From: Sudeep Holla sudeep.holla@arm.com

[ Upstream commit c6e045361a27ecd4fac6413164e0d091d80eee99 ]

Commit bb1be7498500 ("firmware: arm_ffa: Add v1.1 get_partition_info support") adds support to discovery the UUIDs of the partitions or just fetch the partition count using the PARTITION_INFO_GET_RETURN_COUNT_ONLY flag.

However the commit doesn't handle the fact that the older version doesn't understand the flag and must be MBZ which results in firmware returning invalid parameter error. That results in the failure of the driver probe which is in correct.

Limit the usage of the PARTITION_INFO_GET_RETURN_COUNT_ONLY flag for the versions above v1.0(i.e v1.1 and onwards) which fixes the issue.

Fixes: bb1be7498500 ("firmware: arm_ffa: Add v1.1 get_partition_info support") Reported-by: Jens Wiklander jens.wiklander@linaro.org Reported-by: Marc Bonnici marc.bonnici@arm.com Tested-by: Jens Wiklander jens.wiklander@linaro.org Reviewed-by: Jens Wiklander jens.wiklander@linaro.org Link: https://lore.kernel.org/r/20230419-ffa_fixes_6-4-v2-2-d9108e43a176@arm.com Signed-off-by: Sudeep Holla sudeep.holla@arm.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/firmware/arm_ffa/driver.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/firmware/arm_ffa/driver.c b/drivers/firmware/arm_ffa/driver.c index 02774baa90078..e234091386671 100644 --- a/drivers/firmware/arm_ffa/driver.c +++ b/drivers/firmware/arm_ffa/driver.c @@ -193,7 +193,8 @@ __ffa_partition_info_get(u32 uuid0, u32 uuid1, u32 uuid2, u32 uuid3, int idx, count, flags = 0, sz, buf_sz; ffa_value_t partition_info;

- if (!buffer || !num_partitions) /* Just get the count for now */ + if (drv_info->version > FFA_VERSION_1_0 && + (!buffer || !num_partitions)) /* Just get the count for now */ flags = PARTITION_INFO_GET_RETURN_COUNT_ONLY;

mutex_lock(&drv_info->rx_lock);

From: Ruidong Tian tianruidong@linux.alibaba.com

[ Upstream commit 04ac7f98b92181179ea84439642493f3826d04a2 ]

Error handler for etm_setup_aux can not release coresight path because cpu mask was cleared when coresight_trace_id_get_cpu_id failed.

Call coresight_release_path function explicitly when alloc trace id filed.

Fixes: 4ff1fdb4125c4 ("coresight: perf: traceid: Add perf ID allocation and notifiers") Signed-off-by: Ruidong Tian tianruidong@linux.alibaba.com Signed-off-by: Suzuki K Poulose suzuki.poulose@arm.com Link: https://lore.kernel.org/r/20230425032416.125542-1-tianruidong@linux.alibaba.... Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/hwtracing/coresight/coresight-etm-perf.c | 1 + 1 file changed, 1 insertion(+)

diff --git a/drivers/hwtracing/coresight/coresight-etm-perf.c b/drivers/hwtracing/coresight/coresight-etm-perf.c index 711f451b69469..89e8ed214ea49 100644 --- a/drivers/hwtracing/coresight/coresight-etm-perf.c +++ b/drivers/hwtracing/coresight/coresight-etm-perf.c @@ -402,6 +402,7 @@ static void *etm_setup_aux(struct perf_event *event, void **pages, trace_id = coresight_trace_id_get_cpu_id(cpu); if (!IS_VALID_CS_TRACE_ID(trace_id)) { cpumask_clear_cpu(cpu, mask); + coresight_release_path(path); continue; }

From: Jeremy Sowden jeremy@azazel.net

[ Upstream commit 5f5486b620cd43b16a1787ef92b9bc21bd72ef2e ]

When building sign-file, the call to get the CFLAGS for libcrypto is missing white-space between `pkg-config` and `--cflags`:

$(shell $(HOSTPKG_CONFIG)--cflags libcrypto 2> /dev/null)

Removing the redirection of stderr, we see:

$ make -C tools/testing/selftests/bpf sign-file make: Entering directory '[...]/tools/testing/selftests/bpf' make: pkg-config--cflags: No such file or directory SIGN-FILE sign-file make: Leaving directory '[...]/tools/testing/selftests/bpf'

Add the missing space.

Fixes: fc97590668ae ("selftests/bpf: Add test for bpf_verify_pkcs7_signature() kfunc") Signed-off-by: Jeremy Sowden jeremy@azazel.net Signed-off-by: Daniel Borkmann daniel@iogearbox.net Reviewed-by: Roberto Sassu roberto.sassu@huawei.com Link: https://lore.kernel.org/bpf/20230426215032.415792-1-jeremy@azazel.net Signed-off-by: Alexei Starovoitov ast@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- tools/testing/selftests/bpf/Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile index b677dcd0b77af..ad01c9e1ff12b 100644 --- a/tools/testing/selftests/bpf/Makefile +++ b/tools/testing/selftests/bpf/Makefile @@ -197,7 +197,7 @@ $(OUTPUT)/urandom_read: urandom_read.c urandom_read_aux.c $(OUTPUT)/liburandom_r

$(OUTPUT)/sign-file: ../../../../scripts/sign-file.c $(call msg,SIGN-FILE,,$@) - $(Q)$(CC) $(shell $(HOSTPKG_CONFIG)--cflags libcrypto 2> /dev/null) \ + $(Q)$(CC) $(shell $(HOSTPKG_CONFIG) --cflags libcrypto 2> /dev/null) \ $< -o $@ \ $(shell $(HOSTPKG_CONFIG) --libs libcrypto 2> /dev/null || echo -lcrypto)

From: Mario Limonciello mario.limonciello@amd.com

[ Upstream commit b54147fa374dbeadcb01b1762db1a793e06e37de ]

After suspend/resume cycle there is an error message and auto-mode or CnQF stops working.

[ 5741.447511] amd-pmf AMDI0100:00: SMU cmd failed. err: 0xff [ 5741.447523] amd-pmf AMDI0100:00: AMD_PMF_REGISTER_RESPONSE:ff [ 5741.447527] amd-pmf AMDI0100:00: AMD_PMF_REGISTER_ARGUMENT:7 [ 5741.447531] amd-pmf AMDI0100:00: AMD_PMF_REGISTER_MESSAGE:16 [ 5741.447540] amd-pmf AMDI0100:00: [AUTO_MODE] avg power: 0 mW mode: QUIET

This is because the DRAM address used for accessing metrics table needs to be refreshed after a suspend resume cycle. Add a resume callback to reset this again.

Fixes: 1a409b35c995 ("platform/x86/amd/pmf: Get performance metrics from PMFW") Signed-off-by: Mario Limonciello mario.limonciello@amd.com Link: https://lore.kernel.org/r/20230513011408.958-1-mario.limonciello@amd.com Reviewed-by: Hans de Goede hdegoede@redhat.com Signed-off-by: Hans de Goede hdegoede@redhat.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/platform/x86/amd/pmf/core.c | 32 ++++++++++++++++++++++------- 1 file changed, 25 insertions(+), 7 deletions(-)

diff --git a/drivers/platform/x86/amd/pmf/core.c b/drivers/platform/x86/amd/pmf/core.c index 0acc0b6221290..dc9803e1a4b9b 100644 --- a/drivers/platform/x86/amd/pmf/core.c +++ b/drivers/platform/x86/amd/pmf/core.c @@ -245,24 +245,29 @@ static const struct pci_device_id pmf_pci_ids[] = { { } };

-int amd_pmf_init_metrics_table(struct amd_pmf_dev *dev) +static void amd_pmf_set_dram_addr(struct amd_pmf_dev *dev) { u64 phys_addr; u32 hi, low;

- INIT_DELAYED_WORK(&dev->work_buffer, amd_pmf_get_metrics); + phys_addr = virt_to_phys(dev->buf); + hi = phys_addr >> 32; + low = phys_addr & GENMASK(31, 0); + + amd_pmf_send_cmd(dev, SET_DRAM_ADDR_HIGH, 0, hi, NULL); + amd_pmf_send_cmd(dev, SET_DRAM_ADDR_LOW, 0, low, NULL); +}

+int amd_pmf_init_metrics_table(struct amd_pmf_dev *dev) +{ /* Get Metrics Table Address */ dev->buf = kzalloc(sizeof(dev->m_table), GFP_KERNEL); if (!dev->buf) return -ENOMEM;

- phys_addr = virt_to_phys(dev->buf); - hi = phys_addr >> 32; - low = phys_addr & GENMASK(31, 0); + INIT_DELAYED_WORK(&dev->work_buffer, amd_pmf_get_metrics);

- amd_pmf_send_cmd(dev, SET_DRAM_ADDR_HIGH, 0, hi, NULL); - amd_pmf_send_cmd(dev, SET_DRAM_ADDR_LOW, 0, low, NULL); + amd_pmf_set_dram_addr(dev);

/* * Start collecting the metrics data after a small delay @@ -273,6 +278,18 @@ int amd_pmf_init_metrics_table(struct amd_pmf_dev *dev) return 0; }

+static int amd_pmf_resume_handler(struct device *dev) +{ + struct amd_pmf_dev *pdev = dev_get_drvdata(dev); + + if (pdev->buf) + amd_pmf_set_dram_addr(pdev); + + return 0; +} + +static DEFINE_SIMPLE_DEV_PM_OPS(amd_pmf_pm, NULL, amd_pmf_resume_handler); + static void amd_pmf_init_features(struct amd_pmf_dev *dev) { int ret; @@ -414,6 +431,7 @@ static struct platform_driver amd_pmf_driver = { .name = "amd-pmf", .acpi_match_table = amd_pmf_acpi_ids, .dev_groups = amd_pmf_driver_groups, + .pm = pm_sleep_ptr(&amd_pmf_pm), }, .probe = amd_pmf_probe, .remove = amd_pmf_remove,

From: Andreas Kemnade andreas@kemnade.info

[ Upstream commit 7dd3d9bd873f138675cb727eaa51a498d99f0e89 ]

If static allocation and dynamic allocation GPIOs are present, dynamic allocation pollutes the numberspace for static allocation, causing static allocation to fail. Enforce dynamic allocation above GPIO_DYNAMIC_BASE.

Seen on a GTA04 when omap-gpio (static) and twl-gpio (dynamic) raced: [some successful registrations of omap_gpio instances] [ 2.553833] twl4030_gpio twl4030-gpio: gpio (irq 145) chaining IRQs 161..178 [ 2.561401] gpiochip_find_base: found new base at 160 [ 2.564392] gpio gpiochip5: (twl4030): added GPIO chardev (254:5) [ 2.564544] gpio gpiochip5: registered GPIOs 160 to 177 on twl4030 [...] [ 2.692169] omap-gpmc 6e000000.gpmc: GPMC revision 5.0 [ 2.697357] gpmc_mem_init: disabling cs 0 mapped at 0x0-0x1000000 [ 2.703643] gpiochip_find_base: found new base at 178 [ 2.704376] gpio gpiochip6: (omap-gpmc): added GPIO chardev (254:6) [ 2.704589] gpio gpiochip6: registered GPIOs 178 to 181 on omap-gpmc [...] [ 2.840393] gpio gpiochip7: Static allocation of GPIO base is deprecated, use dynamic allocation. [ 2.849365] gpio gpiochip7: (gpio-160-191): GPIO integer space overlap, cannot add chip [ 2.857513] gpiochip_add_data_with_key: GPIOs 160..191 (gpio-160-191) failed to register, -16 [ 2.866149] omap_gpio 48310000.gpio: error -EBUSY: Could not register gpio chip

On that device it is fixed invasively by commit 92bf78b33b0b4 ("gpio: omap: use dynamic allocation of base") but let's also fix that for devices where there is still a mixture of static and dynamic allocation.

Fixes: 7b61212f2a07 ("gpiolib: Get rid of ARCH_NR_GPIOS") Signed-off-by: Andreas Kemnade andreas@kemnade.info Reviewed-by: christophe.leroy@csgroup.eu Reviewed-by: Andy Shevchenko andy.shevchenko@gmail.com Reviewed-by: Linus Walleij linus.walleij@linaro.org Signed-off-by: Bartosz Golaszewski bartosz.golaszewski@linaro.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/gpio/gpiolib.c | 2 ++ 1 file changed, 2 insertions(+)

diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c index 19bd23044b017..4472214fcd43a 100644 --- a/drivers/gpio/gpiolib.c +++ b/drivers/gpio/gpiolib.c @@ -193,6 +193,8 @@ static int gpiochip_find_base(int ngpio) break; /* nope, check the space right after the chip */ base = gdev->base + gdev->ngpio; + if (base < GPIO_DYNAMIC_BASE) + base = GPIO_DYNAMIC_BASE; }

if (gpio_is_valid(base)) {

From: Jakub Kicinski kuba@kernel.org

[ Upstream commit 210620ae44a83f25220450bbfcc22e6fe986b25f ]

alloc_skb_with_frags() fills in page frag sizes but does not set skb->len and skb->data_len. Set those correctly otherwise device offload will most likely generate an empty skb and hit the BUG() at the end of __skb_nsg().

Fixes: 84c61fe1a75b ("tls: rx: do not use the standard strparser") Tested-by: Shai Amiram samiram@nvidia.com Signed-off-by: Jakub Kicinski kuba@kernel.org Reviewed-by: Simon Horman simon.horman@corigine.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- net/tls/tls_strp.c | 2 ++ 1 file changed, 2 insertions(+)

diff --git a/net/tls/tls_strp.c b/net/tls/tls_strp.c index 955ac3e0bf4d3..24016c865e004 100644 --- a/net/tls/tls_strp.c +++ b/net/tls/tls_strp.c @@ -56,6 +56,8 @@ static struct sk_buff *tls_strp_msg_make_copy(struct tls_strparser *strp) offset += skb_frag_size(frag); }

+ skb->len = strp->stm.full_len; + skb->data_len = strp->stm.full_len; skb_copy_header(skb, strp->anchor); rxm = strp_msg(skb); rxm->offset = 0;

From: Jakub Kicinski kuba@kernel.org

[ Upstream commit 14c4be92ebb3e36e392aa9dd8f314038a9f96f3c ]

If a record is partially decrypted we'll have to CoW it, anyway, so go into copy mode and allocate a writable skb right away.

