* Re: BUG_ON in skb_segment, after bpf_skb_change_proto was applied
From: Willem de Bruijn @ 2019-09-03 17:24 UTC (permalink / raw)
To: Shmulik Ladkani
Cc: Willem de Bruijn, Daniel Borkmann, Eric Dumazet, netdev,
Alexander Duyck, Alexei Starovoitov, Yonghong Song,
Steffen Klassert, eyal
In-Reply-To: <20190903200312.7e0ec75e@pixies>
On Tue, Sep 3, 2019 at 1:03 PM Shmulik Ladkani <shmulik@metanetworks.com> wrote:
>
> On Tue, 3 Sep 2019 12:23:54 -0400
> Willem de Bruijn <willemdebruijn.kernel@gmail.com> wrote:
>
> > This is a lot more code change. Especially for stable fixes that need
> > to be backported, a smaller patch is preferable.
>
> Indeed. Thanks for the feedback.
>
> > My suggestion only tested the first frag_skb length. If a list can be
> > created where the first frag_skb is head_frag but a later one is not,
> > it will fail short. I kind of doubt that.
> >
> > By default skb_gro_receive builds GSO skbs that can be segmented
> > along the original gso_size boundaries. We have so far only observed
> > this issue when messing with gso_size.
>
> The rationale was based on inputs specified in 43170c4e0ba7, where a GRO
> skb has a fraglist with different amounts of payloads.
>
> > We can easily refine the test to fall back on to copying only if
> > skb_headlen(list_skb) != mss.
>
> I'm concerned this is too generic; innocent skbs may fall victim to our
> skb copy fallback. Probably those mentioned in 43170c4e0ba7.
>
> > Alternatively, only on SKB_GSO_DODGY is fine, too.
> >
> > I suggest we stick with the two-liner.
>
> OK.
> So lets refine your original codition, testing only the first
> frag_skb, but also ensuring SKB_GSO_DODGY *and* 'skb_headlen(list_skb) != mss'
> (we know existing code DOES work OK for unchanged gso_size, even if frags
> have linear, non head_frag, data).
>
> This hits the known, reproducable case of the mentioned BUG_ON, and is
> tightly scoped to that case.
>
> If that's agreed, I'll submit a proper patch.
Yep, that sounds good to me.
^ permalink raw reply
* Re: [PATCH net-next v3 2/3] dt-bindings: net: dsa: mt7530: Add support for port 5
From: Rob Herring @ 2019-09-03 17:28 UTC (permalink / raw)
To: René van Dorst
Cc: Sean Wang, Andrew Lunn, Vivien Didelot, Florian Fainelli,
David S . Miller, Matthias Brugger, netdev, linux-arm-kernel,
linux-mediatek, Russell King, John Crispin, linux-mips,
Frank Wunderlich, René van Dorst, devicetree
In-Reply-To: <20190902130226.26845-3-opensource@vdorst.com>
On Mon, 2 Sep 2019 15:02:25 +0200, =?UTF-8?q?Ren=C3=A9=20van=20Dorst?= wrote:
> MT7530 port 5 has many modes/configurations.
> Update the documentation how to use port 5.
>
> Signed-off-by: René van Dorst <opensource@vdorst.com>
> Cc: devicetree@vger.kernel.org
> Cc: Rob Herring <robh@kernel.org>
> ---
> v2->v3:
> * Remove 'status = "okay";' lines, suggested by Rob Herring
> v1->v2:
> * Adding extra note about RGMII2 and gpio use.
> rfc->v1:
> * No change
>
> .../devicetree/bindings/net/dsa/mt7530.txt | 214 ++++++++++++++++++
> 1 file changed, 214 insertions(+)
>
Reviewed-by: Rob Herring <robh@kernel.org>
^ permalink raw reply
* Re: Is bug 200755 in anyone's queue??
From: Willem de Bruijn @ 2019-09-03 17:55 UTC (permalink / raw)
Cc: Eric Dumazet, Steve Zabele, Network Development, shum,
vladimir116, saifi.khan, Daniel Borkmann, on2k16nm,
Stephen Hemminger
In-Reply-To: <CA+FuTSf4iLXh-+ADfBNxqcsw=u_vGm7Wsx7vchgwgwvGFYOA6w@mail.gmail.com>
On Fri, Aug 30, 2019 at 4:30 PM Willem de Bruijn
<willemdebruijn.kernel@gmail.com> wrote:
>
> On Fri, Aug 30, 2019 at 4:54 AM Eric Dumazet <eric.dumazet@gmail.com> wrote:
> >
> >
> >
> > On 8/29/19 9:26 PM, Willem de Bruijn wrote:
> >
> > > SO_REUSEPORT was not intended to be used in this way. Opening
> > > multiple connected sockets with the same local port.
> > >
> > > But since the interface allowed connect after joining a group, and
> > > that is being used, I guess that point is moot. Still, I'm a bit
> > > surprised that it ever worked as described.
> > >
> > > Also note that the default distribution algorithm is not round robin
> > > assignment, but hash based. So multiple consecutive datagrams arriving
> > > at the same socket is not unexpected.
> > >
> > > I suspect that this quick hack might "work". It seemed to on the
> > > supplied .c file:
> > >
> > > score = compute_score(sk, net, saddr, sport,
> > > daddr, hnum, dif, sdif);
> > > if (score > badness) {
> > > - if (sk->sk_reuseport) {
> > > + if (sk->sk_reuseport && !sk->sk_state !=
> > > TCP_ESTABLISHED) {
>
> This won't work for a mix of connected and connectionless sockets, of
> course (even ignoring the typo), as it only skips reuseport on the
> connected sockets.
>
> > >
> > > But a more robust approach, that also works on existing kernels, is to
> > > swap the default distribution algorithm with a custom BPF based one (
> > > SO_ATTACH_REUSEPORT_EBPF).
> > >
> >
> > Yes, I suspect that reuseport could still be used by to load-balance incoming packets
> > targetting the same 4-tuple.
> >
> > So all sockets would have the same score, and we would select the first socket in
> > the list (if not applying reuseport hashing)
>
> Can you elaborate a bit?
>
> One option I see is to record in struct sock_reuseport if any port in
> the group is connected and, if so, don't return immediately on the
> first reuseport_select_sock hit, but continue the search for a higher
> scoring connected socket.
>
> Or do return immediately, but do this refined search in
> reuseport_select_sock itself, as it has a reference to all sockets in the
> group in sock_reuseport->socks[]. Instead of the straightforward hash.
That won't work, as reuseport_select_sock does not have access to
protocol specific data, notably inet_dport.
Unfortunately, what I've come up with so far is not concise and slows
down existing reuseport lookup in a busy port table slot. Note that it
is needed for both ipv4 and ipv6.
Do not break out of the port table slot early, but continue to search
for a higher scored match even after matching a reuseport:
"
@@ -413,28 +413,39 @@ static struct sock *udp4_lib_lookup2(struct net *net,
struct udp_hslot *hslot2,
struct sk_buff *skb)
{
+ struct sock *reuseport_result = NULL;
struct sock *sk, *result;
+ int reuseport_score = 0;
int score, badness;
u32 hash = 0;
result = NULL;
badness = 0;
udp_portaddr_for_each_entry_rcu(sk, &hslot2->head) {
score = compute_score(sk, net, saddr, sport,
daddr, hnum, dif, sdif);
if (score > badness) {
- if (sk->sk_reuseport) {
+ if (sk->sk_reuseport &&
+ sk->sk_state != TCP_ESTABLISHED &&
+ !reuseport_result) {
hash = udp_ehashfn(net, daddr, hnum,
saddr, sport);
- result = reuseport_select_sock(sk, hash, skb,
+ reuseport_result =
reuseport_select_sock(sk, hash, skb,
sizeof(struct udphdr));
- if (result)
- return result;
+ if (reuseport_result)
+ reuseport_score = score;
+ continue;
}
badness = score;
result = sk;
}
}
+
+ if (badness < reuseport_score)
+ result = reuseport_result;
+
return result;
"
To break out after the first reuseport hit when it is safe, i.e., when
it holds no connected sockets, requires adding this state to struct
reuseport_sock at __ip4_datagram_connect. And modify
reuseport_select_sock to read this. At least, I have not found a more
elegant solution.
> Steve, Re: your point on a scalable QUIC server. That is an
> interesting case certainly. Opening a connected socket per flow adds
> both memory and port table pressure. I once looked into an SO_TXONLY
> udp socket option that does not hash connected sockets into the port
> table. In effect receiving on a small set of listening sockets (e.g.,
> one per cpu) and sending over separate tx-only sockets. That still
> introduces unnecessary memory allocation. OTOH it amortizes some
> operations, such as route lookup.
>
> Anyway, that does not fix the immediate issue you reported when using
> SO_REUSEPORT as described.
As for the BPF program: good point on accessing the udp port when
skb->data is already beyond the header.
Programs of type sk_filter can use bpf_skb_load_bytes(_relative).
Which I think will work, but have not tested.
As of kernel 4.19 programs of type BPF_PROG_TYPE_SK_REUSEPORT can be
attached (with CAP_SYS_ADMIN). See
tools/testing/selftests/bpf/progs/test_select_reuseport_kern.c for an
example that parses udp headers with bpf_skb_load_bytes.
^ permalink raw reply
* Re: [PATCH 0/4] ethtool: implement Energy Detect Powerdown support via phy-tunable
From: John W. Linville @ 2019-09-03 17:50 UTC (permalink / raw)
To: Alexandru Ardelean
Cc: netdev, linux-kernel, andrew, f.fainelli, hkallweit1, davem
In-Reply-To: <20190903160626.7518-1-alexandru.ardelean@analog.com>
On Tue, Sep 03, 2019 at 07:06:22PM +0300, Alexandru Ardelean wrote:
> This patch series is actually 2 series in 1.
>
> First 2 patches implement the kernel support for controlling Energy Detect
> Powerdown support via phy-tunable, and the next 2 patches implement the
> ethtool user-space control.
> Hopefully, this combination of 2 series is an acceptable approach; if not,
> I am fine to re-update it based on feedback.
I understand your reasoning, but do keep in mind that userland ethtool
and the kernel are managed in different git trees. Seperate patchsets
would be preferable in general, although in some cases having an
initial userland implementation to show against proposed kernel
changes could be helpful.
It would not be unusual for someone to ask for changes on the kernel
patches. If that happens, just repost the kernel changes until you get
a final merge. Once that happens, then repost the userland patches as
a seperate patchset. But I'll keep an eye here -- if Dave merges the
existing kernel patches as-is, I can take the already posted patchs
(unless problems are found in code review).
John
> The `phy_tunable_id` has been named `ETHTOOL_PHY_EDPD` since it looks like
> this feature is common across other PHYs (like EEE), and defining
> `ETHTOOL_PHY_ENERGY_DETECT_POWER_DOWN` seems too long.
>
> The way EDPD works, is that the RX block is put to a lower power mode,
> except for link-pulse detection circuits. The TX block is also put to low
> power mode, but the PHY wakes-up periodically to send link pulses, to avoid
> lock-ups in case the other side is also in EDPD mode.
>
> Currently, there are 2 PHY drivers that look like they could use this new
> PHY tunable feature: the `adin` && `micrel` PHYs.
>
> This series updates only the `adin` PHY driver to support this new feature,
> as this chip has been tested. A change for `micrel` can be proposed after a
> discussion of the PHY-tunable API is resolved.
>
> --
> 2.20.1
>
>
--
John W. Linville Someday the world will need a hero, and you
linville@tuxdriver.com might be all we have. Be ready.
^ permalink raw reply
* Re: [BACKPORT 4.14.y 4/8] net: sctp: fix warning "NULL check before some freeing functions is not needed"
From: Greg KH @ 2019-09-03 18:33 UTC (permalink / raw)
To: Marcelo Ricardo Leitner
Cc: Baolin Wang, stable, vyasevich, nhorman, davem, hariprasad.kelam,
linux-sctp, netdev, arnd, orsonzhai, vincent.guittot,
linux-kernel
In-Reply-To: <20190903145206.GB3499@localhost.localdomain>
On Tue, Sep 03, 2019 at 11:52:06AM -0300, Marcelo Ricardo Leitner wrote:
> On Tue, Sep 03, 2019 at 02:58:16PM +0800, Baolin Wang wrote:
> > From: Hariprasad Kelam <hariprasad.kelam@gmail.com>
> >
> > This patch removes NULL checks before calling kfree.
> >
> > fixes below issues reported by coccicheck
> > net/sctp/sm_make_chunk.c:2586:3-8: WARNING: NULL check before some
> > freeing functions is not needed.
> > net/sctp/sm_make_chunk.c:2652:3-8: WARNING: NULL check before some
> > freeing functions is not needed.
> > net/sctp/sm_make_chunk.c:2667:3-8: WARNING: NULL check before some
> > freeing functions is not needed.
> > net/sctp/sm_make_chunk.c:2684:3-8: WARNING: NULL check before some
> > freeing functions is not needed.
>
> Hi. This doesn't seem the kind of patch that should be backported to
> such old/stable releases. After all, it's just a cleanup.
I agree, this does not seem necessary _unless_ it is needed for a later
real fix.
thanks,
greg k-h
^ permalink raw reply
* Re: [PATCH bpf-next V9 1/3] bpf: new helper to obtain namespace data from current task
From: Carlos Antonio Neira Bustos @ 2019-09-03 18:45 UTC (permalink / raw)
To: Yonghong Song
Cc: netdev@vger.kernel.org, Eric Biederman, brouer@redhat.com,
bpf@vger.kernel.org
In-Reply-To: <20190828210333.itwtyqa5w5egnrwm@ebpf-metal>
Hi Yonghong,
> > Yes, the samples/bpf test case can be removed.
> > Could you create a selftest with tracpoint net/netif_receive_skb, which
> > also uses the proposed helper? net/netif_receive_skb will happen in
> > interrupt context and it should catch the issue as well if
> > filename_lookup still get called in interrupt context.
>
For this one scenario I just created another selftest with the only difference
that the tracepoint is /net/netif_receive_skb so this fails with -EPERM.
Is that enough?.
I have made this comment on include/uapi/linux/bpf.h, maybe is too terse?
struct bpf_pidns_info {
__u32 dev; /* dev_t from /proc/self/ns/pid inode */
__u32 nsid;
__u32 tgid;
__u32 pid;
};
I'm only missing clearing out those questions to be ready to submit v11 of this patch.
Bests
On Wed, Aug 28, 2019 at 05:03:35PM -0400, Carlos Antonio Neira Bustos wrote:
> Thanks, I'll work on the net/netif_receive_skb selftest using this helper.
> I hope I could complete this work this week.
>
> Bests.
>
> On Wed, Aug 28, 2019 at 08:53:25PM +0000, Yonghong Song wrote:
> >
> >
> > On 8/28/19 1:39 PM, Carlos Antonio Neira Bustos wrote:
> > > Yonghong,
> > >
> > > Thanks for the pointer, I fixed this bug, but I found another one that's triggered
> > > now the test program I included in tools/testing/selftests/bpf/test_pidns.
> > > It's seemed that fname was not correctly setup when passing it to filename_lookup.
> > > This is fixed now and I'm doing some more testing.
> > > I think I'll remove the tests on samples/bpf as they are mostly end on -EPERM as
> > > the fix intended.
> > > Is ok to remove them and just focus to finish the self tests code?.
> >
> > Yes, the samples/bpf test case can be removed.
> > Could you create a selftest with tracpoint net/netif_receive_skb, which
> > also uses the proposed helper? net/netif_receive_skb will happen in
> > interrupt context and it should catch the issue as well if
> > filename_lookup still get called in interrupt context.
> >
> > >
> > > Bests
> > >
> > > On Wed, Aug 14, 2019 at 01:25:06AM -0400, carlos antonio neira bustos wrote:
> > >> Thank you very much!
> > >>
> > >> Bests
> > >>
> > >> El mié., 14 de ago. de 2019 00:50, Yonghong Song <yhs@fb.com> escribió:
> > >>
> > >>>
> > >>>
> > >>> On 8/13/19 5:56 PM, Carlos Antonio Neira Bustos wrote:
> > >>>> On Tue, Aug 13, 2019 at 11:11:14PM +0000, Yonghong Song wrote:
> > >>>>>
> > >>>>>
> > >>>>> On 8/13/19 11:47 AM, Carlos Neira wrote:
> > >>>>>> From: Carlos <cneirabustos@gmail.com>
> > >>>>>>
> > >>>>>> New bpf helper bpf_get_current_pidns_info.
> > >>>>>> This helper obtains the active namespace from current and returns
> > >>>>>> pid, tgid, device and namespace id as seen from that namespace,
> > >>>>>> allowing to instrument a process inside a container.
> > >>>>>>
> > >>>>>> Signed-off-by: Carlos Neira <cneirabustos@gmail.com>
> > >>>>>> ---
> > >>>>>> fs/internal.h | 2 --
> > >>>>>> fs/namei.c | 1 -
> > >>>>>> include/linux/bpf.h | 1 +
> > >>>>>> include/linux/namei.h | 4 +++
> > >>>>>> include/uapi/linux/bpf.h | 31 ++++++++++++++++++++++-
> > >>>>>> kernel/bpf/core.c | 1 +
> > >>>>>> kernel/bpf/helpers.c | 64
> > >>> ++++++++++++++++++++++++++++++++++++++++++++++++
> > >>>>>> kernel/trace/bpf_trace.c | 2 ++
> > >>>>>> 8 files changed, 102 insertions(+), 4 deletions(-)
> > >>>>>>
> > >>> [...]
> > >>>>>>
> > >>>>>> +BPF_CALL_2(bpf_get_current_pidns_info, struct bpf_pidns_info *,
> > >>> pidns_info, u32,
> > >>>>>> + size)
> > >>>>>> +{
> > >>>>>> + const char *pidns_path = "/proc/self/ns/pid";
> > >>>>>> + struct pid_namespace *pidns = NULL;
> > >>>>>> + struct filename *tmp = NULL;
> > >>>>>> + struct inode *inode;
> > >>>>>> + struct path kp;
> > >>>>>> + pid_t tgid = 0;
> > >>>>>> + pid_t pid = 0;
> > >>>>>> + int ret;
> > >>>>>> + int len;
> > >>>>>
> > >>>>
> > >>>> Thank you very much for catching this!.
> > >>>> Could you share how to replicate this bug?.
> > >>>
> > >>> The config is attached. just run trace_ns_info and you
> > >>> can reproduce the issue.
> > >>>
> > >>>>
> > >>>>> I am running your sample program and get the following kernel bug:
> > >>>>>
> > >>>>> ...
> > >>>>> [ 26.414825] BUG: sleeping function called from invalid context at
> > >>>>> /data/users/yhs/work/net-next/fs
> > >>>>> /dcache.c:843
> > >>>>> [ 26.416314] in_atomic(): 1, irqs_disabled(): 0, pid: 1911, name: ping
> > >>>>> [ 26.417189] CPU: 0 PID: 1911 Comm: ping Tainted: G W
> > >>>>> 5.3.0-rc1+ #280
> > >>>>> [ 26.418182] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996),
> > >>>>> BIOS 1.9.3-1.el7.centos 04/01/2
> > >>>>> 014
> > >>>>> [ 26.419393] Call Trace:
> > >>>>> [ 26.419697] <IRQ>
> > >>>>> [ 26.419960] dump_stack+0x46/0x5b
> > >>>>> [ 26.420434] ___might_sleep+0xe4/0x110
> > >>>>> [ 26.420894] dput+0x2a/0x200
> > >>>>> [ 26.421265] walk_component+0x10c/0x280
> > >>>>> [ 26.421773] link_path_walk+0x327/0x560
> > >>>>> [ 26.422280] ? proc_ns_dir_readdir+0x1a0/0x1a0
> > >>>>> [ 26.422848] ? path_init+0x232/0x330
> > >>>>> [ 26.423364] path_lookupat+0x88/0x200
> > >>>>> [ 26.423808] ? selinux_parse_skb.constprop.69+0x124/0x430
> > >>>>> [ 26.424521] filename_lookup+0xaf/0x190
> > >>>>> [ 26.425031] ? simple_attr_release+0x20/0x20
> > >>>>> [ 26.425560] bpf_get_current_pidns_info+0xfa/0x190
> > >>>>> [ 26.426168] bpf_prog_83627154cefed596+0xe66/0x1000
> > >>>>> [ 26.426779] trace_call_bpf+0xb5/0x160
> > >>>>> [ 26.427317] ? __netif_receive_skb_core+0x1/0xbb0
> > >>>>> [ 26.427929] ? __netif_receive_skb_core+0x1/0xbb0
> > >>>>> [ 26.428496] kprobe_perf_func+0x4d/0x280
> > >>>>> [ 26.428986] ? tracing_record_taskinfo_skip+0x1a/0x30
> > >>>>> [ 26.429584] ? tracing_record_taskinfo+0xe/0x80
> > >>>>> [ 26.430152] ? ttwu_do_wakeup.isra.114+0xcf/0xf0
> > >>>>> [ 26.430737] ? __netif_receive_skb_core+0x1/0xbb0
> > >>>>> [ 26.431334] ? __netif_receive_skb_core+0x5/0xbb0
> > >>>>> [ 26.431930] kprobe_ftrace_handler+0x90/0xf0
> > >>>>> [ 26.432495] ftrace_ops_assist_func+0x63/0x100
> > >>>>> [ 26.433060] 0xffffffffc03180bf
> > >>>>> [ 26.433471] ? __netif_receive_skb_core+0x1/0xbb0
> > >>>>> ...
> > >>>>>
> > >>>>> To prevent we are running in arbitrary task (e.g., idle task)
> > >>>>> context which may introduce sleeping issues, the following
> > >>>>> probably appropriate:
> > >>>>>
> > >>>>> if (in_nmi() || in_softirq())
> > >>>>> return -EPERM;
> > >>>>>
> > >>>>> Anyway, if in nmi or softirq, the namespace and pid/tgid
> > >>>>> we get may be just accidentally associated with the bpf running
> > >>>>> context, but it could be in a different context. So such info
> > >>>>> is not reliable any way.
> > >>>>>
> > >>>>>> +
> > >>>>>> + if (unlikely(size != sizeof(struct bpf_pidns_info)))
> > >>>>>> + return -EINVAL;
> > >>>>>> + pidns = task_active_pid_ns(current);
> > >>> [...]
> > >>>
^ permalink raw reply
* [PATCH] net: fixed_phy: Add forward declaration for struct gpio_desc;
From: Moritz Fischer @ 2019-09-03 18:46 UTC (permalink / raw)
To: netdev; +Cc: andrew, f.fainelli, hkallweit1, linux-kernel, davem,
Moritz Fischer
Add forward declaration for struct gpio_desc in order to address
the following:
./include/linux/phy_fixed.h:48:17: error: 'struct gpio_desc' declared inside parameter list [-Werror]
./include/linux/phy_fixed.h:48:17: error: its scope is only this definition or declaration, which is probably not what you want [-Werror]
Fixes commit 71bd106d2567 ("net: fixed-phy: Add
fixed_phy_register_with_gpiod() API")
Signed-off-by: Moritz Fischer <mdf@kernel.org>
---
include/linux/phy_fixed.h | 1 +
1 file changed, 1 insertion(+)
diff --git a/include/linux/phy_fixed.h b/include/linux/phy_fixed.h
index 1e5d86ebdaeb..52bc8e487ef7 100644
--- a/include/linux/phy_fixed.h
+++ b/include/linux/phy_fixed.h
@@ -11,6 +11,7 @@ struct fixed_phy_status {
};
struct device_node;
+struct gpio_desc;
#if IS_ENABLED(CONFIG_FIXED_PHY)
extern int fixed_phy_change_carrier(struct net_device *dev, bool new_carrier);
--
2.23.0.187.g17f5b7556c-goog
^ permalink raw reply related
* Re: [PATCH] net/skbuff: silence warnings under memory pressure
From: Michal Hocko @ 2019-09-03 18:53 UTC (permalink / raw)
To: Qian Cai; +Cc: Eric Dumazet, davem, netdev, linux-mm, linux-kernel
In-Reply-To: <1567525342.5576.60.camel@lca.pw>
On Tue 03-09-19 11:42:22, Qian Cai wrote:
> On Tue, 2019-09-03 at 15:22 +0200, Michal Hocko wrote:
> > On Fri 30-08-19 18:15:22, Eric Dumazet wrote:
> > > If there is a risk of flooding the syslog, we should fix this generically
> > > in mm layer, not adding hundred of __GFP_NOWARN all over the places.
> >
> > We do already ratelimit in warn_alloc. If it isn't sufficient then we
> > can think of a different parameters. Or maybe it is the ratelimiting
> > which doesn't work here. Hard to tell and something to explore.
>
> The time-based ratelimit won't work for skb_build() as when a system under
> memory pressure, and the CPU is fast and IO is so slow, it could take a long
> time to swap and trigger OOM.
I really do not understand what does OOM and swapping have to do with
the ratelimiting here. The sole purpose of the ratelimit is to reduce
the amount of warnings to be printed. Slow IO might have an effect on
when the OOM killer is invoked but atomic allocations are not directly
dependent on IO.
> I suppose what happens is those skb_build() allocations are from softirq, and
> once one of them failed, it calls printk() which generates more interrupts.
> Hence, the infinite loop.
Please elaborate more.
--
Michal Hocko
SUSE Labs
^ permalink raw reply
* BUG: using smp_processor_id() in preemptible [ADDR] code: mime_typevmnet0/NUM
From: syzbot @ 2019-09-03 19:04 UTC (permalink / raw)
To: allison, davem, gregkh, linux-kernel, netdev, syzkaller-bugs,
tglx
Hello,
syzbot found the following crash on:
HEAD commit: eea17309 Merge branch 'i2c/for-current' of git://git.kerne..
git tree: upstream
console output: https://syzkaller.appspot.com/x/log.txt?x=10b0622a600000
kernel config: https://syzkaller.appspot.com/x/.config?x=5cbaa3be0b36022f
dashboard link: https://syzkaller.appspot.com/bug?extid=55acd54b57bb4b3840a4
compiler: gcc (GCC) 9.0.0 20181231 (experimental)
Unfortunately, I don't have any reproducer for this crash yet.
IMPORTANT: if you fix the bug, please add the following tag to the commit:
Reported-by: syzbot+55acd54b57bb4b3840a4@syzkaller.appspotmail.com
Started in network mode
Own node identity ff030000000000000000000000000001, cluster identity 4711
BUG: using smp_processor_id() in preemptible [00000000] code:
mime_typevmnet0/24282
caller is dst_cache_get+0x3d/0xb0 net/core/dst_cache.c:68
CPU: 0 PID: 24282 Comm: mime_typevmnet0 Not tainted 5.3.0-rc6+ #148
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS
Google 01/01/2011
Call Trace:
__dump_stack lib/dump_stack.c:77 [inline]
dump_stack+0x172/0x1f0 lib/dump_stack.c:113
check_preemption_disabled lib/smp_processor_id.c:47 [inline]
debug_smp_processor_id.cold+0x87/0x9d lib/smp_processor_id.c:57
dst_cache_get+0x3d/0xb0 net/core/dst_cache.c:68
tipc_udp_xmit.isra.0+0xc4/0xb80 net/tipc/udp_media.c:164
tipc_udp_send_msg+0x3ea/0x490 net/tipc/udp_media.c:241
tipc_bearer_xmit_skb+0x17e/0x370 net/tipc/bearer.c:503
tipc_enable_bearer+0xacf/0xd30 net/tipc/bearer.c:328
__tipc_nl_bearer_enable+0x2de/0x3a0 net/tipc/bearer.c:899
tipc_nl_bearer_enable+0x23/0x40 net/tipc/bearer.c:907
genl_family_rcv_msg+0x74b/0xf90 net/netlink/genetlink.c:629
genl_rcv_msg+0xca/0x170 net/netlink/genetlink.c:654
netlink_rcv_skb+0x177/0x450 net/netlink/af_netlink.c:2477
genl_rcv+0x29/0x40 net/netlink/genetlink.c:665
netlink_unicast_kernel net/netlink/af_netlink.c:1302 [inline]
netlink_unicast+0x531/0x710 net/netlink/af_netlink.c:1328
netlink_sendmsg+0x8a5/0xd60 net/netlink/af_netlink.c:1917
sock_sendmsg_nosec net/socket.c:637 [inline]
sock_sendmsg+0xd7/0x130 net/socket.c:657
___sys_sendmsg+0x803/0x920 net/socket.c:2311
__sys_sendmsg+0x105/0x1d0 net/socket.c:2356
__do_sys_sendmsg net/socket.c:2365 [inline]
__se_sys_sendmsg net/socket.c:2363 [inline]
__x64_sys_sendmsg+0x78/0xb0 net/socket.c:2363
do_syscall_64+0xfd/0x6a0 arch/x86/entry/common.c:296
entry_SYSCALL_64_after_hwframe+0x49/0xbe
RIP: 0033:0x459879
Code: fd b7 fb ff c3 66 2e 0f 1f 84 00 00 00 00 00 66 90 48 89 f8 48 89 f7
48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff
ff 0f 83 cb b7 fb ff c3 66 2e 0f 1f 84 00 00 00 00
RSP: 002b:00007fe5fe7f1c78 EFLAGS: 00000246 ORIG_RAX: 000000000000002e
RAX: ffffffffffffffda RBX: 0000000000000003 RCX: 0000000000459879
RDX: 0000000000000000 RSI: 0000000020000000 RDI: 0000000000000003
RBP: 000000000075bf20 R08: 0000000000000000 R09: 0000000000000000
R10: 0000000000000000 R11: 0000000000000246 R12: 00007fe5fe7f26d4
R13: 00000000004c753c R14: 00000000004dcce8 R15: 00000000ffffffff
Enabled bearer <udp:syz0>, priority 8
---
This bug is generated by a bot. It may contain errors.
See https://goo.gl/tpsmEJ for more information about syzbot.
syzbot engineers can be reached at syzkaller@googlegroups.com.
syzbot will keep track of this bug report. See:
https://goo.gl/tpsmEJ#status for how to communicate with syzbot.
^ permalink raw reply
* [PATCH v2 net-next 1/2] i40e: fix hw_dbg usage in i40e_hmc_get_object_va
From: Mauro S. M. Rodrigues @ 2019-09-03 19:20 UTC (permalink / raw)
To: Jeff Kirsher
Cc: intel-wired-lan, netdev, davem, Andrew Bowers, Jakub Kicinski,
maurosr
The mentioned function references a i40e_hw attribute, as parameter for
hw_dbg, but it doesn't exist in the function scope.
Fixes it by changing parameters from i40e_hmc_info to i40e_hw which can
retrieve the necessary i40e_hmc_info.
v2:
- Fixed reverse xmas tree code style issue as suggested by Jakub Kicinski
Signed-off-by: Mauro S. M. Rodrigues <maurosr@linux.vnet.ibm.com>
---
drivers/net/ethernet/intel/i40e/i40e_lan_hmc.c | 16 +++++++++-------
1 file changed, 9 insertions(+), 7 deletions(-)
diff --git a/drivers/net/ethernet/intel/i40e/i40e_lan_hmc.c b/drivers/net/ethernet/intel/i40e/i40e_lan_hmc.c
index 994011c38fb4..fd987f7ae6e5 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_lan_hmc.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_lan_hmc.c
@@ -1,6 +1,7 @@
// SPDX-License-Identifier: GPL-2.0
/* Copyright(c) 2013 - 2018 Intel Corporation. */
+#include "i40e.h"
#include "i40e_osdep.h"
#include "i40e_register.h"
#include "i40e_type.h"
@@ -963,7 +964,7 @@ static i40e_status i40e_set_hmc_context(u8 *context_bytes,
/**
* i40e_hmc_get_object_va - retrieves an object's virtual address
- * @hmc_info: pointer to i40e_hmc_info struct
+ * @hw: the hardware struct, from which we obtain the i40e_hmc_info pointer
* @object_base: pointer to u64 to get the va
* @rsrc_type: the hmc resource type
* @obj_idx: hmc object index
@@ -972,16 +973,17 @@ static i40e_status i40e_set_hmc_context(u8 *context_bytes,
* base pointer. This function is used for LAN Queue contexts.
**/
static
-i40e_status i40e_hmc_get_object_va(struct i40e_hmc_info *hmc_info,
+i40e_status i40e_hmc_get_object_va(struct i40e_hw *hw,
u8 **object_base,
enum i40e_hmc_lan_rsrc_type rsrc_type,
u32 obj_idx)
{
+ struct i40e_hmc_info *hmc_info = &hw->hmc;
u32 obj_offset_in_sd, obj_offset_in_pd;
- i40e_status ret_code = 0;
struct i40e_hmc_sd_entry *sd_entry;
struct i40e_hmc_pd_entry *pd_entry;
u32 pd_idx, pd_lmt, rel_pd_idx;
+ i40e_status ret_code = 0;
u64 obj_offset_in_fpm;
u32 sd_idx, sd_lmt;
@@ -1047,7 +1049,7 @@ i40e_status i40e_clear_lan_tx_queue_context(struct i40e_hw *hw,
i40e_status err;
u8 *context_bytes;
- err = i40e_hmc_get_object_va(&hw->hmc, &context_bytes,
+ err = i40e_hmc_get_object_va(hw, &context_bytes,
I40E_HMC_LAN_TX, queue);
if (err < 0)
return err;
@@ -1068,7 +1070,7 @@ i40e_status i40e_set_lan_tx_queue_context(struct i40e_hw *hw,
i40e_status err;
u8 *context_bytes;
- err = i40e_hmc_get_object_va(&hw->hmc, &context_bytes,
+ err = i40e_hmc_get_object_va(hw, &context_bytes,
I40E_HMC_LAN_TX, queue);
if (err < 0)
return err;
@@ -1088,7 +1090,7 @@ i40e_status i40e_clear_lan_rx_queue_context(struct i40e_hw *hw,
i40e_status err;
u8 *context_bytes;
- err = i40e_hmc_get_object_va(&hw->hmc, &context_bytes,
+ err = i40e_hmc_get_object_va(hw, &context_bytes,
I40E_HMC_LAN_RX, queue);
if (err < 0)
return err;
@@ -1109,7 +1111,7 @@ i40e_status i40e_set_lan_rx_queue_context(struct i40e_hw *hw,
i40e_status err;
u8 *context_bytes;
- err = i40e_hmc_get_object_va(&hw->hmc, &context_bytes,
+ err = i40e_hmc_get_object_va(hw, &context_bytes,
I40E_HMC_LAN_RX, queue);
if (err < 0)
return err;
--
2.21.0
^ permalink raw reply related
* [PATCH v2 net-next 2/2] i40e: Implement debug macro hw_dbg using dev_dbg
From: Mauro S. M. Rodrigues @ 2019-09-03 19:20 UTC (permalink / raw)
To: Jeff Kirsher
Cc: intel-wired-lan, netdev, davem, Andrew Bowers, Jakub Kicinski,
maurosr
In-Reply-To: <20190903192021.25789-1-maurosr@linux.vnet.ibm.com>
There are several uses of hw_dbg in the code, producing no output. This
patch implments it using dev_debug.
Initially the intention was to implement it using netdev_dbg, analogously
to what is done in ixgbe for instance. That approach was avoided due to
some early usages of hw_dbg, like i40e_pf_reset, before the vsi structure
initialization causing NULL pointer dereference during the driver probe if
the dbg messages were turned on as soon as the module is probed.
v2:
- Use dev_dbg instead of pr_debug, and take advantage of dev_name
instead of crafting pretty much the same device name locally as suggested
by Jakub Kicinski.
Signed-off-by: Mauro S. M. Rodrigues <maurosr@linux.vnet.ibm.com>
---
drivers/net/ethernet/intel/i40e/i40e_common.c | 1 +
drivers/net/ethernet/intel/i40e/i40e_hmc.c | 1 +
drivers/net/ethernet/intel/i40e/i40e_osdep.h | 5 ++++-
3 files changed, 6 insertions(+), 1 deletion(-)
diff --git a/drivers/net/ethernet/intel/i40e/i40e_common.c b/drivers/net/ethernet/intel/i40e/i40e_common.c
index 906cf68d3453..a51678166ff9 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_common.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_common.c
@@ -1,6 +1,7 @@
// SPDX-License-Identifier: GPL-2.0
/* Copyright(c) 2013 - 2018 Intel Corporation. */
+#include "i40e.h"
#include "i40e_type.h"
#include "i40e_adminq.h"
#include "i40e_prototype.h"
diff --git a/drivers/net/ethernet/intel/i40e/i40e_hmc.c b/drivers/net/ethernet/intel/i40e/i40e_hmc.c
index 19ce93d7fd0a..163ee8c6311c 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_hmc.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_hmc.c
@@ -1,6 +1,7 @@
// SPDX-License-Identifier: GPL-2.0
/* Copyright(c) 2013 - 2018 Intel Corporation. */
+#include "i40e.h"
#include "i40e_osdep.h"
#include "i40e_register.h"
#include "i40e_status.h"
diff --git a/drivers/net/ethernet/intel/i40e/i40e_osdep.h b/drivers/net/ethernet/intel/i40e/i40e_osdep.h
index a07574bff550..c302ef2524f8 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_osdep.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_osdep.h
@@ -18,7 +18,10 @@
* actual OS primitives
*/
-#define hw_dbg(hw, S, A...) do {} while (0)
+#define hw_dbg(hw, S, A...) \
+do { \
+ dev_dbg(&((struct i40e_pf *)hw->back)->pdev->dev, S, ##A); \
+} while (0)
#define wr32(a, reg, value) writel((value), ((a)->hw_addr + (reg)))
#define rd32(a, reg) readl((a)->hw_addr + (reg))
--
2.21.0
^ permalink raw reply related
* RE: [PATCH net-next] net/ncsi: support unaligned payload size in NC-SI cmd handler
From: Justin.Lee1 @ 2019-09-03 19:21 UTC (permalink / raw)
To: benwei, davem; +Cc: netdev, openbmc, sam, linux-kernel
In-Reply-To: <CH2PR15MB36869BE1AA44813CE293891BA3BE0@CH2PR15MB3686.namprd15.prod.outlook.com>
That is right. It is necessary to adjust the len for padding on both places.
Thanks,
Justin
> > > Update NC-SI command handler (both standard and OEM) to take into
> > > account of payload paddings in allocating skb (in case of payload
> > > size is not 32-bit aligned).
> > >
> > > The checksum field follows payload field, without taking payload
> > > padding into account can cause checksum being truncated, leading to
> > > dropped packets.
> > >
> > > Signed-off-by: Ben Wei <benwei@fb.com>
> >
> > If you have to align and add padding, I do not see where you are
> > clearing out that padding memory to make sure it is initialized.
> >
> > You do comparisons with 'payload' but make adjustments to 'len'.
> >
> > The logic is very confusing.
>
> Yes let me clarify a bit.
>
> In the code 'payload' is the exact NC-SI payload length, which goes into NC-SI packet header and needs to be actual unpadded payload length.
>
> 'len' is used to allocate total NC-SI packet buffer (include padding).
>
> The original calculation of 'len' was done by summing up NCSI header + payload + checksum, without taking into account of possible padding, e.g.
>
> len += sizeof(struct ncsi_cmd_pkt_hdr) + 4; /* 4 is the checksum size */
> if (nca->payload < 26)
> len += 26;
> else
> len += nca->payload;
> /* Allocate skb */
> skb = alloc_skb(len, GFP_ATOMIC);
>
> This works today for all standard NC-SI commands (in spec v1.1) because all standard commands have payload size < 26, and packet size is then set to minimum of 46 (16 hdr + 26 payload + 4 cksum) bytes.
>
> And mem clearing is done in each of the standard cmd handlers, e.g.
> ncsi_cmd_handler_sp, ncsi_cmd_handler_ae.
>
>
>
> The problem occurs if payload >= 26 and is unaligned. This could happen on some OEM commands, and I see this happening when we carry PLDM traffic over NC-SI packet.
> (PLDM header being 3 bytes and payload size can be large)
>
> The skb allocated would be too small, and later when checksum is calculated and written:
>
> pchecksum = (__be32 *)((void *)h + sizeof(struct ncsi_pkt_hdr) +
> ALIGN(nca->payload, 4));
> *pchecksum = htonl(checksum);
>
> Part of the checksum would fall outside of our allocated buffer.
>
> PLDM over NC-SI and OEM NC-SI commands are currently handled in
>
> @@ -213,17 +213,22 @@ static int ncsi_cmd_handler_oem(struct sk_buff *skb,
>
> So here I ensure the skb allocation takes padding into account, and do the initial mem clearing to set the padding bytes
>
> + unsigned short payload = ALIGN(nca->payload, 4);
>
> len = sizeof(struct ncsi_cmd_pkt_hdr) + 4;
> - if (nca->payload < 26)
> + if (payload < 26)
> len += 26;
> else
> - len += nca->payload;
> + len += payload;
>
> cmd = skb_put_zero(skb, len);
> memcpy(&cmd->mfr_id, nca->data, nca->payload);
>
> So in this patch I updated both standard command handler (in case future spec updates adds commands with payload >= 26) and OEM/generic command handler to support unaligned payload size.
>
> Regards,
> -Ben
^ permalink raw reply
* Re: [PATCH v4 1/2] netfilter: Terminate rule eval if protocol=IPv6 and ipv6 module is disabled
From: Pablo Neira Ayuso @ 2019-09-03 19:31 UTC (permalink / raw)
To: Florian Westphal
Cc: Leonardo Bras, netfilter-devel, coreteam, bridge, netdev,
linux-kernel, Jozsef Kadlecsik, Roopa Prabhu, Nikolay Aleksandrov,
David S. Miller
In-Reply-To: <20190903170550.GA13660@breakpoint.cc>
On Tue, Sep 03, 2019 at 07:05:50PM +0200, Florian Westphal wrote:
> Pablo Neira Ayuso <pablo@netfilter.org> wrote:
> > On Tue, Sep 03, 2019 at 01:46:50PM -0300, Leonardo Bras wrote:
> > > On Fri, 2019-08-30 at 22:58 +0200, Florian Westphal wrote:
> > > > Leonardo Bras <leonardo@linux.ibm.com> wrote:
> > > > > If IPv6 is disabled on boot (ipv6.disable=1), but nft_fib_inet ends up
> > > > > dealing with a IPv6 packet, it causes a kernel panic in
> > > > > fib6_node_lookup_1(), crashing in bad_page_fault.
> > > > >
> > > > > The panic is caused by trying to deference a very low address (0x38
> > > > > in ppc64le), due to ipv6.fib6_main_tbl = NULL.
> > > > > BUG: Kernel NULL pointer dereference at 0x00000038
> > > > >
> > > > > The kernel panic was reproduced in a host that disabled IPv6 on boot and
> > > > > have to process guest packets (coming from a bridge) using it's ip6tables.
> > > > >
> > > > > Terminate rule evaluation when packet protocol is IPv6 but the ipv6 module
> > > > > is not loaded.
> > > > >
> > > > > Signed-off-by: Leonardo Bras <leonardo@linux.ibm.com>
> > > >
> > > > Acked-by: Florian Westphal <fw@strlen.de>
> > > >
> > >
> > > Hello Pablo,
> > >
> > > Any trouble with this patch?
> > > I could see the other* one got applied, but not this one.
> > > *(The other did not get acked, so i released it alone as v5)
> > >
> > > Is there any fix I need to do in this one?
> >
> > Hm, I see, so this one:
> >
> > https://patchwork.ozlabs.org/patch/1156100/
> >
> > is not enough?
>
> No, its not.
>
> > I was expecting we could find a way to handle this from br_netfilter
> > alone itself.
>
> We can't because we support ipv6 fib lookups from the netdev family
> as well.
>
> Alternative is to auto-accept ipv6 packets from the nf_tables eval loop,
> but I think its worse.
Could we add a restriction for nf_tables + br_netfilter + !ipv6. I
mean, if this is an IPv6 packet, nf_tables is on and IPv6 module if
off, then drop this packet?
By dropping packet, the user could diagnose that its setup is
incomplete. I mean, if nf_tables fib ipv6 is used, then this setup is
really wrong and the user forgots to load the ipv6 module.
^ permalink raw reply
* Re: [PATCH] net-ipv6: fix excessive RTF_ADDRCONF flag on ::1/128 local route (and others)
From: David Ahern @ 2019-09-03 19:45 UTC (permalink / raw)
To: Maciej Żenczykowski, Lorenzo Colitti; +Cc: David S . Miller, Linux NetDev
In-Reply-To: <CAHo-OoyQzJptNDcLe93o3-G10oRN+93ZZ35jKkLudSanvgn-2Q@mail.gmail.com>
On 9/3/19 6:17 AM, Maciej Żenczykowski wrote:
> Well, if you look at the commit my commit is fixing, ie.
> commit c7a1ce397adacaf5d4bb2eab0a738b5f80dc3e43
> then you'll see this in the commit description:
> "- dst_nocount is handled by the RTF_ADDRCONF flag"
> and the patch diff itself is from
> "f6i->fib6_flags = RTF_UP | RTF_NONEXTHOP;
> f6i->dst_nocount = true;"
> to
> " .fc_flags = RTF_UP | RTF_ADDRCONF | RTF_NONEXTHOP,"
>
> (and RTF_ANYCAST or RTF_LOCAL is later or'ed in in both versions of the code)
>
> so I'm pretty sure that patch adds ADDRCONF unconditionally to that
> function, and my commit unconditionally removes it.
>
exactly. It was shortsighted of me to add the ADDRCONF flag and removing
it reverts back to the previous behavior.
When I enable radvd, I do see the flag set when it should be and not for
other addresses. I believe the patch is correct.
^ permalink raw reply
* Re: [PATCH] net: fixed_phy: Add forward declaration for struct gpio_desc;
From: Florian Fainelli @ 2019-09-03 19:46 UTC (permalink / raw)
To: Moritz Fischer, netdev; +Cc: andrew, hkallweit1, linux-kernel, davem
In-Reply-To: <20190903184652.3148-1-mdf@kernel.org>
On 9/3/19 11:46 AM, Moritz Fischer wrote:
> Add forward declaration for struct gpio_desc in order to address
> the following:
>
> ./include/linux/phy_fixed.h:48:17: error: 'struct gpio_desc' declared inside parameter list [-Werror]
> ./include/linux/phy_fixed.h:48:17: error: its scope is only this definition or declaration, which is probably not what you want [-Werror]
>
> Fixes commit 71bd106d2567 ("net: fixed-phy: Add
> fixed_phy_register_with_gpiod() API")
There is a standardized tag for that which is:
Fixes: 71bd106d2567 ("net: fixed-phy: Add
fixed_phy_register_with_gpiod() API")
Other than that:
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
> Signed-off-by: Moritz Fischer <mdf@kernel.org>
> ---
> include/linux/phy_fixed.h | 1 +
> 1 file changed, 1 insertion(+)
>
> diff --git a/include/linux/phy_fixed.h b/include/linux/phy_fixed.h
> index 1e5d86ebdaeb..52bc8e487ef7 100644
> --- a/include/linux/phy_fixed.h
> +++ b/include/linux/phy_fixed.h
> @@ -11,6 +11,7 @@ struct fixed_phy_status {
> };
>
> struct device_node;
> +struct gpio_desc;
>
> #if IS_ENABLED(CONFIG_FIXED_PHY)
> extern int fixed_phy_change_carrier(struct net_device *dev, bool new_carrier);
>
--
Florian
^ permalink raw reply
* Re: [PATCH v4 1/2] netfilter: Terminate rule eval if protocol=IPv6 and ipv6 module is disabled
From: Florian Westphal @ 2019-09-03 19:48 UTC (permalink / raw)
To: Pablo Neira Ayuso
Cc: Florian Westphal, Leonardo Bras, netfilter-devel, coreteam,
bridge, netdev, linux-kernel, Jozsef Kadlecsik, Roopa Prabhu,
Nikolay Aleksandrov, David S. Miller
In-Reply-To: <20190903193155.v74ws47zcn6zrwpr@salvia>
Pablo Neira Ayuso <pablo@netfilter.org> wrote:
> > > I was expecting we could find a way to handle this from br_netfilter
> > > alone itself.
> >
> > We can't because we support ipv6 fib lookups from the netdev family
> > as well.
> >
> > Alternative is to auto-accept ipv6 packets from the nf_tables eval loop,
> > but I think its worse.
>
> Could we add a restriction for nf_tables + br_netfilter + !ipv6. I
> mean, if this is an IPv6 packet, nf_tables is on and IPv6 module if
> off, then drop this packet?
We could do that from nft_do_chain_netdev().
^ permalink raw reply
* [pull request][net-next V2 00/18] Mellanox, mlx5 software managed steering
From: Saeed Mahameed @ 2019-09-03 20:04 UTC (permalink / raw)
To: David S. Miller
Cc: netdev@vger.kernel.org, Alex Vesker, Erez Shitrit, Saeed Mahameed
Hi Dave,
This series adds the support for software (driver managed) flow steering.
For more information please see tag log below.
Please pull and let me know if there is any problem.
Please note that the series starts with a merge of mlx5-next branch,
to resolve and avoid dependency with rdma tree.
v2:
- Improve return values transformation of the first patch.
Thanks,
Saeed.
