* Re: [PATCH v2 3/3] selftests/mm: fix ternary operator precedence in ksm_tests
From: David Hildenbrand (Arm) @ 2026-06-30 10:33 UTC (permalink / raw)
To: Sayali Patil, Andrew Morton, Shuah Khan, linux-mm, linux-kernel,
linux-kselftest, Ritesh Harjani
Cc: Zi Yan, Michal Hocko, Oscar Salvador, Lorenzo Stoakes, Dev Jain,
Liam.Howlett, linuxppc-dev, Miaohe Lin, Venkat Rao Bagalkote
In-Reply-To: <bea784beacee411394c332272df9e68148caf7f3.1782811071.git.sayalip@linux.ibm.com>
On 6/30/26 11:32, Sayali Patil wrote:
> The KSM selftest uses conditional expressions to skip accesses to
> merge_across_nodes on systems without NUMA support. However, the
> ternary operator is combined with logical OR without parentheses:
>
> a || numa_available() ? 0 : b || c
>
> Due to operator precedence rules, this is parsed as:
>
> (a || numa_available()) ? 0 : (b || c)
>
> instead of the intended:
>
> a || (numa_available() ? 0 : b) || c
>
> Add parentheses around the conditional expressions to ensure the
> correct evaluation order.
>
> Fixes: 9aa1af954db0 ("selftests: vm: check numa_available() before operating "merge_across_nodes" in ksm_tests")
> Signed-off-by: Sayali Patil <sayalip@linux.ibm.com>
> ---
LGTM, although the code is a bit ugly (already before your changes).
Acked-by: David Hildenbrand (Arm) <david@kernel.org>
--
Cheers,
David
^ permalink raw reply
* Re: [PATCH v2 1/3] selftests/mm: handle EINVAL when configuring gigantic hugepages
From: David Hildenbrand (Arm) @ 2026-06-30 10:45 UTC (permalink / raw)
To: Sayali Patil, Andrew Morton, Shuah Khan, linux-mm, linux-kernel,
linux-kselftest, Ritesh Harjani
Cc: Zi Yan, Michal Hocko, Oscar Salvador, Lorenzo Stoakes, Dev Jain,
Liam.Howlett, linuxppc-dev, Miaohe Lin, Venkat Rao Bagalkote
In-Reply-To: <3d394c8cd59fe380d4e2d13b051544f241918f07.1782811071.git.sayalip@linux.ibm.com>
On 6/30/26 11:32, Sayali Patil wrote:
> Some MM selftests attempt to configure the amount of
> HugeTLB pages of different sizes by writing to nr_hugepages.
>
> PowerPC hash MMU pSeries systems advertise gigantic hugepage sizes
> but do not support runtime allocation of such pages, writes
> to the corresponding nr_hugepages file fail with -EINVAL.
> This causes the test to bail out even though the failure is due
> to a platform limitation rather than the
> functionality being tested.
>
> Treat -EINVAL from the sysfs write as a skipped configuration request
> and continue running the test instead of failing.
>
> Before patch:
> -------------------------
> running ./hugetlb-madvise
> -------------------------
> TAP version 13
> 1..1
> [INFO] detected hugetlb page size: 16777216 KiB
> [INFO] detected hugetlb page size: 16384 KiB
> ok 1 MADV_DONTNEED and MADV_REMOVE on hugetlb
> Totals: pass:1 fail:0 xfail:0 xpass:0 skip:0 error:0
> Bail out! /sys/kernel/mm/hugepages/hugepages-16777216kB/nr_hugepages
> write(0) failed: Invalid argument
> Totals: pass:0 fail:0 xfail:0 xpass:0 skip:0 error:0
> [FAIL]
>
> After patch:
> -------------------------
> running ./hugetlb-madvise
> -------------------------
> TAP version 13
> 1..1
> [INFO] detected hugetlb page size: 16777216 KiB
> [INFO] detected hugetlb page size: 16384 KiB
> ok 1 MADV_DONTNEED and MADV_REMOVE on hugetlb
> Totals: pass:1 fail:0 xfail:0 xpass:0 skip:0 error:0
> /sys/kernel/mm/hugepages/hugepages-16777216kB/nr_hugepages
> write(0) failed: Invalid argument
> [PASS]
>
> Fixes: 27477b28b74f ("selftests/mm: hugepage_settings: add APIs to get and set nr_hugepages")
> Signed-off-by: Sayali Patil <sayalip@linux.ibm.com>
> ---
> .../testing/selftests/mm/hugepage_settings.c | 32 ++++++++++++++++++-
> .../testing/selftests/mm/hugepage_settings.h | 1 +
> 2 files changed, 32 insertions(+), 1 deletion(-)
>
> diff --git a/tools/testing/selftests/mm/hugepage_settings.c b/tools/testing/selftests/mm/hugepage_settings.c
> index 2eab2110ac6a..ce38ae3da01a 100644
> --- a/tools/testing/selftests/mm/hugepage_settings.c
> +++ b/tools/testing/selftests/mm/hugepage_settings.c
> @@ -422,6 +422,36 @@ static void hugetlb_sysfs_path(char *buf, size_t buflen,
> size / 1024, attr);
> }
>
> +void hugetlb_write_num(const char *path, unsigned long num)
> +{
> + int fd, saved_errno;
> + ssize_t numwritten;
> + char buf[21];
> +
> + sprintf(buf, "%lu", num);
> +
> + fd = open(path, O_WRONLY);
> + if (fd == -1)
> + ksft_exit_fail_msg("%s open failed: %s\n", path, strerror(errno));
> +
> + numwritten = write(fd, buf, strlen(buf));
> + saved_errno = errno;
> + close(fd);
> + errno = saved_errno;
> +
> + /* Treat EINVAL as a skipped configuration (e.g., unsupported gigantic pages) */
> + if (numwritten < 0 && errno == EINVAL) {
> + ksft_print_msg("%s write(%s) failed: %s\n", path, buf, strerror(errno));
Should we even print anything here? Rather confusing. It's just like we cannot
allocate anything (no memory).
In general, you are copy-pasting a lot of write_num()+write_file() content,
which is really suboptimal.
All you want is an option for write_num -> write_file to skip on -EINVAL, correct?
There are not that many write_num / write_file users ...
--
Cheers,
David
^ permalink raw reply
* Re: [PATCH v2 2/3] selftests/mm: fix ksm NUMA merge test for systems with memoryless NUMA nodes
From: Sayali Patil @ 2026-06-30 10:45 UTC (permalink / raw)
To: Andrew Morton, Shuah Khan, linux-mm, linux-kernel,
linux-kselftest, Ritesh Harjani
Cc: David Hildenbrand, Zi Yan, Michal Hocko, Oscar Salvador,
Lorenzo Stoakes, Dev Jain, Liam.Howlett, linuxppc-dev, Miaohe Lin,
Venkat Rao Bagalkote
In-Reply-To: <878cbc1dd24921d55049932dcd5fd6ee517557ca.1782811071.git.sayalip@linux.ibm.com>
On 30/06/26 15:02, Sayali Patil wrote:
> The KSM NUMA merge test allocates identical pages on different NUMA
> nodes and verifies KSM behavior with merge_across_nodes enabled and
> disabled.
>
> On systems with memoryless NUMA nodes, for example:
> #numactl -H
> available: 2 nodes (0,4)
> .....
> node 0 cpus: 0 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15
> node 0 size: 14825 MB
> node 0 free: 1382 MB
> node 4 cpus:
> node 4 size: 0 MB
> node 4 free: 0 MB
>
> the test may attempt to allocate memory on a node without memory,
> causing numa_alloc_onnode() to fail and resulting in a spurious test
> failure.
>
> The test currently checks numa_num_configured_nodes() to determine
> whether sufficient NUMA nodes are available. However, configured nodes
> do not necessarily have memory.
>
> Reuse the existing get_first_mem_node() and get_next_mem_node()
> helpers to locate NUMA nodes that actually contain memory, and skip
> the test when fewer than two such nodes are available.
>
> Before patch:
> ---------------------------
> running ./ksm_tests -N -m 1
> ---------------------------
> mbind: Invalid argument
> ok 1 KSM NUMA merging
> Totals: pass:1 fail:0 xfail:0 xpass:0 skip:0 error:0
> [PASS]
> ok 1 ksm_tests -N -m 1
> ---------------------------
> running ./ksm_tests -N -m 0
> ---------------------------
> mbind: Invalid argument
> not ok 1 KSM NUMA merging
> Totals: pass:0 fail:1 xfail:0 xpass:0 skip:0 error:0
> [FAIL]
> not ok 2 ksm_tests -N -m 0 # exit=1
>
> After patch:
> ---------------------------
> running ./ksm_tests -N -m 1
> ---------------------------
> At least 2 NUMA nodes with memory must be available
> ok 1
> SKIP KSM NUMA merging
> Totals: pass:0 fail:0 xfail:0 xpass:0 skip:1 error:0
> [PASS]
> ok 1 ksm_tests -N -m 1
> ---------------------------
> running ./ksm_tests -N -m 0
> ---------------------------
> At least 2 NUMA nodes with memory must be available
> ok 1
> SKIP KSM NUMA merging
> Totals: pass:0 fail:0 xfail:0 xpass:0 skip:1 error:0
> [PASS]
> ok 2 ksm_tests -N -m 0
>
> Fixes: e3820ab252dd ("selftest/vm: fix ksm selftest to run with different NUMA topologies")
> Co-developed-by: David Hildenbrand (Arm) <david@kernel.org>
> Signed-off-by: David Hildenbrand (Arm) <david@kernel.org>
> Signed-off-by: Sayali Patil <sayalip@linux.ibm.com>
> ---
> tools/testing/selftests/mm/ksm_tests.c | 16 +++++++++-------
> 1 file changed, 9 insertions(+), 7 deletions(-)
>
> diff --git a/tools/testing/selftests/mm/ksm_tests.c b/tools/testing/selftests/mm/ksm_tests.c
> index a050f4840cfa..2ebbb544c671 100644
> --- a/tools/testing/selftests/mm/ksm_tests.c
> +++ b/tools/testing/selftests/mm/ksm_tests.c
> @@ -440,9 +440,9 @@ static int get_next_mem_node(int node)
> mem_node = i % (max_node + 1);
> node_size = numa_node_size(mem_node, NULL);
> if (node_size > 0)
> - break;
> + return mem_node;
> }
> - return mem_node;
> + return -ENODEV;
> }
>
> static int get_first_mem_node(void)
> @@ -455,8 +455,8 @@ static int check_ksm_numa_merge(int merge_type, int mapping, int prot, int timeo
> {
> void *numa1_map_ptr, *numa2_map_ptr;
> struct timespec start_time;
> + int first_node, second_node;
> int page_count = 2;
> - int first_node;
>
> if (clock_gettime(CLOCK_MONOTONIC_RAW, &start_time)) {
> ksft_perror("clock_gettime");
> @@ -467,17 +467,19 @@ static int check_ksm_numa_merge(int merge_type, int mapping, int prot, int timeo
> ksft_print_msg("NUMA support not enabled\n");
> return KSFT_SKIP;
> }
> - if (numa_num_configured_nodes() <= 1) {
> - ksft_print_msg("At least 2 NUMA nodes must be available\n");
> + first_node = get_first_mem_node();
> + second_node = get_next_mem_node(first_node);
> +
> + if (second_node < 0) {
> + ksft_print_msg("At least 2 NUMA nodes with memory must be available\n");
> return KSFT_SKIP;
> }
> if (ksm_write_sysfs(KSM_FP("merge_across_nodes"), merge_across_nodes))
> return KSFT_FAIL;
>
> /* allocate 2 pages in 2 different NUMA nodes and fill them with the same data */
> - first_node = get_first_mem_node();
> numa1_map_ptr = numa_alloc_onnode(page_size, first_node);
> - numa2_map_ptr = numa_alloc_onnode(page_size, get_next_mem_node(first_node));
> + numa2_map_ptr = numa_alloc_onnode(page_size, second_node);
> if (!numa1_map_ptr || !numa2_map_ptr) {
> ksft_perror("numa_alloc_onnode");
> return KSFT_FAIL;
AI review comment:
> If get_first_mem_node() doesn't find a node with memory, will it
> return -ENODEV and pass it directly into get_next_mem_node()?
> Looking at get_next_mem_node() with a negative node parameter:
> tools/testing/selftests/mm/ksm_tests.c:get_next_mem_node() {
> ...
> for (i = node + 1; i <= max_node + node; i++) {
> mem_node = i % (max_node + 1);
> node_size = numa_node_size(mem_node, NULL);
> ...
> }
> Because the modulo operator preserves the sign of a negative dividend,
> starting the loop with a negative node value causes mem_node to become
> negative. This means a negative node ID is then passed into libnuma's
> numa_node_size() function.
> Could we check if first_node is valid before attempting to find the
> second node?
The additional check for get_first_mem_node() is not needed. After
numa_available() succeeds, a running system should always have at least
one NUMA node with memory, so get_first_mem_node() is expected to return
a valid node ID. The actual prerequisite for this test is the presence
of two NUMA nodes with memory, which is already validated by checking
the return value of get_next_mem_node().
Thanks,
Sayali
^ permalink raw reply
* Re: [PATCH v2 00/11] ASoC: fsl: Use guard() for mutex & spin locks
From: Mark Brown @ 2026-06-29 18:19 UTC (permalink / raw)
To: phucduc.bui
Cc: Liam Girdwood, Jaroslav Kysela, Takashi Iwai, Shengjiu Wang,
Xiubo Li, Frank Li, Fabio Estevam, Nicolin Chen, Sascha Hauer,
Pengutronix Kernel Team, linux-sound, linux-kernel,
linux-arm-kernel, imx, linuxppc-dev
In-Reply-To: <20260615093824.115751-1-phucduc.bui@gmail.com>
On Mon, 15 Jun 2026 16:38:13 +0700, phucduc.bui@gmail.com wrote:
> ASoC: fsl: Use guard() for mutex & spin locks
>
> From: bui duc phuc <phucduc.bui@gmail.com>
>
> Hi all,
>
> This series converts mutex and spinlock handling in the FSL sound drivers
> to use guard() helpers.
> The changes are code cleanup only and should have no functional impact.
>
> [...]
Applied to
https://git.kernel.org/pub/scm/linux/kernel/git/broonie/sound.git for-7.3
Thanks!
[01/11] ASoC: fsl_asrc: Use guard() for spin locks
https://git.kernel.org/broonie/sound/c/d7e261b7ad1b
[02/11] ASoC: fsl_audmix: Use guard() for spin locks
https://git.kernel.org/broonie/sound/c/58712476dee2
[03/11] ASoC: fsl_easrc: Use guard() for spin locks
https://git.kernel.org/broonie/sound/c/48d84310be60
[04/11] ASoC: fsl_esai: Use guard() for spin locks
https://git.kernel.org/broonie/sound/c/cb87bdabd341
[05/11] ASoC: fsl_spdif: Use guard() for spin locks
https://git.kernel.org/broonie/sound/c/a1b865cff274
[06/11] ASoC: fsl_ssi: Use guard() for mutex locks
https://git.kernel.org/broonie/sound/c/4d748e7082ec
[07/11] ASoC: fsl_xcvr: Use guard() for spin locks
https://git.kernel.org/broonie/sound/c/94b0cb1dd6d9
[08/11] ASoC: imx-audio-rpmsg: Use guard() for spin locks
https://git.kernel.org/broonie/sound/c/929d412fdb0d
[09/11] ASoC: fsl_rpmsg: Use guard() for mutex & spin locks
https://git.kernel.org/broonie/sound/c/11ce4dd4e7be
[10/11] ASoC: fsl: mpc5200_dma: Use guard() for spin locks
https://git.kernel.org/broonie/sound/c/caed9fb2e428
[11/11] ASoC: fsl: mpc5200_psc_ac97: Use guard() for mutex locks
https://git.kernel.org/broonie/sound/c/8a2d7e46317a
All being well this means that it will be integrated into the linux-next
tree (usually sometime in the next 24 hours) and sent to Linus during
the next merge window (or sooner if it is a bug fix), however if
problems are discovered then the patch may be dropped or reverted.
You may get further e-mails resulting from automated or manual testing
and review of the tree, please engage with people reporting problems and
send followup patches addressing any issues that are reported if needed.
If any updates are required or you are submitting further changes they
should be sent as incremental updates against current git, existing
patches will not be replaced.
Please add any relevant lists and maintainers to the CCs when replying
to this mail.
Thanks,
Mark
^ permalink raw reply
* Re: [PATCH bpf v9 0/8] powerpc/bpf: address missing verifier selftest coverage
From: Yeswanth Krishna @ 2026-06-30 11:35 UTC (permalink / raw)
To: adubey, bpf
Cc: hbathini, linuxppc-dev, maddy, ast, andrii, daniel, shuah,
linux-kselftest, stable
In-Reply-To: <20260623231411.6216-1-adubey@linux.ibm.com>
Hi Abhishek,
I have tested this patch series on PowerPC64 (ppc64le) and can confirm
all 8 patches work correctly.
## Test Environment
- System: PowerPC64 (ppc64le)
- Kernel: 7.1.0-rc3 with all 8 patches applied
- BTF Support: Enabled (CONFIG_DEBUG_INFO_BTF=y)
- Test Suite: tools/testing/selftests/bpf/test_progs
## Test Results
### WITHOUT Patches (Baseline):
- Kernel: 7.1.0-rc3-00362-g6916d5703ddf
- Summary: 111/2135 PASSED, 35 SKIPPED, 5 FAILED
- verifier_tailcall_jit: **FAIL**
- Error: "Can't disasm instruction at offset 96: 60 80 1c 00 00 00 00 c0"
### WITH All 8 Patches:
- Kernel: 7.1.0-rc3-00370-g202ecf282b6e
- Summary: 112/2136 PASSED, 35 SKIPPED, 4 FAILED
- verifier_tailcall_jit: **OK**
The critical PowerPC64-specific test `verifier_tailcall_jit` now passes:
#635/1 verifier_tailcall_jit/main:OK
#635 verifier_tailcall_jit:OK
This test was previously failing due to JIT disassembly issues caused by
the dummy_tramp_addr placement. The patches successfully:
1. Fix alignment of long branch trampoline address
2. Relocate dummy_tramp_addr to bottom of stub
3. Fix JIT disassembly truncation
4. Enable PowerPC64 arch support in verifier tests
5. Fix compare instruction (cmpldi vs cmplwi) for tailcalls
6. Add PowerPC64 tailcall verifier test
7. Fix JIT buffer overflow for large programs
8. Fix percpu private stack leak on JIT failure
The 4 remaining failures are all in verifier_arena* tests with -ENOMEM
errors, which are unrelated to these patches and appear to be
platform-specific memory allocation issues with the arena feature.
Please add below tag.
Tested-by: Yeswanth Krishna Tellakula <yeswanth@linux.ibm.com>
Regards,
Yeswanth
On 24/06/26 4:44 am, adubey@linux.ibm.com wrote:
> From: Abhishek Dubey <adubey@linux.ibm.com>
>
> The verifier selftest validates JITed instructions by matching expected
> disassembly output. The first two patches fix issues in powerpc instruction
> disassembly that were causing test flow failures. The fix is common for
> 64-bit & 32-bit powerpc. Add support for the powerpc-specific "__powerpc64"
> architecture tag in the third patch, enabling proper test filtering in
> verifier test files. Introduce verifier testcases for tailcalls on powerpc64.
>
> The first patch in series is fix patch, correcting memory alignment with
> 8-byte boundary for long branch address field. The subsequent patches
> enables verifier selftests on powerpc. The fifth patch in the series fixes
> incorrect comparator usage for comparing tailcall info with tailcall
> threshold. The last two patches fix JIT buffer overflow for large BPF progs
> and private stack memory leak (identified by bot during reviews).
>
> Issue Details:
> --------------
>
> The Long branch stub in the trampoline implementation[1] provides
> flexibility to handles short as well as long branch distance to
> actual trampoline. Whereas, the 8 bytes long dummy_tramp_addr field
> sitting before long branch stub leads to failure when enabling
> verifier based seltest for ppc64.
>
> The verifier selftests require disassembing the final jited image
> to get native instructions. Later the disassembled instruction
> sequence is matched against sequence of instructions provided in
> test-file under __jited() wrapper. The final jited image contains
> Out-of-line stub and Long branch stub as part of epilogue jitting
> for a bpf program. The 8 bytes space for dummy_tramp is sandwiched
> between both above mentioned stubs. These 8 bytes contain memory
> address of dummy trampoline during trampoline invocation which don't
> correspond to any powerpc instructions. So, disassembly fails
> resulting in failure of verifier selftests.
>
> The following code snippet shows the problem with current arrangement
> made for dummy_tramp_addr.
>
> /* Out-of-line stub */
> mflr r0
> [b|bl] tramp
> mtlr r0 //only with OOL
> b bpf_func + 4
> /* Long branch stub */
> .long <dummy_tramp_addr> <---Invalid bytes sequence, disassembly fails
> mflr r11
> bcl 20,31,$+4
> mflr r12
> ld r12, -8-SZL(r12)
> mtctr r12
> mtlr r11 //retain ftrace ABI
> bctr
>
> Consider test program binary of size 112 bytes:
> 0: 00000060 10004de8 00002039 f8ff21f9 81ff21f8 7000e1fb 3000e13b
> 28: 3000e13b 2a006038 f8ff7ff8 00000039 7000e1eb 80002138 7843037d
> 56: 2000804e a602087c 00000060 a603087c bcffff4b c0341d00 000000c0
> 84: a602687d 05009f42 a602887d f0ff8ce9 a603897d a603687d 2004804e
>
> Disassembly output of above binary for ppc64le:
> pc:0 left:112 00 00 00 60 : nop
> pc:4 left:108 10 00 4d e8 : ld 2, 16(13)
> pc:8 left:104 00 00 20 39 : li 9, 0
> pc:12 left:100 f8 ff 21 f9 : std 9, -8(1)
> pc:16 left:96 81 ff 21 f8 : stdu 1, -128(1)
> pc:20 left:92 70 00 e1 fb : std 31, 112(1)
> pc:24 left:88 30 00 e1 3b : addi 31, 1, 48
> pc:28 left:84 30 00 e1 3b : addi 31, 1, 48
> pc:32 left:80 2a 00 60 38 : li 3, 42
> pc:36 left:76 f8 ff 7f f8 : std 3, -8(31)
> pc:40 left:72 00 00 00 39 : li 8, 0
> pc:44 left:68 70 00 e1 eb : ld 31, 112(1)
> pc:48 left:64 80 00 21 38 : addi 1, 1, 128
> pc:52 left:60 78 43 03 7d : mr 3, 8
> pc:56 left:56 20 00 80 4e : blr
> pc:60 left:52 a6 02 08 7c : mflr 0
> pc:64 left:48 00 00 00 60 : nop
> pc:68 left:44 a6 03 08 7c : mtlr 0
> pc:72 left:40 bc ff ff 4b : b .-68
> pc:76 left:36 c0 34 1d 00 :
> ...
>
> Failure log:
> Can't disasm instruction at offset 76: c0 34 1d 00 00 00 00 c0 a6 02 68 7d 05 00 9f 42
> --------------------------------------
>
> Observation:
> Can't disasm instruction at offset 76 as this address has
> ".long <dummy_tramp_addr>" (0xc0341d00000000c0)
> But valid instructions follow at offset 84 onwards.
>
> Move the long branch address space to the bottom of the long
> branch stub. This allows uninterrupted disassembly until the
> last 8 bytes. Exclude these last bytes from the overall
> program length to prevent failure in assembly generation.
>
> Following is disassembler output for same test program with moved down
> dummy_tramp_addr field:
> .....
> .....
> pc:68 left:44 a6 03 08 7c : mtlr 0
> pc:72 left:40 bc ff ff 4b : b .-68
> pc:76 left:36 a6 02 68 7d : mflr 11
> pc:80 left:32 05 00 9f 42 : bcl 20, 31, .+4
> pc:84 left:28 a6 02 88 7d : mflr 12
> pc:88 left:24 14 00 8c e9 : ld 12, 20(12)
> pc:92 left:20 a6 03 89 7d : mtctr 12
> pc:96 left:16 a6 03 68 7d : mtlr 11
> pc:100 left:12 20 04 80 4e : bctr
> pc:104 left:8 c0 34 1d 00 :
>
> Failure log:
> Can't disasm instruction at offset 104: c0 34 1d 00 00 00 00 c0
> ---------------------------------------
> Disassembly logic can truncate at 104, ignoring last 8 bytes.
>
> Update the dummy_tramp_addr field offset calculation from the end
> of the program to reflect its new location, for bpf_arch_text_poke()
> to update the actual trampoline's address in this field.
