Re: [PATCH v3 08/11] eal: expand most macros to empty when using msvc

On Wed, Apr 05, 2023 at 07:25:45PM -0700, Stephen Hemminger wrote: > On Wed, 5 Apr 2023 17:45:16 -0700 > Tyler Retzlaff wrote: > > > For now expand a lot of common rte macros empty. The catch here is we > > need to test that most of the macros do what they should but at the same > > time they ar

Re: [PATCH v3 08/11] eal: expand most macros to empty when using msvc

On Wed, 5 Apr 2023 17:45:16 -0700 Tyler Retzlaff wrote: > For now expand a lot of common rte macros empty. The catch here is we > need to test that most of the macros do what they should but at the same > time they are blocking work needed to bootstrap of the unit tests. > > Later we will retur

[PATCH v3 05/11] eal: use umonitor umwait and tpause intrinsics

Inline assembly is not supported for msvc x64 instead use _umonitor, _umwait and _tpause intrinsics. Signed-off-by: Tyler Retzlaff --- lib/eal/x86/rte_power_intrinsics.c | 12 1 file changed, 12 insertions(+) diff --git a/lib/eal/x86/rte_power_intrinsics.c b/lib/eal/x86/rte_power_

[PATCH v3 09/11] eal: exclude exposure of rte atomic APIs for MSVC builds

It's discouraged to use rte_atomics APIs instead standard APIs should be used from C11. Since MSVC is a new toolchain/platform combination block visibility of the rte_atomic APIs from day 1. Signed-off-by: Tyler Retzlaff --- lib/eal/include/generic/rte_atomic.h | 7 +++ lib/eal/x86/include/r

[PATCH v3 08/11] eal: expand most macros to empty when using msvc

For now expand a lot of common rte macros empty. The catch here is we need to test that most of the macros do what they should but at the same time they are blocking work needed to bootstrap of the unit tests. Later we will return and provide (where possible) expansions that work correctly for msv

[PATCH v3 07/11] eal: hide GCC extension based alignment markers

When compiling with msvc don't expose typedefs used as alignment markers. Signed-off-by: Tyler Retzlaff --- lib/eal/include/rte_common.h | 4 1 file changed, 4 insertions(+) diff --git a/lib/eal/include/rte_common.h b/lib/eal/include/rte_common.h index 15765b4..2f464e3 100644 --- a/lib/eal

[PATCH v3 10/11] telemetry: disable json print formatting with msvc

VLAs are unsafe and will never be implemented in MSVC. When compiling with MSVC just return immediately indicating 0 output characters formatted. For now telemetry doesn't work on Windows, we will revisit support for the telemetry library sometime after we establish the DPDK unit tests. Signed-of

[PATCH v3 11/11] telemetry: avoid expanding versioned symbol macros on msvc

Windows does not support versioned symbols. Fortunately Windows also doesn't have an exported stable ABI. Export rte_tel_data_add_array_int -> rte_tel_data_add_array_int_24 and rte_tel_data_add_dict_int -> rte_tel_data_add_dict_int_v24 functions. Windows does have a way to achieve similar version

[PATCH v3 06/11] eal: typedef cpu flag enum as int for msvc

Forward declaration of a typedef is a non-standard extension and is not supported by msvc. Use an int instead. Abstract the use of the int/enum rte_cpu_flag_t in function parameter lists by re-typdefing the enum rte_cpu_flag_t to the rte_cpu_flag_t identifier. Remove the use of __extension__ on f

[PATCH v3 02/11] eal: use rtm and xtest intrinsics when compiling with msvc

Inline assembly is not supported for msvc x64 instead use _xbegin, _xend, _xabort and _xtest intrinsics. Signed-off-by: Tyler Retzlaff --- lib/eal/x86/include/rte_rtm.h | 19 +++ 1 file changed, 19 insertions(+) diff --git a/lib/eal/x86/include/rte_rtm.h b/lib/eal/x86/include/rt