---
The following changes since commit a06ebb8d953b4100236f3057be51d67640e06323:
Merge branch 'mlx5-next' of git://git.kernel.org/pub/scm/linux/kernel/git/mellanox/linux (2019-09-02 00:16:05 -0700)
are available in the Git repository at:
git://git.kernel.org/pub/scm/linux/kernel/git/saeed/linux.git tags/mlx5-updates-2019-09-01-v2
for you to fetch changes up to e890acd5ff18a0144967d0289869fe5f0415d399:
net/mlx5: Add devlink flow_steering_mode parameter (2019-09-03 12:54:24 -0700)
----------------------------------------------------------------
mlx5-updates-2019-09-01 (Software steering support)
Abstract:
--------
Mellanox ConnetX devices supports packet matching, packet modification and
redirection. These functionalities are also referred to as flow-steering.
To configure a steering rule, the rule is written to the device owned
memory, this memory is accessed and cached by the device when processing
a packet.
Steering rules are constructed from multiple steering entries (STE).
Rules are configured using the Firmware command interface. The Firmware
processes the given driver command and translates them to STEs, then
writes them to the device memory in the current steering tables.
This process is slow due to the architecture of the command interface and
the processing complexity of each rule.
The highlight of this patchset is to cut the middle man (The firmware) and
do steering rules programming into device directly from the driver, with
no firmware intervention whatsoever.
Motivation:
-----------
Software (driver managed) steering allows for high rule insertion rates
compared to the FW steering described above, this is achieved by using
internal RDMA writes to the device owned memory instead of the slow
command interface to program steering rules.
Software (driver managed) steering, doesn't depend on new FW
for new steering functionality, new implementations can be done in the
driver skipping the FW layer.
Performance:
------------
The insertion rate on a single core using the new approach allows
programming ~300K rules per sec. (Done via direct raw test to the new mlx5
sw steering layer, without any kernel layer involved).
Test: TC L2 rules
33K/s with Software steering (this patchset).
5K/s with FW and current driver.
This will improve OVS based solution performance.
Architecture and implementation details:
----------------------------------------
Software steering will be dynamically selected via devlink device
parameter. Example:
$ devlink dev param show pci/0000:06:00.0 name flow_steering_mode
pci/0000:06:00.0:
name flow_steering_mode type driver-specific
values:
cmode runtime value smfs
mlx5 software steering module a.k.a (DR - Direct Rule) is implemented
and contained in mlx5/core/steering directory and controlled by
MLX5_SW_STEERING kconfig flag.
mlx5 core steering layer (fs_core) already provides a shim layer for
implementing different steering mechanisms, software steering will
leverage that as seen at the end of this series.
When Software Steering for a specific steering domain
(NIC/RDMA/Vport/ESwitch, etc ..) is supported, it will cause rules
targeting this domain to be created using SW steering instead of FW.
The implementation includes:
Domain - The steering domain is the object that all other object resides
in. It holds the memory allocator, send engine, locks and other shared
data needed by lower objects such as table, matcher, rule, action.
Each domain can contain multiple tables. Domain is equivalent to
namespaces e.g (NIC/RDMA/Vport/ESwitch, etc ..) as implemented
currently in mlx5_core fs_core (flow steering core).
Table - Table objects are used for holding multiple matchers, each table
has a level used to prevent processing loops. Packets are being
directed to this table once it is set as the root table, this is done
by fs_core using a FW command. A packet is being processed inside the
table matcher by matcher until a successful hit, otherwise the packet
will perform the default action.
Matcher - Matchers objects are used to specify the fields mask for
matching when processing a packet. A matcher belongs to a table, each
matcher can hold multiple rules, each rule with different matching
values corresponding to the matcher mask. Each matcher has a priority
used for rule processing order inside the table.
Action - Action objects are created to specify different steering actions
such as count, reformat (encapsulate, decapsulate, ...), modify
header, forward to table and many other actions. When creating a rule
a sequence of actions can be provided to be executed on a successful
match.
Rule - Rule objects are used to specify a specific match on packets as
well as the actions that should be executed. A rule belongs to a
matcher.
STE - This layer is used to hold the specific STE format for the device
and to convert the requested rule to STEs. Each rule is constructed of
an STE chain, Multiple rules construct a steering graph. Each node in
the graph is a hash table containing multiple STEs. The index of each
STE in the hash table is being calculated using a CRC32 hash function.
Memory pool - Used for managing and caching device owned memory for rule
insertion. The memory is being allocated using DM (device memory) API.
Communication with device - layer for standard RDMA operation using RC QP
to configure the device steering.
Command utility - This module holds all of the FW commands that are
required for SW steering to function.
Patch planning and files:
-------------------------
1) First patch, adds the support to Add flow steering actions to fs_cmd
shim layer.
2) Next 12 patch will add a file per each Software steering
functionality/module as described above. (See patches with title: DR, *)
3) Add CONFIG_MLX5_SW_STEERING for software steering support and enable
build with the new files
4) Next two patches will add the support for software steering in mlx5
steering shim layer
net/mlx5: Add API to set the namespace steering mode
net/mlx5: Add direct rule fs_cmd implementation
5) Last two patches will add the new devlink parameter to select mlx5
steering mode, will be valid only for switchdev mode for now.
Two modes are supported:
1. DMFS - Device managed flow steering
2. SMFS - Software/Driver managed flow steering.
In the DMFS mode, the HW steering entities are created through the
FW. In the SMFS mode this entities are created though the driver
directly.
The driver will use the devlink steering mode only if the steering
domain supports it, for now SMFS will manages only the switchdev
eswitch steering domain.
User command examples:
- Set SMFS flow steering mode::
$ devlink dev param set pci/0000:06:00.0 name flow_steering_mode value "smfs" cmode runtime
- Read device flow steering mode::
$ devlink dev param show pci/0000:06:00.0 name flow_steering_mode
pci/0000:06:00.0:
name flow_steering_mode type driver-specific
values:
cmode runtime value smfs
----------------------------------------------------------------
Alex Vesker (13):
net/mlx5: DR, Add the internal direct rule types definitions
net/mlx5: DR, Add direct rule command utilities
net/mlx5: DR, ICM pool memory allocator
net/mlx5: DR, Expose an internal API to issue RDMA operations
net/mlx5: DR, Add Steering entry (STE) utilities
net/mlx5: DR, Expose steering domain functionality
net/mlx5: DR, Expose steering table functionality
net/mlx5: DR, Expose steering matcher functionality
net/mlx5: DR, Expose steering action functionality
net/mlx5: DR, Expose steering rule functionality
net/mlx5: DR, Add required FW steering functionality
net/mlx5: DR, Expose APIs for direct rule managing
net/mlx5: DR, Add CONFIG_MLX5_SW_STEERING for software steering support
Maor Gottlieb (5):
net/mlx5: Add flow steering actions to fs_cmd shim layer
net/mlx5: Add direct rule fs_cmd implementation
net/mlx5: Add API to set the namespace steering mode
net/mlx5: Add support to use SMFS in switchdev mode
net/mlx5: Add devlink flow_steering_mode parameter
.../networking/device_drivers/mellanox/mlx5.rst | 33 +
drivers/infiniband/hw/mlx5/flow.c | 21 +-
drivers/infiniband/hw/mlx5/main.c | 7 +-
drivers/infiniband/hw/mlx5/mlx5_ib.h | 5 +-
drivers/net/ethernet/mellanox/mlx5/core/Kconfig | 7 +
drivers/net/ethernet/mellanox/mlx5/core/Makefile | 7 +
drivers/net/ethernet/mellanox/mlx5/core/devlink.c | 112 +-
.../net/ethernet/mellanox/mlx5/core/en/tc_tun.c | 27 +-
drivers/net/ethernet/mellanox/mlx5/core/en_rep.h | 2 +-
drivers/net/ethernet/mellanox/mlx5/core/en_tc.c | 46 +-
drivers/net/ethernet/mellanox/mlx5/core/eswitch.h | 7 +-
.../ethernet/mellanox/mlx5/core/eswitch_offloads.c | 87 +-
drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c | 116 +-
drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.h | 25 +
drivers/net/ethernet/mellanox/mlx5/core/fs_core.c | 160 +-
drivers/net/ethernet/mellanox/mlx5/core/fs_core.h | 39 +-
.../ethernet/mellanox/mlx5/core/steering/Makefile | 2 +
.../mellanox/mlx5/core/steering/dr_action.c | 1588 ++++++++++++++
.../ethernet/mellanox/mlx5/core/steering/dr_cmd.c | 480 ++++
.../mellanox/mlx5/core/steering/dr_crc32.c | 98 +
.../mellanox/mlx5/core/steering/dr_domain.c | 395 ++++
.../ethernet/mellanox/mlx5/core/steering/dr_fw.c | 93 +
.../mellanox/mlx5/core/steering/dr_icm_pool.c | 570 +++++
.../mellanox/mlx5/core/steering/dr_matcher.c | 770 +++++++
.../ethernet/mellanox/mlx5/core/steering/dr_rule.c | 1243 +++++++++++
.../ethernet/mellanox/mlx5/core/steering/dr_send.c | 976 +++++++++
.../ethernet/mellanox/mlx5/core/steering/dr_ste.c | 2308 ++++++++++++++++++++
.../mellanox/mlx5/core/steering/dr_table.c | 294 +++
.../mellanox/mlx5/core/steering/dr_types.h | 1060 +++++++++
.../ethernet/mellanox/mlx5/core/steering/fs_dr.c | 600 +++++
.../ethernet/mellanox/mlx5/core/steering/fs_dr.h | 60 +
.../mellanox/mlx5/core/steering/mlx5_ifc_dr.h | 604 +++++
.../ethernet/mellanox/mlx5/core/steering/mlx5dr.h | 212 ++
include/linux/mlx5/fs.h | 33 +-
34 files changed, 11967 insertions(+), 120 deletions(-)
create mode 100644 drivers/net/ethernet/mellanox/mlx5/core/steering/Makefile
create mode 100644 drivers/net/ethernet/mellanox/mlx5/core/steering/dr_action.c
create mode 100644 drivers/net/ethernet/mellanox/mlx5/core/steering/dr_cmd.c
create mode 100644 drivers/net/ethernet/mellanox/mlx5/core/steering/dr_crc32.c
create mode 100644 drivers/net/ethernet/mellanox/mlx5/core/steering/dr_domain.c
create mode 100644 drivers/net/ethernet/mellanox/mlx5/core/steering/dr_fw.c
create mode 100644 drivers/net/ethernet/mellanox/mlx5/core/steering/dr_icm_pool.c
create mode 100644 drivers/net/ethernet/mellanox/mlx5/core/steering/dr_matcher.c
create mode 100644 drivers/net/ethernet/mellanox/mlx5/core/steering/dr_rule.c
create mode 100644 drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c
create mode 100644 drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste.c
create mode 100644 drivers/net/ethernet/mellanox/mlx5/core/steering/dr_table.c
create mode 100644 drivers/net/ethernet/mellanox/mlx5/core/steering/dr_types.h
create mode 100644 drivers/net/ethernet/mellanox/mlx5/core/steering/fs_dr.c
create mode 100644 drivers/net/ethernet/mellanox/mlx5/core/steering/fs_dr.h
create mode 100644 drivers/net/ethernet/mellanox/mlx5/core/steering/mlx5_ifc_dr.h
create mode 100644 drivers/net/ethernet/mellanox/mlx5/core/steering/mlx5dr.h
^ permalink raw reply
* [net-next V2 01/18] net/mlx5: Add flow steering actions to fs_cmd shim layer
From: Saeed Mahameed @ 2019-09-03 20:04 UTC (permalink / raw)
To: David S. Miller
Cc: netdev@vger.kernel.org, Alex Vesker, Erez Shitrit, Maor Gottlieb,
Mark Bloch, Saeed Mahameed
In-Reply-To: <20190903200409.14406-1-saeedm@mellanox.com>
From: Maor Gottlieb <maorg@mellanox.com>
Add flow steering actions: modify header and packet reformat
to the fs_cmd shim layer. This allows each namespace to define
possibly different functionality for alloc/dealloc action commands.
Signed-off-by: Maor Gottlieb <maorg@mellanox.com>
Reviewed-by: Mark Bloch <markb@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
drivers/infiniband/hw/mlx5/flow.c | 21 ++--
drivers/infiniband/hw/mlx5/main.c | 7 +-
drivers/infiniband/hw/mlx5/mlx5_ib.h | 5 +-
.../ethernet/mellanox/mlx5/core/en/tc_tun.c | 27 ++---
.../net/ethernet/mellanox/mlx5/core/en_rep.h | 2 +-
.../net/ethernet/mellanox/mlx5/core/en_tc.c | 46 ++++----
.../net/ethernet/mellanox/mlx5/core/eswitch.h | 6 +-
.../mellanox/mlx5/core/eswitch_offloads.c | 26 +++--
.../net/ethernet/mellanox/mlx5/core/fs_cmd.c | 92 ++++++++++-----
.../net/ethernet/mellanox/mlx5/core/fs_cmd.h | 18 +++
.../net/ethernet/mellanox/mlx5/core/fs_core.c | 105 +++++++++++++++++-
.../net/ethernet/mellanox/mlx5/core/fs_core.h | 11 ++
include/linux/mlx5/fs.h | 33 +++---
13 files changed, 289 insertions(+), 110 deletions(-)
diff --git a/drivers/infiniband/hw/mlx5/flow.c b/drivers/infiniband/hw/mlx5/flow.c
index b8841355fcd5..1c8f04abee0c 100644
--- a/drivers/infiniband/hw/mlx5/flow.c
+++ b/drivers/infiniband/hw/mlx5/flow.c
@@ -322,11 +322,11 @@ void mlx5_ib_destroy_flow_action_raw(struct mlx5_ib_flow_action *maction)
switch (maction->flow_action_raw.sub_type) {
case MLX5_IB_FLOW_ACTION_MODIFY_HEADER:
mlx5_modify_header_dealloc(maction->flow_action_raw.dev->mdev,
- maction->flow_action_raw.action_id);
+ maction->flow_action_raw.modify_hdr);
break;
case MLX5_IB_FLOW_ACTION_PACKET_REFORMAT:
mlx5_packet_reformat_dealloc(maction->flow_action_raw.dev->mdev,
- maction->flow_action_raw.action_id);
+ maction->flow_action_raw.pkt_reformat);
break;
case MLX5_IB_FLOW_ACTION_DECAP:
break;
@@ -352,10 +352,11 @@ mlx5_ib_create_modify_header(struct mlx5_ib_dev *dev,
if (!maction)
return ERR_PTR(-ENOMEM);
- ret = mlx5_modify_header_alloc(dev->mdev, namespace, num_actions, in,
- &maction->flow_action_raw.action_id);
+ maction->flow_action_raw.modify_hdr =
+ mlx5_modify_header_alloc(dev->mdev, namespace, num_actions, in);
- if (ret) {
+ if (IS_ERR(maction->flow_action_raw.modify_hdr)) {
+ ret = PTR_ERR(maction->flow_action_raw.modify_hdr);
kfree(maction);
return ERR_PTR(ret);
}
@@ -479,11 +480,13 @@ static int mlx5_ib_flow_action_create_packet_reformat_ctx(
if (ret)
return ret;
- ret = mlx5_packet_reformat_alloc(dev->mdev, prm_prt, len,
- in, namespace,
- &maction->flow_action_raw.action_id);
- if (ret)
+ maction->flow_action_raw.pkt_reformat =
+ mlx5_packet_reformat_alloc(dev->mdev, prm_prt, len,
+ in, namespace);
+ if (IS_ERR(maction->flow_action_raw.pkt_reformat)) {
+ ret = PTR_ERR(maction->flow_action_raw.pkt_reformat);
return ret;
+ }
maction->flow_action_raw.sub_type =
MLX5_IB_FLOW_ACTION_PACKET_REFORMAT;
diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c
index 016373d1d27e..4e9f1507ffd9 100644
--- a/drivers/infiniband/hw/mlx5/main.c
+++ b/drivers/infiniband/hw/mlx5/main.c
@@ -2658,7 +2658,8 @@ int parse_flow_flow_action(struct mlx5_ib_flow_action *maction,
if (action->action & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR)
return -EINVAL;
action->action |= MLX5_FLOW_CONTEXT_ACTION_MOD_HDR;
- action->modify_id = maction->flow_action_raw.action_id;
+ action->modify_hdr =
+ maction->flow_action_raw.modify_hdr;
return 0;
}
if (maction->flow_action_raw.sub_type ==
@@ -2675,8 +2676,8 @@ int parse_flow_flow_action(struct mlx5_ib_flow_action *maction,
return -EINVAL;
action->action |=
MLX5_FLOW_CONTEXT_ACTION_PACKET_REFORMAT;
- action->reformat_id =
- maction->flow_action_raw.action_id;
+ action->pkt_reformat =
+ maction->flow_action_raw.pkt_reformat;
return 0;
}
/* fall through */
diff --git a/drivers/infiniband/hw/mlx5/mlx5_ib.h b/drivers/infiniband/hw/mlx5/mlx5_ib.h
index a20d2ee08a3b..125a507c10ed 100644
--- a/drivers/infiniband/hw/mlx5/mlx5_ib.h
+++ b/drivers/infiniband/hw/mlx5/mlx5_ib.h
@@ -868,7 +868,10 @@ struct mlx5_ib_flow_action {
struct {
struct mlx5_ib_dev *dev;
u32 sub_type;
- u32 action_id;
+ union {
+ struct mlx5_modify_hdr *modify_hdr;
+ struct mlx5_pkt_reformat *pkt_reformat;
+ };
} flow_action_raw;
};
};
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c
index 4c4620db3d31..f8ee18b4da6f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c
@@ -291,14 +291,14 @@ int mlx5e_tc_tun_create_header_ipv4(struct mlx5e_priv *priv,
*/
goto out;
}
-
- err = mlx5_packet_reformat_alloc(priv->mdev,
- e->reformat_type,
- ipv4_encap_size, encap_header,
- MLX5_FLOW_NAMESPACE_FDB,
- &e->encap_id);
- if (err)
+ e->pkt_reformat = mlx5_packet_reformat_alloc(priv->mdev,
+ e->reformat_type,
+ ipv4_encap_size, encap_header,
+ MLX5_FLOW_NAMESPACE_FDB);
+ if (IS_ERR(e->pkt_reformat)) {
+ err = PTR_ERR(e->pkt_reformat);
goto destroy_neigh_entry;
+ }
e->flags |= MLX5_ENCAP_ENTRY_VALID;
mlx5e_rep_queue_neigh_stats_work(netdev_priv(out_dev));
@@ -407,13 +407,14 @@ int mlx5e_tc_tun_create_header_ipv6(struct mlx5e_priv *priv,
goto out;
}
- err = mlx5_packet_reformat_alloc(priv->mdev,
- e->reformat_type,
- ipv6_encap_size, encap_header,
- MLX5_FLOW_NAMESPACE_FDB,
- &e->encap_id);
- if (err)
+ e->pkt_reformat = mlx5_packet_reformat_alloc(priv->mdev,
+ e->reformat_type,
+ ipv6_encap_size, encap_header,
+ MLX5_FLOW_NAMESPACE_FDB);
+ if (IS_ERR(e->pkt_reformat)) {
+ err = PTR_ERR(e->pkt_reformat);
goto destroy_neigh_entry;
+ }
e->flags |= MLX5_ENCAP_ENTRY_VALID;
mlx5e_rep_queue_neigh_stats_work(netdev_priv(out_dev));
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h
index a0ae5069d8c3..8e512216deb8 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h
@@ -161,7 +161,7 @@ struct mlx5e_encap_entry {
*/
struct hlist_node encap_hlist;
struct list_head flows;
- u32 encap_id;
+ struct mlx5_pkt_reformat *pkt_reformat;
const struct ip_tunnel_info *tun_info;
unsigned char h_dest[ETH_ALEN]; /* destination eth addr */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index 67f66412a33c..30d26eba75a3 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -61,7 +61,7 @@
struct mlx5_nic_flow_attr {
u32 action;
u32 flow_tag;
- u32 mod_hdr_id;
+ struct mlx5_modify_hdr *modify_hdr;
u32 hairpin_tirn;
u8 match_level;
struct mlx5_flow_table *hairpin_ft;
@@ -201,7 +201,7 @@ struct mlx5e_mod_hdr_entry {
struct mod_hdr_key key;
- u32 mod_hdr_id;
+ struct mlx5_modify_hdr *modify_hdr;
refcount_t refcnt;
struct completion res_ready;
@@ -334,7 +334,7 @@ static void mlx5e_mod_hdr_put(struct mlx5e_priv *priv,
WARN_ON(!list_empty(&mh->flows));
if (mh->compl_result > 0)
- mlx5_modify_header_dealloc(priv->mdev, mh->mod_hdr_id);
+ mlx5_modify_header_dealloc(priv->mdev, mh->modify_hdr);
kfree(mh);
}
@@ -395,11 +395,11 @@ static int mlx5e_attach_mod_hdr(struct mlx5e_priv *priv,
hash_add(tbl->hlist, &mh->mod_hdr_hlist, hash_key);
mutex_unlock(&tbl->lock);
- err = mlx5_modify_header_alloc(priv->mdev, namespace,
- mh->key.num_actions,
- mh->key.actions,
- &mh->mod_hdr_id);
- if (err) {
+ mh->modify_hdr = mlx5_modify_header_alloc(priv->mdev, namespace,
+ mh->key.num_actions,
+ mh->key.actions);
+ if (IS_ERR(mh->modify_hdr)) {
+ err = PTR_ERR(mh->modify_hdr);
mh->compl_result = err;
goto alloc_header_err;
}
@@ -412,9 +412,9 @@ static int mlx5e_attach_mod_hdr(struct mlx5e_priv *priv,
list_add(&flow->mod_hdr, &mh->flows);
spin_unlock(&mh->flows_lock);
if (mlx5e_is_eswitch_flow(flow))
- flow->esw_attr->mod_hdr_id = mh->mod_hdr_id;
+ flow->esw_attr->modify_hdr = mh->modify_hdr;
else
- flow->nic_attr->mod_hdr_id = mh->mod_hdr_id;
+ flow->nic_attr->modify_hdr = mh->modify_hdr;
return 0;
@@ -906,7 +906,6 @@ mlx5e_tc_add_nic_flow(struct mlx5e_priv *priv,
struct mlx5_flow_destination dest[2] = {};
struct mlx5_flow_act flow_act = {
.action = attr->action,
- .reformat_id = 0,
.flags = FLOW_ACT_NO_APPEND,
};
struct mlx5_fc *counter = NULL;
@@ -947,7 +946,7 @@ mlx5e_tc_add_nic_flow(struct mlx5e_priv *priv,
if (attr->action & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR) {
err = mlx5e_attach_mod_hdr(priv, flow, parse_attr);
- flow_act.modify_id = attr->mod_hdr_id;
+ flow_act.modify_hdr = attr->modify_hdr;
kfree(parse_attr->mod_hdr_actions);
if (err)
return err;
@@ -1304,14 +1303,13 @@ void mlx5e_tc_encap_flows_add(struct mlx5e_priv *priv,
struct mlx5e_tc_flow *flow;
int err;
- err = mlx5_packet_reformat_alloc(priv->mdev,
- e->reformat_type,
- e->encap_size, e->encap_header,
- MLX5_FLOW_NAMESPACE_FDB,
- &e->encap_id);
- if (err) {
- mlx5_core_warn(priv->mdev, "Failed to offload cached encapsulation header, %d\n",
- err);
+ e->pkt_reformat = mlx5_packet_reformat_alloc(priv->mdev,
+ e->reformat_type,
+ e->encap_size, e->encap_header,
+ MLX5_FLOW_NAMESPACE_FDB);
+ if (IS_ERR(e->pkt_reformat)) {
+ mlx5_core_warn(priv->mdev, "Failed to offload cached encapsulation header, %lu\n",
+ PTR_ERR(e->pkt_reformat));
return;
}
e->flags |= MLX5_ENCAP_ENTRY_VALID;
@@ -1326,7 +1324,7 @@ void mlx5e_tc_encap_flows_add(struct mlx5e_priv *priv,
esw_attr = flow->esw_attr;
spec = &esw_attr->parse_attr->spec;
- esw_attr->dests[flow->tmp_efi_index].encap_id = e->encap_id;
+ esw_attr->dests[flow->tmp_efi_index].pkt_reformat = e->pkt_reformat;
esw_attr->dests[flow->tmp_efi_index].flags |= MLX5_ESW_DEST_ENCAP_VALID;
/* Flow can be associated with multiple encap entries.
* Before offloading the flow verify that all of them have
@@ -1395,7 +1393,7 @@ void mlx5e_tc_encap_flows_del(struct mlx5e_priv *priv,
/* we know that the encap is valid */
e->flags &= ~MLX5_ENCAP_ENTRY_VALID;
- mlx5_packet_reformat_dealloc(priv->mdev, e->encap_id);
+ mlx5_packet_reformat_dealloc(priv->mdev, e->pkt_reformat);
}
static struct mlx5_fc *mlx5e_tc_get_counter(struct mlx5e_tc_flow *flow)
@@ -1561,7 +1559,7 @@ static void mlx5e_encap_dealloc(struct mlx5e_priv *priv, struct mlx5e_encap_entr
mlx5e_rep_encap_entry_detach(netdev_priv(e->out_dev), e);
if (e->flags & MLX5_ENCAP_ENTRY_VALID)
- mlx5_packet_reformat_dealloc(priv->mdev, e->encap_id);
+ mlx5_packet_reformat_dealloc(priv->mdev, e->pkt_reformat);
}
kfree(e->encap_header);
@@ -3048,7 +3046,7 @@ static int mlx5e_attach_encap(struct mlx5e_priv *priv,
flow->encaps[out_index].index = out_index;
*encap_dev = e->out_dev;
if (e->flags & MLX5_ENCAP_ENTRY_VALID) {
- attr->dests[out_index].encap_id = e->encap_id;
+ attr->dests[out_index].pkt_reformat = e->pkt_reformat;
attr->dests[out_index].flags |= MLX5_ESW_DEST_ENCAP_VALID;
*encap_valid = true;
} else {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
index aba9e7a6ad3c..4f70202db6af 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
@@ -69,7 +69,7 @@ struct vport_ingress {
struct mlx5_flow_group *allow_spoofchk_only_grp;
struct mlx5_flow_group *allow_untagged_only_grp;
struct mlx5_flow_group *drop_grp;
- int modify_metadata_id;
+ struct mlx5_modify_hdr *modify_metadata;
struct mlx5_flow_handle *modify_metadata_rule;
struct mlx5_flow_handle *allow_rule;
struct mlx5_flow_handle *drop_rule;
@@ -385,11 +385,11 @@ struct mlx5_esw_flow_attr {
struct {
u32 flags;
struct mlx5_eswitch_rep *rep;
+ struct mlx5_pkt_reformat *pkt_reformat;
struct mlx5_core_dev *mdev;
- u32 encap_id;
struct mlx5_termtbl_handle *termtbl;
} dests[MLX5_MAX_FLOW_FWD_VPORTS];
- u32 mod_hdr_id;
+ struct mlx5_modify_hdr *modify_hdr;
u8 inner_match_level;
u8 outer_match_level;
struct mlx5_fc *counter;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
index 7d3582ee66b7..bee67ff58137 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
@@ -190,10 +190,10 @@ mlx5_eswitch_add_offloaded_rule(struct mlx5_eswitch *esw,
MLX5_FLOW_DEST_VPORT_VHCA_ID;
if (attr->dests[j].flags & MLX5_ESW_DEST_ENCAP) {
flow_act.action |= MLX5_FLOW_CONTEXT_ACTION_PACKET_REFORMAT;
- flow_act.reformat_id = attr->dests[j].encap_id;
+ flow_act.pkt_reformat = attr->dests[j].pkt_reformat;
dest[i].vport.flags |= MLX5_FLOW_DEST_VPORT_REFORMAT_ID;
- dest[i].vport.reformat_id =
- attr->dests[j].encap_id;
+ dest[i].vport.pkt_reformat =
+ attr->dests[j].pkt_reformat;
}
i++;
}
@@ -213,7 +213,7 @@ mlx5_eswitch_add_offloaded_rule(struct mlx5_eswitch *esw,
spec->match_criteria_enable |= MLX5_MATCH_INNER_HEADERS;
if (flow_act.action & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR)
- flow_act.modify_id = attr->mod_hdr_id;
+ flow_act.modify_hdr = attr->modify_hdr;
fdb = esw_get_prio_table(esw, attr->chain, attr->prio, !!split);
if (IS_ERR(fdb)) {
@@ -276,7 +276,7 @@ mlx5_eswitch_add_fwd_rule(struct mlx5_eswitch *esw,
dest[i].vport.flags |= MLX5_FLOW_DEST_VPORT_VHCA_ID;
if (attr->dests[i].flags & MLX5_ESW_DEST_ENCAP) {
dest[i].vport.flags |= MLX5_FLOW_DEST_VPORT_REFORMAT_ID;
- dest[i].vport.reformat_id = attr->dests[i].encap_id;
+ dest[i].vport.pkt_reformat = attr->dests[i].pkt_reformat;
}
}
dest[i].type = MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE;
@@ -1734,7 +1734,7 @@ static int esw_vport_ingress_prio_tag_config(struct mlx5_eswitch *esw,
if (vport->ingress.modify_metadata_rule) {
flow_act.action |= MLX5_FLOW_CONTEXT_ACTION_MOD_HDR;
- flow_act.modify_id = vport->ingress.modify_metadata_id;
+ flow_act.modify_hdr = vport->ingress.modify_metadata;
}
vport->ingress.allow_rule =
@@ -1770,9 +1770,11 @@ static int esw_vport_add_ingress_acl_modify_metadata(struct mlx5_eswitch *esw,
MLX5_SET(set_action_in, action, data,
mlx5_eswitch_get_vport_metadata_for_match(esw, vport->vport));
- err = mlx5_modify_header_alloc(esw->dev, MLX5_FLOW_NAMESPACE_ESW_INGRESS,
- 1, action, &vport->ingress.modify_metadata_id);
- if (err) {
+ vport->ingress.modify_metadata =
+ mlx5_modify_header_alloc(esw->dev, MLX5_FLOW_NAMESPACE_ESW_INGRESS,
+ 1, action);
+ if (IS_ERR(vport->ingress.modify_metadata)) {
+ err = PTR_ERR(vport->ingress.modify_metadata);
esw_warn(esw->dev,
"failed to alloc modify header for vport %d ingress acl (%d)\n",
vport->vport, err);
@@ -1780,7 +1782,7 @@ static int esw_vport_add_ingress_acl_modify_metadata(struct mlx5_eswitch *esw,
}
flow_act.action = MLX5_FLOW_CONTEXT_ACTION_MOD_HDR | MLX5_FLOW_CONTEXT_ACTION_ALLOW;
- flow_act.modify_id = vport->ingress.modify_metadata_id;
+ flow_act.modify_hdr = vport->ingress.modify_metadata;
vport->ingress.modify_metadata_rule = mlx5_add_flow_rules(vport->ingress.acl,
&spec, &flow_act, NULL, 0);
if (IS_ERR(vport->ingress.modify_metadata_rule)) {
@@ -1794,7 +1796,7 @@ static int esw_vport_add_ingress_acl_modify_metadata(struct mlx5_eswitch *esw,
out:
if (err)
- mlx5_modify_header_dealloc(esw->dev, vport->ingress.modify_metadata_id);
+ mlx5_modify_header_dealloc(esw->dev, vport->ingress.modify_metadata);
return err;
}
@@ -1803,7 +1805,7 @@ void esw_vport_del_ingress_acl_modify_metadata(struct mlx5_eswitch *esw,
{
if (vport->ingress.modify_metadata_rule) {
mlx5_del_flow_rules(vport->ingress.modify_metadata_rule);
- mlx5_modify_header_dealloc(esw->dev, vport->ingress.modify_metadata_id);
+ mlx5_modify_header_dealloc(esw->dev, vport->ingress.modify_metadata);
vport->ingress.modify_metadata_rule = NULL;
}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c
index 1e3381604b3d..488f50dfb404 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c
@@ -107,6 +107,34 @@ static int mlx5_cmd_stub_delete_fte(struct mlx5_flow_root_namespace *ns,
return 0;
}
+static int mlx5_cmd_stub_packet_reformat_alloc(struct mlx5_flow_root_namespace *ns,
+ int reformat_type,
+ size_t size,
+ void *reformat_data,
+ enum mlx5_flow_namespace_type namespace,
+ struct mlx5_pkt_reformat *pkt_reformat)
+{
+ return 0;
+}
+
+static void mlx5_cmd_stub_packet_reformat_dealloc(struct mlx5_flow_root_namespace *ns,
+ struct mlx5_pkt_reformat *pkt_reformat)
+{
+}
+
+static int mlx5_cmd_stub_modify_header_alloc(struct mlx5_flow_root_namespace *ns,
+ u8 namespace, u8 num_actions,
+ void *modify_actions,
+ struct mlx5_modify_hdr *modify_hdr)
+{
+ return 0;
+}
+
+static void mlx5_cmd_stub_modify_header_dealloc(struct mlx5_flow_root_namespace *ns,
+ struct mlx5_modify_hdr *modify_hdr)
+{
+}
+
static int mlx5_cmd_update_root_ft(struct mlx5_flow_root_namespace *ns,
struct mlx5_flow_table *ft, u32 underlay_qpn,
bool disconnect)
@@ -412,11 +440,13 @@ static int mlx5_cmd_set_fte(struct mlx5_core_dev *dev,
} else {
MLX5_SET(flow_context, in_flow_context, action,
fte->action.action);
- MLX5_SET(flow_context, in_flow_context, packet_reformat_id,
- fte->action.reformat_id);
+ if (fte->action.pkt_reformat)
+ MLX5_SET(flow_context, in_flow_context, packet_reformat_id,
+ fte->action.pkt_reformat->id);
}
- MLX5_SET(flow_context, in_flow_context, modify_header_id,
- fte->action.modify_id);
+ if (fte->action.modify_hdr)
+ MLX5_SET(flow_context, in_flow_context, modify_header_id,
+ fte->action.modify_hdr->id);
vlan = MLX5_ADDR_OF(flow_context, in_flow_context, push_vlan);
@@ -468,7 +498,7 @@ static int mlx5_cmd_set_fte(struct mlx5_core_dev *dev,
MLX5_FLOW_DEST_VPORT_REFORMAT_ID));
MLX5_SET(extended_dest_format, in_dests,
packet_reformat_id,
- dst->dest_attr.vport.reformat_id);
+ dst->dest_attr.vport.pkt_reformat->id);
}
break;
default:
@@ -643,14 +673,15 @@ int mlx5_cmd_fc_bulk_query(struct mlx5_core_dev *dev, u32 base_id, int bulk_len,
return mlx5_cmd_exec(dev, in, sizeof(in), out, outlen);
}
-int mlx5_packet_reformat_alloc(struct mlx5_core_dev *dev,
- int reformat_type,
- size_t size,
- void *reformat_data,
- enum mlx5_flow_namespace_type namespace,
- u32 *packet_reformat_id)
+static int mlx5_cmd_packet_reformat_alloc(struct mlx5_flow_root_namespace *ns,
+ int reformat_type,
+ size_t size,
+ void *reformat_data,
+ enum mlx5_flow_namespace_type namespace,
+ struct mlx5_pkt_reformat *pkt_reformat)
{
u32 out[MLX5_ST_SZ_DW(alloc_packet_reformat_context_out)];
+ struct mlx5_core_dev *dev = ns->dev;
void *packet_reformat_context_in;
int max_encap_size;
void *reformat;
@@ -693,35 +724,36 @@ int mlx5_packet_reformat_alloc(struct mlx5_core_dev *dev,
memset(out, 0, sizeof(out));
err = mlx5_cmd_exec(dev, in, inlen, out, sizeof(out));
- *packet_reformat_id = MLX5_GET(alloc_packet_reformat_context_out,
- out, packet_reformat_id);
+ pkt_reformat->id = MLX5_GET(alloc_packet_reformat_context_out,
+ out, packet_reformat_id);
kfree(in);
return err;
}
-EXPORT_SYMBOL(mlx5_packet_reformat_alloc);
-void mlx5_packet_reformat_dealloc(struct mlx5_core_dev *dev,
- u32 packet_reformat_id)
+static void mlx5_cmd_packet_reformat_dealloc(struct mlx5_flow_root_namespace *ns,
+ struct mlx5_pkt_reformat *pkt_reformat)
{
u32 in[MLX5_ST_SZ_DW(dealloc_packet_reformat_context_in)];
u32 out[MLX5_ST_SZ_DW(dealloc_packet_reformat_context_out)];
+ struct mlx5_core_dev *dev = ns->dev;
memset(in, 0, sizeof(in));
MLX5_SET(dealloc_packet_reformat_context_in, in, opcode,
MLX5_CMD_OP_DEALLOC_PACKET_REFORMAT_CONTEXT);
MLX5_SET(dealloc_packet_reformat_context_in, in, packet_reformat_id,
- packet_reformat_id);
+ pkt_reformat->id);
mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out));
}
-EXPORT_SYMBOL(mlx5_packet_reformat_dealloc);
-int mlx5_modify_header_alloc(struct mlx5_core_dev *dev,
- u8 namespace, u8 num_actions,
- void *modify_actions, u32 *modify_header_id)
+static int mlx5_cmd_modify_header_alloc(struct mlx5_flow_root_namespace *ns,
+ u8 namespace, u8 num_actions,
+ void *modify_actions,
+ struct mlx5_modify_hdr *modify_hdr)
{
u32 out[MLX5_ST_SZ_DW(alloc_modify_header_context_out)];
int max_actions, actions_size, inlen, err;
+ struct mlx5_core_dev *dev = ns->dev;
void *actions_in;
u8 table_type;
u32 *in;
@@ -772,26 +804,26 @@ int mlx5_modify_header_alloc(struct mlx5_core_dev *dev,
memset(out, 0, sizeof(out));
err = mlx5_cmd_exec(dev, in, inlen, out, sizeof(out));
- *modify_header_id = MLX5_GET(alloc_modify_header_context_out, out, modify_header_id);
+ modify_hdr->id = MLX5_GET(alloc_modify_header_context_out, out, modify_header_id);
kfree(in);
return err;
}
-EXPORT_SYMBOL(mlx5_modify_header_alloc);
-void mlx5_modify_header_dealloc(struct mlx5_core_dev *dev, u32 modify_header_id)
+static void mlx5_cmd_modify_header_dealloc(struct mlx5_flow_root_namespace *ns,
+ struct mlx5_modify_hdr *modify_hdr)
{
u32 in[MLX5_ST_SZ_DW(dealloc_modify_header_context_in)];
u32 out[MLX5_ST_SZ_DW(dealloc_modify_header_context_out)];
+ struct mlx5_core_dev *dev = ns->dev;
memset(in, 0, sizeof(in));
MLX5_SET(dealloc_modify_header_context_in, in, opcode,
MLX5_CMD_OP_DEALLOC_MODIFY_HEADER_CONTEXT);
MLX5_SET(dealloc_modify_header_context_in, in, modify_header_id,
- modify_header_id);
+ modify_hdr->id);
mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out));
}
-EXPORT_SYMBOL(mlx5_modify_header_dealloc);
static const struct mlx5_flow_cmds mlx5_flow_cmds = {
.create_flow_table = mlx5_cmd_create_flow_table,
@@ -803,6 +835,10 @@ static const struct mlx5_flow_cmds mlx5_flow_cmds = {
.update_fte = mlx5_cmd_update_fte,
.delete_fte = mlx5_cmd_delete_fte,
.update_root_ft = mlx5_cmd_update_root_ft,
+ .packet_reformat_alloc = mlx5_cmd_packet_reformat_alloc,
+ .packet_reformat_dealloc = mlx5_cmd_packet_reformat_dealloc,
+ .modify_header_alloc = mlx5_cmd_modify_header_alloc,
+ .modify_header_dealloc = mlx5_cmd_modify_header_dealloc
};
static const struct mlx5_flow_cmds mlx5_flow_cmd_stubs = {
@@ -815,6 +851,10 @@ static const struct mlx5_flow_cmds mlx5_flow_cmd_stubs = {
.update_fte = mlx5_cmd_stub_update_fte,
.delete_fte = mlx5_cmd_stub_delete_fte,
.update_root_ft = mlx5_cmd_stub_update_root_ft,
+ .packet_reformat_alloc = mlx5_cmd_stub_packet_reformat_alloc,
+ .packet_reformat_dealloc = mlx5_cmd_stub_packet_reformat_dealloc,
+ .modify_header_alloc = mlx5_cmd_stub_modify_header_alloc,
+ .modify_header_dealloc = mlx5_cmd_stub_modify_header_dealloc
};
static const struct mlx5_flow_cmds *mlx5_fs_cmd_get_fw_cmds(void)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.h b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.h
index bc4606306009..3268654d6748 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.h
@@ -75,6 +75,24 @@ struct mlx5_flow_cmds {
struct mlx5_flow_table *ft,
u32 underlay_qpn,
bool disconnect);
+
+ int (*packet_reformat_alloc)(struct mlx5_flow_root_namespace *ns,
+ int reformat_type,
+ size_t size,
+ void *reformat_data,
+ enum mlx5_flow_namespace_type namespace,
+ struct mlx5_pkt_reformat *pkt_reformat);
+
+ void (*packet_reformat_dealloc)(struct mlx5_flow_root_namespace *ns,
+ struct mlx5_pkt_reformat *pkt_reformat);
+
+ int (*modify_header_alloc)(struct mlx5_flow_root_namespace *ns,
+ u8 namespace, u8 num_actions,
+ void *modify_actions,
+ struct mlx5_modify_hdr *modify_hdr);
+
+ void (*modify_header_dealloc)(struct mlx5_flow_root_namespace *ns,
+ struct mlx5_modify_hdr *modify_hdr);
};
int mlx5_cmd_fc_alloc(struct mlx5_core_dev *dev, u32 *id);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
index 7bdec442f0ac..1d2333fd3080 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
@@ -1415,7 +1415,8 @@ static bool mlx5_flow_dests_cmp(struct mlx5_flow_destination *d1,
((d1->vport.flags & MLX5_FLOW_DEST_VPORT_VHCA_ID) ?
(d1->vport.vhca_id == d2->vport.vhca_id) : true) &&
((d1->vport.flags & MLX5_FLOW_DEST_VPORT_REFORMAT_ID) ?
- (d1->vport.reformat_id == d2->vport.reformat_id) : true)) ||
+ (d1->vport.pkt_reformat->id ==
+ d2->vport.pkt_reformat->id) : true)) ||
(d1->type == MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE &&
d1->ft == d2->ft) ||
(d1->type == MLX5_FLOW_DESTINATION_TYPE_TIR &&
@@ -2888,3 +2889,105 @@ int mlx5_fs_remove_rx_underlay_qpn(struct mlx5_core_dev *dev, u32 underlay_qpn)
return err;
}
EXPORT_SYMBOL(mlx5_fs_remove_rx_underlay_qpn);
+
+static struct mlx5_flow_root_namespace
+*get_root_namespace(struct mlx5_core_dev *dev, enum mlx5_flow_namespace_type ns_type)
+{
+ struct mlx5_flow_namespace *ns;
+
+ if (ns_type == MLX5_FLOW_NAMESPACE_ESW_EGRESS ||
+ ns_type == MLX5_FLOW_NAMESPACE_ESW_INGRESS)
+ ns = mlx5_get_flow_vport_acl_namespace(dev, ns_type, 0);
+ else
+ ns = mlx5_get_flow_namespace(dev, ns_type);
+ if (!ns)
+ return NULL;
+
+ return find_root(&ns->node);
+}
+
+struct mlx5_modify_hdr *mlx5_modify_header_alloc(struct mlx5_core_dev *dev,
+ u8 ns_type, u8 num_actions,
+ void *modify_actions)
+{
+ struct mlx5_flow_root_namespace *root;
+ struct mlx5_modify_hdr *modify_hdr;
+ int err;
+
+ root = get_root_namespace(dev, ns_type);
+ if (!root)
+ return ERR_PTR(-EOPNOTSUPP);
+
+ modify_hdr = kzalloc(sizeof(*modify_hdr), GFP_KERNEL);
+ if (!modify_hdr)
+ return ERR_PTR(-ENOMEM);
+
+ modify_hdr->ns_type = ns_type;
+ err = root->cmds->modify_header_alloc(root, ns_type, num_actions,
+ modify_actions, modify_hdr);
+ if (err) {
+ kfree(modify_hdr);
+ return ERR_PTR(err);
+ }
+
+ return modify_hdr;
+}
+EXPORT_SYMBOL(mlx5_modify_header_alloc);
+
+void mlx5_modify_header_dealloc(struct mlx5_core_dev *dev,
+ struct mlx5_modify_hdr *modify_hdr)
+{
+ struct mlx5_flow_root_namespace *root;
+
+ root = get_root_namespace(dev, modify_hdr->ns_type);
+ if (WARN_ON(!root))
+ return;
+ root->cmds->modify_header_dealloc(root, modify_hdr);
+ kfree(modify_hdr);
+}
+EXPORT_SYMBOL(mlx5_modify_header_dealloc);
+
+struct mlx5_pkt_reformat *mlx5_packet_reformat_alloc(struct mlx5_core_dev *dev,
+ int reformat_type,
+ size_t size,
+ void *reformat_data,
+ enum mlx5_flow_namespace_type ns_type)
+{
+ struct mlx5_pkt_reformat *pkt_reformat;
+ struct mlx5_flow_root_namespace *root;
+ int err;
+
+ root = get_root_namespace(dev, ns_type);
+ if (!root)
+ return ERR_PTR(-EOPNOTSUPP);
+
+ pkt_reformat = kzalloc(sizeof(*pkt_reformat), GFP_KERNEL);
+ if (!pkt_reformat)
+ return ERR_PTR(-ENOMEM);
+
+ pkt_reformat->ns_type = ns_type;
+ pkt_reformat->reformat_type = reformat_type;
+ err = root->cmds->packet_reformat_alloc(root, reformat_type, size,
+ reformat_data, ns_type,
+ pkt_reformat);
+ if (err) {
+ kfree(pkt_reformat);
+ return ERR_PTR(err);
+ }
+
+ return pkt_reformat;
+}
+EXPORT_SYMBOL(mlx5_packet_reformat_alloc);
+
+void mlx5_packet_reformat_dealloc(struct mlx5_core_dev *dev,
+ struct mlx5_pkt_reformat *pkt_reformat)
+{
+ struct mlx5_flow_root_namespace *root;
+
+ root = get_root_namespace(dev, pkt_reformat->ns_type);
+ if (WARN_ON(!root))
+ return;
+ root->cmds->packet_reformat_dealloc(root, pkt_reformat);
+ kfree(pkt_reformat);
+}
+EXPORT_SYMBOL(mlx5_packet_reformat_dealloc);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h
index 0d16b4b5ab83..ea0f221685ab 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h
@@ -38,6 +38,17 @@
#include <linux/rhashtable.h>
#include <linux/llist.h>
+struct mlx5_modify_hdr {
+ enum mlx5_flow_namespace_type ns_type;
+ u32 id;
+};
+
+struct mlx5_pkt_reformat {
+ enum mlx5_flow_namespace_type ns_type;
+ int reformat_type; /* from mlx5_ifc */
+ u32 id;
+};
+
/* FS_TYPE_PRIO_CHAINS is a PRIO that will have namespaces only,
* and those are in parallel to one another when going over them to connect
* a new flow table. Meaning the last flow table in a TYPE_PRIO prio in one
diff --git a/include/linux/mlx5/fs.h b/include/linux/mlx5/fs.h
index 97ec6be62ac4..724d276ea133 100644
--- a/include/linux/mlx5/fs.h
+++ b/include/linux/mlx5/fs.h
@@ -84,6 +84,8 @@ enum {
FDB_SLOW_PATH,
};
+struct mlx5_pkt_reformat;
+struct mlx5_modify_hdr;
struct mlx5_flow_table;
struct mlx5_flow_group;
struct mlx5_flow_namespace;
@@ -121,7 +123,7 @@ struct mlx5_flow_destination {
struct {
u16 num;
u16 vhca_id;
- u32 reformat_id;
+ struct mlx5_pkt_reformat *pkt_reformat;
u8 flags;
} vport;
};
@@ -195,8 +197,8 @@ enum {
struct mlx5_flow_act {
u32 action;
- u32 reformat_id;
- u32 modify_id;
+ struct mlx5_modify_hdr *modify_hdr;
+ struct mlx5_pkt_reformat *pkt_reformat;
uintptr_t esp_id;
u32 flags;
struct mlx5_fs_vlan vlan[MLX5_FS_VLAN_DEPTH];
@@ -205,8 +207,6 @@ struct mlx5_flow_act {
#define MLX5_DECLARE_FLOW_ACT(name) \
struct mlx5_flow_act name = { .action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST,\
- .reformat_id = 0, \
- .modify_id = 0, \
.flags = 0, }
/* Single destination per rule.