>
> [1] https://lore.kernel.org/all/20241030070850.1361304-18-hbathini@linux.ibm.com
>
> v8->v9:
> Dynamic pass handling until code keeps shrinking
> Fix private stack memory leak
>
> v7->v8:
> Fixed bot identified issues of alt_exit_addr and BPF_EXIT
> Fixed 32-bit ppc function signature mismatch
>
> v6->v7:
> Fixed JIT buffer overflow in case of large BPF progs
> Addressed remaining bot comments
>
> v5->v6:
> Changed alignment NOP emittion dependency on fimage layout
> Adjust tail truncate length for 32-bit ppc
> Addressed few minor bot comments
>
> v4->v5:
> Handled alignment NOP emit logic and corresponding stub offsets
> Handled image buffer overflow problem in last pass
> Above changes took care of other bot reviews
> Included LLVMDisposeMessage() for graceful freeing
> Adjusted parameters in bpf_jit_build_fentry_stubs for ppc32
> Adjusted expected JIT inst. in tailcall test for
> CONFIG_PPC_KERNEL_PCREL config
> Added fix patch at last for inaccurate use of cmplwi inst.
>
> v3->v4:
> Changed logic for emitting alignment NOP
>
> v2->v3:
> Removed fixed NOP from bottom of long branch stub
> Rebased on top of bpf-next
>
> v1->v2:
> Added fix-patch to correct memory alignment in-place
> Moved the optional alignmnet NOP before OOL stub
>
> [v1]: https://lore.kernel.org/bpf/20260225013627.22098-1-adubey@linux.ibm.com
> [v2]: https://lore.kernel.org/bpf/20260403004011.44417-1-adubey@linux.ibm.com
> [v3]: https://lore.kernel.org/bpf/20260411221413.44304-1-adubey@linux.ibm.com
> [v4]: https://lore.kernel.org/bpf/20260517214043.12975-1-adubey@linux.ibm.com
> [v5]: https://lore.kernel.org/bpf/20260519233812.18787-1-adubey@linux.ibm.com
> [v6]: https://lore.kernel.org/bpf/20260529015855.364704-1-adubey@linux.ibm.com
> [v7]: https://lore.kernel.org/bpf/20260611153826.31187-1-adubey@linux.ibm.com
> [v8]: https://lore.kernel.org/bpf/20260616164741.32252-1-adubey@linux.ibm.com
>
> Abhishek Dubey (8):
> powerpc/bpf: fix alignment of long branch trampoline address
> powerpc/bpf: Move out dummy_tramp_addr after Long branch stub
> selftest/bpf: Fixing powerpc JIT disassembly failure
> selftest/bpf: Enable verifier selftest for powerpc64
> powerpc64/bpf: fix compare instruction emitted for tailcall
> selftest/bpf: Add tailcall verifier selftest for powerpc64
> powerpc/bpf: fix buffer overflow in JIT for large BPF programs
> powerpc64/bpf: fix percpu private stack leak on JIT failure
>
> arch/powerpc/net/bpf_jit.h | 20 +++-
> arch/powerpc/net/bpf_jit_comp.c | 99 ++++++++++++++-----
> arch/powerpc/net/bpf_jit_comp32.c | 7 +-
> arch/powerpc/net/bpf_jit_comp64.c | 15 +--
> .../selftests/bpf/jit_disasm_helpers.c | 27 ++++-
> tools/testing/selftests/bpf/progs/bpf_misc.h | 1 +
> .../bpf/progs/verifier_tailcall_jit.c | 69 +++++++++++++
> tools/testing/selftests/bpf/test_loader.c | 5 +
> 8 files changed, 203 insertions(+), 40 deletions(-)
>
^ permalink raw reply
* Re: [PATCH v2 02/19] driver core: platform: provide platform_device_set_of_node()
From: Manuel Ebner @ 2026-06-30 11:37 UTC (permalink / raw)
To: Bartosz Golaszewski, Lee Jones, Thierry Reding,
Sebastian Hesselbarth, Andrew Lunn, David S. Miller, Eric Dumazet,
Jakub Kicinski, Paolo Abeni, Srinivas Kandagatla,
Greg Kroah-Hartman, Vinod Koul, Rafael J. Wysocki,
Danilo Krummrich, Rob Herring, Saravana Kannan,
Madhavan Srinivasan, Michael Ellerman, Nicholas Piggin,
Christophe Leroy (CS GROUP), Andi Shyti, Andy Shevchenko,
Joerg Roedel, Will Deacon, Robin Murphy, Doug Berger,
Florian Fainelli, Broadcom internal kernel review list,
Ulf Hansson, Frank Li, Sascha Hauer, Pengutronix Kernel Team,
Fabio Estevam, Matthew Brost, Thomas Hellström, Rodrigo Vivi,
David Airlie, Simona Vetter, Peter Chen, Paul Cercueil, Bin Liu,
Philipp Zabel, Maximilian Luz, Hans de Goede, Ilpo Järvinen,
Krzysztof Kozlowski, Benjamin Herrenschmidt
Cc: brgl, linux-kernel, netdev, linux-arm-msm, linux-sound,
driver-core, devicetree, linuxppc-dev, linux-i2c, iommu, linux-pm,
imx, linux-arm-kernel, intel-xe, dri-devel, linux-usb, linux-mips,
platform-driver-x86
In-Reply-To: <20260629-pdev-fwnode-ref-v2-2-8abe2513f96e@oss.qualcomm.com>
On Mon, 2026-06-29 at 11:12 +0200, Bartosz Golaszewski wrote:
> [...]
>
> +/**
> + * platform_device_set_of_node - assign an OF node to device
> + * @pdev: platform device to add the node for
> + * @np: new device node
> + *
> + * Assign an OF node to this platform device. Internally keep track of the
> + * reference count. Devices created with platform_device_alloc() must use this
> + * function instead of assigning the node manually.
Doesn't it make sense to add a remark to the kernel doc of platform_device_alloc()?
Thanks
Manuel
> [...]
^ permalink raw reply
* Re: [PATCH V2] ASoC: fsl_audmix: rework runtime PM handling in probe
From: Shengjiu Wang @ 2026-06-30 12:34 UTC (permalink / raw)
To: shengjiu.wang
Cc: Xiubo.Lee, festevam, nicoleotsuka, lgirdwood, broonie, perex,
tiwai, linux-sound, linuxppc-dev, linux-kernel
In-Reply-To: <20260618023818.31618-1-shengjiu.wang@oss.nxp.com>
On Thu, Jun 18, 2026 at 10:33 AM <shengjiu.wang@oss.nxp.com> wrote:
>
> From: Shengjiu Wang <shengjiu.wang@nxp.com>
>
> After pm_runtime_enable() the AUDMIX block is powered off and stays
> suspended until the first runtime resume. Register writes issued between
> probe() and the first resume (e.g. from DAPM or ALSA control paths)
> target unpowered hardware and cause a system hang.
>
> Fix this by calling pm_runtime_resume_and_get() immediately after
> pm_runtime_enable() to power the hardware up and enable its clocks.
> Release the reference afterwards with pm_runtime_put() to allow the
> runtime PM framework to suspend the device and switch the regmap to
> cache-only mode when idle.
>
> When CONFIG_PM is disabled or runtime PM is not enabled, pm_runtime_*
> calls are stubs that do not power up the hardware. Handle this case
> explicitly by calling fsl_audmix_runtime_resume() directly so the
> hardware is always initialised and its clocks are enabled, ensuring
> register accesses succeed regardless of PM configuration.
>
> Fixes: be1df61cf06ef ("ASoC: fsl: Add Audio Mixer CPU DAI driver")
> Signed-off-by: Shengjiu Wang <shengjiu.wang@nxp.com>
> ---
> Changes in v2:
> - remove the call of regcache_cache_only in probe, rework the runtime
> handling in probe, call the pm_runtime_put() to enable the cache only.
> - refine the commit message
>
> sound/soc/fsl/fsl_audmix.c | 24 ++++++++++++++++++++++--
> 1 file changed, 22 insertions(+), 2 deletions(-)
>
> diff --git a/sound/soc/fsl/fsl_audmix.c b/sound/soc/fsl/fsl_audmix.c
> index f819f33ec46b..2885cc10b02d 100644
> --- a/sound/soc/fsl/fsl_audmix.c
> +++ b/sound/soc/fsl/fsl_audmix.c
> @@ -457,6 +457,9 @@ static const struct of_device_id fsl_audmix_ids[] = {
> };
> MODULE_DEVICE_TABLE(of, fsl_audmix_ids);
>
> +static int fsl_audmix_runtime_resume(struct device *dev);
> +static int fsl_audmix_runtime_suspend(struct device *dev);
> +
> static int fsl_audmix_probe(struct platform_device *pdev)
> {
> struct device *dev = &pdev->dev;
> @@ -488,13 +491,25 @@ static int fsl_audmix_probe(struct platform_device *pdev)
> spin_lock_init(&priv->lock);
> platform_set_drvdata(pdev, priv);
> pm_runtime_enable(dev);
> + if (!pm_runtime_enabled(dev)) {
> + ret = fsl_audmix_runtime_resume(dev);
> + if (ret)
> + goto err_disable_pm;
> + }
> +
> + ret = pm_runtime_resume_and_get(dev);
> + if (ret < 0)
> + goto err_pm_get_sync;
> +
> + /* To enable regmap cache only when runtime PM enabled */
> + pm_runtime_put(dev);
Check the comments from Sashiko. Needs to use pm_runtime_put_sync to
avoid the race
of asynchronous.
Will send the next version.
Best regards
Shengjiu Wang
>
> ret = devm_snd_soc_register_component(dev, &fsl_audmix_component,
> fsl_audmix_dai,
> ARRAY_SIZE(fsl_audmix_dai));
> if (ret) {
> dev_err(dev, "failed to register ASoC DAI\n");
> - goto err_disable_pm;
> + goto err_pm_get_sync;
> }
>
> /*
> @@ -506,12 +521,15 @@ static int fsl_audmix_probe(struct platform_device *pdev)
> if (IS_ERR(priv->pdev)) {
> ret = PTR_ERR(priv->pdev);
> dev_err(dev, "failed to register platform: %d\n", ret);
> - goto err_disable_pm;
> + goto err_pm_get_sync;
> }
> }
>
> return 0;
>
> +err_pm_get_sync:
> + if (!pm_runtime_status_suspended(dev))
> + fsl_audmix_runtime_suspend(dev);
> err_disable_pm:
> pm_runtime_disable(dev);
> return ret;
> @@ -522,6 +540,8 @@ static void fsl_audmix_remove(struct platform_device *pdev)
> struct fsl_audmix *priv = dev_get_drvdata(&pdev->dev);
>
> pm_runtime_disable(&pdev->dev);
> + if (!pm_runtime_status_suspended(&pdev->dev))
> + fsl_audmix_runtime_suspend(&pdev->dev);
>
> if (priv->pdev)
> platform_device_unregister(priv->pdev);
> --
> 2.34.1
>
^ permalink raw reply
* [PATCH V3] ASoC: fsl_audmix: rework runtime PM handling in probe
From: shengjiu.wang @ 2026-06-30 12:40 UTC (permalink / raw)
To: shengjiu.wang, Xiubo.Lee, festevam, nicoleotsuka, lgirdwood,
broonie, perex, tiwai, linux-sound, linuxppc-dev, linux-kernel
From: Shengjiu Wang <shengjiu.wang@nxp.com>
After pm_runtime_enable() the AUDMIX block is powered off and stays
suspended until the first runtime resume. Register writes issued between
probe() and the first resume (e.g. from DAPM or ALSA control paths)
target unpowered hardware and cause a system hang.
Fix this by calling pm_runtime_resume_and_get() immediately after
pm_runtime_enable() to power the hardware up and enable its clocks.
Release the reference afterwards with pm_runtime_put_sync() to allow
the runtime PM framework to suspend the device and switch the regmap to
cache-only mode when idle.
When CONFIG_PM is disabled or runtime PM is not enabled, pm_runtime_*
calls are stubs that do not power up the hardware. Handle this case
explicitly by calling fsl_audmix_runtime_resume() directly so the
hardware is always initialised and its clocks are enabled, ensuring
register accesses succeed regardless of PM configuration.
Fixes: be1df61cf06ef ("ASoC: fsl: Add Audio Mixer CPU DAI driver")
Signed-off-by: Shengjiu Wang <shengjiu.wang@nxp.com>
---
Changes in v3:
- address the comments from sashiko.dev
- replace the pm_runtime_put() with pm_runtime_put_sync() to fix the
race of async
Changes in v2:
- remove the call of regcache_cache_only in probe, rework the runtime
handling in probe, call the pm_runtime_put() to enable the cache only.
- refine the commit message
sound/soc/fsl/fsl_audmix.c | 26 ++++++++++++++++++++++++--
1 file changed, 24 insertions(+), 2 deletions(-)
diff --git a/sound/soc/fsl/fsl_audmix.c b/sound/soc/fsl/fsl_audmix.c
index f819f33ec46b..f45d3ef02b72 100644
--- a/sound/soc/fsl/fsl_audmix.c
+++ b/sound/soc/fsl/fsl_audmix.c
@@ -457,6 +457,9 @@ static const struct of_device_id fsl_audmix_ids[] = {
};
MODULE_DEVICE_TABLE(of, fsl_audmix_ids);
+static int fsl_audmix_runtime_resume(struct device *dev);
+static int fsl_audmix_runtime_suspend(struct device *dev);
+
static int fsl_audmix_probe(struct platform_device *pdev)
{
struct device *dev = &pdev->dev;
@@ -488,13 +491,27 @@ static int fsl_audmix_probe(struct platform_device *pdev)
spin_lock_init(&priv->lock);
platform_set_drvdata(pdev, priv);
pm_runtime_enable(dev);
+ if (!pm_runtime_enabled(dev)) {
+ ret = fsl_audmix_runtime_resume(dev);
+ if (ret)
+ goto err_disable_pm;
+ }
+
+ ret = pm_runtime_resume_and_get(dev);
+ if (ret < 0)
+ goto err_pm_get_sync;
+
+ /* To enable regmap cache only when runtime PM enabled */
+ ret = pm_runtime_put_sync(dev);
+ if (ret < 0 && ret != -ENOSYS)
+ goto err_pm_get_sync;
ret = devm_snd_soc_register_component(dev, &fsl_audmix_component,
fsl_audmix_dai,
ARRAY_SIZE(fsl_audmix_dai));
if (ret) {
dev_err(dev, "failed to register ASoC DAI\n");
- goto err_disable_pm;
+ goto err_pm_get_sync;
}
/*
@@ -506,12 +523,15 @@ static int fsl_audmix_probe(struct platform_device *pdev)
if (IS_ERR(priv->pdev)) {
ret = PTR_ERR(priv->pdev);
dev_err(dev, "failed to register platform: %d\n", ret);
- goto err_disable_pm;
+ goto err_pm_get_sync;
}
}
return 0;
+err_pm_get_sync:
+ if (!pm_runtime_status_suspended(dev))
+ fsl_audmix_runtime_suspend(dev);
err_disable_pm:
pm_runtime_disable(dev);
return ret;
@@ -522,6 +542,8 @@ static void fsl_audmix_remove(struct platform_device *pdev)
struct fsl_audmix *priv = dev_get_drvdata(&pdev->dev);
pm_runtime_disable(&pdev->dev);
+ if (!pm_runtime_status_suspended(&pdev->dev))
+ fsl_audmix_runtime_suspend(&pdev->dev);
if (priv->pdev)
platform_device_unregister(priv->pdev);
--
2.34.1
^ permalink raw reply related
* Re: [PATCH v2 1/9] time: Respect COMPAT_32BIT_TIME for old time type functions
From: Arnd Bergmann @ 2026-06-30 13:00 UTC (permalink / raw)
To: Thomas Weißschuh, Andy Lutomirski, Thomas Gleixner,
Ingo Molnar, Borislav Petkov, Dave Hansen, x86, H. Peter Anvin,
Russell King, Catalin Marinas, Will Deacon, Madhavan Srinivasan,
Michael Ellerman, Nicholas Piggin, Christophe Leroy,
Thomas Bogendoerfer, Vincenzo Frascino, John Stultz, Stephen Boyd,
David S . Miller, Andreas Larsson
Cc: linux-kernel, linux-arm-kernel, linuxppc-dev, linux-mips,
linux-api, sparclinux
In-Reply-To: <20260630-vdso-compat_32bit_time-v2-1-520d194640dd@linutronix.de>
On Tue, Jun 30, 2026, at 09:38, Thomas Weißschuh wrote:
> The "old" time types use 32-bit seconds which are not y2038-safe.
> Respect COMPAT_32BIT_TIME for functions using those types.
> time(), stime() and gettimeofday() are disabled completely.
Looks good, yes
> settimeofday() is kept as it is required to do the initial timewarping
> after boot. However the 'tv' argument will be rejected.
Not sure about this part, did we already discuss this last time?
I can see how keeping the timewarping functionality is the easy way
out, but completely disabling the settimeofday syscall the same
way we do on new architectures seems so much more consistent.
Note how scripts/syscall.tbl blocks sys_settimeofday on
architectures that don't set the time32 flag, which ideally
should match the COMPAT_32BIT_TIME option here.
Arnd
^ permalink raw reply
* Re: [PATCH v2 0/9] vDSO: Respect COMPAT_32BIT_TIME
From: Arnd Bergmann @ 2026-06-30 13:16 UTC (permalink / raw)
To: Thomas Weißschuh, Andy Lutomirski, Thomas Gleixner,
Ingo Molnar, Borislav Petkov, Dave Hansen, x86, H. Peter Anvin,
Russell King, Catalin Marinas, Will Deacon, Madhavan Srinivasan,
Michael Ellerman, Nicholas Piggin, Christophe Leroy,
Thomas Bogendoerfer, Vincenzo Frascino, John Stultz, Stephen Boyd,
David S . Miller, Andreas Larsson
Cc: linux-kernel, linux-arm-kernel, linuxppc-dev, linux-mips,
linux-api, sparclinux
In-Reply-To: <20260630-vdso-compat_32bit_time-v2-0-520d194640dd@linutronix.de>
On Tue, Jun 30, 2026, at 09:38, Thomas Weißschuh wrote:
> If CONFIG_COMPAT_32BIT_TIME is disabled then the vDSO should not
> provide any 32-bit time related functionality. This is the intended
> effect of the kconfig option and also the fallback system calls would
> also not be implemented.
>
> Currently the kconfig option does not affect the gettimeofday() syscall,
> so also keep that in the vDSO.
>
> I also tried to introduce some helpers to avoid much of the ifdeffery,
> but due to the high variance in the architecture-specific glue code
> these would need to handle they ended up being worse than the current
> proposal.
>
> As a side-effect this will make the self-tests more reliable,
> as there is now always a matching syscall available for each vDSO function.
>
> clock_gettime_time64() was only introduced in v6.19, so libc implementations
^ clock_getres_time64()
> Signed-off-by: Thomas Weißschuh <thomas.weissschuh@linutronix.de>
> ---
Reviewed-by: Arnd Bergmann <arnd@arndb.de>
once we have consensus on my patch 1/9 comment. Thanks for
continuing this work!
Arnd
^ permalink raw reply
* Re: [PATCH v2 02/19] driver core: platform: provide platform_device_set_of_node()
From: Bartosz Golaszewski @ 2026-06-30 13:22 UTC (permalink / raw)
To: Manuel Ebner
Cc: brgl, linux-kernel, netdev, linux-arm-msm, linux-sound,
driver-core, devicetree, linuxppc-dev, linux-i2c, iommu, linux-pm,
imx, linux-arm-kernel, intel-xe, dri-devel, linux-usb, linux-mips,
platform-driver-x86, Bartosz Golaszewski, Lee Jones,
Thierry Reding, Sebastian Hesselbarth, Andrew Lunn,
David S. Miller, Eric Dumazet, Jakub Kicinski, Paolo Abeni,
Srinivas Kandagatla, Greg Kroah-Hartman, Vinod Koul,
Rafael J. Wysocki, Danilo Krummrich, Rob Herring, Saravana Kannan,
Madhavan Srinivasan, Michael Ellerman, Nicholas Piggin,
Christophe Leroy (CS GROUP), Andi Shyti, Andy Shevchenko,
Joerg Roedel, Will Deacon, Robin Murphy, Doug Berger,
Florian Fainelli, Broadcom internal kernel review list,
Ulf Hansson, Frank Li, Sascha Hauer, Pengutronix Kernel Team,
Fabio Estevam, Matthew Brost, Thomas Hellström, Rodrigo Vivi,
David Airlie, Simona Vetter, Peter Chen, Paul Cercueil, Bin Liu,
Philipp Zabel, Maximilian Luz, Hans de Goede, Ilpo Järvinen,
Krzysztof Kozlowski, Benjamin Herrenschmidt
In-Reply-To: <263f58b418a27a2339fc2478f93234e0208b0ad9.camel@mailbox.org>
On Tue, 30 Jun 2026 13:37:54 +0200, Manuel Ebner <manuelebner@mailbox.org> said:
> On Mon, 2026-06-29 at 11:12 +0200, Bartosz Golaszewski wrote:
>> [...]
>>
>> +/**
>> + * platform_device_set_of_node - assign an OF node to device
>> + * @pdev: platform device to add the node for
>> + * @np: new device node
>> + *
>> + * Assign an OF node to this platform device. Internally keep track of the
>> + * reference count. Devices created with platform_device_alloc() must use this
>> + * function instead of assigning the node manually.
>
> Doesn't it make sense to add a remark to the kernel doc of platform_device_alloc()?
>
> Thanks
> Manuel
>
>> [...]
>
Sure, will do in the next iteration.
Bart
^ permalink raw reply
* Re: [PATCH V3] ASoC: fsl_audmix: rework runtime PM handling in probe
From: Mark Brown @ 2026-06-30 13:25 UTC (permalink / raw)
To: shengjiu.wang
Cc: shengjiu.wang, Xiubo.Lee, festevam, nicoleotsuka, lgirdwood,
perex, tiwai, linux-sound, linuxppc-dev, linux-kernel
In-Reply-To: <20260630124016.645114-1-shengjiu.wang@oss.nxp.com>
[-- Attachment #1: Type: text/plain, Size: 302 bytes --]
On Tue, Jun 30, 2026 at 08:40:16PM +0800, shengjiu.wang@oss.nxp.com wrote:
> Changes in v3:
> - address the comments from sashiko.dev
> - replace the pm_runtime_put() with pm_runtime_put_sync() to fix the
> race of async
I already applied v2, please submit new changes with these updates.
[-- Attachment #2: signature.asc --]
[-- Type: application/pgp-signature, Size: 488 bytes --]
^ permalink raw reply
* Re: [PATCH v2] powerpc/powernv: Cache OPAL check_token() results
From: Sourabh Jain @ 2026-06-30 13:50 UTC (permalink / raw)
To: Shivang Upadhyay
Cc: adityag, chleroy, linux-kernel, linuxppc-dev, maddy, mahesh, mpe,
npiggin, thuth
In-Reply-To: <20260626123534.396456-1-shivangu@linux.ibm.com>
On 26/06/26 18:05, Shivang Upadhyay wrote:
> `opal_check_token()` function is used to determine if a specific
> OPAL firmware call is supported on the current platform. This check
> is performed frequently during boot and runtime, resulting in
> unnecessary firmware calls for the same token values.
>
> Add a caching layer for the opal_check_token() OPAL call to avoid
> repeated firmware calls for token availability checks. This reduces
> firmware call overhead during boot.
>
> Testing with buildroot images shows OPAL calls reduced from
> 35578 to 28983, before console bring-up.
My testing shows similar statistics.
As per my testing, the upstream kernel (without this patch) at commit
840ef6c78e6a2f694b578, compiled with powernv_defconfig, shows ~7K
CHECK_TOKEN OPAL calls to boot the kernel and reach the console.
With this patch included, there are only 8 CHECK_TOKEN opal calls.
There is a significant reduction in CHECK_TOKEN OPAL calls
with this patch. Thanks for working on this improvement.
The changes look good to me. Feel free to add:
Reviewed-by: Sourabh Jain <sourabhjain@linux.ibm.com>
>
> Signed-off-by: Shivang Upadhyay <shivangu@linux.ibm.com>
> ---
> Changelog:
> * v1: https://lore.kernel.org/all/20260601112520.161605-1-shivangu@linux.ibm.com/
> - implemented tri-state check as suggestd by Sourabh.
> - made the implementation more clear.