[PATCH v3 01/11] eal: use rdtsc intrinsic when compiling with msvc

Inline assembly is not supported for msvc x64 instead use __rdtsc intrinsic. Signed-off-by: Tyler Retzlaff --- lib/eal/x86/include/rte_cycles.h | 8 1 file changed, 8 insertions(+) diff --git a/lib/eal/x86/include/rte_cycles.h b/lib/eal/x86/include/rte_cycles.h index a461a4d..0c142ce 1

[PATCH v3 04/11] eal: use cpuid and cpuidex intrinsics

Inline assembly is not supported for msvc x64 instead use __cpuid and __cpuidex intrinsics. Signed-off-by: Tyler Retzlaff --- lib/eal/x86/rte_cpuflags.c | 4 lib/eal/x86/rte_cpuid.h | 7 +++ lib/eal/x86/rte_cycles.c | 36 lib/eal/x86/rte

[PATCH v3 00/11] msvc integration changes

In accordance with draft plan http://mails.dpdk.org/archives/web/2023-February/002023.html introduces conditionally compiled code to enable building with MSVC that _does not_ require C99/C11 meaning it can be integrated now. This series covers minimal changes for item #2 in draft plan for EAL depe

[PATCH v3 03/11] eal: use barrier intrinsics when compiling with msvc

Inline assembly is not supported for msvc x64 instead expand rte_compiler_barrier as _ReadWriteBarrier and for rte_smp_mb _m_mfence intrinsics. Signed-off-by: Tyler Retzlaff --- lib/eal/include/generic/rte_atomic.h | 4 lib/eal/x86/include/rte_atomic.h | 5 - 2 files changed, 8 inse

Re: [PATCH 3/9] eal: use barrier intrinsics when compiling with msvc

On Wed, Apr 05, 2023 at 10:57:02AM +, Konstantin Ananyev wrote: > > > > >>>Inline assembly is not supported for msvc x64 instead use > > > >>>_{Read,Write,ReadWrite}Barrier() intrinsics. > > > >>> > > > >>>Signed-off-by: Tyler Retzlaff > > > >>>--- > > > >>> lib/eal/include/generic/rte_atomi

[PATCH v3] devtools: add script to check for non inclusive naming

Script to find words that should not be used. Really just a wrapper around git grep command. By default it prints matches. Uses the word lists from Inclusive Naming Initiative see https://inclusivenaming.org/word-lists/ Examples: $ ./devtools/check-naming-policy.sh -c app/test-compress-perf/comp_

Re: [PATCH] MAINTAINERS: sort file entries

On Wed, Apr 05, 2023 at 04:12:51PM -0700, Stephen Hemminger wrote: > The list of file paths (F:) is only partially sorted > in some cases. > > Signed-off-by: Stephen Hemminger > --- Acked-by: Tyler Retzlaff

[PATCH] MAINTAINERS: sort file entries

The list of file paths (F:) is only partially sorted in some cases. Signed-off-by: Stephen Hemminger --- MAINTAINERS | 10 +- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/MAINTAINERS b/MAINTAINERS index 8df23e50999f..5fa432b00aac 100644 --- a/MAINTAINERS +++ b/MAINTAINER

[PATCH v5] improve code portability

Improve portability of telemetry code to allow it to be compiled by msvc unconditionally. Remove use of designated initialization ranges (gcc extension). Instead use a combination of a trivially initialized array and standard C isalnum. v5: * declare allowed array static * fix alpha-numeric -

[PATCH v5] telemetry: remove non-portable array initialization syntax

Use of ranges in designated initialization are a non-standard gcc extension. Only initialize '_' and '/' elements of the array and filter tests of characters through name with standard C isalnum before checking the array. Suggested-by: Konstantin Ananyev Suggested-by: Bruce Richardson Signed-of

Re: [PATCH v2 1/2] eal: provide leading and trailing zero bit count abstraction

On Wed, Apr 05, 2023 at 04:51:42PM +0100, Bruce Richardson wrote: > On Wed, Apr 05, 2023 at 08:22:16AM -0700, Tyler Retzlaff wrote: > > On Wed, Apr 05, 2023 at 09:44:54AM +0100, Bruce Richardson wrote: > > > On Tue, Apr 04, 2023 at 02:23:22PM -0700, Tyler Retzlaff wrote: > > > > On Thu, Jan 05, 202

