* [PATCH 2/8] x86/hyperv: Add interrupt handler annotations
2018-06-05 20:37 ` [PATCH 1/8] use the new async probing feature for the hyperv drivers kys
@ 2018-06-05 20:37 ` kys
2018-06-05 20:37 ` [PATCH 3/8] Drivers: hv: vmbus: Add comments on ring buffer signaling kys
` (5 subsequent siblings)
6 siblings, 0 replies; 9+ messages in thread
From: kys @ 2018-06-05 20:37 UTC (permalink / raw)
To: gregkh, linux-kernel, devel, olaf, apw, jasowang, sthemmin,
Michael.H.Kelley, vkuznets
Cc: Michael Kelley, K . Y . Srinivasan
From: Michael Kelley <mikelley@microsoft.com>
Add standard interrupt handler annotations to
hyperv_vector_handler(). This does not fix any observed
bug, but avoids potential removal of the code by link
time optimization and makes it consistent with
hv_stimer0_vector_handler in the same source file.
Suggested-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Michael Kelley <mikelley@microsoft.com>
Signed-off-by: K. Y. Srinivasan <kys@microsoft.com>
---
arch/x86/kernel/cpu/mshyperv.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c
index 031082c96db8..8a49b7ef7b76 100644
--- a/arch/x86/kernel/cpu/mshyperv.c
+++ b/arch/x86/kernel/cpu/mshyperv.c
@@ -41,7 +41,7 @@ static void (*hv_stimer0_handler)(void);
static void (*hv_kexec_handler)(void);
static void (*hv_crash_handler)(struct pt_regs *regs);
-void hyperv_vector_handler(struct pt_regs *regs)
+__visible void __irq_entry hyperv_vector_handler(struct pt_regs *regs)
{
struct pt_regs *old_regs = set_irq_regs(regs);
--
2.17.1
^ permalink raw reply related [flat|nested] 9+ messages in thread* [PATCH 3/8] Drivers: hv: vmbus: Add comments on ring buffer signaling
2018-06-05 20:37 ` [PATCH 1/8] use the new async probing feature for the hyperv drivers kys
2018-06-05 20:37 ` [PATCH 2/8] x86/hyperv: Add interrupt handler annotations kys
@ 2018-06-05 20:37 ` kys
2018-06-05 20:37 ` [PATCH 4/8] Drivers: hv: vmbus: Fix the offer_in_progress in vmbus_process_offer() kys
` (4 subsequent siblings)
6 siblings, 0 replies; 9+ messages in thread
From: kys @ 2018-06-05 20:37 UTC (permalink / raw)
To: gregkh, linux-kernel, devel, olaf, apw, jasowang, sthemmin,
Michael.H.Kelley, vkuznets
Cc: Michael Kelley, K . Y . Srinivasan
From: Michael Kelley <mikelley@microsoft.com>
Add comments describing intricacies of Hyper-V ring buffer
signaling code. This information is not in Hyper-V public
documents, so include here to capture the knowledge for
future coders.
There are no code changes in this commit.
Signed-off-by: Michael Kelley <mikelley@microsoft.com>
Signed-off-by: K. Y. Srinivasan <kys@microsoft.com>
---
drivers/hv/ring_buffer.c | 65 +++++++++++++++++++++++++++++++++-------
include/linux/hyperv.h | 31 ++++++++++++++-----
2 files changed, 77 insertions(+), 19 deletions(-)
diff --git a/drivers/hv/ring_buffer.c b/drivers/hv/ring_buffer.c
index 8699bb969e7e..ce6ea6dad490 100644
--- a/drivers/hv/ring_buffer.c
+++ b/drivers/hv/ring_buffer.c
@@ -429,7 +429,24 @@ static u32 hv_pkt_iter_bytes_read(const struct hv_ring_buffer_info *rbi,
}
/*
- * Update host ring buffer after iterating over packets.
+ * Update host ring buffer after iterating over packets. If the host has
+ * stopped queuing new entries because it found the ring buffer full, and
+ * sufficient space is being freed up, signal the host. But be careful to
+ * only signal the host when necessary, both for performance reasons and
+ * because Hyper-V protects itself by throttling guests that signal
+ * inappropriately.
+ *
+ * Determining when to signal is tricky. There are three key data inputs
+ * that must be handled in this order to avoid race conditions:
+ *
+ * 1. Update the read_index
+ * 2. Read the pending_send_sz
+ * 3. Read the current write_index
+ *
+ * The interrupt_mask is not used to determine when to signal. The
+ * interrupt_mask is used only on the guest->host ring buffer when
+ * sending requests to the host. The host does not use it on the host->
+ * guest ring buffer to indicate whether it should be signaled.