>
> ---
> arch/powerpc/include/asm/opal.h | 1 +
> arch/powerpc/platforms/powernv/opal-call.c | 2 +-
> arch/powerpc/platforms/powernv/opal.c | 30 ++++++++++++++++++++++
> 3 files changed, 32 insertions(+), 1 deletion(-)
>
> diff --git a/arch/powerpc/include/asm/opal.h b/arch/powerpc/include/asm/opal.h
> index 0a398265ba04..e7e11479122b 100644
> --- a/arch/powerpc/include/asm/opal.h
> +++ b/arch/powerpc/include/asm/opal.h
> @@ -156,6 +156,7 @@ int64_t opal_pci_next_error(uint64_t phb_id, __be64 *first_frozen_pe,
> int64_t opal_pci_poll(uint64_t id);
> int64_t opal_return_cpu(void);
> int64_t opal_check_token(uint64_t token);
> +int64_t opal_check_token_call(uint64_t token);
> int64_t opal_reinit_cpus(uint64_t flags);
>
> int64_t opal_xscom_read(uint32_t gcid, uint64_t pcb_addr, __be64 *val);
> diff --git a/arch/powerpc/platforms/powernv/opal-call.c b/arch/powerpc/platforms/powernv/opal-call.c
> index 021b0ec29e24..00325c189e69 100644
> --- a/arch/powerpc/platforms/powernv/opal-call.c
> +++ b/arch/powerpc/platforms/powernv/opal-call.c
> @@ -207,7 +207,7 @@ OPAL_CALL(opal_validate_flash, OPAL_FLASH_VALIDATE);
> OPAL_CALL(opal_manage_flash, OPAL_FLASH_MANAGE);
> OPAL_CALL(opal_update_flash, OPAL_FLASH_UPDATE);
> OPAL_CALL(opal_resync_timebase, OPAL_RESYNC_TIMEBASE);
> -OPAL_CALL(opal_check_token, OPAL_CHECK_TOKEN);
> +OPAL_CALL(opal_check_token_call, OPAL_CHECK_TOKEN);
> OPAL_CALL(opal_dump_init, OPAL_DUMP_INIT);
> OPAL_CALL(opal_dump_info, OPAL_DUMP_INFO);
> OPAL_CALL(opal_dump_info2, OPAL_DUMP_INFO2);
> diff --git a/arch/powerpc/platforms/powernv/opal.c b/arch/powerpc/platforms/powernv/opal.c
> index 1946dbdc9fa1..1e9cb5271ee7 100644
> --- a/arch/powerpc/platforms/powernv/opal.c
> +++ b/arch/powerpc/platforms/powernv/opal.c
> @@ -1125,6 +1125,36 @@ EXPORT_SYMBOL_GPL(opal_flash_read);
> EXPORT_SYMBOL_GPL(opal_flash_write);
> EXPORT_SYMBOL_GPL(opal_flash_erase);
> EXPORT_SYMBOL_GPL(opal_prd_msg);
> +
> +/**
> + * opal_check_token - Check if an OPAL call token is supported
> + * @token: OPAL token number to check
> + *
> + * Returns 1 if supported, 0 if not.
> + */
> +int64_t opal_check_token(uint64_t token)
> +{
> + static u8 token_cache[OPAL_LAST];
> + enum {
> + SUPP_UNKNOWN = 0,
> + PRESENT,
> + ABSENT
> + };
> +
> + if (token > OPAL_LAST)
> + return 0;
> +
> + if (token_cache[token] == SUPP_UNKNOWN) {
> + /* Do the actual opal_call here */
> + if (opal_check_token_call(token)) {
> + token_cache[token] = PRESENT;
> + } else {
> + token_cache[token] = ABSENT;
> + }
> + }
> +
> + return (token_cache[token] == PRESENT);
> +}
> EXPORT_SYMBOL_GPL(opal_check_token);
>
> /* Convert a region of vmalloc memory to an opal sg list */
^ permalink raw reply
* [PATCH v1 00/18] ibmveth: Add multi-queue RX Support
From: Mingming Cao @ 2026-06-30 14:53 UTC (permalink / raw)
To: netdev
Cc: horms, bjking1, haren, ricklind, mmc, kuba, edumazet, pabeni,
linuxppc-dev, maddy, mpe
Power11 PHYP firmware adds Virtual Ethernet multi-queue (MQ) RX for
the ibmveth device: multiple logical-LAN RX queues, per-queue buffer
posting, and completion delivery. Guest Linux did not use that
platform support; ibmveth still registered one RX queue even when
PHYP was MQ-capable.
This series adds the ibmveth MQ client. When PHYP advertises the
capability through H_ILLAN_ATTRIBUTES, the driver registers
multiple RX queues, receives on per-queue NAPI, and exposes queue
count through ethtool. Older firmware without the bit is unchanged.
ibmveth today registers one logical LAN, one set of buffer pools, and
one NAPI context. PHYP MQ mode gives each RX queue its own handle:
buffers are posted with H_ADD_LOGICAL_LAN_BUFFERS_QUEUE, subordinate
queues register through H_REG_LOGICAL_LAN_QUEUE, and traffic can
land on any active queue. Queue selection is firmware-defined; v1
does not program RSS or hash tables. The driver needs per-queue
pools, IRQs, and poll state to match.
Queue-aware hcalls are selected only when probe sets multi_queue
from H_ILLAN_ATTRIBUTES; legacy firmware keeps the original hcall
path unchanged through the entire series.
This splits the work so review follows the actual bring-up sequence:
1. Hypercall definitions and MQ data structures (patches 1-3)
2. Refactor open/close into helpers - RX, per-queue pools,
IRQ, TX, PHYP (4-10)
3. Turn on the MQ datapath at probe/open (11)
4. Per-queue RX/TX stats, get_stats64, and sysfs pool readout
(12-14)
5. Runtime RX queue resize via ethtool -L (15-17)
6. Runtime stability fixes from LPAR testing (18)
- Helper patches (4-10) reshape ibmveth_open()/close() into
queue-aware helpers. Runtime behaviour is unchanged through that
block: num_rx_queues stays 1 and multi_queue is false until patch 11.
- Patch 11 is the switch: probe sets multi_queue from firmware, raises
num_rx_queues, registers subordinates, and replenishes every active
queue.
- Patch 18 fixes poll hangs after aggressive ethtool -L cycling,
NAPI/close deadlocks on ip link down, and preserves probe-time
pool->active across close/open so RX works after link down/up.
Design notes
* Per-queue buffer pools (rx_buff_pool[queue][pool]) - PHYP ties
posted buffers to a queue handle; a shared pool set does not work.
Patch 5 also disables the 64 KiB pool at standard MTU to save
per-queue memory in MQ.
* Legacy mode keeps queue 0 on h_register_logical_lan(); MQ uses
handles for all queues (subordinates via H_REG_LOGICAL_LAN_QUEUE).
Close uses H_FREE_LOGICAL_LAN for the whole adapter.
* ethtool -L resizes incrementally while the netdev stays up so
surviving queues keep PHYP handles, pools, and IRQ state. A
close/open cycle would drop traffic and force full LAN
re-registration for every queue.
Tested on ppc64le PowerVM LPAR with MQ-capable firmware:
* MQ path: ethtool -L under iperf3 load, link down/up during traffic
* Legacy firmware (no MQ bit): full open/close/stress on the
refactored helper path to confirm single-queue behaviour is
unchanged
* ethtool -L resize while all RX queues are receiving traffic, not
only a single-flow iperf session
* ip link down/up and ping after reopen (patch 18)
Future work
* IRQ affinity hints for subordinate queue IRQs returned by PHYP
* Summed global no_buffer drop counter across all RX queues in MQ mode
Comments and suggestions on patch split, design, and testing are
welcome.
Mingming Cao <mmc@linux.ibm.com>
Mingming Cao (18):
ibmveth: Add MQ RX hypercall wrappers and call definitions
ibmveth: Prepare adapter data structures for MQ RX
ibmveth: Add MQ-ready RX statistics structures
ibmveth: Refactor RX resource allocation for MQ RX bring-up
ibmveth: Refactor buffer pool management for per-queue MQ RX
ibmveth: Refactor RX interrupt control for MQ RX queues
ibmveth: Refactor TX resource allocation in open/close paths
ibmveth: Add RX queue register/deregister helpers for MQ
ibmveth: Refactor open/close into MQ-ready resource pipeline
ibmveth: Add queue-aware RX buffer submit helper for MQ
ibmveth: Enable multi-queue RX receive path
ibmveth: Add per-queue RX statistics collection and reporting
ibmveth: Add per-queue TX statistics reporting
ibmveth: Expose per-queue buffer pool details via sysfs
ibmveth: Add helpers for incremental MQ RX queue resize
ibmveth: Implement incremental MQ RX queue resize
ibmveth: Wire ethtool set_channels to MQ RX queue resize
ibmveth: Fix MQ RX poll and shutdown hangs after queue resize
arch/powerpc/include/asm/hvcall.h | 6 +-
drivers/net/ethernet/ibm/ibmveth.c | 2451 +++++++++++++++++++++++-----
drivers/net/ethernet/ibm/ibmveth.h | 226 ++-
3 files changed, 2284 insertions(+), 399 deletions(-)
--
2.39.3 (Apple Git-146)
^ permalink raw reply
* [PATCH v1 01/18] ibmveth: Add MQ RX hypercall wrappers and call definitions
From: Mingming Cao @ 2026-06-30 14:53 UTC (permalink / raw)
To: netdev
Cc: horms, bjking1, haren, ricklind, mmc, kuba, edumazet, pabeni,
linuxppc-dev, maddy, mpe, Dave Marquardt
In-Reply-To: <cover.1782758799.git.mmc@linux.ibm.com>
Single-queue ibmveth only needs h_register_logical_lan() plus legacy
buffer add/free calls. MQ RX uses per-queue handles, so the driver must
also be able to register/deregister subordinate queues and post/free
buffers against a specific queue handle.
Add the PHYP call IDs for:
H_REG_LOGICAL_LAN_QUEUE
H_ADD_LOGICAL_LAN_BUFFERS_QUEUE
H_FREE_LOGICAL_LAN_BUFFER_QUEUE
H_FREE_LOGICAL_LAN_QUEUE
and add ibmveth.h wrapper helpers (h_reg_logical_lan_queue(),
h_add_logical_lan_buffers_queue(), h_free_logical_lan_buffer_queue(),
h_free_logical_lan_queue()) with argument ordering and return semantics
matching the existing ibmveth hcall wrappers.
This patch is intentionally plumbing only: no runtime behavior change
yet. Legacy firmware keeps H_REGISTER_LOGICAL_LAN and the existing
buffer hcalls. The new wrappers are used only when a later commit sets
multi_queue from H_ILLAN_ATTRIBUTES.
Signed-off-by: Mingming Cao <mmc@linux.ibm.com>
Reviewed-by: Dave Marquardt <davemarq@linux.ibm.com>
---
arch/powerpc/include/asm/hvcall.h | 6 +-
drivers/net/ethernet/ibm/ibmveth.c | 3 +-
drivers/net/ethernet/ibm/ibmveth.h | 158 +++++++++++++++++++++++++++++
3 files changed, 165 insertions(+), 2 deletions(-)
diff --git a/arch/powerpc/include/asm/hvcall.h b/arch/powerpc/include/asm/hvcall.h
index dff90a7d7f70..bf2f1b0356c4 100644
--- a/arch/powerpc/include/asm/hvcall.h
+++ b/arch/powerpc/include/asm/hvcall.h
@@ -362,7 +362,11 @@
#define H_GUEST_DELETE 0x488
#define H_PKS_WRAP_OBJECT 0x490
#define H_PKS_UNWRAP_OBJECT 0x494
-#define MAX_HCALL_OPCODE H_PKS_UNWRAP_OBJECT
+#define H_REG_LOGICAL_LAN_QUEUE 0x49C
+#define H_ADD_LOGICAL_LAN_BUFFERS_QUEUE 0x4A0
+#define H_FREE_LOGICAL_LAN_BUFFER_QUEUE 0x4A4
+#define H_FREE_LOGICAL_LAN_QUEUE 0x4A8
+#define MAX_HCALL_OPCODE H_FREE_LOGICAL_LAN_QUEUE
/* Scope args for H_SCM_UNBIND_ALL */
#define H_UNBIND_SCOPE_ALL (0x1)
diff --git a/drivers/net/ethernet/ibm/ibmveth.c b/drivers/net/ethernet/ibm/ibmveth.c
index 73e051d26b9d..af287eeafc0c 100644
--- a/drivers/net/ethernet/ibm/ibmveth.c
+++ b/drivers/net/ethernet/ibm/ibmveth.c
@@ -584,7 +584,8 @@ static int ibmveth_allocate_tx_ltb(struct ibmveth_adapter *adapter, int idx)
}
static int ibmveth_register_logical_lan(struct ibmveth_adapter *adapter,
- union ibmveth_buf_desc rxq_desc, u64 mac_address)
+ union ibmveth_buf_desc rxq_desc,
+ u64 mac_address)
{
int rc, try_again = 1;
diff --git a/drivers/net/ethernet/ibm/ibmveth.h b/drivers/net/ethernet/ibm/ibmveth.h
index d87713668ed3..45cfb0d054e3 100644
--- a/drivers/net/ethernet/ibm/ibmveth.h
+++ b/drivers/net/ethernet/ibm/ibmveth.h
@@ -66,6 +66,164 @@ static inline long h_add_logical_lan_buffers(unsigned long unit_address,
desc5, desc6, desc7, desc8);
}
+/**
+ * h_reg_logical_lan_queue - Register a subordinate receive queue
+ * @unit_address: Device unit address
+ * @buffer_list: DMA address of 4KB page for tracking registered buffers
+ * @rec_queue: Buffer descriptor of receive queue
+ *
+ * Registers a subordinate receive queue with the hypervisor.
+ *
+ * Return:
+ * H_SUCCESS (0) on success
+ * H_PARAMETER if parameters are invalid
+ *
+ * On success, hypervisor returns:
+ * R3: H_SUCCESS
+ * R4: Queue handle
+ * R5: IRQ number for this queue
+ */
+static inline long h_reg_logical_lan_queue(unsigned long unit_address,
+ unsigned long buffer_list,
+ unsigned long rec_queue,
+ unsigned long *queue_handle,
+ unsigned long *irq)
+{
+ unsigned long retbuf[PLPAR_HCALL9_BUFSIZE];
+ long rc;
+
+ rc = plpar_hcall9(H_REG_LOGICAL_LAN_QUEUE,
+ retbuf, unit_address,
+ buffer_list, rec_queue);
+
+ if (rc == H_SUCCESS) {
+ if (queue_handle)
+ *queue_handle = retbuf[0];
+ if (irq)
+ *irq = retbuf[1];
+ }
+
+ return rc;
+}
+
+/**
+ * h_add_logical_lan_buffers_queue - Add buffers to subordinate queue
+ * @unit_address: Device unit address
+ * @queue_handle: Queue handle from h_reg_logical_lan_queue()
+ * @buffersznum: Buffer size (upper 32 bits) | count (lower 32 bits)
+ * @ioba12: Buffer addresses 1 and 2 packed (addr1 | addr2 << 32)
+ * @ioba34: Buffer addresses 3 and 4 packed
+ * @ioba56: Buffer addresses 5 and 6 packed
+ * @ioba78: Buffer addresses 7 and 8 packed
+ * @ioba910: Buffer addresses 9 and 10 packed
+ * @ioba1112: Buffer addresses 11 and 12 packed
+ *
+ * Return:
+ * H_SUCCESS - All buffers added successfully
+ * H_PARAMETER - Invalid parameters
+ * H_HARDWARE - Hardware error
+ */
+static inline long h_add_logical_lan_buffers_queue(unsigned long unit_address,
+ unsigned long queue_handle,
+ unsigned long buffersznum,
+ unsigned long ioba12,
+ unsigned long ioba34,
+ unsigned long ioba56,
+ unsigned long ioba78,
+ unsigned long ioba910,
+ unsigned long ioba1112)
+{
+ unsigned long retbuf[PLPAR_HCALL9_BUFSIZE];
+
+ return plpar_hcall9(H_ADD_LOGICAL_LAN_BUFFERS_QUEUE,
+ retbuf, unit_address,
+ queue_handle, buffersznum,
+ ioba12, ioba34, ioba56,
+ ioba78, ioba910, ioba1112);
+}
+
+/**
+ * h_free_logical_lan_buffer_queue - Free buffer from subordinate queue
+ * @unit_address: Device unit address
+ * @buf_size: Size of buffer to remove from pool
+ * @queue_handle: Queue handle from h_reg_logical_lan_queue()
+ *
+ * Removes a buffer of specified size from the subordinate queue's buffer pool.
+ *
+ * Return:
+ * H_SUCCESS - Buffer removed successfully
+ * H_PARAMETER - Invalid parameters
+ * H_HARDWARE - Hardware error
+ * H_NOT_FOUND - Buffer pool does not exist
+ */
+static inline long h_free_logical_lan_buffer_queue(unsigned long unit_address,
+ unsigned long buf_size,
+ unsigned long queue_handle)
+{
+ unsigned long retbuf[PLPAR_HCALL9_BUFSIZE];
+
+ return plpar_hcall9(H_FREE_LOGICAL_LAN_BUFFER_QUEUE,
+ retbuf, unit_address, buf_size, queue_handle);
+}
+
+/**
+ * h_free_logical_lan_queue - Deregister subordinate receive queue
+ * @unit_address: Device unit address
+ * @queue_handle: Queue handle from h_reg_logical_lan_queue()
+ *
+ * Deregisters and frees all structures associated with the subordinate queue.
+ *
+ * Return:
+ * H_SUCCESS - Queue freed successfully
+ * H_PARAMETER - Invalid parameters
+ * H_HARDWARE - Hardware error
+ * H_STATE - VIOA not in valid state
+ * H_BUSY / H_LONG_BUSY_* - Resource busy, retry
+ */
+static inline long h_free_logical_lan_queue(unsigned long unit_address,
+ unsigned long queue_handle)
+{
+ unsigned long retbuf[PLPAR_HCALL9_BUFSIZE];
+
+ return plpar_hcall9(H_FREE_LOGICAL_LAN_QUEUE,
+ retbuf, unit_address, queue_handle);
+}
+
+/**
+ * h_register_logical_lan_with_handle - Register primary queue and get handle
+ * @unit_address: Device unit address
+ * @buffer_list: DMA address of buffer list
+ * @rec_queue: Buffer descriptor of receive queue
+ * @filter_list: DMA address of filter list
+ * @mac_address: MAC address
+ * @queue_handle: Output parameter for queue handle
+ *
+ * Registers the primary receive queue (queue 0) with the hypervisor and
+ * returns the queue handle. This is needed in multi-queue mode to use
+ * h_add_logical_lan_buffers_queue() for all queues including queue 0.
+ *
+ * Return: H_SUCCESS (0) on success, error code otherwise
+ */
+static inline long h_register_logical_lan_with_handle(unsigned long unit_address,
+ unsigned long buffer_list,
+ unsigned long rec_queue,
+ unsigned long filter_list,
+ unsigned long mac_address,
+ u64 *queue_handle)
+{
+ unsigned long retbuf[PLPAR_HCALL9_BUFSIZE];
+ long rc;
+
+ rc = plpar_hcall9(H_REGISTER_LOGICAL_LAN, retbuf,
+ unit_address, buffer_list, rec_queue,
+ filter_list, mac_address);
+
+ if (rc == H_SUCCESS && queue_handle)
+ *queue_handle = retbuf[0];
+
+ return rc;
+}
+
/* FW allows us to send 6 descriptors but we only use one so mark
* the other 5 as unused (0)
*/
--
2.39.3 (Apple Git-146)
^ permalink raw reply related
* [PATCH v1 02/18] ibmveth: Prepare adapter data structures for MQ RX
From: Mingming Cao @ 2026-06-30 14:53 UTC (permalink / raw)
To: netdev
Cc: horms, bjking1, haren, ricklind, mmc, kuba, edumazet, pabeni,
linuxppc-dev, maddy, mpe, Dave Marquardt
In-Reply-To: <cover.1782758799.git.mmc@linux.ibm.com>
MQ RX needs per-queue state for NAPI, queue handles/IRQs, RX rings,
buffer-list DMA mappings, and buffer pools. The current driver stores
most of this as single instances tied to queue 0.
Convert those fields to queue-indexed layouts sized by
IBMVETH_MAX_RX_QUEUES:
rx_queue[]
napi[]
queue_handle[] / queue_irq[]
buffer_list_addr[] / buffer_list_dma[]
rx_buff_pool[queue][pool]
and add num_rx_queues to track how many RX queues are active.
This patch keeps behavior unchanged by mechanically switching existing
references to index 0 — e.g. rx_queue[0], rx_buff_pool[0][pool], and
napi[0]. open/poll/close still drive a single RX queue only.
The goal is to make later helper and datapath patches queue-aware
without mixing structural churn and behavior changes in one commit.
