Displaying 20 results from an estimated 37 matches for "swiotlb_force".
2007 Jan 20
5
[PATCH] Fix linux compilation on x86-64
This patch fixes Linux 2.6.18 compilation on x86-64 and also works on
i386.
Signed-off-by: Stefan Berger <stefanb@us.ibm.com>
_______________________________________________
Xen-devel mailing list
Xen-devel@lists.xensource.com
http://lists.xensource.com/xen-devel
2013 Sep 04
1
[PATCHv2] tracing/events: Add bounce tracing to swiotbl
...but
calls spinlock functions, memcpy() and xen_phys_to_bus() as well. This patch
introduces the swiotlb:swiotlb_bounced event, which also prints out the
following informations to help you find out why bouncing happened:
dev_name: 0000:08:00.0 dma_mask=ffffffffffffffff dev_addr=9149f000 size=32768
swiotlb_force=0
If you use Xen, and (dev_addr + size + 1) > dma_mask, the buffer is out of the
device's DMA range. If swiotlb_force == 1, you should really change the kernel
parameters. Otherwise, the buffer is not contiguous in mfn space.
Signed-off-by: Zoltan Kiss <zoltan.kiss at citrix.com>
---...
2013 Sep 04
1
[PATCHv2] tracing/events: Add bounce tracing to swiotbl
...but
calls spinlock functions, memcpy() and xen_phys_to_bus() as well. This patch
introduces the swiotlb:swiotlb_bounced event, which also prints out the
following informations to help you find out why bouncing happened:
dev_name: 0000:08:00.0 dma_mask=ffffffffffffffff dev_addr=9149f000 size=32768
swiotlb_force=0
If you use Xen, and (dev_addr + size + 1) > dma_mask, the buffer is out of the
device's DMA range. If swiotlb_force == 1, you should really change the kernel
parameters. Otherwise, the buffer is not contiguous in mfn space.
Signed-off-by: Zoltan Kiss <zoltan.kiss at citrix.com>
---...
2013 Sep 04
1
[PATCHv2] tracing/events: Add bounce tracing to swiotbl
...but
calls spinlock functions, memcpy() and xen_phys_to_bus() as well. This patch
introduces the swiotlb:swiotlb_bounced event, which also prints out the
following informations to help you find out why bouncing happened:
dev_name: 0000:08:00.0 dma_mask=ffffffffffffffff dev_addr=9149f000 size=32768
swiotlb_force=0
If you use Xen, and (dev_addr + size + 1) > dma_mask, the buffer is out of the
device's DMA range. If swiotlb_force == 1, you should really change the kernel
parameters. Otherwise, the buffer is not contiguous in mfn space.
Signed-off-by: Zoltan Kiss <zoltan.kiss at citrix.com>
---...
2013 Aug 22
2
[PATCH] tracing/events: Add bounce tracing to swiotbl-xen
...y(), but
calls spinlock functions, memcpy() and xen_phys_to_bus() as well. This patch
introduces the swiotlb-xen:bounced event, which also prints out the following
informations to help you find out why bouncing happened:
dev_name: 0000:08:00.0 dma_mask=ffffffffffffffff dev_addr=9149f000 size=32768
swiotlb_force=0
If (dev_addr + size + 1) > dma_mask, the buffer is out of the device's DMA
range. If swiotlb_force == 1, you should really change the kernel parameters.
Otherwise, the buffer is not contiguous in mfn space.
Signed-off-by: Zoltan Kiss <zoltan.kiss at citrix.com>
---
drivers/xen/swi...
2013 Aug 22
2
[PATCH] tracing/events: Add bounce tracing to swiotbl-xen
...y(), but
calls spinlock functions, memcpy() and xen_phys_to_bus() as well. This patch
introduces the swiotlb-xen:bounced event, which also prints out the following
informations to help you find out why bouncing happened:
dev_name: 0000:08:00.0 dma_mask=ffffffffffffffff dev_addr=9149f000 size=32768
swiotlb_force=0
If (dev_addr + size + 1) > dma_mask, the buffer is out of the device's DMA
range. If swiotlb_force == 1, you should really change the kernel parameters.