@@ -236,19 +236,18 @@ u32 mlx5_fc_id(struct mlx5_fc *counter);
int mlx5_fs_add_rx_underlay_qpn(struct mlx5_core_dev *dev, u32 underlay_qpn);
int mlx5_fs_remove_rx_underlay_qpn(struct mlx5_core_dev *dev, u32 underlay_qpn);
-int mlx5_modify_header_alloc(struct mlx5_core_dev *dev,
- u8 namespace, u8 num_actions,
- void *modify_actions, u32 *modify_header_id);
+struct mlx5_modify_hdr *mlx5_modify_header_alloc(struct mlx5_core_dev *dev,
+ u8 ns_type, u8 num_actions,
+ void *modify_actions);
void mlx5_modify_header_dealloc(struct mlx5_core_dev *dev,
- u32 modify_header_id);
-
-int mlx5_packet_reformat_alloc(struct mlx5_core_dev *dev,
- int reformat_type,
- size_t size,
- void *reformat_data,
- enum mlx5_flow_namespace_type namespace,
- u32 *packet_reformat_id);
+ struct mlx5_modify_hdr *modify_hdr);
+
+struct mlx5_pkt_reformat *mlx5_packet_reformat_alloc(struct mlx5_core_dev *dev,
+ int reformat_type,
+ size_t size,
+ void *reformat_data,
+ enum mlx5_flow_namespace_type ns_type);
void mlx5_packet_reformat_dealloc(struct mlx5_core_dev *dev,
- u32 packet_reformat_id);
+ struct mlx5_pkt_reformat *reformat);
#endif
--
2.21.0
^ permalink raw reply related
* [net-next V2 04/18] net/mlx5: DR, ICM pool memory allocator
From: Saeed Mahameed @ 2019-09-03 20:04 UTC (permalink / raw)
To: David S. Miller
Cc: netdev@vger.kernel.org, Alex Vesker, Erez Shitrit, Mark Bloch,
Saeed Mahameed
In-Reply-To: <20190903200409.14406-1-saeedm@mellanox.com>
From: Alex Vesker <valex@mellanox.com>
ICM device memory is used for writing steering rules (STEs) to the NIC.
An ICM memory pool allocator was implemented to manage the required
memory. The pool consists of buckets, a bucket per chunk size.
Once a bucket is empty we will cut a row of memory from the latest
allocated MR, if the MR size is not sufficient we will allocate a new MR.
HW design requires that chunks memory address should be aligned to the
chunk size, this is the reason for managing the MR with row size that
insures memory alignment.
Current design is greedy in memory but provides quick allocation times
in steady state.
Signed-off-by: Alex Vesker <valex@mellanox.com>
Reviewed-by: Erez Shitrit <erezsh@mellanox.com>
Reviewed-by: Mark Bloch <markb@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
.../mellanox/mlx5/core/steering/dr_icm_pool.c | 570 ++++++++++++++++++
1 file changed, 570 insertions(+)
create mode 100644 drivers/net/ethernet/mellanox/mlx5/core/steering/dr_icm_pool.c
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_icm_pool.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_icm_pool.c
new file mode 100644
index 000000000000..e76f61e7555e
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_icm_pool.c
@@ -0,0 +1,570 @@
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+/* Copyright (c) 2019 Mellanox Technologies. */
+
+#include "dr_types.h"
+
+#define DR_ICM_MODIFY_HDR_ALIGN_BASE 64
+#define DR_ICM_SYNC_THRESHOLD (64 * 1024 * 1024)
+
+struct mlx5dr_icm_pool;
+
+struct mlx5dr_icm_bucket {
+ struct mlx5dr_icm_pool *pool;
+
+ /* Chunks that aren't visible to HW not directly and not in cache */
+ struct list_head free_list;
+ unsigned int free_list_count;
+
+ /* Used chunks, HW may be accessing this memory */
+ struct list_head used_list;
+ unsigned int used_list_count;
+
+ /* HW may be accessing this memory but at some future,
+ * undetermined time, it might cease to do so. Before deciding to call
+ * sync_ste, this list is moved to sync_list
+ */
+ struct list_head hot_list;
+ unsigned int hot_list_count;
+
+ /* Pending sync list, entries from the hot list are moved to this list.
+ * sync_ste is executed and then sync_list is concatenated to the free list
+ */
+ struct list_head sync_list;
+ unsigned int sync_list_count;
+
+ u32 total_chunks;
+ u32 num_of_entries;
+ u32 entry_size;
+ /* protect the ICM bucket */
+ struct mutex mutex;
+};
+
+struct mlx5dr_icm_pool {
+ struct mlx5dr_icm_bucket *buckets;
+ enum mlx5dr_icm_type icm_type;
+ enum mlx5dr_icm_chunk_size max_log_chunk_sz;
+ enum mlx5dr_icm_chunk_size num_of_buckets;
+ struct list_head icm_mr_list;
+ /* protect the ICM MR list */
+ struct mutex mr_mutex;
+ struct mlx5dr_domain *dmn;
+};
+
+struct mlx5dr_icm_dm {
+ u32 obj_id;
+ enum mlx5_sw_icm_type type;
+ u64 addr;
+ size_t length;
+};
+
+struct mlx5dr_icm_mr {
+ struct mlx5dr_icm_pool *pool;
+ struct mlx5_core_mkey mkey;
+ struct mlx5dr_icm_dm dm;
+ size_t used_length;
+ size_t length;
+ u64 icm_start_addr;
+ struct list_head mr_list;
+};
+
+static int dr_icm_create_dm_mkey(struct mlx5_core_dev *mdev,
+ u32 pd, u64 length, u64 start_addr, int mode,
+ struct mlx5_core_mkey *mkey)
+{
+ u32 inlen = MLX5_ST_SZ_BYTES(create_mkey_in);
+ u32 in[MLX5_ST_SZ_DW(create_mkey_in)] = {};
+ void *mkc;
+
+ mkc = MLX5_ADDR_OF(create_mkey_in, in, memory_key_mkey_entry);
+
+ MLX5_SET(mkc, mkc, access_mode_1_0, mode);
+ MLX5_SET(mkc, mkc, access_mode_4_2, (mode >> 2) & 0x7);
+ MLX5_SET(mkc, mkc, lw, 1);
+ MLX5_SET(mkc, mkc, lr, 1);
+ if (mode == MLX5_MKC_ACCESS_MODE_SW_ICM) {
+ MLX5_SET(mkc, mkc, rw, 1);
+ MLX5_SET(mkc, mkc, rr, 1);
+ }
+
+ MLX5_SET64(mkc, mkc, len, length);
+ MLX5_SET(mkc, mkc, pd, pd);
+ MLX5_SET(mkc, mkc, qpn, 0xffffff);
+ MLX5_SET64(mkc, mkc, start_addr, start_addr);
+
+ return mlx5_core_create_mkey(mdev, mkey, in, inlen);
+}
+
+static struct mlx5dr_icm_mr *
+dr_icm_pool_mr_create(struct mlx5dr_icm_pool *pool,
+ enum mlx5_sw_icm_type type,
+ size_t align_base)
+{
+ struct mlx5_core_dev *mdev = pool->dmn->mdev;
+ struct mlx5dr_icm_mr *icm_mr;
+ size_t align_diff;
+ int err;
+
+ icm_mr = kvzalloc(sizeof(*icm_mr), GFP_KERNEL);
+ if (!icm_mr)
+ return NULL;
+
+ icm_mr->pool = pool;
+ INIT_LIST_HEAD(&icm_mr->mr_list);
+
+ icm_mr->dm.type = type;
+
+ /* 2^log_biggest_table * entry-size * double-for-alignment */
+ icm_mr->dm.length = mlx5dr_icm_pool_chunk_size_to_byte(pool->max_log_chunk_sz,
+ pool->icm_type) * 2;
+
+ err = mlx5_dm_sw_icm_alloc(mdev, icm_mr->dm.type, icm_mr->dm.length, 0,
+ &icm_mr->dm.addr, &icm_mr->dm.obj_id);
+ if (err) {
+ mlx5dr_err(pool->dmn, "Failed to allocate SW ICM memory, err (%d)\n", err);
+ goto free_icm_mr;
+ }
+
+ /* Register device memory */
+ err = dr_icm_create_dm_mkey(mdev, pool->dmn->pdn,
+ icm_mr->dm.length,
+ icm_mr->dm.addr,
+ MLX5_MKC_ACCESS_MODE_SW_ICM,
+ &icm_mr->mkey);
+ if (err) {
+ mlx5dr_err(pool->dmn, "Failed to create SW ICM MKEY, err (%d)\n", err);
+ goto free_dm;
+ }
+
+ icm_mr->icm_start_addr = icm_mr->dm.addr;
+
+ align_diff = icm_mr->icm_start_addr % align_base;
+ if (align_diff)
+ icm_mr->used_length = align_base - align_diff;
+
+ list_add_tail(&icm_mr->mr_list, &pool->icm_mr_list);
+
+ return icm_mr;
+
+free_dm:
+ mlx5_dm_sw_icm_dealloc(mdev, icm_mr->dm.type, icm_mr->dm.length, 0,
+ icm_mr->dm.addr, icm_mr->dm.obj_id);
+free_icm_mr:
+ kvfree(icm_mr);
+ return NULL;
+}
+
+static void dr_icm_pool_mr_destroy(struct mlx5dr_icm_mr *icm_mr)
+{
+ struct mlx5_core_dev *mdev = icm_mr->pool->dmn->mdev;
+ struct mlx5dr_icm_dm *dm = &icm_mr->dm;
+
+ list_del(&icm_mr->mr_list);
+ mlx5_core_destroy_mkey(mdev, &icm_mr->mkey);
+ mlx5_dm_sw_icm_dealloc(mdev, dm->type, dm->length, 0,
+ dm->addr, dm->obj_id);
+ kvfree(icm_mr);
+}
+
+static int dr_icm_chunk_ste_init(struct mlx5dr_icm_chunk *chunk)
+{
+ struct mlx5dr_icm_bucket *bucket = chunk->bucket;
+
+ chunk->ste_arr = kvzalloc(bucket->num_of_entries *
+ sizeof(chunk->ste_arr[0]), GFP_KERNEL);
+ if (!chunk->ste_arr)
+ return -ENOMEM;
+
+ chunk->hw_ste_arr = kvzalloc(bucket->num_of_entries *
+ DR_STE_SIZE_REDUCED, GFP_KERNEL);
+ if (!chunk->hw_ste_arr)
+ goto out_free_ste_arr;
+
+ chunk->miss_list = kvmalloc(bucket->num_of_entries *
+ sizeof(chunk->miss_list[0]), GFP_KERNEL);
+ if (!chunk->miss_list)
+ goto out_free_hw_ste_arr;
+
+ return 0;
+
+out_free_hw_ste_arr:
+ kvfree(chunk->hw_ste_arr);
+out_free_ste_arr:
+ kvfree(chunk->ste_arr);
+ return -ENOMEM;
+}
+
+static int dr_icm_chunks_create(struct mlx5dr_icm_bucket *bucket)
+{
+ size_t mr_free_size, mr_req_size, mr_row_size;
+ struct mlx5dr_icm_pool *pool = bucket->pool;
+ struct mlx5dr_icm_mr *icm_mr = NULL;
+ struct mlx5dr_icm_chunk *chunk;
+ enum mlx5_sw_icm_type dm_type;
+ size_t align_base;
+ int i, err = 0;
+
+ mr_req_size = bucket->num_of_entries * bucket->entry_size;
+ mr_row_size = mlx5dr_icm_pool_chunk_size_to_byte(pool->max_log_chunk_sz,
+ pool->icm_type);
+
+ if (pool->icm_type == DR_ICM_TYPE_STE) {
+ dm_type = MLX5_SW_ICM_TYPE_STEERING;
+ /* Align base is the biggest chunk size / row size */
+ align_base = mr_row_size;
+ } else {
+ dm_type = MLX5_SW_ICM_TYPE_HEADER_MODIFY;
+ /* Align base is 64B */
+ align_base = DR_ICM_MODIFY_HDR_ALIGN_BASE;
+ }
+
+ mutex_lock(&pool->mr_mutex);
+ if (!list_empty(&pool->icm_mr_list)) {
+ icm_mr = list_last_entry(&pool->icm_mr_list,
+ struct mlx5dr_icm_mr, mr_list);
+
+ if (icm_mr)
+ mr_free_size = icm_mr->dm.length - icm_mr->used_length;
+ }
+
+ if (!icm_mr || mr_free_size < mr_row_size) {
+ icm_mr = dr_icm_pool_mr_create(pool, dm_type, align_base);
+ if (!icm_mr) {
+ err = -ENOMEM;
+ goto out_err;
+ }
+ }
+
+ /* Create memory aligned chunks */
+ for (i = 0; i < mr_row_size / mr_req_size; i++) {
+ chunk = kvzalloc(sizeof(*chunk), GFP_KERNEL);
+ if (!chunk) {
+ err = -ENOMEM;
+ goto out_err;
+ }
+
+ chunk->bucket = bucket;
+ chunk->rkey = icm_mr->mkey.key;
+ /* mr start addr is zero based */
+ chunk->mr_addr = icm_mr->used_length;
+ chunk->icm_addr = (uintptr_t)icm_mr->icm_start_addr + icm_mr->used_length;
+ icm_mr->used_length += mr_req_size;
+ chunk->num_of_entries = bucket->num_of_entries;
+ chunk->byte_size = chunk->num_of_entries * bucket->entry_size;
+
+ if (pool->icm_type == DR_ICM_TYPE_STE) {
+ err = dr_icm_chunk_ste_init(chunk);
+ if (err)
+ goto out_free_chunk;
+ }
+
+ INIT_LIST_HEAD(&chunk->chunk_list);
+ list_add(&chunk->chunk_list, &bucket->free_list);
+ bucket->free_list_count++;
+ bucket->total_chunks++;
+ }
+ mutex_unlock(&pool->mr_mutex);
+ return 0;
+
+out_free_chunk:
+ kvfree(chunk);
+out_err:
+ mutex_unlock(&pool->mr_mutex);
+ return err;
+}
+
+static void dr_icm_chunk_ste_cleanup(struct mlx5dr_icm_chunk *chunk)
+{
+ kvfree(chunk->miss_list);
+ kvfree(chunk->hw_ste_arr);
+ kvfree(chunk->ste_arr);
+}
+
+static void dr_icm_chunk_destroy(struct mlx5dr_icm_chunk *chunk)
+{
+ struct mlx5dr_icm_bucket *bucket = chunk->bucket;
+
+ list_del(&chunk->chunk_list);
+ bucket->total_chunks--;
+
+ if (bucket->pool->icm_type == DR_ICM_TYPE_STE)
+ dr_icm_chunk_ste_cleanup(chunk);
+
+ kvfree(chunk);
+}
+
+static void dr_icm_bucket_init(struct mlx5dr_icm_pool *pool,
+ struct mlx5dr_icm_bucket *bucket,
+ enum mlx5dr_icm_chunk_size chunk_size)
+{
+ if (pool->icm_type == DR_ICM_TYPE_STE)
+ bucket->entry_size = DR_STE_SIZE;
+ else
+ bucket->entry_size = DR_MODIFY_ACTION_SIZE;
+
+ bucket->num_of_entries = mlx5dr_icm_pool_chunk_size_to_entries(chunk_size);
+ bucket->pool = pool;
+ mutex_init(&bucket->mutex);
+ INIT_LIST_HEAD(&bucket->free_list);
+ INIT_LIST_HEAD(&bucket->used_list);
+ INIT_LIST_HEAD(&bucket->hot_list);
+ INIT_LIST_HEAD(&bucket->sync_list);
+}
+
+static void dr_icm_bucket_cleanup(struct mlx5dr_icm_bucket *bucket)
+{
+ struct mlx5dr_icm_chunk *chunk, *next;
+
+ mutex_destroy(&bucket->mutex);
+ list_splice_tail_init(&bucket->sync_list, &bucket->free_list);
+ list_splice_tail_init(&bucket->hot_list, &bucket->free_list);
+
+ list_for_each_entry_safe(chunk, next, &bucket->free_list, chunk_list)
+ dr_icm_chunk_destroy(chunk);
+
+ WARN_ON(bucket->total_chunks != 0);
+
+ /* Cleanup of unreturned chunks */
+ list_for_each_entry_safe(chunk, next, &bucket->used_list, chunk_list)
+ dr_icm_chunk_destroy(chunk);
+}
+
+static u64 dr_icm_hot_mem_size(struct mlx5dr_icm_pool *pool)
+{
+ u64 hot_size = 0;
+ int chunk_order;
+
+ for (chunk_order = 0; chunk_order < pool->num_of_buckets; chunk_order++)
+ hot_size += pool->buckets[chunk_order].hot_list_count *
+ mlx5dr_icm_pool_chunk_size_to_byte(chunk_order, pool->icm_type);
+
+ return hot_size;
+}
+
+static bool dr_icm_reuse_hot_entries(struct mlx5dr_icm_pool *pool,
+ struct mlx5dr_icm_bucket *bucket)
+{
+ u64 bytes_for_sync;
+
+ bytes_for_sync = dr_icm_hot_mem_size(pool);
+ if (bytes_for_sync < DR_ICM_SYNC_THRESHOLD || !bucket->hot_list_count)
+ return false;
+
+ return true;
+}
+
+static void dr_icm_chill_bucket_start(struct mlx5dr_icm_bucket *bucket)
+{
+ list_splice_tail_init(&bucket->hot_list, &bucket->sync_list);
+ bucket->sync_list_count += bucket->hot_list_count;
+ bucket->hot_list_count = 0;
+}
+
+static void dr_icm_chill_bucket_end(struct mlx5dr_icm_bucket *bucket)
+{
+ list_splice_tail_init(&bucket->sync_list, &bucket->free_list);
+ bucket->free_list_count += bucket->sync_list_count;
+ bucket->sync_list_count = 0;
+}
+
+static void dr_icm_chill_bucket_abort(struct mlx5dr_icm_bucket *bucket)
+{
+ list_splice_tail_init(&bucket->sync_list, &bucket->hot_list);
+ bucket->hot_list_count += bucket->sync_list_count;
+ bucket->sync_list_count = 0;
+}
+
+static void dr_icm_chill_buckets_start(struct mlx5dr_icm_pool *pool,
+ struct mlx5dr_icm_bucket *cb,
+ bool buckets[DR_CHUNK_SIZE_MAX])
+{
+ struct mlx5dr_icm_bucket *bucket;
+ int i;
+
+ for (i = 0; i < pool->num_of_buckets; i++) {
+ bucket = &pool->buckets[i];
+ if (bucket == cb) {
+ dr_icm_chill_bucket_start(bucket);
+ continue;
+ }
+
+ /* Freeing the mutex is done at the end of that process, after
+ * sync_ste was executed at dr_icm_chill_buckets_end func.
+ */
+ if (mutex_trylock(&bucket->mutex)) {
+ dr_icm_chill_bucket_start(bucket);
+ buckets[i] = true;
+ }
+ }
+}
+
+static void dr_icm_chill_buckets_end(struct mlx5dr_icm_pool *pool,
+ struct mlx5dr_icm_bucket *cb,
+ bool buckets[DR_CHUNK_SIZE_MAX])
+{
+ struct mlx5dr_icm_bucket *bucket;
+ int i;
+
+ for (i = 0; i < pool->num_of_buckets; i++) {
+ bucket = &pool->buckets[i];
+ if (bucket == cb) {
+ dr_icm_chill_bucket_end(bucket);
+ continue;
+ }
+
+ if (!buckets[i])
+ continue;
+
+ dr_icm_chill_bucket_end(bucket);
+ mutex_unlock(&bucket->mutex);
+ }
+}
+
+static void dr_icm_chill_buckets_abort(struct mlx5dr_icm_pool *pool,
+ struct mlx5dr_icm_bucket *cb,
+ bool buckets[DR_CHUNK_SIZE_MAX])
+{
+ struct mlx5dr_icm_bucket *bucket;
+ int i;
+
+ for (i = 0; i < pool->num_of_buckets; i++) {
+ bucket = &pool->buckets[i];
+ if (bucket == cb) {
+ dr_icm_chill_bucket_abort(bucket);
+ continue;
+ }
+
+ if (!buckets[i])
+ continue;
+
+ dr_icm_chill_bucket_abort(bucket);
+ mutex_unlock(&bucket->mutex);
+ }
+}
+
+/* Allocate an ICM chunk, each chunk holds a piece of ICM memory and
+ * also memory used for HW STE management for optimizations.
+ */
+struct mlx5dr_icm_chunk *
+mlx5dr_icm_alloc_chunk(struct mlx5dr_icm_pool *pool,
+ enum mlx5dr_icm_chunk_size chunk_size)
+{
+ struct mlx5dr_icm_chunk *chunk = NULL; /* Fix compilation warning */
+ bool buckets[DR_CHUNK_SIZE_MAX] = {};
+ struct mlx5dr_icm_bucket *bucket;
+ int err;
+
+ if (chunk_size > pool->max_log_chunk_sz)
+ return NULL;
+
+ bucket = &pool->buckets[chunk_size];
+
+ mutex_lock(&bucket->mutex);
+
+ /* Take chunk from pool if available, otherwise allocate new chunks */
+ if (list_empty(&bucket->free_list)) {
+ if (dr_icm_reuse_hot_entries(pool, bucket)) {
+ dr_icm_chill_buckets_start(pool, bucket, buckets);
+ err = mlx5dr_cmd_sync_steering(pool->dmn->mdev);
+ if (err) {
+ dr_icm_chill_buckets_abort(pool, bucket, buckets);
+ mlx5dr_dbg(pool->dmn, "Sync_steering failed\n");
+ chunk = NULL;
+ goto out;
+ }
+ dr_icm_chill_buckets_end(pool, bucket, buckets);
+ } else {
+ dr_icm_chunks_create(bucket);
+ }
+ }
+
+ if (!list_empty(&bucket->free_list)) {
+ chunk = list_last_entry(&bucket->free_list,
+ struct mlx5dr_icm_chunk,
+ chunk_list);
+ if (chunk) {
+ list_del_init(&chunk->chunk_list);
+ list_add_tail(&chunk->chunk_list, &bucket->used_list);
+ bucket->free_list_count--;
+ bucket->used_list_count++;
+ }
+ }
+out:
+ mutex_unlock(&bucket->mutex);
+ return chunk;
+}
+
+void mlx5dr_icm_free_chunk(struct mlx5dr_icm_chunk *chunk)
+{
+ struct mlx5dr_icm_bucket *bucket = chunk->bucket;
+
+ if (bucket->pool->icm_type == DR_ICM_TYPE_STE) {
+ memset(chunk->ste_arr, 0,
+ bucket->num_of_entries * sizeof(chunk->ste_arr[0]));
+ memset(chunk->hw_ste_arr, 0,
+ bucket->num_of_entries * DR_STE_SIZE_REDUCED);
+ }
+
+ mutex_lock(&bucket->mutex);
+ list_del_init(&chunk->chunk_list);
+ list_add_tail(&chunk->chunk_list, &bucket->hot_list);
+ bucket->hot_list_count++;
+ bucket->used_list_count--;
+ mutex_unlock(&bucket->mutex);
+}
+
+struct mlx5dr_icm_pool *mlx5dr_icm_pool_create(struct mlx5dr_domain *dmn,
+ enum mlx5dr_icm_type icm_type)
+{
+ enum mlx5dr_icm_chunk_size max_log_chunk_sz;
+ struct mlx5dr_icm_pool *pool;
+ int i;
+
+ if (icm_type == DR_ICM_TYPE_STE)
+ max_log_chunk_sz = dmn->info.max_log_sw_icm_sz;
+ else
+ max_log_chunk_sz = dmn->info.max_log_action_icm_sz;
+
+ pool = kvzalloc(sizeof(*pool), GFP_KERNEL);
+ if (!pool)
+ return NULL;
+
+ pool->buckets = kcalloc(max_log_chunk_sz + 1,
+ sizeof(pool->buckets[0]),
+ GFP_KERNEL);
+ if (!pool->buckets)
+ goto free_pool;
+
+ pool->dmn = dmn;
+ pool->icm_type = icm_type;
+ pool->max_log_chunk_sz = max_log_chunk_sz;
+ pool->num_of_buckets = max_log_chunk_sz + 1;
+ INIT_LIST_HEAD(&pool->icm_mr_list);
+
+ for (i = 0; i < pool->num_of_buckets; i++)
+ dr_icm_bucket_init(pool, &pool->buckets[i], i);
+
+ mutex_init(&pool->mr_mutex);
+
+ return pool;
+
+free_pool:
+ kvfree(pool);
+ return NULL;
+}
+
+void mlx5dr_icm_pool_destroy(struct mlx5dr_icm_pool *pool)
+{
+ struct mlx5dr_icm_mr *icm_mr, *next;
+ int i;
+
+ mutex_destroy(&pool->mr_mutex);
+
+ list_for_each_entry_safe(icm_mr, next, &pool->icm_mr_list, mr_list)
+ dr_icm_pool_mr_destroy(icm_mr);
+
+ for (i = 0; i < pool->num_of_buckets; i++)
+ dr_icm_bucket_cleanup(&pool->buckets[i]);
+
+ kfree(pool->buckets);
+ kvfree(pool);
+}
--
2.21.0
^ permalink raw reply related
* [net-next V2 05/18] net/mlx5: DR, Expose an internal API to issue RDMA operations
From: Saeed Mahameed @ 2019-09-03 20:04 UTC (permalink / raw)
To: David S. Miller
Cc: netdev@vger.kernel.org, Alex Vesker, Erez Shitrit, Mark Bloch,
Saeed Mahameed
In-Reply-To: <20190903200409.14406-1-saeedm@mellanox.com>
From: Alex Vesker <valex@mellanox.com>
Inserting or deleting a rule is done by RDMA read/write operation to SW
ICM device memory. This file provides the support for executing these
operations. It includes allocating the needed resources and providing an
API for writing steering entries to the memory.
Signed-off-by: Alex Vesker <valex@mellanox.com>
Signed-off-by: Mark Bloch <markb@mellanox.com>
Reviewed-by: Erez Shitrit <erezsh@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
.../mellanox/mlx5/core/steering/dr_send.c | 976 ++++++++++++++++++
1 file changed, 976 insertions(+)
create mode 100644 drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c
new file mode 100644
index 000000000000..ef0dea44f3b3
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c
@@ -0,0 +1,976 @@
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+/* Copyright (c) 2019 Mellanox Technologies. */
+
+#include "dr_types.h"
+
+#define QUEUE_SIZE 128
+#define SIGNAL_PER_DIV_QUEUE 16
+#define TH_NUMS_TO_DRAIN 2
+
+enum { CQ_OK = 0, CQ_EMPTY = -1, CQ_POLL_ERR = -2 };
+
+struct dr_data_seg {
+ u64 addr;
+ u32 length;
+ u32 lkey;
+ unsigned int send_flags;
+};
+
+struct postsend_info {
+ struct dr_data_seg write;
+ struct dr_data_seg read;
+ u64 remote_addr;
+ u32 rkey;
+};
+
+struct dr_qp_rtr_attr {
+ struct mlx5dr_cmd_gid_attr dgid_attr;
+ enum ib_mtu mtu;
+ u32 qp_num;
+ u16 port_num;
+ u8 min_rnr_timer;
+ u8 sgid_index;
+ u16 udp_src_port;
+};
+
+struct dr_qp_rts_attr {
+ u8 timeout;
+ u8 retry_cnt;
+ u8 rnr_retry;
+};
+
+struct dr_qp_init_attr {
+ u32 cqn;
+ u32 pdn;
+ u32 max_send_wr;
+ struct mlx5_uars_page *uar;
+};
+
+static int dr_parse_cqe(struct mlx5dr_cq *dr_cq, struct mlx5_cqe64 *cqe64)
+{
+ unsigned int idx;
+ u8 opcode;
+
+ opcode = get_cqe_opcode(cqe64);
+ if (opcode == MLX5_CQE_REQ_ERR) {
+ idx = be16_to_cpu(cqe64->wqe_counter) &
+ (dr_cq->qp->sq.wqe_cnt - 1);
+ dr_cq->qp->sq.cc = dr_cq->qp->sq.wqe_head[idx] + 1;
+ } else if (opcode == MLX5_CQE_RESP_ERR) {
+ ++dr_cq->qp->sq.cc;
+ } else {
+ idx = be16_to_cpu(cqe64->wqe_counter) &
+ (dr_cq->qp->sq.wqe_cnt - 1);
+ dr_cq->qp->sq.cc = dr_cq->qp->sq.wqe_head[idx] + 1;
+
+ return CQ_OK;
+ }
+
+ return CQ_POLL_ERR;
+}
+
+static int dr_cq_poll_one(struct mlx5dr_cq *dr_cq)
+{
+ struct mlx5_cqe64 *cqe64;
+ int err;
+
+ cqe64 = mlx5_cqwq_get_cqe(&dr_cq->wq);
+ if (!cqe64)
+ return CQ_EMPTY;
+
+ mlx5_cqwq_pop(&dr_cq->wq);
+ err = dr_parse_cqe(dr_cq, cqe64);
+ mlx5_cqwq_update_db_record(&dr_cq->wq);
+
+ return err;
+}
+
+static int dr_poll_cq(struct mlx5dr_cq *dr_cq, int ne)
+{
+ int npolled;
+ int err = 0;
+
+ for (npolled = 0; npolled < ne; ++npolled) {
+ err = dr_cq_poll_one(dr_cq);
+ if (err != CQ_OK)
+ break;
+ }
+
+ return err == CQ_POLL_ERR ? err : npolled;
+}
+
+static void dr_qp_event(struct mlx5_core_qp *mqp, int event)
+{
+ pr_info("DR QP event %u on QP #%u\n", event, mqp->qpn);
+}
+
+static struct mlx5dr_qp *dr_create_rc_qp(struct mlx5_core_dev *mdev,
+ struct dr_qp_init_attr *attr)
+{
+ u32 temp_qpc[MLX5_ST_SZ_DW(qpc)] = {};
+ struct mlx5_wq_param wqp;
+ struct mlx5dr_qp *dr_qp;
+ int inlen;
+ void *qpc;
+ void *in;
+ int err;
+
+ dr_qp = kzalloc(sizeof(*dr_qp), GFP_KERNEL);
+ if (!dr_qp)
+ return NULL;
+
+ wqp.buf_numa_node = mdev->priv.numa_node;
+ wqp.db_numa_node = mdev->priv.numa_node;
+
+ dr_qp->rq.pc = 0;
+ dr_qp->rq.cc = 0;
+ dr_qp->rq.wqe_cnt = 4;
+ dr_qp->sq.pc = 0;
+ dr_qp->sq.cc = 0;
+ dr_qp->sq.wqe_cnt = roundup_pow_of_two(attr->max_send_wr);
+
+ MLX5_SET(qpc, temp_qpc, log_rq_stride, ilog2(MLX5_SEND_WQE_DS) - 4);
+ MLX5_SET(qpc, temp_qpc, log_rq_size, ilog2(dr_qp->rq.wqe_cnt));
+ MLX5_SET(qpc, temp_qpc, log_sq_size, ilog2(dr_qp->sq.wqe_cnt));
+ err = mlx5_wq_qp_create(mdev, &wqp, temp_qpc, &dr_qp->wq,
+ &dr_qp->wq_ctrl);
+ if (err) {
+ mlx5_core_info(mdev, "Can't create QP WQ\n");
+ goto err_wq;
+ }
+
+ dr_qp->sq.wqe_head = kcalloc(dr_qp->sq.wqe_cnt,
+ sizeof(dr_qp->sq.wqe_head[0]),
+ GFP_KERNEL);
+
+ if (!dr_qp->sq.wqe_head) {
+ mlx5_core_warn(mdev, "Can't allocate wqe head\n");
+ goto err_wqe_head;
+ }
+
+ inlen = MLX5_ST_SZ_BYTES(create_qp_in) +
+ MLX5_FLD_SZ_BYTES(create_qp_in, pas[0]) *
+ dr_qp->wq_ctrl.buf.npages;
+ in = kvzalloc(inlen, GFP_KERNEL);
+ if (!in) {
+ err = -ENOMEM;
+ goto err_in;
+ }
+
+ qpc = MLX5_ADDR_OF(create_qp_in, in, qpc);
+ MLX5_SET(qpc, qpc, st, MLX5_QP_ST_RC);
+ MLX5_SET(qpc, qpc, pm_state, MLX5_QP_PM_MIGRATED);
+ MLX5_SET(qpc, qpc, pd, attr->pdn);
+ MLX5_SET(qpc, qpc, uar_page, attr->uar->index);
+ MLX5_SET(qpc, qpc, log_page_size,
+ dr_qp->wq_ctrl.buf.page_shift - MLX5_ADAPTER_PAGE_SHIFT);
+ MLX5_SET(qpc, qpc, fre, 1);
+ MLX5_SET(qpc, qpc, rlky, 1);
+ MLX5_SET(qpc, qpc, cqn_snd, attr->cqn);
+ MLX5_SET(qpc, qpc, cqn_rcv, attr->cqn);
+ MLX5_SET(qpc, qpc, log_rq_stride, ilog2(MLX5_SEND_WQE_DS) - 4);
+ MLX5_SET(qpc, qpc, log_rq_size, ilog2(dr_qp->rq.wqe_cnt));
+ MLX5_SET(qpc, qpc, rq_type, MLX5_NON_ZERO_RQ);
+ MLX5_SET(qpc, qpc, log_sq_size, ilog2(dr_qp->sq.wqe_cnt));
+ MLX5_SET64(qpc, qpc, dbr_addr, dr_qp->wq_ctrl.db.dma);
+ if (MLX5_CAP_GEN(mdev, cqe_version) == 1)
+ MLX5_SET(qpc, qpc, user_index, 0xFFFFFF);
+ mlx5_fill_page_frag_array(&dr_qp->wq_ctrl.buf,
+ (__be64 *)MLX5_ADDR_OF(create_qp_in,
+ in, pas));
+
+ err = mlx5_core_create_qp(mdev, &dr_qp->mqp, in, inlen);
+ kfree(in);
+
+ if (err) {
+ mlx5_core_warn(mdev, " Can't create QP\n");
+ goto err_in;
+ }
+ dr_qp->mqp.event = dr_qp_event;
+ dr_qp->uar = attr->uar;
+
+ return dr_qp;
+
+err_in:
+ kfree(dr_qp->sq.wqe_head);
+err_wqe_head:
+ mlx5_wq_destroy(&dr_qp->wq_ctrl);
+err_wq:
+ kfree(dr_qp);
+ return NULL;
+}
+
+static void dr_destroy_qp(struct mlx5_core_dev *mdev,
+ struct mlx5dr_qp *dr_qp)
+{
+ mlx5_core_destroy_qp(mdev, &dr_qp->mqp);
+ kfree(dr_qp->sq.wqe_head);
+ mlx5_wq_destroy(&dr_qp->wq_ctrl);
+ kfree(dr_qp);
+}
+
+static void dr_cmd_notify_hw(struct mlx5dr_qp *dr_qp, void *ctrl)
+{
+ dma_wmb();
+ *dr_qp->wq.sq.db = cpu_to_be32(dr_qp->sq.pc & 0xfffff);
+
+ /* After wmb() the hw aware of new work */
+ wmb();
+
+ mlx5_write64(ctrl, dr_qp->uar->map + MLX5_BF_OFFSET);
+}
+
+static void dr_rdma_segments(struct mlx5dr_qp *dr_qp, u64 remote_addr,
+ u32 rkey, struct dr_data_seg *data_seg,
+ u32 opcode, int nreq)
+{
+ struct mlx5_wqe_raddr_seg *wq_raddr;
+ struct mlx5_wqe_ctrl_seg *wq_ctrl;
+ struct mlx5_wqe_data_seg *wq_dseg;
+ unsigned int size;
+ unsigned int idx;
+
+ size = sizeof(*wq_ctrl) / 16 + sizeof(*wq_dseg) / 16 +
+ sizeof(*wq_raddr) / 16;
+
+ idx = dr_qp->sq.pc & (dr_qp->sq.wqe_cnt - 1);
+
+ wq_ctrl = mlx5_wq_cyc_get_wqe(&dr_qp->wq.sq, idx);
+ wq_ctrl->imm = 0;
+ wq_ctrl->fm_ce_se = (data_seg->send_flags) ?
+ MLX5_WQE_CTRL_CQ_UPDATE : 0;
+ wq_ctrl->opmod_idx_opcode = cpu_to_be32(((dr_qp->sq.pc & 0xffff) << 8) |
+ opcode);
+ wq_ctrl->qpn_ds = cpu_to_be32(size | dr_qp->mqp.qpn << 8);
+ wq_raddr = (void *)(wq_ctrl + 1);
+ wq_raddr->raddr = cpu_to_be64(remote_addr);
+ wq_raddr->rkey = cpu_to_be32(rkey);
+ wq_raddr->reserved = 0;
+
+ wq_dseg = (void *)(wq_raddr + 1);
+ wq_dseg->byte_count = cpu_to_be32(data_seg->length);
+ wq_dseg->lkey = cpu_to_be32(data_seg->lkey);
+ wq_dseg->addr = cpu_to_be64(data_seg->addr);
+
+ dr_qp->sq.wqe_head[idx] = dr_qp->sq.pc++;
+
+ if (nreq)
+ dr_cmd_notify_hw(dr_qp, wq_ctrl);
+}
+
+static void dr_post_send(struct mlx5dr_qp *dr_qp, struct postsend_info *send_info)
+{
+ dr_rdma_segments(dr_qp, send_info->remote_addr, send_info->rkey,
+ &send_info->write, MLX5_OPCODE_RDMA_WRITE, 0);
+ dr_rdma_segments(dr_qp, send_info->remote_addr, send_info->rkey,
+ &send_info->read, MLX5_OPCODE_RDMA_READ, 1);
+}
+
+/**
+ * mlx5dr_send_fill_and_append_ste_send_info: Add data to be sent
+ * with send_list parameters:
+ *
+ * @ste: The data that attached to this specific ste
+ * @size: of data to write
+ * @offset: of the data from start of the hw_ste entry
+ * @data: data
+ * @ste_info: ste to be sent with send_list
+ * @send_list: to append into it
+ * @copy_data: if true indicates that the data should be kept because
+ * it's not backuped any where (like in re-hash).
+ * if false, it lets the data to be updated after
+ * it was added to the list.
+ */
+void mlx5dr_send_fill_and_append_ste_send_info(struct mlx5dr_ste *ste, u16 size,
+ u16 offset, u8 *data,
+ struct mlx5dr_ste_send_info *ste_info,
+ struct list_head *send_list,
+ bool copy_data)
+{
+ ste_info->size = size;
+ ste_info->ste = ste;
+ ste_info->offset = offset;
+
+ if (copy_data) {
+ memcpy(ste_info->data_cont, data, size);
+ ste_info->data = ste_info->data_cont;
+ } else {
+ ste_info->data = data;
+ }
+
+ list_add_tail(&ste_info->send_list, send_list);
+}
+
+/* The function tries to consume one wc each time, unless the queue is full, in
+ * that case, which means that the hw is behind the sw in a full queue len
+ * the function will drain the cq till it empty.
+ */
+static int dr_handle_pending_wc(struct mlx5dr_domain *dmn,
+ struct mlx5dr_send_ring *send_ring)
+{
+ bool is_drain = false;
+ int ne;
+
+ if (send_ring->pending_wqe < send_ring->signal_th)
+ return 0;
+
+ /* Queue is full start drain it */
+ if (send_ring->pending_wqe >=
+ dmn->send_ring->signal_th * TH_NUMS_TO_DRAIN)
+ is_drain = true;
+
+ do {
+ ne = dr_poll_cq(send_ring->cq, 1);
+ if (ne < 0)
+ return ne;
+ else if (ne == 1)
+ send_ring->pending_wqe -= send_ring->signal_th;
+ } while (is_drain && send_ring->pending_wqe);
+
+ return 0;
+}
+
+static void dr_fill_data_segs(struct mlx5dr_send_ring *send_ring,
+ struct postsend_info *send_info)
+{
+ send_ring->pending_wqe++;
+
+ if (send_ring->pending_wqe % send_ring->signal_th == 0)
+ send_info->write.send_flags |= IB_SEND_SIGNALED;
+
+ send_ring->pending_wqe++;
+ send_info->read.length = send_info->write.length;
+ /* Read into the same write area */
+ send_info->read.addr = (uintptr_t)send_info->write.addr;
+ send_info->read.lkey = send_ring->mr->mkey.key;
+
+ if (send_ring->pending_wqe % send_ring->signal_th == 0)
+ send_info->read.send_flags = IB_SEND_SIGNALED;
+ else
+ send_info->read.send_flags = 0;
+}
+
+static int dr_postsend_icm_data(struct mlx5dr_domain *dmn,
+ struct postsend_info *send_info)
+{
+ struct mlx5dr_send_ring *send_ring = dmn->send_ring;
+ u32 buff_offset;
+ int ret;
+
+ ret = dr_handle_pending_wc(dmn, send_ring);
+ if (ret)
+ return ret;
+
+ if (send_info->write.length > dmn->info.max_inline_size) {
+ buff_offset = (send_ring->tx_head &
+ (dmn->send_ring->signal_th - 1)) *
+ send_ring->max_post_send_size;
+ /* Copy to ring mr */
+ memcpy(send_ring->buf + buff_offset,
+ (void *)(uintptr_t)send_info->write.addr,
+ send_info->write.length);
+ send_info->write.addr = (uintptr_t)send_ring->mr->dma_addr + buff_offset;
+ send_info->write.lkey = send_ring->mr->mkey.key;
+ }
+
+ send_ring->tx_head++;
+ dr_fill_data_segs(send_ring, send_info);
+ dr_post_send(send_ring->qp, send_info);
+
+ return 0;
+}
+
+static int dr_get_tbl_copy_details(struct mlx5dr_domain *dmn,
+ struct mlx5dr_ste_htbl *htbl,
+ u8 **data,
+ u32 *byte_size,
+ int *iterations,
+ int *num_stes)
+{
+ int alloc_size;
+
+ if (htbl->chunk->byte_size > dmn->send_ring->max_post_send_size) {
+ *iterations = htbl->chunk->byte_size /
+ dmn->send_ring->max_post_send_size;
+ *byte_size = dmn->send_ring->max_post_send_size;
+ alloc_size = *byte_size;
+ *num_stes = *byte_size / DR_STE_SIZE;
+ } else {
+ *iterations = 1;
+ *num_stes = htbl->chunk->num_of_entries;
+ alloc_size = *num_stes * DR_STE_SIZE;
+ }
+
+ *data = kzalloc(alloc_size, GFP_KERNEL);
+ if (!*data)
+ return -ENOMEM;
+
+ return 0;
+}
+
+/**
+ * mlx5dr_send_postsend_ste: write size bytes into offset from the hw cm.
+ *
+ * @dmn: Domain
+ * @ste: The ste struct that contains the data (at
+ * least part of it)
+ * @data: The real data to send size data
+ * @size: for writing.
+ * @offset: The offset from the icm mapped data to
+ * start write to this for write only part of the
+ * buffer.
+ *
+ * Return: 0 on success.
