[v4,1/2] eal: make base address hint OS-specific
Checks
Commit Message
Not all OS's follow Linux's memory layout, which may lead to
problems following the suggested common address hint absent
of a base-virtaddr flag. Make this address hint OS-specific.
Cc: stable@dpdk.org
Signed-off-by: Anatoly Burakov <anatoly.burakov@intel.com>
---
lib/librte_eal/common/eal_common_memory.c | 19 +------------------
lib/librte_eal/common/eal_private.h | 6 ++++++
lib/librte_eal/freebsd/eal/eal_memory.c | 10 ++++++++++
lib/librte_eal/linux/eal/eal_memory.c | 20 ++++++++++++++++++++
4 files changed, 37 insertions(+), 18 deletions(-)
Comments
On Wed, Jul 31, 2019 at 2:47 PM Anatoly Burakov
<anatoly.burakov@intel.com> wrote:
>
> Not all OS's follow Linux's memory layout, which may lead to
> problems following the suggested common address hint absent
> of a base-virtaddr flag. Make this address hint OS-specific.
>
> Cc: stable@dpdk.org
Missing Fixes: ?
>
> Signed-off-by: Anatoly Burakov <anatoly.burakov@intel.com>
> ---
> lib/librte_eal/common/eal_common_memory.c | 19 +------------------
> lib/librte_eal/common/eal_private.h | 6 ++++++
> lib/librte_eal/freebsd/eal/eal_memory.c | 10 ++++++++++
> lib/librte_eal/linux/eal/eal_memory.c | 20 ++++++++++++++++++++
> 4 files changed, 37 insertions(+), 18 deletions(-)
>
> diff --git a/lib/librte_eal/common/eal_common_memory.c b/lib/librte_eal/common/eal_common_memory.c
> index 19ea47570..4a9cc1f19 100644
> --- a/lib/librte_eal/common/eal_common_memory.c
> +++ b/lib/librte_eal/common/eal_common_memory.c
> @@ -40,23 +40,6 @@
> static void *next_baseaddr;
> static uint64_t system_page_sz;
>
> -#ifdef RTE_ARCH_64
> -/*
> - * Linux kernel uses a really high address as starting address for serving
> - * mmaps calls. If there exists addressing limitations and IOVA mode is VA,
> - * this starting address is likely too high for those devices. However, it
> - * is possible to use a lower address in the process virtual address space
> - * as with 64 bits there is a lot of available space.
> - *
> - * Current known limitations are 39 or 40 bits. Setting the starting address
> - * at 4GB implies there are 508GB or 1020GB for mapping the available
> - * hugepages. This is likely enough for most systems, although a device with
> - * addressing limitations should call rte_mem_check_dma_mask for ensuring all
> - * memory is within supported range.
> - */
> -static uint64_t baseaddr = 0x100000000;
> -#endif
> -
> #define MAX_MMAP_WITH_DEFINED_ADDR_TRIES 5
> void *
> eal_get_virtual_area(void *requested_addr, size_t *size,
> @@ -85,7 +68,7 @@ eal_get_virtual_area(void *requested_addr, size_t *size,
> #ifdef RTE_ARCH_64
> if (next_baseaddr == NULL && internal_config.base_virtaddr == 0 &&
> rte_eal_process_type() == RTE_PROC_PRIMARY)
> - next_baseaddr = (void *) baseaddr;
> + next_baseaddr = (void *) eal_get_baseaddr();
> #endif
> if (requested_addr == NULL && next_baseaddr != NULL) {
> requested_addr = next_baseaddr;
> diff --git a/lib/librte_eal/common/eal_private.h b/lib/librte_eal/common/eal_private.h
> index 798ede553..31eae2278 100644
> --- a/lib/librte_eal/common/eal_private.h
> +++ b/lib/librte_eal/common/eal_private.h
> @@ -381,4 +381,10 @@ rte_option_init(void);
> void
> rte_option_usage(void);
>
> +/**
> + * Get OS-specific EAL mapping base address.
