From: Thomas Gleixner <tglx@linutronix.de>
To: LKML <linux-kernel@vger.kernel.org>
Cc: Paolo Bonzini <pbonzini@redhat.com>,
Radim Krcmar <rkrcmar@redhat.com>,
Peter Zijlstra <peterz@infradead.org>,
Juergen Gross <jgross@suse.com>,
Pavel Tatashin <pasha.tatashin@oracle.com>,
steven.sistare@oracle.com, daniel.m.jordan@oracle.com,
x86@kernel.org, kvm@vger.kernel.org
Subject: [patch 1/7] x86/kvmclock: Remove memblock dependency
Date: Fri, 06 Jul 2018 18:13:08 +0200 [thread overview]
Message-ID: <20180706162049.306418570@linutronix.de> (raw)
In-Reply-To: 20180706161307.733337643@linutronix.de
From: Pavel Tatashin <pasha.tatashin@oracle.com>
KVM clock is initialized later compared to other hypervisor clocks because
it has a dependency on the memblock allocator.
Bring it in line with other hypervisors by using memory from the BSS
instead of allocating it.
The benefits:
- Remove ifdef from common code
- Earlier availability of the clock
- Remove dependency on memblock, and reduce code
The downside:
- Static allocation of the per cpu data structures sized NR_CPUS * 64byte
Will be addressed in follow up patches.
[ tglx: Split out from larger series ]
Signed-off-by: Pavel Tatashin <pasha.tatashin@oracle.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Radim Krcmar <rkrcmar@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Juergen Gross <jgross@suse.com>
Cc: steven.sistare@oracle.com
Cc: daniel.m.jordan@oracle.com
Cc: x86@kernel.org
Cc: kvm@vger.kernel.org
---
arch/x86/kernel/kvm.c | 1
arch/x86/kernel/kvmclock.c | 66 +++++++--------------------------------------
arch/x86/kernel/setup.c | 4 --
3 files changed, 12 insertions(+), 59 deletions(-)
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -628,6 +628,7 @@ const __initconst struct hypervisor_x86
.name = "KVM",
.detect = kvm_detect,
.type = X86_HYPER_KVM,
+ .init.init_platform = kvmclock_init,
.init.guest_late_init = kvm_guest_init,
.init.x2apic_available = kvm_para_available,
};
--- a/arch/x86/kernel/kvmclock.c
+++ b/arch/x86/kernel/kvmclock.c
@@ -23,9 +23,9 @@
#include <asm/apic.h>
#include <linux/percpu.h>
#include <linux/hardirq.h>
-#include <linux/memblock.h>
#include <linux/sched.h>
#include <linux/sched/clock.h>
+#include <linux/mm.h>
#include <asm/mem_encrypt.h>
#include <asm/x86_init.h>
@@ -44,6 +44,13 @@ static int parse_no_kvmclock(char *arg)
}
early_param("no-kvmclock", parse_no_kvmclock);
+/* Aligned to page sizes to match whats mapped via vsyscalls to userspace */
+#define HV_CLOCK_SIZE (sizeof(struct pvclock_vsyscall_time_info) * NR_CPUS)
+#define WALL_CLOCK_SIZE (sizeof(struct pvclock_wall_clock))
+
+static u8 hv_clock_mem[PAGE_ALIGN(HV_CLOCK_SIZE)] __aligned(PAGE_SIZE);
+static u8 wall_clock_mem[PAGE_ALIGN(WALL_CLOCK_SIZE)] __aligned(PAGE_SIZE);
+
/* The hypervisor will put information about time periodically here */
static struct pvclock_vsyscall_time_info *hv_clock;
static struct pvclock_wall_clock *wall_clock;
@@ -244,43 +251,12 @@ static void kvm_shutdown(void)
native_machine_shutdown();
}
-static phys_addr_t __init kvm_memblock_alloc(phys_addr_t size,
- phys_addr_t align)
-{
- phys_addr_t mem;
-
- mem = memblock_alloc(size, align);
- if (!mem)
- return 0;
-
- if (sev_active()) {
- if (early_set_memory_decrypted((unsigned long)__va(mem), size))
- goto e_free;
- }
-
- return mem;
-e_free:
- memblock_free(mem, size);
- return 0;
-}
-
-static void __init kvm_memblock_free(phys_addr_t addr, phys_addr_t size)
-{
- if (sev_active())
- early_set_memory_encrypted((unsigned long)__va(addr), size);
-
- memblock_free(addr, size);
-}
-
void __init kvmclock_init(void)
{
struct pvclock_vcpu_time_info *vcpu_time;
- unsigned long mem, mem_wall_clock;
- int size, cpu, wall_clock_size;
+ int cpu;
u8 flags;
