From: Elias El Yandouzi <eliasely@amazon.com>
To: <xen-devel@lists.xenproject.org>
Cc: julien@xen.org, pdurrant@amazon.com, dwmw@amazon.com,
"Hongyan Xia" <hongyxia@amazon.com>,
"Jan Beulich" <jbeulich@suse.com>,
"Andrew Cooper" <andrew.cooper3@citrix.com>,
"Roger Pau Monné" <roger.pau@citrix.com>,
"Julien Grall" <jgrall@amazon.com>,
"Elias El Yandouzi" <eliasely@amazon.com>
Subject: [PATCH V3 (resend) 01/19] x86: Create per-domain mapping of guest_root_pt
Date: Mon, 13 May 2024 13:40:28 +0000 [thread overview]
Message-ID: <20240513134046.82605-2-eliasely@amazon.com> (raw)
In-Reply-To: <20240513134046.82605-1-eliasely@amazon.com>
From: Hongyan Xia <hongyxia@amazon.com>
Create a per-domain mapping of PV guest_root_pt as direct map is being
removed.
Note that we do not map and unmap root_pgt for now since it is still a
xenheap page.
Signed-off-by: Hongyan Xia <hongyxia@amazon.com>
Signed-off-by: Julien Grall <jgrall@amazon.com>
Signed-off-by: Elias El Yandouzi <eliasely@amazon.com>
----
Changes in V3:
* Rename SHADOW_ROOT
* Haven't addressed the potentially over-allocation issue as I don't get it
Changes in V2:
* Rework the shadow perdomain mapping solution in the follow-up patches
Changes since Hongyan's version:
* Remove the final dot in the commit title
diff --git a/xen/arch/x86/include/asm/config.h b/xen/arch/x86/include/asm/config.h
index ab7288cb36..5d710384df 100644
--- a/xen/arch/x86/include/asm/config.h
+++ b/xen/arch/x86/include/asm/config.h
@@ -203,7 +203,7 @@ 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 4: mirror of per-domain mappings (for compat xlat area accesses). */
@@ -317,6 +317,14 @@ extern unsigned long xen_phys_start;
#define ARG_XLAT_START(v) \
(ARG_XLAT_VIRT_START + ((v)->vcpu_id << ARG_XLAT_VA_SHIFT))
+/* pv_root_pt mapping area. The fourth per-domain-mapping sub-area */
+#define PV_ROOT_PT_MAPPING_VIRT_START PERDOMAIN_VIRT_SLOT(3)
+#define PV_ROOT_PT_MAPPING_ENTRIES MAX_VIRT_CPUS
+
+/* The address of a particular VCPU's PV_ROOT_PT */
+#define PV_ROOT_PT_MAPPING_VCPU_VIRT_START(v) \
+ (PV_ROOT_PT_MAPPING_VIRT_START + ((v)->vcpu_id * PAGE_SIZE))
+
#define ELFSIZE 64
#define ARCH_CRASH_SAVE_VMCOREINFO
diff --git a/xen/arch/x86/include/asm/domain.h b/xen/arch/x86/include/asm/domain.h
index f5daeb182b..8a97530607 100644
--- a/xen/arch/x86/include/asm/domain.h
+++ b/xen/arch/x86/include/asm/domain.h
@@ -272,6 +272,7 @@ struct time_scale {
struct pv_domain
{
l1_pgentry_t **gdt_ldt_l1tab;
+ l1_pgentry_t **root_pt_l1tab;
atomic_t nr_l4_pages;
diff --git a/xen/arch/x86/mm.c b/xen/arch/x86/mm.c
index d968bbbc73..efdf20f775 100644
--- a/xen/arch/x86/mm.c
+++ b/xen/arch/x86/mm.c
@@ -505,6 +505,13 @@ void share_xen_page_with_guest(struct page_info *page, struct domain *d,
nrspin_unlock(&d->page_alloc_lock);
}
+#define pv_root_pt_idx(v) \