This will make subsequent fix simpler because we won't have to teach tls_strp_msg_make_copy() how to copy skbs while preserving decrypt status.

Tested-by: Shai Amiram samiram@nvidia.com Signed-off-by: Jakub Kicinski kuba@kernel.org Reviewed-by: Simon Horman simon.horman@corigine.com Signed-off-by: David S. Miller davem@davemloft.net Stable-dep-of: eca9bfafee3a ("tls: rx: strp: preserve decryption status of skbs when needed") Signed-off-by: Sasha Levin sashal@kernel.org --- include/linux/skbuff.h | 10 ++++++++++ net/tls/tls_strp.c | 16 +++++++++++----- 2 files changed, 21 insertions(+), 5 deletions(-)

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index dbcaac8b69665..4a882f9ba1f1f 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -1577,6 +1577,16 @@ static inline void skb_copy_hash(struct sk_buff *to, const struct sk_buff *from) to->l4_hash = from->l4_hash; };

+static inline int skb_cmp_decrypted(const struct sk_buff *skb1, + const struct sk_buff *skb2) +{ +#ifdef CONFIG_TLS_DEVICE + return skb2->decrypted - skb1->decrypted; +#else + return 0; +#endif +} + static inline void skb_copy_decrypted(struct sk_buff *to, const struct sk_buff *from) { diff --git a/net/tls/tls_strp.c b/net/tls/tls_strp.c index 9889df5ce0660..e2e48217e7ac9 100644 --- a/net/tls/tls_strp.c +++ b/net/tls/tls_strp.c @@ -326,15 +326,19 @@ static int tls_strp_read_copy(struct tls_strparser *strp, bool qshort) return 0; }

-static bool tls_strp_check_no_dup(struct tls_strparser *strp) +static bool tls_strp_check_queue_ok(struct tls_strparser *strp) { unsigned int len = strp->stm.offset + strp->stm.full_len; - struct sk_buff *skb; + struct sk_buff *first, *skb; u32 seq;

- skb = skb_shinfo(strp->anchor)->frag_list; - seq = TCP_SKB_CB(skb)->seq; + first = skb_shinfo(strp->anchor)->frag_list; + skb = first; + seq = TCP_SKB_CB(first)->seq;

+ /* Make sure there's no duplicate data in the queue, + * and the decrypted status matches. + */ while (skb->len < len) { seq += skb->len; len -= skb->len; @@ -342,6 +346,8 @@ static bool tls_strp_check_no_dup(struct tls_strparser *strp)

if (TCP_SKB_CB(skb)->seq != seq) return false; + if (skb_cmp_decrypted(first, skb)) + return false; }

return true; @@ -422,7 +428,7 @@ static int tls_strp_read_sock(struct tls_strparser *strp) return tls_strp_read_copy(strp, true); }

- if (!tls_strp_check_no_dup(strp)) + if (!tls_strp_check_queue_ok(strp)) return tls_strp_read_copy(strp, false);

strp->msg_ready = 1;

From: Jakub Kicinski kuba@kernel.org

[ Upstream commit eca9bfafee3a0487e59c59201ae14c7594ba940a ]

When receive buffer is small we try to copy out the data from TCP into a skb maintained by TLS to prevent connection from stalling. Unfortunately if a single record is made up of a mix of decrypted and non-decrypted skbs combining them into a single skb leads to loss of decryption status, resulting in decryption errors or data corruption.

Similarly when trying to use TCP receive queue directly we need to make sure that all the skbs within the record have the same status. If we don't the mixed status will be detected correctly but we'll CoW the anchor, again collapsing it into a single paged skb without decrypted status preserved. So the "fixup" code will not know which parts of skb to re-encrypt.

Fixes: 84c61fe1a75b ("tls: rx: do not use the standard strparser") Tested-by: Shai Amiram samiram@nvidia.com Signed-off-by: Jakub Kicinski kuba@kernel.org Reviewed-by: Simon Horman simon.horman@corigine.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- include/net/tls.h | 1 + net/tls/tls.h | 5 ++ net/tls/tls_device.c | 22 +++----- net/tls/tls_strp.c | 117 ++++++++++++++++++++++++++++++++++++------- 4 files changed, 114 insertions(+), 31 deletions(-)

diff --git a/include/net/tls.h b/include/net/tls.h index 154949c7b0c88..c36bf4c50027e 100644 --- a/include/net/tls.h +++ b/include/net/tls.h @@ -124,6 +124,7 @@ struct tls_strparser { u32 mark : 8; u32 stopped : 1; u32 copy_mode : 1; + u32 mixed_decrypted : 1; u32 msg_ready : 1;

struct strp_msg stm; diff --git a/net/tls/tls.h b/net/tls/tls.h index 804c3880d0288..0672acab27731 100644 --- a/net/tls/tls.h +++ b/net/tls/tls.h @@ -167,6 +167,11 @@ static inline bool tls_strp_msg_ready(struct tls_sw_context_rx *ctx) return ctx->strp.msg_ready; }

+static inline bool tls_strp_msg_mixed_decrypted(struct tls_sw_context_rx *ctx) +{ + return ctx->strp.mixed_decrypted; +} + #ifdef CONFIG_TLS_DEVICE int tls_device_init(void); void tls_device_cleanup(void); diff --git a/net/tls/tls_device.c b/net/tls/tls_device.c index 3b87c7b04ac87..bf69c9d6d06c0 100644 --- a/net/tls/tls_device.c +++ b/net/tls/tls_device.c @@ -1007,20 +1007,14 @@ int tls_device_decrypted(struct sock *sk, struct tls_context *tls_ctx) struct tls_sw_context_rx *sw_ctx = tls_sw_ctx_rx(tls_ctx); struct sk_buff *skb = tls_strp_msg(sw_ctx); struct strp_msg *rxm = strp_msg(skb); - int is_decrypted = skb->decrypted; - int is_encrypted = !is_decrypted; - struct sk_buff *skb_iter; - int left; - - left = rxm->full_len + rxm->offset - skb_pagelen(skb); - /* Check if all the data is decrypted already */ - skb_iter = skb_shinfo(skb)->frag_list; - while (skb_iter && left > 0) { - is_decrypted &= skb_iter->decrypted; - is_encrypted &= !skb_iter->decrypted; - - left -= skb_iter->len; - skb_iter = skb_iter->next; + int is_decrypted, is_encrypted; + + if (!tls_strp_msg_mixed_decrypted(sw_ctx)) { + is_decrypted = skb->decrypted; + is_encrypted = !is_decrypted; + } else { + is_decrypted = 0; + is_encrypted = 0; }

trace_tls_device_decrypted(sk, tcp_sk(sk)->copied_seq - rxm->full_len, diff --git a/net/tls/tls_strp.c b/net/tls/tls_strp.c index 61fbf84baf9e0..da95abbb7ea32 100644 --- a/net/tls/tls_strp.c +++ b/net/tls/tls_strp.c @@ -29,7 +29,8 @@ static void tls_strp_anchor_free(struct tls_strparser *strp) struct skb_shared_info *shinfo = skb_shinfo(strp->anchor);

DEBUG_NET_WARN_ON_ONCE(atomic_read(&shinfo->dataref) != 1); - shinfo->frag_list = NULL; + if (!strp->copy_mode) + shinfo->frag_list = NULL; consume_skb(strp->anchor); strp->anchor = NULL; } @@ -195,22 +196,22 @@ static void tls_strp_flush_anchor_copy(struct tls_strparser *strp) for (i = 0; i < shinfo->nr_frags; i++) __skb_frag_unref(&shinfo->frags[i], false); shinfo->nr_frags = 0; + if (strp->copy_mode) { + kfree_skb_list(shinfo->frag_list); + shinfo->frag_list = NULL; + } strp->copy_mode = 0; + strp->mixed_decrypted = 0; }

-static int tls_strp_copyin(read_descriptor_t *desc, struct sk_buff *in_skb, - unsigned int offset, size_t in_len) +static int tls_strp_copyin_frag(struct tls_strparser *strp, struct sk_buff *skb, + struct sk_buff *in_skb, unsigned int offset, + size_t in_len) { - struct tls_strparser *strp = (struct tls_strparser *)desc->arg.data; - struct sk_buff *skb; - skb_frag_t *frag; size_t len, chunk; + skb_frag_t *frag; int sz;

- if (strp->msg_ready) - return 0; - - skb = strp->anchor; frag = &skb_shinfo(skb)->frags[skb->len / PAGE_SIZE];

len = in_len; @@ -228,10 +229,8 @@ static int tls_strp_copyin(read_descriptor_t *desc, struct sk_buff *in_skb, skb_frag_size_add(frag, chunk);

sz = tls_rx_msg_size(strp, skb); - if (sz < 0) { - desc->error = sz; - return 0; - } + if (sz < 0) + return sz;

/* We may have over-read, sz == 0 is guaranteed under-read */ if (unlikely(sz && sz < skb->len)) { @@ -271,15 +270,99 @@ static int tls_strp_copyin(read_descriptor_t *desc, struct sk_buff *in_skb, offset += chunk; }

- if (strp->stm.full_len == skb->len) { +read_done: + return in_len - len; +} + +static int tls_strp_copyin_skb(struct tls_strparser *strp, struct sk_buff *skb, + struct sk_buff *in_skb, unsigned int offset, + size_t in_len) +{ + struct sk_buff *nskb, *first, *last; + struct skb_shared_info *shinfo; + size_t chunk; + int sz; + + if (strp->stm.full_len) + chunk = strp->stm.full_len - skb->len; + else + chunk = TLS_MAX_PAYLOAD_SIZE + PAGE_SIZE; + chunk = min(chunk, in_len); + + nskb = tls_strp_skb_copy(strp, in_skb, offset, chunk); + if (!nskb) + return -ENOMEM; + + shinfo = skb_shinfo(skb); + if (!shinfo->frag_list) { + shinfo->frag_list = nskb; + nskb->prev = nskb; + } else { + first = shinfo->frag_list; + last = first->prev; + last->next = nskb; + first->prev = nskb; + } + + skb->len += chunk; + skb->data_len += chunk; + + if (!strp->stm.full_len) { + sz = tls_rx_msg_size(strp, skb); + if (sz < 0) + return sz; + + /* We may have over-read, sz == 0 is guaranteed under-read */ + if (unlikely(sz && sz < skb->len)) { + int over = skb->len - sz; + + WARN_ON_ONCE(over > chunk); + skb->len -= over; + skb->data_len -= over; + __pskb_trim(nskb, nskb->len - over); + + chunk -= over; + } + + strp->stm.full_len = sz; + } + + return chunk; +} + +static int tls_strp_copyin(read_descriptor_t *desc, struct sk_buff *in_skb, + unsigned int offset, size_t in_len) +{ + struct tls_strparser *strp = (struct tls_strparser *)desc->arg.data; + struct sk_buff *skb; + int ret; + + if (strp->msg_ready) + return 0; + + skb = strp->anchor; + if (!skb->len) + skb_copy_decrypted(skb, in_skb); + else + strp->mixed_decrypted |= !!skb_cmp_decrypted(skb, in_skb); + + if (IS_ENABLED(CONFIG_TLS_DEVICE) && strp->mixed_decrypted) + ret = tls_strp_copyin_skb(strp, skb, in_skb, offset, in_len); + else + ret = tls_strp_copyin_frag(strp, skb, in_skb, offset, in_len); + if (ret < 0) { + desc->error = ret; + ret = 0; + } + + if (strp->stm.full_len && strp->stm.full_len == skb->len) { desc->count = 0;

strp->msg_ready = 1; tls_rx_msg_ready(strp); }

-read_done: - return in_len - len; + return ret; }

static int tls_strp_read_copyin(struct tls_strparser *strp)

From: Shenwei Wang shenwei.wang@nxp.com

[ Upstream commit 9025944fddfed5966c8f102f1fe921ab3aee2c12 ]

Two dma_wmb() are added in the XDP TX path to ensure proper ordering of descriptor and buffer updates: 1. A dma_wmb() is added after updating the last BD to make sure the updates to rest of the descriptor are visible before transferring ownership to FEC. 2. A dma_wmb() is also added after updating the bdp to ensure these updates are visible before updating txq->bd.cur. 3. Start the xmit of the frame immediately right after configuring the tx descriptor.

Fixes: 6d6b39f180b8 ("net: fec: add initial XDP support") Signed-off-by: Shenwei Wang shenwei.wang@nxp.com Reviewed-by: Wei Fang wei.fang@nxp.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/freescale/fec_main.c | 17 +++++++++++------ 1 file changed, 11 insertions(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c index 577d94821b3e7..38e5b5abe067c 100644 --- a/drivers/net/ethernet/freescale/fec_main.c +++ b/drivers/net/ethernet/freescale/fec_main.c @@ -3834,6 +3834,11 @@ static int fec_enet_txq_xmit_frame(struct fec_enet_private *fep, index = fec_enet_get_bd_index(last_bdp, &txq->bd); txq->tx_skbuff[index] = NULL;

+ /* Make sure the updates to rest of the descriptor are performed before + * transferring ownership. + */ + dma_wmb(); + /* Send it on its way. Tell FEC it's ready, interrupt when done, * it's the last BD of the frame, and to put the CRC on the end. */ @@ -3843,8 +3848,14 @@ static int fec_enet_txq_xmit_frame(struct fec_enet_private *fep, /* If this was the last BD in the ring, start at the beginning again. */ bdp = fec_enet_get_nextdesc(last_bdp, &txq->bd);

+ /* Make sure the update to bdp are performed before txq->bd.cur. */ + dma_wmb(); + txq->bd.cur = bdp;

+ /* Trigger transmission start */ + writel(0, txq->bd.reg_desc_active); + return 0; }

@@ -3873,12 +3884,6 @@ static int fec_enet_xdp_xmit(struct net_device *dev, sent_frames++; }

- /* Make sure the update to bdp and tx_skbuff are performed. */ - wmb(); - - /* Trigger transmission start */ - writel(0, txq->bd.reg_desc_active); - __netif_tx_unlock(nq);

return sent_frames;

From: Amadeusz Sławiński amadeuszx.slawinski@linux.intel.com

[ Upstream commit ff04437f6dcd138b50483afc7b313f016020ce8f ]

When changing value of kcontrol, FW module to which data should be send needs to be found. Currently it is done in improper way, fix it. Change function name to indicate that it looks only for volume module.