Signed-off-by: Mingming Cao <mmc@linux.ibm.com>
Reviewed-by: Dave Marquardt <davemarq@linux.ibm.com>
---
drivers/net/ethernet/ibm/ibmveth.c | 195 +++++++++++++++--------------
drivers/net/ethernet/ibm/ibmveth.h | 16 ++-
2 files changed, 112 insertions(+), 99 deletions(-)
diff --git a/drivers/net/ethernet/ibm/ibmveth.c b/drivers/net/ethernet/ibm/ibmveth.c
index af287eeafc0c..4f9dbee7477d 100644
--- a/drivers/net/ethernet/ibm/ibmveth.c
+++ b/drivers/net/ethernet/ibm/ibmveth.c
@@ -101,7 +101,7 @@ static struct ibmveth_stat ibmveth_stats[] = {
/* simple methods of getting data from the current rxq entry */
static inline u32 ibmveth_rxq_flags(struct ibmveth_adapter *adapter)
{
- return be32_to_cpu(adapter->rx_queue.queue_addr[adapter->rx_queue.index].flags_off);
+ return be32_to_cpu(adapter->rx_queue[0].queue_addr[adapter->rx_queue[0].index].flags_off);
}
static inline int ibmveth_rxq_toggle(struct ibmveth_adapter *adapter)
@@ -112,7 +112,7 @@ static inline int ibmveth_rxq_toggle(struct ibmveth_adapter *adapter)
static inline int ibmveth_rxq_pending_buffer(struct ibmveth_adapter *adapter)
{
- return ibmveth_rxq_toggle(adapter) == adapter->rx_queue.toggle;
+ return ibmveth_rxq_toggle(adapter) == adapter->rx_queue[0].toggle;
}
static inline int ibmveth_rxq_buffer_valid(struct ibmveth_adapter *adapter)
@@ -132,7 +132,7 @@ static inline int ibmveth_rxq_large_packet(struct ibmveth_adapter *adapter)
static inline int ibmveth_rxq_frame_length(struct ibmveth_adapter *adapter)
{
- return be32_to_cpu(adapter->rx_queue.queue_addr[adapter->rx_queue.index].length);
+ return be32_to_cpu(adapter->rx_queue[0].queue_addr[adapter->rx_queue[0].index].length);
}
static inline int ibmveth_rxq_csum_good(struct ibmveth_adapter *adapter)
@@ -386,7 +386,7 @@ static void ibmveth_replenish_buffer_pool(struct ibmveth_adapter *adapter,
*/
static void ibmveth_update_rx_no_buffer(struct ibmveth_adapter *adapter)
{
- __be64 *p = adapter->buffer_list_addr + 4096 - 8;
+ __be64 *p = adapter->buffer_list_addr[0] + 4096 - 8;
adapter->rx_no_buffer = be64_to_cpup(p);
}
@@ -399,7 +399,7 @@ static void ibmveth_replenish_task(struct ibmveth_adapter *adapter)
adapter->replenish_task_cycles++;
for (i = (IBMVETH_NUM_BUFF_POOLS - 1); i >= 0; i--) {
- struct ibmveth_buff_pool *pool = &adapter->rx_buff_pool[i];
+ struct ibmveth_buff_pool *pool = &adapter->rx_buff_pool[0][i];
if (pool->active &&
(atomic_read(&pool->available) < pool->threshold))
@@ -463,12 +463,12 @@ static int ibmveth_remove_buffer_from_pool(struct ibmveth_adapter *adapter,
struct sk_buff *skb;
if (WARN_ON(pool >= IBMVETH_NUM_BUFF_POOLS) ||
- WARN_ON(index >= adapter->rx_buff_pool[pool].size)) {
+ WARN_ON(index >= adapter->rx_buff_pool[0][pool].size)) {
schedule_work(&adapter->work);
return -EINVAL;
}
- skb = adapter->rx_buff_pool[pool].skbuff[index];
+ skb = adapter->rx_buff_pool[0][pool].skbuff[index];
if (WARN_ON(!skb)) {
schedule_work(&adapter->work);
return -EFAULT;
@@ -482,24 +482,24 @@ static int ibmveth_remove_buffer_from_pool(struct ibmveth_adapter *adapter,
/* remove the skb pointer to mark free. actual freeing is done
* by upper level networking after gro_receive
*/
- adapter->rx_buff_pool[pool].skbuff[index] = NULL;
+ adapter->rx_buff_pool[0][pool].skbuff[index] = NULL;
dma_unmap_single(&adapter->vdev->dev,
- adapter->rx_buff_pool[pool].dma_addr[index],
- adapter->rx_buff_pool[pool].buff_size,
+ adapter->rx_buff_pool[0][pool].dma_addr[index],
+ adapter->rx_buff_pool[0][pool].buff_size,
DMA_FROM_DEVICE);
}
- free_index = adapter->rx_buff_pool[pool].producer_index;
- adapter->rx_buff_pool[pool].producer_index++;
- if (adapter->rx_buff_pool[pool].producer_index >=
- adapter->rx_buff_pool[pool].size)
- adapter->rx_buff_pool[pool].producer_index = 0;
- adapter->rx_buff_pool[pool].free_map[free_index] = index;
+ free_index = adapter->rx_buff_pool[0][pool].producer_index;
+ adapter->rx_buff_pool[0][pool].producer_index++;
+ if (adapter->rx_buff_pool[0][pool].producer_index >=
+ adapter->rx_buff_pool[0][pool].size)
+ adapter->rx_buff_pool[0][pool].producer_index = 0;
+ adapter->rx_buff_pool[0][pool].free_map[free_index] = index;
mb();
- atomic_dec(&(adapter->rx_buff_pool[pool].available));
+ atomic_dec(&adapter->rx_buff_pool[0][pool].available);
return 0;
}
@@ -507,17 +507,17 @@ static int ibmveth_remove_buffer_from_pool(struct ibmveth_adapter *adapter,
/* get the current buffer on the rx queue */
static inline struct sk_buff *ibmveth_rxq_get_buffer(struct ibmveth_adapter *adapter)
{
- u64 correlator = adapter->rx_queue.queue_addr[adapter->rx_queue.index].correlator;
+ u64 correlator = adapter->rx_queue[0].queue_addr[adapter->rx_queue[0].index].correlator;
unsigned int pool = correlator >> 32;
unsigned int index = correlator & 0xffffffffUL;
if (WARN_ON(pool >= IBMVETH_NUM_BUFF_POOLS) ||
- WARN_ON(index >= adapter->rx_buff_pool[pool].size)) {
+ WARN_ON(index >= adapter->rx_buff_pool[0][pool].size)) {
schedule_work(&adapter->work);
return NULL;
}
- return adapter->rx_buff_pool[pool].skbuff[index];
+ return adapter->rx_buff_pool[0][pool].skbuff[index];
}
/**
@@ -538,14 +538,14 @@ static int ibmveth_rxq_harvest_buffer(struct ibmveth_adapter *adapter,
u64 cor;
int rc;
- cor = adapter->rx_queue.queue_addr[adapter->rx_queue.index].correlator;
+ cor = adapter->rx_queue[0].queue_addr[adapter->rx_queue[0].index].correlator;
rc = ibmveth_remove_buffer_from_pool(adapter, cor, reuse);
if (unlikely(rc))
return rc;
- if (++adapter->rx_queue.index == adapter->rx_queue.num_slots) {
- adapter->rx_queue.index = 0;
- adapter->rx_queue.toggle = !adapter->rx_queue.toggle;
+ if (++adapter->rx_queue[0].index == adapter->rx_queue[0].num_slots) {
+ adapter->rx_queue[0].index = 0;
+ adapter->rx_queue[0].toggle = !adapter->rx_queue[0].toggle;
}
return 0;
@@ -596,7 +596,7 @@ static int ibmveth_register_logical_lan(struct ibmveth_adapter *adapter,
*/
retry:
rc = h_register_logical_lan(adapter->vdev->unit_address,
- adapter->buffer_list_dma, rxq_desc.desc,
+ adapter->buffer_list_dma[0], rxq_desc.desc,
adapter->filter_list_dma, mac_address);
if (rc != H_SUCCESS && try_again) {
@@ -624,14 +624,14 @@ static int ibmveth_open(struct net_device *netdev)
netdev_dbg(netdev, "open starting\n");
- napi_enable(&adapter->napi);
+ napi_enable(&adapter->napi[0]);
for(i = 0; i < IBMVETH_NUM_BUFF_POOLS; i++)
- rxq_entries += adapter->rx_buff_pool[i].size;
+ rxq_entries += adapter->rx_buff_pool[0][i].size;
rc = -ENOMEM;
- adapter->buffer_list_addr = (void*) get_zeroed_page(GFP_KERNEL);
- if (!adapter->buffer_list_addr) {
+ adapter->buffer_list_addr[0] = (void *)get_zeroed_page(GFP_KERNEL);
+ if (!adapter->buffer_list_addr[0]) {
netdev_err(netdev, "unable to allocate list pages\n");
goto out;
}
@@ -644,17 +644,18 @@ static int ibmveth_open(struct net_device *netdev)
dev = &adapter->vdev->dev;
- adapter->rx_queue.queue_len = sizeof(struct ibmveth_rx_q_entry) *
+ adapter->rx_queue[0].queue_len = sizeof(struct ibmveth_rx_q_entry) *
rxq_entries;
- adapter->rx_queue.queue_addr =
- dma_alloc_coherent(dev, adapter->rx_queue.queue_len,
- &adapter->rx_queue.queue_dma, GFP_KERNEL);
- if (!adapter->rx_queue.queue_addr)
+ adapter->rx_queue[0].queue_addr =
+ dma_alloc_coherent(dev, adapter->rx_queue[0].queue_len,
+ &adapter->rx_queue[0].queue_dma, GFP_KERNEL);
+ if (!adapter->rx_queue[0].queue_addr)
goto out_free_filter_list;
- adapter->buffer_list_dma = dma_map_single(dev,
- adapter->buffer_list_addr, 4096, DMA_BIDIRECTIONAL);
- if (dma_mapping_error(dev, adapter->buffer_list_dma)) {
+ adapter->buffer_list_dma[0] = dma_map_single(dev,
+ adapter->buffer_list_addr[0],
+ 4096, DMA_BIDIRECTIONAL);
+ if (dma_mapping_error(dev, adapter->buffer_list_dma[0])) {
netdev_err(netdev, "unable to map buffer list pages\n");
goto out_free_queue_mem;
}
@@ -671,19 +672,19 @@ static int ibmveth_open(struct net_device *netdev)
goto out_free_tx_ltb;
}
- adapter->rx_queue.index = 0;
- adapter->rx_queue.num_slots = rxq_entries;
- adapter->rx_queue.toggle = 1;
+ adapter->rx_queue[0].index = 0;
+ adapter->rx_queue[0].num_slots = rxq_entries;
+ adapter->rx_queue[0].toggle = 1;
mac_address = ether_addr_to_u64(netdev->dev_addr);
rxq_desc.fields.flags_len = IBMVETH_BUF_VALID |
- adapter->rx_queue.queue_len;
- rxq_desc.fields.address = adapter->rx_queue.queue_dma;
+ adapter->rx_queue[0].queue_len;
+ rxq_desc.fields.address = adapter->rx_queue[0].queue_dma;
- netdev_dbg(netdev, "buffer list @ 0x%p\n", adapter->buffer_list_addr);
+ netdev_dbg(netdev, "buffer list @ 0x%p\n", adapter->buffer_list_addr[0]);
netdev_dbg(netdev, "filter list @ 0x%p\n", adapter->filter_list_addr);
- netdev_dbg(netdev, "receive q @ 0x%p\n", adapter->rx_queue.queue_addr);
+ netdev_dbg(netdev, "receive q @ 0x%p\n", adapter->rx_queue[0].queue_addr);
h_vio_signal(adapter->vdev->unit_address, VIO_IRQ_DISABLE);
@@ -694,7 +695,7 @@ static int ibmveth_open(struct net_device *netdev)
lpar_rc);
netdev_err(netdev, "buffer TCE:0x%llx filter TCE:0x%llx rxq "
"desc:0x%llx MAC:0x%llx\n",
- adapter->buffer_list_dma,
+ adapter->buffer_list_dma[0],
adapter->filter_list_dma,
rxq_desc.desc,
mac_address);
@@ -703,11 +704,11 @@ static int ibmveth_open(struct net_device *netdev)
}
for (i = 0; i < IBMVETH_NUM_BUFF_POOLS; i++) {
- if (!adapter->rx_buff_pool[i].active)
+ if (!adapter->rx_buff_pool[0][i].active)
continue;
- if (ibmveth_alloc_buffer_pool(&adapter->rx_buff_pool[i])) {
+ if (ibmveth_alloc_buffer_pool(&adapter->rx_buff_pool[0][i])) {
netdev_err(netdev, "unable to alloc pool\n");
- adapter->rx_buff_pool[i].active = 0;
+ adapter->rx_buff_pool[0][i].active = 0;
rc = -ENOMEM;
goto out_free_buffer_pools;
}
@@ -739,9 +740,9 @@ static int ibmveth_open(struct net_device *netdev)
out_free_buffer_pools:
while (--i >= 0) {
- if (adapter->rx_buff_pool[i].active)
+ if (adapter->rx_buff_pool[0][i].active)
ibmveth_free_buffer_pool(adapter,
- &adapter->rx_buff_pool[i]);
+ &adapter->rx_buff_pool[0][i]);
}
out_unmap_filter_list:
dma_unmap_single(dev, adapter->filter_list_dma, 4096,
@@ -753,18 +754,18 @@ static int ibmveth_open(struct net_device *netdev)
}
out_unmap_buffer_list:
- dma_unmap_single(dev, adapter->buffer_list_dma, 4096,
+ dma_unmap_single(dev, adapter->buffer_list_dma[0], 4096,
DMA_BIDIRECTIONAL);
out_free_queue_mem:
- dma_free_coherent(dev, adapter->rx_queue.queue_len,
- adapter->rx_queue.queue_addr,
- adapter->rx_queue.queue_dma);
+ dma_free_coherent(dev, adapter->rx_queue[0].queue_len,
+ adapter->rx_queue[0].queue_addr,
+ adapter->rx_queue[0].queue_dma);
out_free_filter_list:
free_page((unsigned long)adapter->filter_list_addr);
out_free_buffer_list:
- free_page((unsigned long)adapter->buffer_list_addr);
+ free_page((unsigned long)adapter->buffer_list_addr[0]);
out:
- napi_disable(&adapter->napi);
+ napi_disable(&adapter->napi[0]);
return rc;
}
@@ -777,7 +778,7 @@ static int ibmveth_close(struct net_device *netdev)
netdev_dbg(netdev, "close starting\n");
- napi_disable(&adapter->napi);
+ napi_disable(&adapter->napi[0]);
netif_tx_stop_all_queues(netdev);
@@ -796,22 +797,22 @@ static int ibmveth_close(struct net_device *netdev)
ibmveth_update_rx_no_buffer(adapter);
- dma_unmap_single(dev, adapter->buffer_list_dma, 4096,
+ dma_unmap_single(dev, adapter->buffer_list_dma[0], 4096,
DMA_BIDIRECTIONAL);
- free_page((unsigned long)adapter->buffer_list_addr);
+ free_page((unsigned long)adapter->buffer_list_addr[0]);
dma_unmap_single(dev, adapter->filter_list_dma, 4096,
DMA_BIDIRECTIONAL);
free_page((unsigned long)adapter->filter_list_addr);
- dma_free_coherent(dev, adapter->rx_queue.queue_len,
- adapter->rx_queue.queue_addr,
- adapter->rx_queue.queue_dma);
+ dma_free_coherent(dev, adapter->rx_queue[0].queue_len,
+ adapter->rx_queue[0].queue_addr,
+ adapter->rx_queue[0].queue_dma);
for (i = 0; i < IBMVETH_NUM_BUFF_POOLS; i++)
- if (adapter->rx_buff_pool[i].active)
+ if (adapter->rx_buff_pool[0][i].active)
ibmveth_free_buffer_pool(adapter,
- &adapter->rx_buff_pool[i]);
+ &adapter->rx_buff_pool[0][i]);
for (i = 0; i < netdev->real_num_tx_queues; i++)
ibmveth_free_tx_ltb(adapter, i);
@@ -1449,7 +1450,7 @@ static void ibmveth_rx_csum_helper(struct sk_buff *skb,
static int ibmveth_poll(struct napi_struct *napi, int budget)
{
struct ibmveth_adapter *adapter =
- container_of(napi, struct ibmveth_adapter, napi);
+ container_of(napi, struct ibmveth_adapter, napi[0]);
struct net_device *netdev = adapter->netdev;
int frames_processed = 0;
unsigned long lpar_rc;
@@ -1574,11 +1575,11 @@ static irqreturn_t ibmveth_interrupt(int irq, void *dev_instance)
struct ibmveth_adapter *adapter = netdev_priv(netdev);
unsigned long lpar_rc;
- if (napi_schedule_prep(&adapter->napi)) {
+ if (napi_schedule_prep(&adapter->napi[0])) {
lpar_rc = h_vio_signal(adapter->vdev->unit_address,
VIO_IRQ_DISABLE);
WARN_ON(lpar_rc != H_SUCCESS);
- __napi_schedule(&adapter->napi);
+ __napi_schedule(&adapter->napi[0]);
}
return IRQ_HANDLED;
}
@@ -1646,7 +1647,7 @@ static int ibmveth_change_mtu(struct net_device *dev, int new_mtu)
int need_restart = 0;
for (i = 0; i < IBMVETH_NUM_BUFF_POOLS; i++)
- if (new_mtu_oh <= adapter->rx_buff_pool[i].buff_size)
+ if (new_mtu_oh <= adapter->rx_buff_pool[0][i].buff_size)
break;
if (i == IBMVETH_NUM_BUFF_POOLS)
@@ -1661,9 +1662,9 @@ static int ibmveth_change_mtu(struct net_device *dev, int new_mtu)
/* Look for an active buffer pool that can hold the new MTU */
for (i = 0; i < IBMVETH_NUM_BUFF_POOLS; i++) {
- adapter->rx_buff_pool[i].active = 1;
+ adapter->rx_buff_pool[0][i].active = 1;
- if (new_mtu_oh <= adapter->rx_buff_pool[i].buff_size) {
+ if (new_mtu_oh <= adapter->rx_buff_pool[0][i].buff_size) {
WRITE_ONCE(dev->mtu, new_mtu);
vio_cmo_set_dev_desired(viodev,
ibmveth_get_desired_dma
@@ -1721,12 +1722,12 @@ static unsigned long ibmveth_get_desired_dma(struct vio_dev *vdev)
for (i = 0; i < IBMVETH_NUM_BUFF_POOLS; i++) {
/* add the size of the active receive buffers */
- if (adapter->rx_buff_pool[i].active)
+ if (adapter->rx_buff_pool[0][i].active)
ret +=
- adapter->rx_buff_pool[i].size *
- IOMMU_PAGE_ALIGN(adapter->rx_buff_pool[i].
+ adapter->rx_buff_pool[0][i].size *
+ IOMMU_PAGE_ALIGN(adapter->rx_buff_pool[0][i].
buff_size, tbl);
- rxqentries += adapter->rx_buff_pool[i].size;
+ rxqentries += adapter->rx_buff_pool[0][i].size;
}
/* add the size of the receive queue entries */
ret += IOMMU_PAGE_ALIGN(
@@ -1845,7 +1846,7 @@ static int ibmveth_probe(struct vio_dev *dev, const struct vio_device_id *id)
adapter->mcastFilterSize = be32_to_cpu(*mcastFilterSize_p);
ibmveth_init_link_settings(netdev);
- netif_napi_add_weight(netdev, &adapter->napi, ibmveth_poll, 16);
+ netif_napi_add_weight(netdev, &adapter->napi[0], ibmveth_poll, 16);
netdev->irq = dev->irq;
netdev->netdev_ops = &ibmveth_netdev_ops;
@@ -1877,6 +1878,10 @@ static int ibmveth_probe(struct vio_dev *dev, const struct vio_device_id *id)
netdev->features |= NETIF_F_FRAGLIST;
}
+ /* Initialize queue count - always 1 for now */
+ adapter->multi_queue = 0;
+ adapter->num_rx_queues = 1;
+
if (ret == H_SUCCESS &&
(ret_attr & IBMVETH_ILLAN_RX_MULTI_BUFF_SUPPORT)) {
adapter->rx_buffers_per_hcall = IBMVETH_MAX_RX_PER_HCALL;
@@ -1899,10 +1904,10 @@ static int ibmveth_probe(struct vio_dev *dev, const struct vio_device_id *id)
memcpy(pool_count, pool_count_cmo, sizeof(pool_count));
for (i = 0; i < IBMVETH_NUM_BUFF_POOLS; i++) {
- struct kobject *kobj = &adapter->rx_buff_pool[i].kobj;
+ struct kobject *kobj = &adapter->rx_buff_pool[0][i].kobj;
int error;
- ibmveth_init_buffer_pool(&adapter->rx_buff_pool[i], i,
+ ibmveth_init_buffer_pool(&adapter->rx_buff_pool[0][i], i,
pool_count[i], pool_size[i],
pool_active[i]);
error = kobject_init_and_add(kobj, &ktype_veth_pool,
@@ -1950,7 +1955,7 @@ static void ibmveth_remove(struct vio_dev *dev)
cancel_work_sync(&adapter->work);
for (i = 0; i < IBMVETH_NUM_BUFF_POOLS; i++)
- kobject_put(&adapter->rx_buff_pool[i].kobj);
+ kobject_put(&adapter->rx_buff_pool[0][i].kobj);
unregister_netdev(netdev);
@@ -2036,11 +2041,11 @@ static ssize_t veth_pool_store(struct kobject *kobj, struct attribute *attr,
/* Make sure there is a buffer pool with buffers that
can hold a packet of the size of the MTU */
for (i = 0; i < IBMVETH_NUM_BUFF_POOLS; i++) {
- if (pool == &adapter->rx_buff_pool[i])
+ if (pool == &adapter->rx_buff_pool[0][i])
continue;
- if (!adapter->rx_buff_pool[i].active)
+ if (!adapter->rx_buff_pool[0][i].active)
continue;
- if (mtu <= adapter->rx_buff_pool[i].buff_size)
+ if (mtu <= adapter->rx_buff_pool[0][i].buff_size)
break;
}
@@ -2214,11 +2219,11 @@ static void ibmveth_remove_buffer_from_pool_test(struct kunit *test)
/* Set sane values for buffer pools */
for (int i = 0; i < IBMVETH_NUM_BUFF_POOLS; i++)
- ibmveth_init_buffer_pool(&adapter->rx_buff_pool[i], i,
+ ibmveth_init_buffer_pool(&adapter->rx_buff_pool[0][i], i,
pool_count[i], pool_size[i],
pool_active[i]);
- pool = &adapter->rx_buff_pool[0];
+ pool = &adapter->rx_buff_pool[0][0];
pool->skbuff = kunit_kcalloc(test, pool->size, sizeof(void *), GFP_KERNEL);
KUNIT_ASSERT_NOT_ERR_OR_NULL(test, pool->skbuff);
@@ -2226,7 +2231,7 @@ static void ibmveth_remove_buffer_from_pool_test(struct kunit *test)
KUNIT_EXPECT_EQ(test, -EINVAL, ibmveth_remove_buffer_from_pool(adapter, correlator, false));
KUNIT_EXPECT_EQ(test, -EINVAL, ibmveth_remove_buffer_from_pool(adapter, correlator, true));
- correlator = ((u64)0 << 32) | adapter->rx_buff_pool[0].size;
+ correlator = ((u64)0 << 32) | adapter->rx_buff_pool[0][0].size;
KUNIT_EXPECT_EQ(test, -EINVAL, ibmveth_remove_buffer_from_pool(adapter, correlator, false));
KUNIT_EXPECT_EQ(test, -EINVAL, ibmveth_remove_buffer_from_pool(adapter, correlator, true));
@@ -2259,30 +2264,32 @@ static void ibmveth_rxq_get_buffer_test(struct kunit *test)
INIT_WORK(&adapter->work, ibmveth_reset_kunit);
- adapter->rx_queue.queue_len = 1;
- adapter->rx_queue.index = 0;
- adapter->rx_queue.queue_addr = kunit_kzalloc(test, sizeof(struct ibmveth_rx_q_entry),
- GFP_KERNEL);
- KUNIT_ASSERT_NOT_ERR_OR_NULL(test, adapter->rx_queue.queue_addr);
+ adapter->rx_queue[0].queue_len = 1;
+ adapter->rx_queue[0].index = 0;
+ adapter->rx_queue[0].queue_addr =
+ kunit_kzalloc(test, sizeof(struct ibmveth_rx_q_entry),
+ GFP_KERNEL);
+ KUNIT_ASSERT_NOT_ERR_OR_NULL(test, adapter->rx_queue[0].queue_addr);
/* Set sane values for buffer pools */
for (int i = 0; i < IBMVETH_NUM_BUFF_POOLS; i++)
- ibmveth_init_buffer_pool(&adapter->rx_buff_pool[i], i,
+ ibmveth_init_buffer_pool(&adapter->rx_buff_pool[0][i], i,
pool_count[i], pool_size[i],
pool_active[i]);
- pool = &adapter->rx_buff_pool[0];
+ pool = &adapter->rx_buff_pool[0][0];
pool->skbuff = kunit_kcalloc(test, pool->size, sizeof(void *), GFP_KERNEL);
KUNIT_ASSERT_NOT_ERR_OR_NULL(test, pool->skbuff);
- adapter->rx_queue.queue_addr[0].correlator = (u64)IBMVETH_NUM_BUFF_POOLS << 32 | 0;
+ adapter->rx_queue[0].queue_addr[0].correlator = (u64)IBMVETH_NUM_BUFF_POOLS << 32 | 0;
KUNIT_EXPECT_PTR_EQ(test, NULL, ibmveth_rxq_get_buffer(adapter));
- adapter->rx_queue.queue_addr[0].correlator = (u64)0 << 32 | adapter->rx_buff_pool[0].size;
+ adapter->rx_queue[0].queue_addr[0].correlator =
+ (u64)0 << 32 | adapter->rx_buff_pool[0][0].size;
KUNIT_EXPECT_PTR_EQ(test, NULL, ibmveth_rxq_get_buffer(adapter));
pool->skbuff[0] = skb;
- adapter->rx_queue.queue_addr[0].correlator = (u64)0 << 32 | 0;
+ adapter->rx_queue[0].queue_addr[0].correlator = (u64)0 << 32 | 0;
KUNIT_EXPECT_PTR_EQ(test, skb, ibmveth_rxq_get_buffer(adapter));
flush_work(&adapter->work);
diff --git a/drivers/net/ethernet/ibm/ibmveth.h b/drivers/net/ethernet/ibm/ibmveth.h
index 45cfb0d054e3..b17894695c2e 100644
--- a/drivers/net/ethernet/ibm/ibmveth.h
+++ b/drivers/net/ethernet/ibm/ibmveth.h
@@ -279,6 +279,8 @@ static inline long h_illan_attributes(unsigned long unit_address,
#define IBMVETH_MAX_TX_BUF_SIZE (1024 * 64)
#define IBMVETH_MAX_QUEUES 16U
#define IBMVETH_DEFAULT_QUEUES 8U
+#define IBMVETH_MAX_RX_QUEUES 1U
+#define IBMVETH_DEFAULT_RX_QUEUES 1U
#define IBMVETH_MAX_RX_PER_HCALL 8U
static int pool_size[] = { 512, 1024 * 2, 1024 * 16, 1024 * 32, 1024 * 64 };
@@ -315,18 +317,22 @@ struct ibmveth_rx_q {
struct ibmveth_adapter {
struct vio_dev *vdev;
struct net_device *netdev;
- struct napi_struct napi;
+ struct napi_struct napi[IBMVETH_MAX_RX_QUEUES];
struct work_struct work;
unsigned int mcastFilterSize;
- void *buffer_list_addr;
+ void *buffer_list_addr[IBMVETH_MAX_RX_QUEUES];
void *filter_list_addr;
void *tx_ltb_ptr[IBMVETH_MAX_QUEUES];
unsigned int tx_ltb_size;
dma_addr_t tx_ltb_dma[IBMVETH_MAX_QUEUES];
- dma_addr_t buffer_list_dma;
+ dma_addr_t buffer_list_dma[IBMVETH_MAX_RX_QUEUES];
dma_addr_t filter_list_dma;
- struct ibmveth_buff_pool rx_buff_pool[IBMVETH_NUM_BUFF_POOLS];
- struct ibmveth_rx_q rx_queue;
+ struct ibmveth_buff_pool rx_buff_pool[IBMVETH_MAX_RX_QUEUES][IBMVETH_NUM_BUFF_POOLS];
+ struct ibmveth_rx_q rx_queue[IBMVETH_MAX_RX_QUEUES];
+ u64 queue_handle[IBMVETH_MAX_RX_QUEUES];
+ unsigned int queue_irq[IBMVETH_MAX_RX_QUEUES];
+ int multi_queue;
+ unsigned int num_rx_queues;
int rx_csum;
int large_send;
bool is_active_trunk;
--
2.39.3 (Apple Git-146)
^ permalink raw reply related
* [PATCH v1 03/18] ibmveth: Add MQ-ready RX statistics structures
From: Mingming Cao @ 2026-06-30 14:53 UTC (permalink / raw)
To: netdev
Cc: horms, bjking1, haren, ricklind, mmc, kuba, edumazet, pabeni,
linuxppc-dev, maddy, mpe, Dave Marquardt
In-Reply-To: <cover.1782758799.git.mmc@linux.ibm.com>
We'll want per-queue RX counters once MQ is running, and it's useful to
see whether the driver is hitting legacy or per-queue hcalls. Add the
structs and alloc helpers now, wire them up later:
ibmveth_hcall_stats for register/add/free/send hcall counts,
ibmveth_rx_queue_stats for per-queue packets/bytes/polls/etc.,
ibmveth_alloc_rx_qstats() / ibmveth_free_rx_qstats().