- size = PAGE_ALIGN(sizeof(struct pvclock_vsyscall_time_info)*NR_CPUS);
-
if (!kvm_para_available())
return;
@@ -290,28 +266,11 @@ void __init kvmclock_init(void)
} else if (!(kvmclock && kvm_para_has_feature(KVM_FEATURE_CLOCKSOURCE)))
return;
- wall_clock_size = PAGE_ALIGN(sizeof(struct pvclock_wall_clock));
- mem_wall_clock = kvm_memblock_alloc(wall_clock_size, PAGE_SIZE);
- if (!mem_wall_clock)
- return;
-
- wall_clock = __va(mem_wall_clock);
- memset(wall_clock, 0, wall_clock_size);
-
- mem = kvm_memblock_alloc(size, PAGE_SIZE);
- if (!mem) {
- kvm_memblock_free(mem_wall_clock, wall_clock_size);
- wall_clock = NULL;
- return;
- }
-
- hv_clock = __va(mem);
- memset(hv_clock, 0, size);
+ wall_clock = (struct pvclock_wall_clock *)wall_clock_mem;
+ hv_clock = (struct pvclock_vsyscall_time_info *)hv_clock_mem;
if (kvm_register_clock("primary cpu clock")) {
hv_clock = NULL;
- kvm_memblock_free(mem, size);
- kvm_memblock_free(mem_wall_clock, wall_clock_size);
wall_clock = NULL;
return;
}
@@ -354,13 +313,10 @@ int __init kvm_setup_vsyscall_timeinfo(v
int cpu;
u8 flags;
struct pvclock_vcpu_time_info *vcpu_time;
- unsigned int size;
if (!hv_clock)
return 0;
- size = PAGE_ALIGN(sizeof(struct pvclock_vsyscall_time_info)*NR_CPUS);
-
cpu = get_cpu();
vcpu_time = &hv_clock[cpu].pvti;
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -1197,10 +1197,6 @@ void __init setup_arch(char **cmdline_p)
memblock_find_dma_reserve();
-#ifdef CONFIG_KVM_GUEST
- kvmclock_init();
-#endif
-
tsc_early_delay_calibrate();
if (!early_xdbc_setup_hardware())
early_xdbc_register_console();
next prev parent reply other threads:[~2018-07-06 16:24 UTC|newest]
Thread overview: 27+ messages / expand[flat|nested] mbox.gz Atom feed top
2018-07-06 16:13 [patch 0/7] x86/kvmclock: Remove memblock dependency and further cleanups Thomas Gleixner
2018-07-06 16:13 ` Thomas Gleixner [this message]
2018-07-06 16:13 ` [patch 2/7] x86/kvmclock: Remove page size requirement from wall_clock Thomas Gleixner
2018-07-12 2:15 ` Pavel Tatashin
2018-07-06 16:13 ` [patch 3/7] x86/kvmclock: Decrapify kvm_register_clock() Thomas Gleixner
2018-07-06 17:38 ` Paolo Bonzini
2018-07-06 17:39 ` Thomas Gleixner
2018-07-12 2:24 ` Pavel Tatashin
2018-07-06 16:13 ` [patch 4/7] x86/kvmclock: Cleanup the code Thomas Gleixner
2018-07-06 17:39 ` Paolo Bonzini
2018-07-09 9:05 ` Peter Zijlstra
2018-07-09 10:03 ` Thomas Gleixner
2018-07-09 11:32 ` Paolo Bonzini
2018-07-06 16:13 ` [patch 5/7] x86/kvmclock: Mark variables __initdata and __ro_after_init Thomas Gleixner
2018-07-12 2:31 ` Pavel Tatashin
2018-07-06 16:13 ` [patch 6/7] x86/kvmclock: Move kvmclock vsyscall param and init to kvmclock Thomas Gleixner
2018-07-06 17:43 ` Paolo Bonzini
2018-07-06 19:23 ` Thomas Gleixner
2018-07-12 2:52 ` Pavel Tatashin
2018-07-06 16:13 ` [patch 7/7] x86/kvmclock: Switch kvmclock data to a PER_CPU variable Thomas Gleixner
2018-07-12 3:12 ` Pavel Tatashin
2018-07-06 17:47 ` [patch 0/7] x86/kvmclock: Remove memblock dependency and further cleanups Paolo Bonzini
2018-07-06 23:51 ` Brijesh Singh
2018-07-09 9:22 ` [patch 8/7] x86/kvmclock: Avoid TSC recalibration Peter Zijlstra
2018-07-12 2:12 ` [patch 0/7] x86/kvmclock: Remove memblock dependency and further cleanups Pavel Tatashin
2018-07-13 22:51 ` Thomas Gleixner
2018-07-14 0:20 ` Pavel Tatashin
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=20180706162049.306418570@linutronix.de \
--to=tglx@linutronix.de \
--cc=daniel.m.jordan@oracle.com \
--cc=jgross@suse.com \
--cc=kvm@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=pasha.tatashin@oracle.com \
--cc=pbonzini@redhat.com \
--cc=peterz@infradead.org \
--cc=rkrcmar@redhat.com \
--cc=steven.sistare@oracle.com \
--cc=x86@kernel.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 NNTP newsgroup(s).