Re: [PATCH v2 9/9] telemetry: avoid expanding versioned symbol macros on msvc

On Wed, Apr 05, 2023 at 09:02:10AM -0700, Tyler Retzlaff wrote: > On Wed, Apr 05, 2023 at 11:56:05AM +0100, Bruce Richardson wrote: > > On Tue, Apr 04, 2023 at 01:07:27PM -0700, Tyler Retzlaff wrote: > > > Windows does not support versioned symbols. Fortunately Windows also > > > doesn't have an ex

[PATCH v3 5/5] telemetry: remove VLA in json string format function

Since variable length arrays (VLAs) are potentially insecure and unsupported by some compilers, rework the code to remove their use. As with previous changes to remove VLAs in the telemetry code, this function uses two methods to avoid modifying the buffer when adding to it fails: * if there are on

[PATCH v3 4/5] telemetry: rename local variables

In the newly separated out function, rename "tmp" to "buf" to have more meaningful variable names. Signed-off-by: Bruce Richardson --- When committing, this patch can be merged with the previous. I've kept them separate for now, as it makes reviewing a lot easier. --- lib/telemetry/telemetry_j

[PATCH v3 2/5] telemetry: remove variable length array in printf fn

The json_snprintf function, used to add json characters on to a buffer, leaving the buffer unmodified in case of error, used a variable length array to store the data temporarily while checking for overflow. VLAs can be unsafe, and are unsupported by some compilers, so remove use of the VLA. For t

[PATCH v3 3/5] telemetry: split out body of json string format fn

To enable further rework to (efficiently) avoid using variable-length arrays, we first separate out the body of the __json_format_str function. This means that the actual VLA buffer is in the wrapper function, and means we can reuse the actual writing code in multiple code paths without duplication

[PATCH v3 1/5] telemetry: fix autotest failures on Alpine

On Alpine linux, the telemetry_data_autotest was failing for the test where we had dictionaries embedded in other dictionaries up to three levels deep. Indications are that this issue is due to excess data being stored on the stack, so replace stack-allocated buffer data with dynamically allocated

[PATCH v3 0/5] telemetry: remove variable length arrays

This patchset introduces a series of changes to remove variable-length arrays from the telemetry code. The first patch replaces a VLA with malloc memory for the serialization of the json objects contained within the main response object, which fixes a crash observed on alpine linux. Subsequent pat

Re: [PATCH v2 9/9] telemetry: avoid expanding versioned symbol macros on msvc

On Wed, Apr 05, 2023 at 11:56:05AM +0100, Bruce Richardson wrote: > On Tue, Apr 04, 2023 at 01:07:27PM -0700, Tyler Retzlaff wrote: > > Windows does not support versioned symbols. Fortunately Windows also > > doesn't have an exported stable ABI. > > > > Export rte_tel_data_add_array_int -> rte_tel

Re: [PATCH v2 6/9] eal: expand most macros to empty when using msvc

On Wed, Apr 05, 2023 at 11:44:43AM +0100, Bruce Richardson wrote: > On Tue, Apr 04, 2023 at 01:07:24PM -0700, Tyler Retzlaff wrote: > > For now expand a lot of common rte macros empty. The catch here is we > > need to test that most of the macros do what they should but at the same > > time they ar

Re: [PATCH v2 1/2] eal: provide leading and trailing zero bit count abstraction

On Wed, Apr 05, 2023 at 08:22:16AM -0700, Tyler Retzlaff wrote: > On Wed, Apr 05, 2023 at 09:44:54AM +0100, Bruce Richardson wrote: > > On Tue, Apr 04, 2023 at 02:23:22PM -0700, Tyler Retzlaff wrote: > > > On Thu, Jan 05, 2023 at 08:09:19AM +0100, Morten Brørup wrote: > > > > > From: Tyler Retzlaff