This allows to change volume during runtime, instead of only changing init value.

Fixes: be2b81b519d7 ("ASoC: Intel: avs: Parse control tuples") Reviewed-by: Cezary Rojewski cezary.rojewski@intel.com Signed-off-by: Amadeusz Sławiński amadeuszx.slawinski@linux.intel.com Link: https://lore.kernel.org/r/20230519201711.4073845-2-amadeuszx.slawinski@linux... Signed-off-by: Mark Brown broonie@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- sound/soc/intel/avs/control.c | 22 +++++++++++++++------- 1 file changed, 15 insertions(+), 7 deletions(-)

diff --git a/sound/soc/intel/avs/control.c b/sound/soc/intel/avs/control.c index a8b14b784f8a5..3dfa2e9816db0 100644 --- a/sound/soc/intel/avs/control.c +++ b/sound/soc/intel/avs/control.c @@ -21,17 +21,25 @@ static struct avs_dev *avs_get_kcontrol_adev(struct snd_kcontrol *kcontrol) return to_avs_dev(w->dapm->component->dev); }

-static struct avs_path_module *avs_get_kcontrol_module(struct avs_dev *adev, u32 id) +static struct avs_path_module *avs_get_volume_module(struct avs_dev *adev, u32 id) { struct avs_path *path; struct avs_path_pipeline *ppl; struct avs_path_module *mod;

- list_for_each_entry(path, &adev->path_list, node) - list_for_each_entry(ppl, &path->ppl_list, node) - list_for_each_entry(mod, &ppl->mod_list, node) - if (mod->template->ctl_id && mod->template->ctl_id == id) + spin_lock(&adev->path_list_lock); + list_for_each_entry(path, &adev->path_list, node) { + list_for_each_entry(ppl, &path->ppl_list, node) { + list_for_each_entry(mod, &ppl->mod_list, node) { + if (guid_equal(&mod->template->cfg_ext->type, &AVS_PEAKVOL_MOD_UUID) + && mod->template->ctl_id == id) { + spin_unlock(&adev->path_list_lock); return mod; + } + } + } + } + spin_unlock(&adev->path_list_lock);

return NULL; } @@ -49,7 +57,7 @@ int avs_control_volume_get(struct snd_kcontrol *kcontrol, struct snd_ctl_elem_va /* prevent access to modules while path is being constructed */ mutex_lock(&adev->path_mutex);

- active_module = avs_get_kcontrol_module(adev, ctl_data->id); + active_module = avs_get_volume_module(adev, ctl_data->id); if (active_module) { ret = avs_ipc_peakvol_get_volume(adev, active_module->module_id, active_module->instance_id, &dspvols, @@ -89,7 +97,7 @@ int avs_control_volume_put(struct snd_kcontrol *kcontrol, struct snd_ctl_elem_va changed = 1; }

- active_module = avs_get_kcontrol_module(adev, ctl_data->id); + active_module = avs_get_volume_module(adev, ctl_data->id); if (active_module) { dspvol.channel_id = AVS_ALL_CHANNELS_MASK; dspvol.target_volume = *volume;

From: Imre Deak imre.deak@intel.com

[ Upstream commit b108bdd0e22a402bd3e4a6391acbb6aefad31a9e ]

Bspec requires disabling the DPLLs on TC ports before disconnecting the port's PHY. Add a post_pll_disable encoder hook and move the call to disconnect the port's PHY from the post_disable hook to the new hook.

Reviewed-by: Mika Kahola mika.kahola@intel.com Signed-off-by: Imre Deak imre.deak@intel.com Link: https://patchwork.freedesktop.org/patch/msgid/20230323142035.1432621-28-imre... Stable-dep-of: 45dfbd992923 ("drm/i915: Fix PIPEDMC disabling for a bigjoiner configuration") Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/gpu/drm/i915/display/intel_ddi.c | 15 ++++++++++++--- drivers/gpu/drm/i915/display/intel_display.c | 2 ++ drivers/gpu/drm/i915/display/intel_dp_mst.c | 15 +++++++++++++++ 3 files changed, 29 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_ddi.c b/drivers/gpu/drm/i915/display/intel_ddi.c index 254559abedfba..379050d228941 100644 --- a/drivers/gpu/drm/i915/display/intel_ddi.c +++ b/drivers/gpu/drm/i915/display/intel_ddi.c @@ -2731,9 +2731,6 @@ static void intel_ddi_post_disable(struct intel_atomic_state *state, const struct drm_connector_state *old_conn_state) { struct drm_i915_private *dev_priv = to_i915(encoder->base.dev); - struct intel_digital_port *dig_port = enc_to_dig_port(encoder); - enum phy phy = intel_port_to_phy(dev_priv, encoder->port); - bool is_tc_port = intel_phy_is_tc(dev_priv, phy); struct intel_crtc *slave_crtc;

if (!intel_crtc_has_type(old_crtc_state, INTEL_OUTPUT_DP_MST)) { @@ -2783,6 +2780,17 @@ static void intel_ddi_post_disable(struct intel_atomic_state *state, else intel_ddi_post_disable_dp(state, encoder, old_crtc_state, old_conn_state); +} + +static void intel_ddi_post_pll_disable(struct intel_atomic_state *state, + struct intel_encoder *encoder, + const struct intel_crtc_state *old_crtc_state, + const struct drm_connector_state *old_conn_state) +{ + struct drm_i915_private *i915 = to_i915(encoder->base.dev); + struct intel_digital_port *dig_port = enc_to_dig_port(encoder); + enum phy phy = intel_port_to_phy(i915, encoder->port); + bool is_tc_port = intel_phy_is_tc(i915, phy);

main_link_aux_power_domain_put(dig_port, old_crtc_state);

@@ -4381,6 +4389,7 @@ void intel_ddi_init(struct drm_i915_private *dev_priv, enum port port) encoder->pre_pll_enable = intel_ddi_pre_pll_enable; encoder->pre_enable = intel_ddi_pre_enable; encoder->disable = intel_disable_ddi; + encoder->post_pll_disable = intel_ddi_post_pll_disable; encoder->post_disable = intel_ddi_post_disable; encoder->update_pipe = intel_ddi_update_pipe; encoder->get_hw_state = intel_ddi_get_hw_state; diff --git a/drivers/gpu/drm/i915/display/intel_display.c b/drivers/gpu/drm/i915/display/intel_display.c index df4c6e000961c..963680ea6fedd 100644 --- a/drivers/gpu/drm/i915/display/intel_display.c +++ b/drivers/gpu/drm/i915/display/intel_display.c @@ -2022,6 +2022,8 @@ static void hsw_crtc_disable(struct intel_atomic_state *state,

intel_disable_shared_dpll(old_crtc_state);

+ intel_encoders_post_pll_disable(state, crtc); + intel_dmc_disable_pipe(i915, crtc->pipe); }

diff --git a/drivers/gpu/drm/i915/display/intel_dp_mst.c b/drivers/gpu/drm/i915/display/intel_dp_mst.c index 7c9b328bc2d73..a93018ce0e312 100644 --- a/drivers/gpu/drm/i915/display/intel_dp_mst.c +++ b/drivers/gpu/drm/i915/display/intel_dp_mst.c @@ -623,6 +623,20 @@ static void intel_mst_post_disable_dp(struct intel_atomic_state *state, intel_dp->active_mst_links); }

+static void intel_mst_post_pll_disable_dp(struct intel_atomic_state *state, + struct intel_encoder *encoder, + const struct intel_crtc_state *old_crtc_state, + const struct drm_connector_state *old_conn_state) +{ + struct intel_dp_mst_encoder *intel_mst = enc_to_mst(encoder); + struct intel_digital_port *dig_port = intel_mst->primary; + struct intel_dp *intel_dp = &dig_port->dp; + + if (intel_dp->active_mst_links == 0 && + dig_port->base.post_pll_disable) + dig_port->base.post_pll_disable(state, encoder, old_crtc_state, old_conn_state); +} + static void intel_mst_pre_pll_enable_dp(struct intel_atomic_state *state, struct intel_encoder *encoder, const struct intel_crtc_state *pipe_config, @@ -1146,6 +1160,7 @@ intel_dp_create_fake_mst_encoder(struct intel_digital_port *dig_port, enum pipe intel_encoder->compute_config_late = intel_dp_mst_compute_config_late; intel_encoder->disable = intel_mst_disable_dp; intel_encoder->post_disable = intel_mst_post_disable_dp; + intel_encoder->post_pll_disable = intel_mst_post_pll_disable_dp; intel_encoder->update_pipe = intel_ddi_update_pipe; intel_encoder->pre_pll_enable = intel_mst_pre_pll_enable_dp; intel_encoder->pre_enable = intel_mst_pre_enable_dp;

From: Paul Blakey paulb@nvidia.com

[ Upstream commit dfa1e46d6093831b9d49f0f350227a1d13644a2f ]

Cited patch is using the eswitch object mapping pool while in nic mode where it isn't initialized. This results in the trace below [0].

Fix that by using either nic or eswitch object mapping pool depending if eswitch is enabled or not.

[0]: [ 826.446057] ================================================================== [ 826.446729] BUG: KASAN: slab-use-after-free in mlx5_add_flow_rules+0x30/0x490 [mlx5_core] [ 826.447515] Read of size 8 at addr ffff888194485830 by task tc/6233

[ 826.448243] CPU: 16 PID: 6233 Comm: tc Tainted: G W 6.3.0-rc6+ #1 [ 826.448890] Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS rel-1.13.0-0-gf21b5a4aeb02-prebuilt.qemu.org 04/01/2014 [ 826.449785] Call Trace: [ 826.450052] <TASK> [ 826.450302] dump_stack_lvl+0x33/0x50 [ 826.450650] print_report+0xc2/0x610 [ 826.450998] ? __virt_addr_valid+0xb1/0x130 [ 826.451385] ? mlx5_add_flow_rules+0x30/0x490 [mlx5_core] [ 826.451935] kasan_report+0xae/0xe0 [ 826.452276] ? mlx5_add_flow_rules+0x30/0x490 [mlx5_core] [ 826.452829] mlx5_add_flow_rules+0x30/0x490 [mlx5_core] [ 826.453368] ? __kmalloc_node+0x5a/0x120 [ 826.453733] esw_add_restore_rule+0x20f/0x270 [mlx5_core] [ 826.454288] ? mlx5_eswitch_add_send_to_vport_meta_rule+0x260/0x260 [mlx5_core] [ 826.455011] ? mutex_unlock+0x80/0xd0 [ 826.455361] ? __mutex_unlock_slowpath.constprop.0+0x210/0x210 [ 826.455862] ? mapping_add+0x2cb/0x440 [mlx5_core] [ 826.456425] mlx5e_tc_action_miss_mapping_get+0x139/0x180 [mlx5_core] [ 826.457058] ? mlx5e_tc_update_skb_nic+0xb0/0xb0 [mlx5_core] [ 826.457636] ? __kasan_kmalloc+0x77/0x90 [ 826.458000] ? __kmalloc+0x57/0x120 [ 826.458336] mlx5_tc_ct_flow_offload+0x325/0xe40 [mlx5_core] [ 826.458916] ? ct_kernel_enter.constprop.0+0x48/0xa0 [ 826.459360] ? mlx5_tc_ct_parse_action+0xf0/0xf0 [mlx5_core] [ 826.459933] ? mlx5e_mod_hdr_attach+0x491/0x520 [mlx5_core] [ 826.460507] ? mlx5e_mod_hdr_get+0x12/0x20 [mlx5_core] [ 826.461046] ? mlx5e_tc_attach_mod_hdr+0x154/0x170 [mlx5_core] [ 826.461635] mlx5e_configure_flower+0x969/0x2110 [mlx5_core] [ 826.462217] ? _raw_spin_lock_bh+0x85/0xe0 [ 826.462597] ? __mlx5e_add_fdb_flow+0x750/0x750 [mlx5_core] [ 826.463163] ? kasan_save_stack+0x2e/0x40 [ 826.463534] ? down_read+0x115/0x1b0 [ 826.463878] ? down_write_killable+0x110/0x110 [ 826.464288] ? tc_setup_action.part.0+0x9f/0x3b0 [ 826.464701] ? mlx5e_is_uplink_rep+0x4c/0x90 [mlx5_core] [ 826.465253] ? mlx5e_tc_reoffload_flows_work+0x130/0x130 [mlx5_core] [ 826.465878] tc_setup_cb_add+0x112/0x250 [ 826.466247] fl_hw_replace_filter+0x230/0x310 [cls_flower] [ 826.466724] ? fl_hw_destroy_filter+0x1a0/0x1a0 [cls_flower] [ 826.467212] fl_change+0x14e1/0x2030 [cls_flower] [ 826.467636] ? sock_def_readable+0x89/0x120 [ 826.468019] ? fl_tmplt_create+0x2d0/0x2d0 [cls_flower] [ 826.468509] ? kasan_unpoison+0x23/0x50 [ 826.468873] ? get_random_u16+0x180/0x180 [ 826.469244] ? __radix_tree_lookup+0x2b/0x130 [ 826.469640] ? fl_get+0x7b/0x140 [cls_flower] [ 826.470042] ? fl_mask_put+0x200/0x200 [cls_flower] [ 826.470478] ? __mutex_unlock_slowpath.constprop.0+0x210/0x210 [ 826.470973] ? fl_tmplt_create+0x2d0/0x2d0 [cls_flower] [ 826.471427] tc_new_tfilter+0x644/0x1050 [ 826.471795] ? tc_get_tfilter+0x860/0x860 [ 826.472170] ? __thaw_task+0x130/0x130 [ 826.472525] ? arch_stack_walk+0x98/0xf0 [ 826.472892] ? cap_capable+0x9f/0xd0 [ 826.473235] ? security_capable+0x47/0x60 [ 826.473608] rtnetlink_rcv_msg+0x1d5/0x550 [ 826.473985] ? rtnl_calcit.isra.0+0x1f0/0x1f0 [ 826.474383] ? __stack_depot_save+0x35/0x4c0 [ 826.474779] ? kasan_save_stack+0x2e/0x40 [ 826.475149] ? kasan_save_stack+0x1e/0x40 [ 826.475518] ? __kasan_record_aux_stack+0x9f/0xb0 [ 826.475939] ? task_work_add+0x77/0x1c0 [ 826.476305] netlink_rcv_skb+0xe0/0x210 [ 826.476661] ? rtnl_calcit.isra.0+0x1f0/0x1f0 [ 826.477057] ? netlink_ack+0x7c0/0x7c0 [ 826.477412] ? rhashtable_jhash2+0xef/0x150 [ 826.477796] ? _copy_from_iter+0x105/0x770 [ 826.484386] netlink_unicast+0x346/0x490 [ 826.484755] ? netlink_attachskb+0x400/0x400 [ 826.485145] ? kernel_text_address+0xc2/0xd0 [ 826.485535] netlink_sendmsg+0x3b0/0x6c0 [ 826.485902] ? kernel_text_address+0xc2/0xd0 [ 826.486296] ? netlink_unicast+0x490/0x490 [ 826.486671] ? iovec_from_user.part.0+0x7a/0x1a0 [ 826.487083] ? netlink_unicast+0x490/0x490 [ 826.487461] sock_sendmsg+0x73/0xc0 [ 826.487803] ____sys_sendmsg+0x364/0x380 [ 826.488186] ? import_iovec+0x7/0x10 [ 826.488531] ? kernel_sendmsg+0x30/0x30 [ 826.488893] ? __copy_msghdr+0x180/0x180 [ 826.489258] ? kasan_save_stack+0x2e/0x40 [ 826.489629] ? kasan_save_stack+0x1e/0x40 [ 826.490002] ? __kasan_record_aux_stack+0x9f/0xb0 [ 826.490424] ? __call_rcu_common.constprop.0+0x46/0x580 [ 826.490876] ___sys_sendmsg+0xdf/0x140 [ 826.491231] ? copy_msghdr_from_user+0x110/0x110 [ 826.491649] ? fget_raw+0x120/0x120 [ 826.491988] ? ___sys_recvmsg+0xd9/0x130 [ 826.492355] ? folio_batch_add_and_move+0x80/0xa0 [ 826.492776] ? _raw_spin_lock+0x7a/0xd0 [ 826.493137] ? _raw_spin_lock+0x7a/0xd0 [ 826.493500] ? _raw_read_lock_irq+0x30/0x30 [ 826.493880] ? kasan_set_track+0x21/0x30 [ 826.494249] ? kasan_save_free_info+0x2a/0x40 [ 826.494650] ? do_sys_openat2+0xff/0x270 [ 826.495016] ? __fget_light+0x1b5/0x200 [ 826.495377] ? __virt_addr_valid+0xb1/0x130 [ 826.495763] __sys_sendmsg+0xb2/0x130 [ 826.496118] ? __sys_sendmsg_sock+0x20/0x20 [ 826.496501] ? __x64_sys_rseq+0x2e0/0x2e0 [ 826.496874] ? do_user_addr_fault+0x276/0x820 [ 826.497273] ? fpregs_assert_state_consistent+0x52/0x60 [ 826.497727] ? exit_to_user_mode_prepare+0x30/0x120 [ 826.498158] do_syscall_64+0x3d/0x90 [ 826.498502] entry_SYSCALL_64_after_hwframe+0x46/0xb0 [ 826.498949] RIP: 0033:0x7f9b67f4f887 [ 826.499294] Code: 0a 00 f7 d8 64 89 02 48 c7 c0 ff ff ff ff eb b9 0f 1f 00 f3 0f 1e fa 64 8b 04 25 18 00 00 00 85 c0 75 10 b8 2e 00 00 00 0f 05 <48> 3d 00 f0 ff ff 77 51 c3 48 83 ec 28 89 54 24 1c 48 89 74 24 10 [ 826.500742] RSP: 002b:00007fff5d1a5498 EFLAGS: 00000246 ORIG_RAX: 000000000000002e [ 826.501395] RAX: ffffffffffffffda RBX: 0000000064413ce6 RCX: 00007f9b67f4f887 [ 826.501975] RDX: 0000000000000000 RSI: 00007fff5d1a5500 RDI: 0000000000000003 [ 826.502556] RBP: 0000000000000000 R08: 0000000000000001 R09: 0000000000000001 [ 826.503135] R10: 00007f9b67e08708 R11: 0000000000000246 R12: 0000000000000001 [ 826.503714] R13: 0000000000000001 R14: 00007fff5d1a9800 R15: 0000000000485400 [ 826.504304] </TASK>