+ */
+int mlx5dr_send_postsend_ste(struct mlx5dr_domain *dmn, struct mlx5dr_ste *ste,
+ u8 *data, u16 size, u16 offset)
+{
+ struct postsend_info send_info = {};
+
+ send_info.write.addr = (uintptr_t)data;
+ send_info.write.length = size;
+ send_info.write.lkey = 0;
+ send_info.remote_addr = mlx5dr_ste_get_mr_addr(ste) + offset;
+ send_info.rkey = ste->htbl->chunk->rkey;
+
+ return dr_postsend_icm_data(dmn, &send_info);
+}
+
+int mlx5dr_send_postsend_htbl(struct mlx5dr_domain *dmn,
+ struct mlx5dr_ste_htbl *htbl,
+ u8 *formatted_ste, u8 *mask)
+{
+ u32 byte_size = htbl->chunk->byte_size;
+ int num_stes_per_iter;
+ int iterations;
+ u8 *data;
+ int ret;
+ int i;
+ int j;
+
+ ret = dr_get_tbl_copy_details(dmn, htbl, &data, &byte_size,
+ &iterations, &num_stes_per_iter);
+ if (ret)
+ return ret;
+
+ /* Send the data iteration times */
+ for (i = 0; i < iterations; i++) {
+ u32 ste_index = i * (byte_size / DR_STE_SIZE);
+ struct postsend_info send_info = {};
+
+ /* Copy all ste's on the data buffer
+ * need to add the bit_mask
+ */
+ for (j = 0; j < num_stes_per_iter; j++) {
+ u8 *hw_ste = htbl->ste_arr[ste_index + j].hw_ste;
+ u32 ste_off = j * DR_STE_SIZE;
+
+ if (mlx5dr_ste_is_not_valid_entry(hw_ste)) {
+ memcpy(data + ste_off,
+ formatted_ste, DR_STE_SIZE);
+ } else {
+ /* Copy data */
+ memcpy(data + ste_off,
+ htbl->ste_arr[ste_index + j].hw_ste,
+ DR_STE_SIZE_REDUCED);
+ /* Copy bit_mask */
+ memcpy(data + ste_off + DR_STE_SIZE_REDUCED,
+ mask, DR_STE_SIZE_MASK);
+ }
+ }
+
+ send_info.write.addr = (uintptr_t)data;
+ send_info.write.length = byte_size;
+ send_info.write.lkey = 0;
+ send_info.remote_addr =
+ mlx5dr_ste_get_mr_addr(htbl->ste_arr + ste_index);
+ send_info.rkey = htbl->chunk->rkey;
+
+ ret = dr_postsend_icm_data(dmn, &send_info);
+ if (ret)
+ goto out_free;
+ }
+
+out_free:
+ kfree(data);
+ return ret;
+}
+
+/* Initialize htble with default STEs */
+int mlx5dr_send_postsend_formatted_htbl(struct mlx5dr_domain *dmn,
+ struct mlx5dr_ste_htbl *htbl,
+ u8 *ste_init_data,
+ bool update_hw_ste)
+{
+ u32 byte_size = htbl->chunk->byte_size;
+ int iterations;
+ int num_stes;
+ u8 *data;
+ int ret;
+ int i;
+
+ ret = dr_get_tbl_copy_details(dmn, htbl, &data, &byte_size,
+ &iterations, &num_stes);
+ if (ret)
+ return ret;
+
+ for (i = 0; i < num_stes; i++) {
+ u8 *copy_dst;
+
+ /* Copy the same ste on the data buffer */
+ copy_dst = data + i * DR_STE_SIZE;
+ memcpy(copy_dst, ste_init_data, DR_STE_SIZE);
+
+ if (update_hw_ste) {
+ /* Copy the reduced ste to hash table ste_arr */
+ copy_dst = htbl->hw_ste_arr + i * DR_STE_SIZE_REDUCED;
+ memcpy(copy_dst, ste_init_data, DR_STE_SIZE_REDUCED);
+ }
+ }
+
+ /* Send the data iteration times */
+ for (i = 0; i < iterations; i++) {
+ u8 ste_index = i * (byte_size / DR_STE_SIZE);
+ struct postsend_info send_info = {};
+
+ send_info.write.addr = (uintptr_t)data;
+ send_info.write.length = byte_size;
+ send_info.write.lkey = 0;
+ send_info.remote_addr =
+ mlx5dr_ste_get_mr_addr(htbl->ste_arr + ste_index);
+ send_info.rkey = htbl->chunk->rkey;
+
+ ret = dr_postsend_icm_data(dmn, &send_info);
+ if (ret)
+ goto out_free;
+ }
+
+out_free:
+ kfree(data);
+ return ret;
+}
+
+int mlx5dr_send_postsend_action(struct mlx5dr_domain *dmn,
+ struct mlx5dr_action *action)
+{
+ struct postsend_info send_info = {};
+ int ret;
+
+ send_info.write.addr = (uintptr_t)action->rewrite.data;
+ send_info.write.length = action->rewrite.chunk->byte_size;
+ send_info.write.lkey = 0;
+ send_info.remote_addr = action->rewrite.chunk->mr_addr;
+ send_info.rkey = action->rewrite.chunk->rkey;
+
+ mutex_lock(&dmn->mutex);
+ ret = dr_postsend_icm_data(dmn, &send_info);
+ mutex_unlock(&dmn->mutex);
+
+ return ret;
+}
+
+static int dr_modify_qp_rst2init(struct mlx5_core_dev *mdev,
+ struct mlx5dr_qp *dr_qp,
+ int port)
+{
+ u32 in[MLX5_ST_SZ_DW(rst2init_qp_in)] = {};
+ void *qpc;
+
+ qpc = MLX5_ADDR_OF(rst2init_qp_in, in, qpc);
+
+ MLX5_SET(qpc, qpc, primary_address_path.vhca_port_num, port);
+ MLX5_SET(qpc, qpc, pm_state, MLX5_QPC_PM_STATE_MIGRATED);
+ MLX5_SET(qpc, qpc, rre, 1);
+ MLX5_SET(qpc, qpc, rwe, 1);
+
+ return mlx5_core_qp_modify(mdev, MLX5_CMD_OP_RST2INIT_QP, 0, qpc,
+ &dr_qp->mqp);
+}
+
+static int dr_cmd_modify_qp_rtr2rts(struct mlx5_core_dev *mdev,
+ struct mlx5dr_qp *dr_qp,
+ struct dr_qp_rts_attr *attr)
+{
+ u32 in[MLX5_ST_SZ_DW(rtr2rts_qp_in)] = {};
+ void *qpc;
+
+ qpc = MLX5_ADDR_OF(rtr2rts_qp_in, in, qpc);
+
+ MLX5_SET(rtr2rts_qp_in, in, qpn, dr_qp->mqp.qpn);
+
+ MLX5_SET(qpc, qpc, log_ack_req_freq, 0);
+ MLX5_SET(qpc, qpc, retry_count, attr->retry_cnt);
+ MLX5_SET(qpc, qpc, rnr_retry, attr->rnr_retry);
+
+ return mlx5_core_qp_modify(mdev, MLX5_CMD_OP_RTR2RTS_QP, 0, qpc,
+ &dr_qp->mqp);
+}
+
+static int dr_cmd_modify_qp_init2rtr(struct mlx5_core_dev *mdev,
+ struct mlx5dr_qp *dr_qp,
+ struct dr_qp_rtr_attr *attr)
+{
+ u32 in[MLX5_ST_SZ_DW(init2rtr_qp_in)] = {};
+ void *qpc;
+
+ qpc = MLX5_ADDR_OF(init2rtr_qp_in, in, qpc);
+
+ MLX5_SET(init2rtr_qp_in, in, qpn, dr_qp->mqp.qpn);
+
+ MLX5_SET(qpc, qpc, mtu, attr->mtu);
+ MLX5_SET(qpc, qpc, log_msg_max, DR_CHUNK_SIZE_MAX - 1);
+ MLX5_SET(qpc, qpc, remote_qpn, attr->qp_num);
+ memcpy(MLX5_ADDR_OF(qpc, qpc, primary_address_path.rmac_47_32),
+ attr->dgid_attr.mac, sizeof(attr->dgid_attr.mac));
+ memcpy(MLX5_ADDR_OF(qpc, qpc, primary_address_path.rgid_rip),
+ attr->dgid_attr.gid, sizeof(attr->dgid_attr.gid));
+ MLX5_SET(qpc, qpc, primary_address_path.src_addr_index,
+ attr->sgid_index);
+
+ if (attr->dgid_attr.roce_ver == MLX5_ROCE_VERSION_2)
+ MLX5_SET(qpc, qpc, primary_address_path.udp_sport,
+ attr->udp_src_port);
+
+ MLX5_SET(qpc, qpc, primary_address_path.vhca_port_num, attr->port_num);
+ MLX5_SET(qpc, qpc, min_rnr_nak, 1);
+
+ return mlx5_core_qp_modify(mdev, MLX5_CMD_OP_INIT2RTR_QP, 0, qpc,
+ &dr_qp->mqp);
+}
+
+static int dr_prepare_qp_to_rts(struct mlx5dr_domain *dmn)
+{
+ struct mlx5dr_qp *dr_qp = dmn->send_ring->qp;
+ struct dr_qp_rts_attr rts_attr = {};
+ struct dr_qp_rtr_attr rtr_attr = {};
+ enum ib_mtu mtu = IB_MTU_1024;
+ u16 gid_index = 0;
+ int port = 1;
+ int ret;
+
+ /* Init */
+ ret = dr_modify_qp_rst2init(dmn->mdev, dr_qp, port);
+ if (ret)
+ return ret;
+
+ /* RTR */
+ ret = mlx5dr_cmd_query_gid(dmn->mdev, port, gid_index, &rtr_attr.dgid_attr);
+ if (ret)
+ return ret;
+
+ rtr_attr.mtu = mtu;
+ rtr_attr.qp_num = dr_qp->mqp.qpn;
+ rtr_attr.min_rnr_timer = 12;
+ rtr_attr.port_num = port;
+ rtr_attr.sgid_index = gid_index;
+ rtr_attr.udp_src_port = dmn->info.caps.roce_min_src_udp;
+
+ ret = dr_cmd_modify_qp_init2rtr(dmn->mdev, dr_qp, &rtr_attr);
+ if (ret)
+ return ret;
+
+ /* RTS */
+ rts_attr.timeout = 14;
+ rts_attr.retry_cnt = 7;
+ rts_attr.rnr_retry = 7;
+
+ ret = dr_cmd_modify_qp_rtr2rts(dmn->mdev, dr_qp, &rts_attr);
+ if (ret)
+ return ret;
+
+ return 0;
+}
+
+static void dr_cq_event(struct mlx5_core_cq *mcq,
+ enum mlx5_event event)
+{
+ pr_info("CQ event %u on CQ #%u\n", event, mcq->cqn);
+}
+
+static struct mlx5dr_cq *dr_create_cq(struct mlx5_core_dev *mdev,
+ struct mlx5_uars_page *uar,
+ size_t ncqe)
+{
+ u32 temp_cqc[MLX5_ST_SZ_DW(cqc)] = {};
+ u32 out[MLX5_ST_SZ_DW(create_cq_out)];
+ struct mlx5_wq_param wqp;
+ struct mlx5_cqe64 *cqe;
+ struct mlx5dr_cq *cq;
+ int inlen, err, eqn;
+ unsigned int irqn;
+ void *cqc, *in;
+ __be64 *pas;
+ u32 i;
+
+ cq = kzalloc(sizeof(*cq), GFP_KERNEL);
+ if (!cq)
+ return NULL;
+
+ ncqe = roundup_pow_of_two(ncqe);
+ MLX5_SET(cqc, temp_cqc, log_cq_size, ilog2(ncqe));
+
+ wqp.buf_numa_node = mdev->priv.numa_node;
+ wqp.db_numa_node = mdev->priv.numa_node;
+
+ err = mlx5_cqwq_create(mdev, &wqp, temp_cqc, &cq->wq,
+ &cq->wq_ctrl);
+ if (err)
+ goto out;
+
+ for (i = 0; i < mlx5_cqwq_get_size(&cq->wq); i++) {
+ cqe = mlx5_cqwq_get_wqe(&cq->wq, i);
+ cqe->op_own = MLX5_CQE_INVALID << 4 | MLX5_CQE_OWNER_MASK;
+ }
+
+ inlen = MLX5_ST_SZ_BYTES(create_cq_in) +
+ sizeof(u64) * cq->wq_ctrl.buf.npages;
+ in = kvzalloc(inlen, GFP_KERNEL);
+ if (!in)
+ goto err_cqwq;
+
+ err = mlx5_vector2eqn(mdev, smp_processor_id(), &eqn, &irqn);
+ if (err) {
+ kvfree(in);
+ goto err_cqwq;
+ }
+
+ cqc = MLX5_ADDR_OF(create_cq_in, in, cq_context);
+ MLX5_SET(cqc, cqc, log_cq_size, ilog2(ncqe));
+ MLX5_SET(cqc, cqc, c_eqn, eqn);
+ MLX5_SET(cqc, cqc, uar_page, uar->index);
+ MLX5_SET(cqc, cqc, log_page_size, cq->wq_ctrl.buf.page_shift -
+ MLX5_ADAPTER_PAGE_SHIFT);
+ MLX5_SET64(cqc, cqc, dbr_addr, cq->wq_ctrl.db.dma);
+
+ pas = (__be64 *)MLX5_ADDR_OF(create_cq_in, in, pas);
+ mlx5_fill_page_frag_array(&cq->wq_ctrl.buf, pas);
+
+ cq->mcq.event = dr_cq_event;
+
+ err = mlx5_core_create_cq(mdev, &cq->mcq, in, inlen, out, sizeof(out));
+ kvfree(in);
+
+ if (err)
+ goto err_cqwq;
+
+ cq->mcq.cqe_sz = 64;
+ cq->mcq.set_ci_db = cq->wq_ctrl.db.db;
+ cq->mcq.arm_db = cq->wq_ctrl.db.db + 1;
+ *cq->mcq.set_ci_db = 0;
+ *cq->mcq.arm_db = 0;
+ cq->mcq.vector = 0;
+ cq->mcq.irqn = irqn;
+ cq->mcq.uar = uar;
+
+ return cq;
+
+err_cqwq:
+ mlx5_wq_destroy(&cq->wq_ctrl);
+out:
+ kfree(cq);
+ return NULL;
+}
+
+static void dr_destroy_cq(struct mlx5_core_dev *mdev, struct mlx5dr_cq *cq)
+{
+ mlx5_core_destroy_cq(mdev, &cq->mcq);
+ mlx5_wq_destroy(&cq->wq_ctrl);
+ kfree(cq);
+}
+
+static int
+dr_create_mkey(struct mlx5_core_dev *mdev, u32 pdn, struct mlx5_core_mkey *mkey)
+{
+ u32 in[MLX5_ST_SZ_DW(create_mkey_in)] = {};
+ void *mkc;
+
+ mkc = MLX5_ADDR_OF(create_mkey_in, in, memory_key_mkey_entry);
+ MLX5_SET(mkc, mkc, access_mode_1_0, MLX5_MKC_ACCESS_MODE_PA);
+ MLX5_SET(mkc, mkc, a, 1);
+ MLX5_SET(mkc, mkc, rw, 1);
+ MLX5_SET(mkc, mkc, rr, 1);
+ MLX5_SET(mkc, mkc, lw, 1);
+ MLX5_SET(mkc, mkc, lr, 1);
+
+ MLX5_SET(mkc, mkc, pd, pdn);
+ MLX5_SET(mkc, mkc, length64, 1);
+ MLX5_SET(mkc, mkc, qpn, 0xffffff);
+
+ return mlx5_core_create_mkey(mdev, mkey, in, sizeof(in));
+}
+
+static struct mlx5dr_mr *dr_reg_mr(struct mlx5_core_dev *mdev,
+ u32 pdn, void *buf, size_t size)
+{
+ struct mlx5dr_mr *mr = kzalloc(sizeof(*mr), GFP_KERNEL);
+ struct device *dma_device;
+ dma_addr_t dma_addr;
+ int err;
+
+ if (!mr)
+ return NULL;
+
+ dma_device = &mdev->pdev->dev;
+ dma_addr = dma_map_single(dma_device, buf, size,
+ DMA_BIDIRECTIONAL);
+ err = dma_mapping_error(dma_device, dma_addr);
+ if (err) {
+ mlx5_core_warn(mdev, "Can't dma buf\n");
+ kfree(mr);
+ return NULL;
+ }
+
+ err = dr_create_mkey(mdev, pdn, &mr->mkey);
+ if (err) {
+ mlx5_core_warn(mdev, "Can't create mkey\n");
+ dma_unmap_single(dma_device, dma_addr, size,
+ DMA_BIDIRECTIONAL);
+ kfree(mr);
+ return NULL;
+ }
+
+ mr->dma_addr = dma_addr;
+ mr->size = size;
+ mr->addr = buf;
+
+ return mr;
+}
+
+static void dr_dereg_mr(struct mlx5_core_dev *mdev, struct mlx5dr_mr *mr)
+{
+ mlx5_core_destroy_mkey(mdev, &mr->mkey);
+ dma_unmap_single(&mdev->pdev->dev, mr->dma_addr, mr->size,
+ DMA_BIDIRECTIONAL);
+ kfree(mr);
+}
+
+int mlx5dr_send_ring_alloc(struct mlx5dr_domain *dmn)
+{
+ struct dr_qp_init_attr init_attr = {};
+ int cq_size;
+ int size;
+ int ret;
+
+ dmn->send_ring = kzalloc(sizeof(*dmn->send_ring), GFP_KERNEL);
+ if (!dmn->send_ring)
+ return -ENOMEM;
+
+ cq_size = QUEUE_SIZE + 1;
+ dmn->send_ring->cq = dr_create_cq(dmn->mdev, dmn->uar, cq_size);
+ if (!dmn->send_ring->cq) {
+ ret = -ENOMEM;
+ goto free_send_ring;
+ }
+
+ init_attr.cqn = dmn->send_ring->cq->mcq.cqn;
+ init_attr.pdn = dmn->pdn;
+ init_attr.uar = dmn->uar;
+ init_attr.max_send_wr = QUEUE_SIZE;
+
+ dmn->send_ring->qp = dr_create_rc_qp(dmn->mdev, &init_attr);
+ if (!dmn->send_ring->qp) {
+ ret = -ENOMEM;
+ goto clean_cq;
+ }
+
+ dmn->send_ring->cq->qp = dmn->send_ring->qp;
+
+ dmn->info.max_send_wr = QUEUE_SIZE;
+ dmn->info.max_inline_size = min(dmn->send_ring->qp->max_inline_data,
+ DR_STE_SIZE);
+
+ dmn->send_ring->signal_th = dmn->info.max_send_wr /
+ SIGNAL_PER_DIV_QUEUE;
+
+ /* Prepare qp to be used */
+ ret = dr_prepare_qp_to_rts(dmn);
+ if (ret)
+ goto clean_qp;
+
+ dmn->send_ring->max_post_send_size =
+ mlx5dr_icm_pool_chunk_size_to_byte(DR_CHUNK_SIZE_1K,
+ DR_ICM_TYPE_STE);
+
+ /* Allocating the max size as a buffer for writing */
+ size = dmn->send_ring->signal_th * dmn->send_ring->max_post_send_size;
+ dmn->send_ring->buf = kzalloc(size, GFP_KERNEL);
+ if (!dmn->send_ring->buf) {
+ ret = -ENOMEM;
+ goto clean_qp;
+ }
+
+ memset(dmn->send_ring->buf, 0, size);
+ dmn->send_ring->buf_size = size;
+
+ dmn->send_ring->mr = dr_reg_mr(dmn->mdev,
+ dmn->pdn, dmn->send_ring->buf, size);
+ if (!dmn->send_ring->mr) {
+ ret = -ENOMEM;
+ goto free_mem;
+ }
+
+ dmn->send_ring->sync_mr = dr_reg_mr(dmn->mdev,
+ dmn->pdn, dmn->send_ring->sync_buff,
+ MIN_READ_SYNC);
+ if (!dmn->send_ring->sync_mr) {
+ ret = -ENOMEM;
+ goto clean_mr;
+ }
+
+ return 0;
+
+clean_mr:
+ dr_dereg_mr(dmn->mdev, dmn->send_ring->mr);
+free_mem:
+ kfree(dmn->send_ring->buf);
+clean_qp:
+ dr_destroy_qp(dmn->mdev, dmn->send_ring->qp);
+clean_cq:
+ dr_destroy_cq(dmn->mdev, dmn->send_ring->cq);
+free_send_ring:
+ kfree(dmn->send_ring);
+
+ return ret;
+}
+
+void mlx5dr_send_ring_free(struct mlx5dr_domain *dmn,
+ struct mlx5dr_send_ring *send_ring)
+{
+ dr_destroy_qp(dmn->mdev, send_ring->qp);
+ dr_destroy_cq(dmn->mdev, send_ring->cq);
+ dr_dereg_mr(dmn->mdev, send_ring->sync_mr);
+ dr_dereg_mr(dmn->mdev, send_ring->mr);
+ kfree(send_ring->buf);
+ kfree(send_ring);
+}
+
+int mlx5dr_send_ring_force_drain(struct mlx5dr_domain *dmn)
+{
+ struct mlx5dr_send_ring *send_ring = dmn->send_ring;
+ struct postsend_info send_info = {};
+ u8 data[DR_STE_SIZE];
+ int num_of_sends_req;
+ int ret;
+ int i;
+
+ /* Sending this amount of requests makes sure we will get drain */
+ num_of_sends_req = send_ring->signal_th * TH_NUMS_TO_DRAIN / 2;
+
+ /* Send fake requests forcing the last to be signaled */
+ send_info.write.addr = (uintptr_t)data;
+ send_info.write.length = DR_STE_SIZE;
+ send_info.write.lkey = 0;
+ /* Using the sync_mr in order to write/read */
+ send_info.remote_addr = (uintptr_t)send_ring->sync_mr->addr;
+ send_info.rkey = send_ring->sync_mr->mkey.key;
+
+ for (i = 0; i < num_of_sends_req; i++) {
+ ret = dr_postsend_icm_data(dmn, &send_info);
+ if (ret)
+ return ret;
+ }
+
+ ret = dr_handle_pending_wc(dmn, send_ring);
+
+ return ret;
+}
--
2.21.0
^ permalink raw reply related
* [net-next V2 03/18] net/mlx5: DR, Add direct rule command utilities
From: Saeed Mahameed @ 2019-09-03 20:04 UTC (permalink / raw)
To: David S. Miller
Cc: netdev@vger.kernel.org, Alex Vesker, Erez Shitrit, Mark Bloch,
Saeed Mahameed
In-Reply-To: <20190903200409.14406-1-saeedm@mellanox.com>
From: Alex Vesker <valex@mellanox.com>
Add direct rule command utilities which consists of all the FW
commands that are executed to provide the SW steering functionality.
Signed-off-by: Alex Vesker <valex@mellanox.com>
Reviewed-by: Erez Shitrit <erezsh@mellanox.com>
Reviewed-by: Mark Bloch <markb@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
.../mellanox/mlx5/core/steering/dr_cmd.c | 480 ++++++++++++++
.../mellanox/mlx5/core/steering/mlx5_ifc_dr.h | 604 ++++++++++++++++++
2 files changed, 1084 insertions(+)
create mode 100644 drivers/net/ethernet/mellanox/mlx5/core/steering/dr_cmd.c
create mode 100644 drivers/net/ethernet/mellanox/mlx5/core/steering/mlx5_ifc_dr.h
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_cmd.c
new file mode 100644
index 000000000000..41662c4e2664
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_cmd.c
@@ -0,0 +1,480 @@
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+/* Copyright (c) 2019 Mellanox Technologies. */
+
+#include "dr_types.h"
+
+int mlx5dr_cmd_query_esw_vport_context(struct mlx5_core_dev *mdev,
+ bool other_vport,
+ u16 vport_number,
+ u64 *icm_address_rx,
+ u64 *icm_address_tx)
+{
+ u32 out[MLX5_ST_SZ_DW(query_esw_vport_context_out)] = {};
+ u32 in[MLX5_ST_SZ_DW(query_esw_vport_context_in)] = {};
+ int err;
+
+ MLX5_SET(query_esw_vport_context_in, in, opcode,
+ MLX5_CMD_OP_QUERY_ESW_VPORT_CONTEXT);
+ MLX5_SET(query_esw_vport_context_in, in, other_vport, other_vport);
+ MLX5_SET(query_esw_vport_context_in, in, vport_number, vport_number);
+
+ err = mlx5_cmd_exec(mdev, in, sizeof(in), out, sizeof(out));
+ if (err)
+ return err;
+
+ *icm_address_rx =
+ MLX5_GET64(query_esw_vport_context_out, out,
+ esw_vport_context.sw_steering_vport_icm_address_rx);
+ *icm_address_tx =
+ MLX5_GET64(query_esw_vport_context_out, out,
+ esw_vport_context.sw_steering_vport_icm_address_tx);
+ return 0;
+}
+
+int mlx5dr_cmd_query_gvmi(struct mlx5_core_dev *mdev, bool other_vport,
+ u16 vport_number, u16 *gvmi)
+{
+ u32 in[MLX5_ST_SZ_DW(query_hca_cap_in)] = {};
+ int out_size;
+ void *out;
+ int err;
+
+ out_size = MLX5_ST_SZ_BYTES(query_hca_cap_out);
+ out = kzalloc(out_size, GFP_KERNEL);
+ if (!out)
+ return -ENOMEM;
+
+ MLX5_SET(query_hca_cap_in, in, opcode, MLX5_CMD_OP_QUERY_HCA_CAP);
+ MLX5_SET(query_hca_cap_in, in, other_function, other_vport);
+ MLX5_SET(query_hca_cap_in, in, function_id, vport_number);
+ MLX5_SET(query_hca_cap_in, in, op_mod,
+ MLX5_SET_HCA_CAP_OP_MOD_GENERAL_DEVICE << 1 |
+ HCA_CAP_OPMOD_GET_CUR);
+
+ err = mlx5_cmd_exec(mdev, in, sizeof(in), out, out_size);
+ if (err) {
+ kfree(out);
+ return err;
+ }
+
+ *gvmi = MLX5_GET(query_hca_cap_out, out, capability.cmd_hca_cap.vhca_id);
+
+ kfree(out);
+ return 0;
+}
+
+int mlx5dr_cmd_query_esw_caps(struct mlx5_core_dev *mdev,
+ struct mlx5dr_esw_caps *caps)
+{
+ caps->drop_icm_address_rx =
+ MLX5_CAP64_ESW_FLOWTABLE(mdev,
+ sw_steering_fdb_action_drop_icm_address_rx);
+ caps->drop_icm_address_tx =
+ MLX5_CAP64_ESW_FLOWTABLE(mdev,
+ sw_steering_fdb_action_drop_icm_address_tx);
+ caps->uplink_icm_address_rx =
+ MLX5_CAP64_ESW_FLOWTABLE(mdev,
+ sw_steering_uplink_icm_address_rx);
+ caps->uplink_icm_address_tx =
+ MLX5_CAP64_ESW_FLOWTABLE(mdev,
+ sw_steering_uplink_icm_address_tx);
+ caps->sw_owner =
+ MLX5_CAP_ESW_FLOWTABLE_FDB(mdev,
+ sw_owner);
+
+ return 0;
+}
+
+int mlx5dr_cmd_query_device(struct mlx5_core_dev *mdev,
+ struct mlx5dr_cmd_caps *caps)
+{
+ caps->prio_tag_required = MLX5_CAP_GEN(mdev, prio_tag_required);
+ caps->eswitch_manager = MLX5_CAP_GEN(mdev, eswitch_manager);
+ caps->gvmi = MLX5_CAP_GEN(mdev, vhca_id);
+ caps->flex_protocols = MLX5_CAP_GEN(mdev, flex_parser_protocols);
+
+ if (mlx5dr_matcher_supp_flex_parser_icmp_v4(caps)) {
+ caps->flex_parser_id_icmp_dw0 = MLX5_CAP_GEN(mdev, flex_parser_id_icmp_dw0);
+ caps->flex_parser_id_icmp_dw1 = MLX5_CAP_GEN(mdev, flex_parser_id_icmp_dw1);
+ }
+
+ if (mlx5dr_matcher_supp_flex_parser_icmp_v6(caps)) {
+ caps->flex_parser_id_icmpv6_dw0 =
+ MLX5_CAP_GEN(mdev, flex_parser_id_icmpv6_dw0);
+ caps->flex_parser_id_icmpv6_dw1 =
+ MLX5_CAP_GEN(mdev, flex_parser_id_icmpv6_dw1);
+ }
+
+ caps->nic_rx_drop_address =
+ MLX5_CAP64_FLOWTABLE(mdev, sw_steering_nic_rx_action_drop_icm_address);
+ caps->nic_tx_drop_address =
+ MLX5_CAP64_FLOWTABLE(mdev, sw_steering_nic_tx_action_drop_icm_address);
+ caps->nic_tx_allow_address =
+ MLX5_CAP64_FLOWTABLE(mdev, sw_steering_nic_tx_action_allow_icm_address);
+
+ caps->rx_sw_owner = MLX5_CAP_FLOWTABLE_NIC_RX(mdev, sw_owner);
+ caps->max_ft_level = MLX5_CAP_FLOWTABLE_NIC_RX(mdev, max_ft_level);
+
+ caps->tx_sw_owner = MLX5_CAP_FLOWTABLE_NIC_TX(mdev, sw_owner);
+
+ caps->log_icm_size = MLX5_CAP_DEV_MEM(mdev, log_steering_sw_icm_size);
+ caps->hdr_modify_icm_addr =
+ MLX5_CAP64_DEV_MEM(mdev, header_modify_sw_icm_start_address);
+
+ caps->roce_min_src_udp = MLX5_CAP_ROCE(mdev, r_roce_min_src_udp_port);
+
+ return 0;
+}
+
+int mlx5dr_cmd_query_flow_table(struct mlx5_core_dev *dev,
+ enum fs_flow_table_type type,
+ u32 table_id,
+ struct mlx5dr_cmd_query_flow_table_details *output)
+{
+ u32 out[MLX5_ST_SZ_DW(query_flow_table_out)] = {};
+ u32 in[MLX5_ST_SZ_DW(query_flow_table_in)] = {};
+ int err;
+
+ MLX5_SET(query_flow_table_in, in, opcode,
+ MLX5_CMD_OP_QUERY_FLOW_TABLE);
+
+ MLX5_SET(query_flow_table_in, in, table_type, type);
+ MLX5_SET(query_flow_table_in, in, table_id, table_id);
+
+ err = mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out));
+ if (err)
+ return err;
+
+ output->status = MLX5_GET(query_flow_table_out, out, status);
+ output->level = MLX5_GET(query_flow_table_out, out, flow_table_context.level);
+
+ output->sw_owner_icm_root_1 = MLX5_GET64(query_flow_table_out, out,
+ flow_table_context.sw_owner_icm_root_1);
+ output->sw_owner_icm_root_0 = MLX5_GET64(query_flow_table_out, out,
+ flow_table_context.sw_owner_icm_root_0);
+
+ return 0;
+}
+
+int mlx5dr_cmd_sync_steering(struct mlx5_core_dev *mdev)
+{
+ u32 out[MLX5_ST_SZ_DW(sync_steering_out)] = {};
+ u32 in[MLX5_ST_SZ_DW(sync_steering_in)] = {};
+
+ MLX5_SET(sync_steering_in, in, opcode, MLX5_CMD_OP_SYNC_STEERING);
+
+ return mlx5_cmd_exec(mdev, in, sizeof(in), out, sizeof(out));
+}
+
+int mlx5dr_cmd_set_fte_modify_and_vport(struct mlx5_core_dev *mdev,
+ u32 table_type,
+ u32 table_id,
+ u32 group_id,
+ u32 modify_header_id,
+ u32 vport_id)
+{
+ u32 out[MLX5_ST_SZ_DW(set_fte_out)] = {};
+ void *in_flow_context;
+ unsigned int inlen;
+ void *in_dests;
+ u32 *in;
+ int err;
+
+ inlen = MLX5_ST_SZ_BYTES(set_fte_in) +
+ 1 * MLX5_ST_SZ_BYTES(dest_format_struct); /* One destination only */
+
+ in = kvzalloc(inlen, GFP_KERNEL);
+ if (!in)
+ return -ENOMEM;
+
+ MLX5_SET(set_fte_in, in, opcode, MLX5_CMD_OP_SET_FLOW_TABLE_ENTRY);
+ MLX5_SET(set_fte_in, in, table_type, table_type);
+ MLX5_SET(set_fte_in, in, table_id, table_id);
+
+ in_flow_context = MLX5_ADDR_OF(set_fte_in, in, flow_context);
+ MLX5_SET(flow_context, in_flow_context, group_id, group_id);
+ MLX5_SET(flow_context, in_flow_context, modify_header_id, modify_header_id);
+ MLX5_SET(flow_context, in_flow_context, destination_list_size, 1);
+ MLX5_SET(flow_context, in_flow_context, action,
+ MLX5_FLOW_CONTEXT_ACTION_FWD_DEST |
+ MLX5_FLOW_CONTEXT_ACTION_MOD_HDR);
+
+ in_dests = MLX5_ADDR_OF(flow_context, in_flow_context, destination);
+ MLX5_SET(dest_format_struct, in_dests, destination_type,
+ MLX5_FLOW_DESTINATION_TYPE_VPORT);
+ MLX5_SET(dest_format_struct, in_dests, destination_id, vport_id);
+
+ err = mlx5_cmd_exec(mdev, in, inlen, out, sizeof(out));
+ kvfree(in);
+
+ return err;
+}
+
+int mlx5dr_cmd_del_flow_table_entry(struct mlx5_core_dev *mdev,
+ u32 table_type,
+ u32 table_id)
+{
+ u32 out[MLX5_ST_SZ_DW(delete_fte_out)] = {};
+ u32 in[MLX5_ST_SZ_DW(delete_fte_in)] = {};
+
+ MLX5_SET(delete_fte_in, in, opcode, MLX5_CMD_OP_DELETE_FLOW_TABLE_ENTRY);
+ MLX5_SET(delete_fte_in, in, table_type, table_type);
+ MLX5_SET(delete_fte_in, in, table_id, table_id);
+
+ return mlx5_cmd_exec(mdev, in, sizeof(in), out, sizeof(out));
+}
+
+int mlx5dr_cmd_alloc_modify_header(struct mlx5_core_dev *mdev,
+ u32 table_type,
+ u8 num_of_actions,
+ u64 *actions,
+ u32 *modify_header_id)
+{
+ u32 out[MLX5_ST_SZ_DW(alloc_modify_header_context_out)] = {};
+ void *p_actions;
+ u32 inlen;
+ u32 *in;
+ int err;
+
+ inlen = MLX5_ST_SZ_BYTES(alloc_modify_header_context_in) +
+ num_of_actions * sizeof(u64);
+ in = kvzalloc(inlen, GFP_KERNEL);
+ if (!in)
+ return -ENOMEM;
+
+ MLX5_SET(alloc_modify_header_context_in, in, opcode,
+ MLX5_CMD_OP_ALLOC_MODIFY_HEADER_CONTEXT);
+ MLX5_SET(alloc_modify_header_context_in, in, table_type, table_type);
+ MLX5_SET(alloc_modify_header_context_in, in, num_of_actions, num_of_actions);
+ p_actions = MLX5_ADDR_OF(alloc_modify_header_context_in, in, actions);
+ memcpy(p_actions, actions, num_of_actions * sizeof(u64));
+
+ err = mlx5_cmd_exec(mdev, in, inlen, out, sizeof(out));
+ if (err)
+ goto out;
+
+ *modify_header_id = MLX5_GET(alloc_modify_header_context_out, out,
+ modify_header_id);
+out:
+ kvfree(in);
+ return err;
+}
+
+int mlx5dr_cmd_dealloc_modify_header(struct mlx5_core_dev *mdev,
+ u32 modify_header_id)
+{
+ u32 out[MLX5_ST_SZ_DW(dealloc_modify_header_context_out)] = {};
+ u32 in[MLX5_ST_SZ_DW(dealloc_modify_header_context_in)] = {};
+
+ MLX5_SET(dealloc_modify_header_context_in, in, opcode,
+ MLX5_CMD_OP_DEALLOC_MODIFY_HEADER_CONTEXT);
+ MLX5_SET(dealloc_modify_header_context_in, in, modify_header_id,
+ modify_header_id);
+
+ return mlx5_cmd_exec(mdev, in, sizeof(in), out, sizeof(out));
+}
+
+int mlx5dr_cmd_create_empty_flow_group(struct mlx5_core_dev *mdev,
+ u32 table_type,
+ u32 table_id,
+ u32 *group_id)
+{
+ u32 out[MLX5_ST_SZ_DW(create_flow_group_out)] = {};
+ int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in);
+ u32 *in;
+ int err;
+
+ in = kzalloc(inlen, GFP_KERNEL);
+ if (!in)
+ return -ENOMEM;
+
+ MLX5_SET(create_flow_group_in, in, opcode, MLX5_CMD_OP_CREATE_FLOW_GROUP);
+ MLX5_SET(create_flow_group_in, in, table_type, table_type);
+ MLX5_SET(create_flow_group_in, in, table_id, table_id);
+
+ err = mlx5_cmd_exec(mdev, in, inlen, out, sizeof(out));
+ if (err)
+ goto out;
+
+ *group_id = MLX5_GET(create_flow_group_out, out, group_id);
+
+out:
+ kfree(in);
+ return err;
+}
+
+int mlx5dr_cmd_destroy_flow_group(struct mlx5_core_dev *mdev,
+ u32 table_type,
+ u32 table_id,
+ u32 group_id)
+{
+ u32 in[MLX5_ST_SZ_DW(destroy_flow_group_in)] = {};
+ u32 out[MLX5_ST_SZ_DW(destroy_flow_group_out)] = {};
+
+ MLX5_SET(create_flow_group_in, in, opcode, MLX5_CMD_OP_DESTROY_FLOW_GROUP);
+ MLX5_SET(destroy_flow_group_in, in, table_type, table_type);
+ MLX5_SET(destroy_flow_group_in, in, table_id, table_id);
+ MLX5_SET(destroy_flow_group_in, in, group_id, group_id);
+
+ return mlx5_cmd_exec(mdev, in, sizeof(in), out, sizeof(out));
+}
+
+int mlx5dr_cmd_create_flow_table(struct mlx5_core_dev *mdev,
+ u32 table_type,
+ u64 icm_addr_rx,
+ u64 icm_addr_tx,
+ u8 level,
+ bool sw_owner,
+ bool term_tbl,
+ u64 *fdb_rx_icm_addr,
+ u32 *table_id)
+{
+ u32 out[MLX5_ST_SZ_DW(create_flow_table_out)] = {};
+ u32 in[MLX5_ST_SZ_DW(create_flow_table_in)] = {};
+ void *ft_mdev;
+ int err;
+
+ MLX5_SET(create_flow_table_in, in, opcode, MLX5_CMD_OP_CREATE_FLOW_TABLE);
+ MLX5_SET(create_flow_table_in, in, table_type, table_type);
+
+ ft_mdev = MLX5_ADDR_OF(create_flow_table_in, in, flow_table_context);
+ MLX5_SET(flow_table_context, ft_mdev, termination_table, term_tbl);
+ MLX5_SET(flow_table_context, ft_mdev, sw_owner, sw_owner);
+ MLX5_SET(flow_table_context, ft_mdev, level, level);
+
+ if (sw_owner) {
+ /* icm_addr_0 used for FDB RX / NIC TX / NIC_RX
+ * icm_addr_1 used for FDB TX
+ */
+ if (table_type == MLX5_FLOW_TABLE_TYPE_NIC_RX) {
+ MLX5_SET64(flow_table_context, ft_mdev,
+ sw_owner_icm_root_0, icm_addr_rx);
+ } else if (table_type == MLX5_FLOW_TABLE_TYPE_NIC_TX) {
+ MLX5_SET64(flow_table_context, ft_mdev,
+ sw_owner_icm_root_0, icm_addr_tx);
+ } else if (table_type == MLX5_FLOW_TABLE_TYPE_FDB) {
+ MLX5_SET64(flow_table_context, ft_mdev,
+ sw_owner_icm_root_0, icm_addr_rx);
+ MLX5_SET64(flow_table_context, ft_mdev,
+ sw_owner_icm_root_1, icm_addr_tx);
+ }
+ }
+
+ err = mlx5_cmd_exec(mdev, in, sizeof(in), out, sizeof(out));
+ if (err)
+ return err;
+
+ *table_id = MLX5_GET(create_flow_table_out, out, table_id);
+ if (!sw_owner && table_type == MLX5_FLOW_TABLE_TYPE_FDB)
+ *fdb_rx_icm_addr =
+ (u64)MLX5_GET(create_flow_table_out, out, icm_address_31_0) |
+ (u64)MLX5_GET(create_flow_table_out, out, icm_address_39_32) << 32 |
+ (u64)MLX5_GET(create_flow_table_out, out, icm_address_63_40) << 40;
+
+ return 0;
+}
+
+int mlx5dr_cmd_destroy_flow_table(struct mlx5_core_dev *mdev,
+ u32 table_id,
+ u32 table_type)
+{
+ u32 out[MLX5_ST_SZ_DW(destroy_flow_table_out)] = {};
+ u32 in[MLX5_ST_SZ_DW(destroy_flow_table_in)] = {};
+
+ MLX5_SET(destroy_flow_table_in, in, opcode,
+ MLX5_CMD_OP_DESTROY_FLOW_TABLE);
+ MLX5_SET(destroy_flow_table_in, in, table_type, table_type);
+ MLX5_SET(destroy_flow_table_in, in, table_id, table_id);
+
+ return mlx5_cmd_exec(mdev, in, sizeof(in), out, sizeof(out));
+}
+
+int mlx5dr_cmd_create_reformat_ctx(struct mlx5_core_dev *mdev,
+ enum mlx5_reformat_ctx_type rt,
+ size_t reformat_size,
+ void *reformat_data,
+ u32 *reformat_id)
+{
+ u32 out[MLX5_ST_SZ_DW(alloc_packet_reformat_context_out)] = {};
+ size_t inlen, cmd_data_sz, cmd_total_sz;
+ void *prctx;
+ void *pdata;
+ void *in;
+ int err;
+
+ cmd_total_sz = MLX5_ST_SZ_BYTES(alloc_packet_reformat_context_in);
+ cmd_data_sz = MLX5_FLD_SZ_BYTES(alloc_packet_reformat_context_in,
+ packet_reformat_context.reformat_data);
+ inlen = ALIGN(cmd_total_sz + reformat_size - cmd_data_sz, 4);
+ in = kvzalloc(inlen, GFP_KERNEL);
+ if (!in)
+ return -ENOMEM;
+
+ MLX5_SET(alloc_packet_reformat_context_in, in, opcode,
+ MLX5_CMD_OP_ALLOC_PACKET_REFORMAT_CONTEXT);
+
+ prctx = MLX5_ADDR_OF(alloc_packet_reformat_context_in, in, packet_reformat_context);
+ pdata = MLX5_ADDR_OF(packet_reformat_context_in, prctx, reformat_data);
+
+ MLX5_SET(packet_reformat_context_in, prctx, reformat_type, rt);
+ MLX5_SET(packet_reformat_context_in, prctx, reformat_data_size, reformat_size);
+ memcpy(pdata, reformat_data, reformat_size);
+
+ err = mlx5_cmd_exec(mdev, in, inlen, out, sizeof(out));
+ if (err)
+ return err;
+
+ *reformat_id = MLX5_GET(alloc_packet_reformat_context_out, out, packet_reformat_id);
+ kvfree(in);
+
+ return err;
+}
+
+void mlx5dr_cmd_destroy_reformat_ctx(struct mlx5_core_dev *mdev,
+ u32 reformat_id)
+{
+ u32 out[MLX5_ST_SZ_DW(dealloc_packet_reformat_context_out)] = {};
+ u32 in[MLX5_ST_SZ_DW(dealloc_packet_reformat_context_in)] = {};
+
+ MLX5_SET(dealloc_packet_reformat_context_in, in, opcode,
+ MLX5_CMD_OP_DEALLOC_PACKET_REFORMAT_CONTEXT);
+ MLX5_SET(dealloc_packet_reformat_context_in, in, packet_reformat_id,
+ reformat_id);
+
+ mlx5_cmd_exec(mdev, in, sizeof(in), out, sizeof(out));
+}
+
+int mlx5dr_cmd_query_gid(struct mlx5_core_dev *mdev, u8 vhca_port_num,
+ u16 index, struct mlx5dr_cmd_gid_attr *attr)
+{
+ u32 out[MLX5_ST_SZ_DW(query_roce_address_out)] = {};
+ u32 in[MLX5_ST_SZ_DW(query_roce_address_in)] = {};
+ int err;
+
+ MLX5_SET(query_roce_address_in, in, opcode,
+ MLX5_CMD_OP_QUERY_ROCE_ADDRESS);
+
+ MLX5_SET(query_roce_address_in, in, roce_address_index, index);
+ MLX5_SET(query_roce_address_in, in, vhca_port_num, vhca_port_num);
+
+ err = mlx5_cmd_exec(mdev, in, sizeof(in), out, sizeof(out));
+ if (err)
+ return err;
+
+ memcpy(&attr->gid,
+ MLX5_ADDR_OF(query_roce_address_out,
+ out, roce_address.source_l3_address),
+ sizeof(attr->gid));
+ memcpy(attr->mac,
+ MLX5_ADDR_OF(query_roce_address_out, out,
+ roce_address.source_mac_47_32),
+ sizeof(attr->mac));
+
+ if (MLX5_GET(query_roce_address_out, out,
+ roce_address.roce_version) == MLX5_ROCE_VERSION_2)
+ attr->roce_ver = MLX5_ROCE_VERSION_2;
+ else
+ attr->roce_ver = MLX5_ROCE_VERSION_1;
+
+ return 0;
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/mlx5_ifc_dr.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/mlx5_ifc_dr.h
new file mode 100644
index 000000000000..596c927220d9
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/mlx5_ifc_dr.h
@@ -0,0 +1,604 @@
+/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */
+/* Copyright (c) 2019, Mellanox Technologies */
+
+#ifndef MLX5_IFC_DR_H
+#define MLX5_IFC_DR_H
+
+enum {
+ MLX5DR_ACTION_MDFY_HW_FLD_L2_0 = 0,
+ MLX5DR_ACTION_MDFY_HW_FLD_L2_1 = 1,
+ MLX5DR_ACTION_MDFY_HW_FLD_L2_2 = 2,
+ MLX5DR_ACTION_MDFY_HW_FLD_L3_0 = 3,
+ MLX5DR_ACTION_MDFY_HW_FLD_L3_1 = 4,
+ MLX5DR_ACTION_MDFY_HW_FLD_L3_2 = 5,
+ MLX5DR_ACTION_MDFY_HW_FLD_L3_3 = 6,
+ MLX5DR_ACTION_MDFY_HW_FLD_L3_4 = 7,
+ MLX5DR_ACTION_MDFY_HW_FLD_L4_0 = 8,
+ MLX5DR_ACTION_MDFY_HW_FLD_L4_1 = 9,
+ MLX5DR_ACTION_MDFY_HW_FLD_MPLS = 10,
+ MLX5DR_ACTION_MDFY_HW_FLD_L2_TNL_0 = 11,
+ MLX5DR_ACTION_MDFY_HW_FLD_REG_0 = 12,
+ MLX5DR_ACTION_MDFY_HW_FLD_REG_1 = 13,
+ MLX5DR_ACTION_MDFY_HW_FLD_REG_2 = 14,
+ MLX5DR_ACTION_MDFY_HW_FLD_REG_3 = 15,
+ MLX5DR_ACTION_MDFY_HW_FLD_L4_2 = 16,
+ MLX5DR_ACTION_MDFY_HW_FLD_FLEX_0 = 17,
+ MLX5DR_ACTION_MDFY_HW_FLD_FLEX_1 = 18,
+ MLX5DR_ACTION_MDFY_HW_FLD_FLEX_2 = 19,
+ MLX5DR_ACTION_MDFY_HW_FLD_FLEX_3 = 20,
+ MLX5DR_ACTION_MDFY_HW_FLD_L2_TNL_1 = 21,
+ MLX5DR_ACTION_MDFY_HW_FLD_METADATA = 22,
+ MLX5DR_ACTION_MDFY_HW_FLD_RESERVED = 23,
+};
+
+enum {
+ MLX5DR_ACTION_MDFY_HW_OP_SET = 0x2,
+ MLX5DR_ACTION_MDFY_HW_OP_ADD = 0x3,
+};
+
+enum {
+ MLX5DR_ACTION_MDFY_HW_HDR_L3_NONE = 0x0,
+ MLX5DR_ACTION_MDFY_HW_HDR_L3_IPV4 = 0x1,
+ MLX5DR_ACTION_MDFY_HW_HDR_L3_IPV6 = 0x2,
+};
+
+enum {
+ MLX5DR_ACTION_MDFY_HW_HDR_L4_NONE = 0x0,
+ MLX5DR_ACTION_MDFY_HW_HDR_L4_TCP = 0x1,
+ MLX5DR_ACTION_MDFY_HW_HDR_L4_UDP = 0x2,
+};
+
+enum {
+ MLX5DR_STE_LU_TYPE_NOP = 0x00,
+ MLX5DR_STE_LU_TYPE_SRC_GVMI_AND_QP = 0x05,
+ MLX5DR_STE_LU_TYPE_ETHL2_TUNNELING_I = 0x0a,
+ MLX5DR_STE_LU_TYPE_ETHL2_DST_O = 0x06,
+ MLX5DR_STE_LU_TYPE_ETHL2_DST_I = 0x07,
+ MLX5DR_STE_LU_TYPE_ETHL2_DST_D = 0x1b,
+ MLX5DR_STE_LU_TYPE_ETHL2_SRC_O = 0x08,
+ MLX5DR_STE_LU_TYPE_ETHL2_SRC_I = 0x09,
+ MLX5DR_STE_LU_TYPE_ETHL2_SRC_D = 0x1c,
+ MLX5DR_STE_LU_TYPE_ETHL2_SRC_DST_O = 0x36,
+ MLX5DR_STE_LU_TYPE_ETHL2_SRC_DST_I = 0x37,
+ MLX5DR_STE_LU_TYPE_ETHL2_SRC_DST_D = 0x38,
+ MLX5DR_STE_LU_TYPE_ETHL3_IPV6_DST_O = 0x0d,
+ MLX5DR_STE_LU_TYPE_ETHL3_IPV6_DST_I = 0x0e,
+ MLX5DR_STE_LU_TYPE_ETHL3_IPV6_DST_D = 0x1e,
+ MLX5DR_STE_LU_TYPE_ETHL3_IPV6_SRC_O = 0x0f,
+ MLX5DR_STE_LU_TYPE_ETHL3_IPV6_SRC_I = 0x10,
+ MLX5DR_STE_LU_TYPE_ETHL3_IPV6_SRC_D = 0x1f,
+ MLX5DR_STE_LU_TYPE_ETHL3_IPV4_5_TUPLE_O = 0x11,
+ MLX5DR_STE_LU_TYPE_ETHL3_IPV4_5_TUPLE_I = 0x12,
+ MLX5DR_STE_LU_TYPE_ETHL3_IPV4_5_TUPLE_D = 0x20,
+ MLX5DR_STE_LU_TYPE_ETHL3_IPV4_MISC_O = 0x29,
+ MLX5DR_STE_LU_TYPE_ETHL3_IPV4_MISC_I = 0x2a,
+ MLX5DR_STE_LU_TYPE_ETHL3_IPV4_MISC_D = 0x2b,
+ MLX5DR_STE_LU_TYPE_ETHL4_O = 0x13,
+ MLX5DR_STE_LU_TYPE_ETHL4_I = 0x14,
+ MLX5DR_STE_LU_TYPE_ETHL4_D = 0x21,
+ MLX5DR_STE_LU_TYPE_ETHL4_MISC_O = 0x2c,
+ MLX5DR_STE_LU_TYPE_ETHL4_MISC_I = 0x2d,
+ MLX5DR_STE_LU_TYPE_ETHL4_MISC_D = 0x2e,
+ MLX5DR_STE_LU_TYPE_MPLS_FIRST_O = 0x15,
+ MLX5DR_STE_LU_TYPE_MPLS_FIRST_I = 0x24,
+ MLX5DR_STE_LU_TYPE_MPLS_FIRST_D = 0x25,
+ MLX5DR_STE_LU_TYPE_GRE = 0x16,
+ MLX5DR_STE_LU_TYPE_FLEX_PARSER_0 = 0x22,
+ MLX5DR_STE_LU_TYPE_FLEX_PARSER_1 = 0x23,
+ MLX5DR_STE_LU_TYPE_FLEX_PARSER_TNL_HEADER = 0x19,
+ MLX5DR_STE_LU_TYPE_GENERAL_PURPOSE = 0x18,
+ MLX5DR_STE_LU_TYPE_STEERING_REGISTERS_0 = 0x2f,
+ MLX5DR_STE_LU_TYPE_STEERING_REGISTERS_1 = 0x30,
+ MLX5DR_STE_LU_TYPE_DONT_CARE = 0x0f,
+};
+
+enum mlx5dr_ste_entry_type {
+ MLX5DR_STE_TYPE_TX = 1,
+ MLX5DR_STE_TYPE_RX = 2,
+ MLX5DR_STE_TYPE_MODIFY_PKT = 6,
+};
+
+struct mlx5_ifc_ste_general_bits {
+ u8 entry_type[0x4];
+ u8 reserved_at_4[0x4];
+ u8 entry_sub_type[0x8];
+ u8 byte_mask[0x10];
+
+ u8 next_table_base_63_48[0x10];
+ u8 next_lu_type[0x8];
+ u8 next_table_base_39_32_size[0x8];
+
+ u8 next_table_base_31_5_size[0x1b];
+ u8 linear_hash_enable[0x1];
+ u8 reserved_at_5c[0x2];
+ u8 next_table_rank[0x2];
+
+ u8 reserved_at_60[0xa0];
+ u8 tag_value[0x60];
+ u8 bit_mask[0x60];
+};
+
+struct mlx5_ifc_ste_sx_transmit_bits {
+ u8 entry_type[0x4];
+ u8 reserved_at_4[0x4];
+ u8 entry_sub_type[0x8];
+ u8 byte_mask[0x10];
+
+ u8 next_table_base_63_48[0x10];
+ u8 next_lu_type[0x8];
+ u8 next_table_base_39_32_size[0x8];
+
+ u8 next_table_base_31_5_size[0x1b];
+ u8 linear_hash_enable[0x1];
+ u8 reserved_at_5c[0x2];
+ u8 next_table_rank[0x2];
+
+ u8 sx_wire[0x1];
+ u8 sx_func_lb[0x1];
+ u8 sx_sniffer[0x1];
+ u8 sx_wire_enable[0x1];
+ u8 sx_func_lb_enable[0x1];
+ u8 sx_sniffer_enable[0x1];
+ u8 action_type[0x3];
+ u8 reserved_at_69[0x1];
+ u8 action_description[0x6];
+ u8 gvmi[0x10];
+
+ u8 encap_pointer_vlan_data[0x20];
+
+ u8 loopback_syndome_en[0x8];
+ u8 loopback_syndome[0x8];
+ u8 counter_trigger[0x10];
+
+ u8 miss_address_63_48[0x10];
+ u8 counter_trigger_23_16[0x8];
+ u8 miss_address_39_32[0x8];
+
+ u8 miss_address_31_6[0x1a];
+ u8 learning_point[0x1];
+ u8 go_back[0x1];
+ u8 match_polarity[0x1];
+ u8 mask_mode[0x1];
+ u8 miss_rank[0x2];
+};
+
+struct mlx5_ifc_ste_rx_steering_mult_bits {
+ u8 entry_type[0x4];
+ u8 reserved_at_4[0x4];
+ u8 entry_sub_type[0x8];
+ u8 byte_mask[0x10];
+
+ u8 next_table_base_63_48[0x10];
+ u8 next_lu_type[0x8];
+ u8 next_table_base_39_32_size[0x8];
+
+ u8 next_table_base_31_5_size[0x1b];
+ u8 linear_hash_enable[0x1];
+ u8 reserved_at_[0x2];
+ u8 next_table_rank[0x2];
+
+ u8 member_count[0x10];
+ u8 gvmi[0x10];
+
+ u8 qp_list_pointer[0x20];
+
+ u8 reserved_at_a0[0x1];
+ u8 tunneling_action[0x3];
+ u8 action_description[0x4];
+ u8 reserved_at_a8[0x8];
+ u8 counter_trigger_15_0[0x10];
+
+ u8 miss_address_63_48[0x10];
+ u8 counter_trigger_23_16[0x08];
+ u8 miss_address_39_32[0x8];
+
+ u8 miss_address_31_6[0x1a];
+ u8 learning_point[0x1];
+ u8 fail_on_error[0x1];
+ u8 match_polarity[0x1];
+ u8 mask_mode[0x1];
+ u8 miss_rank[0x2];
+};
+
+struct mlx5_ifc_ste_modify_packet_bits {
+ u8 entry_type[0x4];
+ u8 reserved_at_4[0x4];
+ u8 entry_sub_type[0x8];
+ u8 byte_mask[0x10];
+
+ u8 next_table_base_63_48[0x10];
+ u8 next_lu_type[0x8];
+ u8 next_table_base_39_32_size[0x8];
+
+ u8 next_table_base_31_5_size[0x1b];
+ u8 linear_hash_enable[0x1];
+ u8 reserved_at_[0x2];
+ u8 next_table_rank[0x2];
+
+ u8 number_of_re_write_actions[0x10];
+ u8 gvmi[0x10];
+
+ u8 header_re_write_actions_pointer[0x20];
+
+ u8 reserved_at_a0[0x1];
+ u8 tunneling_action[0x3];
+ u8 action_description[0x4];
+ u8 reserved_at_a8[0x8];
+ u8 counter_trigger_15_0[0x10];
+
+ u8 miss_address_63_48[0x10];
+ u8 counter_trigger_23_16[0x08];
+ u8 miss_address_39_32[0x8];
+
+ u8 miss_address_31_6[0x1a];
+ u8 learning_point[0x1];
+ u8 fail_on_error[0x1];
+ u8 match_polarity[0x1];
+ u8 mask_mode[0x1];
+ u8 miss_rank[0x2];
+};
+
+struct mlx5_ifc_ste_eth_l2_src_bits {
+ u8 smac_47_16[0x20];
+
+ u8 smac_15_0[0x10];
+ u8 l3_ethertype[0x10];
+
+ u8 qp_type[0x2];
+ u8 ethertype_filter[0x1];
+ u8 reserved_at_43[0x1];
+ u8 sx_sniffer[0x1];
+ u8 force_lb[0x1];
+ u8 functional_lb[0x1];
+ u8 port[0x1];
+ u8 reserved_at_48[0x4];
+ u8 first_priority[0x3];
+ u8 first_cfi[0x1];
+ u8 first_vlan_qualifier[0x2];
+ u8 reserved_at_52[0x2];
+ u8 first_vlan_id[0xc];
+
+ u8 ip_fragmented[0x1];
+ u8 tcp_syn[0x1];
+ u8 encp_type[0x2];
+ u8 l3_type[0x2];
+ u8 l4_type[0x2];
+ u8 reserved_at_68[0x4];
+ u8 second_priority[0x3];
+ u8 second_cfi[0x1];
+ u8 second_vlan_qualifier[0x2];
+ u8 reserved_at_72[0x2];
+ u8 second_vlan_id[0xc];
+};
+
+struct mlx5_ifc_ste_eth_l2_dst_bits {
+ u8 dmac_47_16[0x20];
+
+ u8 dmac_15_0[0x10];
+ u8 l3_ethertype[0x10];
+
+ u8 qp_type[0x2];
+ u8 ethertype_filter[0x1];
+ u8 reserved_at_43[0x1];
+ u8 sx_sniffer[0x1];
+ u8 force_lb[0x1];
+ u8 functional_lb[0x1];
+ u8 port[0x1];
+ u8 reserved_at_48[0x4];
+ u8 first_priority[0x3];
+ u8 first_cfi[0x1];
+ u8 first_vlan_qualifier[0x2];
+ u8 reserved_at_52[0x2];
+ u8 first_vlan_id[0xc];
+
+ u8 ip_fragmented[0x1];
+ u8 tcp_syn[0x1];
+ u8 encp_type[0x2];
+ u8 l3_type[0x2];
+ u8 l4_type[0x2];
+ u8 reserved_at_68[0x4];
+ u8 second_priority[0x3];
+ u8 second_cfi[0x1];
+ u8 second_vlan_qualifier[0x2];
+ u8 reserved_at_72[0x2];
+ u8 second_vlan_id[0xc];
+};
+
+struct mlx5_ifc_ste_eth_l2_src_dst_bits {
+ u8 dmac_47_16[0x20];
+
+ u8 dmac_15_0[0x10];
+ u8 smac_47_32[0x10];
+
+ u8 smac_31_0[0x20];
+
+ u8 sx_sniffer[0x1];
+ u8 force_lb[0x1];
+ u8 functional_lb[0x1];
+ u8 port[0x1];
+ u8 l3_type[0x2];
+ u8 reserved_at_66[0x6];
+ u8 first_priority[0x3];
+ u8 first_cfi[0x1];
+ u8 first_vlan_qualifier[0x2];
+ u8 reserved_at_72[0x2];
+ u8 first_vlan_id[0xc];
+};
+
+struct mlx5_ifc_ste_eth_l3_ipv4_5_tuple_bits {
+ u8 destination_address[0x20];
+
+ u8 source_address[0x20];
+
+ u8 source_port[0x10];
+ u8 destination_port[0x10];
+
+ u8 fragmented[0x1];
+ u8 first_fragment[0x1];
+ u8 reserved_at_62[0x2];
+ u8 reserved_at_64[0x1];
+ u8 ecn[0x2];
+ u8 tcp_ns[0x1];
+ u8 tcp_cwr[0x1];
+ u8 tcp_ece[0x1];
+ u8 tcp_urg[0x1];
+ u8 tcp_ack[0x1];
+ u8 tcp_psh[0x1];
+ u8 tcp_rst[0x1];
+ u8 tcp_syn[0x1];
+ u8 tcp_fin[0x1];
+ u8 dscp[0x6];
+ u8 reserved_at_76[0x2];
+ u8 protocol[0x8];
+};
+
+struct mlx5_ifc_ste_eth_l3_ipv6_dst_bits {
+ u8 dst_ip_127_96[0x20];
+
+ u8 dst_ip_95_64[0x20];
+
+ u8 dst_ip_63_32[0x20];
+
+ u8 dst_ip_31_0[0x20];
+};
+
+struct mlx5_ifc_ste_eth_l2_tnl_bits {
+ u8 dmac_47_16[0x20];
+
+ u8 dmac_15_0[0x10];
+ u8 l3_ethertype[0x10];
+
+ u8 l2_tunneling_network_id[0x20];
+
+ u8 ip_fragmented[0x1];
+ u8 tcp_syn[0x1];
+ u8 encp_type[0x2];
+ u8 l3_type[0x2];
+ u8 l4_type[0x2];
+ u8 first_priority[0x3];
+ u8 first_cfi[0x1];
+ u8 reserved_at_6c[0x3];
+ u8 gre_key_flag[0x1];
+ u8 first_vlan_qualifier[0x2];
+ u8 reserved_at_72[0x2];
+ u8 first_vlan_id[0xc];
+};
+
+struct mlx5_ifc_ste_eth_l3_ipv6_src_bits {
+ u8 src_ip_127_96[0x20];
+
+ u8 src_ip_95_64[0x20];
+
+ u8 src_ip_63_32[0x20];
+
+ u8 src_ip_31_0[0x20];
+};
+
+struct mlx5_ifc_ste_eth_l3_ipv4_misc_bits {
+ u8 version[0x4];
+ u8 ihl[0x4];
+ u8 reserved_at_8[0x8];
+ u8 total_length[0x10];
+
+ u8 identification[0x10];
+ u8 flags[0x3];
+ u8 fragment_offset[0xd];
+
+ u8 time_to_live[0x8];
+ u8 reserved_at_48[0x8];
+ u8 checksum[0x10];
+
+ u8 reserved_at_60[0x20];
+};
+
+struct mlx5_ifc_ste_eth_l4_bits {
+ u8 fragmented[0x1];
+ u8 first_fragment[0x1];
+ u8 reserved_at_2[0x6];
+ u8 protocol[0x8];
+ u8 dst_port[0x10];
+
+ u8 ipv6_version[0x4];
+ u8 reserved_at_24[0x1];
+ u8 ecn[0x2];
+ u8 tcp_ns[0x1];
+ u8 tcp_cwr[0x1];
+ u8 tcp_ece[0x1];
+ u8 tcp_urg[0x1];
+ u8 tcp_ack[0x1];
+ u8 tcp_psh[0x1];
+ u8 tcp_rst[0x1];
+ u8 tcp_syn[0x1];
+ u8 tcp_fin[0x1];
+ u8 src_port[0x10];
+
+ u8 ipv6_payload_length[0x10];
+ u8 ipv6_hop_limit[0x8];
+ u8 dscp[0x6];
+ u8 reserved_at_5e[0x2];
+
+ u8 tcp_data_offset[0x4];
+ u8 reserved_at_64[0x8];
+ u8 flow_label[0x14];
+};
+
+struct mlx5_ifc_ste_eth_l4_misc_bits {
+ u8 checksum[0x10];
+ u8 length[0x10];
+
+ u8 seq_num[0x20];
+
+ u8 ack_num[0x20];
+
+ u8 urgent_pointer[0x10];
+ u8 window_size[0x10];
+};
+
+struct mlx5_ifc_ste_mpls_bits {
+ u8 mpls0_label[0x14];
+ u8 mpls0_exp[0x3];
+ u8 mpls0_s_bos[0x1];
+ u8 mpls0_ttl[0x8];
+
+ u8 mpls1_label[0x20];
+
+ u8 mpls2_label[0x20];
+
+ u8 reserved_at_60[0x16];
+ u8 mpls4_s_bit[0x1];
+ u8 mpls4_qualifier[0x1];
+ u8 mpls3_s_bit[0x1];
+ u8 mpls3_qualifier[0x1];
+ u8 mpls2_s_bit[0x1];
+ u8 mpls2_qualifier[0x1];
+ u8 mpls1_s_bit[0x1];
+ u8 mpls1_qualifier[0x1];
+ u8 mpls0_s_bit[0x1];
+ u8 mpls0_qualifier[0x1];
+};
+
+struct mlx5_ifc_ste_register_0_bits {
+ u8 register_0_h[0x20];
+
+ u8 register_0_l[0x20];
+
+ u8 register_1_h[0x20];
+
+ u8 register_1_l[0x20];
+};
+
+struct mlx5_ifc_ste_register_1_bits {
+ u8 register_2_h[0x20];
+
+ u8 register_2_l[0x20];
+
+ u8 register_3_h[0x20];
+
+ u8 register_3_l[0x20];
+};
+
+struct mlx5_ifc_ste_gre_bits {
+ u8 gre_c_present[0x1];
+ u8 reserved_at_30[0x1];
+ u8 gre_k_present[0x1];
+ u8 gre_s_present[0x1];
+ u8 strict_src_route[0x1];
+ u8 recur[0x3];
+ u8 flags[0x5];
+ u8 version[0x3];
+ u8 gre_protocol[0x10];
+
+ u8 checksum[0x10];
+ u8 offset[0x10];
+
+ u8 gre_key_h[0x18];
+ u8 gre_key_l[0x8];
+
+ u8 seq_num[0x20];
+};
+
+struct mlx5_ifc_ste_flex_parser_0_bits {
+ u8 parser_3_label[0x14];
+ u8 parser_3_exp[0x3];
+ u8 parser_3_s_bos[0x1];
+ u8 parser_3_ttl[0x8];
+
+ u8 flex_parser_2[0x20];
+
+ u8 flex_parser_1[0x20];
+
+ u8 flex_parser_0[0x20];
+};
+
+struct mlx5_ifc_ste_flex_parser_1_bits {
+ u8 flex_parser_7[0x20];
+
+ u8 flex_parser_6[0x20];
+
+ u8 flex_parser_5[0x20];
+
+ u8 flex_parser_4[0x20];
+};
+
+struct mlx5_ifc_ste_flex_parser_tnl_bits {
+ u8 flex_parser_tunneling_header_63_32[0x20];
+
+ u8 flex_parser_tunneling_header_31_0[0x20];
+
+ u8 reserved_at_40[0x40];
+};
+
+struct mlx5_ifc_ste_general_purpose_bits {
+ u8 general_purpose_lookup_field[0x20];
+
+ u8 reserved_at_20[0x20];
+
+ u8 reserved_at_40[0x20];
+
+ u8 reserved_at_60[0x20];
+};
+
+struct mlx5_ifc_ste_src_gvmi_qp_bits {
+ u8 loopback_syndrome[0x8];
+ u8 reserved_at_8[0x8];
+ u8 source_gvmi[0x10];
+
+ u8 reserved_at_20[0x5];
+ u8 force_lb[0x1];
+ u8 functional_lb[0x1];
+ u8 source_is_requestor[0x1];
+ u8 source_qp[0x18];
+
+ u8 reserved_at_40[0x20];
+
+ u8 reserved_at_60[0x20];
+};
+
+struct mlx5_ifc_l2_hdr_bits {
+ u8 dmac_47_16[0x20];
+
+ u8 dmac_15_0[0x10];
+ u8 smac_47_32[0x10];
+
+ u8 smac_31_0[0x20];
+
+ u8 ethertype[0x10];
+ u8 vlan_type[0x10];
+
+ u8 vlan[0x10];
+ u8 reserved_at_90[0x10];
+};
+
+/* Both HW set and HW add share the same HW format with different opcodes */
+struct mlx5_ifc_dr_action_hw_set_bits {
+ u8 opcode[0x8];
+ u8 destination_field_code[0x8];
+ u8 reserved_at_10[0x2];
+ u8 destination_left_shifter[0x6];
+ u8 reserved_at_18[0x3];
+ u8 destination_length[0x5];
+
+ u8 inline_data[0x20];
+};
+
+#endif /* MLX5_IFC_DR_H */
--
2.21.0
^ permalink raw reply related
* [net-next V2 07/18] net/mlx5: DR, Expose steering domain functionality
From: Saeed Mahameed @ 2019-09-03 20:04 UTC (permalink / raw)
To: David S. Miller
Cc: netdev@vger.kernel.org, Alex Vesker, Erez Shitrit, Mark Bloch,
Saeed Mahameed
In-Reply-To: <20190903200409.14406-1-saeedm@mellanox.com>
From: Alex Vesker <valex@mellanox.com>
Domain is the frame for all of the dr (direct rule) objects.