*/
void hv_pkt_iter_close(struct vmbus_channel *channel)
{
@@ -445,22 +462,30 @@ void hv_pkt_iter_close(struct vmbus_channel *channel)
start_read_index = rbi->ring_buffer->read_index;
rbi->ring_buffer->read_index = rbi->priv_read_index;
+ /*
+ * Older versions of Hyper-V (before WS2102 and Win8) do not
+ * implement pending_send_sz and simply poll if the host->guest
+ * ring buffer is full. No signaling is needed or expected.
+ */
if (!rbi->ring_buffer->feature_bits.feat_pending_send_sz)
return;
/*
* Issue a full memory barrier before making the signaling decision.
- * Here is the reason for having this barrier:
- * If the reading of the pend_sz (in this function)
- * were to be reordered and read before we commit the new read
- * index (in the calling function) we could
- * have a problem. If the host were to set the pending_sz after we
- * have sampled pending_sz and go to sleep before we commit the
+ * If reading pending_send_sz were to be reordered and happen
+ * before we commit the new read_index, a race could occur. If the
+ * host were to set the pending_send_sz after we have sampled
+ * pending_send_sz, and the ring buffer blocks before we commit the
* read index, we could miss sending the interrupt. Issue a full
* memory barrier to address this.
*/
virt_mb();
+ /*
+ * If the pending_send_sz is zero, then the ring buffer is not
+ * blocked and there is no need to signal. This is far by the
+ * most common case, so exit quickly for best performance.
+ */
pending_sz = READ_ONCE(rbi->ring_buffer->pending_send_sz);
if (!pending_sz)
return;
@@ -474,14 +499,32 @@ void hv_pkt_iter_close(struct vmbus_channel *channel)
bytes_read = hv_pkt_iter_bytes_read(rbi, start_read_index);
/*
- * If there was space before we began iteration,
- * then host was not blocked.
+ * We want to signal the host only if we're transitioning
+ * from a "not enough free space" state to a "enough free
+ * space" state. For example, it's possible that this function
+ * could run and free up enough space to signal the host, and then
+ * run again and free up additional space before the host has a
+ * chance to clear the pending_send_sz. The 2nd invocation would
+ * be a null transition from "enough free space" to "enough free
+ * space", which doesn't warrant a signal.
+ *
+ * Exactly filling the ring buffer is treated as "not enough
+ * space". The ring buffer always must have at least one byte
+ * empty so the empty and full conditions are distinguishable.
+ * hv_get_bytes_to_write() doesn't fully tell the truth in
+ * this regard.
+ *
+ * So first check if we were in the "enough free space" state
+ * before we began the iteration. If so, the host was not
+ * blocked, and there's no need to signal.
*/
-
if (curr_write_sz - bytes_read > pending_sz)
return;
- /* If pending write will not fit, don't give false hope. */
+ /*
+ * Similarly, if the new state is "not enough space", then
+ * there's no need to signal.
+ */
if (curr_write_sz <= pending_sz)
return;
diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h
index 11b5612dc066..3265300b2b16 100644
--- a/include/linux/hyperv.h
+++ b/include/linux/hyperv.h
@@ -88,18 +88,33 @@ struct hv_ring_buffer {
u32 interrupt_mask;
/*
- * Win8 uses some of the reserved bits to implement
- * interrupt driven flow management. On the send side
- * we can request that the receiver interrupt the sender
- * when the ring transitions from being full to being able
- * to handle a message of size "pending_send_sz".
+ * WS2012/Win8 and later versions of Hyper-V implement interrupt
+ * driven flow management. The feature bit feat_pending_send_sz
+ * is set by the host on the host->guest ring buffer, and by the
+ * guest on the guest->host ring buffer.
*
- * Add necessary state for this enhancement.
+ * The meaning of the feature bit is a bit complex in that it has
+ * semantics that apply to both ring buffers. If the guest sets
+ * the feature bit in the guest->host ring buffer, the guest is
+ * telling the host that:
+ * 1) It will set the pending_send_sz field in the guest->host ring
+ * buffer when it is waiting for space to become available, and
+ * 2) It will read the pending_send_sz field in the host->guest
+ * ring buffer and interrupt the host when it frees enough space
+ *
+ * Similarly, if the host sets the feature bit in the host->guest
+ * ring buffer, the host is telling the guest that:
+ * 1) It will set the pending_send_sz field in the host->guest ring
+ * buffer when it is waiting for space to become available, and
+ * 2) It will read the pending_send_sz field in the guest->host
+ * ring buffer and interrupt the guest when it frees enough space
+ *
+ * If either the guest or host does not set the feature bit that it
+ * owns, that guest or host must do polling if it encounters a full
+ * ring buffer, and not signal the other end with an interrupt.