[ 826.504753] Allocated by task 3764: [ 826.505090] kasan_save_stack+0x1e/0x40 [ 826.505453] kasan_set_track+0x21/0x30 [ 826.505810] __kasan_kmalloc+0x77/0x90 [ 826.506164] __mlx5_create_flow_table+0x16d/0xbb0 [mlx5_core] [ 826.506742] esw_offloads_enable+0x60d/0xfb0 [mlx5_core] [ 826.507292] mlx5_eswitch_enable_locked+0x4d3/0x680 [mlx5_core] [ 826.507885] mlx5_devlink_eswitch_mode_set+0x2a3/0x580 [mlx5_core] [ 826.508513] devlink_nl_cmd_eswitch_set_doit+0xdf/0x1f0 [ 826.508969] genl_family_rcv_msg_doit.isra.0+0x146/0x1c0 [ 826.509427] genl_rcv_msg+0x28d/0x3e0 [ 826.509772] netlink_rcv_skb+0xe0/0x210 [ 826.510133] genl_rcv+0x24/0x40 [ 826.510448] netlink_unicast+0x346/0x490 [ 826.510810] netlink_sendmsg+0x3b0/0x6c0 [ 826.511179] sock_sendmsg+0x73/0xc0 [ 826.511519] __sys_sendto+0x18d/0x220 [ 826.511867] __x64_sys_sendto+0x72/0x80 [ 826.512232] do_syscall_64+0x3d/0x90 [ 826.512576] entry_SYSCALL_64_after_hwframe+0x46/0xb0

[ 826.513220] Freed by task 5674: [ 826.513535] kasan_save_stack+0x1e/0x40 [ 826.513893] kasan_set_track+0x21/0x30 [ 826.514245] kasan_save_free_info+0x2a/0x40 [ 826.514629] ____kasan_slab_free+0x11a/0x1b0 [ 826.515021] __kmem_cache_free+0x14d/0x280 [ 826.515399] tree_put_node+0x109/0x1c0 [mlx5_core] [ 826.515907] mlx5_destroy_flow_table+0x119/0x630 [mlx5_core] [ 826.516481] esw_offloads_steering_cleanup+0xe7/0x150 [mlx5_core] [ 826.517084] esw_offloads_disable+0xe0/0x160 [mlx5_core] [ 826.517632] mlx5_eswitch_disable_locked+0x26c/0x290 [mlx5_core] [ 826.518225] mlx5_devlink_eswitch_mode_set+0x128/0x580 [mlx5_core] [ 826.518834] devlink_nl_cmd_eswitch_set_doit+0xdf/0x1f0 [ 826.519286] genl_family_rcv_msg_doit.isra.0+0x146/0x1c0 [ 826.519748] genl_rcv_msg+0x28d/0x3e0 [ 826.520101] netlink_rcv_skb+0xe0/0x210 [ 826.520458] genl_rcv+0x24/0x40 [ 826.520771] netlink_unicast+0x346/0x490 [ 826.521137] netlink_sendmsg+0x3b0/0x6c0 [ 826.521505] sock_sendmsg+0x73/0xc0 [ 826.521842] __sys_sendto+0x18d/0x220 [ 826.522191] __x64_sys_sendto+0x72/0x80 [ 826.522554] do_syscall_64+0x3d/0x90 [ 826.522894] entry_SYSCALL_64_after_hwframe+0x46/0xb0

[ 826.523540] Last potentially related work creation: [ 826.523969] kasan_save_stack+0x1e/0x40 [ 826.524331] __kasan_record_aux_stack+0x9f/0xb0 [ 826.524739] insert_work+0x30/0x130 [ 826.525078] __queue_work+0x34b/0x690 [ 826.525426] queue_work_on+0x48/0x50 [ 826.525766] __rhashtable_remove_fast_one+0x4af/0x4d0 [mlx5_core] [ 826.526365] del_sw_flow_group+0x1b5/0x270 [mlx5_core] [ 826.526898] tree_put_node+0x109/0x1c0 [mlx5_core] [ 826.527407] esw_offloads_steering_cleanup+0xd3/0x150 [mlx5_core] [ 826.528009] esw_offloads_disable+0xe0/0x160 [mlx5_core] [ 826.528616] mlx5_eswitch_disable_locked+0x26c/0x290 [mlx5_core] [ 826.529218] mlx5_devlink_eswitch_mode_set+0x128/0x580 [mlx5_core] [ 826.529823] devlink_nl_cmd_eswitch_set_doit+0xdf/0x1f0 [ 826.530276] genl_family_rcv_msg_doit.isra.0+0x146/0x1c0 [ 826.530733] genl_rcv_msg+0x28d/0x3e0 [ 826.531079] netlink_rcv_skb+0xe0/0x210 [ 826.531439] genl_rcv+0x24/0x40 [ 826.531755] netlink_unicast+0x346/0x490 [ 826.532123] netlink_sendmsg+0x3b0/0x6c0 [ 826.532487] sock_sendmsg+0x73/0xc0 [ 826.532825] __sys_sendto+0x18d/0x220 [ 826.533175] __x64_sys_sendto+0x72/0x80 [ 826.533533] do_syscall_64+0x3d/0x90 [ 826.533877] entry_SYSCALL_64_after_hwframe+0x46/0xb0

[ 826.534521] The buggy address belongs to the object at ffff888194485800 which belongs to the cache kmalloc-512 of size 512 [ 826.535506] The buggy address is located 48 bytes inside of freed 512-byte region [ffff888194485800, ffff888194485a00)

[ 826.536666] The buggy address belongs to the physical page: [ 826.537138] page:00000000d75841dd refcount:1 mapcount:0 mapping:0000000000000000 index:0x0 pfn:0x194480 [ 826.537915] head:00000000d75841dd order:3 entire_mapcount:0 nr_pages_mapped:0 pincount:0 [ 826.538595] flags: 0x200000000010200(slab|head|node=0|zone=2) [ 826.539089] raw: 0200000000010200 ffff888100042c80 ffffea0004523800 dead000000000002 [ 826.539755] raw: 0000000000000000 0000000000200020 00000001ffffffff 0000000000000000 [ 826.540417] page dumped because: kasan: bad access detected

[ 826.541095] Memory state around the buggy address: [ 826.541519] ffff888194485700: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc [ 826.542149] ffff888194485780: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc [ 826.542773] >ffff888194485800: fa fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb [ 826.543400] ^ [ 826.543822] ffff888194485880: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb [ 826.544452] ffff888194485900: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb [ 826.545079] ==================================================================

Fixes: 6702782845a5 ("net/mlx5e: TC, Set CT miss to the specific ct action instance") Signed-off-by: Paul Blakey paulb@nvidia.com Reviewed-by: Vlad Buslov vladbu@nvidia.com Signed-off-by: Saeed Mahameed saeedm@nvidia.com Signed-off-by: Sasha Levin sashal@kernel.org --- .../net/ethernet/mellanox/mlx5/core/en_tc.c | 34 +++++++++++++++---- 1 file changed, 27 insertions(+), 7 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c index 2b1094e5b0c9d..53acd9a8a4c35 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -5793,22 +5793,43 @@ bool mlx5e_tc_update_skb_nic(struct mlx5_cqe64 *cqe, struct sk_buff *skb) 0, NULL); }

+static struct mapping_ctx * +mlx5e_get_priv_obj_mapping(struct mlx5e_priv *priv) +{ + struct mlx5e_tc_table *tc; + struct mlx5_eswitch *esw; + struct mapping_ctx *ctx; + + if (is_mdev_switchdev_mode(priv->mdev)) { + esw = priv->mdev->priv.eswitch; + ctx = esw->offloads.reg_c0_obj_pool; + } else { + tc = mlx5e_fs_get_tc(priv->fs); + ctx = tc->mapping; + } + + return ctx; +} + int mlx5e_tc_action_miss_mapping_get(struct mlx5e_priv *priv, struct mlx5_flow_attr *attr, u64 act_miss_cookie, u32 *act_miss_mapping) { - struct mlx5_eswitch *esw = priv->mdev->priv.eswitch; struct mlx5_mapped_obj mapped_obj = {}; + struct mlx5_eswitch *esw; struct mapping_ctx *ctx; int err;

- ctx = esw->offloads.reg_c0_obj_pool; - + ctx = mlx5e_get_priv_obj_mapping(priv); mapped_obj.type = MLX5_MAPPED_OBJ_ACT_MISS; mapped_obj.act_miss_cookie = act_miss_cookie; err = mapping_add(ctx, &mapped_obj, act_miss_mapping); if (err) return err;

+ if (!is_mdev_switchdev_mode(priv->mdev)) + return 0; + + esw = priv->mdev->priv.eswitch; attr->act_id_restore_rule = esw_add_restore_rule(esw, *act_miss_mapping); if (IS_ERR(attr->act_id_restore_rule)) goto err_rule; @@ -5823,10 +5844,9 @@ int mlx5e_tc_action_miss_mapping_get(struct mlx5e_priv *priv, struct mlx5_flow_a void mlx5e_tc_action_miss_mapping_put(struct mlx5e_priv *priv, struct mlx5_flow_attr *attr, u32 act_miss_mapping) { - struct mlx5_eswitch *esw = priv->mdev->priv.eswitch; - struct mapping_ctx *ctx; + struct mapping_ctx *ctx = mlx5e_get_priv_obj_mapping(priv);

- ctx = esw->offloads.reg_c0_obj_pool; - mlx5_del_flow_rules(attr->act_id_restore_rule); + if (is_mdev_switchdev_mode(priv->mdev)) + mlx5_del_flow_rules(attr->act_id_restore_rule); mapping_remove(ctx, act_miss_mapping); }

From: Maher Sanalla msanalla@nvidia.com

[ Upstream commit 0a431418f685e100c45ff150efaf4a5afa6f1982 ]

This reverts commit 606e6a72e29dff9e3341c4cc9b554420e4793f401 which exposes the vnic diagnostic counters via debugfs. Instead, The upcoming series will expose the same counters through devlink health reporter.