RE: [RFC 0/1] ring: add callback infrastructire to ring library

> > Hi Honnappa, > > Responses inline. > I will continue with an initial implementation of this feature and capture > performance data as suggested. > > Rgds, > Rory > > > -Original Message- > > From: Honnappa Nagarahalli > > Sent: Wednesday, April 5, 2023 1:46 AM > > To: Sexton, Ror

Re: [PATCH 1/2] telemetry: use malloc instead of variable length array

On Wed, Apr 05, 2023 at 08:25:21AM -0700, Tyler Retzlaff wrote: > On Wed, Apr 05, 2023 at 09:54:46AM +0100, Bruce Richardson wrote: > > On Tue, Apr 04, 2023 at 06:04:32PM -0700, Stephen Hemminger wrote: > > > On Tue, 4 Apr 2023 09:47:21 +0100 > > > Bruce Richardson wrote: > > > > > > > My suggest

[PATCH v2 5/5] telemetry: remove VLA in json string format function

Since variable length arrays (VLAs) are potentially unsecure and unsupported by some compilers, rework the code to remove their use. As with previous changes to remove VLAs in the telemetry code, this function uses two methods to avoid modifying the buffer when adding to it fails: * if there are on

[PATCH v2 4/5] telemetry: rename local variables

In the newly separated out function, rename "tmp" to "buf" to have more meaningful variable names. Signed-off-by: Bruce Richardson --- When committing, this patch can be merged with the previous. I've kept them separate for now, as it makes reviewing a lot easier. --- lib/telemetry/telemetry_j

[PATCH v2 3/5] telemetry: split out body of json string format fn

To enable further rework to (efficiently) avoid using variable-length arrays, we first separate out the body of the __json_format_str function. This means that the actual VLA buffer is in the wrapper function, and means we can reuse the actual writing code in multiple code paths without duplication

[PATCH v2 2/5] telemetry: remove variable length array in printf fn

The json_snprintf function, used to add json characters on to a buffer, leaving the buffer unmodified in case of error, used a variable length array to store the data temporarily while checking for overflow. VLAs can be unsafe, and are unsupported by some compilers, so remove use of the VLA. For t

[PATCH v2 1/5] telemetry: fix autotest failures on Alpine

On Alpine linux, the telemetry_data_autotest was failing for the test where we had dictionaries embedded in other dictionaries up to three levels deep. Indications are that this issue is due to excess data being stored on the stack, so replace stack-allocated buffer data with dynamically allocated

[PATCH v2 0/5] telemetry: remove variable length arrays

This patchset introduces a series of changes to remove variable-length arrays from the telemetry code. The first patch replaces a VLA with malloc memory for the serialization of the json objects contained within the main response object, which fixes a crash observed on alpine linux. Subsequent pat

Re: [PATCH v2 3/9] eal: use barrier intrinsics when compiling with msvc

On Wed, Apr 05, 2023 at 10:45:26AM +, Konstantin Ananyev wrote: > > > > Inline assembly is not supported for msvc x64 instead use > > _mm_{s,l,m}fence() intrinsics. > > > > Signed-off-by: Tyler Retzlaff > > --- > > lib/eal/include/generic/rte_atomic.h | 4 > > lib/eal/x86/include/rte

Re: [PATCH 3/9] eal: use barrier intrinsics when compiling with msvc

On Wed, Apr 05, 2023 at 02:35:47PM +0200, Morten Brørup wrote: > > From: Konstantin Ananyev [mailto:konstantin.anan...@huawei.com] > > Sent: Wednesday, 5 April 2023 12.57 > > > > > > >>Another ore generic comment - do we really need to pollute all that > > > > >>code > > with RTE_TOOLCHAIN_MSVC i