Marked __maybe_unused until open and the RX path start using them. No
behavior change yet.
Signed-off-by: Mingming Cao <mmc@linux.ibm.com>
Reviewed-by: Dave Marquardt <davemarq@linux.ibm.com>
---
drivers/net/ethernet/ibm/ibmveth.c | 27 +++++++++++++++++++++++++++
drivers/net/ethernet/ibm/ibmveth.h | 29 +++++++++++++++++++++++++++++
2 files changed, 56 insertions(+)
diff --git a/drivers/net/ethernet/ibm/ibmveth.c b/drivers/net/ethernet/ibm/ibmveth.c
index 4f9dbee7477d..8f9f927bff23 100644
--- a/drivers/net/ethernet/ibm/ibmveth.c
+++ b/drivers/net/ethernet/ibm/ibmveth.c
@@ -611,6 +611,33 @@ static int ibmveth_register_logical_lan(struct ibmveth_adapter *adapter,
return rc;
}
+/**
+ * ibmveth_alloc_rx_qstats - Allocate per-queue RX statistics
+ * @adapter: ibmveth adapter structure
+ *
+ * Return: 0 on success, -ENOMEM on failure
+ */
+static int __maybe_unused ibmveth_alloc_rx_qstats(struct ibmveth_adapter *adapter)
+{
+ adapter->rx_qstats = kcalloc(IBMVETH_MAX_RX_QUEUES,
+ sizeof(struct ibmveth_rx_queue_stats),
+ GFP_KERNEL);
+ if (!adapter->rx_qstats)
+ return -ENOMEM;
+
+ return 0;
+}
+
+/**
+ * ibmveth_free_rx_qstats - Free per-queue RX statistics
+ * @adapter: ibmveth adapter structure
+ */
+static void __maybe_unused ibmveth_free_rx_qstats(struct ibmveth_adapter *adapter)
+{
+ kfree(adapter->rx_qstats);
+ adapter->rx_qstats = NULL;
+}
+
static int ibmveth_open(struct net_device *netdev)
{
struct ibmveth_adapter *adapter = netdev_priv(netdev);
diff --git a/drivers/net/ethernet/ibm/ibmveth.h b/drivers/net/ethernet/ibm/ibmveth.h
index b17894695c2e..f0dffe42e8fe 100644
--- a/drivers/net/ethernet/ibm/ibmveth.h
+++ b/drivers/net/ethernet/ibm/ibmveth.h
@@ -290,6 +290,30 @@ static int pool_active[] = { 1, 1, 0, 0, 1};
#define IBM_VETH_INVALID_MAP ((u16)0xffff)
+struct ibmveth_hcall_stats {
+ u64 reg_lan_queue; /* H_REG_LOGICAL_LAN_QUEUE */
+ u64 reg_lan; /* H_REGISTER_LOGICAL_LAN */
+ u64 add_bufs_queue; /* H_ADD_LOGICAL_LAN_BUFFERS_QUEUE */
+ u64 add_bufs; /* H_ADD_LOGICAL_LAN_BUFFERS */
+ u64 add_buf; /* H_ADD_LOGICAL_LAN_BUFFER */
+ u64 free_lan_queue; /* H_FREE_LOGICAL_LAN_QUEUE */
+ u64 free_lan; /* H_FREE_LOGICAL_LAN */
+ u64 send_lan; /* H_SEND_LOGICAL_LAN */
+};
+
+struct ibmveth_rx_queue_stats {
+ u64 packets;
+ u64 bytes;
+ u64 interrupts;
+ u64 polls;
+ u64 large_packets;
+ u64 invalid_buffers;
+ u64 no_buffer_drops;
+};
+
+#define IBMVETH_NUM_RX_QSTATS \
+ (sizeof(struct ibmveth_rx_queue_stats) / sizeof(u64))
+
struct ibmveth_buff_pool {
u32 size;
u32 index;
@@ -352,6 +376,11 @@ struct ibmveth_adapter {
u64 tx_send_failed;
u64 tx_large_packets;
u64 rx_large_packets;
+
+ /* Multi-queue statistics */
+ struct ibmveth_hcall_stats hcall_stats;
+ struct ibmveth_rx_queue_stats *rx_qstats;
+
/* Ethtool settings */
u8 duplex;
u32 speed;
--
2.39.3 (Apple Git-146)
^ permalink raw reply related
* [PATCH v1 04/18] ibmveth: Refactor RX resource allocation for MQ RX bring-up
From: Mingming Cao @ 2026-06-30 14:53 UTC (permalink / raw)
To: netdev
Cc: horms, bjking1, haren, ricklind, mmc, kuba, edumazet, pabeni,
linuxppc-dev, maddy, mpe, Dave Marquardt
In-Reply-To: <cover.1782758799.git.mmc@linux.ibm.com>
ibmveth_open() allocates the filter list and every RX queue inline.
That's already ~160 lines and would get ugly once we loop over
num_rx_queues, especially on error unwind.
Pull the RX bits into helpers:
ibmveth_alloc_filter_list() / ibmveth_free_filter_list()
— shared multicast filter list (one per adapter, not per queue)
ibmveth_alloc_rx_queues() / ibmveth_cleanup_rx_resources()
— per-queue buffer lists and RX rings, looping [0, num_rx_queues)
alloc_rx_queues() rolls back on failure so open() does not need nested
goto chains for every queue index.
This is the first of several helper-only patches (pools, IRQ, TX, PHYP
registration, open/close wiring, buffer submit) that reshape bring-up
ahead of MQ datapath commit later in the series.
Signed-off-by: Mingming Cao <mmc@linux.ibm.com>
Reviewed-by: Dave Marquardt <davemarq@linux.ibm.com>
---
drivers/net/ethernet/ibm/ibmveth.c | 168 +++++++++++++++++++++++++++++
1 file changed, 168 insertions(+)
diff --git a/drivers/net/ethernet/ibm/ibmveth.c b/drivers/net/ethernet/ibm/ibmveth.c
index 8f9f927bff23..b8adc9935471 100644
--- a/drivers/net/ethernet/ibm/ibmveth.c
+++ b/drivers/net/ethernet/ibm/ibmveth.c
@@ -147,6 +147,174 @@ static unsigned int ibmveth_real_max_tx_queues(void)
return min(n_cpu, IBMVETH_MAX_QUEUES);
}
+/**
+ * ibmveth_alloc_filter_list - Allocate and map filter list
+ * @adapter: ibmveth adapter structure
+ *
+ * Return: 0 on success, negative error code on failure
+ */
+static int __maybe_unused ibmveth_alloc_filter_list(struct ibmveth_adapter *adapter)
+{
+ struct device *dev = &adapter->vdev->dev;
+ struct net_device *netdev = adapter->netdev;
+
+ adapter->filter_list_addr = (void *)get_zeroed_page(GFP_KERNEL);
+ if (!adapter->filter_list_addr) {
+ netdev_err(netdev, "unable to allocate filter pages\n");
+ return -ENOMEM;
+ }
+
+ adapter->filter_list_dma = dma_map_single(dev,
+ adapter->filter_list_addr,
+ 4096, DMA_BIDIRECTIONAL);
+ if (dma_mapping_error(dev, adapter->filter_list_dma)) {
+ netdev_err(netdev, "unable to map filter list pages\n");
+ free_page((unsigned long)adapter->filter_list_addr);
+ adapter->filter_list_addr = NULL;
+ return -ENOMEM;
+ }
+
+ netdev_dbg(netdev, "filter list @ 0x%p (DMA: 0x%llx)\n",
+ adapter->filter_list_addr,
+ (unsigned long long)adapter->filter_list_dma);
+
+ return 0;
+}
+
+/**
+ * ibmveth_free_filter_list - Free filter list resources
+ * @adapter: ibmveth adapter structure
+ */
+static void __maybe_unused ibmveth_free_filter_list(struct ibmveth_adapter *adapter)
+{
+ struct device *dev = &adapter->vdev->dev;
+
+ if (adapter->filter_list_dma) {
+ dma_unmap_single(dev, adapter->filter_list_dma, 4096,
+ DMA_BIDIRECTIONAL);
+ adapter->filter_list_dma = 0;
+ }
+
+ if (adapter->filter_list_addr) {
+ free_page((unsigned long)adapter->filter_list_addr);
+ adapter->filter_list_addr = NULL;
+ }
+}
+
+/**
+ * ibmveth_alloc_rx_queues - Allocate per-queue RX resources
+ * @adapter: ibmveth adapter structure
+ * @rxq_entries: Number of entries per RX queue
+ *
+ * Return: 0 on success, negative error code on failure
+ */
+static int __maybe_unused
+ibmveth_alloc_rx_queues(struct ibmveth_adapter *adapter, int rxq_entries)
+{
+ struct device *dev = &adapter->vdev->dev;
+ struct net_device *netdev = adapter->netdev;
+ int i;
+
+ for (i = 0; i < adapter->num_rx_queues; i++) {
+ adapter->buffer_list_addr[i] = (void *)get_zeroed_page(GFP_KERNEL);
+ if (!adapter->buffer_list_addr[i]) {
+ netdev_err(netdev, "unable to allocate buffer list for queue %d\n", i);
+ goto err_cleanup;
+ }
+
+ adapter->rx_queue[i].queue_len =
+ sizeof(struct ibmveth_rx_q_entry) * rxq_entries;
+ adapter->rx_queue[i].queue_addr =
+ dma_alloc_coherent(dev, adapter->rx_queue[i].queue_len,
+ &adapter->rx_queue[i].queue_dma,
+ GFP_KERNEL);
+ if (!adapter->rx_queue[i].queue_addr) {
+ netdev_err(netdev, "unable to allocate RX queue for queue %d\n", i);
+ goto err_cleanup;
+ }
+
+ adapter->buffer_list_dma[i] = dma_map_single(dev,
+ adapter->buffer_list_addr[i],
+ 4096, DMA_BIDIRECTIONAL);
+ if (dma_mapping_error(dev, adapter->buffer_list_dma[i])) {
+ netdev_err(netdev, "unable to map buffer list for queue %d\n", i);
+ adapter->buffer_list_dma[i] = 0;
+ goto err_cleanup;
+ }
+
+ adapter->rx_queue[i].index = 0;
+ adapter->rx_queue[i].num_slots = rxq_entries;
+ adapter->rx_queue[i].toggle = 1;
+
+ netdev_dbg(netdev, "queue %d: buffer_list @ 0x%p (DMA: 0x%llx), rx_queue @ 0x%p (DMA: 0x%llx), %llu entries\n",
+ i, adapter->buffer_list_addr[i],
+ (unsigned long long)adapter->buffer_list_dma[i],
+ adapter->rx_queue[i].queue_addr,
+ (unsigned long long)adapter->rx_queue[i].queue_dma,
+ (unsigned long long)rxq_entries);
+ }
+
+ netdev_dbg(netdev, "allocated %d RX queue(s) with %d entries each\n",
+ adapter->num_rx_queues, rxq_entries);
+
+ return 0;
+
+err_cleanup:
+ /* Clean up previously allocated queues */
+ for (; i >= 0; i--) {
+ if (adapter->buffer_list_dma[i]) {
+ dma_unmap_single(dev, adapter->buffer_list_dma[i],
+ 4096, DMA_BIDIRECTIONAL);
+ adapter->buffer_list_dma[i] = 0;
+ }
+ if (adapter->rx_queue[i].queue_addr) {
+ dma_free_coherent(dev, adapter->rx_queue[i].queue_len,
+ adapter->rx_queue[i].queue_addr,
+ adapter->rx_queue[i].queue_dma);
+ adapter->rx_queue[i].queue_addr = NULL;
+ }
+ if (adapter->buffer_list_addr[i]) {
+ free_page((unsigned long)adapter->buffer_list_addr[i]);
+ adapter->buffer_list_addr[i] = NULL;
+ }
+ }
+
+ return -ENOMEM;
+}
+
+/**
+ * ibmveth_cleanup_rx_resources - Free all RX queue resources
+ * @adapter: ibmveth adapter structure
+ */
+static void __maybe_unused ibmveth_cleanup_rx_resources(struct ibmveth_adapter *adapter)
+{
+ struct device *dev = &adapter->vdev->dev;
+ int i;
+
+ netdev_dbg(adapter->netdev, "cleaning up %d RX queue(s)\n",
+ adapter->num_rx_queues);
+
+ for (i = 0; i < adapter->num_rx_queues; i++) {
+ if (adapter->buffer_list_dma[i]) {
+ dma_unmap_single(dev, adapter->buffer_list_dma[i],
+ 4096, DMA_BIDIRECTIONAL);
+ adapter->buffer_list_dma[i] = 0;
+ }
+
+ if (adapter->rx_queue[i].queue_addr) {
+ dma_free_coherent(dev, adapter->rx_queue[i].queue_len,
+ adapter->rx_queue[i].queue_addr,
+ adapter->rx_queue[i].queue_dma);
+ adapter->rx_queue[i].queue_addr = NULL;
+ }
+
+ if (adapter->buffer_list_addr[i]) {
+ free_page((unsigned long)adapter->buffer_list_addr[i]);
+ adapter->buffer_list_addr[i] = NULL;
+ }
+ }
+}
+
/* setup the initial settings for a buffer pool */
static void ibmveth_init_buffer_pool(struct ibmveth_buff_pool *pool,
u32 pool_index, u32 pool_size,
--
2.39.3 (Apple Git-146)
^ permalink raw reply related
* [PATCH v1 05/18] ibmveth: Refactor buffer pool management for per-queue MQ RX
From: Mingming Cao @ 2026-06-30 14:53 UTC (permalink / raw)
To: netdev
Cc: horms, bjking1, haren, ricklind, mmc, kuba, edumazet, pabeni,
linuxppc-dev, maddy, mpe, Dave Marquardt
In-Reply-To: <cover.1782758799.git.mmc@linux.ibm.com>
This is the key memory-model change for MQ RX.
Legacy ibmveth uses five adapter-level RX buffer pools (512 B
through 64 KiB slots). pool_active[] enables the standard-MTU pools by
default; larger pools activate when MTU requires them. With single-queue
RX that set is shared on one completion path.
MQ requires the same pool model per queue: buffers post with
H_ADD_LOGICAL_LAN_BUFFERS_QUEUE against a queue handle and completions
return on that queue. Sharing pools across queues would mix ownership and
break queue-local replenish/drain/teardown.
Refactor around queue-local pools with static geometry (still defined at
probe on queue 0, copied to queues 1..N at alloc time):
rx_buff_pool[queue][pool]
ibmveth_alloc_queue_buffer_pools()
ibmveth_free_queue_buffer_pools()
ibmveth_alloc_buffer_pools() / ibmveth_free_buffer_pools()
Queue 0 remains the template for pool geometry (size, buff_size,
threshold, active). For queues 1..N we copy metadata from queue 0, then
allocate actual backing arrays/skbs per queue.
At the default 1500-byte MTU, pool 4 (64 KiB buffers) is not needed and
costs guest memory when allocated per queue in MQ mode. Clear
pool_active[4] so open() skips it; ibmveth_change_mtu() still enables
larger pools when MTU warrants jumbo frames.
Error handling is also made queue-safe:
- if allocation fails in one pool, unwind only what was allocated for
that queue, then unwind prior queues in the caller
- free paths release pools based on real allocations
(free_map/dma_addr/skbuff), not only pool->active
That allocation-based free check is intentional: later resize and failure
paths can leave memory allocated even when active was already cleared.
Freeing by allocation state avoids leaks and double-free corner cases.
This split keeps the per-queue pool design isolated and reviewable ahead
of the MQ datapath enable commit later in the series.
Signed-off-by: Mingming Cao <mmc@linux.ibm.com>
Reviewed-by: Dave Marquardt <davemarq@linux.ibm.com>
---
drivers/net/ethernet/ibm/ibmveth.c | 127 +++++++++++++++++++++++++++++
drivers/net/ethernet/ibm/ibmveth.h | 2 +-
2 files changed, 128 insertions(+), 1 deletion(-)
diff --git a/drivers/net/ethernet/ibm/ibmveth.c b/drivers/net/ethernet/ibm/ibmveth.c
index b8adc9935471..95068fb20dba 100644
--- a/drivers/net/ethernet/ibm/ibmveth.c
+++ b/drivers/net/ethernet/ibm/ibmveth.c
@@ -611,6 +611,133 @@ static void ibmveth_free_buffer_pool(struct ibmveth_adapter *adapter,
}
}
+/**
+ * ibmveth_alloc_queue_buffer_pools - Allocate buffer pools for a single queue
+ * @adapter: ibmveth adapter structure
+ * @queue: queue index
+ *
+ * Allocates all active buffer pools for the specified queue.
+ * Pool metadata must be initialized before calling this function.
+ *
+ * Return: 0 on success, negative error code on failure
+ */
+static int ibmveth_alloc_queue_buffer_pools(struct ibmveth_adapter *adapter,
+ int queue)
+{
+ struct net_device *netdev = adapter->netdev;
+ int i;
+
+ for (i = 0; i < IBMVETH_NUM_BUFF_POOLS; i++) {
+ if (!adapter->rx_buff_pool[queue][i].active)
+ continue;
+
+ if (ibmveth_alloc_buffer_pool(&adapter->rx_buff_pool[queue][i])) {
+ netdev_err(netdev,
+ "unable to allocate buffer pool %d for queue %d (size=%u, count=%u)\n",
+ i, queue,
+ adapter->rx_buff_pool[queue][i].buff_size,
+ adapter->rx_buff_pool[queue][i].size);
+ adapter->rx_buff_pool[queue][i].active = 0;
+
+ /* Free pools allocated so far for this queue */
+ while (--i >= 0) {
+ if (adapter->rx_buff_pool[queue][i].active)
+ ibmveth_free_buffer_pool(adapter,
+ &adapter->rx_buff_pool[queue][i]);
+ }
+ return -ENOMEM;
+ }
+ }
+
+ return 0;
+}
+
+/**
+ * ibmveth_free_queue_buffer_pools - Free buffer pools for a single queue
+ * @adapter: ibmveth adapter structure
+ * @queue: queue index
+ *
+ * Frees all active buffer pools for the specified queue.
+ */
+static void ibmveth_free_queue_buffer_pools(struct ibmveth_adapter *adapter,
+ int queue)
+{
+ int i;
+
+ for (i = 0; i < IBMVETH_NUM_BUFF_POOLS; i++) {
+ struct ibmveth_buff_pool *pool = &adapter->rx_buff_pool[queue][i];
+
+ /* Free pool if it has allocated memory, regardless of active flag.
+ * Pools may have memory allocated but not marked active during
+ * queue scale-up, so we must check for actual allocations.
+ */
+ if (pool->free_map || pool->dma_addr || pool->skbuff)
+ ibmveth_free_buffer_pool(adapter, pool);
+ }
+}
+
+/**
+ * ibmveth_alloc_buffer_pools - Allocate buffer pools for all queues
+ * @adapter: ibmveth adapter structure
+ *
+ * Initializes pool metadata for queues 1-N from queue 0 settings,
+ * then allocates buffer pools for all queues using the helper function.
+ *
+ * Return: 0 on success, negative error code on failure
+ */
+static int __maybe_unused ibmveth_alloc_buffer_pools(struct ibmveth_adapter *adapter)
+{
+ struct net_device *netdev = adapter->netdev;
+ int i, q, rc;
+
+ /* Initialize pool metadata for queues 1-15 from queue 0 settings */
+ for (q = 1; q < adapter->num_rx_queues; q++) {
+ for (i = 0; i < IBMVETH_NUM_BUFF_POOLS; i++) {
+ struct ibmveth_buff_pool *src = &adapter->rx_buff_pool[0][i];
+ struct ibmveth_buff_pool *dst = &adapter->rx_buff_pool[q][i];
+
+ dst->size = src->size;
+ dst->index = src->index;
+ dst->buff_size = src->buff_size;
+ dst->threshold = src->threshold;
+ dst->active = src->active;
+ }
+ }
+
+ /* Allocate actual buffers for all queues */
+ for (q = 0; q < adapter->num_rx_queues; q++) {
+ rc = ibmveth_alloc_queue_buffer_pools(adapter, q);
+ if (rc) {
+ /* Free pools for all previous queues */
+ while (--q >= 0)
+ ibmveth_free_queue_buffer_pools(adapter, q);
+ return rc;
+ }
+ }
+
+ netdev_dbg(netdev, "allocated buffer pools for %d queue(s)\n",
+ adapter->num_rx_queues);
+ return 0;
+}
+
+/**
+ * ibmveth_free_buffer_pools - Free buffer pools for all queues
+ * @adapter: ibmveth adapter structure
+ *
+ * Frees buffer pools for all queues using the helper function.
+ */
+static void __maybe_unused ibmveth_free_buffer_pools(struct ibmveth_adapter *adapter)
+{
+ int q;
+
+ /* Free buffer pools for all queues */
+ for (q = 0; q < adapter->num_rx_queues; q++)
+ ibmveth_free_queue_buffer_pools(adapter, q);
+
+ netdev_dbg(adapter->netdev, "freed buffer pools for %d queue(s)\n",
+ adapter->num_rx_queues);
+}
+
/**
* ibmveth_remove_buffer_from_pool - remove a buffer from a pool
* @adapter: adapter instance
diff --git a/drivers/net/ethernet/ibm/ibmveth.h b/drivers/net/ethernet/ibm/ibmveth.h
index f0dffe42e8fe..d2ceeccd5fbd 100644
--- a/drivers/net/ethernet/ibm/ibmveth.h
+++ b/drivers/net/ethernet/ibm/ibmveth.h
@@ -286,7 +286,7 @@ static inline long h_illan_attributes(unsigned long unit_address,
static int pool_size[] = { 512, 1024 * 2, 1024 * 16, 1024 * 32, 1024 * 64 };
static int pool_count[] = { 256, 512, 256, 256, 256 };
static int pool_count_cmo[] = { 256, 512, 256, 256, 64 };
-static int pool_active[] = { 1, 1, 0, 0, 1};
+static int pool_active[] = { 1, 1, 0, 0, 0};
#define IBM_VETH_INVALID_MAP ((u16)0xffff)
--
2.39.3 (Apple Git-146)
^ permalink raw reply related
* [PATCH v1 06/18] ibmveth: Refactor RX interrupt control for MQ RX queues
From: Mingming Cao @ 2026-06-30 14:53 UTC (permalink / raw)
To: netdev
Cc: horms, bjking1, haren, ricklind, mmc, kuba, edumazet, pabeni,
linuxppc-dev, maddy, mpe, Dave Marquardt
In-Reply-To: <cover.1782758799.git.mmc@linux.ibm.com>
Queue 0 and subordinate RX queues use different interrupt control
interfaces in PHYP:
- queue 0: h_vio_signal() after h_register_logical_lan()
- queue N: H_VIOCTL against the queue handle/hwirq mapping
The current code is single-queue oriented and cannot safely scale to
multiple RX queues in poll completion and open/close IRQ setup.
Introduce queue-indexed interrupt helpers:
ibmveth_enable_irq(adapter, queue_index)
ibmveth_disable_irq(adapter, queue_index)
ibmveth_setup_rx_interrupts()
ibmveth_cleanup_rx_interrupts()
These helpers centralize queue0-vs-subordinate dispatch and make IRQ
lifecycle symmetric across open/close and future resize paths.
request_irq() is wired with &adapter->napi[i] as dev_id per queue, so
interrupt ownership follows the NAPI instance that services that RX
queue.
Signed-off-by: Mingming Cao <mmc@linux.ibm.com>
Reviewed-by: Dave Marquardt <davemarq@linux.ibm.com>
---
drivers/net/ethernet/ibm/ibmveth.c | 160 +++++++++++++++++++++++++++++
1 file changed, 160 insertions(+)
diff --git a/drivers/net/ethernet/ibm/ibmveth.c b/drivers/net/ethernet/ibm/ibmveth.c
index 95068fb20dba..b5ae979c1f82 100644
--- a/drivers/net/ethernet/ibm/ibmveth.c
+++ b/drivers/net/ethernet/ibm/ibmveth.c
@@ -315,6 +315,166 @@ static void __maybe_unused ibmveth_cleanup_rx_resources(struct ibmveth_adapter *
}
}
+/**
+ * ibmveth_toggle_irq - Common helper to enable/disable queue interrupts
+ * @adapter: ibmveth adapter structure
+ * @queue_index: Index of the queue (0 for primary, 1+ for subordinate)
+ * @enable: true to enable, false to disable
+ *
+ * For queue 0 (primary), uses h_vio_signal() as it's registered via
+ * h_register_logical_lan(). For subordinate queues (1+), uses H_VIOCTL
+ * with H_ENABLE/DISABLE_VIO_INTERRUPT for per-queue interrupt control.
