* [dpdk-stable] [PATCH] memory: make eal_get_virtual_area() aware of base-virtaddr alignment
@ 2018-06-15 12:24 Dariusz Stojaczyk
2018-06-15 14:22 ` Burakov, Anatoly
2018-06-15 15:13 ` [dpdk-stable] [PATCH v2] " Dariusz Stojaczyk
0 siblings, 2 replies; 4+ messages in thread
From: Dariusz Stojaczyk @ 2018-06-15 12:24 UTC (permalink / raw)
To: dev, Anatoly Burakov; +Cc: Dariusz Stojaczyk, stable
From: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
Whenever a calculated base-virtaddr offset had to be
manually aligned to requested page_sz, we did not take
account of that alignment in incrementing the base-virtaddr
offset further. The next requested virtual area could print
a warning "hint [...] not respected!" and let the system
pick an address instead. As a result, this breaks secondary
process support on many system configurations.
Fixes: b7cc54187ea4 ("mem: move virtual area function in common directory")
Cc: anatoly.burakov@intel.com
Cc: stable@dpdk.org
Signed-off-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
---
lib/librte_eal/common/eal_common_memory.c | 14 ++++++++------
1 file changed, 8 insertions(+), 6 deletions(-)
diff --git a/lib/librte_eal/common/eal_common_memory.c b/lib/librte_eal/common/eal_common_memory.c
index 4f0688f9d..7c8a316c2 100644
--- a/lib/librte_eal/common/eal_common_memory.c
+++ b/lib/librte_eal/common/eal_common_memory.c
@@ -34,7 +34,7 @@
#define MEMSEG_LIST_FMT "memseg-%" PRIu64 "k-%i-%i"
-static uint64_t baseaddr_offset;
+static void *next_baseaddr;
static uint64_t system_page_sz;
void *
@@ -56,9 +56,11 @@ eal_get_virtual_area(void *requested_addr, size_t *size,
allow_shrink = (flags & EAL_VIRTUAL_AREA_ALLOW_SHRINK) > 0;
unmap = (flags & EAL_VIRTUAL_AREA_UNMAP) > 0;
- if (requested_addr == NULL && internal_config.base_virtaddr != 0) {
- requested_addr = (void *) (internal_config.base_virtaddr +
- (size_t)baseaddr_offset);
+ if (next_baseaddr == NULL && internal_config.base_virtaddr != 0)
+ next_baseaddr = (void *) internal_config.base_virtaddr;
+
+ if (requested_addr == NULL && next_baseaddr) {
+ requested_addr = next_baseaddr;
requested_addr = RTE_PTR_ALIGN(requested_addr, page_sz);
addr_is_hint = true;
}
@@ -116,6 +118,8 @@ eal_get_virtual_area(void *requested_addr, size_t *size,
RTE_LOG(WARNING, EAL, "WARNING! Base virtual address hint (%p != %p) not respected!\n",
requested_addr, aligned_addr);
RTE_LOG(WARNING, EAL, " This may cause issues with mapping memory into secondary processes\n");
+ } else {
+ next_baseaddr = RTE_PTR_ADD(aligned_addr, *size);
}
RTE_LOG(DEBUG, EAL, "Virtual area found at %p (size = 0x%zx)\n",
@@ -148,8 +152,6 @@ eal_get_virtual_area(void *requested_addr, size_t *size,
munmap(aligned_end, after_len);
}
- baseaddr_offset += *size;
-
return aligned_addr;
}
--
2.11.0
^ permalink raw reply [flat|nested] 4+ messages in thread
* Re: [dpdk-stable] [PATCH] memory: make eal_get_virtual_area() aware of base-virtaddr alignment
2018-06-15 12:24 [dpdk-stable] [PATCH] memory: make eal_get_virtual_area() aware of base-virtaddr alignment Dariusz Stojaczyk
@ 2018-06-15 14:22 ` Burakov, Anatoly
2018-06-15 15:13 ` [dpdk-stable] [PATCH v2] " Dariusz Stojaczyk
1 sibling, 0 replies; 4+ messages in thread
From: Burakov, Anatoly @ 2018-06-15 14:22 UTC (permalink / raw)
To: Dariusz Stojaczyk, dev; +Cc: Dariusz Stojaczyk, stable
On 15-Jun-18 1:24 PM, Dariusz Stojaczyk wrote:
> From: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
>
> Whenever a calculated base-virtaddr offset had to be
> manually aligned to requested page_sz, we did not take
> account of that alignment in incrementing the base-virtaddr
> offset further. The next requested virtual area could print
> a warning "hint [...] not respected!" and let the system
> pick an address instead. As a result, this breaks secondary
> process support on many system configurations.
>
> Fixes: b7cc54187ea4 ("mem: move virtual area function in common directory")
> Cc: anatoly.burakov@intel.com
> Cc: stable@dpdk.org
>
> Signed-off-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
> ---
Acked-by: Anatoly Burakov <anatoly.burakov@intel.com>
--
Thanks,
Anatoly
^ permalink raw reply [flat|nested] 4+ messages in thread
* [dpdk-stable] [PATCH v2] memory: make eal_get_virtual_area() aware of base-virtaddr alignment
2018-06-15 12:24 [dpdk-stable] [PATCH] memory: make eal_get_virtual_area() aware of base-virtaddr alignment Dariusz Stojaczyk
2018-06-15 14:22 ` Burakov, Anatoly
@ 2018-06-15 15:13 ` Dariusz Stojaczyk
2018-07-12 22:01 ` [dpdk-stable] [dpdk-dev] " Thomas Monjalon
1 sibling, 1 reply; 4+ messages in thread
From: Dariusz Stojaczyk @ 2018-06-15 15:13 UTC (permalink / raw)
To: dev, Anatoly Burakov; +Cc: Dariusz Stojaczyk, stable
From: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
Whenever a calculated base-virtaddr offset had to be
manually aligned to requested page_sz, we did not take
account of that alignment in incrementing the base-virtaddr
offset further. The next requested virtual area could print
a warning "hint [...] not respected!" and let the system
pick an address instead. As a result, this breaks secondary
process support on many system configurations.
