diff mbox

[PATCHv3,3/9] pseries: Clean up hash page table allocation error handling

Message ID 1453091083-13931-4-git-send-email-david@gibson.dropbear.id.au
State New, archived
Headers show

Commit Message

David Gibson Jan. 18, 2016, 4:24 a.m. UTC
The spapr_alloc_htab() and spapr_reset_htab() functions currently handle
all errors with error_setg(&error_abort, ...).

But really, the callers are really better placed to decide on the error
handling.  So, instead make the functions use the error propagation
infrastructure.

In the callers we change to &error_fatal instead of &error_abort, since
this can be triggered by a bad configuration or kernel error rather than
indicating a programming error in qemu.

While we're at it improve the messages themselves a bit, and clean up the
indentation a little.

Signed-off-by: David Gibson <david@gibson.dropbear.id.au>
---
 hw/ppc/spapr.c | 24 ++++++++++++++++--------
 1 file changed, 16 insertions(+), 8 deletions(-)

Comments

Thomas Huth Jan. 18, 2016, 8:47 a.m. UTC | #1
On 18.01.2016 05:24, David Gibson wrote:
> The spapr_alloc_htab() and spapr_reset_htab() functions currently handle
> all errors with error_setg(&error_abort, ...).
> 
> But really, the callers are really better placed to decide on the error
> handling.  So, instead make the functions use the error propagation
> infrastructure.
> 
> In the callers we change to &error_fatal instead of &error_abort, since
> this can be triggered by a bad configuration or kernel error rather than
> indicating a programming error in qemu.
> 
> While we're at it improve the messages themselves a bit, and clean up the
> indentation a little.
> 
> Signed-off-by: David Gibson <david@gibson.dropbear.id.au>
> ---
>  hw/ppc/spapr.c | 24 ++++++++++++++++--------
>  1 file changed, 16 insertions(+), 8 deletions(-)
> 
> diff --git a/hw/ppc/spapr.c b/hw/ppc/spapr.c
> index b7fd09a..d28e349 100644
> --- a/hw/ppc/spapr.c
> +++ b/hw/ppc/spapr.c
> @@ -1016,7 +1016,7 @@ static void emulate_spapr_hypercall(PowerPCCPU *cpu)
>  #define CLEAN_HPTE(_hpte)  ((*(uint64_t *)(_hpte)) &= tswap64(~HPTE64_V_HPTE_DIRTY))
>  #define DIRTY_HPTE(_hpte)  ((*(uint64_t *)(_hpte)) |= tswap64(HPTE64_V_HPTE_DIRTY))
>  
> -static void spapr_alloc_htab(sPAPRMachineState *spapr)
> +static void spapr_alloc_htab(sPAPRMachineState *spapr, Error **errp)
>  {
>      long shift;
>      int index;
> @@ -1031,7 +1031,8 @@ static void spapr_alloc_htab(sPAPRMachineState *spapr)
>           * For HV KVM, host kernel will return -ENOMEM when requested
>           * HTAB size can't be allocated.
>           */
> -        error_setg(&error_abort, "Failed to allocate HTAB of requested size, try with smaller maxmem");
> +        error_setg_errno(errp, -shift,
> +                         "Error allocating KVM hash page table, try smaller maxmem");
>      } else if (shift > 0) {
>          /*
>           * Kernel handles htab, we don't need to allocate one
> @@ -1040,7 +1041,10 @@ static void spapr_alloc_htab(sPAPRMachineState *spapr)
>           * but we don't allow booting of such guests.
>           */
>          if (shift != spapr->htab_shift) {
> -            error_setg(&error_abort, "Failed to allocate HTAB of requested size, try with smaller maxmem");
> +            error_setg(errp,
> +                "Small allocation for KVM hash page table (%ld < %"
> +                PRIu32 "), try smaller maxmem",
> +                shift, spapr->htab_shift);

Maybe you should add an "return" statement here - theoretically you do
not want to continue with "kvmppc_kern_htab = true" in case of errors.
(practically this does not happen because errp = error_fatal, but in
case the caller gets changed, this might introduce subtle errors otherwise)

>          }
>  
>          spapr->htab_shift = shift;
> @@ -1064,17 +1068,21 @@ static void spapr_alloc_htab(sPAPRMachineState *spapr)
>   * If host kernel has allocated HTAB, KVM_PPC_ALLOCATE_HTAB ioctl is
>   * used to clear HTAB. Otherwise QEMU-allocated HTAB is cleared manually.
>   */
> -static void spapr_reset_htab(sPAPRMachineState *spapr)
> +static void spapr_reset_htab(sPAPRMachineState *spapr, Error **errp)
>  {
>      long shift;
>      int index;
>  
>      shift = kvmppc_reset_htab(spapr->htab_shift);
>      if (shift < 0) {
> -        error_setg(&error_abort, "Failed to reset HTAB");
> +        error_setg_errno(errp, -shift,
> +                   "Error resetting KVM hash page table, try smaller maxmem");

dito, better do an "return" here...

