On 03/09/2024 11:30 am, Michal Orzel wrote:
>
> On 02/09/2024 12:03, Andrew Cooper wrote:
>>
>> These are all loops over a scalar value, and don't need to call general bitop
>> helpers behind the scenes.
>>
>> No functional change.
>>
>> Signed-off-by: Andrew Cooper <[email protected]>
>> ---
>> CC: Stefano Stabellini <[email protected]>
>> CC: Julien Grall <[email protected]>
>> CC: Volodymyr Babchuk <[email protected]>
>> CC: Bertrand Marquis <[email protected]>
>> CC: Michal Orzel <[email protected]>
>>
>> Slighly RFC. It's unclear whether len is the size of the register, or the
>> size of the access. For sub-GPR accesses, won't the upper bits be clear
>> anyway? If so, this can be simplified further.
> See dispatch_mmio_write(). "len" refers to access size (i.e. 1/4/8 bytes).
> Each register is defined
> with a region access i.e. VGIC_ACCESS_32bit that is compared with the actual
> access. In the current code
> there is no register with 8B access. If there is a mismatch, there will be a
> data abort injected.
> Also, the top 32-bits are not cleared anywhere, so I don't think we can drop
> masking. @Julien?
Ok, so it is necessary right now to have the clamping logic in every
callback.
However, given that the size is validated before dispatching, clamping
once in dispatch_mmio_write() would save a lot of repeated code in the
callbacks.
i.e., I think this:
diff --git a/xen/arch/arm/vgic/vgic-mmio.c b/xen/arch/arm/vgic/vgic-mmio.c
index bd4caf7fc326..e8b9805a0b2c 100644
--- a/xen/arch/arm/vgic/vgic-mmio.c
+++ b/xen/arch/arm/vgic/vgic-mmio.c
@@ -590,6 +590,9 @@ static int dispatch_mmio_write(struct vcpu *vcpu,
mmio_info_t *info,
if ( !region )
return 0;
+ if ( len < sizeof(data) )
+ data &= ~((1UL << (len * 8)) - 1);
+
switch (iodev->iodev_type)
{
case IODEV_DIST:
would work to replace every if() introduced below.
~Andrew
>
>> $ ../scripts/bloat-o-meter xen-syms-arm64-{before,after}
>> add/remove: 0/0 grow/shrink: 2/5 up/down: 20/-140 (-120)
>> Function old new delta
>> vgic_mmio_write_spending 320 332 +12
>> vgic_mmio_write_cpending 368 376 +8
>> vgic_mmio_write_sactive 192 176 -16
>> vgic_mmio_write_cactive 192 176 -16
>> vgic_mmio_write_cenable 316 288 -28
>> vgic_mmio_write_senable 320 284 -36
>> vgic_mmio_write_sgir 344 300 -44
>>
>> $ ../scripts/bloat-o-meter xen-syms-arm32-{before,after}
>> add/remove: 0/0 grow/shrink: 0/4 up/down: 0/-32 (-32)
>> Function old new delta
>> vgic_mmio_write_sactive 204 200 -4
>> vgic_mmio_write_cpending 464 460 -4
>> vgic_mmio_write_cactive 204 200 -4
>> vgic_mmio_write_sgir 336 316 -20
>> ---
>> xen/arch/arm/vgic/vgic-mmio-v2.c | 3 +--
>> xen/arch/arm/vgic/vgic-mmio.c | 36 +++++++++++++++++++++-----------
>> 2 files changed, 25 insertions(+), 14 deletions(-)
>>
>> diff --git a/xen/arch/arm/vgic/vgic-mmio-v2.c
>> b/xen/arch/arm/vgic/vgic-mmio-v2.c
>> index 670b335db2c3..42fac0403f07 100644
>> --- a/xen/arch/arm/vgic/vgic-mmio-v2.c
>> +++ b/xen/arch/arm/vgic/vgic-mmio-v2.c
>> @@ -90,7 +90,6 @@ static void vgic_mmio_write_sgir(struct vcpu *source_vcpu,
>> unsigned int intid = val & GICD_SGI_INTID_MASK;
>> unsigned long targets = (val & GICD_SGI_TARGET_MASK) >>