Fixes: b7cc54187ea4 ("mem: move virtual area function in common directory")
Cc: anatoly.burakov@intel.com
Cc: stable@dpdk.org
Signed-off-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
Acked-by: Anatoly Burakov <anatoly.burakov@intel.com>
---
Changes from v1:
* do not increment next_baseaddr if its currently NULL.
Otherwise this patch breaks applications without base-virtaddr specified
* switched to explicit `!= NULL` comparisons
lib/librte_eal/common/eal_common_memory.c | 14 ++++++++------
1 file changed, 8 insertions(+), 6 deletions(-)
diff --git a/lib/librte_eal/common/eal_common_memory.c b/lib/librte_eal/common/eal_common_memory.c
index 4f0688f9d..2413ce1e7 100644
--- a/lib/librte_eal/common/eal_common_memory.c
+++ b/lib/librte_eal/common/eal_common_memory.c
@@ -34,7 +34,7 @@
#define MEMSEG_LIST_FMT "memseg-%" PRIu64 "k-%i-%i"
-static uint64_t baseaddr_offset;
+static void *next_baseaddr;
static uint64_t system_page_sz;
void *
@@ -56,9 +56,11 @@ eal_get_virtual_area(void *requested_addr, size_t *size,
allow_shrink = (flags & EAL_VIRTUAL_AREA_ALLOW_SHRINK) > 0;
unmap = (flags & EAL_VIRTUAL_AREA_UNMAP) > 0;
- if (requested_addr == NULL && internal_config.base_virtaddr != 0) {
- requested_addr = (void *) (internal_config.base_virtaddr +
- (size_t)baseaddr_offset);
+ if (next_baseaddr == NULL && internal_config.base_virtaddr != 0)
+ next_baseaddr = (void *) internal_config.base_virtaddr;
+
+ if (requested_addr == NULL && next_baseaddr != NULL) {
+ requested_addr = next_baseaddr;
requested_addr = RTE_PTR_ALIGN(requested_addr, page_sz);
addr_is_hint = true;
}
@@ -116,6 +118,8 @@ eal_get_virtual_area(void *requested_addr, size_t *size,
RTE_LOG(WARNING, EAL, "WARNING! Base virtual address hint (%p != %p) not respected!\n",
requested_addr, aligned_addr);
RTE_LOG(WARNING, EAL, " This may cause issues with mapping memory into secondary processes\n");
+ } else if (next_baseaddr != NULL) {
+ next_baseaddr = RTE_PTR_ADD(aligned_addr, *size);
}
RTE_LOG(DEBUG, EAL, "Virtual area found at %p (size = 0x%zx)\n",
@@ -148,8 +152,6 @@ eal_get_virtual_area(void *requested_addr, size_t *size,
munmap(aligned_end, after_len);
}
- baseaddr_offset += *size;
-
return aligned_addr;
}
--
2.11.0
^ permalink raw reply [flat|nested] 4+ messages in thread
* Re: [dpdk-stable] [dpdk-dev] [PATCH v2] memory: make eal_get_virtual_area() aware of base-virtaddr alignment
2018-06-15 15:13 ` [dpdk-stable] [PATCH v2] " Dariusz Stojaczyk
@ 2018-07-12 22:01 ` Thomas Monjalon
0 siblings, 0 replies; 4+ messages in thread
From: Thomas Monjalon @ 2018-07-12 22:01 UTC (permalink / raw)
To: Dariusz Stojaczyk; +Cc: dev, Dariusz Stojaczyk, Anatoly Burakov, stable
15/06/2018 17:13, Dariusz Stojaczyk:
> From: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
>
> Whenever a calculated base-virtaddr offset had to be
> manually aligned to requested page_sz, we did not take
> account of that alignment in incrementing the base-virtaddr
> offset further. The next requested virtual area could print
> a warning "hint [...] not respected!" and let the system
> pick an address instead. As a result, this breaks secondary
> process support on many system configurations.
>
> Fixes: b7cc54187ea4 ("mem: move virtual area function in common directory")
> Cc: anatoly.burakov@intel.com
> Cc: stable@dpdk.org
>
> Signed-off-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
> Acked-by: Anatoly Burakov <anatoly.burakov@intel.com>
Applied, thanks
^ permalink raw reply [flat|nested] 4+ messages in thread
end of thread, other threads:[~2018-07-12 22:01 UTC | newest]
Thread overview: 4+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2018-06-15 12:24 [dpdk-stable] [PATCH] memory: make eal_get_virtual_area() aware of base-virtaddr alignment Dariusz Stojaczyk
2018-06-15 14:22 ` Burakov, Anatoly
2018-06-15 15:13 ` [dpdk-stable] [PATCH v2] " Dariusz Stojaczyk
2018-07-12 22:01 ` [dpdk-stable] [dpdk-dev] " Thomas Monjalon
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).