>      } else if (shift > 0) {
>          if (shift != spapr->htab_shift) {
> -            error_setg(&error_abort, "Requested HTAB allocation failed during reset");
> +            error_setg(errp,
> +                "Reduced size on reset of KVM hash page table (%ld < %"
> +                PRIu32 "), try smaller maxmem",
> +                shift, spapr->htab_shift);

... and here.

>          }
>  
>          /* Tell readers to update their file descriptor */
> @@ -1145,7 +1153,7 @@ static void ppc_spapr_reset(void)
>      foreach_dynamic_sysbus_device(find_unknown_sysbus_device, NULL);
>  
>      /* Reset the hash table & recalc the RMA */
> -    spapr_reset_htab(spapr);
> +    spapr_reset_htab(spapr, &error_fatal);
>  
>      qemu_devices_reset();
>  
> @@ -1792,7 +1800,7 @@ static void ppc_spapr_init(MachineState *machine)
>          }
>          spapr->htab_shift++;
>      }
> -    spapr_alloc_htab(spapr);
> +    spapr_alloc_htab(spapr, &error_fatal);
>  
>      /* Set up Interrupt Controller before we create the VCPUs */
>      spapr->icp = xics_system_init(machine,
> 

 Thomas
Markus Armbruster Jan. 18, 2016, 10:21 a.m. UTC | #2
Thomas Huth <thuth@redhat.com> writes:

> On 18.01.2016 05:24, David Gibson wrote:
>> The spapr_alloc_htab() and spapr_reset_htab() functions currently handle
>> all errors with error_setg(&error_abort, ...).
>> 
>> But really, the callers are really better placed to decide on the error
>> handling.  So, instead make the functions use the error propagation
>> infrastructure.
>> 
>> In the callers we change to &error_fatal instead of &error_abort, since
>> this can be triggered by a bad configuration or kernel error rather than
>> indicating a programming error in qemu.
>> 
>> While we're at it improve the messages themselves a bit, and clean up the
>> indentation a little.
>> 
>> Signed-off-by: David Gibson <david@gibson.dropbear.id.au>
>> ---
>>  hw/ppc/spapr.c | 24 ++++++++++++++++--------
>>  1 file changed, 16 insertions(+), 8 deletions(-)
>> 
>> diff --git a/hw/ppc/spapr.c b/hw/ppc/spapr.c
>> index b7fd09a..d28e349 100644
>> --- a/hw/ppc/spapr.c
>> +++ b/hw/ppc/spapr.c
>> @@ -1016,7 +1016,7 @@ static void emulate_spapr_hypercall(PowerPCCPU *cpu)
>>  #define CLEAN_HPTE(_hpte)  ((*(uint64_t *)(_hpte)) &= tswap64(~HPTE64_V_HPTE_DIRTY))
>>  #define DIRTY_HPTE(_hpte)  ((*(uint64_t *)(_hpte)) |= tswap64(HPTE64_V_HPTE_DIRTY))
>>  
>> -static void spapr_alloc_htab(sPAPRMachineState *spapr)
>> +static void spapr_alloc_htab(sPAPRMachineState *spapr, Error **errp)
>>  {
>>      long shift;
>>      int index;
>> @@ -1031,7 +1031,8 @@ static void spapr_alloc_htab(sPAPRMachineState *spapr)
>>           * For HV KVM, host kernel will return -ENOMEM when requested
>>           * HTAB size can't be allocated.
>>           */
>> -        error_setg(&error_abort, "Failed to allocate HTAB of requested size, try with smaller maxmem");
>> +        error_setg_errno(errp, -shift,
>> +                         "Error allocating KVM hash page table, try smaller maxmem");
>>      } else if (shift > 0) {
>>          /*
>>           * Kernel handles htab, we don't need to allocate one
>> @@ -1040,7 +1041,10 @@ static void spapr_alloc_htab(sPAPRMachineState *spapr)
>>           * but we don't allow booting of such guests.
>>           */
>>          if (shift != spapr->htab_shift) {
>> -            error_setg(&error_abort, "Failed to allocate HTAB of requested size, try with smaller maxmem");
>> +            error_setg(errp,
>> +                "Small allocation for KVM hash page table (%ld < %"
>> +                PRIu32 "), try smaller maxmem",
>> +                shift, spapr->htab_shift);
>
> Maybe you should add an "return" statement here - theoretically you do
> not want to continue with "kvmppc_kern_htab = true" in case of errors.
> (practically this does not happen because errp = error_fatal, but in
> case the caller gets changed, this might introduce subtle errors otherwise)

Good point.