> + */
> +uint64_t
> +eal_get_baseaddr(void);
> +
> #endif /* _EAL_PRIVATE_H_ */
> diff --git a/lib/librte_eal/freebsd/eal/eal_memory.c b/lib/librte_eal/freebsd/eal/eal_memory.c
> index 9b9a0577a..1bfdb52fb 100644
> --- a/lib/librte_eal/freebsd/eal/eal_memory.c
> +++ b/lib/librte_eal/freebsd/eal/eal_memory.c
> @@ -22,6 +22,16 @@
>
> #define EAL_PAGE_SIZE (sysconf(_SC_PAGESIZE))
>
> +uint64_t eal_get_baseaddr(void)
> +{
> + /*
> + * FreeBSD may allocate something in the space we will be mapping things
> + * before we get a chance to do that, so use a base address that's far
> + * away from where malloc() et al usually map things.
> + */
> + return 0x1000000000;
> +}
> +
> /*
> * Get physical address of any mapped virtual address in the current process.
> */
> diff --git a/lib/librte_eal/linux/eal/eal_memory.c b/lib/librte_eal/linux/eal/eal_memory.c
> index 1c089a1ef..8516f0d35 100644
> --- a/lib/librte_eal/linux/eal/eal_memory.c
> +++ b/lib/librte_eal/linux/eal/eal_memory.c
> @@ -70,6 +70,26 @@ static int phys_addrs_available = -1;
>
> #define RANDOMIZE_VA_SPACE_FILE "/proc/sys/kernel/randomize_va_space"
>
> +uint64_t eal_get_baseaddr(void)
> +{
> + /*
> + * Linux kernel uses a really high address as starting address for
> + * serving mmaps calls. If there exists addressing limitations and IOVA
> + * mode is VA, this starting address is likely too high for those
> + * devices. However, it is possible to use a lower address in the
> + * process virtual address space as with 64 bits there is a lot of
> + * available space.
> + *
> + * Current known limitations are 39 or 40 bits. Setting the starting
> + * address at 4GB implies there are 508GB or 1020GB for mapping the
> + * available hugepages. This is likely enough for most systems, although
> + * a device with addressing limitations should call
> + * rte_mem_check_dma_mask for ensuring all memory is within supported
> + * range.
> + */
> + return 0x100000000;
> +}
> +
> /*
> * Get physical address of any mapped virtual address in the current process.
> */
> --
> 2.17.1
What about windows port?
On Wed, 2 Oct 2019 13:41:30 +0200
David Marchand <david.marchand@redhat.com> wrote:
> > +uint64_t eal_get_baseaddr(void)
> > +{
> > + /*
> > + * Linux kernel uses a really high address as starting address for
> > + * serving mmaps calls. If there exists addressing limitations and IOVA
> > + * mode is VA, this starting address is likely too high for those
> > + * devices. However, it is possible to use a lower address in the
> > + * process virtual address space as with 64 bits there is a lot of
> > + * available space.
> > + *
> > + * Current known limitations are 39 or 40 bits. Setting the starting
> > + * address at 4GB implies there are 508GB or 1020GB for mapping the
> > + * available hugepages. This is likely enough for most systems, although
> > + * a device with addressing limitations should call
> > + * rte_mem_check_dma_mask for ensuring all memory is within supported
> > + * range.
> > + */
> > + return 0x100000000;
Is this going to work right on 32 bit builds where sizeof(uint) == 4
then constants default to 32. Does it need ul or ull suffix (or a cast)?
On 02-Oct-19 12:41 PM, David Marchand wrote:
> On Wed, Jul 31, 2019 at 2:47 PM Anatoly Burakov
> <anatoly.burakov@intel.com> wrote:
>>
>> Not all OS's follow Linux's memory layout, which may lead to
>> problems following the suggested common address hint absent
>> of a base-virtaddr flag. Make this address hint OS-specific.
>>
>> Cc: stable@dpdk.org
>
> Missing Fixes: ?
No, not really. This isn't a bug as such - it was intended behavior.
It's just /wrong/ intended behavior :)
>
> What about windows port?
>
>
I don't see it supporting secondary processes or mapping shared config
anywhere. So probably unimplemented for now.