There are different domain types which also affect the object under that
domain. Each domain can hold multiple tables which can hold multiple
matchers and so on, this means that all of the dr (direct rule) objects
exist under a specific domain. The domain object also holds the
resources needed for other objects such as memory management and
communication with the device.
Signed-off-by: Alex Vesker <valex@mellanox.com>
Reviewed-by: Erez Shitrit <erezsh@mellanox.com>
Reviewed-by: Mark Bloch <markb@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
.../mellanox/mlx5/core/steering/dr_domain.c | 395 ++++++++++++++++++
1 file changed, 395 insertions(+)
create mode 100644 drivers/net/ethernet/mellanox/mlx5/core/steering/dr_domain.c
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_domain.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_domain.c
new file mode 100644
index 000000000000..3b9cf0bccf4d
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_domain.c
@@ -0,0 +1,395 @@
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+/* Copyright (c) 2019 Mellanox Technologies. */
+
+#include <linux/mlx5/eswitch.h>
+#include "dr_types.h"
+
+static int dr_domain_init_cache(struct mlx5dr_domain *dmn)
+{
+ /* Per vport cached FW FT for checksum recalculation, this
+ * recalculation is needed due to a HW bug.
+ */
+ dmn->cache.recalc_cs_ft = kcalloc(dmn->info.caps.num_vports,
+ sizeof(dmn->cache.recalc_cs_ft[0]),
+ GFP_KERNEL);
+ if (!dmn->cache.recalc_cs_ft)
+ return -ENOMEM;
+
+ return 0;
+}
+
+static void dr_domain_uninit_cache(struct mlx5dr_domain *dmn)
+{
+ int i;
+
+ for (i = 0; i < dmn->info.caps.num_vports; i++) {
+ if (!dmn->cache.recalc_cs_ft[i])
+ continue;
+
+ mlx5dr_fw_destroy_recalc_cs_ft(dmn, dmn->cache.recalc_cs_ft[i]);
+ }
+
+ kfree(dmn->cache.recalc_cs_ft);
+}
+
+int mlx5dr_domain_cache_get_recalc_cs_ft_addr(struct mlx5dr_domain *dmn,
+ u32 vport_num,
+ u64 *rx_icm_addr)
+{
+ struct mlx5dr_fw_recalc_cs_ft *recalc_cs_ft;
+
+ recalc_cs_ft = dmn->cache.recalc_cs_ft[vport_num];
+ if (!recalc_cs_ft) {
+ /* Table not in cache, need to allocate a new one */
+ recalc_cs_ft = mlx5dr_fw_create_recalc_cs_ft(dmn, vport_num);
+ if (!recalc_cs_ft)
+ return -EINVAL;
+
+ dmn->cache.recalc_cs_ft[vport_num] = recalc_cs_ft;
+ }
+
+ *rx_icm_addr = recalc_cs_ft->rx_icm_addr;
+
+ return 0;
+}
+
+static int dr_domain_init_resources(struct mlx5dr_domain *dmn)
+{
+ int ret;
+
+ ret = mlx5_core_alloc_pd(dmn->mdev, &dmn->pdn);
+ if (ret) {
+ mlx5dr_dbg(dmn, "Couldn't allocate PD\n");
+ return ret;
+ }
+
+ dmn->uar = mlx5_get_uars_page(dmn->mdev);
+ if (!dmn->uar) {
+ mlx5dr_err(dmn, "Couldn't allocate UAR\n");
+ goto clean_pd;
+ }
+
+ dmn->ste_icm_pool = mlx5dr_icm_pool_create(dmn, DR_ICM_TYPE_STE);
+ if (!dmn->ste_icm_pool) {
+ mlx5dr_err(dmn, "Couldn't get icm memory for %s\n",
+ dev_name(dmn->mdev->device));
+ goto clean_uar;
+ }
+
+ dmn->action_icm_pool = mlx5dr_icm_pool_create(dmn, DR_ICM_TYPE_MODIFY_ACTION);
+ if (!dmn->action_icm_pool) {
+ mlx5dr_err(dmn, "Couldn't get action icm memory for %s\n",
+ dev_name(dmn->mdev->device));
+ goto free_ste_icm_pool;
+ }
+
+ ret = mlx5dr_send_ring_alloc(dmn);
+ if (ret) {
+ mlx5dr_err(dmn, "Couldn't create send-ring for %s\n",
+ dev_name(dmn->mdev->device));
+ goto free_action_icm_pool;
+ }
+
+ return 0;
+
+free_action_icm_pool:
+ mlx5dr_icm_pool_destroy(dmn->action_icm_pool);
+free_ste_icm_pool:
+ mlx5dr_icm_pool_destroy(dmn->ste_icm_pool);
+clean_uar:
+ mlx5_put_uars_page(dmn->mdev, dmn->uar);
+clean_pd:
+ mlx5_core_dealloc_pd(dmn->mdev, dmn->pdn);
+
+ return ret;
+}
+
+static void dr_domain_uninit_resources(struct mlx5dr_domain *dmn)
+{
+ mlx5dr_send_ring_free(dmn, dmn->send_ring);
+ mlx5dr_icm_pool_destroy(dmn->action_icm_pool);
+ mlx5dr_icm_pool_destroy(dmn->ste_icm_pool);
+ mlx5_put_uars_page(dmn->mdev, dmn->uar);
+ mlx5_core_dealloc_pd(dmn->mdev, dmn->pdn);
+}
+
+static int dr_domain_query_vport(struct mlx5dr_domain *dmn,
+ bool other_vport,
+ u16 vport_number)
+{
+ struct mlx5dr_cmd_vport_cap *vport_caps;
+ int ret;
+
+ vport_caps = &dmn->info.caps.vports_caps[vport_number];
+
+ ret = mlx5dr_cmd_query_esw_vport_context(dmn->mdev,
+ other_vport,
+ vport_number,
+ &vport_caps->icm_address_rx,
+ &vport_caps->icm_address_tx);
+ if (ret)
+ return ret;
+
+ ret = mlx5dr_cmd_query_gvmi(dmn->mdev,
+ other_vport,
+ vport_number,
+ &vport_caps->vport_gvmi);
+ if (ret)
+ return ret;
+
+ vport_caps->num = vport_number;
+ vport_caps->vhca_gvmi = dmn->info.caps.gvmi;
+
+ return 0;
+}
+
+static int dr_domain_query_vports(struct mlx5dr_domain *dmn)
+{
+ struct mlx5dr_esw_caps *esw_caps = &dmn->info.caps.esw_caps;
+ struct mlx5dr_cmd_vport_cap *wire_vport;
+ int vport;
+ int ret;
+
+ /* Query vports (except wire vport) */
+ for (vport = 0; vport < dmn->info.caps.num_esw_ports - 1; vport++) {
+ ret = dr_domain_query_vport(dmn, !!vport, vport);
+ if (ret)
+ return ret;
+ }
+
+ /* Last vport is the wire port */
+ wire_vport = &dmn->info.caps.vports_caps[vport];
+ wire_vport->num = WIRE_PORT;
+ wire_vport->icm_address_rx = esw_caps->uplink_icm_address_rx;
+ wire_vport->icm_address_tx = esw_caps->uplink_icm_address_tx;
+ wire_vport->vport_gvmi = 0;
+ wire_vport->vhca_gvmi = dmn->info.caps.gvmi;
+
+ return 0;
+}
+
+static int dr_domain_query_fdb_caps(struct mlx5_core_dev *mdev,
+ struct mlx5dr_domain *dmn)
+{
+ int ret;
+
+ if (!dmn->info.caps.eswitch_manager)
+ return -EOPNOTSUPP;
+
+ ret = mlx5dr_cmd_query_esw_caps(mdev, &dmn->info.caps.esw_caps);
+ if (ret)
+ return ret;
+
+ dmn->info.caps.fdb_sw_owner = dmn->info.caps.esw_caps.sw_owner;
+ dmn->info.caps.esw_rx_drop_address = dmn->info.caps.esw_caps.drop_icm_address_rx;
+ dmn->info.caps.esw_tx_drop_address = dmn->info.caps.esw_caps.drop_icm_address_tx;
+
+ dmn->info.caps.vports_caps = kcalloc(dmn->info.caps.num_esw_ports,
+ sizeof(dmn->info.caps.vports_caps[0]),
+ GFP_KERNEL);
+ if (!dmn->info.caps.vports_caps)
+ return -ENOMEM;
+
+ ret = dr_domain_query_vports(dmn);
+ if (ret) {
+ mlx5dr_dbg(dmn, "Failed to query vports caps\n");
+ goto free_vports_caps;
+ }
+
+ dmn->info.caps.num_vports = dmn->info.caps.num_esw_ports - 1;
+
+ return 0;
+
+free_vports_caps:
+ kfree(dmn->info.caps.vports_caps);
+ dmn->info.caps.vports_caps = NULL;
+ return ret;
+}
+
+static int dr_domain_caps_init(struct mlx5_core_dev *mdev,
+ struct mlx5dr_domain *dmn)
+{
+ struct mlx5dr_cmd_vport_cap *vport_cap;
+ int ret;
+
+ if (MLX5_CAP_GEN(mdev, port_type) != MLX5_CAP_PORT_TYPE_ETH) {
+ mlx5dr_dbg(dmn, "Failed to allocate domain, bad link type\n");
+ return -EOPNOTSUPP;
+ }
+
+ dmn->info.caps.num_esw_ports = mlx5_eswitch_get_total_vports(mdev);
+
+ ret = mlx5dr_cmd_query_device(mdev, &dmn->info.caps);
+ if (ret)
+ return ret;
+
+ ret = dr_domain_query_fdb_caps(mdev, dmn);
+ if (ret)
+ return ret;
+
+ switch (dmn->type) {
+ case MLX5DR_DOMAIN_TYPE_NIC_RX:
+ if (!dmn->info.caps.rx_sw_owner)
+ return -ENOTSUPP;
+
+ dmn->info.supp_sw_steering = true;
+ dmn->info.rx.ste_type = MLX5DR_STE_TYPE_RX;
+ dmn->info.rx.default_icm_addr = dmn->info.caps.nic_rx_drop_address;
+ dmn->info.rx.drop_icm_addr = dmn->info.caps.nic_rx_drop_address;
+ break;
+ case MLX5DR_DOMAIN_TYPE_NIC_TX:
+ if (!dmn->info.caps.tx_sw_owner)
+ return -ENOTSUPP;
+
+ dmn->info.supp_sw_steering = true;
+ dmn->info.tx.ste_type = MLX5DR_STE_TYPE_TX;
+ dmn->info.tx.default_icm_addr = dmn->info.caps.nic_tx_allow_address;
+ dmn->info.tx.drop_icm_addr = dmn->info.caps.nic_tx_drop_address;
+ break;
+ case MLX5DR_DOMAIN_TYPE_FDB:
+ if (!dmn->info.caps.eswitch_manager)
+ return -ENOTSUPP;
+
+ if (!dmn->info.caps.fdb_sw_owner)
+ return -ENOTSUPP;
+
+ dmn->info.rx.ste_type = MLX5DR_STE_TYPE_RX;
+ dmn->info.tx.ste_type = MLX5DR_STE_TYPE_TX;
+ vport_cap = mlx5dr_get_vport_cap(&dmn->info.caps, 0);
+ if (!vport_cap) {
+ mlx5dr_dbg(dmn, "Failed to get esw manager vport\n");
+ return -ENOENT;
+ }
+
+ dmn->info.supp_sw_steering = true;
+ dmn->info.tx.default_icm_addr = vport_cap->icm_address_tx;
+ dmn->info.rx.default_icm_addr = vport_cap->icm_address_rx;
+ dmn->info.rx.drop_icm_addr = dmn->info.caps.esw_rx_drop_address;
+ dmn->info.tx.drop_icm_addr = dmn->info.caps.esw_tx_drop_address;
+ break;
+ default:
+ mlx5dr_dbg(dmn, "Invalid domain\n");
+ ret = -EINVAL;
+ break;
+ }
+
+ return ret;
+}
+
+static void dr_domain_caps_uninit(struct mlx5dr_domain *dmn)
+{
+ kfree(dmn->info.caps.vports_caps);
+}
+
+struct mlx5dr_domain *
+mlx5dr_domain_create(struct mlx5_core_dev *mdev, enum mlx5dr_domain_type type)
+{
+ struct mlx5dr_domain *dmn;
+ int ret;
+
+ if (type > MLX5DR_DOMAIN_TYPE_FDB)
+ return NULL;
+
+ dmn = kzalloc(sizeof(*dmn), GFP_KERNEL);
+ if (!dmn)
+ return NULL;
+
+ dmn->mdev = mdev;
+ dmn->type = type;
+ refcount_set(&dmn->refcount, 1);
+ mutex_init(&dmn->mutex);
+
+ if (dr_domain_caps_init(mdev, dmn)) {
+ mlx5dr_dbg(dmn, "Failed init domain, no caps\n");
+ goto free_domain;
+ }
+
+ dmn->info.max_log_action_icm_sz = DR_CHUNK_SIZE_4K;
+ dmn->info.max_log_sw_icm_sz = min_t(u32, DR_CHUNK_SIZE_1024K,
+ dmn->info.caps.log_icm_size);
+
+ if (!dmn->info.supp_sw_steering) {
+ mlx5dr_err(dmn, "SW steering not supported for %s\n",
+ dev_name(mdev->device));
+ goto uninit_caps;
+ }
+
+ /* Allocate resources */
+ ret = dr_domain_init_resources(dmn);
+ if (ret) {
+ mlx5dr_err(dmn, "Failed init domain resources for %s\n",
+ dev_name(mdev->device));
+ goto uninit_caps;
+ }
+
+ ret = dr_domain_init_cache(dmn);
+ if (ret) {
+ mlx5dr_err(dmn, "Failed initialize domain cache\n");
+ goto uninit_resourses;
+ }
+
+ /* Init CRC table for htbl CRC calculation */
+ mlx5dr_crc32_init_table();
+
+ return dmn;
+
+uninit_resourses:
+ dr_domain_uninit_resources(dmn);
+uninit_caps:
+ dr_domain_caps_uninit(dmn);
+free_domain:
+ kfree(dmn);
+ return NULL;
+}
+
+/* Assure synchronization of the device steering tables with updates made by SW
+ * insertion.
+ */
+int mlx5dr_domain_sync(struct mlx5dr_domain *dmn, u32 flags)
+{
+ int ret = 0;
+
+ if (flags & MLX5DR_DOMAIN_SYNC_FLAGS_SW) {
+ mutex_lock(&dmn->mutex);
+ ret = mlx5dr_send_ring_force_drain(dmn);
+ mutex_unlock(&dmn->mutex);
+ if (ret)
+ return ret;
+ }
+
+ if (flags & MLX5DR_DOMAIN_SYNC_FLAGS_HW)
+ ret = mlx5dr_cmd_sync_steering(dmn->mdev);
+
+ return ret;
+}
+
+int mlx5dr_domain_destroy(struct mlx5dr_domain *dmn)
+{
+ if (refcount_read(&dmn->refcount) > 1)
+ return -EBUSY;
+
+ /* make sure resources are not used by the hardware */
+ mlx5dr_cmd_sync_steering(dmn->mdev);
+ dr_domain_uninit_cache(dmn);
+ dr_domain_uninit_resources(dmn);
+ dr_domain_caps_uninit(dmn);
+ mutex_destroy(&dmn->mutex);
+ kfree(dmn);
+ return 0;
+}
+
+void mlx5dr_domain_set_peer(struct mlx5dr_domain *dmn,
+ struct mlx5dr_domain *peer_dmn)
+{
+ mutex_lock(&dmn->mutex);
+
+ if (dmn->peer_dmn)
+ refcount_dec(&dmn->peer_dmn->refcount);
+
+ dmn->peer_dmn = peer_dmn;
+
+ if (dmn->peer_dmn)
+ refcount_inc(&dmn->peer_dmn->refcount);
+
+ mutex_unlock(&dmn->mutex);
+}
--
2.21.0
^ permalink raw reply related
* [net-next V2 08/18] net/mlx5: DR, Expose steering table functionality
From: Saeed Mahameed @ 2019-09-03 20:04 UTC (permalink / raw)
To: David S. Miller
Cc: netdev@vger.kernel.org, Alex Vesker, Erez Shitrit, Mark Bloch,
Saeed Mahameed
In-Reply-To: <20190903200409.14406-1-saeedm@mellanox.com>
From: Alex Vesker <valex@mellanox.com>
Tables are objects which are used for storing matchers, each table
belongs to a domain and defined by the domain type. When a packet
reaches the table it is being processed by each of its matchers until a
successful match. Tables can hold multiple matchers ordered by matcher
priority. Each table has a level.
Signed-off-by: Alex Vesker <valex@mellanox.com>
Reviewed-by: Erez Shitrit <erezsh@mellanox.com>
Reviewed-by: Mark Bloch <markb@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
.../mellanox/mlx5/core/steering/dr_table.c | 294 ++++++++++++++++++
1 file changed, 294 insertions(+)
create mode 100644 drivers/net/ethernet/mellanox/mlx5/core/steering/dr_table.c
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_table.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_table.c
new file mode 100644
index 000000000000..e178d8d3dbc9
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_table.c
@@ -0,0 +1,294 @@
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+/* Copyright (c) 2019 Mellanox Technologies. */
+
+#include "dr_types.h"
+
+int mlx5dr_table_set_miss_action(struct mlx5dr_table *tbl,
+ struct mlx5dr_action *action)
+{
+ struct mlx5dr_matcher *last_matcher = NULL;
+ struct mlx5dr_htbl_connect_info info;
+ struct mlx5dr_ste_htbl *last_htbl;
+ int ret;
+
+ if (action && action->action_type != DR_ACTION_TYP_FT)
+ return -EOPNOTSUPP;
+
+ mutex_lock(&tbl->dmn->mutex);
+
+ if (!list_empty(&tbl->matcher_list))
+ last_matcher = list_last_entry(&tbl->matcher_list,
+ struct mlx5dr_matcher,
+ matcher_list);
+
+ if (tbl->dmn->type == MLX5DR_DOMAIN_TYPE_NIC_RX ||
+ tbl->dmn->type == MLX5DR_DOMAIN_TYPE_FDB) {
+ if (last_matcher)
+ last_htbl = last_matcher->rx.e_anchor;
+ else
+ last_htbl = tbl->rx.s_anchor;
+
+ tbl->rx.default_icm_addr = action ?
+ action->dest_tbl.tbl->rx.s_anchor->chunk->icm_addr :
+ tbl->rx.nic_dmn->default_icm_addr;
+
+ info.type = CONNECT_MISS;
+ info.miss_icm_addr = tbl->rx.default_icm_addr;
+
+ ret = mlx5dr_ste_htbl_init_and_postsend(tbl->dmn,
+ tbl->rx.nic_dmn,
+ last_htbl,
+ &info, true);
+ if (ret) {
+ mlx5dr_dbg(tbl->dmn, "Failed to set RX miss action, ret %d\n", ret);
+ goto out;
+ }
+ }
+
+ if (tbl->dmn->type == MLX5DR_DOMAIN_TYPE_NIC_TX ||
+ tbl->dmn->type == MLX5DR_DOMAIN_TYPE_FDB) {
+ if (last_matcher)
+ last_htbl = last_matcher->tx.e_anchor;
+ else
+ last_htbl = tbl->tx.s_anchor;
+
+ tbl->tx.default_icm_addr = action ?
+ action->dest_tbl.tbl->tx.s_anchor->chunk->icm_addr :
+ tbl->tx.nic_dmn->default_icm_addr;
+
+ info.type = CONNECT_MISS;
+ info.miss_icm_addr = tbl->tx.default_icm_addr;
+
+ ret = mlx5dr_ste_htbl_init_and_postsend(tbl->dmn,
+ tbl->tx.nic_dmn,
+ last_htbl, &info, true);
+ if (ret) {
+ mlx5dr_dbg(tbl->dmn, "Failed to set TX miss action, ret %d\n", ret);
+ goto out;
+ }
+ }
+
+ /* Release old action */
+ if (tbl->miss_action)
+ refcount_dec(&tbl->miss_action->refcount);
+
+ /* Set new miss action */
+ tbl->miss_action = action;
+ if (tbl->miss_action)
+ refcount_inc(&action->refcount);
+
+out:
+ mutex_unlock(&tbl->dmn->mutex);
+ return ret;
+}
+
+static void dr_table_uninit_nic(struct mlx5dr_table_rx_tx *nic_tbl)
+{
+ mlx5dr_htbl_put(nic_tbl->s_anchor);
+}
+
+static void dr_table_uninit_fdb(struct mlx5dr_table *tbl)
+{
+ dr_table_uninit_nic(&tbl->rx);
+ dr_table_uninit_nic(&tbl->tx);
+}
+
+static void dr_table_uninit(struct mlx5dr_table *tbl)
+{
+ mutex_lock(&tbl->dmn->mutex);
+
+ switch (tbl->dmn->type) {
+ case MLX5DR_DOMAIN_TYPE_NIC_RX:
+ dr_table_uninit_nic(&tbl->rx);
+ break;
+ case MLX5DR_DOMAIN_TYPE_NIC_TX:
+ dr_table_uninit_nic(&tbl->tx);
+ break;
+ case MLX5DR_DOMAIN_TYPE_FDB:
+ dr_table_uninit_fdb(tbl);
+ break;
+ default:
+ WARN_ON(true);
+ break;
+ }
+
+ mutex_unlock(&tbl->dmn->mutex);
+}
+
+static int dr_table_init_nic(struct mlx5dr_domain *dmn,
+ struct mlx5dr_table_rx_tx *nic_tbl)
+{
+ struct mlx5dr_domain_rx_tx *nic_dmn = nic_tbl->nic_dmn;
+ struct mlx5dr_htbl_connect_info info;
+ int ret;
+
+ nic_tbl->default_icm_addr = nic_dmn->default_icm_addr;
+
+ nic_tbl->s_anchor = mlx5dr_ste_htbl_alloc(dmn->ste_icm_pool,
+ DR_CHUNK_SIZE_1,
+ MLX5DR_STE_LU_TYPE_DONT_CARE,
+ 0);
+ if (!nic_tbl->s_anchor)
+ return -ENOMEM;
+
+ info.type = CONNECT_MISS;
+ info.miss_icm_addr = nic_dmn->default_icm_addr;
+ ret = mlx5dr_ste_htbl_init_and_postsend(dmn, nic_dmn,
+ nic_tbl->s_anchor,
+ &info, true);
+ if (ret)
+ goto free_s_anchor;
+
+ mlx5dr_htbl_get(nic_tbl->s_anchor);
+
+ return 0;
+
+free_s_anchor:
+ mlx5dr_ste_htbl_free(nic_tbl->s_anchor);
+ return ret;
+}
+
+static int dr_table_init_fdb(struct mlx5dr_table *tbl)
+{
+ int ret;
+
+ ret = dr_table_init_nic(tbl->dmn, &tbl->rx);
+ if (ret)
+ return ret;
+
+ ret = dr_table_init_nic(tbl->dmn, &tbl->tx);
+ if (ret)
+ goto destroy_rx;
+
+ return 0;
+
+destroy_rx:
+ dr_table_uninit_nic(&tbl->rx);
+ return ret;
+}
+
+static int dr_table_init(struct mlx5dr_table *tbl)
+{
+ int ret = 0;
+
+ INIT_LIST_HEAD(&tbl->matcher_list);
+
+ mutex_lock(&tbl->dmn->mutex);
+
+ switch (tbl->dmn->type) {
+ case MLX5DR_DOMAIN_TYPE_NIC_RX:
+ tbl->table_type = MLX5_FLOW_TABLE_TYPE_NIC_RX;
+ tbl->rx.nic_dmn = &tbl->dmn->info.rx;
+ ret = dr_table_init_nic(tbl->dmn, &tbl->rx);
+ break;
+ case MLX5DR_DOMAIN_TYPE_NIC_TX:
+ tbl->table_type = MLX5_FLOW_TABLE_TYPE_NIC_TX;
+ tbl->tx.nic_dmn = &tbl->dmn->info.tx;
+ ret = dr_table_init_nic(tbl->dmn, &tbl->tx);
+ break;
+ case MLX5DR_DOMAIN_TYPE_FDB:
+ tbl->table_type = MLX5_FLOW_TABLE_TYPE_FDB;
+ tbl->rx.nic_dmn = &tbl->dmn->info.rx;
+ tbl->tx.nic_dmn = &tbl->dmn->info.tx;
+ ret = dr_table_init_fdb(tbl);
+ break;
+ default:
+ WARN_ON(true);
+ break;
+ }
+
+ mutex_unlock(&tbl->dmn->mutex);
+
+ return ret;
+}
+
+static int dr_table_destroy_sw_owned_tbl(struct mlx5dr_table *tbl)
+{
+ return mlx5dr_cmd_destroy_flow_table(tbl->dmn->mdev,
+ tbl->table_id,
+ tbl->table_type);
+}
+
+static int dr_table_create_sw_owned_tbl(struct mlx5dr_table *tbl)
+{
+ u64 icm_addr_rx = 0;
+ u64 icm_addr_tx = 0;
+ int ret;
+
+ if (tbl->rx.s_anchor)
+ icm_addr_rx = tbl->rx.s_anchor->chunk->icm_addr;
+
+ if (tbl->tx.s_anchor)
+ icm_addr_tx = tbl->tx.s_anchor->chunk->icm_addr;
+
+ ret = mlx5dr_cmd_create_flow_table(tbl->dmn->mdev,
+ tbl->table_type,
+ icm_addr_rx,
+ icm_addr_tx,
+ tbl->dmn->info.caps.max_ft_level - 1,
+ true, false, NULL,
+ &tbl->table_id);
+
+ return ret;
+}
+
+struct mlx5dr_table *mlx5dr_table_create(struct mlx5dr_domain *dmn, u32 level)
+{
+ struct mlx5dr_table *tbl;
+ int ret;
+
+ refcount_inc(&dmn->refcount);
+
+ tbl = kzalloc(sizeof(*tbl), GFP_KERNEL);
+ if (!tbl)
+ goto dec_ref;
+
+ tbl->dmn = dmn;
+ tbl->level = level;
+ refcount_set(&tbl->refcount, 1);
+
+ ret = dr_table_init(tbl);
+ if (ret)
+ goto free_tbl;
+
+ ret = dr_table_create_sw_owned_tbl(tbl);
+ if (ret)
+ goto uninit_tbl;
+
+ return tbl;
+
+uninit_tbl:
+ dr_table_uninit(tbl);
+free_tbl:
+ kfree(tbl);
+dec_ref:
+ refcount_dec(&dmn->refcount);
+ return NULL;
+}
+
+int mlx5dr_table_destroy(struct mlx5dr_table *tbl)
+{
+ int ret;
+
+ if (refcount_read(&tbl->refcount) > 1)
+ return -EBUSY;
+
+ ret = dr_table_destroy_sw_owned_tbl(tbl);
+ if (ret)
+ return ret;
+
+ dr_table_uninit(tbl);
+
+ if (tbl->miss_action)
+ refcount_dec(&tbl->miss_action->refcount);
+
+ refcount_dec(&tbl->dmn->refcount);
+ kfree(tbl);
+
+ return ret;
+}
+
+u32 mlx5dr_table_get_id(struct mlx5dr_table *tbl)
+{
+ return tbl->table_id;
+}
--
2.21.0
^ permalink raw reply related
* [net-next V2 06/18] net/mlx5: DR, Add Steering entry (STE) utilities
From: Saeed Mahameed @ 2019-09-03 20:04 UTC (permalink / raw)
To: David S. Miller
Cc: netdev@vger.kernel.org, Alex Vesker, Erez Shitrit, Mark Bloch,
Saeed Mahameed
In-Reply-To: <20190903200409.14406-1-saeedm@mellanox.com>
From: Alex Vesker <valex@mellanox.com>
Steering Entry (STE) object is the basic building block of the steering
map. There are several types of STEs. Each rule can be constructed of
multiple STEs. Each STE dictates which fields of the packet's header are
being matched as well as the information about the next step in map (hit
and miss pointers). The hardware gets a packet and tries to match it
against the STEs, going to either the hit pointer or the miss pointer.
This file handles the STE operations.
Signed-off-by: Alex Vesker <valex@mellanox.com>
Signed-off-by: Erez Shitrit <erezsh@mellanox.com>
Reviewed-by: Mark Bloch <markb@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
.../mellanox/mlx5/core/steering/dr_crc32.c | 98 +
.../mellanox/mlx5/core/steering/dr_ste.c | 2308 +++++++++++++++++
2 files changed, 2406 insertions(+)
create mode 100644 drivers/net/ethernet/mellanox/mlx5/core/steering/dr_crc32.c
create mode 100644 drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste.c
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_crc32.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_crc32.c
new file mode 100644
index 000000000000..9e2eccbb1eb8
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_crc32.c
@@ -0,0 +1,98 @@
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+/* Copyright (c) 2019 Mellanox Technologies. */
+
+/* Copyright (c) 2011-2015 Stephan Brumme. All rights reserved.
+ * Slicing-by-16 contributed by Bulat Ziganshin
+ *
+ * This software is provided 'as-is', without any express or implied warranty.
+ * In no event will the author be held liable for any damages arising from the
+ * of this software.
+ *
+ * Permission is granted to anyone to use this software for any purpose,
+ * including commercial applications, and to alter it and redistribute it
+ * freely, subject to the following restrictions:
+ *
+ * 1. The origin of this software must not be misrepresented; you must not
+ * claim that you wrote the original software.
+ * 2. If you use this software in a product, an acknowledgment in the product
+ * documentation would be appreciated but is not required.
+ * 3. Altered source versions must be plainly marked as such, and must not be
+ * misrepresented as being the original software.
+ *
+ * Taken from http://create.stephan-brumme.com/crc32/ and adapted.