*/
u32 pending_send_sz;
-
u32 reserved1[12];
-
union {
struct {
u32 feat_pending_send_sz:1;
--
2.17.1
^ permalink raw reply related [flat|nested] 9+ messages in thread* [PATCH 4/8] Drivers: hv: vmbus: Fix the offer_in_progress in vmbus_process_offer()
2018-06-05 20:37 ` [PATCH 1/8] use the new async probing feature for the hyperv drivers kys
2018-06-05 20:37 ` [PATCH 2/8] x86/hyperv: Add interrupt handler annotations kys
2018-06-05 20:37 ` [PATCH 3/8] Drivers: hv: vmbus: Add comments on ring buffer signaling kys
@ 2018-06-05 20:37 ` kys
2018-06-05 20:37 ` [PATCH 5/8] Drivers: hv: vmbus: Remove x86 MSR refs in arch independent code kys
` (3 subsequent siblings)
6 siblings, 0 replies; 9+ messages in thread
From: kys @ 2018-06-05 20:37 UTC (permalink / raw)
To: gregkh, linux-kernel, devel, olaf, apw, jasowang, sthemmin,
Michael.H.Kelley, vkuznets
Cc: Dexuan Cui, stable, K . Y . Srinivasan
From: Dexuan Cui <decui@microsoft.com>
I didn't really hit a real bug, but just happened to spot the bug:
we have decreased the counter at the beginning of vmbus_process_offer(),
so we mustn't decrease it again.
Fixes: 6f3d791f3006 ("Drivers: hv: vmbus: Fix rescind handling issues")
Signed-off-by: Dexuan Cui <decui@microsoft.com>
Cc: stable@vger.kernel.org
Cc: Stephen Hemminger <sthemmin@microsoft.com>
Cc: K. Y. Srinivasan <kys@microsoft.com>
Cc: Stable <stable@vger.kernel.org> # 4.14 and above
Signed-off-by: K. Y. Srinivasan <kys@microsoft.com>
---
drivers/hv/channel_mgmt.c | 4 +---
1 file changed, 1 insertion(+), 3 deletions(-)
diff --git a/drivers/hv/channel_mgmt.c b/drivers/hv/channel_mgmt.c
index ecc2bd275a73..f3b551a50653 100644
--- a/drivers/hv/channel_mgmt.c
+++ b/drivers/hv/channel_mgmt.c
@@ -527,10 +527,8 @@ static void vmbus_process_offer(struct vmbus_channel *newchannel)
struct hv_device *dev
= newchannel->primary_channel->device_obj;
- if (vmbus_add_channel_kobj(dev, newchannel)) {
- atomic_dec(&vmbus_connection.offer_in_progress);
+ if (vmbus_add_channel_kobj(dev, newchannel))
goto err_free_chan;
- }
if (channel->sc_creation_callback != NULL)
channel->sc_creation_callback(newchannel);
--
2.17.1
^ permalink raw reply related [flat|nested] 9+ messages in thread* [PATCH 5/8] Drivers: hv: vmbus: Remove x86 MSR refs in arch independent code
2018-06-05 20:37 ` [PATCH 1/8] use the new async probing feature for the hyperv drivers kys
` (2 preceding siblings ...)
2018-06-05 20:37 ` [PATCH 4/8] Drivers: hv: vmbus: Fix the offer_in_progress in vmbus_process_offer() kys
@ 2018-06-05 20:37 ` kys
2018-06-05 20:37 ` [PATCH 6/8] Drivers: hv: vmbus: Make TLFS #define names architecture neutral kys
` (2 subsequent siblings)
6 siblings, 0 replies; 9+ messages in thread
From: kys @ 2018-06-05 20:37 UTC (permalink / raw)
To: gregkh, linux-kernel, devel, olaf, apw, jasowang, sthemmin,
Michael.H.Kelley, vkuznets
Cc: Michael Kelley, K . Y . Srinivasan
From: Michael Kelley <mikelley@microsoft.com>
In architecture independent code for manipulating Hyper-V synthetic timers
and synthetic interrupts, pass in an ordinal number identifying the timer
or interrupt, rather than an actual MSR register address. Then in
x86/x64 specific code, map the ordinal number to the appropriate MSR.
This change facilitates the introduction of an ARM64 version of Hyper-V,
which uses the same synthetic timers and interrupts, but a different
mechanism for accessing them.
