base = GDT_VIRT_START(n);
@@ -1673,8 +1689,8 @@ static void __context_switch(void)
per_cpu(curr_vcpu, cpu) = n;
}
-static void context_switch_irqoff(struct vcpu *prev, struct vcpu *next,
- unsigned int cpu)
+void context_switch_irqoff(struct vcpu *prev, struct vcpu *next,
+ unsigned int cpu)
{
const struct domain *prevd = prev->domain, *nextd = next->domain;
@@ -1764,7 +1780,24 @@ void context_switch(struct vcpu *prev, struct vcpu *next)
set_current(next);
- context_switch_irqoff(prev, next, cpu);
+ if ( is_pv_domain(prevd) && !is_pv_32bit_domain(prevd) )
+ {
+ struct desc_struct *gdt = this_cpu(compat_gdt_table) -
+ FIRST_RESERVED_GDT_ENTRY;
+ const struct desc_ptr gdtr = {
+ .base = (unsigned long)gdt,
+ .limit = LAST_RESERVED_GDT_BYTE,
+ };
+ void *stack = (struct cpu_info *)(stack_base[cpu] + STACK_SIZE) - 1;
+
+ /* Switch to global accessible gdt and tss. */
+ lgdt(&gdtr);
+ ltr(TSS_ENTRY << 3);
+
+ context_switch_irqoff_stack(prev, next, cpu, stack);
+ }
+ else
+ context_switch_irqoff(prev, next, cpu);
}
void continue_running(struct vcpu *same)
diff --git a/xen/arch/x86/pv/domain.c b/xen/arch/x86/pv/domain.c
index 74e9e667d2..6692aa6922 100644
--- a/xen/arch/x86/pv/domain.c
+++ b/xen/arch/x86/pv/domain.c
@@ -96,10 +96,32 @@ int switch_compat(struct domain *d)
static int pv_create_gdt_ldt_l1tab(struct vcpu *v)
{
- return create_perdomain_mapping(v->domain, GDT_VIRT_START(v),
- 1U << GDT_LDT_VCPU_SHIFT,
- v->domain->arch.pv_domain.gdt_ldt_l1tab,
- NULL);
+ int rc;
+
+ rc = create_perdomain_mapping(v->domain, GDT_VIRT_START(v),
+ 1U << GDT_LDT_VCPU_SHIFT,
+ v->domain->arch.pv_domain.gdt_ldt_l1tab,
+ NULL);
+ if ( !rc && !is_pv_32bit_vcpu(v) )
+ {
+ struct desc_struct *gdt;
+
+ gdt = (struct desc_struct *)GDT_VIRT_START(v) +
+ FIRST_RESERVED_GDT_ENTRY;
+ rc = create_perdomain_mapping(v->domain, (unsigned long)gdt,
+ NR_RESERVED_GDT_BYTES,
+ NULL, NIL(struct page_info *));
+ if ( !rc )
+ {
+ memcpy(gdt, boot_cpu_gdt_table, NR_RESERVED_GDT_BYTES);
+ _set_tssldt_desc(gdt + TSS_ENTRY - FIRST_RESERVED_GDT_ENTRY,
+ TSS_START(v),
+ offsetof(struct tss_struct, __cacheline_filler) - 1,
+ SYS_DESC_tss_avail);
+ }
+ }
+
+ return rc;
}
static void pv_destroy_gdt_ldt_l1tab(struct vcpu *v)
@@ -119,6 +141,46 @@ void pv_vcpu_destroy(struct vcpu *v)
pv_destroy_gdt_ldt_l1tab(v);
xfree(v->arch.pv_vcpu.trap_ctxt);
v->arch.pv_vcpu.trap_ctxt = NULL;
+
+ if ( !is_pv_32bit_vcpu(v) )
+ destroy_perdomain_mapping(v->domain, STACKS_START(v),
+ STACK_SIZE + PAGE_SIZE);
+}
+
+static int pv_vcpu_init_tss_stacks(struct vcpu *v)
+{
+ struct domain *d = v->domain;
+ void *stacks;
+ int rc;
+
+ /* Populate page tables. */
+ rc = create_perdomain_mapping(d, STACKS_START(v), STACK_SIZE + PAGE_SIZE,
+ NIL(l1_pgentry_t *), NULL);
+ if ( rc )
+ goto done;
+
+ /* Map TSS. */
+ rc = create_perdomain_mapping(d, TSS_START(v), PAGE_SIZE,
+ NULL, NIL(struct page_info *));
+ if ( rc )
+ goto done;
+
+ /* Map stacks. */
