| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-Id: <20211116141054.17800-2-jgross@suse.com>
Date: Tue, 16 Nov 2021 15:10:51 +0100
From: Juergen Gross <jgross@...e.com>
To: kvm@...r.kernel.org, x86@...nel.org, linux-doc@...r.kernel.org,
linux-kernel@...r.kernel.org
Cc: Juergen Gross <jgross@...e.com>, Jonathan Corbet <corbet@....net>,
Paolo Bonzini <pbonzini@...hat.com>,
Sean Christopherson <seanjc@...gle.com>,
Vitaly Kuznetsov <vkuznets@...hat.com>,
Wanpeng Li <wanpengli@...cent.com>,
Jim Mattson <jmattson@...gle.com>,
Joerg Roedel <joro@...tes.org>,
Thomas Gleixner <tglx@...utronix.de>,
Ingo Molnar <mingo@...hat.com>, Borislav Petkov <bp@...en8.de>,
Dave Hansen <dave.hansen@...ux.intel.com>,
"H. Peter Anvin" <hpa@...or.com>
Subject: [PATCH v3 1/4] x86/kvm: add boot parameter for adding vcpu-id bits
Today the maximum vcpu-id of a kvm guest's vcpu on x86 systems is set
via a #define in a header file.
In order to support higher vcpu-ids without generally increasing the
memory consumption of guests on the host (some guest structures contain
arrays sized by KVM_MAX_VCPU_IDS) add a boot parameter for adding some
bits to the vcpu-id. Additional bits are needed as the vcpu-id is
constructed via bit-wise concatenation of socket-id, core-id, etc.
As those ids maximum values are not always a power of 2, the vcpu-ids
are sparse.
The additional number of bits needed is basically the number of
topology levels with a non-power-of-2 maximum value, excluding the top
most level.
The default value of the new parameter will be 2 in order to support
today's possible topologies. The special value of -1 will use the
number of bits needed for a guest with the current host's topology.
Calculating the maximum vcpu-id dynamically requires to allocate the
arrays using KVM_MAX_VCPU_IDS as the size dynamically.
Signed-of-by: Juergen Gross <jgross@...e.com>
---
V2:
- switch to specifying additional bits (based on comment by Vitaly
Kuznetsov)
V3:
- set default of new parameter to 2 (Eduardo Habkost)
- deliberately NOT add another bit for topology_max_die_per_package()
== 1 AND parameter being -1, as this would make this parameter
setting always equivalent to specifying "2"
Signed-off-by: Juergen Gross <jgross@...e.com>
---
.../admin-guide/kernel-parameters.txt | 18 ++++++++++++
arch/x86/include/asm/kvm_host.h | 16 ++--------
arch/x86/kvm/ioapic.c | 12 +++++++-
arch/x86/kvm/ioapic.h | 4 +--
arch/x86/kvm/x86.c | 29 +++++++++++++++++++
5 files changed, 63 insertions(+), 16 deletions(-)
diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index 9725c546a0d4..e269c3f66ba4 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -2445,6 +2445,24 @@
feature (tagged TLBs) on capable Intel chips.
Default is 1 (enabled)
+ kvm.vcpu_id_add_bits=
+ [KVM,X86] The vcpu-ids of guests are sparse, as they
+ are constructed by bit-wise concatenation of the ids of
+ the different topology levels (sockets, cores, threads).
+
+ This parameter specifies how many additional bits the
+ maximum vcpu-id needs compared to the maximum number of
+ vcpus.
+
+ Normally this value is the number of topology levels
+ without the threads level and without the highest
+ level.
+
+ The special value -1 can be used to support guests
+ with the same topology is the host.
+
+ Default: 2
+
l1d_flush= [X86,INTEL]
Control mitigation for L1D based snooping vulnerability.
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index e5d8700319cc..bcef56f1039a 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -38,19 +38,7 @@
#define __KVM_HAVE_ARCH_VCPU_DEBUGFS
#define KVM_MAX_VCPUS 1024
-
-/*
- * In x86, the VCPU ID corresponds to the APIC ID, and APIC IDs
- * might be larger than the actual number of VCPUs because the
- * APIC ID encodes CPU topology information.
- *
- * In the worst case, we'll need less than one extra bit for the
- * Core ID, and less than one extra bit for the Package (Die) ID,
- * so ratio of 4 should be enough.