With abort() / exit(), we don't have to worry about recovery.  In
particular, we don't have to revert half-done changes.

Conversions away from abort() / exit() need to consider error recovery.
We have to make sure the function leaves things in a sane state on
error.  This normally means taking an early return, and often means
reverting some state changes.

[...]
David Gibson Jan. 19, 2016, 12:20 a.m. UTC | #3
On Mon, Jan 18, 2016 at 09:47:59AM +0100, Thomas Huth wrote:
> On 18.01.2016 05:24, David Gibson wrote:
> > The spapr_alloc_htab() and spapr_reset_htab() functions currently handle
> > all errors with error_setg(&error_abort, ...).
> > 
> > But really, the callers are really better placed to decide on the error
> > handling.  So, instead make the functions use the error propagation
> > infrastructure.
> > 
> > In the callers we change to &error_fatal instead of &error_abort, since
> > this can be triggered by a bad configuration or kernel error rather than
> > indicating a programming error in qemu.
> > 
> > While we're at it improve the messages themselves a bit, and clean up the
> > indentation a little.
> > 
> > Signed-off-by: David Gibson <david@gibson.dropbear.id.au>
> > ---
> >  hw/ppc/spapr.c | 24 ++++++++++++++++--------
> >  1 file changed, 16 insertions(+), 8 deletions(-)
> > 
> > diff --git a/hw/ppc/spapr.c b/hw/ppc/spapr.c
> > index b7fd09a..d28e349 100644
> > --- a/hw/ppc/spapr.c
> > +++ b/hw/ppc/spapr.c
> > @@ -1016,7 +1016,7 @@ static void emulate_spapr_hypercall(PowerPCCPU *cpu)
> >  #define CLEAN_HPTE(_hpte)  ((*(uint64_t *)(_hpte)) &= tswap64(~HPTE64_V_HPTE_DIRTY))
> >  #define DIRTY_HPTE(_hpte)  ((*(uint64_t *)(_hpte)) |= tswap64(HPTE64_V_HPTE_DIRTY))
> >  
> > -static void spapr_alloc_htab(sPAPRMachineState *spapr)
> > +static void spapr_alloc_htab(sPAPRMachineState *spapr, Error **errp)
> >  {
> >      long shift;
> >      int index;
> > @@ -1031,7 +1031,8 @@ static void spapr_alloc_htab(sPAPRMachineState *spapr)
> >           * For HV KVM, host kernel will return -ENOMEM when requested
> >           * HTAB size can't be allocated.
> >           */
> > -        error_setg(&error_abort, "Failed to allocate HTAB of requested size, try with smaller maxmem");
> > +        error_setg_errno(errp, -shift,
> > +                         "Error allocating KVM hash page table, try smaller maxmem");
> >      } else if (shift > 0) {
> >          /*
> >           * Kernel handles htab, we don't need to allocate one
> > @@ -1040,7 +1041,10 @@ static void spapr_alloc_htab(sPAPRMachineState *spapr)
> >           * but we don't allow booting of such guests.
> >           */
> >          if (shift != spapr->htab_shift) {
> > -            error_setg(&error_abort, "Failed to allocate HTAB of requested size, try with smaller maxmem");
> > +            error_setg(errp,
> > +                "Small allocation for KVM hash page table (%ld < %"
> > +                PRIu32 "), try smaller maxmem",
> > +                shift, spapr->htab_shift);
> 
> Maybe you should add an "return" statement here - theoretically you do
> not want to continue with "kvmppc_kern_htab = true" in case of errors.
> (practically this does not happen because errp = error_fatal, but in
> case the caller gets changed, this might introduce subtle errors
> otherwise)

No, actually.  If the error is non-fatal, then we *must* set
kvmppc_kern_htab = true.  It is possible we can continue without the
size of hash table we wanted - we did so until pretty recently.  But
it *is* still a kernel provided hash table, and must be marked as such
to operate correctly.