+ stacks = (void *)STACKS_START(v);
+ rc = create_perdomain_mapping(d, STACKS_START(v), STACK_SIZE,
+ NULL, NIL(struct page_info *));
+ if ( rc )
+ goto done;
+#ifdef MEMORY_GUARD
+ /* Remove guard page. */
+ destroy_perdomain_mapping(d, (unsigned
long)memguard_get_guard_page(stacks),
+ PAGE_SIZE);
+#endif
+
+ tss_init((struct tss_struct *)TSS_START(v), STACKS_START(v));
+
+ done:
+ return 0;
}
int pv_vcpu_initialise(struct vcpu *v)
@@ -157,6 +219,8 @@ int pv_vcpu_initialise(struct vcpu *v)
if ( (rc = setup_compat_l4(v)) )
goto done;
}
+ else
+ rc = pv_vcpu_init_tss_stacks(v);
done:
if ( rc )
diff --git a/xen/arch/x86/x86_64/entry.S b/xen/arch/x86/x86_64/entry.S
index 1dd9ccf6a2..997b75167c 100644
--- a/xen/arch/x86/x86_64/entry.S
+++ b/xen/arch/x86/x86_64/entry.S
@@ -742,3 +742,7 @@ autogen_stubs: /* Automatically generated stubs. */
.section .init.rodata
.size autogen_entrypoints, . - autogen_entrypoints
+
+ENTRY(context_switch_irqoff_stack)
+ mov %rcx, %rsp
+ jmp context_switch_irqoff
diff --git a/xen/include/asm-x86/config.h b/xen/include/asm-x86/config.h
index 9ef9d03ca7..46096cc666 100644
--- a/xen/include/asm-x86/config.h
+++ b/xen/include/asm-x86/config.h
@@ -202,7 +202,7 @@ extern unsigned char boot_edid_info[128];
/* Slot 260: per-domain mappings (including map cache). */
#define PERDOMAIN_VIRT_START (PML4_ADDR(260))
#define PERDOMAIN_SLOT_MBYTES (PML4_ENTRY_BYTES >> (20 + PAGETABLE_ORDER))
-#define PERDOMAIN_SLOTS 3
+#define PERDOMAIN_SLOTS 4
#define PERDOMAIN_VIRT_SLOT(s) (PERDOMAIN_VIRT_START + (s) * \
(PERDOMAIN_SLOT_MBYTES << 20))
/* Slot 261: machine-to-phys conversion table (256GB). */
@@ -310,6 +310,13 @@ extern unsigned long xen_phys_start;
#define ARG_XLAT_START(v) \
(ARG_XLAT_VIRT_START + ((v)->vcpu_id << ARG_XLAT_VA_SHIFT))
+/* per-vcpu Xen stacks and TSS. The fourth per-domain-mapping sub-area. */
+#define TSS_STACKS_VIRT_START PERDOMAIN_VIRT_SLOT(3)
+#define TSS_STACKS_VA_SHIFT (PAGE_SHIFT + STACK_ORDER + 1)
+#define STACKS_START(v) (TSS_STACKS_VIRT_START + \
+ ((v)->vcpu_id << TSS_STACKS_VA_SHIFT))
+#define TSS_START(v) (STACKS_START(v) + STACK_SIZE)
+
#define NATIVE_VM_ASSIST_VALID ((1UL << VMASST_TYPE_4gb_segments) | \
(1UL << VMASST_TYPE_4gb_segments_notify) | \
(1UL << VMASST_TYPE_writable_pagetables) | \
diff --git a/xen/include/asm-x86/mm.h b/xen/include/asm-x86/mm.h
index 84e112b830..6678bf04f5 100644
--- a/xen/include/asm-x86/mm.h
+++ b/xen/include/asm-x86/mm.h
@@ -636,4 +636,9 @@ static inline bool arch_mfn_in_directmap(unsigned long mfn)
return mfn <= (virt_to_mfn(eva - 1) + 1);
}
+void context_switch_irqoff(struct vcpu *prev, struct vcpu *next,
+ unsigned int cpu);
+void context_switch_irqoff_stack(struct vcpu *prev, struct vcpu *next,
+ unsigned int cpu, void *stack);
+
#endif /* __ASM_X86_MM_H__ */
--
2.13.6
_______________________________________________
Xen-devel mailing list
Xen-devel@lists.xenproject.org
https://lists.xenproject.org/mailman/listinfo/xen-devel