+ ((v)->vcpu_id >> PAGETABLE_ORDER)
+
+#define pv_root_pt_pte(v) \
+ ((v)->domain->arch.pv.root_pt_l1tab[pv_root_pt_idx(v)] + \
+ ((v)->vcpu_id & (L1_PAGETABLE_ENTRIES - 1)))
+
void make_cr3(struct vcpu *v, mfn_t mfn)
{
struct domain *d = v->domain;
@@ -524,6 +531,13 @@ void write_ptbase(struct vcpu *v)
if ( is_pv_vcpu(v) && v->domain->arch.pv.xpti )
{
+ mfn_t guest_root_pt = _mfn(MASK_EXTR(v->arch.cr3, PAGE_MASK));
+ l1_pgentry_t *pte = pv_root_pt_pte(v);
+
+ ASSERT(v == current);
+
+ l1e_write(pte, l1e_from_mfn(guest_root_pt, __PAGE_HYPERVISOR_RO));
+
cpu_info->root_pgt_changed = true;
cpu_info->pv_cr3 = __pa(this_cpu(root_pgt));
if ( new_cr4 & X86_CR4_PCIDE )
diff --git a/xen/arch/x86/pv/domain.c b/xen/arch/x86/pv/domain.c
index 2a445bb17b..1b025986f7 100644
--- a/xen/arch/x86/pv/domain.c
+++ b/xen/arch/x86/pv/domain.c
@@ -288,6 +288,21 @@ static void pv_destroy_gdt_ldt_l1tab(struct vcpu *v)
1U << GDT_LDT_VCPU_SHIFT);
}
+static int pv_create_root_pt_l1tab(struct vcpu *v)
+{
+ return create_perdomain_mapping(v->domain,
+ PV_ROOT_PT_MAPPING_VCPU_VIRT_START(v),
+ 1, v->domain->arch.pv.root_pt_l1tab,
+ NULL);
+}
+
+static void pv_destroy_root_pt_l1tab(struct vcpu *v)
+
+{
+ destroy_perdomain_mapping(v->domain,
+ PV_ROOT_PT_MAPPING_VCPU_VIRT_START(v), 1);
+}
+
void pv_vcpu_destroy(struct vcpu *v)
{
if ( is_pv_32bit_vcpu(v) )
@@ -297,6 +312,7 @@ void pv_vcpu_destroy(struct vcpu *v)
}
pv_destroy_gdt_ldt_l1tab(v);
+ pv_destroy_root_pt_l1tab(v);
XFREE(v->arch.pv.trap_ctxt);
}
@@ -311,6 +327,13 @@ int pv_vcpu_initialise(struct vcpu *v)
if ( rc )
return rc;
+ if ( v->domain->arch.pv.xpti )
+ {
+ rc = pv_create_root_pt_l1tab(v);
+ if ( rc )
+ goto done;
+ }
+
BUILD_BUG_ON(X86_NR_VECTORS * sizeof(*v->arch.pv.trap_ctxt) >
PAGE_SIZE);
v->arch.pv.trap_ctxt = xzalloc_array(struct trap_info, X86_NR_VECTORS);
@@ -346,10 +369,12 @@ void pv_domain_destroy(struct domain *d)
destroy_perdomain_mapping(d, GDT_LDT_VIRT_START,
GDT_LDT_MBYTES << (20 - PAGE_SHIFT));
+ destroy_perdomain_mapping(d, PV_ROOT_PT_MAPPING_VIRT_START, PV_ROOT_PT_MAPPING_ENTRIES);
XFREE(d->arch.pv.cpuidmasks);
FREE_XENHEAP_PAGE(d->arch.pv.gdt_ldt_l1tab);
+ FREE_XENHEAP_PAGE(d->arch.pv.root_pt_l1tab);
}
void noreturn cf_check continue_pv_domain(void);
@@ -371,6 +396,12 @@ int pv_domain_initialise(struct domain *d)
goto fail;
clear_page(d->arch.pv.gdt_ldt_l1tab);
+ d->arch.pv.root_pt_l1tab =
+ alloc_xenheap_pages(0, MEMF_node(domain_to_node(d)));
+ if ( !d->arch.pv.root_pt_l1tab )
+ goto fail;
+ clear_page(d->arch.pv.root_pt_l1tab);
+
if ( levelling_caps & ~LCAP_faulting &&
(d->arch.pv.cpuidmasks = xmemdup(&cpuidmask_defaults)) == NULL )
goto fail;
@@ -381,6 +412,11 @@ int pv_domain_initialise(struct domain *d)
if ( rc )
goto fail;
+ rc = create_perdomain_mapping(d, PV_ROOT_PT_MAPPING_VIRT_START,
+ PV_ROOT_PT_MAPPING_ENTRIES, NULL, NULL);