Signed-off-by: Michael Kelley <mikelley@microsoft.com>
Signed-off-by: K. Y. Srinivasan <kys@microsoft.com>
---
arch/x86/include/asm/mshyperv.h | 12 ++++++++----
drivers/hv/hv.c | 20 ++++++++------------
2 files changed, 16 insertions(+), 16 deletions(-)
diff --git a/arch/x86/include/asm/mshyperv.h b/arch/x86/include/asm/mshyperv.h
index b90e79610cf7..caf9035a2758 100644
--- a/arch/x86/include/asm/mshyperv.h
+++ b/arch/x86/include/asm/mshyperv.h
@@ -75,8 +75,10 @@ static inline void vmbus_signal_eom(struct hv_message *msg, u32 old_msg_type)
}
}
-#define hv_init_timer(timer, tick) wrmsrl(timer, tick)
-#define hv_init_timer_config(config, val) wrmsrl(config, val)
+#define hv_init_timer(timer, tick) \
+ wrmsrl(HV_X64_MSR_STIMER0_COUNT + (2*timer), tick)
+#define hv_init_timer_config(timer, val) \
+ wrmsrl(HV_X64_MSR_STIMER0_CONFIG + (2*timer), val)
#define hv_get_simp(val) rdmsrl(HV_X64_MSR_SIMP, val)
#define hv_set_simp(val) wrmsrl(HV_X64_MSR_SIMP, val)
@@ -89,8 +91,10 @@ static inline void vmbus_signal_eom(struct hv_message *msg, u32 old_msg_type)
#define hv_get_vp_index(index) rdmsrl(HV_X64_MSR_VP_INDEX, index)
-#define hv_get_synint_state(int_num, val) rdmsrl(int_num, val)
-#define hv_set_synint_state(int_num, val) wrmsrl(int_num, val)
+#define hv_get_synint_state(int_num, val) \
+ rdmsrl(HV_X64_MSR_SINT0 + int_num, val)
+#define hv_set_synint_state(int_num, val) \
+ wrmsrl(HV_X64_MSR_SINT0 + int_num, val)
void hyperv_callback_vector(void);
void hyperv_reenlightenment_vector(void);
diff --git a/drivers/hv/hv.c b/drivers/hv/hv.c
index 9b82549cbbc8..96c403a07906 100644
--- a/drivers/hv/hv.c
+++ b/drivers/hv/hv.c
@@ -127,14 +127,14 @@ static int hv_ce_set_next_event(unsigned long delta,
current_tick = hyperv_cs->read(NULL);
current_tick += delta;
- hv_init_timer(HV_X64_MSR_STIMER0_COUNT, current_tick);
+ hv_init_timer(0, current_tick);
return 0;
}
static int hv_ce_shutdown(struct clock_event_device *evt)
{
- hv_init_timer(HV_X64_MSR_STIMER0_COUNT, 0);
- hv_init_timer_config(HV_X64_MSR_STIMER0_CONFIG, 0);
+ hv_init_timer(0, 0);
+ hv_init_timer_config(0, 0);
if (direct_mode_enabled)
hv_disable_stimer0_percpu_irq(stimer0_irq);
@@ -164,7 +164,7 @@ static int hv_ce_set_oneshot(struct clock_event_device *evt)
timer_cfg.direct_mode = 0;
timer_cfg.sintx = VMBUS_MESSAGE_SINT;
}
- hv_init_timer_config(HV_X64_MSR_STIMER0_CONFIG, timer_cfg.as_uint64);
+ hv_init_timer_config(0, timer_cfg.as_uint64);
return 0;
}
@@ -298,8 +298,7 @@ int hv_synic_init(unsigned int cpu)
hv_set_siefp(siefp.as_uint64);
/* Setup the shared SINT. */
- hv_get_synint_state(HV_X64_MSR_SINT0 + VMBUS_MESSAGE_SINT,
- shared_sint.as_uint64);
+ hv_get_synint_state(VMBUS_MESSAGE_SINT, shared_sint.as_uint64);
shared_sint.vector = HYPERVISOR_CALLBACK_VECTOR;
shared_sint.masked = false;
@@ -308,8 +307,7 @@ int hv_synic_init(unsigned int cpu)
else
shared_sint.auto_eoi = true;
- hv_set_synint_state(HV_X64_MSR_SINT0 + VMBUS_MESSAGE_SINT,
- shared_sint.as_uint64);
+ hv_set_synint_state(VMBUS_MESSAGE_SINT, shared_sint.as_uint64);
/* Enable the global synic bit */
hv_get_synic_state(sctrl.as_uint64);
@@ -405,15 +403,13 @@ int hv_synic_cleanup(unsigned int cpu)
put_cpu_ptr(hv_cpu);
}
- hv_get_synint_state(HV_X64_MSR_SINT0 + VMBUS_MESSAGE_SINT,
- shared_sint.as_uint64);
+ hv_get_synint_state(VMBUS_MESSAGE_SINT, shared_sint.as_uint64);
shared_sint.masked = 1;
/* Need to correctly cleanup in the case of SMP!!! */
/* Disable the interrupt */
- hv_set_synint_state(HV_X64_MSR_SINT0 + VMBUS_MESSAGE_SINT,
- shared_sint.as_uint64);
+ hv_set_synint_state(VMBUS_MESSAGE_SINT, shared_sint.as_uint64);
hv_get_simp(simp.as_uint64);
simp.simp_enabled = 0;
--
2.17.1
^ permalink raw reply related [flat|nested] 9+ messages in thread* [PATCH 6/8] Drivers: hv: vmbus: Make TLFS #define names architecture neutral
2018-06-05 20:37 ` [PATCH 1/8] use the new async probing feature for the hyperv drivers kys
` (3 preceding siblings ...)