Re: [PATCH 1/2] telemetry: use malloc instead of variable length array

On Wed, 5 Apr 2023 18:30:51 +0300 Dmitry Kozlyuk wrote: > 2023-04-05 08:25 (UTC-0700), Tyler Retzlaff: > > On Wed, Apr 05, 2023 at 09:54:46AM +0100, Bruce Richardson wrote: > > > On Tue, Apr 04, 2023 at 06:04:32PM -0700, Stephen Hemminger wrote: > > > > On Tue, 4 Apr 2023 09:47:21 +0100 > >

Re: [PATCH 1/2] telemetry: use malloc instead of variable length array

2023-04-05 08:25 (UTC-0700), Tyler Retzlaff: > On Wed, Apr 05, 2023 at 09:54:46AM +0100, Bruce Richardson wrote: > > On Tue, Apr 04, 2023 at 06:04:32PM -0700, Stephen Hemminger wrote: > > > On Tue, 4 Apr 2023 09:47:21 +0100 > > > Bruce Richardson wrote: > > > > > > > My suggestion is to use a

Re: [PATCH v4] telemetry: remove non-portable array initialization syntax

On Wed, Apr 05, 2023 at 09:56:24AM +0100, Bruce Richardson wrote: > On Tue, Apr 04, 2023 at 11:09:16AM -0700, Tyler Retzlaff wrote: > > Use of ranges in designated initialization are a non-standard gcc > > extension. > > > > Only initialize '_' and '/' elements of the array and filter tests > > of

Re: [PATCH 1/2] telemetry: use malloc instead of variable length array

On Wed, Apr 05, 2023 at 09:54:46AM +0100, Bruce Richardson wrote: > On Tue, Apr 04, 2023 at 06:04:32PM -0700, Stephen Hemminger wrote: > > On Tue, 4 Apr 2023 09:47:21 +0100 > > Bruce Richardson wrote: > > > > > My suggestion is to use a combination of these methods. In json_snprintf > > > check i

Re: [PATCH v2 1/2] eal: provide leading and trailing zero bit count abstraction

On Wed, Apr 05, 2023 at 09:44:54AM +0100, Bruce Richardson wrote: > On Tue, Apr 04, 2023 at 02:23:22PM -0700, Tyler Retzlaff wrote: > > On Thu, Jan 05, 2023 at 08:09:19AM +0100, Morten Brørup wrote: > > > > From: Tyler Retzlaff [mailto:roret...@linux.microsoft.com] > > > > Sent: Thursday, 24 Novemb

RE: [PATCH v2] vfio: do not coalesce DMA mappings

[AMD Official Use Only - General] > -Original Message- > From: Burakov, Anatoly > Sent: Wednesday, April 5, 2023 7:46 PM > To: Gupta, Nipun ; David Marchand > > Cc: dev@dpdk.org; tho...@monjalon.net; Yigit, Ferruh > ; Agarwal, Nikhil > Subject: Re: [PATCH v2] vfio: do not coalesce DMA

RE: [RFC 0/1] ring: add callback infrastructire to ring library

Hi Honnappa, Responses inline. I will continue with an initial implementation of this feature and capture performance data as suggested. Rgds, Rory > -Original Message- > From: Honnappa Nagarahalli > Sent: Wednesday, April 5, 2023 1:46 AM > To: Sexton, Rory ; konstantin.v.anan...@yan

[Bug 1211] ice: 'eth / ipv4 / udp dst is XXX / mark' rte_flow not marking any packet

https://bugs.dpdk.org/show_bug.cgi?id=1211 Bug ID: 1211 Summary: ice: 'eth / ipv4 / udp dst is XXX / mark' rte_flow not marking any packet Product: DPDK Version: 23.03 Hardware: All OS: All Statu

[PATCH v2 10/10] net/octeon_ep: set secondary process dev ops

This patch sets the dev ops and transmit/receive callbacks for secondary process. Signed-off-by: Sathesh Edara --- drivers/net/octeon_ep/otx_ep_ethdev.c | 22 +++--- 1 file changed, 19 insertions(+), 3 deletions(-) diff --git a/drivers/net/octeon_ep/otx_ep_ethdev.c b/drivers/ne