+ if ( rc )
+ goto fail;
+
d->arch.ctxt_switch = &pv_csw;
d->arch.pv.xpti = is_hardware_domain(d) ? opt_xpti_hwdom : opt_xpti_domu;
diff --git a/xen/arch/x86/x86_64/asm-offsets.c b/xen/arch/x86/x86_64/asm-offsets.c
index 630bdc3945..c1ae5013af 100644
--- a/xen/arch/x86/x86_64/asm-offsets.c
+++ b/xen/arch/x86/x86_64/asm-offsets.c
@@ -80,6 +80,7 @@ void __dummy__(void)
#undef OFFSET_EF
+ OFFSET(VCPU_id, struct vcpu, vcpu_id);
OFFSET(VCPU_processor, struct vcpu, processor);
OFFSET(VCPU_domain, struct vcpu, domain);
OFFSET(VCPU_vcpu_info, struct vcpu, vcpu_info_area.map);
diff --git a/xen/arch/x86/x86_64/entry.S b/xen/arch/x86/x86_64/entry.S
index df015589ce..c1377da7a5 100644
--- a/xen/arch/x86/x86_64/entry.S
+++ b/xen/arch/x86/x86_64/entry.S
@@ -162,7 +162,15 @@ FUNC_LOCAL(restore_all_guest)
and %rsi, %rdi
and %r9, %rsi
add %rcx, %rdi
+
+ /*
+ * The address in the vCPU cr3 is always mapped in the per-domain
+ * pv_root_pt virt area.
+ */
+ imul $PAGE_SIZE, VCPU_id(%rbx), %esi
+ movabs $PV_ROOT_PT_MAPPING_VIRT_START, %rcx
add %rcx, %rsi
+
mov $ROOT_PAGETABLE_FIRST_XEN_SLOT, %ecx
mov root_table_offset(SH_LINEAR_PT_VIRT_START)*8(%rsi), %r8
mov %r8, root_table_offset(SH_LINEAR_PT_VIRT_START)*8(%rdi)
--
2.40.1
next prev parent reply other threads:[~2024-05-13 13:41 UTC|newest]
Thread overview: 66+ messages / expand[flat|nested] mbox.gz Atom feed top
2024-05-13 13:40 [PATCH V3 (resend) 00/19] Remove the directmap Elias El Yandouzi
2024-05-13 13:40 ` Elias El Yandouzi [this message]
2024-05-14 14:51 ` [PATCH V3 (resend) 01/19] x86: Create per-domain mapping of guest_root_pt Jan Beulich
2024-05-15 18:25 ` Elias El Yandouzi
2024-05-16 7:17 ` Jan Beulich
2024-06-13 16:31 ` Elias El Yandouzi
2024-06-14 6:23 ` Jan Beulich
2024-06-17 7:33 ` Roger Pau Monné
2024-05-13 13:40 ` [PATCH V3 (resend) 02/19] x86/pv: Domheap pages should be mapped while relocating initrd Elias El Yandouzi
2024-05-13 15:40 ` Roger Pau Monné
2024-05-13 13:40 ` [PATCH V3 (resend) 03/19] x86/pv: Rewrite how building PV dom0 handles domheap mappings Elias El Yandouzi
2024-05-13 16:49 ` Roger Pau Monné
2024-05-14 14:58 ` Jan Beulich
2024-05-14 15:03 ` Jan Beulich
2024-05-13 13:40 ` [PATCH V3 (resend) 04/19] x86: Lift mapcache variable to the arch level Elias El Yandouzi
2024-05-14 8:21 ` Roger Pau Monné
2024-05-15 13:11 ` Jan Beulich
2024-05-13 13:40 ` [PATCH V3 (resend) 05/19] x86/mapcache: Initialise the mapcache for the idle domain Elias El Yandouzi
2024-05-14 8:42 ` Roger Pau Monné
2024-05-15 13:44 ` Jan Beulich
2024-05-13 13:40 ` [PATCH V3 (resend) 06/19] x86: Add a boot option to enable and disable the direct map Elias El Yandouzi
2024-05-14 9:20 ` Roger Pau Monné
2024-05-14 10:20 ` Roger Pau Monné
2024-05-15 13:54 ` Jan Beulich
2024-05-16 9:19 ` Roger Pau Monné
2024-05-16 9:24 ` Jan Beulich