2018-06-05 20:37 ` [PATCH 5/8] Drivers: hv: vmbus: Remove x86 MSR refs in arch independent code kys
@ 2018-06-05 20:37 ` kys
2018-06-05 20:37 ` [PATCH 7/8] tools: hv: update lsvmbus to be compatible with python3 kys
2018-06-05 20:37 ` [PATCH 8/8] Tools: hv: vss: fix loop device detection kys
6 siblings, 0 replies; 9+ messages in thread
From: kys @ 2018-06-05 20:37 UTC (permalink / raw)
To: gregkh, linux-kernel, devel, olaf, apw, jasowang, sthemmin,
Michael.H.Kelley, vkuznets
Cc: Michael Kelley, K . Y . Srinivasan
From: Michael Kelley <mikelley@microsoft.com>
The Hyper-V feature and hint flags in hyperv-tlfs.h are all defined
with the string "X64" in the name. Some of these flags are indeed
x86/x64 specific, but others are not. For the ones that are used
in architecture independent Hyper-V driver code, or will be used in
the upcoming support for Hyper-V for ARM64, this patch removes the
"X64" from the name.
This patch changes the flags that are currently known to be
used on multiple architectures. Hyper-V for ARM64 is still a
work-in-progress and the Top Level Functional Spec (TLFS) has not
been separated into x86/x64 and ARM64 areas. So additional flags
may need to be updated later.
This patch only changes symbol names. There are no functional
changes.
Signed-off-by: Michael Kelley <mikelley@microsoft.com>
Signed-off-by: K. Y. Srinivasan <kys@microsoft.com>
---
arch/x86/hyperv/hv_init.c | 4 ++--
arch/x86/include/asm/hyperv-tlfs.h | 12 ++++++------
arch/x86/kernel/cpu/mshyperv.c | 4 ++--
drivers/hv/hv.c | 10 +++++-----
4 files changed, 15 insertions(+), 15 deletions(-)
diff --git a/arch/x86/hyperv/hv_init.c b/arch/x86/hyperv/hv_init.c
index cfecc2272f2d..3db87293dce0 100644
--- a/arch/x86/hyperv/hv_init.c
+++ b/arch/x86/hyperv/hv_init.c
@@ -302,7 +302,7 @@ void hyperv_init(void)
* Register Hyper-V specific clocksource.
*/
#ifdef CONFIG_HYPERV_TSCPAGE
- if (ms_hyperv.features & HV_X64_MSR_REFERENCE_TSC_AVAILABLE) {
+ if (ms_hyperv.features & HV_MSR_REFERENCE_TSC_AVAILABLE) {
union hv_x64_msr_hypercall_contents tsc_msr;
tsc_pg = __vmalloc(PAGE_SIZE, GFP_KERNEL, PAGE_KERNEL);
@@ -331,7 +331,7 @@ void hyperv_init(void)
*/
hyperv_cs = &hyperv_cs_msr;
- if (ms_hyperv.features & HV_X64_MSR_TIME_REF_COUNT_AVAILABLE)
+ if (ms_hyperv.features & HV_MSR_TIME_REF_COUNT_AVAILABLE)
clocksource_register_hz(&hyperv_cs_msr, NSEC_PER_SEC/100);
return;
diff --git a/arch/x86/include/asm/hyperv-tlfs.h b/arch/x86/include/asm/hyperv-tlfs.h
index 416cb0e0c496..44657e07fd59 100644
--- a/arch/x86/include/asm/hyperv-tlfs.h
+++ b/arch/x86/include/asm/hyperv-tlfs.h
@@ -35,9 +35,9 @@
/* VP Runtime (HV_X64_MSR_VP_RUNTIME) available */
#define HV_X64_MSR_VP_RUNTIME_AVAILABLE (1 << 0)
/* Partition Reference Counter (HV_X64_MSR_TIME_REF_COUNT) available*/
-#define HV_X64_MSR_TIME_REF_COUNT_AVAILABLE (1 << 1)