On 02-Oct-19 3:42 PM, Stephen Hemminger wrote:
> On Wed, 2 Oct 2019 13:41:30 +0200
> David Marchand <david.marchand@redhat.com> wrote:
>
>>> +uint64_t eal_get_baseaddr(void)
>>> +{
>>> + /*
>>> + * Linux kernel uses a really high address as starting address for
>>> + * serving mmaps calls. If there exists addressing limitations and IOVA
>>> + * mode is VA, this starting address is likely too high for those
>>> + * devices. However, it is possible to use a lower address in the
>>> + * process virtual address space as with 64 bits there is a lot of
>>> + * available space.
>>> + *
>>> + * Current known limitations are 39 or 40 bits. Setting the starting
>>> + * address at 4GB implies there are 508GB or 1020GB for mapping the
>>> + * available hugepages. This is likely enough for most systems, although
>>> + * a device with addressing limitations should call
>>> + * rte_mem_check_dma_mask for ensuring all memory is within supported
>>> + * range.
>>> + */
>>> + return 0x100000000;
>
> Is this going to work right on 32 bit builds where sizeof(uint) == 4
> then constants default to 32. Does it need ul or ull suffix (or a cast)?
>
Adding ULL in v2, thanks.
@@ -40,23 +40,6 @@
static void *next_baseaddr;
static uint64_t system_page_sz;
-#ifdef RTE_ARCH_64
-/*
- * Linux kernel uses a really high address as starting address for serving
- * mmaps calls. If there exists addressing limitations and IOVA mode is VA,
- * this starting address is likely too high for those devices. However, it
- * is possible to use a lower address in the process virtual address space
- * as with 64 bits there is a lot of available space.
- *
- * Current known limitations are 39 or 40 bits. Setting the starting address
- * at 4GB implies there are 508GB or 1020GB for mapping the available
- * hugepages. This is likely enough for most systems, although a device with
- * addressing limitations should call rte_mem_check_dma_mask for ensuring all
- * memory is within supported range.
- */
-static uint64_t baseaddr = 0x100000000;
-#endif
-
#define MAX_MMAP_WITH_DEFINED_ADDR_TRIES 5
void *
eal_get_virtual_area(void *requested_addr, size_t *size,
@@ -85,7 +68,7 @@ eal_get_virtual_area(void *requested_addr, size_t *size,
#ifdef RTE_ARCH_64
if (next_baseaddr == NULL && internal_config.base_virtaddr == 0 &&
rte_eal_process_type() == RTE_PROC_PRIMARY)
- next_baseaddr = (void *) baseaddr;
+ next_baseaddr = (void *) eal_get_baseaddr();
#endif
if (requested_addr == NULL && next_baseaddr != NULL) {
requested_addr = next_baseaddr;
@@ -381,4 +381,10 @@ rte_option_init(void);
void
rte_option_usage(void);
+/**
+ * Get OS-specific EAL mapping base address.
+ */
+uint64_t
+eal_get_baseaddr(void);
+
#endif /* _EAL_PRIVATE_H_ */
@@ -22,6 +22,16 @@
#define EAL_PAGE_SIZE (sysconf(_SC_PAGESIZE))
+uint64_t eal_get_baseaddr(void)
+{
+ /*
+ * FreeBSD may allocate something in the space we will be mapping things
+ * before we get a chance to do that, so use a base address that's far
+ * away from where malloc() et al usually map things.
+ */
+ return 0x1000000000;
+}
+
/*
* Get physical address of any mapped virtual address in the current process.
*/
@@ -70,6 +70,26 @@ static int phys_addrs_available = -1;
#define RANDOMIZE_VA_SPACE_FILE "/proc/sys/kernel/randomize_va_space"
+uint64_t eal_get_baseaddr(void)
+{
+ /*
+ * Linux kernel uses a really high address as starting address for
+ * serving mmaps calls. If there exists addressing limitations and IOVA
+ * mode is VA, this starting address is likely too high for those
+ * devices. However, it is possible to use a lower address in the
+ * process virtual address space as with 64 bits there is a lot of
+ * available space.
+ *
+ * Current known limitations are 39 or 40 bits. Setting the starting
+ * address at 4GB implies there are 508GB or 1020GB for mapping the
+ * available hugepages. This is likely enough for most systems, although
+ * a device with addressing limitations should call
+ * rte_mem_check_dma_mask for ensuring all memory is within supported
+ * range.
+ */
+ return 0x100000000;
+}
+
/*
* Get physical address of any mapped virtual address in the current process.
*/