+ */
+
+#include "dr_types.h"
+
+#define DR_STE_CRC_POLY 0xEDB88320L
+
+static u32 dr_ste_crc_tab32[8][256];
+
+static void dr_crc32_calc_lookup_entry(u32 (*tbl)[256], u8 i, u8 j)
+{
+ tbl[i][j] = (tbl[i - 1][j] >> 8) ^ tbl[0][tbl[i - 1][j] & 0xff];
+}
+
+void mlx5dr_crc32_init_table(void)
+{
+ u32 crc, i, j;
+
+ for (i = 0; i < 256; i++) {
+ crc = i;
+ for (j = 0; j < 8; j++) {
+ if (crc & 0x00000001L)
+ crc = (crc >> 1) ^ DR_STE_CRC_POLY;
+ else
+ crc = crc >> 1;
+ }
+ dr_ste_crc_tab32[0][i] = crc;
+ }
+
+ /* Init CRC lookup tables according to crc_slice_8 algorithm */
+ for (i = 0; i < 256; i++) {
+ dr_crc32_calc_lookup_entry(dr_ste_crc_tab32, 1, i);
+ dr_crc32_calc_lookup_entry(dr_ste_crc_tab32, 2, i);
+ dr_crc32_calc_lookup_entry(dr_ste_crc_tab32, 3, i);
+ dr_crc32_calc_lookup_entry(dr_ste_crc_tab32, 4, i);
+ dr_crc32_calc_lookup_entry(dr_ste_crc_tab32, 5, i);
+ dr_crc32_calc_lookup_entry(dr_ste_crc_tab32, 6, i);
+ dr_crc32_calc_lookup_entry(dr_ste_crc_tab32, 7, i);
+ }
+}
+
+/* Compute CRC32 (Slicing-by-8 algorithm) */
+u32 mlx5dr_crc32_slice8_calc(const void *input_data, size_t length)
+{
+ const u32 *curr = (const u32 *)input_data;
+ const u8 *curr_char;
+ u32 crc = 0, one, two;
+
+ if (!input_data)
+ return 0;
+
+ /* Process eight bytes at once (Slicing-by-8) */
+ while (length >= 8) {
+ one = *curr++ ^ crc;
+ two = *curr++;
+
+ crc = dr_ste_crc_tab32[0][(two >> 24) & 0xff]
+ ^ dr_ste_crc_tab32[1][(two >> 16) & 0xff]
+ ^ dr_ste_crc_tab32[2][(two >> 8) & 0xff]
+ ^ dr_ste_crc_tab32[3][two & 0xff]
+ ^ dr_ste_crc_tab32[4][(one >> 24) & 0xff]
+ ^ dr_ste_crc_tab32[5][(one >> 16) & 0xff]
+ ^ dr_ste_crc_tab32[6][(one >> 8) & 0xff]
+ ^ dr_ste_crc_tab32[7][one & 0xff];
+
+ length -= 8;
+ }
+
+ curr_char = (const u8 *)curr;
+ /* Remaining 1 to 7 bytes (standard algorithm) */
+ while (length-- != 0)
+ crc = (crc >> 8) ^ dr_ste_crc_tab32[0][(crc & 0xff)
+ ^ *curr_char++];
+
+ return ((crc >> 24) & 0xff) | ((crc << 8) & 0xff0000) |
+ ((crc >> 8) & 0xff00) | ((crc << 24) & 0xff000000);
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste.c
new file mode 100644
index 000000000000..6b0af64536d8
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste.c
@@ -0,0 +1,2308 @@
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+/* Copyright (c) 2019 Mellanox Technologies. */
+
+#include <linux/types.h>
+#include "dr_types.h"
+
+#define DR_STE_CRC_POLY 0xEDB88320L
+#define STE_IPV4 0x1
+#define STE_IPV6 0x2
+#define STE_TCP 0x1
+#define STE_UDP 0x2
+#define STE_SPI 0x3
+#define IP_VERSION_IPV4 0x4
+#define IP_VERSION_IPV6 0x6
+#define STE_SVLAN 0x1
+#define STE_CVLAN 0x2
+
+#define DR_STE_ENABLE_FLOW_TAG BIT(31)
+
+/* Set to STE a specific value using DR_STE_SET */
+#define DR_STE_SET_VAL(lookup_type, tag, t_fname, spec, s_fname, value) do { \
+ if ((spec)->s_fname) { \
+ MLX5_SET(ste_##lookup_type, tag, t_fname, value); \
+ (spec)->s_fname = 0; \
+ } \
+} while (0)
+
+/* Set to STE spec->s_fname to tag->t_fname */
+#define DR_STE_SET_TAG(lookup_type, tag, t_fname, spec, s_fname) \
+ DR_STE_SET_VAL(lookup_type, tag, t_fname, spec, s_fname, spec->s_fname)
+
+/* Set to STE -1 to bit_mask->bm_fname and set spec->s_fname as used */
+#define DR_STE_SET_MASK(lookup_type, bit_mask, bm_fname, spec, s_fname) \
+ DR_STE_SET_VAL(lookup_type, bit_mask, bm_fname, spec, s_fname, -1)
+
+/* Set to STE spec->s_fname to bit_mask->bm_fname and set spec->s_fname as used */
+#define DR_STE_SET_MASK_V(lookup_type, bit_mask, bm_fname, spec, s_fname) \
+ DR_STE_SET_VAL(lookup_type, bit_mask, bm_fname, spec, s_fname, (spec)->s_fname)
+
+#define DR_STE_SET_TCP_FLAGS(lookup_type, tag, spec) do { \
+ MLX5_SET(ste_##lookup_type, tag, tcp_ns, !!((spec)->tcp_flags & (1 << 8))); \
+ MLX5_SET(ste_##lookup_type, tag, tcp_cwr, !!((spec)->tcp_flags & (1 << 7))); \
+ MLX5_SET(ste_##lookup_type, tag, tcp_ece, !!((spec)->tcp_flags & (1 << 6))); \
+ MLX5_SET(ste_##lookup_type, tag, tcp_urg, !!((spec)->tcp_flags & (1 << 5))); \
+ MLX5_SET(ste_##lookup_type, tag, tcp_ack, !!((spec)->tcp_flags & (1 << 4))); \
+ MLX5_SET(ste_##lookup_type, tag, tcp_psh, !!((spec)->tcp_flags & (1 << 3))); \
+ MLX5_SET(ste_##lookup_type, tag, tcp_rst, !!((spec)->tcp_flags & (1 << 2))); \
+ MLX5_SET(ste_##lookup_type, tag, tcp_syn, !!((spec)->tcp_flags & (1 << 1))); \
+ MLX5_SET(ste_##lookup_type, tag, tcp_fin, !!((spec)->tcp_flags & (1 << 0))); \
+} while (0)
+
+#define DR_STE_SET_MPLS_MASK(lookup_type, mask, in_out, bit_mask) do { \
+ DR_STE_SET_MASK_V(lookup_type, mask, mpls0_label, mask, \
+ in_out##_first_mpls_label);\
+ DR_STE_SET_MASK_V(lookup_type, mask, mpls0_s_bos, mask, \
+ in_out##_first_mpls_s_bos); \
+ DR_STE_SET_MASK_V(lookup_type, mask, mpls0_exp, mask, \
+ in_out##_first_mpls_exp); \
+ DR_STE_SET_MASK_V(lookup_type, mask, mpls0_ttl, mask, \
+ in_out##_first_mpls_ttl); \
+} while (0)
+
+#define DR_STE_SET_MPLS_TAG(lookup_type, mask, in_out, tag) do { \
+ DR_STE_SET_TAG(lookup_type, tag, mpls0_label, mask, \
+ in_out##_first_mpls_label);\
+ DR_STE_SET_TAG(lookup_type, tag, mpls0_s_bos, mask, \
+ in_out##_first_mpls_s_bos); \
+ DR_STE_SET_TAG(lookup_type, tag, mpls0_exp, mask, \
+ in_out##_first_mpls_exp); \
+ DR_STE_SET_TAG(lookup_type, tag, mpls0_ttl, mask, \
+ in_out##_first_mpls_ttl); \
+} while (0)
+
+#define DR_STE_IS_OUTER_MPLS_OVER_GRE_SET(_misc) (\
+ (_misc)->outer_first_mpls_over_gre_label || \
+ (_misc)->outer_first_mpls_over_gre_exp || \
+ (_misc)->outer_first_mpls_over_gre_s_bos || \
+ (_misc)->outer_first_mpls_over_gre_ttl)
+#define DR_STE_IS_OUTER_MPLS_OVER_UDP_SET(_misc) (\
+ (_misc)->outer_first_mpls_over_udp_label || \
+ (_misc)->outer_first_mpls_over_udp_exp || \
+ (_misc)->outer_first_mpls_over_udp_s_bos || \
+ (_misc)->outer_first_mpls_over_udp_ttl)
+
+#define DR_STE_CALC_LU_TYPE(lookup_type, rx, inner) \
+ ((inner) ? MLX5DR_STE_LU_TYPE_##lookup_type##_I : \
+ (rx) ? MLX5DR_STE_LU_TYPE_##lookup_type##_D : \
+ MLX5DR_STE_LU_TYPE_##lookup_type##_O)
+
+enum dr_ste_tunl_action {
+ DR_STE_TUNL_ACTION_NONE = 0,
+ DR_STE_TUNL_ACTION_ENABLE = 1,
+ DR_STE_TUNL_ACTION_DECAP = 2,
+ DR_STE_TUNL_ACTION_L3_DECAP = 3,
+ DR_STE_TUNL_ACTION_POP_VLAN = 4,
+};
+
+enum dr_ste_action_type {
+ DR_STE_ACTION_TYPE_PUSH_VLAN = 1,
+ DR_STE_ACTION_TYPE_ENCAP_L3 = 3,
+ DR_STE_ACTION_TYPE_ENCAP = 4,
+};
+
+struct dr_hw_ste_format {
+ u8 ctrl[DR_STE_SIZE_CTRL];
+ u8 tag[DR_STE_SIZE_TAG];
+ u8 mask[DR_STE_SIZE_MASK];
+};
+
+u32 mlx5dr_ste_calc_hash_index(u8 *hw_ste_p, struct mlx5dr_ste_htbl *htbl)
+{
+ struct dr_hw_ste_format *hw_ste = (struct dr_hw_ste_format *)hw_ste_p;
+ u8 masked[DR_STE_SIZE_TAG] = {};
+ u32 crc32, index;
+ u16 bit;
+ int i;
+
+ /* Don't calculate CRC if the result is predicted */
+ if (htbl->chunk->num_of_entries == 1 || htbl->byte_mask == 0)
+ return 0;
+
+ /* Mask tag using byte mask, bit per byte */
+ bit = 1 << (DR_STE_SIZE_TAG - 1);
+ for (i = 0; i < DR_STE_SIZE_TAG; i++) {
+ if (htbl->byte_mask & bit)
+ masked[i] = hw_ste->tag[i];
+
+ bit = bit >> 1;
+ }
+
+ crc32 = mlx5dr_crc32_slice8_calc(masked, DR_STE_SIZE_TAG);
+ index = crc32 & (htbl->chunk->num_of_entries - 1);
+
+ return index;
+}
+
+static u16 dr_ste_conv_bit_to_byte_mask(u8 *bit_mask)
+{
+ u16 byte_mask = 0;
+ int i;
+
+ for (i = 0; i < DR_STE_SIZE_MASK; i++) {
+ byte_mask = byte_mask << 1;
+ if (bit_mask[i] == 0xff)
+ byte_mask |= 1;
+ }
+ return byte_mask;
+}
+
+void mlx5dr_ste_set_bit_mask(u8 *hw_ste_p, u8 *bit_mask)
+{
+ struct dr_hw_ste_format *hw_ste = (struct dr_hw_ste_format *)hw_ste_p;
+
+ memcpy(hw_ste->mask, bit_mask, DR_STE_SIZE_MASK);
+}
+
+void mlx5dr_ste_rx_set_flow_tag(u8 *hw_ste_p, u32 flow_tag)
+{
+ MLX5_SET(ste_rx_steering_mult, hw_ste_p, qp_list_pointer,
+ DR_STE_ENABLE_FLOW_TAG | flow_tag);
+}
+
+void mlx5dr_ste_set_counter_id(u8 *hw_ste_p, u32 ctr_id)
+{
+ /* This can be used for both rx_steering_mult and for sx_transmit */
+ MLX5_SET(ste_rx_steering_mult, hw_ste_p, counter_trigger_15_0, ctr_id);
+ MLX5_SET(ste_rx_steering_mult, hw_ste_p, counter_trigger_23_16, ctr_id >> 16);
+}
+
+void mlx5dr_ste_set_go_back_bit(u8 *hw_ste_p)
+{
+ MLX5_SET(ste_sx_transmit, hw_ste_p, go_back, 1);
+}
+
+void mlx5dr_ste_set_tx_push_vlan(u8 *hw_ste_p, u32 vlan_hdr,
+ bool go_back)
+{
+ MLX5_SET(ste_sx_transmit, hw_ste_p, action_type,
+ DR_STE_ACTION_TYPE_PUSH_VLAN);
+ MLX5_SET(ste_sx_transmit, hw_ste_p, encap_pointer_vlan_data, vlan_hdr);
+ /* Due to HW limitation we need to set this bit, otherwise reforamt +
+ * push vlan will not work.
+ */
+ if (go_back)
+ mlx5dr_ste_set_go_back_bit(hw_ste_p);
+}
+
+void mlx5dr_ste_set_tx_encap(void *hw_ste_p, u32 reformat_id, int size, bool encap_l3)
+{
+ MLX5_SET(ste_sx_transmit, hw_ste_p, action_type,
+ encap_l3 ? DR_STE_ACTION_TYPE_ENCAP_L3 : DR_STE_ACTION_TYPE_ENCAP);
+ /* The hardware expects here size in words (2 byte) */
+ MLX5_SET(ste_sx_transmit, hw_ste_p, action_description, size / 2);
+ MLX5_SET(ste_sx_transmit, hw_ste_p, encap_pointer_vlan_data, reformat_id);
+}
+
+void mlx5dr_ste_set_rx_decap(u8 *hw_ste_p)
+{
+ MLX5_SET(ste_rx_steering_mult, hw_ste_p, tunneling_action,
+ DR_STE_TUNL_ACTION_DECAP);
+}
+
+void mlx5dr_ste_set_rx_pop_vlan(u8 *hw_ste_p)
+{
+ MLX5_SET(ste_rx_steering_mult, hw_ste_p, tunneling_action,
+ DR_STE_TUNL_ACTION_POP_VLAN);
+}
+
+void mlx5dr_ste_set_rx_decap_l3(u8 *hw_ste_p, bool vlan)
+{
+ MLX5_SET(ste_rx_steering_mult, hw_ste_p, tunneling_action,
+ DR_STE_TUNL_ACTION_L3_DECAP);
+ MLX5_SET(ste_modify_packet, hw_ste_p, action_description, vlan ? 1 : 0);
+}
+
+void mlx5dr_ste_set_entry_type(u8 *hw_ste_p, u8 entry_type)
+{
+ MLX5_SET(ste_general, hw_ste_p, entry_type, entry_type);
+}
+
+u8 mlx5dr_ste_get_entry_type(u8 *hw_ste_p)
+{
+ return MLX5_GET(ste_general, hw_ste_p, entry_type);
+}
+
+void mlx5dr_ste_set_rewrite_actions(u8 *hw_ste_p, u16 num_of_actions,
+ u32 re_write_index)
+{
+ MLX5_SET(ste_modify_packet, hw_ste_p, number_of_re_write_actions,
+ num_of_actions);
+ MLX5_SET(ste_modify_packet, hw_ste_p, header_re_write_actions_pointer,
+ re_write_index);
+}
+
+void mlx5dr_ste_set_hit_gvmi(u8 *hw_ste_p, u16 gvmi)
+{
+ MLX5_SET(ste_general, hw_ste_p, next_table_base_63_48, gvmi);
+}
+
+void mlx5dr_ste_init(u8 *hw_ste_p, u8 lu_type, u8 entry_type,
+ u16 gvmi)
+{
+ MLX5_SET(ste_general, hw_ste_p, entry_type, entry_type);
+ MLX5_SET(ste_general, hw_ste_p, entry_sub_type, lu_type);
+ MLX5_SET(ste_general, hw_ste_p, next_lu_type, MLX5DR_STE_LU_TYPE_DONT_CARE);
+
+ /* Set GVMI once, this is the same for RX/TX
+ * bits 63_48 of next table base / miss address encode the next GVMI
+ */
+ MLX5_SET(ste_rx_steering_mult, hw_ste_p, gvmi, gvmi);
+ MLX5_SET(ste_rx_steering_mult, hw_ste_p, next_table_base_63_48, gvmi);
+ MLX5_SET(ste_rx_steering_mult, hw_ste_p, miss_address_63_48, gvmi);
+}
+
+static void dr_ste_set_always_hit(struct dr_hw_ste_format *hw_ste)
+{
+ memset(&hw_ste->tag, 0, sizeof(hw_ste->tag));
+ memset(&hw_ste->mask, 0, sizeof(hw_ste->mask));
+}
+
+static void dr_ste_set_always_miss(struct dr_hw_ste_format *hw_ste)
+{
+ hw_ste->tag[0] = 0xdc;
+ hw_ste->mask[0] = 0;
+}
+
+u64 mlx5dr_ste_get_miss_addr(u8 *hw_ste)
+{
+ u64 index =
+ (MLX5_GET(ste_rx_steering_mult, hw_ste, miss_address_31_6) |
+ MLX5_GET(ste_rx_steering_mult, hw_ste, miss_address_39_32) << 26);
+
+ return index << 6;
+}
+
+void mlx5dr_ste_set_hit_addr(u8 *hw_ste, u64 icm_addr, u32 ht_size)
+{
+ u64 index = (icm_addr >> 5) | ht_size;
+
+ MLX5_SET(ste_general, hw_ste, next_table_base_39_32_size, index >> 27);
+ MLX5_SET(ste_general, hw_ste, next_table_base_31_5_size, index);
+}
+
+u64 mlx5dr_ste_get_icm_addr(struct mlx5dr_ste *ste)
+{
+ u32 index = ste - ste->htbl->ste_arr;
+
+ return ste->htbl->chunk->icm_addr + DR_STE_SIZE * index;
+}
+
+u64 mlx5dr_ste_get_mr_addr(struct mlx5dr_ste *ste)
+{
+ u32 index = ste - ste->htbl->ste_arr;
+
+ return ste->htbl->chunk->mr_addr + DR_STE_SIZE * index;
+}
+
+struct list_head *mlx5dr_ste_get_miss_list(struct mlx5dr_ste *ste)
+{
+ u32 index = ste - ste->htbl->ste_arr;
+
+ return &ste->htbl->miss_list[index];
+}
+
+static void dr_ste_always_hit_htbl(struct mlx5dr_ste *ste,
+ struct mlx5dr_ste_htbl *next_htbl)
+{
+ struct mlx5dr_icm_chunk *chunk = next_htbl->chunk;
+ u8 *hw_ste = ste->hw_ste;
+
+ MLX5_SET(ste_general, hw_ste, byte_mask, next_htbl->byte_mask);
+ MLX5_SET(ste_general, hw_ste, next_lu_type, next_htbl->lu_type);
+ mlx5dr_ste_set_hit_addr(hw_ste, chunk->icm_addr, chunk->num_of_entries);
+
+ dr_ste_set_always_hit((struct dr_hw_ste_format *)ste->hw_ste);
+}
+
+bool mlx5dr_ste_is_last_in_rule(struct mlx5dr_matcher_rx_tx *nic_matcher,
+ u8 ste_location)
+{
+ return ste_location == nic_matcher->num_of_builders;
+}
+
+/* Replace relevant fields, except of:
+ * htbl - keep the origin htbl
+ * miss_list + list - already took the src from the list.
+ * icm_addr/mr_addr - depends on the hosting table.
+ *
+ * Before:
+ * | a | -> | b | -> | c | ->
+ *
+ * After:
+ * | a | -> | c | ->
+ * While the data that was in b copied to a.
+ */
+static void dr_ste_replace(struct mlx5dr_ste *dst, struct mlx5dr_ste *src)
+{
+ memcpy(dst->hw_ste, src->hw_ste, DR_STE_SIZE_REDUCED);
+ dst->next_htbl = src->next_htbl;
+ if (dst->next_htbl)
+ dst->next_htbl->pointing_ste = dst;
+
+ refcount_set(&dst->refcount, refcount_read(&src->refcount));
+
+ INIT_LIST_HEAD(&dst->rule_list);
+ list_splice_tail_init(&src->rule_list, &dst->rule_list);
+}
+
+/* Free ste which is the head and the only one in miss_list */
+static void
+dr_ste_remove_head_ste(struct mlx5dr_ste *ste,
+ struct mlx5dr_matcher_rx_tx *nic_matcher,
+ struct mlx5dr_ste_send_info *ste_info_head,
+ struct list_head *send_ste_list,
+ struct mlx5dr_ste_htbl *stats_tbl)
+{
+ u8 tmp_data_ste[DR_STE_SIZE] = {};
+ struct mlx5dr_ste tmp_ste = {};
+ u64 miss_addr;
+
+ tmp_ste.hw_ste = tmp_data_ste;
+
+ /* Use temp ste because dr_ste_always_miss_addr
+ * touches bit_mask area which doesn't exist at ste->hw_ste.
+ */
+ memcpy(tmp_ste.hw_ste, ste->hw_ste, DR_STE_SIZE_REDUCED);
+ miss_addr = nic_matcher->e_anchor->chunk->icm_addr;
+ mlx5dr_ste_always_miss_addr(&tmp_ste, miss_addr);
+ memcpy(ste->hw_ste, tmp_ste.hw_ste, DR_STE_SIZE_REDUCED);
+
+ list_del_init(&ste->miss_list_node);
+
+ /* Write full STE size in order to have "always_miss" */
+ mlx5dr_send_fill_and_append_ste_send_info(ste, DR_STE_SIZE,
+ 0, tmp_data_ste,
+ ste_info_head,
+ send_ste_list,
+ true /* Copy data */);
+
+ stats_tbl->ctrl.num_of_valid_entries--;
+}
+
+/* Free ste which is the head but NOT the only one in miss_list:
+ * |_ste_| --> |_next_ste_| -->|__| -->|__| -->/0
+ */
+static void
+dr_ste_replace_head_ste(struct mlx5dr_ste *ste, struct mlx5dr_ste *next_ste,
+ struct mlx5dr_ste_send_info *ste_info_head,
+ struct list_head *send_ste_list,
+ struct mlx5dr_ste_htbl *stats_tbl)
+
+{
+ struct mlx5dr_ste_htbl *next_miss_htbl;
+
+ next_miss_htbl = next_ste->htbl;
+
+ /* Remove from the miss_list the next_ste before copy */
+ list_del_init(&next_ste->miss_list_node);
+
+ /* All rule-members that use next_ste should know about that */
+ mlx5dr_rule_update_rule_member(next_ste, ste);
+
+ /* Move data from next into ste */
+ dr_ste_replace(ste, next_ste);
+
+ /* Del the htbl that contains the next_ste.
+ * The origin htbl stay with the same number of entries.
+ */
+ mlx5dr_htbl_put(next_miss_htbl);
+
+ mlx5dr_send_fill_and_append_ste_send_info(ste, DR_STE_SIZE_REDUCED,
+ 0, ste->hw_ste,
+ ste_info_head,
+ send_ste_list,
+ true /* Copy data */);
+
+ stats_tbl->ctrl.num_of_collisions--;
+ stats_tbl->ctrl.num_of_valid_entries--;
+}
+
+/* Free ste that is located in the middle of the miss list:
+ * |__| -->|_prev_ste_|->|_ste_|-->|_next_ste_|
+ */
+static void dr_ste_remove_middle_ste(struct mlx5dr_ste *ste,
+ struct mlx5dr_ste_send_info *ste_info,
+ struct list_head *send_ste_list,
+ struct mlx5dr_ste_htbl *stats_tbl)
+{
+ struct mlx5dr_ste *prev_ste;
+ u64 miss_addr;
+
+ prev_ste = list_entry(mlx5dr_ste_get_miss_list(ste)->prev, struct mlx5dr_ste,
+ miss_list_node);
+ if (!prev_ste) {
+ WARN_ON(true);
+ return;
+ }
+
+ miss_addr = mlx5dr_ste_get_miss_addr(ste->hw_ste);
+ mlx5dr_ste_set_miss_addr(prev_ste->hw_ste, miss_addr);
+
+ mlx5dr_send_fill_and_append_ste_send_info(prev_ste, DR_STE_SIZE_REDUCED, 0,
+ prev_ste->hw_ste, ste_info,
+ send_ste_list, true /* Copy data*/);
+
+ list_del_init(&ste->miss_list_node);
+
+ stats_tbl->ctrl.num_of_valid_entries--;
+ stats_tbl->ctrl.num_of_collisions--;
+}
+
+void mlx5dr_ste_free(struct mlx5dr_ste *ste,
+ struct mlx5dr_matcher *matcher,
+ struct mlx5dr_matcher_rx_tx *nic_matcher)
+{
+ struct mlx5dr_ste_send_info *cur_ste_info, *tmp_ste_info;
+ struct mlx5dr_domain *dmn = matcher->tbl->dmn;
+ struct mlx5dr_ste_send_info ste_info_head;
+ struct mlx5dr_ste *next_ste, *first_ste;
+ bool put_on_origin_table = true;
+ struct mlx5dr_ste_htbl *stats_tbl;
+ LIST_HEAD(send_ste_list);
+
+ first_ste = list_entry(mlx5dr_ste_get_miss_list(ste)->next,
+ struct mlx5dr_ste, miss_list_node);
+ stats_tbl = first_ste->htbl;
+
+ /* Two options:
+ * 1. ste is head:
+ * a. head ste is the only ste in the miss list
+ * b. head ste is not the only ste in the miss-list
+ * 2. ste is not head
+ */
+ if (first_ste == ste) { /* Ste is the head */
+ struct mlx5dr_ste *last_ste;
+
+ last_ste = list_last_entry(mlx5dr_ste_get_miss_list(ste),
+ struct mlx5dr_ste, miss_list_node);
+ if (last_ste == first_ste)
+ next_ste = NULL;
+ else
+ next_ste = list_entry(ste->miss_list_node.next,
+ struct mlx5dr_ste, miss_list_node);
+
+ if (!next_ste) {
+ /* One and only entry in the list */
+ dr_ste_remove_head_ste(ste, nic_matcher,
+ &ste_info_head,
+ &send_ste_list,
+ stats_tbl);
+ } else {
+ /* First but not only entry in the list */
+ dr_ste_replace_head_ste(ste, next_ste, &ste_info_head,
+ &send_ste_list, stats_tbl);
+ put_on_origin_table = false;
+ }
+ } else { /* Ste in the middle of the list */
+ dr_ste_remove_middle_ste(ste, &ste_info_head, &send_ste_list, stats_tbl);
+ }
+
+ /* Update HW */
+ list_for_each_entry_safe(cur_ste_info, tmp_ste_info,
+ &send_ste_list, send_list) {
+ list_del(&cur_ste_info->send_list);
+ mlx5dr_send_postsend_ste(dmn, cur_ste_info->ste,
+ cur_ste_info->data, cur_ste_info->size,
+ cur_ste_info->offset);
+ }
+
+ if (put_on_origin_table)
+ mlx5dr_htbl_put(ste->htbl);
+}
+
+bool mlx5dr_ste_equal_tag(void *src, void *dst)
+{
+ struct dr_hw_ste_format *s_hw_ste = (struct dr_hw_ste_format *)src;
+ struct dr_hw_ste_format *d_hw_ste = (struct dr_hw_ste_format *)dst;
+
+ return !memcmp(s_hw_ste->tag, d_hw_ste->tag, DR_STE_SIZE_TAG);
+}
+
+void mlx5dr_ste_set_hit_addr_by_next_htbl(u8 *hw_ste,
+ struct mlx5dr_ste_htbl *next_htbl)
+{
+ struct mlx5dr_icm_chunk *chunk = next_htbl->chunk;
+
+ mlx5dr_ste_set_hit_addr(hw_ste, chunk->icm_addr, chunk->num_of_entries);
+}
+
+void mlx5dr_ste_set_miss_addr(u8 *hw_ste_p, u64 miss_addr)
+{
+ u64 index = miss_addr >> 6;
+
+ /* Miss address for TX and RX STEs located in the same offsets */
+ MLX5_SET(ste_rx_steering_mult, hw_ste_p, miss_address_39_32, index >> 26);
+ MLX5_SET(ste_rx_steering_mult, hw_ste_p, miss_address_31_6, index);
+}
+
+void mlx5dr_ste_always_miss_addr(struct mlx5dr_ste *ste, u64 miss_addr)
+{
+ u8 *hw_ste = ste->hw_ste;
+
+ MLX5_SET(ste_rx_steering_mult, hw_ste, next_lu_type, MLX5DR_STE_LU_TYPE_DONT_CARE);
+ mlx5dr_ste_set_miss_addr(hw_ste, miss_addr);
+ dr_ste_set_always_miss((struct dr_hw_ste_format *)ste->hw_ste);
+}
+
+/* The assumption here is that we don't update the ste->hw_ste if it is not
+ * used ste, so it will be all zero, checking the next_lu_type.
+ */
+bool mlx5dr_ste_is_not_valid_entry(u8 *p_hw_ste)
+{
+ struct dr_hw_ste_format *hw_ste = (struct dr_hw_ste_format *)p_hw_ste;
+
+ if (MLX5_GET(ste_general, hw_ste, next_lu_type) ==
+ MLX5DR_STE_LU_TYPE_NOP)
+ return true;
+
+ return false;
+}
+
+bool mlx5dr_ste_not_used_ste(struct mlx5dr_ste *ste)
+{
+ return !refcount_read(&ste->refcount);
+}
+
+static u16 get_bits_per_mask(u16 byte_mask)
+{
+ u16 bits = 0;
+
+ while (byte_mask) {
+ byte_mask = byte_mask & (byte_mask - 1);
+ bits++;
+ }
+
+ return bits;
+}
+
+/* Init one ste as a pattern for ste data array */
+void mlx5dr_ste_set_formatted_ste(u16 gvmi,
+ struct mlx5dr_domain_rx_tx *nic_dmn,
+ struct mlx5dr_ste_htbl *htbl,
+ u8 *formatted_ste,
+ struct mlx5dr_htbl_connect_info *connect_info)
+{
+ struct mlx5dr_ste ste = {};
+
+ mlx5dr_ste_init(formatted_ste, htbl->lu_type, nic_dmn->ste_type, gvmi);
+ ste.hw_ste = formatted_ste;
+
+ if (connect_info->type == CONNECT_HIT)
+ dr_ste_always_hit_htbl(&ste, connect_info->hit_next_htbl);
+ else
+ mlx5dr_ste_always_miss_addr(&ste, connect_info->miss_icm_addr);
+}
+
+int mlx5dr_ste_htbl_init_and_postsend(struct mlx5dr_domain *dmn,
+ struct mlx5dr_domain_rx_tx *nic_dmn,
+ struct mlx5dr_ste_htbl *htbl,
+ struct mlx5dr_htbl_connect_info *connect_info,
+ bool update_hw_ste)
+{
+ u8 formatted_ste[DR_STE_SIZE] = {};
+
+ mlx5dr_ste_set_formatted_ste(dmn->info.caps.gvmi,
+ nic_dmn,
+ htbl,
+ formatted_ste,
+ connect_info);
+
+ return mlx5dr_send_postsend_formatted_htbl(dmn, htbl, formatted_ste, update_hw_ste);
+}
+
+int mlx5dr_ste_create_next_htbl(struct mlx5dr_matcher *matcher,
+ struct mlx5dr_matcher_rx_tx *nic_matcher,
+ struct mlx5dr_ste *ste,
+ u8 *cur_hw_ste,
+ enum mlx5dr_icm_chunk_size log_table_size)
+{
+ struct dr_hw_ste_format *hw_ste = (struct dr_hw_ste_format *)cur_hw_ste;
+ struct mlx5dr_domain_rx_tx *nic_dmn = nic_matcher->nic_tbl->nic_dmn;
+ struct mlx5dr_domain *dmn = matcher->tbl->dmn;
+ struct mlx5dr_htbl_connect_info info;
+ struct mlx5dr_ste_htbl *next_htbl;
+
+ if (!mlx5dr_ste_is_last_in_rule(nic_matcher, ste->ste_chain_location)) {
+ u32 bits_in_mask;
+ u8 next_lu_type;
+ u16 byte_mask;
+
+ next_lu_type = MLX5_GET(ste_general, hw_ste, next_lu_type);
+ byte_mask = MLX5_GET(ste_general, hw_ste, byte_mask);
+
+ /* Don't allocate table more than required,
+ * the size of the table defined via the byte_mask, so no need
+ * to allocate more than that.
+ */
+ bits_in_mask = get_bits_per_mask(byte_mask) * BITS_PER_BYTE;
+ log_table_size = min(log_table_size, bits_in_mask);
+
+ next_htbl = mlx5dr_ste_htbl_alloc(dmn->ste_icm_pool,
+ log_table_size,
+ next_lu_type,
+ byte_mask);
+ if (!next_htbl) {
+ mlx5dr_dbg(dmn, "Failed allocating table\n");
+ return -ENOMEM;
+ }
+
+ /* Write new table to HW */
+ info.type = CONNECT_MISS;
+ info.miss_icm_addr = nic_matcher->e_anchor->chunk->icm_addr;
+ if (mlx5dr_ste_htbl_init_and_postsend(dmn, nic_dmn, next_htbl,
+ &info, false)) {
+ mlx5dr_info(dmn, "Failed writing table to HW\n");
+ goto free_table;
+ }
+
+ mlx5dr_ste_set_hit_addr_by_next_htbl(cur_hw_ste, next_htbl);
+ ste->next_htbl = next_htbl;
+ next_htbl->pointing_ste = ste;
+ }
+
+ return 0;
+
+free_table:
+ mlx5dr_ste_htbl_free(next_htbl);
+ return -ENOENT;
+}
+
+static void dr_ste_set_ctrl(struct mlx5dr_ste_htbl *htbl)
+{
+ struct mlx5dr_ste_htbl_ctrl *ctrl = &htbl->ctrl;
+ int num_of_entries;
+
+ htbl->ctrl.may_grow = true;
+
+ if (htbl->chunk_size == DR_CHUNK_SIZE_MAX - 1)
+ htbl->ctrl.may_grow = false;
+
+ /* Threshold is 50%, one is added to table of size 1 */
+ num_of_entries = mlx5dr_icm_pool_chunk_size_to_entries(htbl->chunk_size);
+ ctrl->increase_threshold = (num_of_entries + 1) / 2;
+}
+
+struct mlx5dr_ste_htbl *mlx5dr_ste_htbl_alloc(struct mlx5dr_icm_pool *pool,
+ enum mlx5dr_icm_chunk_size chunk_size,
+ u8 lu_type, u16 byte_mask)
+{
+ struct mlx5dr_icm_chunk *chunk;
+ struct mlx5dr_ste_htbl *htbl;
+ int i;
+
+ htbl = kzalloc(sizeof(*htbl), GFP_KERNEL);
+ if (!htbl)
+ return NULL;
+
+ chunk = mlx5dr_icm_alloc_chunk(pool, chunk_size);
+ if (!chunk)
+ goto out_free_htbl;
+
+ htbl->chunk = chunk;
+ htbl->lu_type = lu_type;
+ htbl->byte_mask = byte_mask;
+ htbl->ste_arr = chunk->ste_arr;
+ htbl->hw_ste_arr = chunk->hw_ste_arr;
+ htbl->miss_list = chunk->miss_list;
+ refcount_set(&htbl->refcount, 0);
+
+ for (i = 0; i < chunk->num_of_entries; i++) {
+ struct mlx5dr_ste *ste = &htbl->ste_arr[i];
+
+ ste->hw_ste = htbl->hw_ste_arr + i * DR_STE_SIZE_REDUCED;
+ ste->htbl = htbl;
+ refcount_set(&ste->refcount, 0);
+ INIT_LIST_HEAD(&ste->miss_list_node);
+ INIT_LIST_HEAD(&htbl->miss_list[i]);
+ INIT_LIST_HEAD(&ste->rule_list);
+ }
+
+ htbl->chunk_size = chunk_size;
+ dr_ste_set_ctrl(htbl);
+ return htbl;
+
+out_free_htbl:
+ kfree(htbl);
+ return NULL;
+}
+
+int mlx5dr_ste_htbl_free(struct mlx5dr_ste_htbl *htbl)
+{
+ if (refcount_read(&htbl->refcount))
+ return -EBUSY;
+
+ mlx5dr_icm_free_chunk(htbl->chunk);
+ kfree(htbl);
+ return 0;
+}
+
+int mlx5dr_ste_build_pre_check(struct mlx5dr_domain *dmn,
+ u8 match_criteria,
+ struct mlx5dr_match_param *mask,
+ struct mlx5dr_match_param *value)
+{
+ if (!value && (match_criteria & DR_MATCHER_CRITERIA_MISC)) {
+ if (mask->misc.source_port && mask->misc.source_port != 0xffff) {
+ mlx5dr_dbg(dmn, "Partial mask source_port is not supported\n");
+ return -EINVAL;
+ }
+ }
+
+ return 0;
+}
+
+int mlx5dr_ste_build_ste_arr(struct mlx5dr_matcher *matcher,
+ struct mlx5dr_matcher_rx_tx *nic_matcher,
+ struct mlx5dr_match_param *value,
+ u8 *ste_arr)
+{
+ struct mlx5dr_domain_rx_tx *nic_dmn = nic_matcher->nic_tbl->nic_dmn;
+ struct mlx5dr_domain *dmn = matcher->tbl->dmn;
+ struct mlx5dr_ste_build *sb;
+ int ret, i;
+
+ ret = mlx5dr_ste_build_pre_check(dmn, matcher->match_criteria,
+ &matcher->mask, value);
+ if (ret)
+ return ret;
+
+ sb = nic_matcher->ste_builder;
+ for (i = 0; i < nic_matcher->num_of_builders; i++) {
+ mlx5dr_ste_init(ste_arr,
+ sb->lu_type,
+ nic_dmn->ste_type,
+ dmn->info.caps.gvmi);
+
+ mlx5dr_ste_set_bit_mask(ste_arr, sb->bit_mask);
+
+ ret = sb->ste_build_tag_func(value, sb, ste_arr);
+ if (ret)
+ return ret;
+
+ /* Connect the STEs */
+ if (i < (nic_matcher->num_of_builders - 1)) {
+ /* Need the next builder for these fields,
+ * not relevant for the last ste in the chain.
+ */
+ sb++;
+ MLX5_SET(ste_general, ste_arr, next_lu_type, sb->lu_type);
+ MLX5_SET(ste_general, ste_arr, byte_mask, sb->byte_mask);
+ }
+ ste_arr += DR_STE_SIZE;
+ }
+ return 0;
+}
+
+static int dr_ste_build_eth_l2_src_des_bit_mask(struct mlx5dr_match_param *value,
+ bool inner, u8 *bit_mask)
+{
+ struct mlx5dr_match_spec *mask = inner ? &value->inner : &value->outer;
+
+ DR_STE_SET_MASK_V(eth_l2_src_dst, bit_mask, dmac_47_16, mask, dmac_47_16);
+ DR_STE_SET_MASK_V(eth_l2_src_dst, bit_mask, dmac_15_0, mask, dmac_15_0);
+
+ if (mask->smac_47_16 || mask->smac_15_0) {
+ MLX5_SET(ste_eth_l2_src_dst, bit_mask, smac_47_32,
+ mask->smac_47_16 >> 16);
+ MLX5_SET(ste_eth_l2_src_dst, bit_mask, smac_31_0,
+ mask->smac_47_16 << 16 | mask->smac_15_0);
+ mask->smac_47_16 = 0;
+ mask->smac_15_0 = 0;
+ }
+
+ DR_STE_SET_MASK_V(eth_l2_src_dst, bit_mask, first_vlan_id, mask, first_vid);
+ DR_STE_SET_MASK_V(eth_l2_src_dst, bit_mask, first_cfi, mask, first_cfi);
+ DR_STE_SET_MASK_V(eth_l2_src_dst, bit_mask, first_priority, mask, first_prio);
+ DR_STE_SET_MASK(eth_l2_src_dst, bit_mask, l3_type, mask, ip_version);
+
+ if (mask->cvlan_tag) {
+ MLX5_SET(ste_eth_l2_src_dst, bit_mask, first_vlan_qualifier, -1);
+ mask->cvlan_tag = 0;
+ } else if (mask->svlan_tag) {
+ MLX5_SET(ste_eth_l2_src_dst, bit_mask, first_vlan_qualifier, -1);
+ mask->svlan_tag = 0;
+ }
+
+ if (mask->cvlan_tag || mask->svlan_tag) {
+ pr_info("Invalid c/svlan mask configuration\n");
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
+static void dr_ste_copy_mask_misc(char *mask, struct mlx5dr_match_misc *spec)
+{
+ spec->gre_c_present = MLX5_GET(fte_match_set_misc, mask, gre_c_present);
+ spec->gre_k_present = MLX5_GET(fte_match_set_misc, mask, gre_k_present);
+ spec->gre_s_present = MLX5_GET(fte_match_set_misc, mask, gre_s_present);
+ spec->source_vhca_port = MLX5_GET(fte_match_set_misc, mask, source_vhca_port);
+ spec->source_sqn = MLX5_GET(fte_match_set_misc, mask, source_sqn);
+
+ spec->source_port = MLX5_GET(fte_match_set_misc, mask, source_port);
+
+ spec->outer_second_prio = MLX5_GET(fte_match_set_misc, mask, outer_second_prio);
+ spec->outer_second_cfi = MLX5_GET(fte_match_set_misc, mask, outer_second_cfi);
+ spec->outer_second_vid = MLX5_GET(fte_match_set_misc, mask, outer_second_vid);
+ spec->inner_second_prio = MLX5_GET(fte_match_set_misc, mask, inner_second_prio);
+ spec->inner_second_cfi = MLX5_GET(fte_match_set_misc, mask, inner_second_cfi);
+ spec->inner_second_vid = MLX5_GET(fte_match_set_misc, mask, inner_second_vid);
+
+ spec->outer_second_cvlan_tag =
+ MLX5_GET(fte_match_set_misc, mask, outer_second_cvlan_tag);
+ spec->inner_second_cvlan_tag =
+ MLX5_GET(fte_match_set_misc, mask, inner_second_cvlan_tag);
+ spec->outer_second_svlan_tag =
+ MLX5_GET(fte_match_set_misc, mask, outer_second_svlan_tag);
+ spec->inner_second_svlan_tag =
+ MLX5_GET(fte_match_set_misc, mask, inner_second_svlan_tag);
+
+ spec->gre_protocol = MLX5_GET(fte_match_set_misc, mask, gre_protocol);
+
+ spec->gre_key_h = MLX5_GET(fte_match_set_misc, mask, gre_key.nvgre.hi);
+ spec->gre_key_l = MLX5_GET(fte_match_set_misc, mask, gre_key.nvgre.lo);
+
+ spec->vxlan_vni = MLX5_GET(fte_match_set_misc, mask, vxlan_vni);
+
+ spec->geneve_vni = MLX5_GET(fte_match_set_misc, mask, geneve_vni);
+ spec->geneve_oam = MLX5_GET(fte_match_set_misc, mask, geneve_oam);
+
+ spec->outer_ipv6_flow_label =
+ MLX5_GET(fte_match_set_misc, mask, outer_ipv6_flow_label);
+
+ spec->inner_ipv6_flow_label =
+ MLX5_GET(fte_match_set_misc, mask, inner_ipv6_flow_label);
+
+ spec->geneve_opt_len = MLX5_GET(fte_match_set_misc, mask, geneve_opt_len);
+ spec->geneve_protocol_type =
+ MLX5_GET(fte_match_set_misc, mask, geneve_protocol_type);
+
+ spec->bth_dst_qp = MLX5_GET(fte_match_set_misc, mask, bth_dst_qp);
+}
+
+static void dr_ste_copy_mask_spec(char *mask, struct mlx5dr_match_spec *spec)
+{
+ u32 raw_ip[4];
+
+ spec->smac_47_16 = MLX5_GET(fte_match_set_lyr_2_4, mask, smac_47_16);
+
+ spec->smac_15_0 = MLX5_GET(fte_match_set_lyr_2_4, mask, smac_15_0);
+ spec->ethertype = MLX5_GET(fte_match_set_lyr_2_4, mask, ethertype);
+
+ spec->dmac_47_16 = MLX5_GET(fte_match_set_lyr_2_4, mask, dmac_47_16);
+
+ spec->dmac_15_0 = MLX5_GET(fte_match_set_lyr_2_4, mask, dmac_15_0);
+ spec->first_prio = MLX5_GET(fte_match_set_lyr_2_4, mask, first_prio);
+ spec->first_cfi = MLX5_GET(fte_match_set_lyr_2_4, mask, first_cfi);
+ spec->first_vid = MLX5_GET(fte_match_set_lyr_2_4, mask, first_vid);
+
+ spec->ip_protocol = MLX5_GET(fte_match_set_lyr_2_4, mask, ip_protocol);
+ spec->ip_dscp = MLX5_GET(fte_match_set_lyr_2_4, mask, ip_dscp);
+ spec->ip_ecn = MLX5_GET(fte_match_set_lyr_2_4, mask, ip_ecn);
+ spec->cvlan_tag = MLX5_GET(fte_match_set_lyr_2_4, mask, cvlan_tag);
+ spec->svlan_tag = MLX5_GET(fte_match_set_lyr_2_4, mask, svlan_tag);
+ spec->frag = MLX5_GET(fte_match_set_lyr_2_4, mask, frag);
+ spec->ip_version = MLX5_GET(fte_match_set_lyr_2_4, mask, ip_version);
+ spec->tcp_flags = MLX5_GET(fte_match_set_lyr_2_4, mask, tcp_flags);
+ spec->tcp_sport = MLX5_GET(fte_match_set_lyr_2_4, mask, tcp_sport);
+ spec->tcp_dport = MLX5_GET(fte_match_set_lyr_2_4, mask, tcp_dport);
+
+ spec->ttl_hoplimit = MLX5_GET(fte_match_set_lyr_2_4, mask, ttl_hoplimit);
+
+ spec->udp_sport = MLX5_GET(fte_match_set_lyr_2_4, mask, udp_sport);
+ spec->udp_dport = MLX5_GET(fte_match_set_lyr_2_4, mask, udp_dport);
+
+ memcpy(raw_ip, MLX5_ADDR_OF(fte_match_set_lyr_2_4, mask,
+ src_ipv4_src_ipv6.ipv6_layout.ipv6),
+ sizeof(raw_ip));
+
+ spec->src_ip_127_96 = be32_to_cpu(raw_ip[0]);
+ spec->src_ip_95_64 = be32_to_cpu(raw_ip[1]);
+ spec->src_ip_63_32 = be32_to_cpu(raw_ip[2]);
+ spec->src_ip_31_0 = be32_to_cpu(raw_ip[3]);
+
+ memcpy(raw_ip, MLX5_ADDR_OF(fte_match_set_lyr_2_4, mask,
+ dst_ipv4_dst_ipv6.ipv6_layout.ipv6),
+ sizeof(raw_ip));
+
+ spec->dst_ip_127_96 = be32_to_cpu(raw_ip[0]);
+ spec->dst_ip_95_64 = be32_to_cpu(raw_ip[1]);
+ spec->dst_ip_63_32 = be32_to_cpu(raw_ip[2]);
+ spec->dst_ip_31_0 = be32_to_cpu(raw_ip[3]);
+}
+
+static void dr_ste_copy_mask_misc2(char *mask, struct mlx5dr_match_misc2 *spec)
+{
+ spec->outer_first_mpls_label =
+ MLX5_GET(fte_match_set_misc2, mask, outer_first_mpls.mpls_label);
+ spec->outer_first_mpls_exp =
+ MLX5_GET(fte_match_set_misc2, mask, outer_first_mpls.mpls_exp);
+ spec->outer_first_mpls_s_bos =
+ MLX5_GET(fte_match_set_misc2, mask, outer_first_mpls.mpls_s_bos);
+ spec->outer_first_mpls_ttl =
+ MLX5_GET(fte_match_set_misc2, mask, outer_first_mpls.mpls_ttl);
+ spec->inner_first_mpls_label =
+ MLX5_GET(fte_match_set_misc2, mask, inner_first_mpls.mpls_label);
+ spec->inner_first_mpls_exp =
+ MLX5_GET(fte_match_set_misc2, mask, inner_first_mpls.mpls_exp);
+ spec->inner_first_mpls_s_bos =
+ MLX5_GET(fte_match_set_misc2, mask, inner_first_mpls.mpls_s_bos);
+ spec->inner_first_mpls_ttl =
+ MLX5_GET(fte_match_set_misc2, mask, inner_first_mpls.mpls_ttl);
+ spec->outer_first_mpls_over_gre_label =
+ MLX5_GET(fte_match_set_misc2, mask, outer_first_mpls_over_gre.mpls_label);
+ spec->outer_first_mpls_over_gre_exp =
+ MLX5_GET(fte_match_set_misc2, mask, outer_first_mpls_over_gre.mpls_exp);
+ spec->outer_first_mpls_over_gre_s_bos =
+ MLX5_GET(fte_match_set_misc2, mask, outer_first_mpls_over_gre.mpls_s_bos);
+ spec->outer_first_mpls_over_gre_ttl =
+ MLX5_GET(fte_match_set_misc2, mask, outer_first_mpls_over_gre.mpls_ttl);
+ spec->outer_first_mpls_over_udp_label =
+ MLX5_GET(fte_match_set_misc2, mask, outer_first_mpls_over_udp.mpls_label);
+ spec->outer_first_mpls_over_udp_exp =
+ MLX5_GET(fte_match_set_misc2, mask, outer_first_mpls_over_udp.mpls_exp);
+ spec->outer_first_mpls_over_udp_s_bos =
+ MLX5_GET(fte_match_set_misc2, mask, outer_first_mpls_over_udp.mpls_s_bos);
+ spec->outer_first_mpls_over_udp_ttl =
+ MLX5_GET(fte_match_set_misc2, mask, outer_first_mpls_over_udp.mpls_ttl);
+ spec->metadata_reg_c_7 = MLX5_GET(fte_match_set_misc2, mask, metadata_reg_c_7);
+ spec->metadata_reg_c_6 = MLX5_GET(fte_match_set_misc2, mask, metadata_reg_c_6);
+ spec->metadata_reg_c_5 = MLX5_GET(fte_match_set_misc2, mask, metadata_reg_c_5);
+ spec->metadata_reg_c_4 = MLX5_GET(fte_match_set_misc2, mask, metadata_reg_c_4);