+#define HV_MSR_TIME_REF_COUNT_AVAILABLE (1 << 1)
/* Partition reference TSC MSR is available */
-#define HV_X64_MSR_REFERENCE_TSC_AVAILABLE (1 << 9)
+#define HV_MSR_REFERENCE_TSC_AVAILABLE (1 << 9)
/* A partition's reference time stamp counter (TSC) page */
#define HV_X64_MSR_REFERENCE_TSC 0x40000021
@@ -60,7 +60,7 @@
* Synthetic Timer MSRs (HV_X64_MSR_STIMER0_CONFIG through
* HV_X64_MSR_STIMER3_COUNT) available
*/
-#define HV_X64_MSR_SYNTIMER_AVAILABLE (1 << 3)
+#define HV_MSR_SYNTIMER_AVAILABLE (1 << 3)
/*
* APIC access MSRs (HV_X64_MSR_EOI, HV_X64_MSR_ICR and HV_X64_MSR_TPR)
* are available
@@ -86,7 +86,7 @@
#define HV_FEATURE_GUEST_CRASH_MSR_AVAILABLE (1 << 10)
/* stimer Direct Mode is available */
-#define HV_X64_STIMER_DIRECT_MODE_AVAILABLE (1 << 19)
+#define HV_STIMER_DIRECT_MODE_AVAILABLE (1 << 19)
/*
* Feature identification: EBX indicates which flags were specified at
@@ -160,9 +160,9 @@
#define HV_X64_RELAXED_TIMING_RECOMMENDED (1 << 5)
/*
- * Virtual APIC support
+ * Recommend not using Auto End-Of-Interrupt feature
*/
-#define HV_X64_DEPRECATING_AEOI_RECOMMENDED (1 << 9)
+#define HV_DEPRECATING_AEOI_RECOMMENDED (1 << 9)
/* Recommend using the newer ExProcessorMasks interface */
#define HV_X64_EX_PROCESSOR_MASKS_RECOMMENDED (1 << 11)
diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c
index 8a49b7ef7b76..ad12733f6058 100644
--- a/arch/x86/kernel/cpu/mshyperv.c
+++ b/arch/x86/kernel/cpu/mshyperv.c
@@ -50,7 +50,7 @@ __visible void __irq_entry hyperv_vector_handler(struct pt_regs *regs)
if (vmbus_handler)
vmbus_handler();
- if (ms_hyperv.hints & HV_X64_DEPRECATING_AEOI_RECOMMENDED)
+ if (ms_hyperv.hints & HV_DEPRECATING_AEOI_RECOMMENDED)
ack_APIC_irq();
exiting_irq();
@@ -300,7 +300,7 @@ static void __init ms_hyperv_init_platform(void)
hyperv_reenlightenment_vector);
/* Setup the IDT for stimer0 */
- if (ms_hyperv.misc_features & HV_X64_STIMER_DIRECT_MODE_AVAILABLE)
+ if (ms_hyperv.misc_features & HV_STIMER_DIRECT_MODE_AVAILABLE)
alloc_intr_gate(HYPERV_STIMER0_VECTOR,
hv_stimer0_callback_vector);
#endif
diff --git a/drivers/hv/hv.c b/drivers/hv/hv.c
index 96c403a07906..c72e8d7bd7fc 100644
--- a/drivers/hv/hv.c
+++ b/drivers/hv/hv.c
@@ -64,7 +64,7 @@ int hv_init(void)
return -ENOMEM;
direct_mode_enabled = ms_hyperv.misc_features &
- HV_X64_STIMER_DIRECT_MODE_AVAILABLE;
+ HV_STIMER_DIRECT_MODE_AVAILABLE;
return 0;
}
@@ -302,7 +302,7 @@ int hv_synic_init(unsigned int cpu)
shared_sint.vector = HYPERVISOR_CALLBACK_VECTOR;
shared_sint.masked = false;
- if (ms_hyperv.hints & HV_X64_DEPRECATING_AEOI_RECOMMENDED)
+ if (ms_hyperv.hints & HV_DEPRECATING_AEOI_RECOMMENDED)
shared_sint.auto_eoi = false;
else
shared_sint.auto_eoi = true;
@@ -320,7 +320,7 @@ int hv_synic_init(unsigned int cpu)
/*
* Register the per-cpu clockevent source.
