drivers/hv: correct tsc page sequence invalid value
PATCH 1/1 drivers/hv: correct tsc page sequence invalid value
From: Andrey Smetanin <[email protected]>
Hypervisor Top Level Functional Specification v3/4 says that TSC page sequence value = -1(0xFFFFFFFF) is used to indicate that TSC page no longer reliable source of reference timer. Unfortunately, we found that Windows Hyper-V guest side implementation uses sequence value = 0 to indicate that Tsc page no longer valid. This is clearly visible inside Windows 2012R2 ntoskrnl.exe HvlGetReferenceTime() function dissassembly:
HvlGetReferenceTime proc near
xchg ax, axloc_1401C3132:
mov rax, cs:HvlpReferenceTscPage
mov r9d, [rax]
test r9d, r9d
jz short loc_1401C3176 rdtsc
mov rcx, cs:HvlpReferenceTscPage
shl rdx, 20h
or rdx, rax
mov rax, [rcx+8]
mov rcx, cs:HvlpReferenceTscPage
mov r8, [rcx+10h]
mul rdx
mov rax, cs:HvlpReferenceTscPage
add rdx, r8
mov ecx, [rax]
cmp ecx, r9d
jnz short loc_1401C3132
jmp short loc_1401C3184loc_1401C3176:
mov ecx, 40000020h
rdmsr
shl rdx, 20h
or rdx, raxloc_1401C3184:
mov rax, rdx
retn
HvlGetReferenceTime endp
This patch aligns Tsc page invalid sequence value with Windows Hyper-V guest implementation which is more compatible with both Hyper-V hypervisor and KVM hypervisor.
TARGET: Microsoft Hyper-V Linux guest drivers
--- drivers/hv/hv.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)
drivers/hv/hv.c +2 -2
@@ -139,7 +139,7 @@ static cycle_t read_hv_clock_tsc(struct clocksource *arg)cycle_t current_tick;struct ms_hyperv_tsc_page *tsc_pg = hv_context.tsc_page; -if (tsc_pg->tsc_sequence !=-1 ) { +if (tsc_pg->tsc_sequence !=0 ) {/* * Use the tsc page to compute the value. */
@@ -161,7 +161,7 @@ static cycle_t read_hv_clock_tsc(struct clocksource *arg)if (tsc_pg->tsc_sequence == sequence)return current_tick; -if (tsc_pg->tsc_sequence !=-1 ) +if (tsc_pg->tsc_sequence !=0 )continue ;/* * Fallback using MSR method.
Signature · 1 line
2.1.4
Quoted 54 lines
-----Original Message-----
From: Denis V. Lunev [mailto:[email protected]]
Sent: Monday, November 2, 2015 3:34 AM
Cc: [email protected]; [email protected]; linux- [email protected]; Andrey Smetanin <[email protected]>; KY Srinivasan <[email protected]>; Haiyang Zhang <[email protected]>; Vitaly Kuznetsov <[email protected]>; Denis V. Lunev <[email protected]>
Subject: [PATCH 1/1]drivers/hv: correct tsc page sequence invalid valueFrom: Andrey Smetanin <[email protected]>
Hypervisor Top Level Functional Specification v3/4 says that TSC page sequence value = -1(0xFFFFFFFF) is used to indicate that TSC page no longer reliable source of reference timer. Unfortunately, we found that Windows Hyper-V guest side implementation uses sequence value = 0 to indicate that Tsc page no longer valid. This is clearly visible inside Windows 2012R2 ntoskrnl.exe
HvlGetReferenceTime()function dissassembly:HvlGetReferenceTime proc near
xchg ax, axloc_1401C3132:mov rax, cs:HvlpReferenceTscPage mov r9d, [rax] test r9d, r9d jz short loc_1401C3176rdtsc
mov rcx, cs:HvlpReferenceTscPage
shl rdx, 20h
or rdx, rax
mov rax, [rcx+8]
mov rcx, cs:HvlpReferenceTscPage
mov r8, [rcx+10h]
mul rdx
mov rax, cs:HvlpReferenceTscPage
add rdx, r8
mov ecx, [rax]
cmp ecx, r9d
jnz shortloc_1401C3132
jmp shortloc_1401C3184loc_1401C3176:
mov ecx, 40000020h
rdmsr
shl rdx, 20h
or rdx, raxloc_1401C3184:
mov rax, rdx
retn
HvlGetReferenceTime endp
Quoted 6 lines
This patch aligns Tsc page invalid sequence value with Windows Hyper-V guest implementation which is more compatible with both Hyper-V hypervisor and KVM hypervisor.