Signed-off-by: Maher Sanalla msanalla@nvidia.com Signed-off-by: Saeed Mahameed saeedm@nvidia.com Stable-dep-of: 8c253dfc89ef ("net/mlx5: E-switch, Devcom, sync devcom events and devcom comp register") Signed-off-by: Sasha Levin sashal@kernel.org --- .../net/ethernet/mellanox/mlx5/core/Makefile | 2 +- .../ethernet/mellanox/mlx5/core/esw/debugfs.c | 182 ------------------ .../net/ethernet/mellanox/mlx5/core/eswitch.c | 6 - .../net/ethernet/mellanox/mlx5/core/eswitch.h | 5 - .../mellanox/mlx5/core/eswitch_offloads.c | 3 - 5 files changed, 1 insertion(+), 197 deletions(-) delete mode 100644 drivers/net/ethernet/mellanox/mlx5/core/esw/debugfs.c

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Makefile b/drivers/net/ethernet/mellanox/mlx5/core/Makefile index 8d4e25cc54ea3..78755dfeaccea 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/Makefile +++ b/drivers/net/ethernet/mellanox/mlx5/core/Makefile @@ -69,7 +69,7 @@ mlx5_core-$(CONFIG_MLX5_TC_SAMPLE) += en/tc/sample.o # mlx5_core-$(CONFIG_MLX5_ESWITCH) += eswitch.o eswitch_offloads.o eswitch_offloads_termtbl.o \ ecpf.o rdma.o esw/legacy.o \ - esw/debugfs.o esw/devlink_port.o esw/vporttbl.o esw/qos.o + esw/devlink_port.o esw/vporttbl.o esw/qos.o

mlx5_core-$(CONFIG_MLX5_ESWITCH) += esw/acl/helper.o \ esw/acl/egress_lgcy.o esw/acl/egress_ofld.o \ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/debugfs.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/debugfs.c deleted file mode 100644 index 2db13c71e88cd..0000000000000 --- a/drivers/net/ethernet/mellanox/mlx5/core/esw/debugfs.c +++ /dev/null @@ -1,182 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB -/* Copyright (c) 2022, NVIDIA CORPORATION & AFFILIATES. All rights reserved. */ - -#include <linux/debugfs.h> -#include "eswitch.h" - -enum vnic_diag_counter { - MLX5_VNIC_DIAG_TOTAL_Q_UNDER_PROCESSOR_HANDLE, - MLX5_VNIC_DIAG_SEND_QUEUE_PRIORITY_UPDATE_FLOW, - MLX5_VNIC_DIAG_COMP_EQ_OVERRUN, - MLX5_VNIC_DIAG_ASYNC_EQ_OVERRUN, - MLX5_VNIC_DIAG_CQ_OVERRUN, - MLX5_VNIC_DIAG_INVALID_COMMAND, - MLX5_VNIC_DIAG_QOUTA_EXCEEDED_COMMAND, -}; - -static int mlx5_esw_query_vnic_diag(struct mlx5_vport *vport, enum vnic_diag_counter counter, - u32 *val) -{ - u32 out[MLX5_ST_SZ_DW(query_vnic_env_out)] = {}; - u32 in[MLX5_ST_SZ_DW(query_vnic_env_in)] = {}; - struct mlx5_core_dev *dev = vport->dev; - u16 vport_num = vport->vport; - void *vnic_diag_out; - int err; - - MLX5_SET(query_vnic_env_in, in, opcode, MLX5_CMD_OP_QUERY_VNIC_ENV); - MLX5_SET(query_vnic_env_in, in, vport_number, vport_num); - if (!mlx5_esw_is_manager_vport(dev->priv.eswitch, vport_num)) - MLX5_SET(query_vnic_env_in, in, other_vport, 1); - - err = mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out)); - if (err) - return err; - - vnic_diag_out = MLX5_ADDR_OF(query_vnic_env_out, out, vport_env); - switch (counter) { - case MLX5_VNIC_DIAG_TOTAL_Q_UNDER_PROCESSOR_HANDLE: - *val = MLX5_GET(vnic_diagnostic_statistics, vnic_diag_out, total_error_queues); - break; - case MLX5_VNIC_DIAG_SEND_QUEUE_PRIORITY_UPDATE_FLOW: - *val = MLX5_GET(vnic_diagnostic_statistics, vnic_diag_out, - send_queue_priority_update_flow); - break; - case MLX5_VNIC_DIAG_COMP_EQ_OVERRUN: - *val = MLX5_GET(vnic_diagnostic_statistics, vnic_diag_out, comp_eq_overrun); - break; - case MLX5_VNIC_DIAG_ASYNC_EQ_OVERRUN: - *val = MLX5_GET(vnic_diagnostic_statistics, vnic_diag_out, async_eq_overrun); - break; - case MLX5_VNIC_DIAG_CQ_OVERRUN: - *val = MLX5_GET(vnic_diagnostic_statistics, vnic_diag_out, cq_overrun); - break; - case MLX5_VNIC_DIAG_INVALID_COMMAND: - *val = MLX5_GET(vnic_diagnostic_statistics, vnic_diag_out, invalid_command); - break; - case MLX5_VNIC_DIAG_QOUTA_EXCEEDED_COMMAND: - *val = MLX5_GET(vnic_diagnostic_statistics, vnic_diag_out, quota_exceeded_command); - break; - } - - return 0; -} - -static int __show_vnic_diag(struct seq_file *file, struct mlx5_vport *vport, - enum vnic_diag_counter type) -{ - u32 val = 0; - int ret; - - ret = mlx5_esw_query_vnic_diag(vport, type, &val); - if (ret) - return ret; - - seq_printf(file, "%d\n", val); - return 0; -} - -static int total_q_under_processor_handle_show(struct seq_file *file, void *priv) -{ - return __show_vnic_diag(file, file->private, MLX5_VNIC_DIAG_TOTAL_Q_UNDER_PROCESSOR_HANDLE); -} - -static int send_queue_priority_update_flow_show(struct seq_file *file, void *priv) -{ - return __show_vnic_diag(file, file->private, - MLX5_VNIC_DIAG_SEND_QUEUE_PRIORITY_UPDATE_FLOW); -} - -static int comp_eq_overrun_show(struct seq_file *file, void *priv) -{ - return __show_vnic_diag(file, file->private, MLX5_VNIC_DIAG_COMP_EQ_OVERRUN); -} - -static int async_eq_overrun_show(struct seq_file *file, void *priv) -{ - return __show_vnic_diag(file, file->private, MLX5_VNIC_DIAG_ASYNC_EQ_OVERRUN); -} - -static int cq_overrun_show(struct seq_file *file, void *priv) -{ - return __show_vnic_diag(file, file->private, MLX5_VNIC_DIAG_CQ_OVERRUN); -} - -static int invalid_command_show(struct seq_file *file, void *priv) -{ - return __show_vnic_diag(file, file->private, MLX5_VNIC_DIAG_INVALID_COMMAND); -} - -static int quota_exceeded_command_show(struct seq_file *file, void *priv) -{ - return __show_vnic_diag(file, file->private, MLX5_VNIC_DIAG_QOUTA_EXCEEDED_COMMAND); -} - -DEFINE_SHOW_ATTRIBUTE(total_q_under_processor_handle); -DEFINE_SHOW_ATTRIBUTE(send_queue_priority_update_flow); -DEFINE_SHOW_ATTRIBUTE(comp_eq_overrun); -DEFINE_SHOW_ATTRIBUTE(async_eq_overrun); -DEFINE_SHOW_ATTRIBUTE(cq_overrun); -DEFINE_SHOW_ATTRIBUTE(invalid_command); -DEFINE_SHOW_ATTRIBUTE(quota_exceeded_command); - -void mlx5_esw_vport_debugfs_destroy(struct mlx5_eswitch *esw, u16 vport_num) -{ - struct mlx5_vport *vport = mlx5_eswitch_get_vport(esw, vport_num); - - debugfs_remove_recursive(vport->dbgfs); - vport->dbgfs = NULL; -} - -/* vnic diag dir name is "pf", "ecpf" or "{vf/sf}_xxxx" */ -#define VNIC_DIAG_DIR_NAME_MAX_LEN 8 - -void mlx5_esw_vport_debugfs_create(struct mlx5_eswitch *esw, u16 vport_num, bool is_sf, u16 sf_num) -{ - struct mlx5_vport *vport = mlx5_eswitch_get_vport(esw, vport_num); - struct dentry *vnic_diag; - char dir_name[VNIC_DIAG_DIR_NAME_MAX_LEN]; - int err; - - if (!MLX5_CAP_GEN(esw->dev, vport_group_manager)) - return; - - if (vport_num == MLX5_VPORT_PF) { - strcpy(dir_name, "pf"); - } else if (vport_num == MLX5_VPORT_ECPF) { - strcpy(dir_name, "ecpf"); - } else { - err = snprintf(dir_name, VNIC_DIAG_DIR_NAME_MAX_LEN, "%s_%d", is_sf ? "sf" : "vf", - is_sf ? sf_num : vport_num - MLX5_VPORT_FIRST_VF); - if (WARN_ON(err < 0)) - return; - } - - vport->dbgfs = debugfs_create_dir(dir_name, esw->dbgfs); - vnic_diag = debugfs_create_dir("vnic_diag", vport->dbgfs); - - if (MLX5_CAP_GEN(esw->dev, vnic_env_queue_counters)) { - debugfs_create_file("total_q_under_processor_handle", 0444, vnic_diag, vport, - &total_q_under_processor_handle_fops); - debugfs_create_file("send_queue_priority_update_flow", 0444, vnic_diag, vport, - &send_queue_priority_update_flow_fops); - } - - if (MLX5_CAP_GEN(esw->dev, eq_overrun_count)) { - debugfs_create_file("comp_eq_overrun", 0444, vnic_diag, vport, - &comp_eq_overrun_fops); - debugfs_create_file("async_eq_overrun", 0444, vnic_diag, vport, - &async_eq_overrun_fops); - } - - if (MLX5_CAP_GEN(esw->dev, vnic_env_cq_overrun)) - debugfs_create_file("cq_overrun", 0444, vnic_diag, vport, &cq_overrun_fops); - - if (MLX5_CAP_GEN(esw->dev, invalid_command_count)) - debugfs_create_file("invalid_command", 0444, vnic_diag, vport, - &invalid_command_fops); - - if (MLX5_CAP_GEN(esw->dev, quota_exceeded_count)) - debugfs_create_file("quota_exceeded_command", 0444, vnic_diag, vport, - &quota_exceeded_command_fops); -} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c index 19fed514fc173..bb2720a23a501 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c @@ -36,7 +36,6 @@ #include <linux/mlx5/vport.h> #include <linux/mlx5/fs.h> #include <linux/mlx5/mpfs.h> -#include <linux/debugfs.h> #include "esw/acl/lgcy.h" #include "esw/legacy.h" #include "esw/qos.h" @@ -1056,7 +1055,6 @@ int mlx5_eswitch_load_vport(struct mlx5_eswitch *esw, u16 vport_num, if (err) return err;

- mlx5_esw_vport_debugfs_create(esw, vport_num, false, 0); err = esw_offloads_load_rep(esw, vport_num); if (err) goto err_rep; @@ -1064,7 +1062,6 @@ int mlx5_eswitch_load_vport(struct mlx5_eswitch *esw, u16 vport_num, return err;

err_rep: - mlx5_esw_vport_debugfs_destroy(esw, vport_num); mlx5_esw_vport_disable(esw, vport_num); return err; } @@ -1072,7 +1069,6 @@ int mlx5_eswitch_load_vport(struct mlx5_eswitch *esw, u16 vport_num, void mlx5_eswitch_unload_vport(struct mlx5_eswitch *esw, u16 vport_num) { esw_offloads_unload_rep(esw, vport_num); - mlx5_esw_vport_debugfs_destroy(esw, vport_num); mlx5_esw_vport_disable(esw, vport_num); }

@@ -1672,7 +1668,6 @@ int mlx5_eswitch_init(struct mlx5_core_dev *dev) dev->priv.eswitch = esw; BLOCKING_INIT_NOTIFIER_HEAD(&esw->n_head);

- esw->dbgfs = debugfs_create_dir("esw", mlx5_debugfs_get_dev_root(esw->dev)); esw_info(dev, "Total vports %d, per vport: max uc(%d) max mc(%d)\n", esw->total_vports, @@ -1696,7 +1691,6 @@ void mlx5_eswitch_cleanup(struct mlx5_eswitch *esw)

esw_info(esw->dev, "cleanup\n");

- debugfs_remove_recursive(esw->dbgfs); esw->dev->priv.eswitch = NULL; destroy_workqueue(esw->work_queue); WARN_ON(refcount_read(&esw->qos.refcnt)); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h index c8c12d1672f99..31876db3c7641 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h @@ -195,7 +195,6 @@ struct mlx5_vport { enum mlx5_eswitch_vport_event enabled_events; int index; struct devlink_port *dl_port; - struct dentry *dbgfs; };

struct mlx5_esw_indir_table; @@ -342,7 +341,6 @@ struct mlx5_eswitch { u32 large_group_num; } params; struct blocking_notifier_head n_head; - struct dentry *dbgfs; };

void esw_offloads_disable(struct mlx5_eswitch *esw); @@ -705,9 +703,6 @@ int mlx5_esw_offloads_devlink_port_register(struct mlx5_eswitch *esw, u16 vport_ void mlx5_esw_offloads_devlink_port_unregister(struct mlx5_eswitch *esw, u16 vport_num); struct devlink_port *mlx5_esw_offloads_devlink_port(struct mlx5_eswitch *esw, u16 vport_num);

-void mlx5_esw_vport_debugfs_create(struct mlx5_eswitch *esw, u16 vport_num, bool is_sf, u16 sf_num); -void mlx5_esw_vport_debugfs_destroy(struct mlx5_eswitch *esw, u16 vport_num); - int mlx5_esw_devlink_sf_port_register(struct mlx5_eswitch *esw, struct devlink_port *dl_port, u16 vport_num, u32 controller, u32 sfnum); void mlx5_esw_devlink_sf_port_unregister(struct mlx5_eswitch *esw, u16 vport_num); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c index 590df9bf39a56..727b30f3a229a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c @@ -3777,14 +3777,12 @@ int mlx5_esw_offloads_sf_vport_enable(struct mlx5_eswitch *esw, struct devlink_p if (err) goto devlink_err;

- mlx5_esw_vport_debugfs_create(esw, vport_num, true, sfnum); err = mlx5_esw_offloads_rep_load(esw, vport_num); if (err) goto rep_err; return 0;

rep_err: - mlx5_esw_vport_debugfs_destroy(esw, vport_num); mlx5_esw_devlink_sf_port_unregister(esw, vport_num); devlink_err: mlx5_esw_vport_disable(esw, vport_num); @@ -3794,7 +3792,6 @@ int mlx5_esw_offloads_sf_vport_enable(struct mlx5_eswitch *esw, struct devlink_p void mlx5_esw_offloads_sf_vport_disable(struct mlx5_eswitch *esw, u16 vport_num) { mlx5_esw_offloads_rep_unload(esw, vport_num); - mlx5_esw_vport_debugfs_destroy(esw, vport_num); mlx5_esw_devlink_sf_port_unregister(esw, vport_num); mlx5_esw_vport_disable(esw, vport_num); }

From: Henning Schild henning.schild@siemens.com

[ Upstream commit 3002b8642f016d7fe3ff56240dacea1075f6b877 ]

In fact the device with chip id 0xD283 is called NCT6126D, and that is the chip id the Nuvoton code was written for. Correct that name to avoid confusion, because a NCT6116D in fact exists as well but has another chip id, and is currently not supported.