*/
- if (ms_hyperv.features & HV_X64_MSR_SYNTIMER_AVAILABLE)
+ if (ms_hyperv.features & HV_MSR_SYNTIMER_AVAILABLE)
clockevents_config_and_register(hv_cpu->clk_evt,
HV_TIMER_FREQUENCY,
HV_MIN_DELTA_TICKS,
@@ -335,7 +335,7 @@ void hv_synic_clockevents_cleanup(void)
{
int cpu;
- if (!(ms_hyperv.features & HV_X64_MSR_SYNTIMER_AVAILABLE))
+ if (!(ms_hyperv.features & HV_MSR_SYNTIMER_AVAILABLE))
return;
if (direct_mode_enabled)
@@ -394,7 +394,7 @@ int hv_synic_cleanup(unsigned int cpu)
return -EBUSY;
/* Turn off clockevent device */
- if (ms_hyperv.features & HV_X64_MSR_SYNTIMER_AVAILABLE) {
+ if (ms_hyperv.features & HV_MSR_SYNTIMER_AVAILABLE) {
struct hv_per_cpu_context *hv_cpu
= this_cpu_ptr(hv_context.cpu_context);
--
2.17.1
^ permalink raw reply related [flat|nested] 9+ messages in thread* [PATCH 7/8] tools: hv: update lsvmbus to be compatible with python3
2018-06-05 20:37 ` [PATCH 1/8] use the new async probing feature for the hyperv drivers kys
` (4 preceding siblings ...)
2018-06-05 20:37 ` [PATCH 6/8] Drivers: hv: vmbus: Make TLFS #define names architecture neutral kys
@ 2018-06-05 20:37 ` kys
2018-06-05 20:37 ` [PATCH 8/8] Tools: hv: vss: fix loop device detection kys
6 siblings, 0 replies; 9+ messages in thread
From: kys @ 2018-06-05 20:37 UTC (permalink / raw)
To: gregkh, linux-kernel, devel, olaf, apw, jasowang, sthemmin,
Michael.H.Kelley, vkuznets
Cc: K . Y . Srinivasan
From: Olaf Hering <olaf@aepfle.de>
Python3 changed the way how 'print' works.
Adjust the code to a syntax that is understood by python2 and python3.
Signed-off-by: Olaf Hering <olaf@aepfle.de>
Acked-by: Dexuan Cui <decui@microsoft.com>
Signed-off-by: K. Y. Srinivasan <kys@microsoft.com>
---
tools/hv/lsvmbus | 12 ++++++------
1 file changed, 6 insertions(+), 6 deletions(-)
diff --git a/tools/hv/lsvmbus b/tools/hv/lsvmbus
index 353e56768df8..55e7374bade0 100644
--- a/tools/hv/lsvmbus
+++ b/tools/hv/lsvmbus
@@ -17,7 +17,7 @@ if options.verbose is not None:
vmbus_sys_path = '/sys/bus/vmbus/devices'
if not os.path.isdir(vmbus_sys_path):
- print "%s doesn't exist: exiting..." % vmbus_sys_path
+ print("%s doesn't exist: exiting..." % vmbus_sys_path)
exit(-1)
vmbus_dev_dict = {
@@ -93,11 +93,11 @@ format2 = '%2s: Class_ID = %s - %s\n\tDevice_ID = %s\n\tSysfs path: %s\n%s'
for d in vmbus_dev_list:
if verbose == 0:
- print ('VMBUS ID ' + format0) % (d.vmbus_id, d.dev_desc)
+ print(('VMBUS ID ' + format0) % (d.vmbus_id, d.dev_desc))
elif verbose == 1:
- print ('VMBUS ID ' + format1) % \
- (d.vmbus_id, d.class_id, d.dev_desc, d.chn_vp_mapping)
+ print (('VMBUS ID ' + format1) % \
+ (d.vmbus_id, d.class_id, d.dev_desc, d.chn_vp_mapping))
else:
- print ('VMBUS ID ' + format2) % \
+ print (('VMBUS ID ' + format2) % \
(d.vmbus_id, d.class_id, d.dev_desc, \
- d.device_id, d.sysfs_path, d.chn_vp_mapping)
+ d.device_id, d.sysfs_path, d.chn_vp_mapping))
--
2.17.1
^ permalink raw reply related [flat|nested] 9+ messages in thread* [PATCH 8/8] Tools: hv: vss: fix loop device detection
2018-06-05 20:37 ` [PATCH 1/8] use the new async probing feature for the hyperv drivers kys
` (5 preceding siblings ...)
2018-06-05 20:37 ` [PATCH 7/8] tools: hv: update lsvmbus to be compatible with python3 kys
@ 2018-06-05 20:37 ` kys
6 siblings, 0 replies; 9+ messages in thread
From: kys @ 2018-06-05 20:37 UTC (permalink / raw)
To: gregkh, linux-kernel, devel, olaf, apw, jasowang, sthemmin,
Michael.H.Kelley, vkuznets
Cc: K . Y . Srinivasan
From: Vitaly Kuznetsov <vkuznets@redhat.com>
Commit ea81fdf0981d ("Tools: hv: vss: Skip freezing filesystems backed by
loop") added skip for filesystems backed by loop device. However, it seems
the detection of such cases is incomplete.