- */
-#define KVM_VCPU_ID_RATIO 4
-#define KVM_MAX_VCPU_IDS (KVM_MAX_VCPUS * KVM_VCPU_ID_RATIO)
-
+#define KVM_MAX_VCPU_IDS kvm_max_vcpu_ids()
/* memory slots that are not exposed to userspace */
#define KVM_PRIVATE_MEM_SLOTS 3
@@ -1621,6 +1609,8 @@ extern u64 kvm_max_tsc_scaling_ratio;
extern u64 kvm_default_tsc_scaling_ratio;
/* bus lock detection supported? */
extern bool kvm_has_bus_lock_exit;
+/* maximum vcpu-id */
+unsigned int kvm_max_vcpu_ids(void);
extern u64 kvm_mce_cap_supported;
diff --git a/arch/x86/kvm/ioapic.c b/arch/x86/kvm/ioapic.c
index 816a82515dcd..64ba9b1c8b3d 100644
--- a/arch/x86/kvm/ioapic.c
+++ b/arch/x86/kvm/ioapic.c
@@ -685,11 +685,21 @@ static const struct kvm_io_device_ops ioapic_mmio_ops = {
int kvm_ioapic_init(struct kvm *kvm)
{
struct kvm_ioapic *ioapic;
+ size_t sz;
int ret;
- ioapic = kzalloc(sizeof(struct kvm_ioapic), GFP_KERNEL_ACCOUNT);
+ sz = sizeof(struct kvm_ioapic) +
+ sizeof(*ioapic->rtc_status.dest_map.map) *
+ BITS_TO_LONGS(KVM_MAX_VCPU_IDS) +
+ sizeof(*ioapic->rtc_status.dest_map.vectors) *
+ (KVM_MAX_VCPU_IDS);
+ ioapic = kzalloc(sz, GFP_KERNEL_ACCOUNT);
if (!ioapic)
return -ENOMEM;
+ ioapic->rtc_status.dest_map.map = (void *)(ioapic + 1);
+ ioapic->rtc_status.dest_map.vectors =
+ (void *)(ioapic->rtc_status.dest_map.map +
+ BITS_TO_LONGS(KVM_MAX_VCPU_IDS));
spin_lock_init(&ioapic->lock);
INIT_DELAYED_WORK(&ioapic->eoi_inject, kvm_ioapic_eoi_inject_work);
kvm->arch.vioapic = ioapic;
diff --git a/arch/x86/kvm/ioapic.h b/arch/x86/kvm/ioapic.h
index e66e620c3bed..623a3c5afad7 100644
--- a/arch/x86/kvm/ioapic.h
+++ b/arch/x86/kvm/ioapic.h
@@ -39,13 +39,13 @@ struct kvm_vcpu;
struct dest_map {
/* vcpu bitmap where IRQ has been sent */
- DECLARE_BITMAP(map, KVM_MAX_VCPU_IDS);
+ unsigned long *map;
/*
* Vector sent to a given vcpu, only valid when
* the vcpu's bit in map is set
*/
- u8 vectors[KVM_MAX_VCPU_IDS];
+ u8 *vectors;
};
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 259f719014c9..61bab2bdeefb 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -80,6 +80,7 @@
#include <asm/intel_pt.h>
#include <asm/emulate_prefix.h>
#include <asm/sgx.h>
+#include <asm/topology.h>
#include <clocksource/hyperv_timer.h>
#define CREATE_TRACE_POINTS
@@ -186,6 +187,34 @@ module_param(force_emulation_prefix, bool, S_IRUGO);
int __read_mostly pi_inject_timer = -1;
module_param(pi_inject_timer, bint, S_IRUGO | S_IWUSR);
+static int __read_mostly vcpu_id_add_bits = 2;
+module_param(vcpu_id_add_bits, int, S_IRUGO);
+
+unsigned int kvm_max_vcpu_ids(void)
+{
+ int n_bits = fls(KVM_MAX_VCPUS - 1);
+
+ if (vcpu_id_add_bits < -1 || vcpu_id_add_bits > (32 - n_bits)) {
+ pr_err("Invalid value of vcpu_id_add_bits=%d parameter!\n",
+ vcpu_id_add_bits);
+ vcpu_id_add_bits = 2;
+ }
+
+ if (vcpu_id_add_bits >= 0) {
+ n_bits += vcpu_id_add_bits;
+ } else {
+ n_bits++; /* One additional bit for core level. */
+ if (topology_max_die_per_package() > 1)
+ n_bits++; /* One additional bit for die level. */
+ }
+
+ if (!n_bits)
+ n_bits = 1;
+
+ return 1U << n_bits;
+}
+EXPORT_SYMBOL_GPL(kvm_max_vcpu_ids);
+
/*
* Restoring the host value for MSRs that are only consumed when running in
* usermode, e.g. SYSCALL MSRs and TSC_AUX, can be deferred until the CPU
--
2.26.2
Powered by blists - more mailing lists