+ *
+ * Return: 0 on success, error code otherwise
+ */
+static int
+ibmveth_toggle_irq(struct ibmveth_adapter *adapter, int queue_index, bool enable)
+{
+ unsigned long rc;
+ unsigned long irq = adapter->queue_irq[queue_index];
+ const char *action = enable ? "enable" : "disable";
+
+ if (queue_index == 0) {
+ /* Primary queue: use h_vio_signal() */
+ rc = h_vio_signal(adapter->vdev->unit_address,
+ enable ? VIO_IRQ_ENABLE : VIO_IRQ_DISABLE);
+ } else {
+ /* Subordinate queues: use H_VIOCTL with hardware IRQ */
+ struct irq_data *irq_data = irq_get_irq_data(irq);
+ irq_hw_number_t hwirq;
+ u64 vioctl_cmd = enable ? H_ENABLE_VIO_INTERRUPT : H_DISABLE_VIO_INTERRUPT;
+
+ if (!irq_data) {
+ netdev_err(adapter->netdev,
+ "Failed to get IRQ data for queue %d (virq=%lu)\n",
+ queue_index, irq);
+ return -EINVAL;
+ }
+
+ hwirq = irqd_to_hwirq(irq_data);
+ rc = plpar_hcall_norets(H_VIOCTL,
+ adapter->vdev->unit_address,
+ vioctl_cmd,
+ hwirq, 0, 0);
+
+ if (rc == H_PARAMETER) {
+ /* H_PARAMETER is non-fatal when IRQ is already in the requested state. */
+ netdev_warn_once(adapter->netdev,
+ "H_VIOCTL %s IRQ returned H_PARAMETER for queue %d (hwirq=%lu)\n",
+ action, queue_index, hwirq);
+ return 0;
+ }
+ }
+
+ if (rc)
+ netdev_err(adapter->netdev,
+ "Failed to %s IRQ for queue %d, rc=%ld\n",
+ action, queue_index, rc);
+ return rc;
+}
+
+/**
+ * ibmveth_disable_irq - Disable interrupt for a specific queue
+ * @adapter: ibmveth adapter structure
+ * @queue_index: Index of the queue (0 for primary, 1+ for subordinate)
+ *
+ * Return: 0 on success, error code otherwise
+ */
+static int
+ibmveth_disable_irq(struct ibmveth_adapter *adapter, int queue_index)
+{
+ return ibmveth_toggle_irq(adapter, queue_index, false);
+}
+
+/**
+ * ibmveth_enable_irq - Enable interrupt for a specific queue
+ * @adapter: ibmveth adapter structure
+ * @queue_index: Index of the queue (0 for primary, 1+ for subordinate)
+ *
+ * Return: 0 on success, error code otherwise
+ */
+static int
+ibmveth_enable_irq(struct ibmveth_adapter *adapter, int queue_index)
+{
+ return ibmveth_toggle_irq(adapter, queue_index, true);
+}
+
+/**
+ * ibmveth_setup_rx_interrupts - Register IRQs and enable NAPI
+ * @adapter: ibmveth adapter structure
+ *
+ * Registers interrupt handlers for all RX queues and enables NAPI polling.
+ * On error, cleans up any successfully registered IRQs before returning.
+ *
+ * Return: 0 on success, negative error code on failure
+ */
+static int __maybe_unused
+ibmveth_setup_rx_interrupts(struct ibmveth_adapter *adapter)
+{
+ struct net_device *netdev = adapter->netdev;
+ int i, rc;
+
+ for (i = 0; i < adapter->num_rx_queues; i++) {
+ if (!adapter->queue_irq[i]) {
+ netdev_err(netdev, "queue %d has invalid IRQ (0)\n", i);
+ rc = -EINVAL;
+ goto err_free_irqs;
+ }
+
+ rc = request_irq(adapter->queue_irq[i], ibmveth_interrupt,
+ 0, netdev->name, &adapter->napi[i]);
+ if (rc) {
+ netdev_err(netdev,
+ "request_irq() failed for irq 0x%x queue %d: %d\n",
+ adapter->queue_irq[i], i, rc);
+ goto err_free_irqs;
+ }
+ }
+
+ for (i = 0; i < adapter->num_rx_queues; i++)
+ napi_enable(&adapter->napi[i]);
+
+ return 0;
+
+err_free_irqs:
+ while (--i >= 0)
+ free_irq(adapter->queue_irq[i], &adapter->napi[i]);
+ return rc;
+}
+
+/**
+ * ibmveth_cleanup_rx_interrupts - Disable NAPI and free IRQs
+ * @adapter: ibmveth adapter structure
+ *
+ * Disables NAPI polling and frees interrupt handlers for all RX queues.
+ */
+static void
+ibmveth_cleanup_rx_interrupts(struct ibmveth_adapter *adapter)
+{
+ int i;
+
+ for (i = 0; i < adapter->num_rx_queues; i++)
+ napi_disable(&adapter->napi[i]);
+
+ for (i = 0; i < adapter->num_rx_queues; i++) {
+ if (adapter->queue_irq[i])
+ free_irq(adapter->queue_irq[i], &adapter->napi[i]);
+ }
+
+ /* Dispose IRQ mappings for subordinate queues (1-15).
+ * Queue 0 uses netdev->irq from device tree, not irq_create_mapping().
+ */
+ for (i = 1; i < adapter->num_rx_queues; i++) {
+ if (adapter->queue_irq[i]) {
+ irq_dispose_mapping(adapter->queue_irq[i]);
+ adapter->queue_irq[i] = 0;
+ }
+ }
+
+ /* Clear queue 0 IRQ number */
+ adapter->queue_irq[0] = 0;
+}
+
/* setup the initial settings for a buffer pool */
static void ibmveth_init_buffer_pool(struct ibmveth_buff_pool *pool,
u32 pool_index, u32 pool_size,
--
2.39.3 (Apple Git-146)
^ permalink raw reply related
* [PATCH v1 07/18] ibmveth: Refactor TX resource allocation in open/close paths
From: Mingming Cao @ 2026-06-30 14:53 UTC (permalink / raw)
To: netdev
Cc: horms, bjking1, haren, ricklind, mmc, kuba, edumazet, pabeni,
linuxppc-dev, maddy, mpe, Dave Marquardt
In-Reply-To: <cover.1782758799.git.mmc@linux.ibm.com>
Same story as the RX refactor: pull TX LTB alloc out of open/close.
ibmveth_alloc_tx_resources() / ibmveth_free_tx_resources() walk
real_num_tx_queues so ethtool TX channel changes keep working. Hooked
into open/close in the next patch.
No MQ RX behaviour change — TX was already multi-queue capable via
ethtool -L. This patch only tidies the open/close path ahead of the
RX helper wiring in the next patch.
Signed-off-by: Mingming Cao <mmc@linux.ibm.com>
Reviewed-by: Dave Marquardt <davemarq@linux.ibm.com>
---
drivers/net/ethernet/ibm/ibmveth.c | 43 ++++++++++++++++++++++++++++++
1 file changed, 43 insertions(+)
diff --git a/drivers/net/ethernet/ibm/ibmveth.c b/drivers/net/ethernet/ibm/ibmveth.c
index b5ae979c1f82..63b0184c622a 100644
--- a/drivers/net/ethernet/ibm/ibmveth.c
+++ b/drivers/net/ethernet/ibm/ibmveth.c
@@ -1038,6 +1038,49 @@ static int ibmveth_allocate_tx_ltb(struct ibmveth_adapter *adapter, int idx)
return 0;
}
+/**
+ * ibmveth_alloc_tx_resources - Allocate TX resources for all queues
+ * @adapter: ibmveth adapter structure
+ *
+ * Allocates TX Long Term Buffers (LTBs) for all TX queues.
+ *
+ * Return: 0 on success, -ENOMEM on failure
+ */
+static int __maybe_unused
+ibmveth_alloc_tx_resources(struct ibmveth_adapter *adapter)
+{
+ struct net_device *netdev = adapter->netdev;
+ int i;
+
+ for (i = 0; i < netdev->real_num_tx_queues; i++) {
+ if (ibmveth_allocate_tx_ltb(adapter, i))
+ goto err_free_ltbs;
+ }
+
+ return 0;
+
+err_free_ltbs:
+ while (--i >= 0)
+ ibmveth_free_tx_ltb(adapter, i);
+ return -ENOMEM;
+}
+
+/**
+ * ibmveth_free_tx_resources - Free TX resources for all queues
+ * @adapter: ibmveth adapter structure
+ *
+ * Frees TX Long Term Buffers (LTBs) for all TX queues.
+ */
+static void __maybe_unused
+ibmveth_free_tx_resources(struct ibmveth_adapter *adapter)
+{
+ struct net_device *netdev = adapter->netdev;
+ int i;
+
+ for (i = 0; i < netdev->real_num_tx_queues; i++)
+ ibmveth_free_tx_ltb(adapter, i);
+}
+
static int ibmveth_register_logical_lan(struct ibmveth_adapter *adapter,
union ibmveth_buf_desc rxq_desc,
u64 mac_address)
--
2.39.3 (Apple Git-146)
^ permalink raw reply related
* [PATCH v1 08/18] ibmveth: Add RX queue register/deregister helpers for MQ
From: Mingming Cao @ 2026-06-30 14:53 UTC (permalink / raw)
To: netdev
Cc: horms, bjking1, haren, ricklind, mmc, kuba, edumazet, pabeni,
linuxppc-dev, maddy, mpe, Dave Marquardt
In-Reply-To: <cover.1782758799.git.mmc@linux.ibm.com>
MQ RX replaces a single adapter-level register/free pair with a mixed
PHYP model: queue 0 via h_register_logical_lan*(), subordinates via
H_REG_LOGICAL_LAN_QUEUE. Subordinate registration returns queue handles
and hardware IRQ numbers that must be mapped to Linux virqs and unwound
on failure.
Add queue lifecycle helpers to isolate that control plane:
ibmveth_register_logical_lan_queue()
ibmveth_register_single_rx_queue()
ibmveth_deregister_single_rx_queue()
ibmveth_register_rx_queues()
ibmveth_free_all_queues()
ibmveth_dispose_subordinate_irq_mappings()
These helpers are called only when multi_queue is enabled (patch 11).
Until then open/close still use the legacy register and buffer hcall
path; legacy firmware is unchanged.
When multi_queue is enabled, queue 0 uses
h_register_logical_lan_with_handle() so all queues share the per-queue
buffer hcall path. register_rx_queues() registers with PHYP only;
interrupt delivery is enabled later from ibmveth_setup_rx_interrupts()
after request_irq(). Partial registration failure disposes subordinate virq
mappings before ibmveth_free_all_queues() clears handles;
free_all_queues() clears queue handles only — IRQ mappings are released
by dispose_subordinate_irq_mappings() or cleanup_rx_interrupts().
This commit also centralizes hcall accounting on the register/free paths.
Signed-off-by: Mingming Cao <mmc@linux.ibm.com>
Reviewed-by: Dave Marquardt <davemarq@linux.ibm.com>
---
drivers/net/ethernet/ibm/ibmveth.c | 337 ++++++++++++++++++++++++++++-
1 file changed, 332 insertions(+), 5 deletions(-)
diff --git a/drivers/net/ethernet/ibm/ibmveth.c b/drivers/net/ethernet/ibm/ibmveth.c
index 63b0184c622a..7fc11a4e1f61 100644
--- a/drivers/net/ethernet/ibm/ibmveth.c
+++ b/drivers/net/ethernet/ibm/ibmveth.c
@@ -21,6 +21,8 @@
#include <linux/skbuff.h>
#include <linux/init.h>
#include <linux/interrupt.h>
+#include <linux/irq.h>
+#include <linux/irqdomain.h>
#include <linux/mm.h>
#include <linux/pm.h>
#include <linux/ethtool.h>
@@ -399,6 +401,28 @@ ibmveth_enable_irq(struct ibmveth_adapter *adapter, int queue_index)
return ibmveth_toggle_irq(adapter, queue_index, true);
}
+/**
+ * ibmveth_dispose_subordinate_irq_mappings - Drop virq mappings for queues 1..N
+ * @adapter: ibmveth adapter structure
+ *
+ * Subordinate queues get mappings from irq_create_mapping() during PHYP
+ * registration. Queue 0 uses netdev->irq from device tree and is left alone.
+ * Call after free_irq() when handlers were installed, or alone when open
+ * fails during register_rx_queues() before request_irq().
+ */
+static void
+ibmveth_dispose_subordinate_irq_mappings(struct ibmveth_adapter *adapter)
+{
+ int i;
+
+ for (i = 1; i < adapter->num_rx_queues; i++) {
+ if (adapter->queue_irq[i]) {
+ irq_dispose_mapping(adapter->queue_irq[i]);
+ adapter->queue_irq[i] = 0;
+ }
+ }
+}
+
/**
* ibmveth_setup_rx_interrupts - Register IRQs and enable NAPI
* @adapter: ibmveth adapter structure
@@ -1082,8 +1106,8 @@ ibmveth_free_tx_resources(struct ibmveth_adapter *adapter)
}
static int ibmveth_register_logical_lan(struct ibmveth_adapter *adapter,
- union ibmveth_buf_desc rxq_desc,
- u64 mac_address)
+ union ibmveth_buf_desc rxq_desc,
+ u64 mac_address)
{
int rc, try_again = 1;
@@ -1093,13 +1117,29 @@ static int ibmveth_register_logical_lan(struct ibmveth_adapter *adapter,
* try again, but only once.
*/
retry:
- rc = h_register_logical_lan(adapter->vdev->unit_address,
- adapter->buffer_list_dma[0], rxq_desc.desc,
- adapter->filter_list_dma, mac_address);
+ /* In multi-queue mode, obtain a queue handle for queue 0 so all RX
+ * queues can use the same per-queue buffer hypercalls.
+ */
+ if (adapter->multi_queue) {
+ rc = h_register_logical_lan_with_handle(adapter->vdev->unit_address,
+ adapter->buffer_list_dma[0],
+ rxq_desc.desc,
+ adapter->filter_list_dma,
+ mac_address,
+ &adapter->queue_handle[0]);
+ } else {
+ rc = h_register_logical_lan(adapter->vdev->unit_address,
+ adapter->buffer_list_dma[0],
+ rxq_desc.desc,
+ adapter->filter_list_dma,
+ mac_address);
+ }
+ adapter->hcall_stats.reg_lan++;
if (rc != H_SUCCESS && try_again) {
do {
rc = h_free_logical_lan(adapter->vdev->unit_address);
+ adapter->hcall_stats.free_lan++;
} while (H_IS_LONG_BUSY(rc) || (rc == H_BUSY));
try_again = 0;
@@ -1136,6 +1176,293 @@ static void __maybe_unused ibmveth_free_rx_qstats(struct ibmveth_adapter *adapte
adapter->rx_qstats = NULL;
}
+/**
+ * ibmveth_register_logical_lan_queue - Register subordinate queue with hypervisor
+ * @adapter: ibmveth adapter structure
+ * @rxq_desc: Receive queue descriptor
+ * @queue_index: RX queue index (1..N for subordinate queues)
+ *
+ * Registers a subordinate receive queue using H_REG_LOGICAL_LAN_QUEUE.
+ * On success, stores the queue handle and virtual IRQ in the adapter.
+ * Retries once if registration fails (handles kexec case). If IRQ mapping
+ * fails after a successful hypervisor registration, the queue is freed
+ * before returning.
+ *
+ * Return: H_SUCCESS on success, negative errno on IRQ mapping failure,
+ * hypervisor error code otherwise
+ */
+static int
+ibmveth_register_logical_lan_queue(struct ibmveth_adapter *adapter,
+ union ibmveth_buf_desc rxq_desc,
+ int queue_index)
+{
+ unsigned long handle, hwirq;
+ unsigned int virq;
+ long lpar_rc;
+ int try_again = 1;
+
+retry:
+ netdev_dbg(adapter->netdev,
+ "Attempting to register queue %d: unit_addr=0x%x buffer_list_dma=0x%llx rxq_desc=0x%llx\n",
+ queue_index, adapter->vdev->unit_address,
+ (unsigned long long)adapter->buffer_list_dma[queue_index],
+ (unsigned long long)rxq_desc.desc);
+
+ lpar_rc = h_reg_logical_lan_queue(adapter->vdev->unit_address,
+ adapter->buffer_list_dma[queue_index],
+ rxq_desc.desc, &handle, &hwirq);
+ adapter->hcall_stats.reg_lan_queue++;
+
+ if (lpar_rc == H_SUCCESS) {
+ virq = irq_create_mapping(NULL, hwirq);
+ if (!virq) {
+ unsigned long free_rc;
+
+ netdev_err(adapter->netdev,
+ "Failed to map IRQ for queue %d (hwirq=%lu)\n",
+ queue_index, hwirq);
+ do {
+ free_rc = h_free_logical_lan_queue(adapter->vdev->unit_address,
+ handle);
+ } while (H_IS_LONG_BUSY(free_rc) || (free_rc == H_BUSY));
+ adapter->hcall_stats.free_lan_queue++;
+ if (free_rc != H_SUCCESS)
+ netdev_err(adapter->netdev,
+ "h_free_logical_lan_queue failed for queue %d after IRQ map failure: rc=0x%lx\n",
+ queue_index, free_rc);
+ return -EINVAL;
+ }
+
+ adapter->queue_handle[queue_index] = handle;
+ adapter->queue_irq[queue_index] = virq;
+
+ netdev_dbg(adapter->netdev,
+ "queue %d registered: handle=0x%llx irq=%u\n",
+ queue_index, adapter->queue_handle[queue_index],
+ adapter->queue_irq[queue_index]);
+ return H_SUCCESS;
+ }
+
+ if (lpar_rc == H_FUNCTION) {
+ if (adapter->multi_queue) {
+ netdev_info(adapter->netdev,
+ "Multi queue mode not supported by firmware, falling back to single queue\n");
+ adapter->multi_queue = 0;
+ } else {
+ netdev_err(adapter->netdev,
+ "Unexpected H_FUNCTION for queue %d registration (MQ mode already disabled)\n",
+ queue_index);
+ }
+ return lpar_rc;
+ }
+
+ if (try_again) {
+ try_again = 0;
+ goto retry;
+ }
+
+ netdev_err(adapter->netdev,
+ "h_reg_logical_lan_queue failed with %ld after retry\n",
+ lpar_rc);
+ netdev_err(adapter->netdev,
+ "queue %d params: unit_addr=0x%x buffer_list_dma=0x%llx rxq_desc=0x%llx\n",
+ queue_index, adapter->vdev->unit_address,
+ (unsigned long long)adapter->buffer_list_dma[queue_index],
+ (unsigned long long)rxq_desc.desc);
+
+ return lpar_rc;
+}
+
+/**
+ * ibmveth_register_single_rx_queue - Register one subordinate RX queue
+ * @adapter: ibmveth adapter structure
+ * @queue_idx: Queue index to register (1..N)
+ * @mac_address: MAC address (unused; reserved for API symmetry)
+ *
+ * Builds the queue descriptor and registers with the hypervisor via
+ * ibmveth_register_logical_lan_queue().
+ *
+ * Return: 0 on success, -EINVAL if @queue_idx is invalid, -EIO on failure
+ */
+static int
+ibmveth_register_single_rx_queue(struct ibmveth_adapter *adapter,
+ int queue_idx, u64 mac_address)
+{
+ struct net_device *netdev = adapter->netdev;
+ union ibmveth_buf_desc rxq_desc;
+ long lpar_rc;
+
+ (void)mac_address;
+
+ if (WARN_ON(queue_idx < 1 || queue_idx >= IBMVETH_MAX_RX_QUEUES))
+ return -EINVAL;
+
+ rxq_desc.fields.flags_len = IBMVETH_BUF_VALID |
+ adapter->rx_queue[queue_idx].queue_len;
+ rxq_desc.fields.address = adapter->rx_queue[queue_idx].queue_dma;
+
+ lpar_rc = ibmveth_register_logical_lan_queue(adapter, rxq_desc,
+ queue_idx);
+ if (lpar_rc != H_SUCCESS) {
+ netdev_err(netdev, "Failed to register queue %d: rc=0x%lx\n",
+ queue_idx, lpar_rc);
+ return -EIO;
+ }
+
+ netdev_dbg(netdev, "Registered queue %d with handle 0x%llx\n",
+ queue_idx, adapter->queue_handle[queue_idx]);
+
+ return 0;
+}
+
+/**
+ * ibmveth_deregister_single_rx_queue - Deregister one subordinate RX queue
+ * @adapter: ibmveth adapter structure
+ * @queue_idx: Queue index to deregister (1..N)
+ *
+ * Deregisters a single queue via H_FREE_LOGICAL_LAN_QUEUE and disposes
+ * the IRQ mapping for subordinate queues. Queue 0 is freed only through
+ * ibmveth_free_all_queues() (H_FREE_LOGICAL_LAN).
+ */
+static void __maybe_unused
+ibmveth_deregister_single_rx_queue(struct ibmveth_adapter *adapter,
+ int queue_idx)
+{
+ unsigned long lpar_rc;
+
+ if (!adapter->queue_handle[queue_idx])
+ return;
+
+ do {
+ lpar_rc = h_free_logical_lan_queue(adapter->vdev->unit_address,
+ adapter->queue_handle[queue_idx]);
+ } while (H_IS_LONG_BUSY(lpar_rc) || (lpar_rc == H_BUSY));
+
+ adapter->hcall_stats.free_lan_queue++;
+
+ if (lpar_rc != H_SUCCESS) {
+ netdev_err(adapter->netdev,
+ "h_free_logical_lan_queue failed for queue %d: rc=0x%lx\n",
+ queue_idx, lpar_rc);
+ }
+
+ adapter->queue_handle[queue_idx] = 0;
+
+ if (queue_idx > 0 && adapter->queue_irq[queue_idx]) {
+ irq_dispose_mapping(adapter->queue_irq[queue_idx]);
+ adapter->queue_irq[queue_idx] = 0;
+ }
+
+ netdev_dbg(adapter->netdev, "Deregistered queue %d\n", queue_idx);
+}
+
+/**
+ * ibmveth_free_all_queues - Free all RX queues at once
+ * @adapter: ibmveth adapter structure
+ *
+ * Uses H_FREE_LOGICAL_LAN to free all queues in one hypercall.
+ * Used during interface close and registration error cleanup.
+ *
+ * Clears queue handles only; queue_irq[] is released by
+ * ibmveth_cleanup_rx_interrupts() on close, or by
+ * ibmveth_dispose_subordinate_irq_mappings() on partial register failure.
+ */
+static void ibmveth_free_all_queues(struct ibmveth_adapter *adapter)
+{
+ unsigned long lpar_rc;
+ int i;
+
+ netdev_dbg(adapter->netdev, "freeing all RX queues at once\n");
+
+ do {
+ lpar_rc = h_free_logical_lan(adapter->vdev->unit_address);
+ adapter->hcall_stats.free_lan++;
+ } while (H_IS_LONG_BUSY(lpar_rc) || (lpar_rc == H_BUSY));
+
+ if (lpar_rc != H_SUCCESS) {
+ netdev_err(adapter->netdev,
+ "h_free_logical_lan failed: %ld\n", lpar_rc);
+ }
+
+ for (i = 0; i < adapter->num_rx_queues; i++)
+ adapter->queue_handle[i] = 0;
+}
+
+/**
+ * ibmveth_register_rx_queues - Register RX queues with hypervisor
+ * @adapter: ibmveth adapter structure
+ * @mac_address: MAC address for device registration
+ *
+ * Registers queue 0 via ibmveth_register_logical_lan(), then subordinate
+ * queues 1..N when multi-queue mode is enabled.