It was found that with 'devicemapper' storage driver docker creates the
following chain:
NAME MAJ:MIN
loop0 7:0
..docker-8:4-8473394-pool 253:0
..docker-8:4-8473394-eac... 253:1
so when we're looking at the mounted device we see major '253' and not '7'.
Solve the issue by walking /sys/dev/block/*/slaves chain and checking if
there's a loop device somewhere.
Other than that, don't skip mountpoints silently when stat() fails. In case
e.g. SELinux is failing stat we don't want to skip freezing everything
without letting user know about the failure.
Fixes: ea81fdf0981d ("Tools: hv: vss: Skip freezing filesystems backed by loop")
Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Signed-off-by: K. Y. Srinivasan <kys@microsoft.com>
---
tools/hv/hv_vss_daemon.c | 65 +++++++++++++++++++++++++++++++++++++---
1 file changed, 61 insertions(+), 4 deletions(-)
diff --git a/tools/hv/hv_vss_daemon.c b/tools/hv/hv_vss_daemon.c
index 34031a297f02..b13300172762 100644
--- a/tools/hv/hv_vss_daemon.c
+++ b/tools/hv/hv_vss_daemon.c
@@ -36,6 +36,8 @@
#include <linux/hyperv.h>
#include <syslog.h>
#include <getopt.h>
+#include <stdbool.h>
+#include <dirent.h>
/* Don't use syslog() in the function since that can cause write to disk */
static int vss_do_freeze(char *dir, unsigned int cmd)
@@ -68,6 +70,55 @@ static int vss_do_freeze(char *dir, unsigned int cmd)
return !!ret;
}
+static bool is_dev_loop(const char *blkname)
+{
+ char *buffer;
+ DIR *dir;
+ struct dirent *entry;
+ bool ret = false;
+
+ buffer = malloc(PATH_MAX);
+ if (!buffer) {
+ syslog(LOG_ERR, "Can't allocate memory!");
+ exit(1);
+ }
+
+ snprintf(buffer, PATH_MAX, "%s/loop", blkname);
+ if (!access(buffer, R_OK | X_OK)) {
+ ret = true;
+ goto free_buffer;
+ } else if (errno != ENOENT) {
+ syslog(LOG_ERR, "Can't access: %s; error:%d %s!",
+ buffer, errno, strerror(errno));
+ }
+
+ snprintf(buffer, PATH_MAX, "%s/slaves", blkname);
+ dir = opendir(buffer);
+ if (!dir) {
+ if (errno != ENOENT)
+ syslog(LOG_ERR, "Can't opendir: %s; error:%d %s!",
+ buffer, errno, strerror(errno));
+ goto free_buffer;
+ }
+
+ while ((entry = readdir(dir)) != NULL) {
+ if (strcmp(entry->d_name, ".") == 0 ||
+ strcmp(entry->d_name, "..") == 0)
+ continue;
+
+ snprintf(buffer, PATH_MAX, "%s/slaves/%s", blkname,
+ entry->d_name);
+ if (is_dev_loop(buffer)) {
+ ret = true;
+ break;
+ }
+ }
+ closedir(dir);
+free_buffer:
+ free(buffer);
+ return ret;
+}
+
static int vss_operate(int operation)
{
char match[] = "/dev/";
@@ -75,6 +126,7 @@ static int vss_operate(int operation)
struct mntent *ent;
struct stat sb;
char errdir[1024] = {0};
+ char blkdir[23]; /* /sys/dev/block/XXX:XXX */
unsigned int cmd;
int error = 0, root_seen = 0, save_errno = 0;
@@ -96,10 +148,15 @@ static int vss_operate(int operation)
while ((ent = getmntent(mounts))) {
if (strncmp(ent->mnt_fsname, match, strlen(match)))
continue;
- if (stat(ent->mnt_fsname, &sb) == -1)
- continue;
- if (S_ISBLK(sb.st_mode) && major(sb.st_rdev) == LOOP_MAJOR)
- continue;
+ if (stat(ent->mnt_fsname, &sb)) {
+ syslog(LOG_ERR, "Can't stat: %s; error:%d %s!",
+ ent->mnt_fsname, errno, strerror(errno));
+ } else {
+ sprintf(blkdir, "/sys/dev/block/%d:%d",
+ major(sb.st_rdev), minor(sb.st_rdev));
+ if (is_dev_loop(blkdir))
+ continue;
+ }
if (hasmntopt(ent, MNTOPT_RO) != NULL)
continue;
if (strcmp(ent->mnt_type, "vfat") == 0)
--
2.17.1
^ permalink raw reply related [flat|nested] 9+ messages in thread