> 
> >          }
> >  
> >          spapr->htab_shift = shift;
> > @@ -1064,17 +1068,21 @@ static void spapr_alloc_htab(sPAPRMachineState *spapr)
> >   * If host kernel has allocated HTAB, KVM_PPC_ALLOCATE_HTAB ioctl is
> >   * used to clear HTAB. Otherwise QEMU-allocated HTAB is cleared manually.
> >   */
> > -static void spapr_reset_htab(sPAPRMachineState *spapr)
> > +static void spapr_reset_htab(sPAPRMachineState *spapr, Error **errp)
> >  {
> >      long shift;
> >      int index;
> >  
> >      shift = kvmppc_reset_htab(spapr->htab_shift);
> >      if (shift < 0) {
> > -        error_setg(&error_abort, "Failed to reset HTAB");
> > +        error_setg_errno(errp, -shift,
> > +                   "Error resetting KVM hash page table, try smaller maxmem");
> 
> dito, better do an "return" here...

No.  The remaining statement in the function could be relevant if
we're somehow able to keep going here.

> >      } else if (shift > 0) {
> >          if (shift != spapr->htab_shift) {
> > -            error_setg(&error_abort, "Requested HTAB allocation failed during reset");
> > +            error_setg(errp,
> > +                "Reduced size on reset of KVM hash page table (%ld < %"
> > +                PRIu32 "), try smaller maxmem",
> > +                shift, spapr->htab_shift);
> 
> ... and here.

Hrm.. here, yes we would be in trouble, but 'return' wouldn't help in
the slightest.  Instead we'd need to change spapr->htab_shift to have
any hope of continuing.

I'll make that change.
David Gibson Jan. 19, 2016, 1:12 a.m. UTC | #4
On Mon, Jan 18, 2016 at 11:21:08AM +0100, Markus Armbruster wrote:
> Thomas Huth <thuth@redhat.com> writes:
> 
> > On 18.01.2016 05:24, David Gibson wrote:
> >> The spapr_alloc_htab() and spapr_reset_htab() functions currently handle
> >> all errors with error_setg(&error_abort, ...).
> >> 
> >> But really, the callers are really better placed to decide on the error
> >> handling.  So, instead make the functions use the error propagation
> >> infrastructure.
> >> 
> >> In the callers we change to &error_fatal instead of &error_abort, since
> >> this can be triggered by a bad configuration or kernel error rather than
> >> indicating a programming error in qemu.
> >> 
> >> While we're at it improve the messages themselves a bit, and clean up the
> >> indentation a little.
> >> 
> >> Signed-off-by: David Gibson <david@gibson.dropbear.id.au>
> >> ---
> >>  hw/ppc/spapr.c | 24 ++++++++++++++++--------
> >>  1 file changed, 16 insertions(+), 8 deletions(-)
> >> 
> >> diff --git a/hw/ppc/spapr.c b/hw/ppc/spapr.c
> >> index b7fd09a..d28e349 100644
> >> --- a/hw/ppc/spapr.c
> >> +++ b/hw/ppc/spapr.c
> >> @@ -1016,7 +1016,7 @@ static void emulate_spapr_hypercall(PowerPCCPU *cpu)
> >>  #define CLEAN_HPTE(_hpte)  ((*(uint64_t *)(_hpte)) &= tswap64(~HPTE64_V_HPTE_DIRTY))
> >>  #define DIRTY_HPTE(_hpte)  ((*(uint64_t *)(_hpte)) |= tswap64(HPTE64_V_HPTE_DIRTY))
> >>  
> >> -static void spapr_alloc_htab(sPAPRMachineState *spapr)
> >> +static void spapr_alloc_htab(sPAPRMachineState *spapr, Error **errp)
> >>  {
> >>      long shift;
> >>      int index;
> >> @@ -1031,7 +1031,8 @@ static void spapr_alloc_htab(sPAPRMachineState *spapr)
> >>           * For HV KVM, host kernel will return -ENOMEM when requested
> >>           * HTAB size can't be allocated.
> >>           */
> >> -        error_setg(&error_abort, "Failed to allocate HTAB of requested size, try with smaller maxmem");
> >> +        error_setg_errno(errp, -shift,
> >> +                         "Error allocating KVM hash page table, try smaller maxmem");
> >>      } else if (shift > 0) {
> >>          /*
> >>           * Kernel handles htab, we don't need to allocate one
> >> @@ -1040,7 +1041,10 @@ static void spapr_alloc_htab(sPAPRMachineState *spapr)
> >>           * but we don't allow booting of such guests.
> >>           */
> >>          if (shift != spapr->htab_shift) {
> >> -            error_setg(&error_abort, "Failed to allocate HTAB of requested size, try with smaller maxmem");
> >> +            error_setg(errp,
> >> +                "Small allocation for KVM hash page table (%ld < %"
> >> +                PRIu32 "), try smaller maxmem",
> >> +                shift, spapr->htab_shift);
> >
> > Maybe you should add an "return" statement here - theoretically you do
> > not want to continue with "kvmppc_kern_htab = true" in case of errors.
> > (practically this does not happen because errp = error_fatal, but in
> > case the caller gets changed, this might introduce subtle errors otherwise)
> 
> Good point.
> 
> With abort() / exit(), we don't have to worry about recovery.  In
> particular, we don't have to revert half-done changes.
> 
> Conversions away from abort() / exit() need to consider error recovery.
> We have to make sure the function leaves things in a sane state on
> error.  This normally means taking an early return, and often means
> reverting some state changes.