The look at the spec also revealed that GPIO group7 in fact has 8 pins, so correct the pin count in that group as well.

Fixes: d0918a84aff0 ("gpio-f7188x: Add GPIO support for Nuvoton NCT6116") Reported-by: Xing Tong Wu xingtong.wu@siemens.com Signed-off-by: Henning Schild henning.schild@siemens.com Acked-by: Simon Guinot simon.guinot@sequanux.org Signed-off-by: Bartosz Golaszewski bartosz.golaszewski@linaro.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/gpio/Kconfig | 2 +- drivers/gpio/gpio-f7188x.c | 28 ++++++++++++++-------------- 2 files changed, 15 insertions(+), 15 deletions(-)

diff --git a/drivers/gpio/Kconfig b/drivers/gpio/Kconfig index badbe05823180..14b655411aa0a 100644 --- a/drivers/gpio/Kconfig +++ b/drivers/gpio/Kconfig @@ -879,7 +879,7 @@ config GPIO_F7188X help This option enables support for GPIOs found on Fintek Super-I/O chips F71869, F71869A, F71882FG, F71889F and F81866. - As well as Nuvoton Super-I/O chip NCT6116D. + As well as Nuvoton Super-I/O chip NCT6126D.

To compile this driver as a module, choose M here: the module will be called f7188x-gpio. diff --git a/drivers/gpio/gpio-f7188x.c b/drivers/gpio/gpio-f7188x.c index 9effa7769bef5..f54ca5a1775ea 100644 --- a/drivers/gpio/gpio-f7188x.c +++ b/drivers/gpio/gpio-f7188x.c @@ -48,7 +48,7 @@ /* * Nuvoton devices. */ -#define SIO_NCT6116D_ID 0xD283 /* NCT6116D chipset ID */ +#define SIO_NCT6126D_ID 0xD283 /* NCT6126D chipset ID */

#define SIO_LD_GPIO_NUVOTON 0x07 /* GPIO logical device */

@@ -62,7 +62,7 @@ enum chips { f81866, f81804, f81865, - nct6116d, + nct6126d, };

static const char * const f7188x_names[] = { @@ -74,7 +74,7 @@ static const char * const f7188x_names[] = { "f81866", "f81804", "f81865", - "nct6116d", + "nct6126d", };

struct f7188x_sio { @@ -187,8 +187,8 @@ static int f7188x_gpio_set_config(struct gpio_chip *chip, unsigned offset, /* Output mode register (0:open drain 1:push-pull). */ #define f7188x_gpio_out_mode(base) ((base) + 3)

-#define f7188x_gpio_dir_invert(type) ((type) == nct6116d) -#define f7188x_gpio_data_single(type) ((type) == nct6116d) +#define f7188x_gpio_dir_invert(type) ((type) == nct6126d) +#define f7188x_gpio_data_single(type) ((type) == nct6126d)

static struct f7188x_gpio_bank f71869_gpio_bank[] = { F7188X_GPIO_BANK(0, 6, 0xF0, DRVNAME "-0"), @@ -274,7 +274,7 @@ static struct f7188x_gpio_bank f81865_gpio_bank[] = { F7188X_GPIO_BANK(60, 5, 0x90, DRVNAME "-6"), };

-static struct f7188x_gpio_bank nct6116d_gpio_bank[] = { +static struct f7188x_gpio_bank nct6126d_gpio_bank[] = { F7188X_GPIO_BANK(0, 8, 0xE0, DRVNAME "-0"), F7188X_GPIO_BANK(10, 8, 0xE4, DRVNAME "-1"), F7188X_GPIO_BANK(20, 8, 0xE8, DRVNAME "-2"), @@ -282,7 +282,7 @@ static struct f7188x_gpio_bank nct6116d_gpio_bank[] = { F7188X_GPIO_BANK(40, 8, 0xF0, DRVNAME "-4"), F7188X_GPIO_BANK(50, 8, 0xF4, DRVNAME "-5"), F7188X_GPIO_BANK(60, 8, 0xF8, DRVNAME "-6"), - F7188X_GPIO_BANK(70, 1, 0xFC, DRVNAME "-7"), + F7188X_GPIO_BANK(70, 8, 0xFC, DRVNAME "-7"), };

static int f7188x_gpio_get_direction(struct gpio_chip *chip, unsigned offset) @@ -490,9 +490,9 @@ static int f7188x_gpio_probe(struct platform_device *pdev) data->nr_bank = ARRAY_SIZE(f81865_gpio_bank); data->bank = f81865_gpio_bank; break; - case nct6116d: - data->nr_bank = ARRAY_SIZE(nct6116d_gpio_bank); - data->bank = nct6116d_gpio_bank; + case nct6126d: + data->nr_bank = ARRAY_SIZE(nct6126d_gpio_bank); + data->bank = nct6126d_gpio_bank; break; default: return -ENODEV; @@ -559,9 +559,9 @@ static int __init f7188x_find(int addr, struct f7188x_sio *sio) case SIO_F81865_ID: sio->type = f81865; break; - case SIO_NCT6116D_ID: + case SIO_NCT6126D_ID: sio->device = SIO_LD_GPIO_NUVOTON; - sio->type = nct6116d; + sio->type = nct6126d; break; default: pr_info("Unsupported Fintek device 0x%04x\n", devid); @@ -569,7 +569,7 @@ static int __init f7188x_find(int addr, struct f7188x_sio *sio) }

/* double check manufacturer where possible */ - if (sio->type != nct6116d) { + if (sio->type != nct6126d) { manid = superio_inw(addr, SIO_FINTEK_MANID); if (manid != SIO_FINTEK_ID) { pr_debug("Not a Fintek device at 0x%08x\n", addr); @@ -581,7 +581,7 @@ static int __init f7188x_find(int addr, struct f7188x_sio *sio) err = 0;

pr_info("Found %s at %#x\n", f7188x_names[sio->type], (unsigned int)addr); - if (sio->type != nct6116d) + if (sio->type != nct6126d) pr_info(" revision %d\n", superio_inb(addr, SIO_FINTEK_DEVREV));

err:

From: John Fastabend john.fastabend@gmail.com

[ Upstream commit 29173d07f79883ac94f5570294f98af3d4287382 ]

Sk_buffs are fed into sockmap verdict programs either from a strparser (when the user might want to decide how framing of skb is done by attaching another parser program) or directly through tcp_read_sock. The tcp_read_sock is the preferred method for performance when the BPF logic is a stream parser.

The flow for Cilium's common use case with a stream parser is,

tcp_read_sock() sk_psock_verdict_recv ret = bpf_prog_run_pin_on_cpu() sk_psock_verdict_apply(sock, skb, ret) // if system is under memory pressure or app is slow we may // need to queue skb. Do this queuing through ingress_skb and // then kick timer to wake up handler skb_queue_tail(ingress_skb, skb) schedule_work(work);

The work queue is wired up to sk_psock_backlog(). This will then walk the ingress_skb skb list that holds our sk_buffs that could not be handled, but should be OK to run at some later point. However, its possible that the workqueue doing this work still hits an error when sending the skb. When this happens the skbuff is requeued on a temporary 'state' struct kept with the workqueue. This is necessary because its possible to partially send an skbuff before hitting an error and we need to know how and where to restart when the workqueue runs next.

Now for the trouble, we don't rekick the workqueue. This can cause a stall where the skbuff we just cached on the state variable might never be sent. This happens when its the last packet in a flow and no further packets come along that would cause the system to kick the workqueue from that side.

To fix we could do simple schedule_work(), but while under memory pressure it makes sense to back off some instead of continue to retry repeatedly. So instead to fix convert schedule_work to schedule_delayed_work and add backoff logic to reschedule from backlog queue on errors. Its not obvious though what a good backoff is so use '1'.

To test we observed some flakes whil running NGINX compliance test with sockmap we attributed these failed test to this bug and subsequent issue.

From on list discussion. This commit

bec217197b41("skmsg: Schedule psock work if the cached skb exists on the psock")

was intended to address similar race, but had a couple cases it missed. Most obvious it only accounted for receiving traffic on the local socket so if redirecting into another socket we could still get an sk_buff stuck here. Next it missed the case where copied=0 in the recv() handler and then we wouldn't kick the scheduler. Also its sub-optimal to require userspace to kick the internal mechanisms of sockmap to wake it up and copy data to user. It results in an extra syscall and requires the app to actual handle the EAGAIN correctly.

Fixes: 04919bed948dc ("tcp: Introduce tcp_read_skb()") Signed-off-by: John Fastabend john.fastabend@gmail.com Signed-off-by: Daniel Borkmann daniel@iogearbox.net Tested-by: William Findlay will@isovalent.com Reviewed-by: Jakub Sitnicki jakub@cloudflare.com Link: https://lore.kernel.org/bpf/20230523025618.113937-3-john.fastabend@gmail.com Signed-off-by: Sasha Levin sashal@kernel.org --- include/linux/skmsg.h | 2 +- net/core/skmsg.c | 21 ++++++++++++++------- net/core/sock_map.c | 3 ++- 3 files changed, 17 insertions(+), 9 deletions(-)

diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h index 84f787416a54d..904ff9a32ad61 100644 --- a/include/linux/skmsg.h +++ b/include/linux/skmsg.h @@ -105,7 +105,7 @@ struct sk_psock { struct proto *sk_proto; struct mutex work_mutex; struct sk_psock_work_state work_state; - struct work_struct work; + struct delayed_work work; struct rcu_work rwork; };

diff --git a/net/core/skmsg.c b/net/core/skmsg.c index 4a3dc8d272957..0a9ee2acac0bb 100644 --- a/net/core/skmsg.c +++ b/net/core/skmsg.c @@ -482,7 +482,7 @@ int sk_msg_recvmsg(struct sock *sk, struct sk_psock *psock, struct msghdr *msg, } out: if (psock->work_state.skb && copied > 0) - schedule_work(&psock->work); + schedule_delayed_work(&psock->work, 0); return copied; } EXPORT_SYMBOL_GPL(sk_msg_recvmsg); @@ -640,7 +640,8 @@ static void sk_psock_skb_state(struct sk_psock *psock,

static void sk_psock_backlog(struct work_struct *work) { - struct sk_psock *psock = container_of(work, struct sk_psock, work); + struct delayed_work *dwork = to_delayed_work(work); + struct sk_psock *psock = container_of(dwork, struct sk_psock, work); struct sk_psock_work_state *state = &psock->work_state; struct sk_buff *skb = NULL; bool ingress; @@ -680,6 +681,12 @@ static void sk_psock_backlog(struct work_struct *work) if (ret == -EAGAIN) { sk_psock_skb_state(psock, state, skb, len, off); + + /* Delay slightly to prioritize any + * other work that might be here. + */ + if (sk_psock_test_state(psock, SK_PSOCK_TX_ENABLED)) + schedule_delayed_work(&psock->work, 1); goto end; } /* Hard errors break pipe and stop xmit. */ @@ -734,7 +741,7 @@ struct sk_psock *sk_psock_init(struct sock *sk, int node) INIT_LIST_HEAD(&psock->link); spin_lock_init(&psock->link_lock);

- INIT_WORK(&psock->work, sk_psock_backlog); + INIT_DELAYED_WORK(&psock->work, sk_psock_backlog); mutex_init(&psock->work_mutex); INIT_LIST_HEAD(&psock->ingress_msg); spin_lock_init(&psock->ingress_lock); @@ -823,7 +830,7 @@ static void sk_psock_destroy(struct work_struct *work)

sk_psock_done_strp(psock);

- cancel_work_sync(&psock->work); + cancel_delayed_work_sync(&psock->work); mutex_destroy(&psock->work_mutex);

psock_progs_drop(&psock->progs); @@ -938,7 +945,7 @@ static int sk_psock_skb_redirect(struct sk_psock *from, struct sk_buff *skb) }

skb_queue_tail(&psock_other->ingress_skb, skb); - schedule_work(&psock_other->work); + schedule_delayed_work(&psock_other->work, 0); spin_unlock_bh(&psock_other->ingress_lock); return 0; } @@ -1018,7 +1025,7 @@ static int sk_psock_verdict_apply(struct sk_psock *psock, struct sk_buff *skb, spin_lock_bh(&psock->ingress_lock); if (sk_psock_test_state(psock, SK_PSOCK_TX_ENABLED)) { skb_queue_tail(&psock->ingress_skb, skb); - schedule_work(&psock->work); + schedule_delayed_work(&psock->work, 0); err = 0; } spin_unlock_bh(&psock->ingress_lock); @@ -1049,7 +1056,7 @@ static void sk_psock_write_space(struct sock *sk) psock = sk_psock(sk); if (likely(psock)) { if (sk_psock_test_state(psock, SK_PSOCK_TX_ENABLED)) - schedule_work(&psock->work); + schedule_delayed_work(&psock->work, 0); write_space = psock->saved_write_space; } rcu_read_unlock(); diff --git a/net/core/sock_map.c b/net/core/sock_map.c index a055139f410e2..08851511294c0 100644 --- a/net/core/sock_map.c +++ b/net/core/sock_map.c @@ -1624,9 +1624,10 @@ void sock_map_close(struct sock *sk, long timeout) rcu_read_unlock(); sk_psock_stop(psock); release_sock(sk); - cancel_work_sync(&psock->work); + cancel_delayed_work_sync(&psock->work); sk_psock_put(sk, psock); } + /* Make sure we do not recurse. This is a bug. * Leak the socket instead of crashing on a stack overflow. */

From: John Fastabend john.fastabend@gmail.com

[ Upstream commit 405df89dd52cbcd69a3cd7d9a10d64de38f854b2 ]

We noticed some rare sk_buffs were stepping past the queue when system was under memory pressure. The general theory is to skip enqueueing sk_buffs when its not necessary which is the normal case with a system that is properly provisioned for the task, no memory pressure and enough cpu assigned.