Otherwise, the buffer is not contiguous in mfn space.
Signed-off-by: Zoltan Kiss <zoltan.kiss at citrix.com>
---
drivers/xen/swi...
2013 Aug 22
2
[PATCH] tracing/events: Add bounce tracing to swiotbl-xen
...y(), but
calls spinlock functions, memcpy() and xen_phys_to_bus() as well. This patch
introduces the swiotlb-xen:bounced event, which also prints out the following
informations to help you find out why bouncing happened:
dev_name: 0000:08:00.0 dma_mask=ffffffffffffffff dev_addr=9149f000 size=32768
swiotlb_force=0
If (dev_addr + size + 1) > dma_mask, the buffer is out of the device's DMA
range. If swiotlb_force == 1, you should really change the kernel parameters.
Otherwise, the buffer is not contiguous in mfn space.
Signed-off-by: Zoltan Kiss <zoltan.kiss at citrix.com>
---
drivers/xen/swi...
2019 May 08
2
[PATCH 04/10] s390/mm: force swiotlb for protected virtualization
...; +
> +/* protected virtualization */
> +static void pv_init(void)
> +{
> + if (!sev_active())
can't you just use is_prot_virt_guest here?
> + return;
> +
> + /* make sure bounce buffers are shared */
> + swiotlb_init(1);
> + swiotlb_update_mem_attributes();
> + swiotlb_force = SWIOTLB_FORCE;
> +}
> +
> void __init mem_init(void)
> {
> cpumask_set_cpu(0, &init_mm.context.cpu_attach_mask);
> @@ -134,6 +182,8 @@ void __init mem_init(void)
> set_max_mapnr(max_low_pfn);
> high_memory = (void *) __va(max_low_pfn * PAGE_SIZE);
>...
2019 May 08
2
[PATCH 04/10] s390/mm: force swiotlb for protected virtualization
...; +
> +/* protected virtualization */
> +static void pv_init(void)
> +{
> + if (!sev_active())
can't you just use is_prot_virt_guest here?
> + return;
> +
> + /* make sure bounce buffers are shared */
> + swiotlb_init(1);
> + swiotlb_update_mem_attributes();
> + swiotlb_force = SWIOTLB_FORCE;
> +}
> +
> void __init mem_init(void)
> {
> cpumask_set_cpu(0, &init_mm.context.cpu_attach_mask);
> @@ -134,6 +182,8 @@ void __init mem_init(void)
> set_max_mapnr(max_low_pfn);
> high_memory = (void *) __va(max_low_pfn * PAGE_SIZE);
>...
2019 Apr 09
0
[RFC PATCH 03/12] s390/mm: force swiotlb for protected virtualization
...;
> +}
> +EXPORT_SYMBOL_GPL(sev_active);
> +
> +/* protected virtualization */
> +static void pv_init(void)
> +{
> + if (!sev_active())
> + return;
> +
> + /* make sure bounce buffers are shared */
> + swiotlb_init(1);
> + swiotlb_update_mem_attributes();
> + swiotlb_force = SWIOTLB_FORCE;
> +}
> +
> void __init mem_init(void)
> {
> cpumask_set_cpu(0, &init_mm.context.cpu_attach_mask);
> @@ -134,6 +176,8 @@ void __init mem_init(void)
> set_max_mapnr(max_low_pfn);
> high_memory = (void *) __va(max_low_pfn * PAGE_SIZE);
>...
