[GIT PULL] x86/vdso changes for v4.12

From: Ingo Molnar
Date: Mon May 01 2017 - 07:49:24 EST


Linus,

Please pull the latest x86-vdso-for-linus git tree from:

git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git x86-vdso-for-linus

# HEAD: 90b20432aeb850ef84086a72893cd9411479d896 x86/vdso: Add VCLOCK_HVCLOCK vDSO clock read method

Add support for vDSO acceleration of the "Hyper-V TSC page", to speed up clock
reading on Hyper-V guests.

out-of-topic modifications in x86-vdso-for-linus:
---------------------------------------------------
drivers/hv/Kconfig # bd2a9adaadb8: x86/hyperv: Implement hv_get

Thanks,

Ingo

------------------>
Vitaly Kuznetsov (3):
x86/hyperv: Implement hv_get_tsc_page()
x86/hyperv: Move TSC reading method to asm/mshyperv.h
x86/vdso: Add VCLOCK_HVCLOCK vDSO clock read method


arch/x86/entry/vdso/vclock_gettime.c | 24 ++++++++++++++++
arch/x86/entry/vdso/vdso-layout.lds.S | 3 +-
arch/x86/entry/vdso/vdso2c.c | 3 ++
arch/x86/entry/vdso/vma.c | 7 +++++
arch/x86/hyperv/hv_init.c | 48 +++++++++----------------------
arch/x86/include/asm/clocksource.h | 3 +-
arch/x86/include/asm/mshyperv.h | 54 +++++++++++++++++++++++++++++++++++
arch/x86/include/asm/vdso.h | 1 +
drivers/hv/Kconfig | 3 ++
9 files changed, 110 insertions(+), 36 deletions(-)

diff --git a/arch/x86/entry/vdso/vclock_gettime.c b/arch/x86/entry/vdso/vclock_gettime.c
index 9d4d6e138311..fa8dbfcf7ed3 100644
--- a/arch/x86/entry/vdso/vclock_gettime.c
+++ b/arch/x86/entry/vdso/vclock_gettime.c
@@ -17,6 +17,7 @@
#include <asm/unistd.h>
#include <asm/msr.h>
#include <asm/pvclock.h>
+#include <asm/mshyperv.h>
#include <linux/math64.h>
#include <linux/time.h>
#include <linux/kernel.h>
@@ -32,6 +33,11 @@ extern u8 pvclock_page
__attribute__((visibility("hidden")));
#endif

+#ifdef CONFIG_HYPERV_TSCPAGE
+extern u8 hvclock_page
+ __attribute__((visibility("hidden")));
+#endif
+
#ifndef BUILD_VDSO32

notrace static long vdso_fallback_gettime(long clock, struct timespec *ts)
@@ -141,6 +147,20 @@ static notrace u64 vread_pvclock(int *mode)
return last;
}
#endif
+#ifdef CONFIG_HYPERV_TSCPAGE
+static notrace u64 vread_hvclock(int *mode)
+{
+ const struct ms_hyperv_tsc_page *tsc_pg =
+ (const struct ms_hyperv_tsc_page *)&hvclock_page;
+ u64 current_tick = hv_read_tsc_page(tsc_pg);
+
+ if (current_tick != U64_MAX)
+ return current_tick;
+
+ *mode = VCLOCK_NONE;
+ return 0;
+}
+#endif

notrace static u64 vread_tsc(void)
{
@@ -173,6 +193,10 @@ notrace static inline u64 vgetsns(int *mode)
else if (gtod->vclock_mode == VCLOCK_PVCLOCK)
cycles = vread_pvclock(mode);
#endif
+#ifdef CONFIG_HYPERV_TSCPAGE
+ else if (gtod->vclock_mode == VCLOCK_HVCLOCK)
+ cycles = vread_hvclock(mode);
+#endif
else
return 0;
v = (cycles - gtod->cycle_last) & gtod->mask;
diff --git a/arch/x86/entry/vdso/vdso-layout.lds.S b/arch/x86/entry/vdso/vdso-layout.lds.S
index a708aa90b507..8ebb4b6454fe 100644
--- a/arch/x86/entry/vdso/vdso-layout.lds.S
+++ b/arch/x86/entry/vdso/vdso-layout.lds.S
@@ -25,7 +25,7 @@ SECTIONS
* segment.
*/

- vvar_start = . - 2 * PAGE_SIZE;
+ vvar_start = . - 3 * PAGE_SIZE;
vvar_page = vvar_start;

/* Place all vvars at the offsets in asm/vvar.h. */
@@ -36,6 +36,7 @@ SECTIONS
#undef EMIT_VVAR

pvclock_page = vvar_start + PAGE_SIZE;
+ hvclock_page = vvar_start + 2 * PAGE_SIZE;