2024-05-15 13:59 ` Jan Beulich
2024-05-15 16:02 ` Jan Beulich
2024-05-13 13:40 ` [PATCH V3 (resend) 07/19] xen/x86: Add support for the PMAP Elias El Yandouzi
2024-05-14 9:40 ` Roger Pau Monné
2024-05-14 9:43 ` Jan Beulich
2024-05-14 10:22 ` Roger Pau Monné
2024-05-14 10:26 ` Jan Beulich
2024-05-14 11:51 ` Roger Pau Monné
2024-05-14 12:33 ` Jan Beulich
2024-05-13 13:40 ` [PATCH V3 (resend) 08/19] xen/x86: Add build assertion for fixmap entries Elias El Yandouzi
2024-05-14 9:42 ` Roger Pau Monné
2024-05-14 9:45 ` Jan Beulich
2024-05-15 14:03 ` Jan Beulich
2024-05-13 13:40 ` [PATCH V3 (resend) 09/19] x86/domain_page: Remove the fast paths when mfn is not in the directmap Elias El Yandouzi
2024-05-14 11:48 ` Roger Pau Monné
2024-05-15 14:21 ` Jan Beulich
2024-05-13 13:40 ` [PATCH V3 (resend) 10/19] xen/page_alloc: Add a path for xenheap when there is no direct map Elias El Yandouzi
2024-05-14 13:07 ` Roger Pau Monné
2024-05-15 15:13 ` Jan Beulich
2024-05-13 13:40 ` [PATCH V3 (resend) 11/19] x86/setup: Leave early boot slightly earlier Elias El Yandouzi
2024-05-14 14:11 ` Roger Pau Monné
2024-05-15 15:22 ` Jan Beulich
2024-05-13 13:40 ` [PATCH V3 (resend) 12/19] x86/setup: vmap heap nodes when they are outside the direct map Elias El Yandouzi
2024-05-14 15:02 ` Roger Pau Monné
2024-05-15 15:28 ` Jan Beulich
2024-05-13 13:40 ` [PATCH V3 (resend) 13/19] x86/setup: Do not create valid mappings when directmap=no Elias El Yandouzi
2024-05-14 15:39 ` Roger Pau Monné
2024-05-15 15:50 ` Jan Beulich
2024-05-15 15:59 ` Jan Beulich
2024-05-13 13:40 ` [PATCH V3 (resend) 14/19] Rename mfn_to_virt() calls Elias El Yandouzi
2024-05-14 15:45 ` Roger Pau Monné
2024-05-14 16:22 ` Jan Beulich
2024-05-15 9:38 ` Roger Pau Monné
2024-05-15 9:42 ` Jan Beulich
2024-05-16 8:57 ` Jan Beulich
2024-05-13 13:40 ` [PATCH V3 (resend) 15/19] Rename maddr_to_virt() calls Elias El Yandouzi
2024-05-13 13:40 ` [PATCH V3 (resend) 16/19] xen/arm32: mm: Rename 'first' to 'root' in init_secondary_pagetables() Elias El Yandouzi
2024-05-13 13:40 ` [PATCH V3 (resend) 17/19] xen/arm64: mm: Use per-pCPU page-tables Elias El Yandouzi
2024-05-13 13:40 ` [PATCH V3 (resend) 18/19] xen/arm64: Implement a mapcache for arm64 Elias El Yandouzi
2024-05-13 13:40 ` [PATCH V3 (resend) 19/19] xen/arm64: Allow the admin to enable/disable the directmap Elias El Yandouzi
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20240513134046.82605-2-eliasely@amazon.com \
--to=eliasely@amazon.com \
--cc=andrew.cooper3@citrix.com \
--cc=dwmw@amazon.com \
--cc=hongyxia@amazon.com \
--cc=jbeulich@suse.com \
--cc=jgrall@amazon.com \
--cc=julien@xen.org \
--cc=pdurrant@amazon.com \
--cc=roger.pau@citrix.com \
--cc=xen-devel@lists.xenproject.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for read-only IMAP folder(s) and NNTP newsgroup(s).