[PATCH v2 09/10] net/octeon_ep: set watermark for output queues

This patch sets the watermark level for SDP output queues to send backpressure to NIX, when available Rx buffers fall below watermark. Signed-off-by: Sathesh Edara --- drivers/net/octeon_ep/cnxk_ep_vf.c| 7 ++- drivers/net/octeon_ep/otx_ep_common.h | 1 + 2 files changed, 7 insertions(+)

[PATCH v2 08/10] net/octeon_ep: support Mailbox between VF and PF

This patch adds the mailbox communication between VF and PF and supports the following mailbox messages. - Get and set MAC address - Get link information - Get stats - Get and set link status - Set and get MTU - Send notification to PF Signed-off-by: Sathesh Edara --- drivers/net/octeon_ep/cnxk

[PATCH v2 07/10] net/octeon_ep: update queue size checks

This patch updates the output queue size checks to ensure that queue is larger than backpressure watermark.Add setting of default queue sizes to the minimum so that applications like testpmd can be started without explicit queue size arguments. Signed-off-by: Sathesh Edara --- drivers/net/octeon

[PATCH v2 06/10] net/octeon_ep: fix DMA incompletion

This patch fixes the DMA incompletion during packet reads. Signed-off-by: Sathesh Edara --- drivers/net/octeon_ep/otx_ep_common.h | 8 drivers/net/octeon_ep/otx_ep_rxtx.c | 4 2 files changed, 12 insertions(+) diff --git a/drivers/net/octeon_ep/otx_ep_common.h b/drivers/net/oct

[PATCH v2 05/10] net/octeon_ep: support ISM

This patch adds ISM specific functionality. Signed-off-by: Sathesh Edara --- drivers/net/octeon_ep/cnxk_ep_vf.c| 35 +++-- drivers/net/octeon_ep/cnxk_ep_vf.h| 12 ++ drivers/net/octeon_ep/otx2_ep_vf.c| 45 ++--- drivers/net/octeon_ep/otx2_ep_vf.h|

[PATCH v2 04/10] net/octeon_ep: support IQ/OQ reset

This patch adds input and output queue reset functionality, also receive queue interrupt enable and disable functionality. Signed-off-by: Sathesh Edara --- drivers/net/octeon_ep/otx2_ep_vf.c| 193 +- drivers/net/octeon_ep/otx2_ep_vf.h| 61 ++-- drivers/net/oc

[PATCH v2 03/10] net/octeon_ep: support error propagation

This patch adds detection of loop limits being hit, and propagate errors up the call chain when this happens. Signed-off-by: Sathesh Edara --- drivers/net/octeon_ep/cnxk_ep_vf.c| 51 +++ drivers/net/octeon_ep/otx2_ep_vf.c| 49 ++ drivers/net/octeon_ep/otx

[PATCH v2 02/10] net/octeon_ep: support CNX10K series SoC

This patch adds the required functionality in the Octeon endpoint driver to support the following CNX10K series endpoint devices. - CN10KA - CN10KB - CNF10KA - CNF10KB Signed-off-by: Sathesh Edara --- drivers/net/octeon_ep/cnxk_ep_vf.h| 5 - drivers/net/octeon_ep/otx_ep_ethdev.c | 21 ++

[PATCH v2 01/10] net/octeon_ep: support cnf95n and cnf95o SoC

This patch adds the required functionality in the Octeon endpoint driver to support the cnf95n and cnf95o endpoint device. Signed-off-by: Sathesh Edara --- drivers/net/octeon_ep/otx2_ep_vf.h| 2 ++ drivers/net/octeon_ep/otx_ep_ethdev.c | 13 +++-- 2 files changed, 13 insertions(+),

[PATCH v2 00/10] extend octeon ep driver functionality

This patch set adds the following support to octeon_ep driver - extends support for newer SoCs - support new features like IQ/OQ reset, ISM, mailbox between VF and PF and sets the watermark level for output queues. V2 changes: - Fixes compilation errors and warnings Sathesh Edara (10): net/octe

