From: Pavel Tatashin <pasha.tatashin@oracle.com>
To: steven.sistare@oracle.com, daniel.m.jordan@oracle.com,
linux@armlinux.org.uk, schwidefsky@de.ibm.com,
heiko.carstens@de.ibm.com, john.stultz@linaro.org,
sboyd@codeaurora.org, x86@kernel.org,
linux-kernel@vger.kernel.org, mingo@redhat.com,
tglx@linutronix.de, hpa@zytor.com, douly.fnst@cn.fujitsu.com,
peterz@infradead.org, prarit@redhat.com, feng.tang@intel.com,
pmladek@suse.com, gnomes@lxorguk.ukuu.org.uk,
linux-s390@vger.kernel.org, pasha.tatashin@oracle.com,
boris.ostrovsky@oracle.com, jgross@suse.com, pbonzini@redhat.com
Subject: [PATCH v14 01/25] x86/kvmclock: Remove memblock dependency
Date: Tue, 17 Jul 2018 22:21:47 -0400 [thread overview]
Message-ID: <20180718022211.6259-2-pasha.tatashin@oracle.com> (raw)
In-Reply-To: <20180718022211.6259-1-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>
Acked-by: Paolo Bonzini <pbonzini@redhat.com>
---
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(-)
diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
index 5b2300b818af..c65c232d3ddd 100644
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -628,6 +628,7 @@ const __initconst struct hypervisor_x86 x86_hyper_kvm = {
.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,
};
diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c
index bf8d1eb7fca3..890e9e58e4bf 100644
--- 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(void)
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;
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 2f86d883dd95..da1dbd99cb6e 100644
--- 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();
--
2.18.0
next prev parent reply other threads:[~2018-07-18 2:21 UTC|newest]
Thread overview: 44+ messages / expand[flat|nested] mbox.gz Atom feed top
2018-07-18 2:21 [PATCH v14 00/25] Early boot time stamps Pavel Tatashin
2018-07-18 2:21 ` Pavel Tatashin [this message]
2018-07-18 2:21 ` [PATCH v14 02/25] x86/kvmclock: Remove page size requirement from wall_clock Pavel Tatashin
2018-07-18 2:21 ` [PATCH v14 03/25] x86/kvmclock: Decrapify kvm_register_clock() Pavel Tatashin
2018-07-18 2:21 ` [PATCH v14 04/25] x86/kvmclock: Cleanup the code Pavel Tatashin
2018-07-18 2:21 ` [PATCH v14 05/25] x86/kvmclock: Mark variables __initdata and __ro_after_init Pavel Tatashin
2018-07-18 2:21 ` [PATCH v14 06/25] x86/kvmclock: Move kvmclock vsyscall param and init to kvmclock Pavel Tatashin
2018-07-18 2:21 ` [PATCH v14 07/25] x86/kvmclock: Switch kvmclock data to a PER_CPU variable Pavel Tatashin
2018-07-18 2:21 ` [PATCH v14 08/25] x86/kvmclock: Avoid TSC recalibration Pavel Tatashin
2018-07-18 11:14 ` Paolo Bonzini
2018-07-18 13:33 ` Pavel Tatashin
2018-07-18 2:21 ` [PATCH v14 09/25] x86: text_poke() may access uninitialized struct pages Pavel Tatashin
2018-07-18 2:21 ` [PATCH v14 10/25] x86: initialize static branching early Pavel Tatashin
2018-07-18 2:21 ` [PATCH v14 11/25] x86/CPU: Call detect_nopl() only on the BSP Pavel Tatashin
2018-07-18 2:21 ` [PATCH v14 12/25] x86/tsc: redefine notsc to behave as tsc=unstable Pavel Tatashin
2018-07-18 2:21 ` [PATCH v14 13/25] x86/xen/time: initialize pv xen time in init_hypervisor_platform Pavel Tatashin
2018-07-18 2:22 ` [PATCH v14 14/25] x86/xen/time: output xen sched_clock time from 0 Pavel Tatashin
2018-07-18 2:22 ` [PATCH v14 15/25] s390/time: add read_persistent_wall_and_boot_offset() Pavel Tatashin
2018-07-18 2:22 ` [PATCH v14 16/25] time: replace read_boot_clock64() with read_persistent_wall_and_boot_offset() Pavel Tatashin
2018-07-18 2:22 ` [PATCH v14 17/25] time: default boot time offset to local_clock() Pavel Tatashin
2018-07-18 2:22 ` [PATCH v14 18/25] s390/time: remove read_boot_clock64() Pavel Tatashin
2018-07-18 2:22 ` [PATCH v14 19/25] ARM/time: " Pavel Tatashin
2018-07-18 2:22 ` [PATCH v14 20/25] x86/tsc: calibrate tsc only once Pavel Tatashin
2018-07-19 5:33 ` Dou Liyang
2018-07-19 6:25 ` Thomas Gleixner
2018-07-19 6:48 ` Dou Liyang
2018-07-19 10:33 ` Peter Zijlstra
2018-07-19 11:01 ` Thomas Gleixner
2018-07-19 15:58 ` Pavel Tatashin
2018-07-19 16:19 ` Thomas Gleixner
2018-07-19 16:49 ` Pavel Tatashin
2018-07-19 18:38 ` Pavel Tatashin
2018-07-19 20:44 ` Thomas Gleixner
2018-07-19 20:46 ` Pavel Tatashin
2018-07-23 9:28 ` Alan Cox
2018-07-18 2:22 ` [PATCH v14 21/25] x86/tsc: initialize cyc2ns when tsc freq. is determined Pavel Tatashin
2018-07-18 2:22 ` [PATCH v14 22/25] x86/tsc: use tsc early Pavel Tatashin
2018-07-18 2:22 ` [PATCH v14 23/25] sched: move sched clock initialization and merge with generic clock Pavel Tatashin
2018-07-18 2:22 ` [PATCH v14 24/25] sched: early boot clock Pavel Tatashin
2018-07-19 10:39 ` Peter Zijlstra
2018-07-19 14:16 ` Pavel Tatashin
2018-07-18 2:22 ` [PATCH v14 25/25] sched: use static key for sched_clock_running Pavel Tatashin
2018-07-19 10:48 ` Peter Zijlstra
2018-07-19 14:24 ` 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=20180718022211.6259-2-pasha.tatashin@oracle.com \
--to=pasha.tatashin@oracle.com \
--cc=boris.ostrovsky@oracle.com \
--cc=daniel.m.jordan@oracle.com \
--cc=douly.fnst@cn.fujitsu.com \
--cc=feng.tang@intel.com \
--cc=gnomes@lxorguk.ukuu.org.uk \
--cc=heiko.carstens@de.ibm.com \
--cc=hpa@zytor.com \
--cc=jgross@suse.com \
--cc=john.stultz@linaro.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-s390@vger.kernel.org \
--cc=linux@armlinux.org.uk \
--cc=mingo@redhat.com \
--cc=pbonzini@redhat.com \
--cc=peterz@infradead.org \
--cc=pmladek@suse.com \
--cc=prarit@redhat.com \
--cc=sboyd@codeaurora.org \
--cc=schwidefsky@de.ibm.com \
--cc=steven.sistare@oracle.com \
--cc=tglx@linutronix.de \
--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