+ *
+ * Return: 0 on success, -ENONET if queue 0 registration fails, -EIO on
+ * subordinate queue registration failure
+ */
+static int
+ibmveth_register_rx_queues(struct ibmveth_adapter *adapter, u64 mac_address)
+{
+ struct net_device *netdev = adapter->netdev;
+ union ibmveth_buf_desc rxq_desc;
+ unsigned long lpar_rc;
+ int i, rc;
+
+ rxq_desc.fields.flags_len = IBMVETH_BUF_VALID |
+ adapter->rx_queue[0].queue_len;
+ rxq_desc.fields.address = adapter->rx_queue[0].queue_dma;
+ adapter->queue_irq[0] = netdev->irq;
+
+ rc = ibmveth_disable_irq(adapter, 0);
+ if (rc != H_SUCCESS)
+ netdev_dbg(netdev,
+ "Failed to disable IRQ for queue 0 before registration, rc=%d\n",
+ rc);
+
+ lpar_rc = ibmveth_register_logical_lan(adapter, rxq_desc, mac_address);
+ if (lpar_rc != H_SUCCESS) {
+ netdev_err(netdev, "h_register_logical_lan failed: %ld\n", lpar_rc);
+ netdev_err(netdev,
+ "buffer TCE:0x%llx filter TCE:0x%llx rxq desc:0x%llx MAC:0x%llx\n",
+ adapter->buffer_list_dma[0],
+ adapter->filter_list_dma,
+ rxq_desc.desc, mac_address);
+ return -ENONET;
+ }
+
+ if (adapter->num_rx_queues == 1 || !adapter->multi_queue) {
+ netdev_dbg(netdev,
+ "registered 1 RX queue with hypervisor (single-queue mode)\n");
+ return 0;
+ }
+
+ netdev_dbg(netdev, "Registering %d subordinate queues (1-%d)\n",
+ adapter->num_rx_queues - 1, adapter->num_rx_queues - 1);
+
+ for (i = 1; i < adapter->num_rx_queues; i++) {
+ rc = ibmveth_register_single_rx_queue(adapter, i, mac_address);
+ if (rc) {
+ if (!adapter->queue_handle[i] || !adapter->queue_irq[i]) {
+ netdev_err(netdev,
+ "Invalid hypervisor return for queue %d: handle=0x%llx irq=%u\n",
+ i, adapter->queue_handle[i],
+ adapter->queue_irq[i]);
+ }
+ goto err_unregister;
+ }
+ }
+
+ netdev_dbg(netdev,
+ "registered %d RX queues with hypervisor (multi-queue mode)\n",
+ adapter->num_rx_queues);
+
+ return 0;
+
+err_unregister:
+ ibmveth_dispose_subordinate_irq_mappings(adapter);
+ ibmveth_free_all_queues(adapter);
+ return rc;
+}
+
static int ibmveth_open(struct net_device *netdev)
{
struct ibmveth_adapter *adapter = netdev_priv(netdev);
--
2.39.3 (Apple Git-146)
^ permalink raw reply related
* [PATCH v1 09/18] ibmveth: Refactor open/close into MQ-ready resource pipeline
From: Mingming Cao @ 2026-06-30 14:53 UTC (permalink / raw)
To: netdev
Cc: horms, bjking1, haren, ricklind, mmc, kuba, edumazet, pabeni,
linuxppc-dev, maddy, mpe, Dave Marquardt
In-Reply-To: <cover.1782758799.git.mmc@linux.ibm.com>
Patches 4-8 added alloc/free helpers for RX rings, buffer pools, IRQs,
TX LTBs, and PHYP registration, but open() and close() still duplicated
most of that logic inline. This patch wires the helpers in and makes
open/close the readable bring-up/teardown sequence MQ will extend.
ibmveth_open() runs:
1. ibmveth_alloc_rx_qstats()
2. ibmveth_alloc_filter_list()
3. ibmveth_alloc_rx_queues() - buffer lists + RX rings [0, N)
4. ibmveth_alloc_buffer_pools() - guest RX memory before PHYP
5. ibmveth_register_rx_queues() - PHYP registration (no IRQ enable)
6. netif_set_real_num_rx_queues()
7. ibmveth_setup_rx_interrupts() - request_irq, PHYP enable on MQ
8. initial replenish - queue 0 only today
9. ibmveth_alloc_tx_resources()
Each step has a matching out_* label on failure so unwind walks back
through free_all_queues(), cleanup_rx_resources(), and the other helpers
instead of open() carrying its own DMA unmap/free_page/goto maze (~200
lines removed).
ibmveth_close() mirrors that in reverse: stop TX, disable hypervisor IRQs
per queue, free TX LTBs, tear down NAPI/IRQ handlers, drop buffer pools,
H_FREE_LOGICAL_LAN via ibmveth_free_all_queues(), then free
RX/filter/qstats memory.
request_irq() now passes &napi[i] as dev_id on every queue so the
interrupt and poll paths can derive the queue index from the napi pointer
(napi - adapter->napi).
Drop __maybe_unused from the helpers added in patches 4-8 — they are
called from open/close from this patch onward.
Runtime still single-queue until the MQ enable commit later in the series;
replenish still kicks off via ibmveth_interrupt() on queue 0 as before.
Signed-off-by: Mingming Cao <mmc@linux.ibm.com>
Reviewed-by: Dave Marquardt <davemarq@linux.ibm.com>
---
drivers/net/ethernet/ibm/ibmveth.c | 351 +++++++++++------------------
1 file changed, 137 insertions(+), 214 deletions(-)
diff --git a/drivers/net/ethernet/ibm/ibmveth.c b/drivers/net/ethernet/ibm/ibmveth.c
index 7fc11a4e1f61..fa2d4777ffc7 100644
--- a/drivers/net/ethernet/ibm/ibmveth.c
+++ b/drivers/net/ethernet/ibm/ibmveth.c
@@ -155,7 +155,7 @@ static unsigned int ibmveth_real_max_tx_queues(void)
*
* Return: 0 on success, negative error code on failure
*/
-static int __maybe_unused ibmveth_alloc_filter_list(struct ibmveth_adapter *adapter)
+static int ibmveth_alloc_filter_list(struct ibmveth_adapter *adapter)
{
struct device *dev = &adapter->vdev->dev;
struct net_device *netdev = adapter->netdev;
@@ -187,7 +187,7 @@ static int __maybe_unused ibmveth_alloc_filter_list(struct ibmveth_adapter *adap
* ibmveth_free_filter_list - Free filter list resources
* @adapter: ibmveth adapter structure
*/
-static void __maybe_unused ibmveth_free_filter_list(struct ibmveth_adapter *adapter)
+static void ibmveth_free_filter_list(struct ibmveth_adapter *adapter)
{
struct device *dev = &adapter->vdev->dev;
@@ -203,6 +203,33 @@ static void __maybe_unused ibmveth_free_filter_list(struct ibmveth_adapter *adap
}
}
+/**
+ * ibmveth_alloc_rx_qstats - Allocate per-queue RX statistics
+ * @adapter: ibmveth adapter structure
+ *
+ * Return: 0 on success, -ENOMEM on failure
+ */
+static int ibmveth_alloc_rx_qstats(struct ibmveth_adapter *adapter)
+{
+ adapter->rx_qstats = kcalloc(IBMVETH_MAX_RX_QUEUES,
+ sizeof(struct ibmveth_rx_queue_stats),
+ GFP_KERNEL);
+ if (!adapter->rx_qstats)
+ return -ENOMEM;
+
+ return 0;
+}
+
+/**
+ * ibmveth_free_rx_qstats - Free per-queue RX statistics
+ * @adapter: ibmveth adapter structure
+ */
+static void ibmveth_free_rx_qstats(struct ibmveth_adapter *adapter)
+{
+ kfree(adapter->rx_qstats);
+ adapter->rx_qstats = NULL;
+}
+
/**
* ibmveth_alloc_rx_queues - Allocate per-queue RX resources
* @adapter: ibmveth adapter structure
@@ -210,7 +237,7 @@ static void __maybe_unused ibmveth_free_filter_list(struct ibmveth_adapter *adap
*
* Return: 0 on success, negative error code on failure
*/
-static int __maybe_unused
+static int
ibmveth_alloc_rx_queues(struct ibmveth_adapter *adapter, int rxq_entries)
{
struct device *dev = &adapter->vdev->dev;
@@ -288,7 +315,7 @@ ibmveth_alloc_rx_queues(struct ibmveth_adapter *adapter, int rxq_entries)
* ibmveth_cleanup_rx_resources - Free all RX queue resources
* @adapter: ibmveth adapter structure
*/
-static void __maybe_unused ibmveth_cleanup_rx_resources(struct ibmveth_adapter *adapter)
+static void ibmveth_cleanup_rx_resources(struct ibmveth_adapter *adapter)
{
struct device *dev = &adapter->vdev->dev;
int i;
@@ -424,21 +451,22 @@ ibmveth_dispose_subordinate_irq_mappings(struct ibmveth_adapter *adapter)
}
/**
- * ibmveth_setup_rx_interrupts - Register IRQs and enable NAPI
+ * ibmveth_setup_rx_interrupts - Register IRQ handlers and enable NAPI
* @adapter: ibmveth adapter structure
*
* Registers interrupt handlers for all RX queues and enables NAPI polling.
- * On error, cleans up any successfully registered IRQs before returning.
+ * For multi-queue mode, enables hypervisor interrupt delivery only after
+ * every queue has a Linux handler installed.
*
* Return: 0 on success, negative error code on failure
*/
-static int __maybe_unused
+static int
ibmveth_setup_rx_interrupts(struct ibmveth_adapter *adapter)
{
struct net_device *netdev = adapter->netdev;
- int i, rc;
+ int i, rc, num = adapter->num_rx_queues;
- for (i = 0; i < adapter->num_rx_queues; i++) {
+ for (i = 0; i < num; i++) {
if (!adapter->queue_irq[i]) {
netdev_err(netdev, "queue %d has invalid IRQ (0)\n", i);
rc = -EINVAL;
@@ -455,14 +483,34 @@ ibmveth_setup_rx_interrupts(struct ibmveth_adapter *adapter)
}
}
- for (i = 0; i < adapter->num_rx_queues; i++)
+ for (i = 0; i < num; i++)
napi_enable(&adapter->napi[i]);
+ if (adapter->multi_queue && num > 1) {
+ for (i = 0; i < num; i++) {
+ rc = ibmveth_enable_irq(adapter, i);
+ if (rc) {
+ netdev_err(netdev,
+ "Failed to enable IRQ for queue %d, rc=%d\n",
+ i, rc);
+ while (--i >= 0)
+ ibmveth_disable_irq(adapter, i);
+ rc = -EIO;
+ goto err_disable_napi;
+ }
+ }
+ }
+
return 0;
+err_disable_napi:
+ for (i = 0; i < num; i++)
+ napi_disable(&adapter->napi[i]);
+ i = num;
err_free_irqs:
while (--i >= 0)
free_irq(adapter->queue_irq[i], &adapter->napi[i]);
+ ibmveth_dispose_subordinate_irq_mappings(adapter);
return rc;
}
@@ -485,15 +533,7 @@ ibmveth_cleanup_rx_interrupts(struct ibmveth_adapter *adapter)
free_irq(adapter->queue_irq[i], &adapter->napi[i]);
}
- /* Dispose IRQ mappings for subordinate queues (1-15).
- * Queue 0 uses netdev->irq from device tree, not irq_create_mapping().
- */
- for (i = 1; i < adapter->num_rx_queues; i++) {
- if (adapter->queue_irq[i]) {
- irq_dispose_mapping(adapter->queue_irq[i]);
- adapter->queue_irq[i] = 0;
- }
- }
+ ibmveth_dispose_subordinate_irq_mappings(adapter);
/* Clear queue 0 IRQ number */
adapter->queue_irq[0] = 0;
@@ -869,7 +909,7 @@ static void ibmveth_free_queue_buffer_pools(struct ibmveth_adapter *adapter,
*
* Return: 0 on success, negative error code on failure
*/
-static int __maybe_unused ibmveth_alloc_buffer_pools(struct ibmveth_adapter *adapter)
+static int ibmveth_alloc_buffer_pools(struct ibmveth_adapter *adapter)
{
struct net_device *netdev = adapter->netdev;
int i, q, rc;
@@ -910,7 +950,7 @@ static int __maybe_unused ibmveth_alloc_buffer_pools(struct ibmveth_adapter *ada
*
* Frees buffer pools for all queues using the helper function.
*/
-static void __maybe_unused ibmveth_free_buffer_pools(struct ibmveth_adapter *adapter)
+static void ibmveth_free_buffer_pools(struct ibmveth_adapter *adapter)
{
int q;
@@ -1070,7 +1110,7 @@ static int ibmveth_allocate_tx_ltb(struct ibmveth_adapter *adapter, int idx)
*
* Return: 0 on success, -ENOMEM on failure
*/
-static int __maybe_unused
+static int
ibmveth_alloc_tx_resources(struct ibmveth_adapter *adapter)
{
struct net_device *netdev = adapter->netdev;
@@ -1095,7 +1135,7 @@ ibmveth_alloc_tx_resources(struct ibmveth_adapter *adapter)
*
* Frees TX Long Term Buffers (LTBs) for all TX queues.
*/
-static void __maybe_unused
+static void
ibmveth_free_tx_resources(struct ibmveth_adapter *adapter)
{
struct net_device *netdev = adapter->netdev;
@@ -1149,33 +1189,6 @@ static int ibmveth_register_logical_lan(struct ibmveth_adapter *adapter,
return rc;
}
-/**
- * ibmveth_alloc_rx_qstats - Allocate per-queue RX statistics
- * @adapter: ibmveth adapter structure
- *
- * Return: 0 on success, -ENOMEM on failure
- */
-static int __maybe_unused ibmveth_alloc_rx_qstats(struct ibmveth_adapter *adapter)
-{
- adapter->rx_qstats = kcalloc(IBMVETH_MAX_RX_QUEUES,
- sizeof(struct ibmveth_rx_queue_stats),
- GFP_KERNEL);
- if (!adapter->rx_qstats)
- return -ENOMEM;
-
- return 0;
-}
-
-/**
- * ibmveth_free_rx_qstats - Free per-queue RX statistics
- * @adapter: ibmveth adapter structure
- */
-static void __maybe_unused ibmveth_free_rx_qstats(struct ibmveth_adapter *adapter)
-{
- kfree(adapter->rx_qstats);
- adapter->rx_qstats = NULL;
-}
-
/**
* ibmveth_register_logical_lan_queue - Register subordinate queue with hypervisor
* @adapter: ibmveth adapter structure
@@ -1466,208 +1479,108 @@ ibmveth_register_rx_queues(struct ibmveth_adapter *adapter, u64 mac_address)
static int ibmveth_open(struct net_device *netdev)
{
struct ibmveth_adapter *adapter = netdev_priv(netdev);
- u64 mac_address;
+ u64 mac_address = ether_addr_to_u64(netdev->dev_addr);
int rxq_entries = 1;
- unsigned long lpar_rc;
int rc;
- union ibmveth_buf_desc rxq_desc;
int i;
- struct device *dev;
netdev_dbg(netdev, "open starting\n");
- napi_enable(&adapter->napi[0]);
-
- for(i = 0; i < IBMVETH_NUM_BUFF_POOLS; i++)
+ for (i = 0; i < IBMVETH_NUM_BUFF_POOLS; i++)
rxq_entries += adapter->rx_buff_pool[0][i].size;
- rc = -ENOMEM;
- adapter->buffer_list_addr[0] = (void *)get_zeroed_page(GFP_KERNEL);
- if (!adapter->buffer_list_addr[0]) {
- netdev_err(netdev, "unable to allocate list pages\n");
+ rc = ibmveth_alloc_rx_qstats(adapter);
+ if (rc)
goto out;
- }
- adapter->filter_list_addr = (void*) get_zeroed_page(GFP_KERNEL);
- if (!adapter->filter_list_addr) {
- netdev_err(netdev, "unable to allocate filter pages\n");
- goto out_free_buffer_list;
- }
-
- dev = &adapter->vdev->dev;
+ rc = ibmveth_alloc_filter_list(adapter);
+ if (rc)
+ goto out_free_rx_qstats;
- adapter->rx_queue[0].queue_len = sizeof(struct ibmveth_rx_q_entry) *
- rxq_entries;
- adapter->rx_queue[0].queue_addr =
- dma_alloc_coherent(dev, adapter->rx_queue[0].queue_len,
- &adapter->rx_queue[0].queue_dma, GFP_KERNEL);
- if (!adapter->rx_queue[0].queue_addr)
+ rc = ibmveth_alloc_rx_queues(adapter, rxq_entries);
+ if (rc)
goto out_free_filter_list;
- adapter->buffer_list_dma[0] = dma_map_single(dev,
- adapter->buffer_list_addr[0],
- 4096, DMA_BIDIRECTIONAL);
- if (dma_mapping_error(dev, adapter->buffer_list_dma[0])) {
- netdev_err(netdev, "unable to map buffer list pages\n");
+ rc = ibmveth_alloc_buffer_pools(adapter);
+ if (rc)
goto out_free_queue_mem;
- }
- adapter->filter_list_dma = dma_map_single(dev,
- adapter->filter_list_addr, 4096, DMA_BIDIRECTIONAL);
- if (dma_mapping_error(dev, adapter->filter_list_dma)) {
- netdev_err(netdev, "unable to map filter list pages\n");
- goto out_unmap_buffer_list;
- }
+ rc = ibmveth_register_rx_queues(adapter, mac_address);
+ if (rc)
+ goto out_free_buffer_pools;
- for (i = 0; i < netdev->real_num_tx_queues; i++) {
- if (ibmveth_allocate_tx_ltb(adapter, i))
- goto out_free_tx_ltb;
+ rc = netif_set_real_num_rx_queues(netdev, adapter->num_rx_queues);
+ if (rc) {
+ netdev_err(netdev, "failed to set number of rx queues\n");
+ goto out_unregister_queues;
}
- adapter->rx_queue[0].index = 0;
- adapter->rx_queue[0].num_slots = rxq_entries;
- adapter->rx_queue[0].toggle = 1;
-
- mac_address = ether_addr_to_u64(netdev->dev_addr);
-
- rxq_desc.fields.flags_len = IBMVETH_BUF_VALID |
- adapter->rx_queue[0].queue_len;
- rxq_desc.fields.address = adapter->rx_queue[0].queue_dma;
-
- netdev_dbg(netdev, "buffer list @ 0x%p\n", adapter->buffer_list_addr[0]);
- netdev_dbg(netdev, "filter list @ 0x%p\n", adapter->filter_list_addr);
- netdev_dbg(netdev, "receive q @ 0x%p\n", adapter->rx_queue[0].queue_addr);
-
- h_vio_signal(adapter->vdev->unit_address, VIO_IRQ_DISABLE);
-
- lpar_rc = ibmveth_register_logical_lan(adapter, rxq_desc, mac_address);
-
- if (lpar_rc != H_SUCCESS) {
- netdev_err(netdev, "h_register_logical_lan failed with %ld\n",
- lpar_rc);
- netdev_err(netdev, "buffer TCE:0x%llx filter TCE:0x%llx rxq "
- "desc:0x%llx MAC:0x%llx\n",
- adapter->buffer_list_dma[0],
- adapter->filter_list_dma,
- rxq_desc.desc,
- mac_address);
- rc = -ENONET;
- goto out_unmap_filter_list;
- }
+ rc = ibmveth_setup_rx_interrupts(adapter);
+ if (rc)
+ goto out_unregister_queues;
- for (i = 0; i < IBMVETH_NUM_BUFF_POOLS; i++) {
- if (!adapter->rx_buff_pool[0][i].active)
- continue;
- if (ibmveth_alloc_buffer_pool(&adapter->rx_buff_pool[0][i])) {
- netdev_err(netdev, "unable to alloc pool\n");
- adapter->rx_buff_pool[0][i].active = 0;
- rc = -ENOMEM;
- goto out_free_buffer_pools;
+ if (adapter->num_rx_queues > 1) {
+ for (i = 0; i < adapter->num_rx_queues; i++) {
+ netdev_dbg(netdev, "initial replenish cycle for queue %d\n", i);
+ ibmveth_replenish_task(adapter, i);
}
+ } else {
+ netdev_dbg(netdev, "initial replenish cycle\n");
+ ibmveth_interrupt(adapter->queue_irq[0], &adapter->napi[0]);
}
- netdev_dbg(netdev, "registering irq 0x%x\n", netdev->irq);
- rc = request_irq(netdev->irq, ibmveth_interrupt, 0, netdev->name,
- netdev);
- if (rc != 0) {
- netdev_err(netdev, "unable to request irq 0x%x, rc %d\n",
- netdev->irq, rc);
- do {
- lpar_rc = h_free_logical_lan(adapter->vdev->unit_address);
- } while (H_IS_LONG_BUSY(lpar_rc) || (lpar_rc == H_BUSY));
-
- goto out_free_buffer_pools;
- }
-
- rc = -ENOMEM;
-
- netdev_dbg(netdev, "initial replenish cycle\n");
- ibmveth_interrupt(netdev->irq, netdev);
+ rc = ibmveth_alloc_tx_resources(adapter);
+ if (rc)
+ goto out_cleanup_rx_interrupts;
netif_tx_start_all_queues(netdev);
netdev_dbg(netdev, "open complete\n");
-
return 0;
+out_cleanup_rx_interrupts:
+ ibmveth_cleanup_rx_interrupts(adapter);
+out_free_tx_resources:
+ ibmveth_free_tx_resources(adapter);
out_free_buffer_pools:
- while (--i >= 0) {
- if (adapter->rx_buff_pool[0][i].active)
- ibmveth_free_buffer_pool(adapter,
- &adapter->rx_buff_pool[0][i]);
- }
-out_unmap_filter_list:
- dma_unmap_single(dev, adapter->filter_list_dma, 4096,
- DMA_BIDIRECTIONAL);
-
-out_free_tx_ltb:
- while (--i >= 0) {
- ibmveth_free_tx_ltb(adapter, i);
- }
-
-out_unmap_buffer_list:
- dma_unmap_single(dev, adapter->buffer_list_dma[0], 4096,
- DMA_BIDIRECTIONAL);
+ ibmveth_free_buffer_pools(adapter);
+out_unregister_queues:
+ ibmveth_dispose_subordinate_irq_mappings(adapter);
+ ibmveth_free_all_queues(adapter);
out_free_queue_mem:
- dma_free_coherent(dev, adapter->rx_queue[0].queue_len,
- adapter->rx_queue[0].queue_addr,
- adapter->rx_queue[0].queue_dma);
+ ibmveth_cleanup_rx_resources(adapter);
out_free_filter_list:
- free_page((unsigned long)adapter->filter_list_addr);
-out_free_buffer_list:
- free_page((unsigned long)adapter->buffer_list_addr[0]);
+ ibmveth_free_filter_list(adapter);
+out_free_rx_qstats:
+ ibmveth_free_rx_qstats(adapter);
out:
- napi_disable(&adapter->napi[0]);
return rc;
}
static int ibmveth_close(struct net_device *netdev)
{
struct ibmveth_adapter *adapter = netdev_priv(netdev);
- struct device *dev = &adapter->vdev->dev;
- long lpar_rc;
int i;
netdev_dbg(netdev, "close starting\n");
- napi_disable(&adapter->napi[0]);
-
netif_tx_stop_all_queues(netdev);
- h_vio_signal(adapter->vdev->unit_address, VIO_IRQ_DISABLE);
-
- do {
- lpar_rc = h_free_logical_lan(adapter->vdev->unit_address);
- } while (H_IS_LONG_BUSY(lpar_rc) || (lpar_rc == H_BUSY));
-
- if (lpar_rc != H_SUCCESS) {
- netdev_err(netdev, "h_free_logical_lan failed with %lx, "
- "continuing with close\n", lpar_rc);
+ for (i = 0; i < adapter->num_rx_queues; i++) {
+ if (adapter->queue_irq[i]) {
+ ibmveth_disable_irq(adapter, i);
+ synchronize_irq(adapter->queue_irq[i]);
+ }
}
- free_irq(netdev->irq, netdev);
-
+ ibmveth_free_tx_resources(adapter);
+ ibmveth_cleanup_rx_interrupts(adapter);
ibmveth_update_rx_no_buffer(adapter);
-
- dma_unmap_single(dev, adapter->buffer_list_dma[0], 4096,
- DMA_BIDIRECTIONAL);
- free_page((unsigned long)adapter->buffer_list_addr[0]);
-
- dma_unmap_single(dev, adapter->filter_list_dma, 4096,
- DMA_BIDIRECTIONAL);
- free_page((unsigned long)adapter->filter_list_addr);
-
- dma_free_coherent(dev, adapter->rx_queue[0].queue_len,
- adapter->rx_queue[0].queue_addr,
- adapter->rx_queue[0].queue_dma);
-
- for (i = 0; i < IBMVETH_NUM_BUFF_POOLS; i++)
- if (adapter->rx_buff_pool[0][i].active)
- ibmveth_free_buffer_pool(adapter,
- &adapter->rx_buff_pool[0][i]);
-
- for (i = 0; i < netdev->real_num_tx_queues; i++)
- ibmveth_free_tx_ltb(adapter, i);
+ ibmveth_free_all_queues(adapter);
+ ibmveth_free_buffer_pools(adapter);
+ ibmveth_cleanup_rx_resources(adapter);
+ ibmveth_free_filter_list(adapter);
+ ibmveth_free_rx_qstats(adapter);
netdev_dbg(netdev, "close complete\n");
@@ -2423,15 +2336,21 @@ static int ibmveth_poll(struct napi_struct *napi, int budget)
static irqreturn_t ibmveth_interrupt(int irq, void *dev_instance)
{
- struct net_device *netdev = dev_instance;
+ struct napi_struct *napi = dev_instance;
+ struct net_device *netdev = napi->dev;
struct ibmveth_adapter *adapter = netdev_priv(netdev);
unsigned long lpar_rc;
+ int qindex;
- if (napi_schedule_prep(&adapter->napi[0])) {
- lpar_rc = h_vio_signal(adapter->vdev->unit_address,
- VIO_IRQ_DISABLE);
+ qindex = napi - adapter->napi;
+
+ if (WARN_ON(qindex < 0 || qindex >= adapter->num_rx_queues))
+ return IRQ_NONE;
+
+ if (napi_schedule_prep(napi)) {
+ lpar_rc = ibmveth_disable_irq(adapter, qindex);
WARN_ON(lpar_rc != H_SUCCESS);
- __napi_schedule(&adapter->napi[0]);
+ __napi_schedule(napi);
}
return IRQ_HANDLED;
}
@@ -2537,8 +2456,10 @@ static int ibmveth_change_mtu(struct net_device *dev, int new_mtu)
#ifdef CONFIG_NET_POLL_CONTROLLER
static void ibmveth_poll_controller(struct net_device *dev)
{
- ibmveth_replenish_task(netdev_priv(dev));
- ibmveth_interrupt(dev->irq, dev);
+ struct ibmveth_adapter *adapter = netdev_priv(dev);
+
+ ibmveth_replenish_task(adapter);
+ ibmveth_interrupt(dev->irq, &adapter->napi[0]);
}
#endif
@@ -2951,7 +2872,7 @@ static ssize_t veth_pool_store(struct kobject *kobj, struct attribute *attr,
rtnl_unlock();
/* kick the interrupt handler to allocate/deallocate pools */
- ibmveth_interrupt(netdev->irq, netdev);
+ ibmveth_interrupt(netdev->irq, &adapter->napi[0]);
return count;
unlock_err:
@@ -2991,7 +2912,9 @@ static struct kobj_type ktype_veth_pool = {
static int ibmveth_resume(struct device *dev)
{
struct net_device *netdev = dev_get_drvdata(dev);
- ibmveth_interrupt(netdev->irq, netdev);
+ struct ibmveth_adapter *adapter = netdev_priv(netdev);
+
+ ibmveth_interrupt(netdev->irq, &adapter->napi[0]);
return 0;
}
--
2.39.3 (Apple Git-146)
^ permalink raw reply related
* [PATCH v1 10/18] ibmveth: Add queue-aware RX buffer submit helper for MQ
From: Mingming Cao @ 2026-06-30 14:53 UTC (permalink / raw)
To: netdev
Cc: horms, bjking1, haren, ricklind, mmc, kuba, edumazet, pabeni,
linuxppc-dev, maddy, mpe, Dave Marquardt
In-Reply-To: <cover.1782758799.git.mmc@linux.ibm.com>
Replenish is the last open-path hypervisor call that still needs
per-queue awareness before MQ receive is enabled. Today
ibmveth_replenish_buffer_pool() calls h_add_logical_lan_buffer() or
h_add_logical_lan_buffers() directly; MQ posts via
H_ADD_LOGICAL_LAN_BUFFERS_QUEUE against adapter->queue_handle[].