That's true, but Thomas is mistaken about what error recovery is
needed here.

However, I'm going to drop this patch from the series anyway - I've
realised I need to rework the htab allocation substantially for other
reasons, so it would be better to not have that conflict with this
series.
diff mbox

Patch

diff --git a/hw/ppc/spapr.c b/hw/ppc/spapr.c
index b7fd09a..d28e349 100644
--- a/hw/ppc/spapr.c
+++ b/hw/ppc/spapr.c
@@ -1016,7 +1016,7 @@  static void emulate_spapr_hypercall(PowerPCCPU *cpu)
 #define CLEAN_HPTE(_hpte)  ((*(uint64_t *)(_hpte)) &= tswap64(~HPTE64_V_HPTE_DIRTY))
 #define DIRTY_HPTE(_hpte)  ((*(uint64_t *)(_hpte)) |= tswap64(HPTE64_V_HPTE_DIRTY))
 
-static void spapr_alloc_htab(sPAPRMachineState *spapr)
+static void spapr_alloc_htab(sPAPRMachineState *spapr, Error **errp)
 {
     long shift;
     int index;
@@ -1031,7 +1031,8 @@  static void spapr_alloc_htab(sPAPRMachineState *spapr)
          * For HV KVM, host kernel will return -ENOMEM when requested
          * HTAB size can't be allocated.
          */
-        error_setg(&error_abort, "Failed to allocate HTAB of requested size, try with smaller maxmem");
+        error_setg_errno(errp, -shift,
+                         "Error allocating KVM hash page table, try smaller maxmem");
     } else if (shift > 0) {
         /*
          * Kernel handles htab, we don't need to allocate one
@@ -1040,7 +1041,10 @@  static void spapr_alloc_htab(sPAPRMachineState *spapr)
          * but we don't allow booting of such guests.
          */
         if (shift != spapr->htab_shift) {
-            error_setg(&error_abort, "Failed to allocate HTAB of requested size, try with smaller maxmem");
+            error_setg(errp,
+                "Small allocation for KVM hash page table (%ld < %"
+                PRIu32 "), try smaller maxmem",
+                shift, spapr->htab_shift);
         }
 
         spapr->htab_shift = shift;
@@ -1064,17 +1068,21 @@  static void spapr_alloc_htab(sPAPRMachineState *spapr)
  * If host kernel has allocated HTAB, KVM_PPC_ALLOCATE_HTAB ioctl is
  * used to clear HTAB. Otherwise QEMU-allocated HTAB is cleared manually.
  */
-static void spapr_reset_htab(sPAPRMachineState *spapr)
+static void spapr_reset_htab(sPAPRMachineState *spapr, Error **errp)
 {
     long shift;
     int index;
 
     shift = kvmppc_reset_htab(spapr->htab_shift);
     if (shift < 0) {
-        error_setg(&error_abort, "Failed to reset HTAB");
+        error_setg_errno(errp, -shift,
+                   "Error resetting KVM hash page table, try smaller maxmem");
     } else if (shift > 0) {
         if (shift != spapr->htab_shift) {
-            error_setg(&error_abort, "Requested HTAB allocation failed during reset");
+            error_setg(errp,
+                "Reduced size on reset of KVM hash page table (%ld < %"
+                PRIu32 "), try smaller maxmem",
+                shift, spapr->htab_shift);
         }
 
         /* Tell readers to update their file descriptor */
@@ -1145,7 +1153,7 @@  static void ppc_spapr_reset(void)
     foreach_dynamic_sysbus_device(find_unknown_sysbus_device, NULL);
 
     /* Reset the hash table & recalc the RMA */
-    spapr_reset_htab(spapr);
+    spapr_reset_htab(spapr, &error_fatal);
 
     qemu_devices_reset();
 
@@ -1792,7 +1800,7 @@  static void ppc_spapr_init(MachineState *machine)
         }
         spapr->htab_shift++;
     }
-    spapr_alloc_htab(spapr);
+    spapr_alloc_htab(spapr, &error_fatal);
 
     /* Set up Interrupt Controller before we create the VCPUs */
     spapr->icp = xics_system_init(machine,