. = SIZEOF_HEADERS;

diff --git a/arch/x86/entry/vdso/vdso2c.c b/arch/x86/entry/vdso/vdso2c.c
index 491020b2826d..0780a443a53b 100644
--- a/arch/x86/entry/vdso/vdso2c.c
+++ b/arch/x86/entry/vdso/vdso2c.c
@@ -74,6 +74,7 @@ enum {
sym_vvar_page,
sym_hpet_page,
sym_pvclock_page,
+ sym_hvclock_page,
sym_VDSO_FAKE_SECTION_TABLE_START,
sym_VDSO_FAKE_SECTION_TABLE_END,
};
@@ -82,6 +83,7 @@ const int special_pages[] = {
sym_vvar_page,
sym_hpet_page,
sym_pvclock_page,
+ sym_hvclock_page,
};

struct vdso_sym {
@@ -94,6 +96,7 @@ struct vdso_sym required_syms[] = {
[sym_vvar_page] = {"vvar_page", true},
[sym_hpet_page] = {"hpet_page", true},
[sym_pvclock_page] = {"pvclock_page", true},
+ [sym_hvclock_page] = {"hvclock_page", true},
[sym_VDSO_FAKE_SECTION_TABLE_START] = {
"VDSO_FAKE_SECTION_TABLE_START", false
},
diff --git a/arch/x86/entry/vdso/vma.c b/arch/x86/entry/vdso/vma.c
index 226ca70dc6bd..faf80fdeeacc 100644
--- a/arch/x86/entry/vdso/vma.c
+++ b/arch/x86/entry/vdso/vma.c
@@ -22,6 +22,7 @@
#include <asm/page.h>
#include <asm/desc.h>
#include <asm/cpufeature.h>
+#include <asm/mshyperv.h>

#if defined(CONFIG_X86_64)
unsigned int __read_mostly vdso64_enabled = 1;
@@ -121,6 +122,12 @@ static int vvar_fault(const struct vm_special_mapping *sm,
vmf->address,
__pa(pvti) >> PAGE_SHIFT);
}
+ } else if (sym_offset == image->sym_hvclock_page) {
+ struct ms_hyperv_tsc_page *tsc_pg = hv_get_tsc_page();
+
+ if (tsc_pg && vclock_was_used(VCLOCK_HVCLOCK))
+ ret = vm_insert_pfn(vma, vmf->address,
+ vmalloc_to_pfn(tsc_pg));
}

if (ret == 0 || ret == -EBUSY)
diff --git a/arch/x86/hyperv/hv_init.c b/arch/x86/hyperv/hv_init.c
index 8bef70e7f3cc..2b01421f7d0f 100644
--- a/arch/x86/hyperv/hv_init.c
+++ b/arch/x86/hyperv/hv_init.c
@@ -27,45 +27,22 @@
#include <linux/clockchips.h>


-#ifdef CONFIG_X86_64
+#ifdef CONFIG_HYPERV_TSCPAGE

static struct ms_hyperv_tsc_page *tsc_pg;

+struct ms_hyperv_tsc_page *hv_get_tsc_page(void)
+{
+ return tsc_pg;
+}
+
static u64 read_hv_clock_tsc(struct clocksource *arg)
{
- u64 current_tick;
+ u64 current_tick = hv_read_tsc_page(tsc_pg);
+
+ if (current_tick == U64_MAX)
+ rdmsrl(HV_X64_MSR_TIME_REF_COUNT, current_tick);

- if (tsc_pg->tsc_sequence != 0) {
- /*
- * Use the tsc page to compute the value.
- */
-
- while (1) {
- u64 tmp;
- u32 sequence = tsc_pg->tsc_sequence;
- u64 cur_tsc;
- u64 scale = tsc_pg->tsc_scale;
- s64 offset = tsc_pg->tsc_offset;
-
- rdtscll(cur_tsc);
- /* current_tick = ((cur_tsc *scale) >> 64) + offset */
- asm("mulq %3"
- : "=d" (current_tick), "=a" (tmp)
- : "a" (cur_tsc), "r" (scale));
-
- current_tick += offset;
- if (tsc_pg->tsc_sequence == sequence)
- return current_tick;
-
- if (tsc_pg->tsc_sequence != 0)
- continue;
- /*
- * Fallback using MSR method.
- */
- break;
- }
- }
- rdmsrl(HV_X64_MSR_TIME_REF_COUNT, current_tick);
return current_tick;
}

@@ -139,7 +116,7 @@ void hyperv_init(void)
/*
* Register Hyper-V specific clocksource.
*/
-#ifdef CONFIG_X86_64
+#ifdef CONFIG_HYPERV_TSCPAGE
if (ms_hyperv.features & HV_X64_MSR_REFERENCE_TSC_AVAILABLE) {
union hv_x64_msr_hypercall_contents tsc_msr;