But, if we can't allocate memory due to an ENOMEM error when enqueueing the sk_buff into the sockmap receive queue we push it onto a delayed workqueue to retry later. When a new sk_buff is received we then check if that queue is empty. However, there is a problem with simply checking the queue length. When a sk_buff is being processed from the ingress queue but not yet on the sockmap msg receive queue its possible to also recv a sk_buff through normal path. It will check the ingress queue which is zero and then skip ahead of the pkt being processed.

Previously we used sock lock from both contexts which made the problem harder to hit, but not impossible.

To fix instead of popping the skb from the queue entirely we peek the skb from the queue and do the copy there. This ensures checks to the queue length are non-zero while skb is being processed. Then finally when the entire skb has been copied to user space queue or another socket we pop it off the queue. This way the queue length check allows bypassing the queue only after the list has been completely processed.

To reproduce issue we run NGINX compliance test with sockmap running and observe some flakes in our testing that we attributed to this issue.

Fixes: 04919bed948dc ("tcp: Introduce tcp_read_skb()") Suggested-by: Jakub Sitnicki jakub@cloudflare.com Signed-off-by: John Fastabend john.fastabend@gmail.com Signed-off-by: Daniel Borkmann daniel@iogearbox.net Tested-by: William Findlay will@isovalent.com Reviewed-by: Jakub Sitnicki jakub@cloudflare.com Link: https://lore.kernel.org/bpf/20230523025618.113937-5-john.fastabend@gmail.com Signed-off-by: Sasha Levin sashal@kernel.org --- include/linux/skmsg.h | 1 - net/core/skmsg.c | 32 ++++++++------------------------ 2 files changed, 8 insertions(+), 25 deletions(-)

diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h index 904ff9a32ad61..054d7911bfc9f 100644 --- a/include/linux/skmsg.h +++ b/include/linux/skmsg.h @@ -71,7 +71,6 @@ struct sk_psock_link { };

struct sk_psock_work_state { - struct sk_buff *skb; u32 len; u32 off; }; diff --git a/net/core/skmsg.c b/net/core/skmsg.c index 76ff15f8bb06e..bcd45a99a3db3 100644 --- a/net/core/skmsg.c +++ b/net/core/skmsg.c @@ -622,16 +622,12 @@ static int sk_psock_handle_skb(struct sk_psock *psock, struct sk_buff *skb,

static void sk_psock_skb_state(struct sk_psock *psock, struct sk_psock_work_state *state, - struct sk_buff *skb, int len, int off) { spin_lock_bh(&psock->ingress_lock); if (sk_psock_test_state(psock, SK_PSOCK_TX_ENABLED)) { - state->skb = skb; state->len = len; state->off = off; - } else { - sock_drop(psock->sk, skb); } spin_unlock_bh(&psock->ingress_lock); } @@ -642,23 +638,17 @@ static void sk_psock_backlog(struct work_struct *work) struct sk_psock *psock = container_of(dwork, struct sk_psock, work); struct sk_psock_work_state *state = &psock->work_state; struct sk_buff *skb = NULL; + u32 len = 0, off = 0; bool ingress; - u32 len, off; int ret;

mutex_lock(&psock->work_mutex); - if (unlikely(state->skb)) { - spin_lock_bh(&psock->ingress_lock); - skb = state->skb; + if (unlikely(state->len)) { len = state->len; off = state->off; - state->skb = NULL; - spin_unlock_bh(&psock->ingress_lock); } - if (skb) - goto start;

- while ((skb = skb_dequeue(&psock->ingress_skb))) { + while ((skb = skb_peek(&psock->ingress_skb))) { len = skb->len; off = 0; if (skb_bpf_strparser(skb)) { @@ -667,7 +657,6 @@ static void sk_psock_backlog(struct work_struct *work) off = stm->offset; len = stm->full_len; } -start: ingress = skb_bpf_ingress(skb); skb_bpf_redirect_clear(skb); do { @@ -677,8 +666,7 @@ static void sk_psock_backlog(struct work_struct *work) len, ingress); if (ret <= 0) { if (ret == -EAGAIN) { - sk_psock_skb_state(psock, state, skb, - len, off); + sk_psock_skb_state(psock, state, len, off);

/* Delay slightly to prioritize any * other work that might be here. @@ -690,15 +678,16 @@ static void sk_psock_backlog(struct work_struct *work) /* Hard errors break pipe and stop xmit. */ sk_psock_report_error(psock, ret ? -ret : EPIPE); sk_psock_clear_state(psock, SK_PSOCK_TX_ENABLED); - sock_drop(psock->sk, skb); goto end; } off += ret; len -= ret; } while (len);

- if (!ingress) + skb = skb_dequeue(&psock->ingress_skb); + if (!ingress) { kfree_skb(skb); + } } end: mutex_unlock(&psock->work_mutex); @@ -791,11 +780,6 @@ static void __sk_psock_zap_ingress(struct sk_psock *psock) skb_bpf_redirect_clear(skb); sock_drop(psock->sk, skb); } - kfree_skb(psock->work_state.skb); - /* We null the skb here to ensure that calls to sk_psock_backlog - * do not pick up the free'd skb. - */ - psock->work_state.skb = NULL; __sk_psock_purge_ingress_msg(psock); }

@@ -814,7 +798,6 @@ void sk_psock_stop(struct sk_psock *psock) spin_lock_bh(&psock->ingress_lock); sk_psock_clear_state(psock, SK_PSOCK_TX_ENABLED); sk_psock_cork_free(psock); - __sk_psock_zap_ingress(psock); spin_unlock_bh(&psock->ingress_lock); }

@@ -829,6 +812,7 @@ static void sk_psock_destroy(struct work_struct *work) sk_psock_done_strp(psock);

cancel_delayed_work_sync(&psock->work); + __sk_psock_zap_ingress(psock); mutex_destroy(&psock->work_mutex);

psock_progs_drop(&psock->progs);

From: John Fastabend john.fastabend@gmail.com

[ Upstream commit ea444185a6bf7da4dd0df1598ee953e4f7174858 ]

A common mechanism to put a TCP socket into the sockmap is to hook the BPF_SOCK_OPS_{ACTIVE_PASSIVE}_ESTABLISHED_CB event with a BPF program that can map the socket info to the correct BPF verdict parser. When the user adds the socket to the map the psock is created and the new ops are assigned to ensure the verdict program will 'see' the sk_buffs as they arrive.

Part of this process hooks the sk_data_ready op with a BPF specific handler to wake up the BPF verdict program when data is ready to read. The logic is simple enough (posted here for easy reading)

static void sk_psock_verdict_data_ready(struct sock *sk) { struct socket *sock = sk->sk_socket;

if (unlikely(!sock || !sock->ops || !sock->ops->read_skb)) return; sock->ops->read_skb(sk, sk_psock_verdict_recv); }

The oversight here is sk->sk_socket is not assigned until the application accepts() the new socket. However, its entirely ok for the peer application to do a connect() followed immediately by sends. The socket on the receiver is sitting on the backlog queue of the listening socket until its accepted and the data is queued up. If the peer never accepts the socket or is slow it will eventually hit data limits and rate limit the session. But, important for BPF sockmap hooks when this data is received TCP stack does the sk_data_ready() call but the read_skb() for this data is never called because sk_socket is missing. The data sits on the sk_receive_queue.

Then once the socket is accepted if we never receive more data from the peer there will be no further sk_data_ready calls and all the data is still on the sk_receive_queue(). Then user calls recvmsg after accept() and for TCP sockets in sockmap we use the tcp_bpf_recvmsg_parser() handler. The handler checks for data in the sk_msg ingress queue expecting that the BPF program has already run from the sk_data_ready hook and enqueued the data as needed. So we are stuck.

To fix do an unlikely check in recvmsg handler for data on the sk_receive_queue and if it exists wake up data_ready. We have the sock locked in both read_skb and recvmsg so should avoid having multiple runners.

Fixes: 04919bed948dc ("tcp: Introduce tcp_read_skb()") Signed-off-by: John Fastabend john.fastabend@gmail.com Signed-off-by: Daniel Borkmann daniel@iogearbox.net Reviewed-by: Jakub Sitnicki jakub@cloudflare.com Link: https://lore.kernel.org/bpf/20230523025618.113937-7-john.fastabend@gmail.com Signed-off-by: Sasha Levin sashal@kernel.org --- net/ipv4/tcp_bpf.c | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+)

diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c index 73c13642d47f6..01dd76be1a584 100644 --- a/net/ipv4/tcp_bpf.c +++ b/net/ipv4/tcp_bpf.c @@ -212,6 +212,26 @@ static int tcp_bpf_recvmsg_parser(struct sock *sk, return tcp_recvmsg(sk, msg, len, flags, addr_len);

lock_sock(sk); + + /* We may have received data on the sk_receive_queue pre-accept and + * then we can not use read_skb in this context because we haven't + * assigned a sk_socket yet so have no link to the ops. The work-around + * is to check the sk_receive_queue and in these cases read skbs off + * queue again. The read_skb hook is not running at this point because + * of lock_sock so we avoid having multiple runners in read_skb. + */ + if (unlikely(!skb_queue_empty(&sk->sk_receive_queue))) { + tcp_data_ready(sk); + /* This handles the ENOMEM errors if we both receive data + * pre accept and are already under memory pressure. At least + * let user know to retry. + */ + if (unlikely(!skb_queue_empty(&sk->sk_receive_queue))) { + copied = -EAGAIN; + goto out; + } + } + msg_bytes_ready: copied = sk_msg_recvmsg(sk, psock, msg, len, flags); /* The typical case for EFAULT is the socket was gracefully

From: John Fastabend john.fastabend@gmail.com

[ Upstream commit e5c6de5fa025882babf89cecbed80acf49b987fa ]

The read_skb() logic is incrementing the tcp->copied_seq which is used for among other things calculating how many outstanding bytes can be read by the application. This results in application errors, if the application does an ioctl(FIONREAD) we return zero because this is calculated from the copied_seq value.

To fix this we move tcp->copied_seq accounting into the recv handler so that we update these when the recvmsg() hook is called and data is in fact copied into user buffers. This gives an accurate FIONREAD value as expected and improves ACK handling. Before we were calling the tcp_rcv_space_adjust() which would update 'number of bytes copied to user in last RTT' which is wrong for programs returning SK_PASS. The bytes are only copied to the user when recvmsg is handled.

Doing the fix for recvmsg is straightforward, but fixing redirect and SK_DROP pkts is a bit tricker. Build a tcp_psock_eat() helper and then call this from skmsg handlers. This fixes another issue where a broken socket with a BPF program doing a resubmit could hang the receiver. This happened because although read_skb() consumed the skb through sock_drop() it did not update the copied_seq. Now if a single reccv socket is redirecting to many sockets (for example for lb) the receiver sk will be hung even though we might expect it to continue. The hang comes from not updating the copied_seq numbers and memory pressure resulting from that.

We have a slight layer problem of calling tcp_eat_skb even if its not a TCP socket. To fix we could refactor and create per type receiver handlers. I decided this is more work than we want in the fix and we already have some small tweaks depending on caller that use the helper skb_bpf_strparser(). So we extend that a bit and always set the strparser bit when it is in use and then we can gate the seq_copied updates on this.

Fixes: 04919bed948dc ("tcp: Introduce tcp_read_skb()") Signed-off-by: John Fastabend john.fastabend@gmail.com Signed-off-by: Daniel Borkmann daniel@iogearbox.net Reviewed-by: Jakub Sitnicki jakub@cloudflare.com Link: https://lore.kernel.org/bpf/20230523025618.113937-9-john.fastabend@gmail.com Signed-off-by: Sasha Levin sashal@kernel.org --- include/net/tcp.h | 10 ++++++++++ net/core/skmsg.c | 15 +++++++-------- net/ipv4/tcp.c | 10 +--------- net/ipv4/tcp_bpf.c | 28 +++++++++++++++++++++++++++- 4 files changed, 45 insertions(+), 18 deletions(-)

diff --git a/include/net/tcp.h b/include/net/tcp.h index db9f828e9d1ee..76bf0a11bdc77 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -1467,6 +1467,8 @@ static inline void tcp_adjust_rcv_ssthresh(struct sock *sk) }

void tcp_cleanup_rbuf(struct sock *sk, int copied); +void __tcp_cleanup_rbuf(struct sock *sk, int copied); +

/* We provision sk_rcvbuf around 200% of sk_rcvlowat. * If 87.5 % (7/8) of the space has been consumed, we want to override @@ -2323,6 +2325,14 @@ int tcp_bpf_update_proto(struct sock *sk, struct sk_psock *psock, bool restore); void tcp_bpf_clone(const struct sock *sk, struct sock *newsk); #endif /* CONFIG_BPF_SYSCALL */

+#ifdef CONFIG_INET +void tcp_eat_skb(struct sock *sk, struct sk_buff *skb); +#else +static inline void tcp_eat_skb(struct sock *sk, struct sk_buff *skb) +{ +} +#endif + int tcp_bpf_sendmsg_redir(struct sock *sk, bool ingress, struct sk_msg *msg, u32 bytes, int flags); #endif /* CONFIG_NET_SOCK_MSG */ diff --git a/net/core/skmsg.c b/net/core/skmsg.c index 08be5f409fb89..a9060e1f0e437 100644 --- a/net/core/skmsg.c +++ b/net/core/skmsg.c @@ -979,10 +979,8 @@ static int sk_psock_verdict_apply(struct sk_psock *psock, struct sk_buff *skb, err = -EIO; sk_other = psock->sk; if (sock_flag(sk_other, SOCK_DEAD) || - !sk_psock_test_state(psock, SK_PSOCK_TX_ENABLED)) { - skb_bpf_redirect_clear(skb); + !sk_psock_test_state(psock, SK_PSOCK_TX_ENABLED)) goto out_free; - }

skb_bpf_set_ingress(skb);