Signed-off-by Andrey Smetanin <[email protected]>CC "K. Y. Srinivasan" <[email protected]>
Thanks Andrey; the Hyper-V team will be updating the Hyper-V documentation.
Regards,
K. Y
Quoted 35 lines
CC Haiyang Zhang <[email protected]>CC Vitaly Kuznetsov <[email protected]>TARGET: Microsoft Hyper-V Linux guest drivers
Signed-off-by Denis V. Lunev <[email protected]>--- drivers/hv/hv.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)drivers/hv/hv.c +1
-1@@ -139,7 +139,7 @@ static cycle_t read_hv_clock_tsc(struct clocksource *arg)cycle_t current_tick;struct ms_hyperv_tsc_page *tsc_pg = hv_context.tsc_page; -if (tsc_pg->tsc_sequence !=-1 ) { +if (tsc_pg->tsc_sequence !=0 ) {/* * Use the tsc page to compute the value. drivers/hv/hv.c +1
-1*/ @@ -161,7 +161,7 @@ static cycle_t read_hv_clock_tsc(struct clocksource *arg)if (tsc_pg->tsc_sequence == sequence)return current_tick; -if (tsc_pg->tsc_sequence !=-1 ) +if (tsc_pg->tsc_sequence !=0 )continue ;/* * Fallback using MSR method.
--
2.1.4
Quoted 59 lines · KY Srinivasan
Quoted 53 lines
-----Original Message-----
From: Denis V. Lunev [mailto:[email protected]]
Sent: Monday, November 2, 2015 3:34 AM
Cc: [email protected]; [email protected]; linux- [email protected]; Andrey Smetanin <[email protected]>; KY Srinivasan <[email protected]>; Haiyang Zhang <[email protected]>; Vitaly Kuznetsov <[email protected]>; Denis V. Lunev <[email protected]>
Subject: [PATCH 1/1]drivers/hv: correct tsc page sequence invalid valueFrom: Andrey Smetanin <[email protected]>
Hypervisor Top Level Functional Specification v3/4 says that TSC page sequence value = -1(0xFFFFFFFF) is used to indicate that TSC page no longer reliable source of reference timer. Unfortunately, we found that Windows Hyper-V guest side implementation uses sequence value = 0 to indicate that Tsc page no longer valid. This is clearly visible inside Windows 2012R2 ntoskrnl.exe
HvlGetReferenceTime()function dissassembly:HvlGetReferenceTime proc near
xchg ax, axloc_1401C3132:mov rax, cs:HvlpReferenceTscPage mov r9d, [rax] test r9d, r9d jz short loc_1401C3176rdtsc
mov rcx, cs:HvlpReferenceTscPage
shl rdx, 20h
or rdx, rax
mov rax, [rcx+8]
mov rcx, cs:HvlpReferenceTscPage
mov r8, [rcx+10h]
mul rdx
mov rax, cs:HvlpReferenceTscPage
add rdx, r8
mov ecx, [rax]
cmp ecx, r9d
jnz shortloc_1401C3132
jmp shortloc_1401C3184loc_1401C3176:
mov ecx, 40000020h
rdmsr
shl rdx, 20h
or rdx, raxloc_1401C3184:
mov rax, rdx
retn
HvlGetReferenceTime endpQuoted 6 lines
This patch aligns Tsc page invalid sequence value with Windows Hyper-V guest implementation which is more compatible with both Hyper-V hypervisor and KVM hypervisor.
