Re: [PATCH v4 08/10] lib: add support for device coherent type in test_hmm
I haven't tested the change which checks that pages migrated back to sysmem,
but it looks ok so:
Reviewed-by: Alistair Popple
On Thursday, 27 January 2022 2:09:47 PM AEDT Alex Sierra wrote:
> Device Coherent type uses device memory that is coherently accesible by
> the CPU. This could be shown as SP (special purpose) memory range
> at the BIOS-e820 memory enumeration. If no SP memory is supported in
> system, this could be faked by setting CONFIG_EFI_FAKE_MEMMAP.
>
> Currently, test_hmm only supports two different SP ranges of at least
> 256MB size. This could be specified in the kernel parameter variable
> efi_fake_mem. Ex. Two SP ranges of 1GB starting at 0x1 &
> 0x14000 physical address. Ex.
> efi_fake_mem=1G@0x1:0x4,1G@0x14000:0x4
>
> Private and coherent device mirror instances can be created in the same
> probed. This is done by passing the module parameters spm_addr_dev0 &
> spm_addr_dev1. In this case, it will create four instances of
> device_mirror. The first two correspond to private device type, the
> last two to coherent type. Then, they can be easily accessed from user
> space through /dev/hmm_mirror. Usually num_device 0 and 1
> are for private, and 2 and 3 for coherent types. If no module
> parameters are passed, two instances of private type device_mirror will
> be created only.
>
> Signed-off-by: Alex Sierra
> ---
> v4:
> Return number of coherent device pages successfully migrated to system.
> This is returned at cmd->cpages.
> ---
> lib/test_hmm.c | 260 +---
> lib/test_hmm_uapi.h | 15 ++-
> 2 files changed, 205 insertions(+), 70 deletions(-)
>
> diff --git a/lib/test_hmm.c b/lib/test_hmm.c
> index 6f068f7c4ee3..850d5331e370 100644
> --- a/lib/test_hmm.c
> +++ b/lib/test_hmm.c
> @@ -29,11 +29,22 @@
>
> #include "test_hmm_uapi.h"
>
> -#define DMIRROR_NDEVICES 2
> +#define DMIRROR_NDEVICES 4
> #define DMIRROR_RANGE_FAULT_TIMEOUT 1000
> #define DEVMEM_CHUNK_SIZE(256 * 1024 * 1024U)
> #define DEVMEM_CHUNKS_RESERVE16
>
> +/*
> + * For device_private pages, dpage is just a dummy struct page
> + * representing a piece of device memory. dmirror_devmem_alloc_page
> + * allocates a real system memory page as backing storage to fake a
> + * real device. zone_device_data points to that backing page. But
> + * for device_coherent memory, the struct page represents real
> + * physical CPU-accessible memory that we can use directly.
> + */
> +#define BACKING_PAGE(page) (is_device_private_page((page)) ? \
> +(page)->zone_device_data : (page))
> +
> static unsigned long spm_addr_dev0;
> module_param(spm_addr_dev0, long, 0644);
> MODULE_PARM_DESC(spm_addr_dev0,
> @@ -122,6 +133,21 @@ static int dmirror_bounce_init(struct dmirror_bounce
> *bounce,
> return 0;
> }
>
> +static bool dmirror_is_private_zone(struct dmirror_device *mdevice)
> +{
> + return (mdevice->zone_device_type ==
> + HMM_DMIRROR_MEMORY_DEVICE_PRIVATE) ? true : false;
> +}
> +
> +static enum migrate_vma_direction
> + dmirror_select_device(struct dmirror *dmirror)
> +{
> + return (dmirror->mdevice->zone_device_type ==
> + HMM_DMIRROR_MEMORY_DEVICE_PRIVATE) ?
> + MIGRATE_VMA_SELECT_DEVICE_PRIVATE :
> + MIGRATE_VMA_SELECT_DEVICE_COHERENT;
> +}
> +
> static void dmirror_bounce_fini(struct dmirror_bounce *bounce)
> {
> vfree(bounce->ptr);
> @@ -572,16 +598,19 @@ static int dmirror_allocate_chunk(struct dmirror_device
> *mdevice,
> static struct page *dmirror_devmem_alloc_page(struct dmirror_device *mdevice)
> {
> struct page *dpage = NULL;
> - struct page *rpage;
> + struct page *rpage = NULL;
>
> /*
> - * This is a fake device so we alloc real system memory to store
> - * our device memory.
> + * For ZONE_DEVICE private type, this is a fake device so we alloc real
> + * system memory to store our device memory.
> + * For ZONE_DEVICE coherent type we use the actual dpage to store the
> data
> + * and ignore rpage.
>*/
> - rpage = alloc_page(GFP_HIGHUSER);
> - if (!rpage)
> - return NULL;
> -
> + if (dmirror_is_private_zone(mdevice)) {
> + rpage = alloc_page(GFP_HIGHUSER);
> + if (!rpage)
> + return NULL;
> + }
> spin_lock(>lock);
>
> if (mdevice->free_pages) {
> @@ -601,7 +630,8 @@ static struct page *dmirror_devmem_alloc_page(struct
> dmirror_device *mdevice)
> return dpage;
>
> error:
> - __free_page(rpage);
> + if (rpage)
> + __free_page(rpage);
> return NULL;
> }
>
> @@ -627,12 +657,16 @@ static void dmirror_migrate_alloc_and_copy(struct
> migrate_vma *args,
>* unallocated pte_none() or read-only zero page.