Add ibmveth_add_logical_lan_buffers() to pick the hcall:
multi_queue uses h_add_logical_lan_buffers_queue() (up to 12 buffers,
IOBAs packed with odd counts in the upper 32 bits); legacy uses the
existing single- and multi-buffer hcalls. Count add_buf/add_bufs/
add_bufs_queue in hcall_stats.
Thread queue_index through replenish_task() and replenish_buffer_pool()
so they index rx_buff_pool[queue_index][pool]. All callers still pass
queue 0; legacy hcalls remain the live path until MQ probe enables
multi_queue.
Also split H_FUNCTION handling: legacy batch falls back to single-buffer
mode; multi_queue logs an error on unsupported firmware.
Signed-off-by: Mingming Cao <mmc@linux.ibm.com>
Reviewed-by: Dave Marquardt <davemarq@linux.ibm.com>
---
drivers/net/ethernet/ibm/ibmveth.c | 134 ++++++++++++++++++++---------
1 file changed, 94 insertions(+), 40 deletions(-)
diff --git a/drivers/net/ethernet/ibm/ibmveth.c b/drivers/net/ethernet/ibm/ibmveth.c
index fa2d4777ffc7..b3b3886c3eed 100644
--- a/drivers/net/ethernet/ibm/ibmveth.c
+++ b/drivers/net/ethernet/ibm/ibmveth.c
@@ -597,11 +597,73 @@ static inline void ibmveth_flush_buffer(void *addr, unsigned long length)
asm("dcbf %0,%1,1" :: "b" (addr), "r" (offset));
}
+/**
+ * ibmveth_add_logical_lan_buffers - Add receive buffers to hypervisor
+ * @adapter: ibmveth adapter structure
+ * @descs: array of buffer descriptors to add
+ * @filled: number of valid descriptors in the array
+ * @buff_size: size of each buffer (multi-queue mode only)
+ * @queue_index: RX queue index
+ *
+ * Return: hypervisor return code
+ */
+static long ibmveth_add_logical_lan_buffers(struct ibmveth_adapter *adapter,
+ union ibmveth_buf_desc *descs,
+ int filled,
+ unsigned long buff_size,
+ int queue_index)
+{
+ struct vio_dev *vdev = adapter->vdev;
+ unsigned long rc;
+
+ if (adapter->multi_queue) {
+ unsigned long buffersznum = (buff_size << 32) | filled;
+ unsigned long ioba[IBMVETH_MAX_RX_PER_HCALL / 2] = {0};
+ int i;
+
+ /* Pack descriptor addresses into ioba pairs.
+ * Each ioba holds two 32-bit addresses packed into 64 bits:
+ * - Even descriptors (0,2,4...) go in high 32 bits
+ * - Odd descriptors (1,3,5...) go in low 32 bits
+ */
+ for (i = 0; i < filled && i < IBMVETH_MAX_RX_PER_HCALL; i++) {
+ int pair_idx = i / 2; /* Which pair: 0-5 */
+ int is_high = (i % 2 == 0); /* High or low 32 bits */
+
+ if (is_high)
+ ioba[pair_idx] = (unsigned long)descs[i].fields.address << 32;
+ else
+ ioba[pair_idx] |= descs[i].fields.address;
+ }
+
+ rc = h_add_logical_lan_buffers_queue(vdev->unit_address,
+ adapter->queue_handle[queue_index],
+ buffersznum,
+ ioba[0], ioba[1], ioba[2],
+ ioba[3], ioba[4], ioba[5]);
+ adapter->hcall_stats.add_bufs_queue++;
+ } else if (filled == 1) {
+ rc = h_add_logical_lan_buffer(vdev->unit_address,
+ descs[0].desc);
+ adapter->hcall_stats.add_buf++;
+ } else {
+ rc = h_add_logical_lan_buffers(vdev->unit_address,
+ descs[0].desc, descs[1].desc,
+ descs[2].desc, descs[3].desc,
+ descs[4].desc, descs[5].desc,
+ descs[6].desc, descs[7].desc);
+ adapter->hcall_stats.add_bufs++;
+ }
+
+ return rc;
+}
+
/* replenish the buffers for a pool. note that we don't need to
* skb_reserve these since they are used for incoming...
*/
static void ibmveth_replenish_buffer_pool(struct ibmveth_adapter *adapter,
- struct ibmveth_buff_pool *pool)
+ struct ibmveth_buff_pool *pool,
+ int queue_index)
{
union ibmveth_buf_desc descs[IBMVETH_MAX_RX_PER_HCALL] = {0};
u32 remaining = pool->size - atomic_read(&pool->available);
@@ -687,24 +749,15 @@ static void ibmveth_replenish_buffer_pool(struct ibmveth_adapter *adapter,
if (!filled)
break;
- /* single buffer case*/
- if (filled == 1)
- lpar_rc = h_add_logical_lan_buffer(vdev->unit_address,
- descs[0].desc);
- else
- /* Multi-buffer hcall */
- lpar_rc = h_add_logical_lan_buffers(vdev->unit_address,
- descs[0].desc,
- descs[1].desc,
- descs[2].desc,
- descs[3].desc,
- descs[4].desc,
- descs[5].desc,
- descs[6].desc,
- descs[7].desc);
+ lpar_rc = ibmveth_add_logical_lan_buffers(adapter, descs,
+ filled,
+ pool->buff_size,
+ queue_index);
+
if (lpar_rc != H_SUCCESS) {
dev_warn_ratelimited(dev,
- "RX h_add_logical_lan failed: filled=%u, rc=%lu, batch=%u\n",
+ "RX h_add_logical_lan %s failed: filled=%u, rc=%lu, batch=%u\n",
+ adapter->multi_queue ? "_queue" : "",
filled, lpar_rc, batch);
goto hcall_failure;
}
@@ -745,24 +798,19 @@ static void ibmveth_replenish_buffer_pool(struct ibmveth_adapter *adapter,
}
adapter->replenish_add_buff_failure += filled;
- /*
- * If multi rx buffers hcall is no longer supported by FW
- * e.g. in the case of Live Partition Migration
- */
- if (batch > 1 && lpar_rc == H_FUNCTION) {
- /*
- * Instead of retry submit single buffer individually
- * here just set the max rx buffer per hcall to 1
- * buffers will be respleshed next time
- * when ibmveth_replenish_buffer_pool() is called again
- * with single-buffer case
- */
- netdev_info(adapter->netdev,
- "RX Multi buffers not supported by FW, rc=%lu\n",
- lpar_rc);
- adapter->rx_buffers_per_hcall = 1;
- netdev_info(adapter->netdev,
- "Next rx replesh will fall back to single-buffer hcall\n");
+ if (lpar_rc == H_FUNCTION) {
+ if (adapter->multi_queue) {
+ netdev_err(adapter->netdev,
+ "Unexpected H_FUNCTION from multi-queue buffer add (queue=%d, batch=%d)\n",
+ queue_index, batch);
+ break;
+ } else if (batch > 1) {
+ netdev_warn(adapter->netdev,
+ "H_FUNCTION from legacy batch buffer add (batch=%d), falling back to single buffer mode\n",
+ batch);
+ adapter->rx_buffers_per_hcall = 1;
+ continue;
+ }
}
break;
}
@@ -784,18 +832,24 @@ static void ibmveth_update_rx_no_buffer(struct ibmveth_adapter *adapter)
}
/* replenish routine */
-static void ibmveth_replenish_task(struct ibmveth_adapter *adapter)
+static void ibmveth_replenish_task(struct ibmveth_adapter *adapter,
+ int queue_index)
{
int i;
+ if (queue_index >= adapter->num_rx_queues)
+ return;
+
adapter->replenish_task_cycles++;
for (i = (IBMVETH_NUM_BUFF_POOLS - 1); i >= 0; i--) {
- struct ibmveth_buff_pool *pool = &adapter->rx_buff_pool[0][i];
+ struct ibmveth_buff_pool *pool =
+ &adapter->rx_buff_pool[queue_index][i];
if (pool->active &&
(atomic_read(&pool->available) < pool->threshold))
- ibmveth_replenish_buffer_pool(adapter, pool);
+ ibmveth_replenish_buffer_pool(adapter, pool,
+ queue_index);
}
ibmveth_update_rx_no_buffer(adapter);
@@ -2307,7 +2361,7 @@ static int ibmveth_poll(struct napi_struct *napi, int budget)
}
}
- ibmveth_replenish_task(adapter);
+ ibmveth_replenish_task(adapter, 0);
if (frames_processed == budget)
goto out;
@@ -2458,7 +2512,7 @@ static void ibmveth_poll_controller(struct net_device *dev)
{
struct ibmveth_adapter *adapter = netdev_priv(dev);
- ibmveth_replenish_task(adapter);
+ ibmveth_replenish_task(adapter, 0);
ibmveth_interrupt(dev->irq, &adapter->napi[0]);
}
#endif
--
2.39.3 (Apple Git-146)
^ permalink raw reply related
* [PATCH v1 12/18] ibmveth: Add per-queue RX statistics collection and reporting
From: Mingming Cao @ 2026-06-30 14:53 UTC (permalink / raw)
To: netdev
Cc: horms, bjking1, haren, ricklind, mmc, kuba, edumazet, pabeni,
linuxppc-dev, maddy, mpe, Dave Marquardt
In-Reply-To: <cover.1782758799.git.mmc@linux.ibm.com>
Count per-queue RX stats in poll, replenish, and the IRQ handler:
packets, bytes, polls, large_packets, invalid_buffers, no_buffer_drops,
and interrupts. Stop updating netdev->stats.rx_* in poll; totals are
summed from rx_qstats[] in get_stats64(). Per-queue TX stats follow in
the next patch.
Expose the counters via:
- ethtool -S: per-queue rxN_* strings and aggregated invalid/large
packet globals via ibmveth_aggregate_rx_qstats(). pool%d_* reports
queue-0 pool geometry (size, active, available) only: static probe
config used as the template for every queue. Live per-queue pool
usage is exported through sysfs in the next patch.
- get_stats64: sum rx_qstats[] so ip -s and /proc/net/dev report total RX
- ethtool hcall_stats counters and count send_lan on successful TX hcalls
Fix get_channels() reporting: max_rx is IBMVETH_MAX_RX_QUEUES only when
MQ firmware is enabled, rx_count tracks adapter->num_rx_queues.
Signed-off-by: Mingming Cao <mmc@linux.ibm.com>
Reviewed-by: Dave Marquardt <davemarq@linux.ibm.com>
---
drivers/net/ethernet/ibm/ibmveth.c | 152 ++++++++++++++++++++++++++---
1 file changed, 141 insertions(+), 11 deletions(-)
diff --git a/drivers/net/ethernet/ibm/ibmveth.c b/drivers/net/ethernet/ibm/ibmveth.c
index 863e5c68b42c..1c08082ffbd6 100644
--- a/drivers/net/ethernet/ibm/ibmveth.c
+++ b/drivers/net/ethernet/ibm/ibmveth.c
@@ -98,7 +98,15 @@ static struct ibmveth_stat ibmveth_stats[] = {
{ "fw_enabled_ipv6_csum", IBMVETH_STAT_OFF(fw_ipv6_csum_support) },
{ "tx_large_packets", IBMVETH_STAT_OFF(tx_large_packets) },
{ "rx_large_packets", IBMVETH_STAT_OFF(rx_large_packets) },
- { "fw_enabled_large_send", IBMVETH_STAT_OFF(fw_large_send_support) }
+ { "fw_enabled_large_send", IBMVETH_STAT_OFF(fw_large_send_support) },
+ { "hcall_reg_lan_queue", IBMVETH_STAT_OFF(hcall_stats.reg_lan_queue) },
+ { "hcall_reg_lan", IBMVETH_STAT_OFF(hcall_stats.reg_lan) },
+ { "hcall_add_bufs_queue", IBMVETH_STAT_OFF(hcall_stats.add_bufs_queue) },
+ { "hcall_add_bufs", IBMVETH_STAT_OFF(hcall_stats.add_bufs) },
+ { "hcall_add_buf", IBMVETH_STAT_OFF(hcall_stats.add_buf) },
+ { "hcall_free_lan_queue", IBMVETH_STAT_OFF(hcall_stats.free_lan_queue) },
+ { "hcall_free_lan", IBMVETH_STAT_OFF(hcall_stats.free_lan) },
+ { "hcall_send_lan", IBMVETH_STAT_OFF(hcall_stats.send_lan) },
};
/* simple methods of getting data from the current rxq entry */
@@ -847,6 +855,8 @@ static void ibmveth_update_rx_no_buffer(struct ibmveth_adapter *adapter)
__be64 *p = adapter->buffer_list_addr[i] + 4096 - 8;
u64 drops = be64_to_cpup(p);
+ if (adapter->rx_qstats)
+ adapter->rx_qstats[i].no_buffer_drops = drops;
if (i == 0)
adapter->rx_no_buffer = drops;
}
@@ -1925,22 +1935,71 @@ static int ibmveth_set_features(struct net_device *dev,
return rc1 ? rc1 : rc2;
}
+/**
+ * ibmveth_aggregate_rx_qstats - Sum per-queue RX stats into globals
+ * @adapter: ibmveth adapter
+ *
+ * Cold path only (ethtool). Keeps legacy global counters meaningful for
+ * tools that read the adapter-level fields in ibmveth_stats[].
+ */
+static void ibmveth_aggregate_rx_qstats(struct ibmveth_adapter *adapter)
+{
+ u64 total_invalid = 0;
+ u64 total_large = 0;
+ int i;
+
+ if (!adapter->rx_qstats)
+ return;
+
+ for (i = 0; i < adapter->num_rx_queues; i++) {
+ total_invalid += adapter->rx_qstats[i].invalid_buffers;
+ total_large += adapter->rx_qstats[i].large_packets;
+ }
+
+ adapter->rx_invalid_buffer = total_invalid;
+ adapter->rx_large_packets = total_large;
+}
+
static void ibmveth_get_strings(struct net_device *dev, u32 stringset, u8 *data)
{
+ struct ibmveth_adapter *adapter = netdev_priv(dev);
+ u8 *p = data;
int i;
if (stringset != ETH_SS_STATS)
return;
- for (i = 0; i < ARRAY_SIZE(ibmveth_stats); i++, data += ETH_GSTRING_LEN)
- memcpy(data, ibmveth_stats[i].name, ETH_GSTRING_LEN);
+ for (i = 0; i < ARRAY_SIZE(ibmveth_stats); i++) {
+ memcpy(p, ibmveth_stats[i].name, ETH_GSTRING_LEN);
+ p += ETH_GSTRING_LEN;
+ }
+
+ for (i = 0; i < adapter->num_rx_queues; i++) {
+ ethtool_sprintf(&p, "rx%d_packets", i);
+ ethtool_sprintf(&p, "rx%d_bytes", i);
+ ethtool_sprintf(&p, "rx%d_interrupts", i);
+ ethtool_sprintf(&p, "rx%d_polls", i);
+ ethtool_sprintf(&p, "rx%d_large_packets", i);
+ ethtool_sprintf(&p, "rx%d_invalid_buffers", i);
+ ethtool_sprintf(&p, "rx%d_no_buffer_drops", i);
+ }
+
+ for (i = 0; i < IBMVETH_NUM_BUFF_POOLS; i++) {
+ ethtool_sprintf(&p, "pool%d_size", i);
+ ethtool_sprintf(&p, "pool%d_active", i);
+ ethtool_sprintf(&p, "pool%d_available", i);
+ }
}
static int ibmveth_get_sset_count(struct net_device *dev, int sset)
{
+ struct ibmveth_adapter *adapter = netdev_priv(dev);
+
switch (sset) {
case ETH_SS_STATS:
- return ARRAY_SIZE(ibmveth_stats);
+ return ARRAY_SIZE(ibmveth_stats) +
+ adapter->num_rx_queues * IBMVETH_NUM_RX_QSTATS +
+ IBMVETH_NUM_BUFF_POOLS * 3;
default:
return -EOPNOTSUPP;
}
@@ -1949,21 +2008,48 @@ static int ibmveth_get_sset_count(struct net_device *dev, int sset)
static void ibmveth_get_ethtool_stats(struct net_device *dev,
struct ethtool_stats *stats, u64 *data)
{
- int i;
struct ibmveth_adapter *adapter = netdev_priv(dev);
+ int i, j;
+
+ ibmveth_aggregate_rx_qstats(adapter);
for (i = 0; i < ARRAY_SIZE(ibmveth_stats); i++)
data[i] = IBMVETH_GET_STAT(adapter, ibmveth_stats[i].offset);
+
+ for (j = 0; j < adapter->num_rx_queues; j++) {
+ if (adapter->rx_qstats) {
+ data[i++] = adapter->rx_qstats[j].packets;
+ data[i++] = adapter->rx_qstats[j].bytes;
+ data[i++] = adapter->rx_qstats[j].interrupts;
+ data[i++] = adapter->rx_qstats[j].polls;
+ data[i++] = adapter->rx_qstats[j].large_packets;
+ data[i++] = adapter->rx_qstats[j].invalid_buffers;
+ data[i++] = adapter->rx_qstats[j].no_buffer_drops;
+ } else {
+ i += IBMVETH_NUM_RX_QSTATS;
+ }
+ }
+
+ for (j = 0; j < IBMVETH_NUM_BUFF_POOLS; j++) {
+ data[i++] = adapter->rx_buff_pool[0][j].size;
+ data[i++] = adapter->rx_buff_pool[0][j].active;
+ data[i++] = atomic_read(&adapter->rx_buff_pool[0][j].available);
+ }
}
static void ibmveth_get_channels(struct net_device *netdev,
struct ethtool_channels *channels)
{
+ struct ibmveth_adapter *adapter = netdev_priv(netdev);
+
channels->max_tx = ibmveth_real_max_tx_queues();
channels->tx_count = netdev->real_num_tx_queues;
- channels->max_rx = netdev->real_num_rx_queues;
- channels->rx_count = netdev->real_num_rx_queues;
+ if (adapter->multi_queue)
+ channels->max_rx = IBMVETH_MAX_RX_QUEUES;
+ else
+ channels->max_rx = 1;
+ channels->rx_count = adapter->num_rx_queues;
}
static int ibmveth_set_channels(struct net_device *netdev,
@@ -2061,6 +2147,7 @@ static int ibmveth_send(struct ibmveth_adapter *adapter,
return 1;
}
+ adapter->hcall_stats.send_lan++;
return 0;
}
@@ -2311,6 +2398,9 @@ static int ibmveth_poll(struct napi_struct *napi, int budget)
if (WARN_ON(queue_index < 0 || queue_index >= adapter->num_rx_queues))
return 0;
+ if (adapter->rx_qstats)
+ adapter->rx_qstats[queue_index].polls++;
+
restart_poll:
while (frames_processed < budget) {
if (!ibmveth_rxq_pending_buffer(adapter, queue_index))
@@ -2319,7 +2409,10 @@ static int ibmveth_poll(struct napi_struct *napi, int budget)
smp_rmb();
if (!ibmveth_rxq_buffer_valid(adapter, queue_index)) {
wmb(); /* suggested by larson1 */
- adapter->rx_invalid_buffer++;
+ if (adapter->rx_qstats)
+ adapter->rx_qstats[queue_index].invalid_buffers++;
+ else
+ adapter->rx_invalid_buffer++;
netdev_dbg(netdev, "recycling invalid buffer\n");
rc = ibmveth_rxq_harvest_buffer(adapter, queue_index, true);
if (unlikely(rc))
@@ -2384,7 +2477,10 @@ static int ibmveth_poll(struct napi_struct *napi, int budget)
if ((length > netdev->mtu + ETH_HLEN) ||
lrg_pkt || iph_check == 0xffff) {
ibmveth_rx_mss_helper(skb, mss, lrg_pkt);
- adapter->rx_large_packets++;
+ if (adapter->rx_qstats)
+ adapter->rx_qstats[queue_index].large_packets++;
+ else
+ adapter->rx_large_packets++;
}
if (csum_good) {
@@ -2394,8 +2490,11 @@ static int ibmveth_poll(struct napi_struct *napi, int budget)
napi_gro_receive(napi, skb); /* send it up */
- netdev->stats.rx_packets++;
- netdev->stats.rx_bytes += length;
+ if (adapter->rx_qstats) {
+ adapter->rx_qstats[queue_index].packets++;
+ adapter->rx_qstats[queue_index].bytes += length;
+ }
+
frames_processed++;
}
}
@@ -2444,6 +2543,9 @@ static irqreturn_t ibmveth_interrupt(int irq, void *dev_instance)
if (WARN_ON(qindex < 0 || qindex >= adapter->num_rx_queues))
return IRQ_NONE;
+ if (adapter->rx_qstats)
+ adapter->rx_qstats[qindex].interrupts++;
+
if (napi_schedule_prep(napi)) {
lpar_rc = ibmveth_disable_irq(adapter, qindex);
WARN_ON(lpar_rc != H_SUCCESS);
@@ -2656,6 +2758,33 @@ static netdev_features_t ibmveth_features_check(struct sk_buff *skb,
return vlan_features_check(skb, features);
}
+/**
+ * ibmveth_get_stats64 - Return aggregated per-queue RX statistics
+ * @dev: network device
+ * @stats: rtnl link statistics storage
+ *
+ * Sums per-queue rx_qstats into rx_packets/rx_bytes for multi-queue mode.
+ * TX counters continue to come from netdev->stats (updated in start_xmit).
+ */
+static void ibmveth_get_stats64(struct net_device *dev,
+ struct rtnl_link_stats64 *stats)
+{
+ struct ibmveth_adapter *adapter = netdev_priv(dev);
+ int i;
+
+ if (adapter->rx_qstats) {
+ for (i = 0; i < adapter->num_rx_queues; i++) {
+ stats->rx_packets += adapter->rx_qstats[i].packets;
+ stats->rx_bytes += adapter->rx_qstats[i].bytes;
+ }
+ }
+
+ stats->tx_packets = dev->stats.tx_packets;
+ stats->tx_bytes = dev->stats.tx_bytes;
+ stats->tx_dropped = dev->stats.tx_dropped;
+ stats->tx_errors = dev->stats.tx_errors;
+}
+
static const struct net_device_ops ibmveth_netdev_ops = {
.ndo_open = ibmveth_open,
.ndo_stop = ibmveth_close,
@@ -2668,6 +2797,7 @@ static const struct net_device_ops ibmveth_netdev_ops = {
.ndo_validate_addr = eth_validate_addr,
.ndo_set_mac_address = ibmveth_set_mac_addr,
.ndo_features_check = ibmveth_features_check,
+ .ndo_get_stats64 = ibmveth_get_stats64,
#ifdef CONFIG_NET_POLL_CONTROLLER
.ndo_poll_controller = ibmveth_poll_controller,
#endif
--
2.39.3 (Apple Git-146)
^ 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