Signed-off-by Andrey Smetanin <[email protected]>CC "K. Y. Srinivasan" <[email protected]>
Quoted 7 lines
Thanks Andrey; the Hyper-V team will be updating the Hyper-V documentation.
Acked-by K. Y. Srinivasan <[email protected]>Regards,
K. Y
K.Y.,
can you pls clarify the state of this patch? It is a bit unclear to me whether it is applied or not.
By the way, I also do not see the following patch "drivers/hv: cleanup synic msrs if vmbus connect failed" as applied in the Linux-next. You have promised to resend it will correct author.
Thank you in advance,
Den
Quoted 78 lines
-----Original Message-----
From: Denis V. Lunev [mailto:[email protected]]
Sent: Wednesday, November 11, 2015 11:16 PM
To: KY Srinivasan <[email protected]>
Cc: [email protected]; [email protected]; linux- [email protected]; Andrey Smetanin <[email protected]>; Haiyang Zhang <[email protected]>; Vitaly Kuznetsov <[email protected]>
Subject: Re: [PATCH 1/1]drivers/hv: correct tsc page sequence invalid valueQuoted 6 lines · KY Srinivasan
Quoted 6 lines
-----Original Message-----
From: Denis V. Lunev [mailto:[email protected]]
Sent: Monday, November 2, 2015 3:34 AM
Cc: [email protected]; [email protected]; linux- [email protected]; Andrey Smetanin <[email protected]>;KY
Quoted 47 lines
Quoted 47 lines
Srinivasan <[email protected]>; Haiyang Zhang <[email protected]>; Vitaly Kuznetsov <[email protected]>; Denis V. Lunev <[email protected]>
Subject: [PATCH 1/1]drivers/hv: correct tsc page sequence invalid valueFrom: Andrey Smetanin <[email protected]>
Hypervisor Top Level Functional Specification v3/4 says that TSC page sequence value = -1(0xFFFFFFFF) is used to indicate that TSC page no longer reliable source of reference timer. Unfortunately, we found that Windows Hyper-V guest side implementation uses sequence value = 0 to indicate that Tsc page no longer valid. This is clearly visible inside Windows 2012R2 ntoskrnl.exe
HvlGetReferenceTime()function dissassembly:HvlGetReferenceTime proc near
xchg ax, axloc_1401C3132:mov rax, cs:HvlpReferenceTscPage mov r9d, [rax] test r9d, r9d jz short loc_1401C3176rdtsc
mov rcx, cs:HvlpReferenceTscPage
shl rdx, 20h
or rdx, rax
mov rax, [rcx+8]
mov rcx, cs:HvlpReferenceTscPage
mov r8, [rcx+10h]
mul rdx
mov rax, cs:HvlpReferenceTscPage
add rdx, r8
mov ecx, [rax]
cmp ecx, r9d
jnz shortloc_1401C3132
jmp shortloc_1401C3184loc_1401C3176:
mov ecx, 40000020h
rdmsr
shl rdx, 20h
or rdx, raxloc_1401C3184:
mov rax, rdx
retn
HvlGetReferenceTime endpQuoted 7 lines
Quoted 6 lines
This patch aligns Tsc page invalid sequence value with Windows Hyper-V guest implementation which is more compatible with both Hyper-V hypervisor and KVM hypervisor.
Signed-off-by Andrey Smetanin <[email protected]>CC "K. Y. Srinivasan" <[email protected]>Thanks Andrey; the Hyper-V team will be updating the Hyper-V
documentation.
Quoted 3 lines
Acked-by K. Y. Srinivasan <[email protected]>
Quoted 7 lines
Quoted 3 lines
Regards,
K. Y
K.Y.,
can you pls clarify the state of this patch? It is a bit unclear to me whether it is applied or not.
I will be submitting this shortly.