2019 Apr 26
0
[PATCH 04/10] s390/mm: force swiotlb for protected virtualization
...guest? */
+bool sev_active(void)
+{
+ return is_prot_virt_guest();
+}
+EXPORT_SYMBOL_GPL(sev_active);
+
+/* protected virtualization */
+static void pv_init(void)
+{
+ if (!sev_active())
+ return;
+
+ /* make sure bounce buffers are shared */
+ swiotlb_init(1);
+ swiotlb_update_mem_attributes();
+ swiotlb_force = SWIOTLB_FORCE;
+}
+
void __init mem_init(void)
{
cpumask_set_cpu(0, &init_mm.context.cpu_attach_mask);
@@ -134,6 +182,8 @@ void __init mem_init(void)
set_max_mapnr(max_low_pfn);
high_memory = (void *) __va(max_low_pfn * PAGE_SIZE);
+ pv_init();
+
/* Setup guest page hinting...
2019 Jun 06
0
[PATCH v4 1/8] s390/mm: force swiotlb for protected virtualization
...rotected virtualization guest? */
+bool sev_active(void)
+{
+ return is_prot_virt_guest();
+}
+
+/* protected virtualization */
+static void pv_init(void)
+{
+ if (!is_prot_virt_guest())
+ return;
+
+ /* make sure bounce buffers are shared */
+ swiotlb_init(1);
+ swiotlb_update_mem_attributes();
+ swiotlb_force = SWIOTLB_FORCE;
+}
+
void __init mem_init(void)
{
cpumask_set_cpu(0, &init_mm.context.cpu_attach_mask);
@@ -136,6 +181,8 @@ void __init mem_init(void)
set_max_mapnr(max_low_pfn);
high_memory = (void *) __va(max_low_pfn * PAGE_SIZE);
+ pv_init();
+
/* Setup guest page hinting...
2019 Jun 12
0
[PATCH v5 1/8] s390/mm: force swiotlb for protected virtualization
...rotected virtualization guest? */
+bool sev_active(void)
+{
+ return is_prot_virt_guest();
+}
+
+/* protected virtualization */
+static void pv_init(void)
+{
+ if (!is_prot_virt_guest())
+ return;
+
+ /* make sure bounce buffers are shared */
+ swiotlb_init(1);
+ swiotlb_update_mem_attributes();
+ swiotlb_force = SWIOTLB_FORCE;
+}
+
void __init mem_init(void)
{
cpumask_set_cpu(0, &init_mm.context.cpu_attach_mask);
@@ -136,6 +181,8 @@ void __init mem_init(void)
set_max_mapnr(max_low_pfn);
high_memory = (void *) __va(max_low_pfn * PAGE_SIZE);
+ pv_init();
+
/* Setup guest page hinting...
2019 May 23
0
[PATCH v2 1/8] s390/mm: force swiotlb for protected virtualization
...rotected virtualization guest? */
+bool sev_active(void)
+{
+ return is_prot_virt_guest();
+}
+
+/* protected virtualization */
+static void pv_init(void)
+{
+ if (!is_prot_virt_guest())
+ return;
+
+ /* make sure bounce buffers are shared */
+ swiotlb_init(1);
+ swiotlb_update_mem_attributes();
+ swiotlb_force = SWIOTLB_FORCE;
+}
+
void __init mem_init(void)
{
cpumask_set_cpu(0, &init_mm.context.cpu_attach_mask);
@@ -136,6 +181,8 @@ void __init mem_init(void)
set_max_mapnr(max_low_pfn);
high_memory = (void *) __va(max_low_pfn * PAGE_SIZE);
+ pv_init();
+
/* Setup guest page hinting...
2019 May 29
0
[PATCH v3 1/8] s390/mm: force swiotlb for protected virtualization
...rotected virtualization guest? */
+bool sev_active(void)
+{
+ return is_prot_virt_guest();
+}
+
+/* protected virtualization */
+static void pv_init(void)
+{
+ if (!is_prot_virt_guest())
+ return;
+
+ /* make sure bounce buffers are shared */
+ swiotlb_init(1);
+ swiotlb_update_mem_attributes();
+ swiotlb_force = SWIOTLB_FORCE;
+}
+
void __init mem_init(void)
{
cpumask_set_cpu(0, &init_mm.context.cpu_attach_mask);
@@ -136,6 +181,8 @@ void __init mem_init(void)
set_max_mapnr(max_low_pfn);
high_memory = (void *) __va(max_low_pfn * PAGE_SIZE);
+ pv_init();
+
/* Setup guest page hinting...