[Bug 1210] ice: 'eth / ipv4 / udp dst is 4500 / mark' rte_flow not marking any packet

https://bugs.dpdk.org/show_bug.cgi?id=1210 Bug ID: 1210 Summary: ice: 'eth / ipv4 / udp dst is 4500 / mark' rte_flow not marking any packet Product: DPDK Version: 22.11 Hardware: All OS: All St

Re: [PATCH v2] vfio: do not coalesce DMA mappings

On 4/4/2023 5:32 PM, Nipun Gupta wrote: On 4/4/2023 8:43 PM, Burakov, Anatoly wrote: Caution: This message originated from an External Source. Use proper caution when opening attachments, clicking links, or responding. On 2/7/2023 8:56 AM, Gupta, Nipun wrote: [AMD Official Use Only - Gener

[PATCH v2 3/3] vhost: add device op to offload the interrupt kick

This patch adds an operation callback which gets called every time the library wants to call eventfd_write(). This eventfd_write() call could result in a system call, which could potentially block the PMD thread. The callback function can decide whether it's ok to handle the eventfd_write() now or

[PATCH v2 2/3] vhost: make the guest_notifications statistic counter atomic.

Making the guest_notifications statistic counter atomic, allows it to be safely incremented while holding the read access_lock. Signed-off-by: Eelco Chaudron --- lib/vhost/vhost.c |8 lib/vhost/vhost.h |9 ++--- 2 files changed, 14 insertions(+), 3 deletions(-) diff --git a

[PATCH v2 1/3] vhost: Change vhost_virtqueue access lock to a read/write one.

This change will allow the vhost interrupt datapath handling to be split between two processed without one of them holding an explicit lock. Signed-off-by: Eelco Chaudron --- lib/eal/include/generic/rte_rwlock.h | 17 ++ lib/vhost/vhost.c| 46 + lib/vh

[PATCH v2 0/3] vhost: add device op to offload the interrupt kick

This series adds an operation callback which gets called every time the library wants to call eventfd_write(). This eventfd_write() call could result in a system call, which could potentially block the PMD thread. The callback function can decide whether it's ok to handle the eventfd_write() now o

RE: [PATCH 3/9] eal: use barrier intrinsics when compiling with msvc

> From: Konstantin Ananyev [mailto:konstantin.anan...@huawei.com] > Sent: Wednesday, 5 April 2023 12.57 > > > > >>Another ore generic comment - do we really need to pollute all that code > with RTE_TOOLCHAIN_MSVC ifdefs? > > > >>Right now we have ability to have subdir per arch (x86/arm/etc.). > >

RE: [PATCH 3/9] eal: use barrier intrinsics when compiling with msvc

> > >>>Inline assembly is not supported for msvc x64 instead use > > >>>_{Read,Write,ReadWrite}Barrier() intrinsics. > > >>> > > >>>Signed-off-by: Tyler Retzlaff > > >>>--- > > >>> lib/eal/include/generic/rte_atomic.h | 4 > > >>> lib/eal/x86/include/rte_atomic.h | 10 +- > > >>

Re: [PATCH v2 9/9] telemetry: avoid expanding versioned symbol macros on msvc

On Tue, Apr 04, 2023 at 01:07:27PM -0700, Tyler Retzlaff wrote: > Windows does not support versioned symbols. Fortunately Windows also > doesn't have an exported stable ABI. > > Export rte_tel_data_add_array_int -> rte_tel_data_add_array_int_24 > and rte_tel_data_add_dict_int -> rte_tel_data_add_d

RE: [PATCH v2 3/9] eal: use barrier intrinsics when compiling with msvc

> Inline assembly is not supported for msvc x64 instead use > _mm_{s,l,m}fence() intrinsics. > > Signed-off-by: Tyler Retzlaff > --- > lib/eal/include/generic/rte_atomic.h | 4 > lib/eal/x86/include/rte_atomic.h | 10 +- > 2 files changed, 13 insertions(+), 1 deletion(-) >