>*/
> spage = migrate_pfn_to_page(*src);
> +
[PATCH v4 08/10] lib: add support for device coherent type in test_hmm
Device Coherent type uses device memory that is coherently accesible by
the CPU. This could be shown as SP (special purpose) memory range
at the BIOS-e820 memory enumeration. If no SP memory is supported in
system, this could be faked by setting CONFIG_EFI_FAKE_MEMMAP.
Currently, test_hmm only supports two different SP ranges of at least
256MB size. This could be specified in the kernel parameter variable
efi_fake_mem. Ex. Two SP ranges of 1GB starting at 0x1 &
0x14000 physical address. Ex.
efi_fake_mem=1G@0x1:0x4,1G@0x14000:0x4
Private and coherent device mirror instances can be created in the same
probed. This is done by passing the module parameters spm_addr_dev0 &
spm_addr_dev1. In this case, it will create four instances of
device_mirror. The first two correspond to private device type, the
last two to coherent type. Then, they can be easily accessed from user
space through /dev/hmm_mirror. Usually num_device 0 and 1
are for private, and 2 and 3 for coherent types. If no module
parameters are passed, two instances of private type device_mirror will
be created only.
Signed-off-by: Alex Sierra
---
v4:
Return number of coherent device pages successfully migrated to system.
This is returned at cmd->cpages.
---
lib/test_hmm.c | 260 +---
lib/test_hmm_uapi.h | 15 ++-
2 files changed, 205 insertions(+), 70 deletions(-)
diff --git a/lib/test_hmm.c b/lib/test_hmm.c
index 6f068f7c4ee3..850d5331e370 100644
--- a/lib/test_hmm.c
+++ b/lib/test_hmm.c
@@ -29,11 +29,22 @@
#include "test_hmm_uapi.h"
-#define DMIRROR_NDEVICES 2
+#define DMIRROR_NDEVICES 4
#define DMIRROR_RANGE_FAULT_TIMEOUT1000
#define DEVMEM_CHUNK_SIZE (256 * 1024 * 1024U)
#define DEVMEM_CHUNKS_RESERVE 16
+/*
+ * For device_private pages, dpage is just a dummy struct page
+ * representing a piece of device memory. dmirror_devmem_alloc_page
+ * allocates a real system memory page as backing storage to fake a
+ * real device. zone_device_data points to that backing page. But
+ * for device_coherent memory, the struct page represents real
+ * physical CPU-accessible memory that we can use directly.
+ */
+#define BACKING_PAGE(page) (is_device_private_page((page)) ? \
+ (page)->zone_device_data : (page))
+
static unsigned long spm_addr_dev0;
module_param(spm_addr_dev0, long, 0644);
MODULE_PARM_DESC(spm_addr_dev0,
@@ -122,6 +133,21 @@ static int dmirror_bounce_init(struct dmirror_bounce
*bounce,
return 0;
}
+static bool dmirror_is_private_zone(struct dmirror_device *mdevice)
+{
+ return (mdevice->zone_device_type ==
+ HMM_DMIRROR_MEMORY_DEVICE_PRIVATE) ? true : false;
+}
+
+static enum migrate_vma_direction
+ dmirror_select_device(struct dmirror *dmirror)
+{
+ return (dmirror->mdevice->zone_device_type ==
+ HMM_DMIRROR_MEMORY_DEVICE_PRIVATE) ?
+ MIGRATE_VMA_SELECT_DEVICE_PRIVATE :
+ MIGRATE_VMA_SELECT_DEVICE_COHERENT;
+}
+
static void dmirror_bounce_fini(struct dmirror_bounce *bounce)
{
vfree(bounce->ptr);
@@ -572,16 +598,19 @@ static int dmirror_allocate_chunk(struct dmirror_device
*mdevice,
static struct page *dmirror_devmem_alloc_page(struct dmirror_device *mdevice)
{
struct page *dpage = NULL;
- struct page *rpage;
+ struct page *rpage = NULL;
/*
-* This is a fake device so we alloc real system memory to store
-* our device memory.
+* For ZONE_DEVICE private type, this is a fake device so we alloc real
+* system memory to store our device memory.
+* For ZONE_DEVICE coherent type we use the actual dpage to store the
data
+* and ignore rpage.
*/
- rpage = alloc_page(GFP_HIGHUSER);
- if (!rpage)
- return NULL;
-
+ if (dmirror_is_private_zone(mdevice)) {
+ rpage = alloc_page(GFP_HIGHUSER);
+ if (!rpage)
+ return NULL;
+ }
spin_lock(>lock);
if (mdevice->free_pages) {
@@ -601,7 +630,8 @@ static struct page *dmirror_devmem_alloc_page(struct
dmirror_device *mdevice)
return dpage;
error:
- __free_page(rpage);
+ if (rpage)
+ __free_page(rpage);
return NULL;
}
@@ -627,12 +657,16 @@ static void dmirror_migrate_alloc_and_copy(struct
migrate_vma *args,
* unallocated pte_none() or read-only zero page.
*/
spage = migrate_pfn_to_page(*src);
+ if (WARN(spage && is_zone_device_page(spage),
+"page already in device spage pfn: 0x%lx\n",
+page_to_pfn(spage)))
+ continue;
dpage = dmirror_devmem_alloc_page(mdevice);
if (!dpage)
continue;
- rpage =