2019 Apr 09
0
[RFC PATCH 03/12] s390/mm: force swiotlb for protected virtualization
...> > > +static void pv_init(void)
> > > +{
> > > + if (!sev_active())
> > > + return;
> > > +
> > > + /* make sure bounce buffers are shared */
> > > + swiotlb_init(1);
> > > + swiotlb_update_mem_attributes();
> > > + swiotlb_force = SWIOTLB_FORCE;
> > > +}
> > > +
> > > void __init mem_init(void)
> > > {
> > > cpumask_set_cpu(0, &init_mm.context.cpu_attach_mask);
> > > @@ -134,6 +176,8 @@ void __init mem_init(void)
> > > set_max_mapnr(max_low_pfn);
>...
2019 May 09
0
[PATCH 04/10] s390/mm: force swiotlb for protected virtualization
...not
remember to change when the interface for this provided by uv.h went
from sketchy to nice.
Thanks again!
Regards,
Halil
> > + return;
> > +
> > + /* make sure bounce buffers are shared */
> > + swiotlb_init(1);
> > + swiotlb_update_mem_attributes();
> > + swiotlb_force = SWIOTLB_FORCE;
> > +}
> > +
> > void __init mem_init(void)
> > {
> > cpumask_set_cpu(0, &init_mm.context.cpu_attach_mask);
> > @@ -134,6 +182,8 @@ void __init mem_init(void)
> > set_max_mapnr(max_low_pfn);
> > high_memory = (void...
2019 May 09
0
[PATCH 04/10] s390/mm: force swiotlb for protected virtualization
...T_SYMBOL_GPL(sev_active);
> +
> +/* protected virtualization */
> +static void pv_init(void)
> +{
> +??? if (!sev_active())
> +??????? return;
> +
> +??? /* make sure bounce buffers are shared */
> +??? swiotlb_init(1);
> +??? swiotlb_update_mem_attributes();
> +??? swiotlb_force = SWIOTLB_FORCE;
> +}
> +
> ?void __init mem_init(void)
> ?{
> ???? cpumask_set_cpu(0, &init_mm.context.cpu_attach_mask);
> @@ -134,6 +182,8 @@ void __init mem_init(void)
> ???? set_max_mapnr(max_low_pfn);
> ???????? high_memory = (void *) __va(max_low_pfn * PAGE_SI...
2007 Apr 05
3
Swiotlb
While writing a driver for a device doing lots of DMA I''ve hit an
"swiotlb_full()" problem. This surprised me somewhat as I wouldn''t have
expected to need the use of the software TLB - it''s a 64 bit capable
device on a server with only 2 GB of RAM, and so I''d have expected to be
using a hardware TLB. Is this a peculiarity of Xen, or should I be
right
2019 Feb 05
0
[vhost:linux-next 2/23] include/linux/swiotlb.h:99:22: error: static declaration of 'swiotlb_max_mapping_size' follows non-static declaration
...de/linux/swiotlb.h
75
76 bool swiotlb_map(struct device *dev, phys_addr_t *phys, dma_addr_t *dma_addr,
77 size_t size, enum dma_data_direction dir, unsigned long attrs);
78 void __init swiotlb_exit(void);
79 unsigned int swiotlb_max_segment(void);
80 #else
81 #define swiotlb_force SWIOTLB_NO_FORCE
82 static inline bool is_swiotlb_buffer(phys_addr_t paddr)
83 {
84 return false;
85 }
86 static inline bool swiotlb_map(struct device *dev, phys_addr_t *phys,
87 dma_addr_t *dma_addr, size_t size, enum dma_data_direction dir,
88 unsigned long attrs)...