@@ -155,6 +132,9 @@ void hyperv_init(void)
tsc_msr.guest_physical_address = vmalloc_to_pfn(tsc_pg);

wrmsrl(HV_X64_MSR_REFERENCE_TSC, tsc_msr.as_uint64);
+
+ hyperv_cs_tsc.archdata.vclock_mode = VCLOCK_HVCLOCK;
+
clocksource_register_hz(&hyperv_cs_tsc, NSEC_PER_SEC/100);
return;
}
diff --git a/arch/x86/include/asm/clocksource.h b/arch/x86/include/asm/clocksource.h
index eae33c7170c8..47bea8cadbd0 100644
--- a/arch/x86/include/asm/clocksource.h
+++ b/arch/x86/include/asm/clocksource.h
@@ -6,7 +6,8 @@
#define VCLOCK_NONE 0 /* No vDSO clock available. */
#define VCLOCK_TSC 1 /* vDSO should use vread_tsc. */
#define VCLOCK_PVCLOCK 2 /* vDSO should use vread_pvclock. */
-#define VCLOCK_MAX 2
+#define VCLOCK_HVCLOCK 3 /* vDSO should use vread_hvclock. */
+#define VCLOCK_MAX 3

struct arch_clocksource_data {
int vclock_mode;
diff --git a/arch/x86/include/asm/mshyperv.h b/arch/x86/include/asm/mshyperv.h
index 7c9c895432a9..fba100713924 100644
--- a/arch/x86/include/asm/mshyperv.h
+++ b/arch/x86/include/asm/mshyperv.h
@@ -176,4 +176,58 @@ void hyperv_report_panic(struct pt_regs *regs);
bool hv_is_hypercall_page_setup(void);
void hyperv_cleanup(void);
#endif
+#ifdef CONFIG_HYPERV_TSCPAGE
+struct ms_hyperv_tsc_page *hv_get_tsc_page(void);
+static inline u64 hv_read_tsc_page(const struct ms_hyperv_tsc_page *tsc_pg)
+{
+ u64 scale, offset, cur_tsc;
+ u32 sequence;
+
+ /*
+ * The protocol for reading Hyper-V TSC page is specified in Hypervisor
+ * Top-Level Functional Specification ver. 3.0 and above. To get the
+ * reference time we must do the following:
+ * - READ ReferenceTscSequence
+ * A special '0' value indicates the time source is unreliable and we
+ * need to use something else. The currently published specification
+ * versions (up to 4.0b) contain a mistake and wrongly claim '-1'
+ * instead of '0' as the special value, see commit c35b82ef0294.
+ * - ReferenceTime =
+ * ((RDTSC() * ReferenceTscScale) >> 64) + ReferenceTscOffset
+ * - READ ReferenceTscSequence again. In case its value has changed
+ * since our first reading we need to discard ReferenceTime and repeat
+ * the whole sequence as the hypervisor was updating the page in
+ * between.
+ */
+ do {
+ sequence = READ_ONCE(tsc_pg->tsc_sequence);
+ if (!sequence)
+ return U64_MAX;
+ /*
+ * Make sure we read sequence before we read other values from
+ * TSC page.
+ */
+ smp_rmb();
+
+ scale = READ_ONCE(tsc_pg->tsc_scale);
+ offset = READ_ONCE(tsc_pg->tsc_offset);
+ cur_tsc = rdtsc_ordered();
+
+ /*
+ * Make sure we read sequence after we read all other values
+ * from TSC page.
+ */
+ smp_rmb();
+
+ } while (READ_ONCE(tsc_pg->tsc_sequence) != sequence);
+
+ return mul_u64_u64_shr(cur_tsc, scale, 64) + offset;
+}
+
+#else
+static inline struct ms_hyperv_tsc_page *hv_get_tsc_page(void)
+{
+ return NULL;
+}
+#endif
#endif
diff --git a/arch/x86/include/asm/vdso.h b/arch/x86/include/asm/vdso.h
index 2444189cbe28..bccdf4938ddf 100644
--- a/arch/x86/include/asm/vdso.h
+++ b/arch/x86/include/asm/vdso.h
@@ -20,6 +20,7 @@ struct vdso_image {
long sym_vvar_page;
long sym_hpet_page;
long sym_pvclock_page;
+ long sym_hvclock_page;
long sym_VDSO32_NOTE_MASK;
long sym___kernel_sigreturn;
long sym___kernel_rt_sigreturn;
diff --git a/drivers/hv/Kconfig b/drivers/hv/Kconfig
index 0403b51d20ba..c29cd5387a35 100644
--- a/drivers/hv/Kconfig
+++ b/drivers/hv/Kconfig
@@ -7,6 +7,9 @@ config HYPERV
Select this option to run Linux as a Hyper-V client operating
system.

+config HYPERV_TSCPAGE
+ def_bool HYPERV && X86_64
+
config HYPERV_UTILS
tristate "Microsoft Hyper-V Utilities driver"
depends on HYPERV && CONNECTOR && NLS