>> GICD_SGI_TARGET_SHIFT;
>> - unsigned int vcpu_id;
>>
>> switch ( val & GICD_SGI_TARGET_LIST_MASK )
>> {
>> @@ -108,7 +107,7 @@ static void vgic_mmio_write_sgir(struct vcpu
>> *source_vcpu,
>> return;
>> }
>>
>> - bitmap_for_each ( vcpu_id, &targets, 8 )
>> + for_each_set_bit ( vcpu_id, (uint8_t)targets )
>> {
>> struct vcpu *vcpu = d->vcpu[vcpu_id];
>> struct vgic_irq *irq = vgic_get_irq(d, vcpu, intid);
>> diff --git a/xen/arch/arm/vgic/vgic-mmio.c b/xen/arch/arm/vgic/vgic-mmio.c
>> index bd4caf7fc326..f7c336a238ab 100644
>> --- a/xen/arch/arm/vgic/vgic-mmio.c
>> +++ b/xen/arch/arm/vgic/vgic-mmio.c
>> @@ -69,9 +69,11 @@ void vgic_mmio_write_senable(struct vcpu *vcpu,
>> unsigned long val)
>> {
>> uint32_t intid = VGIC_ADDR_TO_INTID(addr, 1);
>> - unsigned int i;
>>
>> - bitmap_for_each ( i, &val, len * 8 )
>> + if ( len < sizeof(val) )
>> + val &= (1UL << (len * 8)) - 1;
>> +
>> + for_each_set_bit ( i, val )
>> {
>> struct vgic_irq *irq = vgic_get_irq(vcpu->domain, vcpu, intid + i);
>> unsigned long flags;
>> @@ -114,9 +116,11 @@ void vgic_mmio_write_cenable(struct vcpu *vcpu,
>> unsigned long val)
>> {
>> uint32_t intid = VGIC_ADDR_TO_INTID(addr, 1);
>> - unsigned int i;
>>
>> - bitmap_for_each ( i, &val, len * 8 )
>> + if ( len < sizeof(val) )
>> + val &= (1UL << (len * 8)) - 1;
>> +
>> + for_each_set_bit ( i, val )
>> {
>> struct vgic_irq *irq;
>> unsigned long flags;
>> @@ -182,11 +186,13 @@ void vgic_mmio_write_spending(struct vcpu *vcpu,
>> unsigned long val)
>> {
>> uint32_t intid = VGIC_ADDR_TO_INTID(addr, 1);
>> - unsigned int i;
>> unsigned long flags;
>> irq_desc_t *desc;
>>
>> - bitmap_for_each ( i, &val, len * 8 )
>> + if ( len < sizeof(val) )
>> + val &= (1UL << (len * 8)) - 1;
>> +
>> + for_each_set_bit ( i, val )
>> {
>> struct vgic_irq *irq = vgic_get_irq(vcpu->domain, vcpu, intid + i);
>>
>> @@ -230,11 +236,13 @@ void vgic_mmio_write_cpending(struct vcpu *vcpu,
>> unsigned long val)
>> {
>> uint32_t intid = VGIC_ADDR_TO_INTID(addr, 1);
>> - unsigned int i;
>> unsigned long flags;
>> irq_desc_t *desc;
>>
>> - bitmap_for_each ( i, &val, len * 8 )
>> + if ( len < sizeof(val) )
>> + val &= (1UL << (len * 8)) - 1;
>> +
>> + for_each_set_bit ( i, val )
>> {
>> struct vgic_irq *irq = vgic_get_irq(vcpu->domain, vcpu, intid + i);
>>
>> @@ -326,9 +334,11 @@ void vgic_mmio_write_cactive(struct vcpu *vcpu,
>> unsigned long val)
>> {
>> uint32_t intid = VGIC_ADDR_TO_INTID(addr, 1);
>> - unsigned int i;
>>
>> - bitmap_for_each ( i, &val, len * 8 )
>> + if ( len < sizeof(val) )
>> + val &= (1UL << (len * 8)) - 1;
>> +
>> + for_each_set_bit ( i, val )
>> {
>> struct vgic_irq *irq = vgic_get_irq(vcpu->domain, vcpu, intid + i);
>>
>> @@ -356,9 +366,11 @@ void vgic_mmio_write_sactive(struct vcpu *vcpu,
>> unsigned long val)
>> {
>> uint32_t intid = VGIC_ADDR_TO_INTID(addr, 1);
>> - unsigned int i;
>>
>> - bitmap_for_each ( i, &val, len * 8 )
>> + if ( len < sizeof(val) )
>> + val &= (1UL << (len * 8)) - 1;
>> +
>> + for_each_set_bit ( i, val )
>> {
>> struct vgic_irq *irq = vgic_get_irq(vcpu->domain, vcpu, intid + i);
>>
>> --
>> 2.39.2
>>
> ~Michal