Quoted 5 lines
By the way, I also do not see the following patch "
drivers/hv: cleanup synic msrs if vmbus connect failed" as applied in the Linux-next. You have promised to resend it will correct author.
It was resent on October 29. It is in Greg's queue.
Regards,
K. Y
Quoted 3 lines
Thank you in advance,
Den
Quoted 88 lines · KY Srinivasan
Quoted 75 lines
-----Original Message-----
From: Denis V. Lunev [mailto:[email protected]]
Sent: Wednesday, November 11, 2015 11:16 PM
To: KY Srinivasan <[email protected]>
Cc: [email protected]; [email protected]; linux- [email protected]; Andrey Smetanin <[email protected]>; Haiyang Zhang <[email protected]>; Vitaly Kuznetsov <[email protected]>
Subject: Re: [PATCH 1/1]drivers/hv: correct tsc page sequence invalid valueQuoted 5 lines · KY Srinivasan
Quoted 5 lines
-----Original Message-----
From: Denis V. Lunev [mailto:[email protected]]
Sent: Monday, November 2, 2015 3:34 AM
Cc: [email protected]; [email protected]; linux- [email protected]; Andrey Smetanin <[email protected]>;KY
Quoted 47 lines
Quoted 47 lines
Srinivasan <[email protected]>; Haiyang Zhang <[email protected]>; Vitaly Kuznetsov <[email protected]>; Denis V. Lunev <[email protected]>
Subject: [PATCH 1/1]drivers/hv: correct tsc page sequence invalid valueFrom: Andrey Smetanin <[email protected]>
Hypervisor Top Level Functional Specification v3/4 says that TSC page sequence value = -1(0xFFFFFFFF) is used to indicate that TSC page no longer reliable source of reference timer. Unfortunately, we found that Windows Hyper-V guest side implementation uses sequence value = 0 to indicate that Tsc page no longer valid. This is clearly visible inside Windows 2012R2 ntoskrnl.exe
HvlGetReferenceTime()function dissassembly:HvlGetReferenceTime proc near
xchg ax, axloc_1401C3132:mov rax, cs:HvlpReferenceTscPage mov r9d, [rax] test r9d, r9d jz short loc_1401C3176rdtsc
mov rcx, cs:HvlpReferenceTscPage
shl rdx, 20h
or rdx, rax
mov rax, [rcx+8]
mov rcx, cs:HvlpReferenceTscPage
mov r8, [rcx+10h]
mul rdx
mov rax, cs:HvlpReferenceTscPage
add rdx, r8
mov ecx, [rax]
cmp ecx, r9d
jnz shortloc_1401C3132
jmp shortloc_1401C3184loc_1401C3176:
mov ecx, 40000020h
rdmsr
shl rdx, 20h
or rdx, raxloc_1401C3184:
mov rax, rdx
retn
HvlGetReferenceTime endpQuoted 7 lines
Quoted 6 lines
This patch aligns Tsc page invalid sequence value with Windows Hyper-V guest implementation which is more compatible with both Hyper-V hypervisor and KVM hypervisor.
Signed-off-by Andrey Smetanin <[email protected]>CC "K. Y. Srinivasan" <[email protected]>Thanks Andrey; the Hyper-V team will be updating the Hyper-V
documentation.
Quoted 2 lines
Acked-by K. Y. Srinivasan <[email protected]>Quoted 7 lines
Quoted 3 lines
Regards,
K. Y
K.Y.,
can you pls clarify the state of this patch? It is a bit unclear to me whether it is applied or not.
I will be submitting this shortly.
Quoted 4 lines
By the way, I also do not see the following patch "
drivers/hv: cleanup synic msrs if vmbus connect failed" as applied in the Linux-next. You have promised to resend it will correct author.
Quoted 7 lines
It was resent on October 29. It is in Greg's queue.
Regards,
K. Y
Quoted 2 lines
Thank you in advance,
Den
thank you very much for this update :)
Den