Re: [PATCH v2 6/9] eal: expand most macros to empty when using msvc

On Tue, Apr 04, 2023 at 01:07:24PM -0700, Tyler Retzlaff wrote: > For now expand a lot of common rte macros empty. The catch here is we > need to test that most of the macros do what they should but at the same > time they are blocking work needed to bootstrap of the unit tests. > > Later we will

Re: [PATCH v2 3/9] eal: use barrier intrinsics when compiling with msvc

On Tue, Apr 04, 2023 at 01:07:21PM -0700, Tyler Retzlaff wrote: > Inline assembly is not supported for msvc x64 instead use > _mm_{s,l,m}fence() intrinsics. > > Signed-off-by: Tyler Retzlaff > --- > lib/eal/include/generic/rte_atomic.h | 4 > lib/eal/x86/include/rte_atomic.h | 10 +

[PATCH v2] eventdev/eth_rx: fix invalid memory access

From: Pavan Nikhilesh Rx adapter internal service structures are only initialized when non-internal port is added to the adapter. Check if Rx adapter service is initialized to determine if runtime set/get parameters are supported. Fixes: 3716f52186af ("eventdev/eth_rx: support runtime set/get pa

[PATCH] eventdev/eth_rx: fix invalid memory access

From: Pavan Nikhilesh Rx adapter internal service structures are only initialized when non-internal port is added to the adapter. Check if Rx adapter service is initialized to determine if runtime set/get parameters are supported. Fixes: 3716f52186af ("eventdev/eth_rx: support runtime set/get pa

Re: [PATCH v2 1/9] eal: use rdtsc intrinsic when compiling with msvc

On Tue, Apr 04, 2023 at 01:07:19PM -0700, Tyler Retzlaff wrote: > Inline assembly is not supported for msvc x64 instead use __rdtsc > intrinsic. > > Signed-off-by: Tyler Retzlaff > --- > lib/eal/x86/include/rte_cycles.h | 8 > 1 file changed, 8 insertions(+) > > diff --git a/lib/eal/x8

Re: [PATCH v4] telemetry: remove non-portable array initialization syntax

On Tue, Apr 04, 2023 at 11:09:16AM -0700, Tyler Retzlaff wrote: > Use of ranges in designated initialization are a non-standard gcc > extension. > > Only initialize '_' and '/' elements of the array and filter tests > of characters through name with standard C isalnum before checking > the array.

Re: [PATCH 1/2] telemetry: use malloc instead of variable length array

On Tue, Apr 04, 2023 at 06:04:32PM -0700, Stephen Hemminger wrote: > On Tue, 4 Apr 2023 09:47:21 +0100 > Bruce Richardson wrote: > > > My suggestion is to use a combination of these methods. In json_snprintf > > check if the input buffer is empty or has only one character in it, and use > > metho

Re: [PATCH 1/2] telemetry: use malloc instead of variable length array

On Tue, Apr 04, 2023 at 06:20:04PM -0700, Stephen Hemminger wrote: > On Tue, 4 Apr 2023 10:34:01 -0700 > Tyler Retzlaff wrote: > > > > > > I think suggestion #2 above should cover most cases, in which case > > > > > using > > > > > your original suggestion of malloc would be ok too for the rare

Re: [PATCH v2 1/2] eal: provide leading and trailing zero bit count abstraction

On Tue, Apr 04, 2023 at 02:23:22PM -0700, Tyler Retzlaff wrote: > On Thu, Jan 05, 2023 at 08:09:19AM +0100, Morten Brørup wrote: > > > From: Tyler Retzlaff [mailto:roret...@linux.microsoft.com] > > > Sent: Thursday, 24 November 2022 00.43 > > > > > > Provide an abstraction for leading and trailing

[PATCH] test/crypto: add cryptodev reconfig test

Add cryptodev tests to verify that the device supports reconfiguration any number of times via rte_cryptodev_configure API. Signed-off-by: Aakash Sasidharan --- app/test/test_cryptodev.c | 81 +++ 1 file changed, 81 insertions(+) diff --git a/app/test/test_cr