+ spec->metadata_reg_c_3 = MLX5_GET(fte_match_set_misc2, mask, metadata_reg_c_3);
+ spec->metadata_reg_c_2 = MLX5_GET(fte_match_set_misc2, mask, metadata_reg_c_2);
+ spec->metadata_reg_c_1 = MLX5_GET(fte_match_set_misc2, mask, metadata_reg_c_1);
+ spec->metadata_reg_c_0 = MLX5_GET(fte_match_set_misc2, mask, metadata_reg_c_0);
+ spec->metadata_reg_a = MLX5_GET(fte_match_set_misc2, mask, metadata_reg_a);
+ spec->metadata_reg_b = MLX5_GET(fte_match_set_misc2, mask, metadata_reg_b);
+}
+
+static void dr_ste_copy_mask_misc3(char *mask, struct mlx5dr_match_misc3 *spec)
+{
+ spec->inner_tcp_seq_num = MLX5_GET(fte_match_set_misc3, mask, inner_tcp_seq_num);
+ spec->outer_tcp_seq_num = MLX5_GET(fte_match_set_misc3, mask, outer_tcp_seq_num);
+ spec->inner_tcp_ack_num = MLX5_GET(fte_match_set_misc3, mask, inner_tcp_ack_num);
+ spec->outer_tcp_ack_num = MLX5_GET(fte_match_set_misc3, mask, outer_tcp_ack_num);
+ spec->outer_vxlan_gpe_vni =
+ MLX5_GET(fte_match_set_misc3, mask, outer_vxlan_gpe_vni);
+ spec->outer_vxlan_gpe_next_protocol =
+ MLX5_GET(fte_match_set_misc3, mask, outer_vxlan_gpe_next_protocol);
+ spec->outer_vxlan_gpe_flags =
+ MLX5_GET(fte_match_set_misc3, mask, outer_vxlan_gpe_flags);
+ spec->icmpv4_header_data = MLX5_GET(fte_match_set_misc3, mask, icmp_header_data);
+ spec->icmpv6_header_data =
+ MLX5_GET(fte_match_set_misc3, mask, icmpv6_header_data);
+ spec->icmpv4_type = MLX5_GET(fte_match_set_misc3, mask, icmp_type);
+ spec->icmpv4_code = MLX5_GET(fte_match_set_misc3, mask, icmp_code);
+ spec->icmpv6_type = MLX5_GET(fte_match_set_misc3, mask, icmpv6_type);
+ spec->icmpv6_code = MLX5_GET(fte_match_set_misc3, mask, icmpv6_code);
+}
+
+void mlx5dr_ste_copy_param(u8 match_criteria,
+ struct mlx5dr_match_param *set_param,
+ struct mlx5dr_match_parameters *mask)
+{
+ u8 tail_param[MLX5_ST_SZ_BYTES(fte_match_set_lyr_2_4)] = {};
+ u8 *data = (u8 *)mask->match_buf;
+ size_t param_location;
+ void *buff;
+
+ if (match_criteria & DR_MATCHER_CRITERIA_OUTER) {
+ if (mask->match_sz < sizeof(struct mlx5dr_match_spec)) {
+ memcpy(tail_param, data, mask->match_sz);
+ buff = tail_param;
+ } else {
+ buff = mask->match_buf;
+ }
+ dr_ste_copy_mask_spec(buff, &set_param->outer);
+ }
+ param_location = sizeof(struct mlx5dr_match_spec);
+
+ if (match_criteria & DR_MATCHER_CRITERIA_MISC) {
+ if (mask->match_sz < param_location +
+ sizeof(struct mlx5dr_match_misc)) {
+ memcpy(tail_param, data + param_location,
+ mask->match_sz - param_location);
+ buff = tail_param;
+ } else {
+ buff = data + param_location;
+ }
+ dr_ste_copy_mask_misc(buff, &set_param->misc);
+ }
+ param_location += sizeof(struct mlx5dr_match_misc);
+
+ if (match_criteria & DR_MATCHER_CRITERIA_INNER) {
+ if (mask->match_sz < param_location +
+ sizeof(struct mlx5dr_match_spec)) {
+ memcpy(tail_param, data + param_location,
+ mask->match_sz - param_location);
+ buff = tail_param;
+ } else {
+ buff = data + param_location;
+ }
+ dr_ste_copy_mask_spec(buff, &set_param->inner);
+ }
+ param_location += sizeof(struct mlx5dr_match_spec);
+
+ if (match_criteria & DR_MATCHER_CRITERIA_MISC2) {
+ if (mask->match_sz < param_location +
+ sizeof(struct mlx5dr_match_misc2)) {
+ memcpy(tail_param, data + param_location,
+ mask->match_sz - param_location);
+ buff = tail_param;
+ } else {
+ buff = data + param_location;
+ }
+ dr_ste_copy_mask_misc2(buff, &set_param->misc2);
+ }
+
+ param_location += sizeof(struct mlx5dr_match_misc2);
+
+ if (match_criteria & DR_MATCHER_CRITERIA_MISC3) {
+ if (mask->match_sz < param_location +
+ sizeof(struct mlx5dr_match_misc3)) {
+ memcpy(tail_param, data + param_location,
+ mask->match_sz - param_location);
+ buff = tail_param;
+ } else {
+ buff = data + param_location;
+ }
+ dr_ste_copy_mask_misc3(buff, &set_param->misc3);
+ }
+}
+
+static int dr_ste_build_eth_l2_src_des_tag(struct mlx5dr_match_param *value,
+ struct mlx5dr_ste_build *sb,
+ u8 *hw_ste_p)
+{
+ struct mlx5dr_match_spec *spec = sb->inner ? &value->inner : &value->outer;
+ struct dr_hw_ste_format *hw_ste = (struct dr_hw_ste_format *)hw_ste_p;
+ u8 *tag = hw_ste->tag;
+
+ DR_STE_SET_TAG(eth_l2_src_dst, tag, dmac_47_16, spec, dmac_47_16);
+ DR_STE_SET_TAG(eth_l2_src_dst, tag, dmac_15_0, spec, dmac_15_0);
+
+ if (spec->smac_47_16 || spec->smac_15_0) {
+ MLX5_SET(ste_eth_l2_src_dst, tag, smac_47_32,
+ spec->smac_47_16 >> 16);
+ MLX5_SET(ste_eth_l2_src_dst, tag, smac_31_0,
+ spec->smac_47_16 << 16 | spec->smac_15_0);
+ spec->smac_47_16 = 0;
+ spec->smac_15_0 = 0;
+ }
+
+ if (spec->ip_version) {
+ if (spec->ip_version == IP_VERSION_IPV4) {
+ MLX5_SET(ste_eth_l2_src_dst, tag, l3_type, STE_IPV4);
+ spec->ip_version = 0;
+ } else if (spec->ip_version == IP_VERSION_IPV6) {
+ MLX5_SET(ste_eth_l2_src_dst, tag, l3_type, STE_IPV6);
+ spec->ip_version = 0;
+ } else {
+ pr_info("Unsupported ip_version value\n");
+ return -EINVAL;
+ }
+ }
+
+ DR_STE_SET_TAG(eth_l2_src_dst, tag, first_vlan_id, spec, first_vid);
+ DR_STE_SET_TAG(eth_l2_src_dst, tag, first_cfi, spec, first_cfi);
+ DR_STE_SET_TAG(eth_l2_src_dst, tag, first_priority, spec, first_prio);
+
+ if (spec->cvlan_tag) {
+ MLX5_SET(ste_eth_l2_src_dst, tag, first_vlan_qualifier, DR_STE_CVLAN);
+ spec->cvlan_tag = 0;
+ } else if (spec->svlan_tag) {
+ MLX5_SET(ste_eth_l2_src_dst, tag, first_vlan_qualifier, DR_STE_SVLAN);
+ spec->svlan_tag = 0;
+ }
+ return 0;
+}
+
+int mlx5dr_ste_build_eth_l2_src_des(struct mlx5dr_ste_build *sb,
+ struct mlx5dr_match_param *mask,
+ bool inner, bool rx)
+{
+ int ret;
+
+ ret = dr_ste_build_eth_l2_src_des_bit_mask(mask, inner, sb->bit_mask);
+ if (ret)
+ return ret;
+
+ sb->rx = rx;
+ sb->inner = inner;
+ sb->lu_type = DR_STE_CALC_LU_TYPE(ETHL2_SRC_DST, rx, inner);
+ sb->byte_mask = dr_ste_conv_bit_to_byte_mask(sb->bit_mask);
+ sb->ste_build_tag_func = &dr_ste_build_eth_l2_src_des_tag;
+
+ return 0;
+}
+
+static void dr_ste_build_eth_l3_ipv6_dst_bit_mask(struct mlx5dr_match_param *value,
+ bool inner, u8 *bit_mask)
+{
+ struct mlx5dr_match_spec *mask = inner ? &value->inner : &value->outer;
+
+ DR_STE_SET_MASK_V(eth_l3_ipv6_dst, bit_mask, dst_ip_127_96, mask, dst_ip_127_96);
+ DR_STE_SET_MASK_V(eth_l3_ipv6_dst, bit_mask, dst_ip_95_64, mask, dst_ip_95_64);
+ DR_STE_SET_MASK_V(eth_l3_ipv6_dst, bit_mask, dst_ip_63_32, mask, dst_ip_63_32);
+ DR_STE_SET_MASK_V(eth_l3_ipv6_dst, bit_mask, dst_ip_31_0, mask, dst_ip_31_0);
+}
+
+static int dr_ste_build_eth_l3_ipv6_dst_tag(struct mlx5dr_match_param *value,
+ struct mlx5dr_ste_build *sb,
+ u8 *hw_ste_p)
+{
+ struct dr_hw_ste_format *hw_ste = (struct dr_hw_ste_format *)hw_ste_p;
+ struct mlx5dr_match_spec *spec = sb->inner ? &value->inner : &value->outer;
+ u8 *tag = hw_ste->tag;
+
+ DR_STE_SET_TAG(eth_l3_ipv6_dst, tag, dst_ip_127_96, spec, dst_ip_127_96);
+ DR_STE_SET_TAG(eth_l3_ipv6_dst, tag, dst_ip_95_64, spec, dst_ip_95_64);
+ DR_STE_SET_TAG(eth_l3_ipv6_dst, tag, dst_ip_63_32, spec, dst_ip_63_32);
+ DR_STE_SET_TAG(eth_l3_ipv6_dst, tag, dst_ip_31_0, spec, dst_ip_31_0);
+
+ return 0;
+}
+
+void mlx5dr_ste_build_eth_l3_ipv6_dst(struct mlx5dr_ste_build *sb,
+ struct mlx5dr_match_param *mask,
+ bool inner, bool rx)
+{
+ dr_ste_build_eth_l3_ipv6_dst_bit_mask(mask, inner, sb->bit_mask);
+
+ sb->rx = rx;
+ sb->inner = inner;
+ sb->lu_type = DR_STE_CALC_LU_TYPE(ETHL3_IPV6_DST, rx, inner);
+ sb->byte_mask = dr_ste_conv_bit_to_byte_mask(sb->bit_mask);
+ sb->ste_build_tag_func = &dr_ste_build_eth_l3_ipv6_dst_tag;
+}
+
+static void dr_ste_build_eth_l3_ipv6_src_bit_mask(struct mlx5dr_match_param *value,
+ bool inner, u8 *bit_mask)
+{
+ struct mlx5dr_match_spec *mask = inner ? &value->inner : &value->outer;
+
+ DR_STE_SET_MASK_V(eth_l3_ipv6_src, bit_mask, src_ip_127_96, mask, src_ip_127_96);
+ DR_STE_SET_MASK_V(eth_l3_ipv6_src, bit_mask, src_ip_95_64, mask, src_ip_95_64);
+ DR_STE_SET_MASK_V(eth_l3_ipv6_src, bit_mask, src_ip_63_32, mask, src_ip_63_32);
+ DR_STE_SET_MASK_V(eth_l3_ipv6_src, bit_mask, src_ip_31_0, mask, src_ip_31_0);
+}
+
+static int dr_ste_build_eth_l3_ipv6_src_tag(struct mlx5dr_match_param *value,
+ struct mlx5dr_ste_build *sb,
+ u8 *hw_ste_p)
+{
+ struct mlx5dr_match_spec *spec = sb->inner ? &value->inner : &value->outer;
+ struct dr_hw_ste_format *hw_ste = (struct dr_hw_ste_format *)hw_ste_p;
+ u8 *tag = hw_ste->tag;
+
+ DR_STE_SET_TAG(eth_l3_ipv6_src, tag, src_ip_127_96, spec, src_ip_127_96);
+ DR_STE_SET_TAG(eth_l3_ipv6_src, tag, src_ip_95_64, spec, src_ip_95_64);
+ DR_STE_SET_TAG(eth_l3_ipv6_src, tag, src_ip_63_32, spec, src_ip_63_32);
+ DR_STE_SET_TAG(eth_l3_ipv6_src, tag, src_ip_31_0, spec, src_ip_31_0);
+
+ return 0;
+}
+
+void mlx5dr_ste_build_eth_l3_ipv6_src(struct mlx5dr_ste_build *sb,
+ struct mlx5dr_match_param *mask,
+ bool inner, bool rx)
+{
+ dr_ste_build_eth_l3_ipv6_src_bit_mask(mask, inner, sb->bit_mask);
+
+ sb->rx = rx;
+ sb->inner = inner;
+ sb->lu_type = DR_STE_CALC_LU_TYPE(ETHL3_IPV6_SRC, rx, inner);
+ sb->byte_mask = dr_ste_conv_bit_to_byte_mask(sb->bit_mask);
+ sb->ste_build_tag_func = &dr_ste_build_eth_l3_ipv6_src_tag;
+}
+
+static void dr_ste_build_eth_l3_ipv4_5_tuple_bit_mask(struct mlx5dr_match_param *value,
+ bool inner,
+ u8 *bit_mask)
+{
+ struct mlx5dr_match_spec *mask = inner ? &value->inner : &value->outer;
+
+ DR_STE_SET_MASK_V(eth_l3_ipv4_5_tuple, bit_mask,
+ destination_address, mask, dst_ip_31_0);
+ DR_STE_SET_MASK_V(eth_l3_ipv4_5_tuple, bit_mask,
+ source_address, mask, src_ip_31_0);
+ DR_STE_SET_MASK_V(eth_l3_ipv4_5_tuple, bit_mask,
+ destination_port, mask, tcp_dport);
+ DR_STE_SET_MASK_V(eth_l3_ipv4_5_tuple, bit_mask,
+ destination_port, mask, udp_dport);
+ DR_STE_SET_MASK_V(eth_l3_ipv4_5_tuple, bit_mask,
+ source_port, mask, tcp_sport);
+ DR_STE_SET_MASK_V(eth_l3_ipv4_5_tuple, bit_mask,
+ source_port, mask, udp_sport);
+ DR_STE_SET_MASK_V(eth_l3_ipv4_5_tuple, bit_mask,
+ protocol, mask, ip_protocol);
+ DR_STE_SET_MASK_V(eth_l3_ipv4_5_tuple, bit_mask,
+ fragmented, mask, frag);
+ DR_STE_SET_MASK_V(eth_l3_ipv4_5_tuple, bit_mask,
+ dscp, mask, ip_dscp);
+ DR_STE_SET_MASK_V(eth_l3_ipv4_5_tuple, bit_mask,
+ ecn, mask, ip_ecn);
+
+ if (mask->tcp_flags) {
+ DR_STE_SET_TCP_FLAGS(eth_l3_ipv4_5_tuple, bit_mask, mask);
+ mask->tcp_flags = 0;
+ }
+}
+
+static int dr_ste_build_eth_l3_ipv4_5_tuple_tag(struct mlx5dr_match_param *value,
+ struct mlx5dr_ste_build *sb,
+ u8 *hw_ste_p)
+{
+ struct dr_hw_ste_format *hw_ste = (struct dr_hw_ste_format *)hw_ste_p;
+ struct mlx5dr_match_spec *spec = sb->inner ? &value->inner : &value->outer;
+ u8 *tag = hw_ste->tag;
+
+ DR_STE_SET_TAG(eth_l3_ipv4_5_tuple, tag, destination_address, spec, dst_ip_31_0);
+ DR_STE_SET_TAG(eth_l3_ipv4_5_tuple, tag, source_address, spec, src_ip_31_0);
+ DR_STE_SET_TAG(eth_l3_ipv4_5_tuple, tag, destination_port, spec, tcp_dport);
+ DR_STE_SET_TAG(eth_l3_ipv4_5_tuple, tag, destination_port, spec, udp_dport);
+ DR_STE_SET_TAG(eth_l3_ipv4_5_tuple, tag, source_port, spec, tcp_sport);
+ DR_STE_SET_TAG(eth_l3_ipv4_5_tuple, tag, source_port, spec, udp_sport);
+ DR_STE_SET_TAG(eth_l3_ipv4_5_tuple, tag, protocol, spec, ip_protocol);
+ DR_STE_SET_TAG(eth_l3_ipv4_5_tuple, tag, fragmented, spec, frag);
+ DR_STE_SET_TAG(eth_l3_ipv4_5_tuple, tag, dscp, spec, ip_dscp);
+ DR_STE_SET_TAG(eth_l3_ipv4_5_tuple, tag, ecn, spec, ip_ecn);
+
+ if (spec->tcp_flags) {
+ DR_STE_SET_TCP_FLAGS(eth_l3_ipv4_5_tuple, tag, spec);
+ spec->tcp_flags = 0;
+ }
+
+ return 0;
+}
+
+void mlx5dr_ste_build_eth_l3_ipv4_5_tuple(struct mlx5dr_ste_build *sb,
+ struct mlx5dr_match_param *mask,
+ bool inner, bool rx)
+{
+ dr_ste_build_eth_l3_ipv4_5_tuple_bit_mask(mask, inner, sb->bit_mask);
+
+ sb->rx = rx;
+ sb->inner = inner;
+ sb->lu_type = DR_STE_CALC_LU_TYPE(ETHL3_IPV4_5_TUPLE, rx, inner);
+ sb->byte_mask = dr_ste_conv_bit_to_byte_mask(sb->bit_mask);
+ sb->ste_build_tag_func = &dr_ste_build_eth_l3_ipv4_5_tuple_tag;
+}
+
+static void
+dr_ste_build_eth_l2_src_or_dst_bit_mask(struct mlx5dr_match_param *value,
+ bool inner, u8 *bit_mask)
+{
+ struct mlx5dr_match_spec *mask = inner ? &value->inner : &value->outer;
+ struct mlx5dr_match_misc *misc_mask = &value->misc;
+
+ DR_STE_SET_MASK_V(eth_l2_src, bit_mask, first_vlan_id, mask, first_vid);
+ DR_STE_SET_MASK_V(eth_l2_src, bit_mask, first_cfi, mask, first_cfi);
+ DR_STE_SET_MASK_V(eth_l2_src, bit_mask, first_priority, mask, first_prio);
+ DR_STE_SET_MASK_V(eth_l2_src, bit_mask, ip_fragmented, mask, frag);
+ DR_STE_SET_MASK_V(eth_l2_src, bit_mask, l3_ethertype, mask, ethertype);
+ DR_STE_SET_MASK(eth_l2_src, bit_mask, l3_type, mask, ip_version);
+
+ if (mask->svlan_tag || mask->cvlan_tag) {
+ MLX5_SET(ste_eth_l2_src, bit_mask, first_vlan_qualifier, -1);
+ mask->cvlan_tag = 0;
+ mask->svlan_tag = 0;
+ }
+
+ if (inner) {
+ if (misc_mask->inner_second_cvlan_tag ||
+ misc_mask->inner_second_svlan_tag) {
+ MLX5_SET(ste_eth_l2_src, bit_mask, second_vlan_qualifier, -1);
+ misc_mask->inner_second_cvlan_tag = 0;
+ misc_mask->inner_second_svlan_tag = 0;
+ }
+
+ DR_STE_SET_MASK_V(eth_l2_src, bit_mask,
+ second_vlan_id, misc_mask, inner_second_vid);
+ DR_STE_SET_MASK_V(eth_l2_src, bit_mask,
+ second_cfi, misc_mask, inner_second_cfi);
+ DR_STE_SET_MASK_V(eth_l2_src, bit_mask,
+ second_priority, misc_mask, inner_second_prio);
+ } else {
+ if (misc_mask->outer_second_cvlan_tag ||
+ misc_mask->outer_second_svlan_tag) {
+ MLX5_SET(ste_eth_l2_src, bit_mask, second_vlan_qualifier, -1);
+ misc_mask->outer_second_cvlan_tag = 0;
+ misc_mask->outer_second_svlan_tag = 0;
+ }
+
+ DR_STE_SET_MASK_V(eth_l2_src, bit_mask,
+ second_vlan_id, misc_mask, outer_second_vid);
+ DR_STE_SET_MASK_V(eth_l2_src, bit_mask,
+ second_cfi, misc_mask, outer_second_cfi);
+ DR_STE_SET_MASK_V(eth_l2_src, bit_mask,
+ second_priority, misc_mask, outer_second_prio);
+ }
+}
+
+static int dr_ste_build_eth_l2_src_or_dst_tag(struct mlx5dr_match_param *value,
+ bool inner, u8 *hw_ste_p)
+{
+ struct dr_hw_ste_format *hw_ste = (struct dr_hw_ste_format *)hw_ste_p;
+ struct mlx5dr_match_spec *spec = inner ? &value->inner : &value->outer;
+ struct mlx5dr_match_misc *misc_spec = &value->misc;
+ u8 *tag = hw_ste->tag;
+
+ DR_STE_SET_TAG(eth_l2_src, tag, first_vlan_id, spec, first_vid);
+ DR_STE_SET_TAG(eth_l2_src, tag, first_cfi, spec, first_cfi);
+ DR_STE_SET_TAG(eth_l2_src, tag, first_priority, spec, first_prio);
+ DR_STE_SET_TAG(eth_l2_src, tag, ip_fragmented, spec, frag);
+ DR_STE_SET_TAG(eth_l2_src, tag, l3_ethertype, spec, ethertype);
+
+ if (spec->ip_version) {
+ if (spec->ip_version == IP_VERSION_IPV4) {
+ MLX5_SET(ste_eth_l2_src, tag, l3_type, STE_IPV4);
+ spec->ip_version = 0;
+ } else if (spec->ip_version == IP_VERSION_IPV6) {
+ MLX5_SET(ste_eth_l2_src, tag, l3_type, STE_IPV6);
+ spec->ip_version = 0;
+ } else {
+ pr_info("Unsupported ip_version value\n");
+ return -EINVAL;
+ }
+ }
+
+ if (spec->cvlan_tag) {
+ MLX5_SET(ste_eth_l2_src, tag, first_vlan_qualifier, DR_STE_CVLAN);
+ spec->cvlan_tag = 0;
+ } else if (spec->svlan_tag) {
+ MLX5_SET(ste_eth_l2_src, tag, first_vlan_qualifier, DR_STE_SVLAN);
+ spec->svlan_tag = 0;
+ }
+
+ if (inner) {
+ if (misc_spec->inner_second_cvlan_tag) {
+ MLX5_SET(ste_eth_l2_src, tag, second_vlan_qualifier, DR_STE_CVLAN);
+ misc_spec->inner_second_cvlan_tag = 0;
+ } else if (misc_spec->inner_second_svlan_tag) {
+ MLX5_SET(ste_eth_l2_src, tag, second_vlan_qualifier, DR_STE_SVLAN);
+ misc_spec->inner_second_svlan_tag = 0;
+ }
+
+ DR_STE_SET_TAG(eth_l2_src, tag, second_vlan_id, misc_spec, inner_second_vid);
+ DR_STE_SET_TAG(eth_l2_src, tag, second_cfi, misc_spec, inner_second_cfi);
+ DR_STE_SET_TAG(eth_l2_src, tag, second_priority, misc_spec, inner_second_prio);
+ } else {
+ if (misc_spec->outer_second_cvlan_tag) {
+ MLX5_SET(ste_eth_l2_src, tag, second_vlan_qualifier, DR_STE_CVLAN);
+ misc_spec->outer_second_cvlan_tag = 0;
+ } else if (misc_spec->outer_second_svlan_tag) {
+ MLX5_SET(ste_eth_l2_src, tag, second_vlan_qualifier, DR_STE_SVLAN);
+ misc_spec->outer_second_svlan_tag = 0;
+ }
+ DR_STE_SET_TAG(eth_l2_src, tag, second_vlan_id, misc_spec, outer_second_vid);
+ DR_STE_SET_TAG(eth_l2_src, tag, second_cfi, misc_spec, outer_second_cfi);
+ DR_STE_SET_TAG(eth_l2_src, tag, second_priority, misc_spec, outer_second_prio);
+ }
+
+ return 0;
+}
+
+static void dr_ste_build_eth_l2_src_bit_mask(struct mlx5dr_match_param *value,
+ bool inner, u8 *bit_mask)
+{
+ struct mlx5dr_match_spec *mask = inner ? &value->inner : &value->outer;
+
+ DR_STE_SET_MASK_V(eth_l2_src, bit_mask, smac_47_16, mask, smac_47_16);
+ DR_STE_SET_MASK_V(eth_l2_src, bit_mask, smac_15_0, mask, smac_15_0);
+
+ dr_ste_build_eth_l2_src_or_dst_bit_mask(value, inner, bit_mask);
+}
+
+static int dr_ste_build_eth_l2_src_tag(struct mlx5dr_match_param *value,
+ struct mlx5dr_ste_build *sb,
+ u8 *hw_ste_p)
+{
+ struct dr_hw_ste_format *hw_ste = (struct dr_hw_ste_format *)hw_ste_p;
+ struct mlx5dr_match_spec *spec = sb->inner ? &value->inner : &value->outer;
+ u8 *tag = hw_ste->tag;
+
+ DR_STE_SET_TAG(eth_l2_src, tag, smac_47_16, spec, smac_47_16);
+ DR_STE_SET_TAG(eth_l2_src, tag, smac_15_0, spec, smac_15_0);
+
+ return dr_ste_build_eth_l2_src_or_dst_tag(value, sb->inner, hw_ste_p);
+}
+
+void mlx5dr_ste_build_eth_l2_src(struct mlx5dr_ste_build *sb,
+ struct mlx5dr_match_param *mask,
+ bool inner, bool rx)
+{
+ dr_ste_build_eth_l2_src_bit_mask(mask, inner, sb->bit_mask);
+ sb->rx = rx;
+ sb->inner = inner;
+ sb->lu_type = DR_STE_CALC_LU_TYPE(ETHL2_SRC, rx, inner);
+ sb->byte_mask = dr_ste_conv_bit_to_byte_mask(sb->bit_mask);
+ sb->ste_build_tag_func = &dr_ste_build_eth_l2_src_tag;
+}
+
+static void dr_ste_build_eth_l2_dst_bit_mask(struct mlx5dr_match_param *value,
+ bool inner, u8 *bit_mask)
+{
+ struct mlx5dr_match_spec *mask = inner ? &value->inner : &value->outer;
+
+ DR_STE_SET_MASK_V(eth_l2_dst, bit_mask, dmac_47_16, mask, dmac_47_16);
+ DR_STE_SET_MASK_V(eth_l2_dst, bit_mask, dmac_15_0, mask, dmac_15_0);
+
+ dr_ste_build_eth_l2_src_or_dst_bit_mask(value, inner, bit_mask);
+}
+
+static int dr_ste_build_eth_l2_dst_tag(struct mlx5dr_match_param *value,
+ struct mlx5dr_ste_build *sb,
+ u8 *hw_ste_p)
+{
+ struct dr_hw_ste_format *hw_ste = (struct dr_hw_ste_format *)hw_ste_p;
+ struct mlx5dr_match_spec *spec = sb->inner ? &value->inner : &value->outer;
+ u8 *tag = hw_ste->tag;
+
+ DR_STE_SET_TAG(eth_l2_dst, tag, dmac_47_16, spec, dmac_47_16);
+ DR_STE_SET_TAG(eth_l2_dst, tag, dmac_15_0, spec, dmac_15_0);
+
+ return dr_ste_build_eth_l2_src_or_dst_tag(value, sb->inner, hw_ste_p);
+}
+
+void mlx5dr_ste_build_eth_l2_dst(struct mlx5dr_ste_build *sb,
+ struct mlx5dr_match_param *mask,
+ bool inner, bool rx)
+{
+ dr_ste_build_eth_l2_dst_bit_mask(mask, inner, sb->bit_mask);
+
+ sb->rx = rx;
+ sb->inner = inner;
+ sb->lu_type = DR_STE_CALC_LU_TYPE(ETHL2_DST, rx, inner);
+ sb->byte_mask = dr_ste_conv_bit_to_byte_mask(sb->bit_mask);
+ sb->ste_build_tag_func = &dr_ste_build_eth_l2_dst_tag;
+}
+
+static void dr_ste_build_eth_l2_tnl_bit_mask(struct mlx5dr_match_param *value,
+ bool inner, u8 *bit_mask)
+{
+ struct mlx5dr_match_spec *mask = inner ? &value->inner : &value->outer;
+ struct mlx5dr_match_misc *misc = &value->misc;
+
+ DR_STE_SET_MASK_V(eth_l2_tnl, bit_mask, dmac_47_16, mask, dmac_47_16);
+ DR_STE_SET_MASK_V(eth_l2_tnl, bit_mask, dmac_15_0, mask, dmac_15_0);
+ DR_STE_SET_MASK_V(eth_l2_tnl, bit_mask, first_vlan_id, mask, first_vid);
+ DR_STE_SET_MASK_V(eth_l2_tnl, bit_mask, first_cfi, mask, first_cfi);
+ DR_STE_SET_MASK_V(eth_l2_tnl, bit_mask, first_priority, mask, first_prio);
+ DR_STE_SET_MASK_V(eth_l2_tnl, bit_mask, ip_fragmented, mask, frag);
+ DR_STE_SET_MASK_V(eth_l2_tnl, bit_mask, l3_ethertype, mask, ethertype);
+ DR_STE_SET_MASK(eth_l2_tnl, bit_mask, l3_type, mask, ip_version);
+
+ if (misc->vxlan_vni) {
+ MLX5_SET(ste_eth_l2_tnl, bit_mask,
+ l2_tunneling_network_id, (misc->vxlan_vni << 8));
+ misc->vxlan_vni = 0;
+ }
+
+ if (mask->svlan_tag || mask->cvlan_tag) {
+ MLX5_SET(ste_eth_l2_tnl, bit_mask, first_vlan_qualifier, -1);
+ mask->cvlan_tag = 0;
+ mask->svlan_tag = 0;
+ }
+}
+
+static int dr_ste_build_eth_l2_tnl_tag(struct mlx5dr_match_param *value,
+ struct mlx5dr_ste_build *sb,
+ u8 *hw_ste_p)
+{
+ struct mlx5dr_match_spec *spec = sb->inner ? &value->inner : &value->outer;
+ struct dr_hw_ste_format *hw_ste = (struct dr_hw_ste_format *)hw_ste_p;
+ struct mlx5dr_match_misc *misc = &value->misc;
+ u8 *tag = hw_ste->tag;
+
+ DR_STE_SET_TAG(eth_l2_tnl, tag, dmac_47_16, spec, dmac_47_16);
+ DR_STE_SET_TAG(eth_l2_tnl, tag, dmac_15_0, spec, dmac_15_0);
+ DR_STE_SET_TAG(eth_l2_tnl, tag, first_vlan_id, spec, first_vid);
+ DR_STE_SET_TAG(eth_l2_tnl, tag, first_cfi, spec, first_cfi);
+ DR_STE_SET_TAG(eth_l2_tnl, tag, ip_fragmented, spec, frag);
+ DR_STE_SET_TAG(eth_l2_tnl, tag, first_priority, spec, first_prio);
+ DR_STE_SET_TAG(eth_l2_tnl, tag, l3_ethertype, spec, ethertype);
+
+ if (misc->vxlan_vni) {
+ MLX5_SET(ste_eth_l2_tnl, tag, l2_tunneling_network_id,
+ (misc->vxlan_vni << 8));
+ misc->vxlan_vni = 0;
+ }
+
+ if (spec->cvlan_tag) {
+ MLX5_SET(ste_eth_l2_tnl, tag, first_vlan_qualifier, DR_STE_CVLAN);
+ spec->cvlan_tag = 0;
+ } else if (spec->svlan_tag) {
+ MLX5_SET(ste_eth_l2_tnl, tag, first_vlan_qualifier, DR_STE_SVLAN);
+ spec->svlan_tag = 0;
+ }
+
+ if (spec->ip_version) {
+ if (spec->ip_version == IP_VERSION_IPV4) {
+ MLX5_SET(ste_eth_l2_tnl, tag, l3_type, STE_IPV4);
+ spec->ip_version = 0;
+ } else if (spec->ip_version == IP_VERSION_IPV6) {
+ MLX5_SET(ste_eth_l2_tnl, tag, l3_type, STE_IPV6);
+ spec->ip_version = 0;
+ } else {
+ return -EINVAL;
+ }
+ }
+
+ return 0;
+}
+
+void mlx5dr_ste_build_eth_l2_tnl(struct mlx5dr_ste_build *sb,
+ struct mlx5dr_match_param *mask, bool inner, bool rx)
+{
+ dr_ste_build_eth_l2_tnl_bit_mask(mask, inner, sb->bit_mask);
+
+ sb->rx = rx;
+ sb->inner = inner;
+ sb->lu_type = MLX5DR_STE_LU_TYPE_ETHL2_TUNNELING_I;
+ sb->byte_mask = dr_ste_conv_bit_to_byte_mask(sb->bit_mask);
+ sb->ste_build_tag_func = &dr_ste_build_eth_l2_tnl_tag;
+}
+
+static void dr_ste_build_eth_l3_ipv4_misc_bit_mask(struct mlx5dr_match_param *value,
+ bool inner, u8 *bit_mask)
+{
+ struct mlx5dr_match_spec *mask = inner ? &value->inner : &value->outer;
+
+ DR_STE_SET_MASK_V(eth_l3_ipv4_misc, bit_mask, time_to_live, mask, ttl_hoplimit);
+}
+
+static int dr_ste_build_eth_l3_ipv4_misc_tag(struct mlx5dr_match_param *value,
+ struct mlx5dr_ste_build *sb,
+ u8 *hw_ste_p)
+{
+ struct dr_hw_ste_format *hw_ste = (struct dr_hw_ste_format *)hw_ste_p;
+ struct mlx5dr_match_spec *spec = sb->inner ? &value->inner : &value->outer;
+ u8 *tag = hw_ste->tag;
+
+ DR_STE_SET_TAG(eth_l3_ipv4_misc, tag, time_to_live, spec, ttl_hoplimit);
+
+ return 0;
+}
+
+void mlx5dr_ste_build_eth_l3_ipv4_misc(struct mlx5dr_ste_build *sb,
+ struct mlx5dr_match_param *mask,
+ bool inner, bool rx)
+{
+ dr_ste_build_eth_l3_ipv4_misc_bit_mask(mask, inner, sb->bit_mask);
+
+ sb->rx = rx;
+ sb->inner = inner;
+ sb->lu_type = DR_STE_CALC_LU_TYPE(ETHL3_IPV4_MISC, rx, inner);
+ sb->byte_mask = dr_ste_conv_bit_to_byte_mask(sb->bit_mask);
+ sb->ste_build_tag_func = &dr_ste_build_eth_l3_ipv4_misc_tag;
+}
+
+static void dr_ste_build_ipv6_l3_l4_bit_mask(struct mlx5dr_match_param *value,
+ bool inner, u8 *bit_mask)
+{
+ struct mlx5dr_match_spec *mask = inner ? &value->inner : &value->outer;
+
+ DR_STE_SET_MASK_V(eth_l4, bit_mask, dst_port, mask, tcp_dport);
+ DR_STE_SET_MASK_V(eth_l4, bit_mask, src_port, mask, tcp_sport);
+ DR_STE_SET_MASK_V(eth_l4, bit_mask, dst_port, mask, udp_dport);
+ DR_STE_SET_MASK_V(eth_l4, bit_mask, src_port, mask, udp_sport);
+ DR_STE_SET_MASK_V(eth_l4, bit_mask, protocol, mask, ip_protocol);
+ DR_STE_SET_MASK_V(eth_l4, bit_mask, fragmented, mask, frag);
+ DR_STE_SET_MASK_V(eth_l4, bit_mask, dscp, mask, ip_dscp);
+ DR_STE_SET_MASK_V(eth_l4, bit_mask, ecn, mask, ip_ecn);
+ DR_STE_SET_MASK_V(eth_l4, bit_mask, ipv6_hop_limit, mask, ttl_hoplimit);
+
+ if (mask->tcp_flags) {
+ DR_STE_SET_TCP_FLAGS(eth_l4, bit_mask, mask);
+ mask->tcp_flags = 0;
+ }
+}
+
+static int dr_ste_build_ipv6_l3_l4_tag(struct mlx5dr_match_param *value,
+ struct mlx5dr_ste_build *sb,
+ u8 *hw_ste_p)
+{
+ struct mlx5dr_match_spec *spec = sb->inner ? &value->inner : &value->outer;
+ struct dr_hw_ste_format *hw_ste = (struct dr_hw_ste_format *)hw_ste_p;
+ u8 *tag = hw_ste->tag;
+
+ DR_STE_SET_TAG(eth_l4, tag, dst_port, spec, tcp_dport);
+ DR_STE_SET_TAG(eth_l4, tag, src_port, spec, tcp_sport);
+ DR_STE_SET_TAG(eth_l4, tag, dst_port, spec, udp_dport);
+ DR_STE_SET_TAG(eth_l4, tag, src_port, spec, udp_sport);
+ DR_STE_SET_TAG(eth_l4, tag, protocol, spec, ip_protocol);
+ DR_STE_SET_TAG(eth_l4, tag, fragmented, spec, frag);
+ DR_STE_SET_TAG(eth_l4, tag, dscp, spec, ip_dscp);
+ DR_STE_SET_TAG(eth_l4, tag, ecn, spec, ip_ecn);
+ DR_STE_SET_TAG(eth_l4, tag, ipv6_hop_limit, spec, ttl_hoplimit);
+
+ if (spec->tcp_flags) {
+ DR_STE_SET_TCP_FLAGS(eth_l4, tag, spec);
+ spec->tcp_flags = 0;
+ }
+
+ return 0;
+}
+
+void mlx5dr_ste_build_ipv6_l3_l4(struct mlx5dr_ste_build *sb,
+ struct mlx5dr_match_param *mask,
+ bool inner, bool rx)
+{
+ dr_ste_build_ipv6_l3_l4_bit_mask(mask, inner, sb->bit_mask);
+
+ sb->rx = rx;
+ sb->inner = inner;
+ sb->lu_type = DR_STE_CALC_LU_TYPE(ETHL4, rx, inner);
+ sb->byte_mask = dr_ste_conv_bit_to_byte_mask(sb->bit_mask);
+ sb->ste_build_tag_func = &dr_ste_build_ipv6_l3_l4_tag;
+}
+
+static int dr_ste_build_empty_always_hit_tag(struct mlx5dr_match_param *value,
+ struct mlx5dr_ste_build *sb,
+ u8 *hw_ste_p)
+{
+ return 0;
+}
+
+void mlx5dr_ste_build_empty_always_hit(struct mlx5dr_ste_build *sb, bool rx)
+{
+ sb->rx = rx;
+ sb->lu_type = MLX5DR_STE_LU_TYPE_DONT_CARE;
+ sb->byte_mask = 0;
+ sb->ste_build_tag_func = &dr_ste_build_empty_always_hit_tag;
+}
+
+static void dr_ste_build_mpls_bit_mask(struct mlx5dr_match_param *value,
+ bool inner, u8 *bit_mask)
+{
+ struct mlx5dr_match_misc2 *misc2_mask = &value->misc2;
+
+ if (inner)
+ DR_STE_SET_MPLS_MASK(mpls, misc2_mask, inner, bit_mask);
+ else
+ DR_STE_SET_MPLS_MASK(mpls, misc2_mask, outer, bit_mask);
+}
+
+static int dr_ste_build_mpls_tag(struct mlx5dr_match_param *value,
+ struct mlx5dr_ste_build *sb,
+ u8 *hw_ste_p)
+{
+ struct dr_hw_ste_format *hw_ste = (struct dr_hw_ste_format *)hw_ste_p;
+ struct mlx5dr_match_misc2 *misc2_mask = &value->misc2;
+ u8 *tag = hw_ste->tag;
+
+ if (sb->inner)
+ DR_STE_SET_MPLS_TAG(mpls, misc2_mask, inner, tag);
+ else
+ DR_STE_SET_MPLS_TAG(mpls, misc2_mask, outer, tag);
+
+ return 0;
+}
+
+void mlx5dr_ste_build_mpls(struct mlx5dr_ste_build *sb,
+ struct mlx5dr_match_param *mask,
+ bool inner, bool rx)
+{
+ dr_ste_build_mpls_bit_mask(mask, inner, sb->bit_mask);
+
+ sb->rx = rx;
+ sb->inner = inner;
+ sb->lu_type = DR_STE_CALC_LU_TYPE(MPLS_FIRST, rx, inner);
+ sb->byte_mask = dr_ste_conv_bit_to_byte_mask(sb->bit_mask);
+ sb->ste_build_tag_func = &dr_ste_build_mpls_tag;
+}
+
+static void dr_ste_build_gre_bit_mask(struct mlx5dr_match_param *value,
+ bool inner, u8 *bit_mask)
+{
+ struct mlx5dr_match_misc *misc_mask = &value->misc;
+
+ DR_STE_SET_MASK_V(gre, bit_mask, gre_protocol, misc_mask, gre_protocol);
+ DR_STE_SET_MASK_V(gre, bit_mask, gre_k_present, misc_mask, gre_k_present);
+ DR_STE_SET_MASK_V(gre, bit_mask, gre_key_h, misc_mask, gre_key_h);
+ DR_STE_SET_MASK_V(gre, bit_mask, gre_key_l, misc_mask, gre_key_l);
+
+ DR_STE_SET_MASK_V(gre, bit_mask, gre_c_present, misc_mask, gre_c_present);
+ DR_STE_SET_MASK_V(gre, bit_mask, gre_s_present, misc_mask, gre_s_present);
+}
+
+static int dr_ste_build_gre_tag(struct mlx5dr_match_param *value,
+ struct mlx5dr_ste_build *sb,
+ u8 *hw_ste_p)
+{
+ struct dr_hw_ste_format *hw_ste = (struct dr_hw_ste_format *)hw_ste_p;
+ struct mlx5dr_match_misc *misc = &value->misc;
+ u8 *tag = hw_ste->tag;
+
+ DR_STE_SET_TAG(gre, tag, gre_protocol, misc, gre_protocol);
+
+ DR_STE_SET_TAG(gre, tag, gre_k_present, misc, gre_k_present);
+ DR_STE_SET_TAG(gre, tag, gre_key_h, misc, gre_key_h);
+ DR_STE_SET_TAG(gre, tag, gre_key_l, misc, gre_key_l);
+
+ DR_STE_SET_TAG(gre, tag, gre_c_present, misc, gre_c_present);
+
+ DR_STE_SET_TAG(gre, tag, gre_s_present, misc, gre_s_present);
+
+ return 0;
+}
+
+void mlx5dr_ste_build_gre(struct mlx5dr_ste_build *sb,
+ struct mlx5dr_match_param *mask, bool inner, bool rx)
+{
+ dr_ste_build_gre_bit_mask(mask, inner, sb->bit_mask);
+
+ sb->rx = rx;
+ sb->inner = inner;
+ sb->lu_type = MLX5DR_STE_LU_TYPE_GRE;
+ sb->byte_mask = dr_ste_conv_bit_to_byte_mask(sb->bit_mask);
+ sb->ste_build_tag_func = &dr_ste_build_gre_tag;
+}
+
+static void dr_ste_build_flex_parser_0_bit_mask(struct mlx5dr_match_param *value,
+ bool inner, u8 *bit_mask)
+{
+ struct mlx5dr_match_misc2 *misc_2_mask = &value->misc2;
+
+ if (DR_STE_IS_OUTER_MPLS_OVER_GRE_SET(misc_2_mask)) {
+ DR_STE_SET_MASK_V(flex_parser_0, bit_mask, parser_3_label,
+ misc_2_mask, outer_first_mpls_over_gre_label);
+
+ DR_STE_SET_MASK_V(flex_parser_0, bit_mask, parser_3_exp,
+ misc_2_mask, outer_first_mpls_over_gre_exp);
+
+ DR_STE_SET_MASK_V(flex_parser_0, bit_mask, parser_3_s_bos,
+ misc_2_mask, outer_first_mpls_over_gre_s_bos);
+
+ DR_STE_SET_MASK_V(flex_parser_0, bit_mask, parser_3_ttl,
+ misc_2_mask, outer_first_mpls_over_gre_ttl);
+ } else {
+ DR_STE_SET_MASK_V(flex_parser_0, bit_mask, parser_3_label,
+ misc_2_mask, outer_first_mpls_over_udp_label);
+
+ DR_STE_SET_MASK_V(flex_parser_0, bit_mask, parser_3_exp,
+ misc_2_mask, outer_first_mpls_over_udp_exp);
+
+ DR_STE_SET_MASK_V(flex_parser_0, bit_mask, parser_3_s_bos,
+ misc_2_mask, outer_first_mpls_over_udp_s_bos);
+
+ DR_STE_SET_MASK_V(flex_parser_0, bit_mask, parser_3_ttl,
+ misc_2_mask, outer_first_mpls_over_udp_ttl);
+ }
+}
+
+static int dr_ste_build_flex_parser_0_tag(struct mlx5dr_match_param *value,
+ struct mlx5dr_ste_build *sb,
+ u8 *hw_ste_p)
+{
+ struct dr_hw_ste_format *hw_ste = (struct dr_hw_ste_format *)hw_ste_p;
+ struct mlx5dr_match_misc2 *misc_2_mask = &value->misc2;
+ u8 *tag = hw_ste->tag;
+
+ if (DR_STE_IS_OUTER_MPLS_OVER_GRE_SET(misc_2_mask)) {
+ DR_STE_SET_TAG(flex_parser_0, tag, parser_3_label,
+ misc_2_mask, outer_first_mpls_over_gre_label);
+
+ DR_STE_SET_TAG(flex_parser_0, tag, parser_3_exp,
+ misc_2_mask, outer_first_mpls_over_gre_exp);
+
+ DR_STE_SET_TAG(flex_parser_0, tag, parser_3_s_bos,
+ misc_2_mask, outer_first_mpls_over_gre_s_bos);
+
+ DR_STE_SET_TAG(flex_parser_0, tag, parser_3_ttl,
+ misc_2_mask, outer_first_mpls_over_gre_ttl);
+ } else {
+ DR_STE_SET_TAG(flex_parser_0, tag, parser_3_label,
+ misc_2_mask, outer_first_mpls_over_udp_label);
+
+ DR_STE_SET_TAG(flex_parser_0, tag, parser_3_exp,
+ misc_2_mask, outer_first_mpls_over_udp_exp);
+
+ DR_STE_SET_TAG(flex_parser_0, tag, parser_3_s_bos,
+ misc_2_mask, outer_first_mpls_over_udp_s_bos);
+
+ DR_STE_SET_TAG(flex_parser_0, tag, parser_3_ttl,
+ misc_2_mask, outer_first_mpls_over_udp_ttl);
+ }
+ return 0;
+}
+
+void mlx5dr_ste_build_flex_parser_0(struct mlx5dr_ste_build *sb,
+ struct mlx5dr_match_param *mask,
+ bool inner, bool rx)
+{
+ dr_ste_build_flex_parser_0_bit_mask(mask, inner, sb->bit_mask);
+
+ sb->rx = rx;
+ sb->inner = inner;
+ sb->lu_type = MLX5DR_STE_LU_TYPE_FLEX_PARSER_0;
+ sb->byte_mask = dr_ste_conv_bit_to_byte_mask(sb->bit_mask);
+ sb->ste_build_tag_func = &dr_ste_build_flex_parser_0_tag;
+}
+
+#define ICMP_TYPE_OFFSET_FIRST_DW 24
+#define ICMP_CODE_OFFSET_FIRST_DW 16
+#define ICMP_HEADER_DATA_OFFSET_SECOND_DW 0
+
+static int dr_ste_build_flex_parser_1_bit_mask(struct mlx5dr_match_param *mask,
+ struct mlx5dr_cmd_caps *caps,
+ u8 *bit_mask)
+{
+ struct mlx5dr_match_misc3 *misc_3_mask = &mask->misc3;
+ bool is_ipv4_mask = DR_MASK_IS_FLEX_PARSER_ICMPV4_SET(misc_3_mask);
+ u32 icmp_header_data_mask;
+ u32 icmp_type_mask;
+ u32 icmp_code_mask;
+ int dw0_location;
+ int dw1_location;
+
+ if (is_ipv4_mask) {
+ icmp_header_data_mask = misc_3_mask->icmpv4_header_data;
+ icmp_type_mask = misc_3_mask->icmpv4_type;
+ icmp_code_mask = misc_3_mask->icmpv4_code;
+ dw0_location = caps->flex_parser_id_icmp_dw0;
+ dw1_location = caps->flex_parser_id_icmp_dw1;
+ } else {
+ icmp_header_data_mask = misc_3_mask->icmpv6_header_data;
+ icmp_type_mask = misc_3_mask->icmpv6_type;
+ icmp_code_mask = misc_3_mask->icmpv6_code;
+ dw0_location = caps->flex_parser_id_icmpv6_dw0;
+ dw1_location = caps->flex_parser_id_icmpv6_dw1;
+ }
+
+ switch (dw0_location) {
+ case 4:
+ if (icmp_type_mask) {
+ MLX5_SET(ste_flex_parser_1, bit_mask, flex_parser_4,
+ (icmp_type_mask << ICMP_TYPE_OFFSET_FIRST_DW));
+ if (is_ipv4_mask)
+ misc_3_mask->icmpv4_type = 0;
+ else
+ misc_3_mask->icmpv6_type = 0;
+ }
+ if (icmp_code_mask) {
+ u32 cur_val = MLX5_GET(ste_flex_parser_1, bit_mask,
+ flex_parser_4);
+ MLX5_SET(ste_flex_parser_1, bit_mask, flex_parser_4,
+ cur_val | (icmp_code_mask << ICMP_CODE_OFFSET_FIRST_DW));
+ if (is_ipv4_mask)
+ misc_3_mask->icmpv4_code = 0;
+ else
+ misc_3_mask->icmpv6_code = 0;
+ }
+ break;
+ default:
+ return -EINVAL;
+ }
+
+ switch (dw1_location) {
+ case 5:
+ if (icmp_header_data_mask) {
+ MLX5_SET(ste_flex_parser_1, bit_mask, flex_parser_5,
+ (icmp_header_data_mask << ICMP_HEADER_DATA_OFFSET_SECOND_DW));
+ if (is_ipv4_mask)
+ misc_3_mask->icmpv4_header_data = 0;
+ else
+ misc_3_mask->icmpv6_header_data = 0;
+ }
+ break;
+ default:
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
+static int dr_ste_build_flex_parser_1_tag(struct mlx5dr_match_param *value,
+ struct mlx5dr_ste_build *sb,
+ u8 *hw_ste_p)
+{
+ struct dr_hw_ste_format *hw_ste = (struct dr_hw_ste_format *)hw_ste_p;
+ struct mlx5dr_match_misc3 *misc_3 = &value->misc3;
+ u8 *tag = hw_ste->tag;
+ u32 icmp_header_data;
+ int dw0_location;
+ int dw1_location;
+ u32 icmp_type;
+ u32 icmp_code;
+ bool is_ipv4;
+
+ is_ipv4 = DR_MASK_IS_FLEX_PARSER_ICMPV4_SET(misc_3);
+ if (is_ipv4) {
+ icmp_header_data = misc_3->icmpv4_header_data;
+ icmp_type = misc_3->icmpv4_type;
+ icmp_code = misc_3->icmpv4_code;
+ dw0_location = sb->caps->flex_parser_id_icmp_dw0;
+ dw1_location = sb->caps->flex_parser_id_icmp_dw1;
+ } else {
+ icmp_header_data = misc_3->icmpv6_header_data;