@@ -1011,18 +1009,19 @@ static int sk_psock_verdict_apply(struct sk_psock *psock, struct sk_buff *skb, err = 0; } spin_unlock_bh(&psock->ingress_lock); - if (err < 0) { - skb_bpf_redirect_clear(skb); + if (err < 0) goto out_free; - } } break; case __SK_REDIRECT: + tcp_eat_skb(psock->sk, skb); err = sk_psock_skb_redirect(psock, skb); break; case __SK_DROP: default: out_free: + skb_bpf_redirect_clear(skb); + tcp_eat_skb(psock->sk, skb); sock_drop(psock->sk, skb); }

@@ -1067,8 +1066,7 @@ static void sk_psock_strp_read(struct strparser *strp, struct sk_buff *skb) skb_dst_drop(skb); skb_bpf_redirect_clear(skb); ret = bpf_prog_run_pin_on_cpu(prog, skb); - if (ret == SK_PASS) - skb_bpf_set_strparser(skb); + skb_bpf_set_strparser(skb); ret = sk_psock_map_verd(ret, skb_bpf_redirect_fetch(skb)); skb->sk = NULL; } @@ -1176,6 +1174,7 @@ static int sk_psock_verdict_recv(struct sock *sk, struct sk_buff *skb) psock = sk_psock(sk); if (unlikely(!psock)) { len = 0; + tcp_eat_skb(sk, skb); sock_drop(sk, skb); goto out; } diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 01ea2705deea9..ed63ee8f0d7e3 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -1570,7 +1570,7 @@ static int tcp_peek_sndq(struct sock *sk, struct msghdr *msg, int len) * calculation of whether or not we must ACK for the sake of * a window update. */ -static void __tcp_cleanup_rbuf(struct sock *sk, int copied) +void __tcp_cleanup_rbuf(struct sock *sk, int copied) { struct tcp_sock *tp = tcp_sk(sk); bool time_to_ack = false; @@ -1785,14 +1785,6 @@ int tcp_read_skb(struct sock *sk, skb_read_actor_t recv_actor) break; } } - WRITE_ONCE(tp->copied_seq, seq); - - tcp_rcv_space_adjust(sk); - - /* Clean up data we have read: This will do ACK frames. */ - if (copied > 0) - __tcp_cleanup_rbuf(sk, copied); - return copied; } EXPORT_SYMBOL(tcp_read_skb); diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c index 01dd76be1a584..5f93918c063c7 100644 --- a/net/ipv4/tcp_bpf.c +++ b/net/ipv4/tcp_bpf.c @@ -11,6 +11,24 @@ #include <net/inet_common.h> #include <net/tls.h>

+void tcp_eat_skb(struct sock *sk, struct sk_buff *skb) +{ + struct tcp_sock *tcp; + int copied; + + if (!skb || !skb->len || !sk_is_tcp(sk)) + return; + + if (skb_bpf_strparser(skb)) + return; + + tcp = tcp_sk(sk); + copied = tcp->copied_seq + skb->len; + WRITE_ONCE(tcp->copied_seq, copied); + tcp_rcv_space_adjust(sk); + __tcp_cleanup_rbuf(sk, skb->len); +} + static int bpf_tcp_ingress(struct sock *sk, struct sk_psock *psock, struct sk_msg *msg, u32 apply_bytes, int flags) { @@ -198,8 +216,10 @@ static int tcp_bpf_recvmsg_parser(struct sock *sk, int flags, int *addr_len) { + struct tcp_sock *tcp = tcp_sk(sk); + u32 seq = tcp->copied_seq; struct sk_psock *psock; - int copied; + int copied = 0;

if (unlikely(flags & MSG_ERRQUEUE)) return inet_recv_error(sk, msg, len, addr_len); @@ -244,9 +264,11 @@ static int tcp_bpf_recvmsg_parser(struct sock *sk,

if (is_fin) { copied = 0; + seq++; goto out; } } + seq += copied; if (!copied) { long timeo; int data; @@ -284,6 +306,10 @@ static int tcp_bpf_recvmsg_parser(struct sock *sk, copied = -EAGAIN; } out: + WRITE_ONCE(tcp->copied_seq, seq); + tcp_rcv_space_adjust(sk); + if (copied > 0) + __tcp_cleanup_rbuf(sk, copied); release_sock(sk); sk_psock_put(sk, psock); return copied;

From: Tian Lan tian.lan@twosigma.com

[ Upstream commit 3e94d54e83cafd2b562bb6d15bb2f72d76200fb5 ]

If multiple CPUs are sharing the same hardware queue, it can cause leak in the active queue counter tracking when __blk_mq_tag_busy() is executed simultaneously.

Fixes: ee78ec1077d3 ("blk-mq: blk_mq_tag_busy is no need to return a value") Signed-off-by: Tian Lan tian.lan@twosigma.com Reviewed-by: Ming Lei ming.lei@redhat.com Reviewed-by: Damien Le Moal dlemoal@kernel.org Reviewed-by: John Garry john.g.garry@oracle.com Link: https://lore.kernel.org/r/20230522210555.794134-1-tilan7663@gmail.com Signed-off-by: Jens Axboe axboe@kernel.dk Signed-off-by: Sasha Levin sashal@kernel.org --- block/blk-mq-tag.c | 12 ++++++++---- 1 file changed, 8 insertions(+), 4 deletions(-)

diff --git a/block/blk-mq-tag.c b/block/blk-mq-tag.c index 9eb968e14d31f..a80d7c62bdfe6 100644 --- a/block/blk-mq-tag.c +++ b/block/blk-mq-tag.c @@ -41,16 +41,20 @@ void __blk_mq_tag_busy(struct blk_mq_hw_ctx *hctx) { unsigned int users;

+ /* + * calling test_bit() prior to test_and_set_bit() is intentional, + * it avoids dirtying the cacheline if the queue is already active. + */ if (blk_mq_is_shared_tags(hctx->flags)) { struct request_queue *q = hctx->queue;

- if (test_bit(QUEUE_FLAG_HCTX_ACTIVE, &q->queue_flags)) + if (test_bit(QUEUE_FLAG_HCTX_ACTIVE, &q->queue_flags) || + test_and_set_bit(QUEUE_FLAG_HCTX_ACTIVE, &q->queue_flags)) return; - set_bit(QUEUE_FLAG_HCTX_ACTIVE, &q->queue_flags); } else { - if (test_bit(BLK_MQ_S_TAG_ACTIVE, &hctx->state)) + if (test_bit(BLK_MQ_S_TAG_ACTIVE, &hctx->state) || + test_and_set_bit(BLK_MQ_S_TAG_ACTIVE, &hctx->state)) return; - set_bit(BLK_MQ_S_TAG_ACTIVE, &hctx->state); }

users = atomic_inc_return(&hctx->tags->active_queues);

From: Wyes Karny wyes.karny@amd.com

[ Upstream commit 249b62c448de7117c18531d626aed6e153cdfd75 ]

amd_pstate active mode driver is only compatible with static governors. Therefore it doesn't need fast_switch functionality. Remove fast_switch_possible flag from amd_pstate active mode driver.

Fixes: ffa5096a7c33 ("cpufreq: amd-pstate: implement Pstate EPP support for the AMD processors") Signed-off-by: Wyes Karny wyes.karny@amd.com Signed-off-by: Rafael J. Wysocki rafael.j.wysocki@intel.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/cpufreq/amd-pstate.c | 2 -- 1 file changed, 2 deletions(-)

diff --git a/drivers/cpufreq/amd-pstate.c b/drivers/cpufreq/amd-pstate.c index 8dd46fad151eb..fda15b4a0770f 100644 --- a/drivers/cpufreq/amd-pstate.c +++ b/drivers/cpufreq/amd-pstate.c @@ -996,7 +996,6 @@ static int amd_pstate_epp_cpu_init(struct cpufreq_policy *policy) policy->policy = CPUFREQ_POLICY_POWERSAVE;

if (boot_cpu_has(X86_FEATURE_CPPC)) { - policy->fast_switch_possible = true; ret = rdmsrl_on_cpu(cpudata->cpu, MSR_AMD_CPPC_REQ, &value); if (ret) return ret; @@ -1019,7 +1018,6 @@ static int amd_pstate_epp_cpu_init(struct cpufreq_policy *policy) static int amd_pstate_epp_cpu_exit(struct cpufreq_policy *policy) { pr_debug("CPU %d exiting\n", policy->cpu); - policy->fast_switch_possible = false; return 0; }

From: Ruihan Li lrh2000@pku.edu.cn

commit 000c2fa2c144c499c881a101819cf1936a1f7cf2 upstream.

Previously, channel open messages were always sent to monitors on the first ioctl() call for unbound HCI sockets, even if the command and arguments were completely invalid. This can leave an exploitable hole with the abuse of invalid ioctl calls.

This commit hardens the ioctl processing logic by first checking if the command is valid, and immediately returning with an ENOIOCTLCMD error code if it is not. This ensures that ioctl calls with invalid commands are free of side effects, and increases the difficulty of further exploitation by forcing exploitation to find a way to pass a valid command first.

Signed-off-by: Ruihan Li lrh2000@pku.edu.cn Co-developed-by: Marcel Holtmann marcel@holtmann.org Signed-off-by: Marcel Holtmann marcel@holtmann.org Signed-off-by: Luiz Augusto von Dentz luiz.von.dentz@intel.com Signed-off-by: Dragos-Marian Panait dragos.panait@windriver.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/bluetooth/hci_sock.c | 28 ++++++++++++++++++++++++++++ 1 file changed, 28 insertions(+)

--- a/net/bluetooth/hci_sock.c +++ b/net/bluetooth/hci_sock.c @@ -987,6 +987,34 @@ static int hci_sock_ioctl(struct socket

BT_DBG("cmd %x arg %lx", cmd, arg);

+ /* Make sure the cmd is valid before doing anything */ + switch (cmd) { + case HCIGETDEVLIST: + case HCIGETDEVINFO: + case HCIGETCONNLIST: + case HCIDEVUP: + case HCIDEVDOWN: + case HCIDEVRESET: + case HCIDEVRESTAT: + case HCISETSCAN: + case HCISETAUTH: + case HCISETENCRYPT: + case HCISETPTYPE: + case HCISETLINKPOL: + case HCISETLINKMODE: + case HCISETACLMTU: + case HCISETSCOMTU: + case HCIINQUIRY: + case HCISETRAW: + case HCIGETCONNINFO: + case HCIGETAUTHINFO: + case HCIBLOCKADDR: + case HCIUNBLOCKADDR: + break; + default: + return -ENOIOCTLCMD; + } + lock_sock(sk);

if (hci_pi(sk)->channel != HCI_CHANNEL_RAW) {

From: Gautham R. Shenoy gautham.shenoy@amd.com

commit 4badf2eb1e986bdbf34dd2f5d4c979553a86fe54 upstream.

Schedutil normally calls the adjust_perf callback for drivers with adjust_perf callback available and fast_switch_possible flag set. However, when frequency invariance is disabled and schedutil tries to invoke fast_switch. So, there is a chance of kernel crash if this function pointer is not set. To protect against this scenario add fast_switch callback to amd_pstate driver.

Fixes: 1d215f0319c2 ("cpufreq: amd-pstate: Add fast switch function for AMD P-State") Signed-off-by: Gautham R. Shenoy gautham.shenoy@amd.com Signed-off-by: Wyes Karny wyes.karny@amd.com Signed-off-by: Rafael J. Wysocki rafael.j.wysocki@intel.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/cpufreq/amd-pstate.c | 37 ++++++++++++++++++++++++++++++------- 1 file changed, 30 insertions(+), 7 deletions(-)

--- a/drivers/cpufreq/amd-pstate.c +++ b/drivers/cpufreq/amd-pstate.c @@ -422,9 +422,8 @@ static int amd_pstate_verify(struct cpuf return 0; }

-static int amd_pstate_target(struct cpufreq_policy *policy, - unsigned int target_freq, - unsigned int relation) +static int amd_pstate_update_freq(struct cpufreq_policy *policy, + unsigned int target_freq, bool fast_switch) { struct cpufreq_freqs freqs; struct amd_cpudata *cpudata = policy->driver_data; @@ -443,14 +442,36 @@ static int amd_pstate_target(struct cpuf des_perf = DIV_ROUND_CLOSEST(target_freq * cap_perf, cpudata->max_freq);

- cpufreq_freq_transition_begin(policy, &freqs); - amd_pstate_update(cpudata, min_perf, des_perf, - max_perf, false); - cpufreq_freq_transition_end(policy, &freqs, false); + WARN_ON(fast_switch && !policy->fast_switch_enabled); + /* + * If fast_switch is desired, then there aren't any registered + * transition notifiers. See comment for + * cpufreq_enable_fast_switch(). + */ + if (!fast_switch) + cpufreq_freq_transition_begin(policy, &freqs); + + amd_pstate_update(cpudata, min_perf, des_perf, max_perf, fast_switch); + + if (!fast_switch) + cpufreq_freq_transition_end(policy, &freqs, false);

return 0; }

+static int amd_pstate_target(struct cpufreq_policy *policy, + unsigned int target_freq, + unsigned int relation) +{ + return amd_pstate_update_freq(policy, target_freq, false); +} + +static unsigned int amd_pstate_fast_switch(struct cpufreq_policy *policy, + unsigned int target_freq) +{ + return amd_pstate_update_freq(policy, target_freq, true); +} + static void amd_pstate_adjust_perf(unsigned int cpu, unsigned long _min_perf, unsigned long target_perf, @@ -698,6 +719,7 @@ static int amd_pstate_cpu_exit(struct cp

freq_qos_remove_request(&cpudata->req[1]); freq_qos_remove_request(&cpudata->req[0]); + policy->fast_switch_possible = false; kfree(cpudata);

return 0; @@ -1230,6 +1252,7 @@ static struct cpufreq_driver amd_pstate_ .flags = CPUFREQ_CONST_LOOPS | CPUFREQ_NEED_UPDATE_LIMITS, .verify = amd_pstate_verify, .target = amd_pstate_target, + .fast_switch = amd_pstate_fast_switch, .init = amd_pstate_cpu_init, .exit = amd_pstate_cpu_exit, .suspend = amd_pstate_cpu_suspend,