+ icmp_type = misc_3->icmpv6_type;
+ icmp_code = misc_3->icmpv6_code;
+ dw0_location = sb->caps->flex_parser_id_icmpv6_dw0;
+ dw1_location = sb->caps->flex_parser_id_icmpv6_dw1;
+ }
+
+ switch (dw0_location) {
+ case 4:
+ if (icmp_type) {
+ MLX5_SET(ste_flex_parser_1, tag, flex_parser_4,
+ (icmp_type << ICMP_TYPE_OFFSET_FIRST_DW));
+ if (is_ipv4)
+ misc_3->icmpv4_type = 0;
+ else
+ misc_3->icmpv6_type = 0;
+ }
+
+ if (icmp_code) {
+ u32 cur_val = MLX5_GET(ste_flex_parser_1, tag,
+ flex_parser_4);
+ MLX5_SET(ste_flex_parser_1, tag, flex_parser_4,
+ cur_val | (icmp_code << ICMP_CODE_OFFSET_FIRST_DW));
+ if (is_ipv4)
+ misc_3->icmpv4_code = 0;
+ else
+ misc_3->icmpv6_code = 0;
+ }
+ break;
+ default:
+ return -EINVAL;
+ }
+
+ switch (dw1_location) {
+ case 5:
+ if (icmp_header_data) {
+ MLX5_SET(ste_flex_parser_1, tag, flex_parser_5,
+ (icmp_header_data << ICMP_HEADER_DATA_OFFSET_SECOND_DW));
+ if (is_ipv4)
+ misc_3->icmpv4_header_data = 0;
+ else
+ misc_3->icmpv6_header_data = 0;
+ }
+ break;
+ default:
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
+int mlx5dr_ste_build_flex_parser_1(struct mlx5dr_ste_build *sb,
+ struct mlx5dr_match_param *mask,
+ struct mlx5dr_cmd_caps *caps,
+ bool inner, bool rx)
+{
+ int ret;
+
+ ret = dr_ste_build_flex_parser_1_bit_mask(mask, caps, sb->bit_mask);
+ if (ret)
+ return ret;
+
+ sb->rx = rx;
+ sb->inner = inner;
+ sb->caps = caps;
+ sb->lu_type = MLX5DR_STE_LU_TYPE_FLEX_PARSER_1;
+ sb->byte_mask = dr_ste_conv_bit_to_byte_mask(sb->bit_mask);
+ sb->ste_build_tag_func = &dr_ste_build_flex_parser_1_tag;
+
+ return 0;
+}
+
+static void dr_ste_build_general_purpose_bit_mask(struct mlx5dr_match_param *value,
+ bool inner, u8 *bit_mask)
+{
+ struct mlx5dr_match_misc2 *misc_2_mask = &value->misc2;
+
+ DR_STE_SET_MASK_V(general_purpose, bit_mask,
+ general_purpose_lookup_field, misc_2_mask,
+ metadata_reg_a);
+}
+
+static int dr_ste_build_general_purpose_tag(struct mlx5dr_match_param *value,
+ struct mlx5dr_ste_build *sb,
+ u8 *hw_ste_p)
+{
+ struct dr_hw_ste_format *hw_ste = (struct dr_hw_ste_format *)hw_ste_p;
+ struct mlx5dr_match_misc2 *misc_2_mask = &value->misc2;
+ u8 *tag = hw_ste->tag;
+
+ DR_STE_SET_TAG(general_purpose, tag, general_purpose_lookup_field,
+ misc_2_mask, metadata_reg_a);
+
+ return 0;
+}
+
+void mlx5dr_ste_build_general_purpose(struct mlx5dr_ste_build *sb,
+ struct mlx5dr_match_param *mask,
+ bool inner, bool rx)
+{
+ dr_ste_build_general_purpose_bit_mask(mask, inner, sb->bit_mask);
+
+ sb->rx = rx;
+ sb->inner = inner;
+ sb->lu_type = MLX5DR_STE_LU_TYPE_GENERAL_PURPOSE;
+ sb->byte_mask = dr_ste_conv_bit_to_byte_mask(sb->bit_mask);
+ sb->ste_build_tag_func = &dr_ste_build_general_purpose_tag;
+}
+
+static void dr_ste_build_eth_l4_misc_bit_mask(struct mlx5dr_match_param *value,
+ bool inner, u8 *bit_mask)
+{
+ struct mlx5dr_match_misc3 *misc_3_mask = &value->misc3;
+
+ if (inner) {
+ DR_STE_SET_MASK_V(eth_l4_misc, bit_mask, seq_num, misc_3_mask,
+ inner_tcp_seq_num);
+ DR_STE_SET_MASK_V(eth_l4_misc, bit_mask, ack_num, misc_3_mask,
+ inner_tcp_ack_num);
+ } else {
+ DR_STE_SET_MASK_V(eth_l4_misc, bit_mask, seq_num, misc_3_mask,
+ outer_tcp_seq_num);
+ DR_STE_SET_MASK_V(eth_l4_misc, bit_mask, ack_num, misc_3_mask,
+ outer_tcp_ack_num);
+ }
+}
+
+static int dr_ste_build_eth_l4_misc_tag(struct mlx5dr_match_param *value,
+ struct mlx5dr_ste_build *sb,
+ u8 *hw_ste_p)
+{
+ struct dr_hw_ste_format *hw_ste = (struct dr_hw_ste_format *)hw_ste_p;
+ struct mlx5dr_match_misc3 *misc3 = &value->misc3;
+ u8 *tag = hw_ste->tag;
+
+ if (sb->inner) {
+ DR_STE_SET_TAG(eth_l4_misc, tag, seq_num, misc3, inner_tcp_seq_num);
+ DR_STE_SET_TAG(eth_l4_misc, tag, ack_num, misc3, inner_tcp_ack_num);
+ } else {
+ DR_STE_SET_TAG(eth_l4_misc, tag, seq_num, misc3, outer_tcp_seq_num);
+ DR_STE_SET_TAG(eth_l4_misc, tag, ack_num, misc3, outer_tcp_ack_num);
+ }
+
+ return 0;
+}
+
+void mlx5dr_ste_build_eth_l4_misc(struct mlx5dr_ste_build *sb,
+ struct mlx5dr_match_param *mask,
+ bool inner, bool rx)
+{
+ dr_ste_build_eth_l4_misc_bit_mask(mask, inner, sb->bit_mask);
+
+ sb->rx = rx;
+ sb->inner = inner;
+ sb->lu_type = DR_STE_CALC_LU_TYPE(ETHL4_MISC, rx, inner);
+ sb->byte_mask = dr_ste_conv_bit_to_byte_mask(sb->bit_mask);
+ sb->ste_build_tag_func = &dr_ste_build_eth_l4_misc_tag;
+}
+
+static void dr_ste_build_flex_parser_tnl_bit_mask(struct mlx5dr_match_param *value,
+ bool inner, u8 *bit_mask)
+{
+ struct mlx5dr_match_misc3 *misc_3_mask = &value->misc3;
+
+ if (misc_3_mask->outer_vxlan_gpe_flags ||
+ misc_3_mask->outer_vxlan_gpe_next_protocol) {
+ MLX5_SET(ste_flex_parser_tnl, bit_mask,
+ flex_parser_tunneling_header_63_32,
+ (misc_3_mask->outer_vxlan_gpe_flags << 24) |
+ (misc_3_mask->outer_vxlan_gpe_next_protocol));
+ misc_3_mask->outer_vxlan_gpe_flags = 0;
+ misc_3_mask->outer_vxlan_gpe_next_protocol = 0;
+ }
+
+ if (misc_3_mask->outer_vxlan_gpe_vni) {
+ MLX5_SET(ste_flex_parser_tnl, bit_mask,
+ flex_parser_tunneling_header_31_0,
+ misc_3_mask->outer_vxlan_gpe_vni << 8);
+ misc_3_mask->outer_vxlan_gpe_vni = 0;
+ }
+}
+
+static int dr_ste_build_flex_parser_tnl_tag(struct mlx5dr_match_param *value,
+ struct mlx5dr_ste_build *sb,
+ u8 *hw_ste_p)
+{
+ struct dr_hw_ste_format *hw_ste = (struct dr_hw_ste_format *)hw_ste_p;
+ struct mlx5dr_match_misc3 *misc3 = &value->misc3;
+ u8 *tag = hw_ste->tag;
+
+ if (misc3->outer_vxlan_gpe_flags ||
+ misc3->outer_vxlan_gpe_next_protocol) {
+ MLX5_SET(ste_flex_parser_tnl, tag,
+ flex_parser_tunneling_header_63_32,
+ (misc3->outer_vxlan_gpe_flags << 24) |
+ (misc3->outer_vxlan_gpe_next_protocol));
+ misc3->outer_vxlan_gpe_flags = 0;
+ misc3->outer_vxlan_gpe_next_protocol = 0;
+ }
+
+ if (misc3->outer_vxlan_gpe_vni) {
+ MLX5_SET(ste_flex_parser_tnl, tag,
+ flex_parser_tunneling_header_31_0,
+ misc3->outer_vxlan_gpe_vni << 8);
+ misc3->outer_vxlan_gpe_vni = 0;
+ }
+
+ return 0;
+}
+
+void mlx5dr_ste_build_flex_parser_tnl(struct mlx5dr_ste_build *sb,
+ struct mlx5dr_match_param *mask,
+ bool inner, bool rx)
+{
+ dr_ste_build_flex_parser_tnl_bit_mask(mask, inner, sb->bit_mask);
+
+ sb->rx = rx;
+ sb->inner = inner;
+ sb->lu_type = MLX5DR_STE_LU_TYPE_FLEX_PARSER_TNL_HEADER;
+ sb->byte_mask = dr_ste_conv_bit_to_byte_mask(sb->bit_mask);
+ sb->ste_build_tag_func = &dr_ste_build_flex_parser_tnl_tag;
+}
+
+static void dr_ste_build_register_0_bit_mask(struct mlx5dr_match_param *value,
+ u8 *bit_mask)
+{
+ struct mlx5dr_match_misc2 *misc_2_mask = &value->misc2;
+
+ DR_STE_SET_MASK_V(register_0, bit_mask, register_0_h,
+ misc_2_mask, metadata_reg_c_0);
+ DR_STE_SET_MASK_V(register_0, bit_mask, register_0_l,
+ misc_2_mask, metadata_reg_c_1);
+ DR_STE_SET_MASK_V(register_0, bit_mask, register_1_h,
+ misc_2_mask, metadata_reg_c_2);
+ DR_STE_SET_MASK_V(register_0, bit_mask, register_1_l,
+ misc_2_mask, metadata_reg_c_3);
+}
+
+static int dr_ste_build_register_0_tag(struct mlx5dr_match_param *value,
+ struct mlx5dr_ste_build *sb,
+ u8 *hw_ste_p)
+{
+ struct dr_hw_ste_format *hw_ste = (struct dr_hw_ste_format *)hw_ste_p;
+ struct mlx5dr_match_misc2 *misc2 = &value->misc2;
+ u8 *tag = hw_ste->tag;
+
+ DR_STE_SET_TAG(register_0, tag, register_0_h, misc2, metadata_reg_c_0);
+ DR_STE_SET_TAG(register_0, tag, register_0_l, misc2, metadata_reg_c_1);
+ DR_STE_SET_TAG(register_0, tag, register_1_h, misc2, metadata_reg_c_2);
+ DR_STE_SET_TAG(register_0, tag, register_1_l, misc2, metadata_reg_c_3);
+
+ return 0;
+}
+
+void mlx5dr_ste_build_register_0(struct mlx5dr_ste_build *sb,
+ struct mlx5dr_match_param *mask,
+ bool inner, bool rx)
+{
+ dr_ste_build_register_0_bit_mask(mask, sb->bit_mask);
+
+ sb->rx = rx;
+ sb->inner = inner;
+ sb->lu_type = MLX5DR_STE_LU_TYPE_STEERING_REGISTERS_0;
+ sb->byte_mask = dr_ste_conv_bit_to_byte_mask(sb->bit_mask);
+ sb->ste_build_tag_func = &dr_ste_build_register_0_tag;
+}
+
+static void dr_ste_build_register_1_bit_mask(struct mlx5dr_match_param *value,
+ u8 *bit_mask)
+{
+ struct mlx5dr_match_misc2 *misc_2_mask = &value->misc2;
+
+ DR_STE_SET_MASK_V(register_1, bit_mask, register_2_h,
+ misc_2_mask, metadata_reg_c_4);
+ DR_STE_SET_MASK_V(register_1, bit_mask, register_2_l,
+ misc_2_mask, metadata_reg_c_5);
+ DR_STE_SET_MASK_V(register_1, bit_mask, register_3_h,
+ misc_2_mask, metadata_reg_c_6);
+ DR_STE_SET_MASK_V(register_1, bit_mask, register_3_l,
+ misc_2_mask, metadata_reg_c_7);
+}
+
+static int dr_ste_build_register_1_tag(struct mlx5dr_match_param *value,
+ struct mlx5dr_ste_build *sb,
+ u8 *hw_ste_p)
+{
+ struct dr_hw_ste_format *hw_ste = (struct dr_hw_ste_format *)hw_ste_p;
+ struct mlx5dr_match_misc2 *misc2 = &value->misc2;
+ u8 *tag = hw_ste->tag;
+
+ DR_STE_SET_TAG(register_1, tag, register_2_h, misc2, metadata_reg_c_4);
+ DR_STE_SET_TAG(register_1, tag, register_2_l, misc2, metadata_reg_c_5);
+ DR_STE_SET_TAG(register_1, tag, register_3_h, misc2, metadata_reg_c_6);
+ DR_STE_SET_TAG(register_1, tag, register_3_l, misc2, metadata_reg_c_7);
+
+ return 0;
+}
+
+void mlx5dr_ste_build_register_1(struct mlx5dr_ste_build *sb,
+ struct mlx5dr_match_param *mask,
+ bool inner, bool rx)
+{
+ dr_ste_build_register_1_bit_mask(mask, sb->bit_mask);
+
+ sb->rx = rx;
+ sb->inner = inner;
+ sb->lu_type = MLX5DR_STE_LU_TYPE_STEERING_REGISTERS_1;
+ sb->byte_mask = dr_ste_conv_bit_to_byte_mask(sb->bit_mask);
+ sb->ste_build_tag_func = &dr_ste_build_register_1_tag;
+}
+
+static int dr_ste_build_src_gvmi_qpn_bit_mask(struct mlx5dr_match_param *value,
+ u8 *bit_mask)
+{
+ struct mlx5dr_match_misc *misc_mask = &value->misc;
+
+ if (misc_mask->source_port != 0xffff)
+ return -EINVAL;
+
+ DR_STE_SET_MASK(src_gvmi_qp, bit_mask, source_gvmi, misc_mask, source_port);
+ DR_STE_SET_MASK(src_gvmi_qp, bit_mask, source_qp, misc_mask, source_sqn);
+
+ return 0;
+}
+
+static int dr_ste_build_src_gvmi_qpn_tag(struct mlx5dr_match_param *value,
+ struct mlx5dr_ste_build *sb,
+ u8 *hw_ste_p)
+{
+ struct dr_hw_ste_format *hw_ste = (struct dr_hw_ste_format *)hw_ste_p;
+ struct mlx5dr_match_misc *misc = &value->misc;
+ struct mlx5dr_cmd_vport_cap *vport_cap;
+ u8 *tag = hw_ste->tag;
+
+ DR_STE_SET_TAG(src_gvmi_qp, tag, source_qp, misc, source_sqn);
+
+ vport_cap = mlx5dr_get_vport_cap(sb->caps, misc->source_port);
+ if (!vport_cap)
+ return -EINVAL;
+
+ if (vport_cap->vport_gvmi)
+ MLX5_SET(ste_src_gvmi_qp, tag, source_gvmi, vport_cap->vport_gvmi);
+
+ misc->source_port = 0;
+
+ return 0;
+}
+
+int mlx5dr_ste_build_src_gvmi_qpn(struct mlx5dr_ste_build *sb,
+ struct mlx5dr_match_param *mask,
+ struct mlx5dr_cmd_caps *caps,
+ bool inner, bool rx)
+{
+ int ret;
+
+ ret = dr_ste_build_src_gvmi_qpn_bit_mask(mask, sb->bit_mask);
+ if (ret)
+ return ret;
+
+ sb->rx = rx;
+ sb->caps = caps;
+ sb->inner = inner;
+ sb->lu_type = MLX5DR_STE_LU_TYPE_SRC_GVMI_AND_QP;
+ sb->byte_mask = dr_ste_conv_bit_to_byte_mask(sb->bit_mask);
+ sb->ste_build_tag_func = &dr_ste_build_src_gvmi_qpn_tag;
+
+ return 0;
+}
--
2.21.0
^ permalink raw reply related
* [net-next V2 09/18] net/mlx5: DR, Expose steering matcher functionality
From: Saeed Mahameed @ 2019-09-03 20:04 UTC (permalink / raw)
To: David S. Miller
Cc: netdev@vger.kernel.org, Alex Vesker, Erez Shitrit, Mark Bloch,
Saeed Mahameed
In-Reply-To: <20190903200409.14406-1-saeedm@mellanox.com>
From: Alex Vesker <valex@mellanox.com>
Matcher defines which packets fields are matched when a packet arrives.
Matcher is a part of a table and can contain one or more rules. Where
rule defines specific values of the matcher's mask definition.
Signed-off-by: Alex Vesker <valex@mellanox.com>
Reviewed-by: Erez Shitrit <erezsh@mellanox.com>
Reviewed-by: Mark Bloch <markb@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
.../mellanox/mlx5/core/steering/dr_matcher.c | 770 ++++++++++++++++++
1 file changed, 770 insertions(+)
create mode 100644 drivers/net/ethernet/mellanox/mlx5/core/steering/dr_matcher.c
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_matcher.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_matcher.c
new file mode 100644
index 000000000000..01008cd66f75
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_matcher.c
@@ -0,0 +1,770 @@
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+/* Copyright (c) 2019 Mellanox Technologies. */
+
+#include "dr_types.h"
+
+static bool dr_mask_is_smac_set(struct mlx5dr_match_spec *spec)
+{
+ return (spec->smac_47_16 || spec->smac_15_0);
+}
+
+static bool dr_mask_is_dmac_set(struct mlx5dr_match_spec *spec)
+{
+ return (spec->dmac_47_16 || spec->dmac_15_0);
+}
+
+static bool dr_mask_is_src_addr_set(struct mlx5dr_match_spec *spec)
+{
+ return (spec->src_ip_127_96 || spec->src_ip_95_64 ||
+ spec->src_ip_63_32 || spec->src_ip_31_0);
+}
+
+static bool dr_mask_is_dst_addr_set(struct mlx5dr_match_spec *spec)
+{
+ return (spec->dst_ip_127_96 || spec->dst_ip_95_64 ||
+ spec->dst_ip_63_32 || spec->dst_ip_31_0);
+}
+
+static bool dr_mask_is_l3_base_set(struct mlx5dr_match_spec *spec)
+{
+ return (spec->ip_protocol || spec->frag || spec->tcp_flags ||
+ spec->ip_ecn || spec->ip_dscp);
+}
+
+static bool dr_mask_is_tcp_udp_base_set(struct mlx5dr_match_spec *spec)
+{
+ return (spec->tcp_sport || spec->tcp_dport ||
+ spec->udp_sport || spec->udp_dport);
+}
+
+static bool dr_mask_is_ipv4_set(struct mlx5dr_match_spec *spec)
+{
+ return (spec->dst_ip_31_0 || spec->src_ip_31_0);
+}
+
+static bool dr_mask_is_ipv4_5_tuple_set(struct mlx5dr_match_spec *spec)
+{
+ return (dr_mask_is_l3_base_set(spec) ||
+ dr_mask_is_tcp_udp_base_set(spec) ||
+ dr_mask_is_ipv4_set(spec));
+}
+
+static bool dr_mask_is_eth_l2_tnl_set(struct mlx5dr_match_misc *misc)
+{
+ return misc->vxlan_vni;
+}
+
+static bool dr_mask_is_ttl_set(struct mlx5dr_match_spec *spec)
+{
+ return spec->ttl_hoplimit;
+}
+
+#define DR_MASK_IS_L2_DST(_spec, _misc, _inner_outer) (_spec.first_vid || \
+ (_spec).first_cfi || (_spec).first_prio || (_spec).cvlan_tag || \
+ (_spec).svlan_tag || (_spec).dmac_47_16 || (_spec).dmac_15_0 || \
+ (_spec).ethertype || (_spec).ip_version || \
+ (_misc)._inner_outer##_second_vid || \
+ (_misc)._inner_outer##_second_cfi || \
+ (_misc)._inner_outer##_second_prio || \
+ (_misc)._inner_outer##_second_cvlan_tag || \
+ (_misc)._inner_outer##_second_svlan_tag)
+
+#define DR_MASK_IS_ETH_L4_SET(_spec, _misc, _inner_outer) ( \
+ dr_mask_is_l3_base_set(&(_spec)) || \
+ dr_mask_is_tcp_udp_base_set(&(_spec)) || \
+ dr_mask_is_ttl_set(&(_spec)) || \
+ (_misc)._inner_outer##_ipv6_flow_label)
+
+#define DR_MASK_IS_ETH_L4_MISC_SET(_misc3, _inner_outer) ( \
+ (_misc3)._inner_outer##_tcp_seq_num || \
+ (_misc3)._inner_outer##_tcp_ack_num)
+
+#define DR_MASK_IS_FIRST_MPLS_SET(_misc2, _inner_outer) ( \
+ (_misc2)._inner_outer##_first_mpls_label || \
+ (_misc2)._inner_outer##_first_mpls_exp || \
+ (_misc2)._inner_outer##_first_mpls_s_bos || \
+ (_misc2)._inner_outer##_first_mpls_ttl)
+
+static bool dr_mask_is_gre_set(struct mlx5dr_match_misc *misc)
+{
+ return (misc->gre_key_h || misc->gre_key_l ||
+ misc->gre_protocol || misc->gre_c_present ||
+ misc->gre_k_present || misc->gre_s_present);
+}
+
+#define DR_MASK_IS_OUTER_MPLS_OVER_GRE_UDP_SET(_misc2, gre_udp) ( \
+ (_misc2).outer_first_mpls_over_##gre_udp##_label || \
+ (_misc2).outer_first_mpls_over_##gre_udp##_exp || \
+ (_misc2).outer_first_mpls_over_##gre_udp##_s_bos || \
+ (_misc2).outer_first_mpls_over_##gre_udp##_ttl)
+
+#define DR_MASK_IS_FLEX_PARSER_0_SET(_misc2) ( \
+ DR_MASK_IS_OUTER_MPLS_OVER_GRE_UDP_SET((_misc2), gre) || \
+ DR_MASK_IS_OUTER_MPLS_OVER_GRE_UDP_SET((_misc2), udp))
+
+static bool dr_mask_is_flex_parser_tnl_set(struct mlx5dr_match_misc3 *misc3)
+{
+ return (misc3->outer_vxlan_gpe_vni ||
+ misc3->outer_vxlan_gpe_next_protocol ||
+ misc3->outer_vxlan_gpe_flags);
+}
+
+static bool dr_mask_is_flex_parser_icmpv6_set(struct mlx5dr_match_misc3 *misc3)
+{
+ return (misc3->icmpv6_type || misc3->icmpv6_code ||
+ misc3->icmpv6_header_data);
+}
+
+static bool dr_mask_is_wqe_metadata_set(struct mlx5dr_match_misc2 *misc2)
+{
+ return misc2->metadata_reg_a;
+}
+
+static bool dr_mask_is_reg_c_0_3_set(struct mlx5dr_match_misc2 *misc2)
+{
+ return (misc2->metadata_reg_c_0 || misc2->metadata_reg_c_1 ||
+ misc2->metadata_reg_c_2 || misc2->metadata_reg_c_3);
+}
+
+static bool dr_mask_is_reg_c_4_7_set(struct mlx5dr_match_misc2 *misc2)
+{
+ return (misc2->metadata_reg_c_4 || misc2->metadata_reg_c_5 ||
+ misc2->metadata_reg_c_6 || misc2->metadata_reg_c_7);
+}
+
+static bool dr_mask_is_gvmi_or_qpn_set(struct mlx5dr_match_misc *misc)
+{
+ return (misc->source_sqn || misc->source_port);
+}
+
+static bool
+dr_matcher_supp_flex_parser_vxlan_gpe(struct mlx5dr_domain *dmn)
+{
+ return dmn->info.caps.flex_protocols &
+ MLX5_FLEX_PARSER_VXLAN_GPE_ENABLED;
+}
+
+int mlx5dr_matcher_select_builders(struct mlx5dr_matcher *matcher,
+ struct mlx5dr_matcher_rx_tx *nic_matcher,
+ bool ipv6)
+{
+ if (ipv6) {
+ nic_matcher->ste_builder = nic_matcher->ste_builder6;
+ nic_matcher->num_of_builders = nic_matcher->num_of_builders6;
+ } else {
+ nic_matcher->ste_builder = nic_matcher->ste_builder4;
+ nic_matcher->num_of_builders = nic_matcher->num_of_builders4;
+ }
+
+ if (!nic_matcher->num_of_builders) {
+ mlx5dr_dbg(matcher->tbl->dmn,
+ "Rule not supported on this matcher due to IP related fields\n");
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
+static int dr_matcher_set_ste_builders(struct mlx5dr_matcher *matcher,
+ struct mlx5dr_matcher_rx_tx *nic_matcher,
+ bool ipv6)
+{
+ struct mlx5dr_domain_rx_tx *nic_dmn = nic_matcher->nic_tbl->nic_dmn;
+ struct mlx5dr_domain *dmn = matcher->tbl->dmn;
+ struct mlx5dr_match_param mask = {};
+ struct mlx5dr_match_misc3 *misc3;
+ struct mlx5dr_ste_build *sb;
+ u8 *num_of_builders;
+ bool inner, rx;
+ int idx = 0;
+ int ret, i;
+
+ if (ipv6) {
+ sb = nic_matcher->ste_builder6;
+ num_of_builders = &nic_matcher->num_of_builders6;
+ } else {
+ sb = nic_matcher->ste_builder4;
+ num_of_builders = &nic_matcher->num_of_builders4;
+ }
+
+ rx = nic_dmn->ste_type == MLX5DR_STE_TYPE_RX;
+
+ /* Create a temporary mask to track and clear used mask fields */
+ if (matcher->match_criteria & DR_MATCHER_CRITERIA_OUTER)
+ mask.outer = matcher->mask.outer;
+
+ if (matcher->match_criteria & DR_MATCHER_CRITERIA_MISC)
+ mask.misc = matcher->mask.misc;
+
+ if (matcher->match_criteria & DR_MATCHER_CRITERIA_INNER)
+ mask.inner = matcher->mask.inner;
+
+ if (matcher->match_criteria & DR_MATCHER_CRITERIA_MISC2)
+ mask.misc2 = matcher->mask.misc2;
+
+ if (matcher->match_criteria & DR_MATCHER_CRITERIA_MISC3)
+ mask.misc3 = matcher->mask.misc3;
+
+ ret = mlx5dr_ste_build_pre_check(dmn, matcher->match_criteria,
+ &matcher->mask, NULL);
+ if (ret)
+ return ret;
+
+ /* Outer */
+ if (matcher->match_criteria & (DR_MATCHER_CRITERIA_OUTER |
+ DR_MATCHER_CRITERIA_MISC |
+ DR_MATCHER_CRITERIA_MISC2 |
+ DR_MATCHER_CRITERIA_MISC3)) {
+ inner = false;
+
+ if (dr_mask_is_wqe_metadata_set(&mask.misc2))
+ mlx5dr_ste_build_general_purpose(&sb[idx++], &mask, inner, rx);
+
+ if (dr_mask_is_reg_c_0_3_set(&mask.misc2))
+ mlx5dr_ste_build_register_0(&sb[idx++], &mask, inner, rx);
+
+ if (dr_mask_is_reg_c_4_7_set(&mask.misc2))
+ mlx5dr_ste_build_register_1(&sb[idx++], &mask, inner, rx);
+
+ if (dr_mask_is_gvmi_or_qpn_set(&mask.misc) &&
+ (dmn->type == MLX5DR_DOMAIN_TYPE_FDB ||
+ dmn->type == MLX5DR_DOMAIN_TYPE_NIC_RX)) {
+ ret = mlx5dr_ste_build_src_gvmi_qpn(&sb[idx++], &mask,
+ &dmn->info.caps,
+ inner, rx);
+ if (ret)
+ return ret;
+ }
+
+ if (dr_mask_is_smac_set(&mask.outer) &&
+ dr_mask_is_dmac_set(&mask.outer)) {
+ ret = mlx5dr_ste_build_eth_l2_src_des(&sb[idx++], &mask,
+ inner, rx);
+ if (ret)
+ return ret;
+ }
+
+ if (dr_mask_is_smac_set(&mask.outer))
+ mlx5dr_ste_build_eth_l2_src(&sb[idx++], &mask, inner, rx);
+
+ if (DR_MASK_IS_L2_DST(mask.outer, mask.misc, outer))
+ mlx5dr_ste_build_eth_l2_dst(&sb[idx++], &mask, inner, rx);
+
+ if (ipv6) {
+ if (dr_mask_is_dst_addr_set(&mask.outer))
+ mlx5dr_ste_build_eth_l3_ipv6_dst(&sb[idx++], &mask,
+ inner, rx);
+
+ if (dr_mask_is_src_addr_set(&mask.outer))
+ mlx5dr_ste_build_eth_l3_ipv6_src(&sb[idx++], &mask,
+ inner, rx);
+
+ if (DR_MASK_IS_ETH_L4_SET(mask.outer, mask.misc, outer))
+ mlx5dr_ste_build_ipv6_l3_l4(&sb[idx++], &mask,
+ inner, rx);
+ } else {
+ if (dr_mask_is_ipv4_5_tuple_set(&mask.outer))
+ mlx5dr_ste_build_eth_l3_ipv4_5_tuple(&sb[idx++], &mask,
+ inner, rx);
+
+ if (dr_mask_is_ttl_set(&mask.outer))
+ mlx5dr_ste_build_eth_l3_ipv4_misc(&sb[idx++], &mask,
+ inner, rx);
+ }
+
+ if (dr_mask_is_flex_parser_tnl_set(&mask.misc3) &&
+ dr_matcher_supp_flex_parser_vxlan_gpe(dmn))
+ mlx5dr_ste_build_flex_parser_tnl(&sb[idx++], &mask,
+ inner, rx);
+
+ if (DR_MASK_IS_ETH_L4_MISC_SET(mask.misc3, outer))
+ mlx5dr_ste_build_eth_l4_misc(&sb[idx++], &mask, inner, rx);
+
+ if (DR_MASK_IS_FIRST_MPLS_SET(mask.misc2, outer))
+ mlx5dr_ste_build_mpls(&sb[idx++], &mask, inner, rx);
+
+ if (DR_MASK_IS_FLEX_PARSER_0_SET(mask.misc2))
+ mlx5dr_ste_build_flex_parser_0(&sb[idx++], &mask,
+ inner, rx);
+
+ misc3 = &mask.misc3;
+ if ((DR_MASK_IS_FLEX_PARSER_ICMPV4_SET(misc3) &&
+ mlx5dr_matcher_supp_flex_parser_icmp_v4(&dmn->info.caps)) ||
+ (dr_mask_is_flex_parser_icmpv6_set(&mask.misc3) &&
+ mlx5dr_matcher_supp_flex_parser_icmp_v6(&dmn->info.caps))) {
+ ret = mlx5dr_ste_build_flex_parser_1(&sb[idx++],
+ &mask, &dmn->info.caps,
+ inner, rx);
+ if (ret)
+ return ret;
+ }
+ if (dr_mask_is_gre_set(&mask.misc))
+ mlx5dr_ste_build_gre(&sb[idx++], &mask, inner, rx);
+ }
+
+ /* Inner */
+ if (matcher->match_criteria & (DR_MATCHER_CRITERIA_INNER |
+ DR_MATCHER_CRITERIA_MISC |
+ DR_MATCHER_CRITERIA_MISC2 |
+ DR_MATCHER_CRITERIA_MISC3)) {
+ inner = true;
+
+ if (dr_mask_is_eth_l2_tnl_set(&mask.misc))
+ mlx5dr_ste_build_eth_l2_tnl(&sb[idx++], &mask, inner, rx);
+
+ if (dr_mask_is_smac_set(&mask.inner) &&
+ dr_mask_is_dmac_set(&mask.inner)) {
+ ret = mlx5dr_ste_build_eth_l2_src_des(&sb[idx++],
+ &mask, inner, rx);
+ if (ret)
+ return ret;
+ }
+
+ if (dr_mask_is_smac_set(&mask.inner))
+ mlx5dr_ste_build_eth_l2_src(&sb[idx++], &mask, inner, rx);
+
+ if (DR_MASK_IS_L2_DST(mask.inner, mask.misc, inner))
+ mlx5dr_ste_build_eth_l2_dst(&sb[idx++], &mask, inner, rx);
+
+ if (ipv6) {
+ if (dr_mask_is_dst_addr_set(&mask.inner))
+ mlx5dr_ste_build_eth_l3_ipv6_dst(&sb[idx++], &mask,
+ inner, rx);
+
+ if (dr_mask_is_src_addr_set(&mask.inner))
+ mlx5dr_ste_build_eth_l3_ipv6_src(&sb[idx++], &mask,
+ inner, rx);
+
+ if (DR_MASK_IS_ETH_L4_SET(mask.inner, mask.misc, inner))
+ mlx5dr_ste_build_ipv6_l3_l4(&sb[idx++], &mask,
+ inner, rx);
+ } else {
+ if (dr_mask_is_ipv4_5_tuple_set(&mask.inner))
+ mlx5dr_ste_build_eth_l3_ipv4_5_tuple(&sb[idx++], &mask,
+ inner, rx);
+
+ if (dr_mask_is_ttl_set(&mask.inner))
+ mlx5dr_ste_build_eth_l3_ipv4_misc(&sb[idx++], &mask,
+ inner, rx);
+ }
+
+ if (DR_MASK_IS_ETH_L4_MISC_SET(mask.misc3, inner))
+ mlx5dr_ste_build_eth_l4_misc(&sb[idx++], &mask, inner, rx);
+
+ if (DR_MASK_IS_FIRST_MPLS_SET(mask.misc2, inner))
+ mlx5dr_ste_build_mpls(&sb[idx++], &mask, inner, rx);
+
+ if (DR_MASK_IS_FLEX_PARSER_0_SET(mask.misc2))
+ mlx5dr_ste_build_flex_parser_0(&sb[idx++], &mask, inner, rx);
+ }
+ /* Empty matcher, takes all */
+ if (matcher->match_criteria == DR_MATCHER_CRITERIA_EMPTY)
+ mlx5dr_ste_build_empty_always_hit(&sb[idx++], rx);
+
+ if (idx == 0) {
+ mlx5dr_dbg(dmn, "Cannot generate any valid rules from mask\n");
+ return -EINVAL;
+ }
+
+ /* Check that all mask fields were consumed */
+ for (i = 0; i < sizeof(struct mlx5dr_match_param); i++) {
+ if (((u8 *)&mask)[i] != 0) {
+ mlx5dr_info(dmn, "Mask contains unsupported parameters\n");
+ return -EOPNOTSUPP;
+ }
+ }
+
+ *num_of_builders = idx;
+
+ return 0;
+}
+
+static int dr_matcher_connect(struct mlx5dr_domain *dmn,
+ struct mlx5dr_matcher_rx_tx *curr_nic_matcher,
+ struct mlx5dr_matcher_rx_tx *next_nic_matcher,
+ struct mlx5dr_matcher_rx_tx *prev_nic_matcher)
+{
+ struct mlx5dr_table_rx_tx *nic_tbl = curr_nic_matcher->nic_tbl;
+ struct mlx5dr_domain_rx_tx *nic_dmn = nic_tbl->nic_dmn;
+ struct mlx5dr_htbl_connect_info info;
+ struct mlx5dr_ste_htbl *prev_htbl;
+ int ret;
+
+ /* Connect end anchor hash table to next_htbl or to the default address */
+ if (next_nic_matcher) {
+ info.type = CONNECT_HIT;
+ info.hit_next_htbl = next_nic_matcher->s_htbl;
+ } else {
+ info.type = CONNECT_MISS;
+ info.miss_icm_addr = nic_tbl->default_icm_addr;
+ }
+ ret = mlx5dr_ste_htbl_init_and_postsend(dmn, nic_dmn,
+ curr_nic_matcher->e_anchor,
+ &info, info.type == CONNECT_HIT);
+ if (ret)
+ return ret;
+
+ /* Connect start hash table to end anchor */
+ info.type = CONNECT_MISS;
+ info.miss_icm_addr = curr_nic_matcher->e_anchor->chunk->icm_addr;
+ ret = mlx5dr_ste_htbl_init_and_postsend(dmn, nic_dmn,
+ curr_nic_matcher->s_htbl,
+ &info, false);
+ if (ret)
+ return ret;
+
+ /* Connect previous hash table to matcher start hash table */
+ if (prev_nic_matcher)
+ prev_htbl = prev_nic_matcher->e_anchor;
+ else
+ prev_htbl = nic_tbl->s_anchor;
+
+ info.type = CONNECT_HIT;
+ info.hit_next_htbl = curr_nic_matcher->s_htbl;
+ ret = mlx5dr_ste_htbl_init_and_postsend(dmn, nic_dmn, prev_htbl,
+ &info, true);
+ if (ret)
+ return ret;
+
+ /* Update the pointing ste and next hash table */
+ curr_nic_matcher->s_htbl->pointing_ste = prev_htbl->ste_arr;
+ prev_htbl->ste_arr[0].next_htbl = curr_nic_matcher->s_htbl;
+
+ if (next_nic_matcher) {
+ next_nic_matcher->s_htbl->pointing_ste = curr_nic_matcher->e_anchor->ste_arr;
+ curr_nic_matcher->e_anchor->ste_arr[0].next_htbl = next_nic_matcher->s_htbl;
+ }
+
+ return 0;
+}
+
+static int dr_matcher_add_to_tbl(struct mlx5dr_matcher *matcher)
+{
+ struct mlx5dr_matcher *next_matcher, *prev_matcher, *tmp_matcher;
+ struct mlx5dr_table *tbl = matcher->tbl;
+ struct mlx5dr_domain *dmn = tbl->dmn;
+ bool first = true;
+ int ret;
+
+ next_matcher = NULL;
+ if (!list_empty(&tbl->matcher_list))
+ list_for_each_entry(tmp_matcher, &tbl->matcher_list, matcher_list) {
+ if (tmp_matcher->prio >= matcher->prio) {
+ next_matcher = tmp_matcher;
+ break;
+ }
+ first = false;
+ }
+
+ prev_matcher = NULL;
+ if (next_matcher && !first)
+ prev_matcher = list_entry(next_matcher->matcher_list.prev,
+ struct mlx5dr_matcher,
+ matcher_list);
+ else if (!first)
+ prev_matcher = list_entry(tbl->matcher_list.prev,
+ struct mlx5dr_matcher,
+ matcher_list);
+
+ if (dmn->type == MLX5DR_DOMAIN_TYPE_FDB ||
+ dmn->type == MLX5DR_DOMAIN_TYPE_NIC_RX) {
+ ret = dr_matcher_connect(dmn, &matcher->rx,
+ next_matcher ? &next_matcher->rx : NULL,
+ prev_matcher ? &prev_matcher->rx : NULL);
+ if (ret)
+ return ret;
+ }
+
+ if (dmn->type == MLX5DR_DOMAIN_TYPE_FDB ||
+ dmn->type == MLX5DR_DOMAIN_TYPE_NIC_TX) {
+ ret = dr_matcher_connect(dmn, &matcher->tx,
+ next_matcher ? &next_matcher->tx : NULL,
+ prev_matcher ? &prev_matcher->tx : NULL);
+ if (ret)
+ return ret;
+ }
+
+ if (prev_matcher)
+ list_add(&matcher->matcher_list, &prev_matcher->matcher_list);
+ else if (next_matcher)
+ list_add_tail(&matcher->matcher_list,
+ &next_matcher->matcher_list);
+ else
+ list_add(&matcher->matcher_list, &tbl->matcher_list);
+
+ return 0;
+}
+
+static void dr_matcher_uninit_nic(struct mlx5dr_matcher_rx_tx *nic_matcher)
+{
+ mlx5dr_htbl_put(nic_matcher->s_htbl);
+ mlx5dr_htbl_put(nic_matcher->e_anchor);
+}
+
+static void dr_matcher_uninit_fdb(struct mlx5dr_matcher *matcher)
+{
+ dr_matcher_uninit_nic(&matcher->rx);
+ dr_matcher_uninit_nic(&matcher->tx);
+}
+
+static void dr_matcher_uninit(struct mlx5dr_matcher *matcher)
+{
+ struct mlx5dr_domain *dmn = matcher->tbl->dmn;
+
+ switch (dmn->type) {
+ case MLX5DR_DOMAIN_TYPE_NIC_RX:
+ dr_matcher_uninit_nic(&matcher->rx);
+ break;
+ case MLX5DR_DOMAIN_TYPE_NIC_TX:
+ dr_matcher_uninit_nic(&matcher->tx);
+ break;
+ case MLX5DR_DOMAIN_TYPE_FDB:
+ dr_matcher_uninit_fdb(matcher);
+ break;
+ default:
+ WARN_ON(true);
+ break;
+ }
+}
+
+static int dr_matcher_init_nic(struct mlx5dr_matcher *matcher,
+ struct mlx5dr_matcher_rx_tx *nic_matcher)
+{
+ struct mlx5dr_domain *dmn = matcher->tbl->dmn;
+ int ret, ret_v4, ret_v6;
+
+ ret_v4 = dr_matcher_set_ste_builders(matcher, nic_matcher, false);
+ ret_v6 = dr_matcher_set_ste_builders(matcher, nic_matcher, true);
+
+ if (ret_v4 && ret_v6) {
+ mlx5dr_dbg(dmn, "Cannot generate IPv4 or IPv6 rules with given mask\n");
+ return -EINVAL;
+ }
+
+ if (!ret_v4)
+ nic_matcher->ste_builder = nic_matcher->ste_builder4;
+ else
+ nic_matcher->ste_builder = nic_matcher->ste_builder6;
+
+ nic_matcher->e_anchor = mlx5dr_ste_htbl_alloc(dmn->ste_icm_pool,
+ DR_CHUNK_SIZE_1,
+ MLX5DR_STE_LU_TYPE_DONT_CARE,
+ 0);
+ if (!nic_matcher->e_anchor)
+ return -ENOMEM;
+
+ nic_matcher->s_htbl = mlx5dr_ste_htbl_alloc(dmn->ste_icm_pool,
+ DR_CHUNK_SIZE_1,
+ nic_matcher->ste_builder[0].lu_type,
+ nic_matcher->ste_builder[0].byte_mask);
+ if (!nic_matcher->s_htbl) {
+ ret = -ENOMEM;
+ goto free_e_htbl;
+ }
+
+ /* make sure the tables exist while empty */
+ mlx5dr_htbl_get(nic_matcher->s_htbl);
+ mlx5dr_htbl_get(nic_matcher->e_anchor);
+
+ return 0;
+
+free_e_htbl:
+ mlx5dr_ste_htbl_free(nic_matcher->e_anchor);
+ return ret;
+}
+
+static int dr_matcher_init_fdb(struct mlx5dr_matcher *matcher)
+{
+ int ret;
+
+ ret = dr_matcher_init_nic(matcher, &matcher->rx);
+ if (ret)
+ return ret;
+
+ ret = dr_matcher_init_nic(matcher, &matcher->tx);
+ if (ret)
+ goto uninit_nic_rx;
+
+ return 0;
+
+uninit_nic_rx:
+ dr_matcher_uninit_nic(&matcher->rx);
+ return ret;
+}
+
+static int dr_matcher_init(struct mlx5dr_matcher *matcher,
+ struct mlx5dr_match_parameters *mask)
+{
+ struct mlx5dr_table *tbl = matcher->tbl;
+ struct mlx5dr_domain *dmn = tbl->dmn;
+ int ret;
+
+ if (matcher->match_criteria >= DR_MATCHER_CRITERIA_MAX) {
+ mlx5dr_info(dmn, "Invalid match criteria attribute\n");
+ return -EINVAL;
+ }
+
+ if (mask) {
+ if (mask->match_sz > sizeof(struct mlx5dr_match_param)) {
+ mlx5dr_info(dmn, "Invalid match size attribute\n");
+ return -EINVAL;
+ }
+ mlx5dr_ste_copy_param(matcher->match_criteria,
+ &matcher->mask, mask);
+ }
+
+ switch (dmn->type) {
+ case MLX5DR_DOMAIN_TYPE_NIC_RX:
+ matcher->rx.nic_tbl = &tbl->rx;
+ ret = dr_matcher_init_nic(matcher, &matcher->rx);
+ break;
+ case MLX5DR_DOMAIN_TYPE_NIC_TX:
+ matcher->tx.nic_tbl = &tbl->tx;
+ ret = dr_matcher_init_nic(matcher, &matcher->tx);
+ break;
+ case MLX5DR_DOMAIN_TYPE_FDB:
+ matcher->rx.nic_tbl = &tbl->rx;
+ matcher->tx.nic_tbl = &tbl->tx;
+ ret = dr_matcher_init_fdb(matcher);
+ break;
+ default:
+ WARN_ON(true);
+ return -EINVAL;
+ }
+
+ return ret;
+}
+
+struct mlx5dr_matcher *
+mlx5dr_matcher_create(struct mlx5dr_table *tbl,
+ u16 priority,
+ u8 match_criteria_enable,
+ struct mlx5dr_match_parameters *mask)
+{
+ struct mlx5dr_matcher *matcher;
+ int ret;
+
+ refcount_inc(&tbl->refcount);
+
+ matcher = kzalloc(sizeof(*matcher), GFP_KERNEL);
+ if (!matcher)
+ goto dec_ref;
+
+ matcher->tbl = tbl;
+ matcher->prio = priority;
+ matcher->match_criteria = match_criteria_enable;
+ refcount_set(&matcher->refcount, 1);
+ INIT_LIST_HEAD(&matcher->matcher_list);
+
+ mutex_lock(&tbl->dmn->mutex);
+
+ ret = dr_matcher_init(matcher, mask);
+ if (ret)
+ goto free_matcher;
+
+ ret = dr_matcher_add_to_tbl(matcher);
+ if (ret)
+ goto matcher_uninit;
+
+ mutex_unlock(&tbl->dmn->mutex);
+
+ return matcher;
+
+matcher_uninit:
+ dr_matcher_uninit(matcher);
+free_matcher:
+ mutex_unlock(&tbl->dmn->mutex);
+ kfree(matcher);
+dec_ref:
+ refcount_dec(&tbl->refcount);
+ return NULL;
+}
+
+static int dr_matcher_disconnect(struct mlx5dr_domain *dmn,
+ struct mlx5dr_table_rx_tx *nic_tbl,
+ struct mlx5dr_matcher_rx_tx *next_nic_matcher,
+ struct mlx5dr_matcher_rx_tx *prev_nic_matcher)
+{
+ struct mlx5dr_domain_rx_tx *nic_dmn = nic_tbl->nic_dmn;
+ struct mlx5dr_htbl_connect_info info;
+ struct mlx5dr_ste_htbl *prev_anchor;
+
+ if (prev_nic_matcher)
+ prev_anchor = prev_nic_matcher->e_anchor;
+ else
+ prev_anchor = nic_tbl->s_anchor;
+
+ /* Connect previous anchor hash table to next matcher or to the default address */
+ if (next_nic_matcher) {
+ info.type = CONNECT_HIT;
+ info.hit_next_htbl = next_nic_matcher->s_htbl;
+ next_nic_matcher->s_htbl->pointing_ste = prev_anchor->ste_arr;
+ prev_anchor->ste_arr[0].next_htbl = next_nic_matcher->s_htbl;
+ } else {
+ info.type = CONNECT_MISS;
+ info.miss_icm_addr = nic_tbl->default_icm_addr;
+ prev_anchor->ste_arr[0].next_htbl = NULL;
+ }
+
+ return mlx5dr_ste_htbl_init_and_postsend(dmn, nic_dmn, prev_anchor,
+ &info, true);
+}
+
+static int dr_matcher_remove_from_tbl(struct mlx5dr_matcher *matcher)
+{
+ struct mlx5dr_matcher *prev_matcher, *next_matcher;
+ struct mlx5dr_table *tbl = matcher->tbl;
+ struct mlx5dr_domain *dmn = tbl->dmn;
+ int ret = 0;
+
+ if (list_is_last(&matcher->matcher_list, &tbl->matcher_list))
+ next_matcher = NULL;
+ else
+ next_matcher = list_next_entry(matcher, matcher_list);
+
+ if (matcher->matcher_list.prev == &tbl->matcher_list)
+ prev_matcher = NULL;
+ else
+ prev_matcher = list_prev_entry(matcher, matcher_list);
+
+ if (dmn->type == MLX5DR_DOMAIN_TYPE_FDB ||
+ dmn->type == MLX5DR_DOMAIN_TYPE_NIC_RX) {
+ ret = dr_matcher_disconnect(dmn, &tbl->rx,
+ next_matcher ? &next_matcher->rx : NULL,
+ prev_matcher ? &prev_matcher->rx : NULL);
+ if (ret)
+ return ret;
+ }
+
+ if (dmn->type == MLX5DR_DOMAIN_TYPE_FDB ||
+ dmn->type == MLX5DR_DOMAIN_TYPE_NIC_TX) {
+ ret = dr_matcher_disconnect(dmn, &tbl->tx,
+ next_matcher ? &next_matcher->tx : NULL,
+ prev_matcher ? &prev_matcher->tx : NULL);
+ if (ret)
+ return ret;
+ }
+
+ list_del(&matcher->matcher_list);
+
+ return 0;
+}
+
+int mlx5dr_matcher_destroy(struct mlx5dr_matcher *matcher)
+{
+ struct mlx5dr_table *tbl = matcher->tbl;
+
+ if (refcount_read(&matcher->refcount) > 1)
+ return -EBUSY;
+
+ mutex_lock(&tbl->dmn->mutex);
+
+ dr_matcher_remove_from_tbl(matcher);
+ dr_matcher_uninit(matcher);
+ refcount_dec(&matcher->tbl->refcount);
+
+ mutex_unlock(&tbl->dmn->mutex);
+ kfree(matcher);
+
+ return 0;
+}
--
2.21.0
^ permalink raw reply related
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox