From: Carlos Llamas cmllamas@google.com

[ Upstream commit 3ce00bb7e91cf57d723905371507af57182c37ef ]

Since commit 1da52815d5f1 ("binder: fix alloc->vma_vm_mm null-ptr dereference") binder caches a pointer to the current->mm during open(). This fixes a null-ptr dereference reported by syzkaller. Unfortunately, it also opens the door for a process to update its mm after the open(), (e.g. via execve) making the cached alloc->mm pointer invalid.

Things get worse when the process continues to mmap() a vma. From this point forward, binder will attempt to find this vma using an obsolete alloc->mm reference. Such as in binder_update_page_range(), where the wrong vma is obtained via vma_lookup(), yet binder proceeds to happily insert new pages into it.

To avoid this issue fail the ->mmap() callback if we detect a mismatch between the vma->vm_mm and the original alloc->mm pointer. This prevents alloc->vm_addr from getting set, so that any subsequent vma_lookup() calls fail as expected.

Fixes: 1da52815d5f1 ("binder: fix alloc->vma_vm_mm null-ptr dereference") Reported-by: Jann Horn jannh@google.com Cc: stable@vger.kernel.org # 5.15+ Signed-off-by: Carlos Llamas cmllamas@google.com Acked-by: Todd Kjos tkjos@google.com Link: https://lore.kernel.org/r/20221104231235.348958-1-cmllamas@google.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/android/binder_alloc.c | 7 +++++++ 1 file changed, 7 insertions(+)

diff --git a/drivers/android/binder_alloc.c b/drivers/android/binder_alloc.c index 9b1778c00610..64999777e0bf 100644 --- a/drivers/android/binder_alloc.c +++ b/drivers/android/binder_alloc.c @@ -760,6 +760,12 @@ int binder_alloc_mmap_handler(struct binder_alloc *alloc, const char *failure_string; struct binder_buffer *buffer;

+ if (unlikely(vma->vm_mm != alloc->vma_vm_mm)) { + ret = -EINVAL; + failure_string = "invalid vma->vm_mm"; + goto err_invalid_mm; + } + mutex_lock(&binder_alloc_mmap_lock); if (alloc->buffer_size) { ret = -EBUSY; @@ -806,6 +812,7 @@ int binder_alloc_mmap_handler(struct binder_alloc *alloc, alloc->buffer_size = 0; err_already_mapped: mutex_unlock(&binder_alloc_mmap_lock); +err_invalid_mm: binder_alloc_debug(BINDER_DEBUG_USER_ERROR, "%s: %d %lx-%lx %s failed %d\n", __func__, alloc->pid, vma->vm_start, vma->vm_end,

From: Xiubo Li xiubli@redhat.com

[ Upstream commit 5bd76b8de5b74fa941a6eafee87728a0fe072267 ]

The request's r_session maybe changed when it was forwarded or resent. Both the forwarding and resending cases the requests will be protected by the mdsc->mutex.

Cc: stable@vger.kernel.org Link: https://bugzilla.redhat.com/show_bug.cgi?id=2137955 Signed-off-by: Xiubo Li xiubli@redhat.com Reviewed-by: Ilya Dryomov idryomov@gmail.com Signed-off-by: Ilya Dryomov idryomov@gmail.com Signed-off-by: Sasha Levin sashal@kernel.org --- fs/ceph/caps.c | 48 ++++++++++++------------------------------------ 1 file changed, 12 insertions(+), 36 deletions(-)

diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c index 1eb2ff0f6bd8..02b5c0ac5654 100644 --- a/fs/ceph/caps.c +++ b/fs/ceph/caps.c @@ -2247,7 +2247,6 @@ static int flush_mdlog_and_wait_inode_unsafe_requests(struct inode *inode) struct ceph_mds_client *mdsc = ceph_sb_to_client(inode->i_sb)->mdsc; struct ceph_inode_info *ci = ceph_inode(inode); struct ceph_mds_request *req1 = NULL, *req2 = NULL; - unsigned int max_sessions; int ret, err = 0;

spin_lock(&ci->i_unsafe_lock); @@ -2265,28 +2264,24 @@ static int flush_mdlog_and_wait_inode_unsafe_requests(struct inode *inode) } spin_unlock(&ci->i_unsafe_lock);

- /* - * The mdsc->max_sessions is unlikely to be changed - * mostly, here we will retry it by reallocating the - * sessions array memory to get rid of the mdsc->mutex - * lock. - */ -retry: - max_sessions = mdsc->max_sessions; - /* * Trigger to flush the journal logs in all the relevant MDSes * manually, or in the worst case we must wait at most 5 seconds * to wait the journal logs to be flushed by the MDSes periodically. */ - if ((req1 || req2) && likely(max_sessions)) { - struct ceph_mds_session **sessions = NULL; - struct ceph_mds_session *s; + if (req1 || req2) { struct ceph_mds_request *req; + struct ceph_mds_session **sessions; + struct ceph_mds_session *s; + unsigned int max_sessions; int i;

+ mutex_lock(&mdsc->mutex); + max_sessions = mdsc->max_sessions; + sessions = kcalloc(max_sessions, sizeof(s), GFP_KERNEL); if (!sessions) { + mutex_unlock(&mdsc->mutex); err = -ENOMEM; goto out; } @@ -2298,16 +2293,6 @@ static int flush_mdlog_and_wait_inode_unsafe_requests(struct inode *inode) s = req->r_session; if (!s) continue; - if (unlikely(s->s_mds >= max_sessions)) { - spin_unlock(&ci->i_unsafe_lock); - for (i = 0; i < max_sessions; i++) { - s = sessions[i]; - if (s) - ceph_put_mds_session(s); - } - kfree(sessions); - goto retry; - } if (!sessions[s->s_mds]) { s = ceph_get_mds_session(s); sessions[s->s_mds] = s; @@ -2320,16 +2305,6 @@ static int flush_mdlog_and_wait_inode_unsafe_requests(struct inode *inode) s = req->r_session; if (!s) continue; - if (unlikely(s->s_mds >= max_sessions)) { - spin_unlock(&ci->i_unsafe_lock); - for (i = 0; i < max_sessions; i++) { - s = sessions[i]; - if (s) - ceph_put_mds_session(s); - } - kfree(sessions); - goto retry; - } if (!sessions[s->s_mds]) { s = ceph_get_mds_session(s); sessions[s->s_mds] = s; @@ -2341,11 +2316,12 @@ static int flush_mdlog_and_wait_inode_unsafe_requests(struct inode *inode) /* the auth MDS */ spin_lock(&ci->i_ceph_lock); if (ci->i_auth_cap) { - s = ci->i_auth_cap->session; - if (!sessions[s->s_mds]) - sessions[s->s_mds] = ceph_get_mds_session(s); + s = ci->i_auth_cap->session; + if (!sessions[s->s_mds]) + sessions[s->s_mds] = ceph_get_mds_session(s); } spin_unlock(&ci->i_ceph_lock); + mutex_unlock(&mdsc->mutex);

/* send flush mdlog request to MDSes */ for (i = 0; i < max_sessions; i++) {

From: Paul Zhang quic_paulz@quicinc.com

[ Upstream commit 18429c51c7ff6e6bfd627316c54670230967a7e5 ]

When invoking function cfg80211_calculate_bitrate_eht about (320 MHz, EHT-MCS 13, EHT-NSS 2, EHT-GI 0), which means the parameters as flags: 0x80, bw: 7, mcs: 13, eht_gi: 0, nss: 2, this formula (result * rate->nss) will overflow and causes the returned bitrate to be 3959 when it should be 57646.

Here is the explanation: u64 tmp; u32 result; … /* tmp = result = 4 * rates_996[0] * = 4 * 480388888 = 0x72889c60 */ tmp = result;

/* tmp = 0x72889c60 * 6144 = 0xabccea90000 */ tmp *= SCALE;

/* tmp = 0xabccea90000 / mcs_divisors[13] * = 0xabccea90000 / 5120 = 0x8970bba6 */ do_div(tmp, mcs_divisors[rate->mcs]);

/* result = 0x8970bba6 */ result = tmp;

/* normally (result * rate->nss) = 0x8970bba6 * 2 = 0x112e1774c, * but since result is u32, (result * rate->nss) = 0x12e1774c, * overflow happens and it loses the highest bit. * Then result = 0x12e1774c / 8 = 39595753, */ result = (result * rate->nss) / 8;

Signed-off-by: Paul Zhang quic_paulz@quicinc.com Signed-off-by: Johannes Berg johannes.berg@intel.com Signed-off-by: Sasha Levin sashal@kernel.org --- net/wireless/util.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/net/wireless/util.c b/net/wireless/util.c index 775836f6785a..450d609b512a 100644 --- a/net/wireless/util.c +++ b/net/wireless/util.c @@ -1555,10 +1555,12 @@ static u32 cfg80211_calculate_bitrate_eht(struct rate_info *rate) tmp = result; tmp *= SCALE; do_div(tmp, mcs_divisors[rate->mcs]); - result = tmp;

/* and take NSS */ - result = (result * rate->nss) / 8; + tmp *= rate->nss; + do_div(tmp, 8); + + result = tmp;

return result / 10000; }

From: Jon Hunter jonathanh@nvidia.com

[ Upstream commit ae4b3c1252f0fd0951d2f072a02ba46cac8d6c92 ]

The following error messages are observed on boot for Tegra234 ...

ERR KERN tegra-qspi 3270000.spi: cannot use DMA: -19 ERR KERN tegra-qspi 3270000.spi: falling back to PIO

Tegra234 does not support DMA for the QSPI and so initialising the DMA is expected to fail. The above error messages are misleading for devices that don't support DMA and so fix this by skipping the DMA initialisation for devices that don't support DMA.

Signed-off-by: Jon Hunter jonathanh@nvidia.com Acked-by: Thierry Reding treding@nvidia.com Link: https://lore.kernel.org/r/20221026155633.141792-1-jonathanh@nvidia.com Signed-off-by: Mark Brown broonie@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/spi/spi-tegra210-quad.c | 6 ++++++ 1 file changed, 6 insertions(+)

diff --git a/drivers/spi/spi-tegra210-quad.c b/drivers/spi/spi-tegra210-quad.c index 904972606bd4..10f0c5a6e0dc 100644 --- a/drivers/spi/spi-tegra210-quad.c +++ b/drivers/spi/spi-tegra210-quad.c @@ -720,6 +720,9 @@ static int tegra_qspi_start_cpu_based_transfer(struct tegra_qspi *qspi, struct s

static void tegra_qspi_deinit_dma(struct tegra_qspi *tqspi) { + if (!tqspi->soc_data->has_dma) + return; + if (tqspi->tx_dma_buf) { dma_free_coherent(tqspi->dev, tqspi->dma_buf_size, tqspi->tx_dma_buf, tqspi->tx_dma_phys); @@ -750,6 +753,9 @@ static int tegra_qspi_init_dma(struct tegra_qspi *tqspi) u32 *dma_buf; int err;

+ if (!tqspi->soc_data->has_dma) + return 0; + dma_chan = dma_request_chan(tqspi->dev, "rx"); if (IS_ERR(dma_chan)) { err = PTR_ERR(dma_chan);

From: Gaosheng Cui cuigaosheng1@huawei.com

[ Upstream commit 986d93f55bdeab1cac858d1e47b41fac10b2d7f6 ]

Shifting signed 32-bit value by 31 bits is undefined, so changing significant bit to unsigned. The UBSAN warning calltrace like below:

UBSAN: shift-out-of-bounds in kernel/auditfilter.c:179:23 left shift of 1 by 31 places cannot be represented in type 'int' Call Trace: <TASK> dump_stack_lvl+0x7d/0xa5 dump_stack+0x15/0x1b ubsan_epilogue+0xe/0x4e __ubsan_handle_shift_out_of_bounds+0x1e7/0x20c audit_register_class+0x9d/0x137 audit_classes_init+0x4d/0xb8 do_one_initcall+0x76/0x430 kernel_init_freeable+0x3b3/0x422 kernel_init+0x24/0x1e0 ret_from_fork+0x1f/0x30 </TASK>

Signed-off-by: Gaosheng Cui cuigaosheng1@huawei.com [PM: remove bad 'Fixes' tag as issue predates git, added in v2.6.6-rc1] Signed-off-by: Paul Moore paul@paul-moore.com Signed-off-by: Sasha Levin sashal@kernel.org --- include/uapi/linux/audit.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/include/uapi/linux/audit.h b/include/uapi/linux/audit.h index 7c1dc818b1d5..d676ed2b246e 100644 --- a/include/uapi/linux/audit.h +++ b/include/uapi/linux/audit.h @@ -187,7 +187,7 @@ #define AUDIT_MAX_KEY_LEN 256 #define AUDIT_BITMASK_SIZE 64 #define AUDIT_WORD(nr) ((__u32)((nr)/32)) -#define AUDIT_BIT(nr) (1 << ((nr) - AUDIT_WORD(nr)*32)) +#define AUDIT_BIT(nr) (1U << ((nr) - AUDIT_WORD(nr)*32))

#define AUDIT_SYSCALL_CLASSES 16 #define AUDIT_CLASS_DIR_WRITE 0

From: Nicolas Cavallari nicolas.cavallari@green-communications.fr

[ Upstream commit 39e7b5de9853bd92ddbfa4b14165babacd7da0ba ]

When trying to transmit an data frame with tx_status to a destination that have no route in the mesh, then it is dropped without recrediting the ack_status_frames idr.

Once it is exhausted, wpa_supplicant starts failing to do SAE with NL80211_CMD_FRAME and logs "nl80211: Frame command failed".

Use ieee80211_free_txskb() instead of kfree_skb() to fix it.

Signed-off-by: Nicolas Cavallari nicolas.cavallari@green-communications.fr Link: https://lore.kernel.org/r/20221027140133.1504-1-nicolas.cavallari@green-comm... Signed-off-by: Johannes Berg johannes.berg@intel.com Signed-off-by: Sasha Levin sashal@kernel.org --- net/mac80211/mesh_pathtbl.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/mac80211/mesh_pathtbl.c b/net/mac80211/mesh_pathtbl.c index acc1c299f1ae..69d5e1ec6ede 100644 --- a/net/mac80211/mesh_pathtbl.c +++ b/net/mac80211/mesh_pathtbl.c @@ -710,7 +710,7 @@ int mesh_path_send_to_gates(struct mesh_path *mpath) void mesh_path_discard_frame(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb) { - kfree_skb(skb); + ieee80211_free_txskb(&sdata->local->hw, skb); sdata->u.mesh.mshstats.dropped_frames_no_route++; }

From: Tyler J. Stachecki stachecki.tyler@gmail.com

[ Upstream commit 3a89b6dec9920026eaa90fe8457f4348d3388a98 ]

The 2.7.0 series of QCN9074's firmware requests 5 segments of memory instead of 3 (as in the 2.5.0 series).

The first segment (11M) is too large to be kalloc'd in one go on x86 and requires piecemeal 1MB allocations, as was the case with the prior public firmware (2.5.0, 15M).

Since f6f92968e1e5, ath11k will break the memory requests, but only if there were fewer than 3 segments requested by the firmware. It seems that 5 segments works fine and allows QCN9074 to boot on x86 with firmware 2.7.0, so change things accordingly.

Tested-on: QCN9074 hw1.0 PCI WLAN.HK.2.7.0.1-01744-QCAHKSWPL_SILICONZ-1 Tested-on: QCN9074 hw1.0 PCI WLAN.HK.2.5.0.1-01208-QCAHKSWPL_SILICONZ-1 Tested-on: WCN6855 hw2.0 PCI WLAN.HSP.1.1-03125-QCAHSPSWPL_V1_V2_SILICONZ_LITE-3.6510.16

Signed-off-by: Tyler J. Stachecki stachecki.tyler@gmail.com Signed-off-by: Kalle Valo quic_kvalo@quicinc.com Link: https://lore.kernel.org/r/20221022042728.43015-1-stachecki.tyler@gmail.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/wireless/ath/ath11k/qmi.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/wireless/ath/ath11k/qmi.h b/drivers/net/wireless/ath/ath11k/qmi.h index 2ec56a34fa81..0909d53cefeb 100644 --- a/drivers/net/wireless/ath/ath11k/qmi.h +++ b/drivers/net/wireless/ath/ath11k/qmi.h @@ -27,7 +27,7 @@ #define ATH11K_QMI_WLANFW_MAX_NUM_MEM_SEG_V01 52 #define ATH11K_QMI_CALDB_SIZE 0x480000 #define ATH11K_QMI_BDF_EXT_STR_LENGTH 0x20 -#define ATH11K_QMI_FW_MEM_REQ_SEGMENT_CNT 3 +#define ATH11K_QMI_FW_MEM_REQ_SEGMENT_CNT 5

#define QMI_WLFW_REQUEST_MEM_IND_V01 0x0035 #define QMI_WLFW_FW_MEM_READY_IND_V01 0x0037

From: Sean Nyekjaer sean@geanix.com

[ Upstream commit 62aa1a344b0904549f6de7af958e8a1136fd5228 ]

When this driver is used with a driver that uses preallocated spi_transfer structs. The speed_hz is halved by every run. This results in:

spi_stm32 44004000.spi: SPI transfer setup failed ads7846 spi0.0: SPI transfer failed: -22

Example when running with DIV_ROUND_UP(): - First run; speed_hz = 1000000, spi->clk_rate 125000000 div 125 -> mbrdiv = 7, cur_speed = 976562 - Second run; speed_hz = 976562 div 128,00007 (roundup to 129) -> mbrdiv = 8, cur_speed = 488281 - Third run; speed_hz = 488281 div 256,000131072067109 (roundup to 257) and then -EINVAL is returned.

Use DIV_ROUND_CLOSEST to allow to round down and allow us to keep the set speed.

Signed-off-by: Sean Nyekjaer sean@geanix.com Link: https://lore.kernel.org/r/20221103080043.3033414-1-sean@geanix.com Signed-off-by: Mark Brown broonie@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/spi/spi-stm32.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/spi/spi-stm32.c b/drivers/spi/spi-stm32.c index 3c2fa2e2f94a..def09cf0dc14 100644 --- a/drivers/spi/spi-stm32.c +++ b/drivers/spi/spi-stm32.c @@ -434,7 +434,7 @@ static int stm32_spi_prepare_mbr(struct stm32_spi *spi, u32 speed_hz, u32 div, mbrdiv;

/* Ensure spi->clk_rate is even */ - div = DIV_ROUND_UP(spi->clk_rate & ~0x1, speed_hz); + div = DIV_ROUND_CLOSEST(spi->clk_rate & ~0x1, speed_hz);

/* * SPI framework set xfer->speed_hz to master->max_speed_hz if

From: Adrien Thierry athierry@redhat.com

[ Upstream commit cdb525ca92b196f8916102b62431aa0d9a644ff2 ]

In some conditions, background processes in udpgro don't have enough time to set up the sockets. When foreground processes start, this results in the test failing with "./udpgso_bench_tx: sendmsg: Connection refused". For instance, this happens from time to time on a Qualcomm SA8540P SoC running CentOS Stream 9.

To fix this, increase the time given to background processes to complete the startup before foreground processes start.

Signed-off-by: Adrien Thierry athierry@redhat.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- tools/testing/selftests/net/udpgro.sh | 4 ++-- tools/testing/selftests/net/udpgro_bench.sh | 2 +- tools/testing/selftests/net/udpgro_frglist.sh | 2 +- 3 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/tools/testing/selftests/net/udpgro.sh b/tools/testing/selftests/net/udpgro.sh index ebbd0b282432..6a443ca3cd3a 100755 --- a/tools/testing/selftests/net/udpgro.sh +++ b/tools/testing/selftests/net/udpgro.sh @@ -50,7 +50,7 @@ run_one() { echo "failed" &

# Hack: let bg programs complete the startup - sleep 0.1 + sleep 0.2 ./udpgso_bench_tx ${tx_args} ret=$? wait $(jobs -p) @@ -117,7 +117,7 @@ run_one_2sock() { echo "failed" &

# Hack: let bg programs complete the startup - sleep 0.1 + sleep 0.2 ./udpgso_bench_tx ${tx_args} -p 12345 sleep 0.1 # first UDP GSO socket should be closed at this point diff --git a/tools/testing/selftests/net/udpgro_bench.sh b/tools/testing/selftests/net/udpgro_bench.sh index fad2d1a71cac..8a1109a545db 100755 --- a/tools/testing/selftests/net/udpgro_bench.sh +++ b/tools/testing/selftests/net/udpgro_bench.sh @@ -39,7 +39,7 @@ run_one() { ip netns exec "${PEER_NS}" ./udpgso_bench_rx -t ${rx_args} -r &

# Hack: let bg programs complete the startup - sleep 0.1 + sleep 0.2 ./udpgso_bench_tx ${tx_args} }

diff --git a/tools/testing/selftests/net/udpgro_frglist.sh b/tools/testing/selftests/net/udpgro_frglist.sh index 832c738cc3c2..7fe85ba51075 100755 --- a/tools/testing/selftests/net/udpgro_frglist.sh +++ b/tools/testing/selftests/net/udpgro_frglist.sh @@ -44,7 +44,7 @@ run_one() { ip netns exec "${PEER_NS}" ./udpgso_bench_rx ${rx_args} -r &

# Hack: let bg programs complete the startup - sleep 0.1 + sleep 0.2 ./udpgso_bench_tx ${tx_args} }

From: Hans de Goede hdegoede@redhat.com

[ Upstream commit f46acc1efd4b5846de9fa05f966e504f328f34a6 ]

The Dell G15 5515 has the WMI interface (and WMI call returns) expected by the nvidia-wmi-ec-backlight interface. But the backlight class device registered by the nvidia-wmi-ec-backlight driver does not actually work.

The amdgpu_bl0 native GPU backlight class device does actually work, add a backlight=native DMI quirk for this.

Reported-by: Iris pawel.js@protonmail.com Reviewed-by: Daniel Dadap ddadap@nvidia.com Signed-off-by: Hans de Goede hdegoede@redhat.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/acpi/video_detect.c | 14 ++++++++++++++ 1 file changed, 14 insertions(+)

diff --git a/drivers/acpi/video_detect.c b/drivers/acpi/video_detect.c index 68a566f69684..aae9261c424a 100644 --- a/drivers/acpi/video_detect.c +++ b/drivers/acpi/video_detect.c @@ -578,6 +578,20 @@ static const struct dmi_system_id video_detect_dmi_table[] = { DMI_MATCH(DMI_BOARD_NAME, "GMxRGxx"), }, }, + /* + * Models which have nvidia-ec-wmi support, but should not use it. + * Note this indicates a likely firmware bug on these models and should + * be revisited if/when Linux gets support for dynamic mux mode. + */ + { + .callback = video_detect_force_native, + /* Dell G15 5515 */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), + DMI_MATCH(DMI_PRODUCT_NAME, "Dell G15 5515"), + }, + }, + /* * Desktops which falsely report a backlight and which our heuristics * for this do not catch.

From: Hans de Goede hdegoede@redhat.com

[ Upstream commit 0df044b34bf33e7e35c32b3bf6747fde6279c162 ]

Add touchscreen info for the RCA Cambio W101 v2 2-in-1.

Link: https://github.com/onitake/gsl-firmware/discussions/193 Signed-off-by: Hans de Goede hdegoede@redhat.com Link: https://lore.kernel.org/r/20221025141131.509211-1-hdegoede@redhat.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/platform/x86/touchscreen_dmi.c | 25 +++++++++++++++++++++++++ 1 file changed, 25 insertions(+)

diff --git a/drivers/platform/x86/touchscreen_dmi.c b/drivers/platform/x86/touchscreen_dmi.c index bc97bfa8e8a6..baae3120efd0 100644 --- a/drivers/platform/x86/touchscreen_dmi.c +++ b/drivers/platform/x86/touchscreen_dmi.c @@ -770,6 +770,22 @@ static const struct ts_dmi_data predia_basic_data = { .properties = predia_basic_props, };

+static const struct property_entry rca_cambio_w101_v2_props[] = { + PROPERTY_ENTRY_U32("touchscreen-min-x", 4), + PROPERTY_ENTRY_U32("touchscreen-min-y", 20), + PROPERTY_ENTRY_U32("touchscreen-size-x", 1644), + PROPERTY_ENTRY_U32("touchscreen-size-y", 874), + PROPERTY_ENTRY_BOOL("touchscreen-swapped-x-y"), + PROPERTY_ENTRY_STRING("firmware-name", "gsl1680-rca-cambio-w101-v2.fw"), + PROPERTY_ENTRY_U32("silead,max-fingers", 10), + { } +}; + +static const struct ts_dmi_data rca_cambio_w101_v2_data = { + .acpi_name = "MSSL1680:00", + .properties = rca_cambio_w101_v2_props, +}; + static const struct property_entry rwc_nanote_p8_props[] = { PROPERTY_ENTRY_U32("touchscreen-min-y", 46), PROPERTY_ENTRY_U32("touchscreen-size-x", 1728), @@ -1409,6 +1425,15 @@ const struct dmi_system_id touchscreen_dmi_table[] = { DMI_EXACT_MATCH(DMI_BOARD_NAME, "0E57"), }, }, + { + /* RCA Cambio W101 v2 */ + /* https://github.com/onitake/gsl-firmware/discussions/193 */ + .driver_data = (void *)&rca_cambio_w101_v2_data, + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "RCA"), + DMI_MATCH(DMI_PRODUCT_NAME, "W101SA23T1"), + }, + }, { /* RWC NANOTE P8 */ .driver_data = (void *)&rwc_nanote_p8_data,

From: Ivan Hu ivan.hu@canonical.com

[ Upstream commit a977ece5773b6746b814aac410da4776023db239 ]

Add INTC1076 (JasonLake), INTC1077 (MeteorLake) and INTC1078 (RaptorLake) devices IDs.

Signed-off-by: Ivan Hu ivan.hu@canonical.com Link: https://lore.kernel.org/r/20221102020548.5225-1-ivan.hu@canonical.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/intel/hid.c | 3 +++ 1 file changed, 3 insertions(+)

diff --git a/drivers/platform/x86/intel/hid.c b/drivers/platform/x86/intel/hid.c index 79cff1fc675c..b6313ecd190c 100644 --- a/drivers/platform/x86/intel/hid.c +++ b/drivers/platform/x86/intel/hid.c @@ -27,6 +27,9 @@ static const struct acpi_device_id intel_hid_ids[] = { {"INTC1051", 0}, {"INTC1054", 0}, {"INTC1070", 0}, + {"INTC1076", 0}, + {"INTC1077", 0}, + {"INTC1078", 0}, {"", 0}, }; MODULE_DEVICE_TABLE(acpi, intel_hid_ids);

From: Bart Van Assche bvanassche@acm.org

[ Upstream commit ecb8c2580d37dbb641451049376d80c8afaa387f ]

From ZBC-1:

- RC BASIS = 0: The RETURNED LOGICAL BLOCK ADDRESS field indicates the highest LBA of a contiguous range of zones that are not sequential write required zones starting with the first zone.

- RC BASIS = 1: The RETURNED LOGICAL BLOCK ADDRESS field indicates the LBA of the last logical block on the logical unit.

The current scsi_debug READ CAPACITY response does not comply with the above if there are one or more sequential write required zones. SCSI initiators need a way to retrieve the largest valid LBA from SCSI devices. Reporting the largest valid LBA if there are one or more sequential zones requires to set the RC BASIS field in the READ CAPACITY response to one. Hence this patch.

Cc: Douglas Gilbert dgilbert@interlog.com Cc: Damien Le Moal damien.lemoal@opensource.wdc.com Suggested-by: Damien Le Moal damien.lemoal@opensource.wdc.com Signed-off-by: Bart Van Assche bvanassche@acm.org Link: https://lore.kernel.org/r/20221102193248.3177608-1-bvanassche@acm.org Reviewed-by: Damien Le Moal damien.lemoal@opensource.wdc.com Acked-by: Douglas Gilbert dgilbert@interlog.com Signed-off-by: Martin K. Petersen martin.petersen@oracle.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/scsi/scsi_debug.c | 7 +++++++ 1 file changed, 7 insertions(+)

diff --git a/drivers/scsi/scsi_debug.c b/drivers/scsi/scsi_debug.c index 95f940f5c996..7346098c1c68 100644 --- a/drivers/scsi/scsi_debug.c +++ b/drivers/scsi/scsi_debug.c @@ -1899,6 +1899,13 @@ static int resp_readcap16(struct scsi_cmnd *scp, arr[14] |= 0x40; }

+ /* + * Since the scsi_debug READ CAPACITY implementation always reports the + * total disk capacity, set RC BASIS = 1 for host-managed ZBC devices. + */ + if (devip->zmodel == BLK_ZONED_HM) + arr[12] |= 1 << 4; + arr[15] = sdebug_lowest_aligned & 0xff;

if (have_dif_prot) {

From: Hans de Goede hdegoede@redhat.com

[ Upstream commit 653f2d94fcda200b02bd79cea2e0307b26c1b747 ]

Like the Acer Switch One 10 S1003, for which there already is a quirk, the Acer Switch V 10 (SW5-017) has a 800x1280 portrait screen mounted in the tablet part of a landscape oriented 2-in-1. Add a quirk for this.

Cc: Rudolf Polzer rpolzer@google.com Signed-off-by: Hans de Goede hdegoede@redhat.com Acked-by: Simon Ser contact@emersion.fr Link: https://patchwork.freedesktop.org/patch/msgid/20221106215052.66995-1-hdegoed... Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/gpu/drm/drm_panel_orientation_quirks.c | 6 ++++++ 1 file changed, 6 insertions(+)

diff --git a/drivers/gpu/drm/drm_panel_orientation_quirks.c b/drivers/gpu/drm/drm_panel_orientation_quirks.c index f0f6fa306521..52d8800a8ab8 100644 --- a/drivers/gpu/drm/drm_panel_orientation_quirks.c +++ b/drivers/gpu/drm/drm_panel_orientation_quirks.c @@ -134,6 +134,12 @@ static const struct dmi_system_id orientation_data[] = { DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "One S1003"), }, .driver_data = (void *)&lcd800x1280_rightside_up, + }, { /* Acer Switch V 10 (SW5-017) */ + .matches = { + DMI_EXACT_MATCH(DMI_SYS_VENDOR, "Acer"), + DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "SW5-017"), + }, + .driver_data = (void *)&lcd800x1280_rightside_up, }, { /* Anbernic Win600 */ .matches = { DMI_EXACT_MATCH(DMI_BOARD_VENDOR, "Anbernic"),

From: Heiko Carstens hca@linux.ibm.com

[ Upstream commit 80ddf5ce1c9291cb175d52ed1227134ad48c47ee ]

Nathan Chancellor reported several link errors on s390 with CONFIG_RELOCATABLE disabled, after binutils commit 906f69cf65da ("IBM zSystems: Issue error for *DBL relocs on misaligned symbols"). The binutils commit reveals potential miscompiles that might have happened already before with linker script defined symbols at odd addresses.

A similar bug was recently fixed in the kernel with commit c9305b6c1f52 ("s390: fix nospec table alignments").

See https://github.com/ClangBuiltLinux/linux/issues/1747 for an analysis from Ulich Weigand.

Therefore always build a relocatable kernel to avoid this problem. There is hardly any use-case for non-relocatable kernels, so this shouldn't be controversial.

Link: https://github.com/ClangBuiltLinux/linux/issues/1747 Signed-off-by: Heiko Carstens hca@linux.ibm.com Reported-by: Nathan Chancellor nathan@kernel.org Tested-by: Nathan Chancellor nathan@kernel.org Link: https://lore.kernel.org/r/20221030182202.2062705-1-hca@linux.ibm.com Signed-off-by: Alexander Gordeev agordeev@linux.ibm.com Signed-off-by: Sasha Levin sashal@kernel.org --- arch/s390/Kconfig | 6 +++--- arch/s390/Makefile | 2 -- arch/s390/boot/Makefile | 3 +-- arch/s390/boot/startup.c | 3 +-- 4 files changed, 5 insertions(+), 9 deletions(-)

diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig index 318fce77601d..de575af02ffe 100644 --- a/arch/s390/Kconfig +++ b/arch/s390/Kconfig @@ -568,8 +568,7 @@ config EXPOLINE_FULL endchoice

config RELOCATABLE - bool "Build a relocatable kernel" - default y + def_bool y help This builds a kernel image that retains relocation information so it can be loaded at an arbitrary address. @@ -578,10 +577,11 @@ config RELOCATABLE bootup process. The relocations make the kernel image about 15% larger (compressed 10%), but are discarded at runtime. + Note: this option exists only for documentation purposes, please do + not remove it.

config RANDOMIZE_BASE bool "Randomize the address of the kernel image (KASLR)" - depends on RELOCATABLE default y help In support of Kernel Address Space Layout Randomization (KASLR), diff --git a/arch/s390/Makefile b/arch/s390/Makefile index 4cb5d17e7ead..47bec926d6c0 100644 --- a/arch/s390/Makefile +++ b/arch/s390/Makefile @@ -14,10 +14,8 @@ KBUILD_AFLAGS_MODULE += -fPIC KBUILD_CFLAGS_MODULE += -fPIC KBUILD_AFLAGS += -m64 KBUILD_CFLAGS += -m64 -ifeq ($(CONFIG_RELOCATABLE),y) KBUILD_CFLAGS += -fPIE LDFLAGS_vmlinux := -pie -endif aflags_dwarf := -Wa,-gdwarf-2 KBUILD_AFLAGS_DECOMPRESSOR := $(CLANG_FLAGS) -m64 -D__ASSEMBLY__ ifndef CONFIG_AS_IS_LLVM diff --git a/arch/s390/boot/Makefile b/arch/s390/boot/Makefile index 883357a211a3..d52c3e2e16bc 100644 --- a/arch/s390/boot/Makefile +++ b/arch/s390/boot/Makefile @@ -37,9 +37,8 @@ CFLAGS_sclp_early_core.o += -I$(srctree)/drivers/s390/char

obj-y := head.o als.o startup.o mem_detect.o ipl_parm.o ipl_report.o obj-y += string.o ebcdic.o sclp_early_core.o mem.o ipl_vmparm.o cmdline.o -obj-y += version.o pgm_check_info.o ctype.o ipl_data.o +obj-y += version.o pgm_check_info.o ctype.o ipl_data.o machine_kexec_reloc.o obj-$(findstring y, $(CONFIG_PROTECTED_VIRTUALIZATION_GUEST) $(CONFIG_PGSTE)) += uv.o -obj-$(CONFIG_RELOCATABLE) += machine_kexec_reloc.o obj-$(CONFIG_RANDOMIZE_BASE) += kaslr.o obj-y += $(if $(CONFIG_KERNEL_UNCOMPRESSED),,decompressor.o) info.o obj-$(CONFIG_KERNEL_ZSTD) += clz_ctz.o diff --git a/arch/s390/boot/startup.c b/arch/s390/boot/startup.c index bc48fe82d949..e5026e1d277f 100644 --- a/arch/s390/boot/startup.c +++ b/arch/s390/boot/startup.c @@ -285,8 +285,7 @@ void startup_kernel(void)

clear_bss_section(); copy_bootdata(); - if (IS_ENABLED(CONFIG_RELOCATABLE)) - handle_relocs(__kaslr_offset); + handle_relocs(__kaslr_offset);

if (__kaslr_offset) { /*

From: Keith Busch kbusch@kernel.org

[ Upstream commit d7ac8dca938cd60cf7bd9a89a229a173c6bcba87 ]

The driver is spamming the kernel logs for entirely harmless errors from user space submitting unsupported commands. Just silence the errors. The application has direct access to command status, so there's no need to log these.

And since every passthrough command now uses the quiet flag, move the setting to the common initializer.

Signed-off-by: Keith Busch kbusch@kernel.org Reviewed-by: Alan Adamson alan.adamson@oracle.com Reviewed-by: Jens Axboe axboe@kernel.dk Reviewed-by: Kanchan Joshi joshi.k@samsung.com Reviewed-by: Chaitanya Kulkarni kch@nvidia.com Reviewed-by: Daniel Wagner dwagner@suse.de Tested-by: Alan Adamson alan.adamson@oracle.com Signed-off-by: Christoph Hellwig hch@lst.de Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/nvme/host/core.c | 3 +-- drivers/nvme/host/pci.c | 2 -- 2 files changed, 1 insertion(+), 4 deletions(-)

diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index ed47c256dbd2..01c36284e542 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -675,6 +675,7 @@ void nvme_init_request(struct request *req, struct nvme_command *cmd) if (req->mq_hctx->type == HCTX_TYPE_POLL) req->cmd_flags |= REQ_POLLED; nvme_clear_nvme_request(req); + req->rq_flags |= RQF_QUIET; memcpy(nvme_req(req)->cmd, cmd, sizeof(*cmd)); } EXPORT_SYMBOL_GPL(nvme_init_request); @@ -1037,7 +1038,6 @@ int __nvme_submit_sync_cmd(struct request_queue *q, struct nvme_command *cmd, goto out; }

- req->rq_flags |= RQF_QUIET; ret = nvme_execute_rq(req, at_head); if (result && ret >= 0) *result = nvme_req(req)->result; @@ -1225,7 +1225,6 @@ static void nvme_keep_alive_work(struct work_struct *work) rq->timeout = ctrl->kato * HZ; rq->end_io = nvme_keep_alive_end_io; rq->end_io_data = ctrl; - rq->rq_flags |= RQF_QUIET; blk_execute_rq_nowait(rq, false); }

diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index 1a6423e94eb3..0f34114c4596 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -1438,7 +1438,6 @@ static enum blk_eh_timer_return nvme_timeout(struct request *req)

abort_req->end_io = abort_endio; abort_req->end_io_data = NULL; - abort_req->rq_flags |= RQF_QUIET; blk_execute_rq_nowait(abort_req, false);

/* @@ -2489,7 +2488,6 @@ static int nvme_delete_queue(struct nvme_queue *nvmeq, u8 opcode) req->end_io_data = nvmeq;

init_completion(&nvmeq->delete_done); - req->rq_flags |= RQF_QUIET; blk_execute_rq_nowait(req, false); return 0; }

From: M Chetan Kumar m.chetan.kumar@linux.intel.com

[ Upstream commit 980ec04a88c9f0046c1da65833fb77b2ffa34b04 ]

Include linux/vmalloc.h in iosm_ipc_coredump.c & iosm_ipc_devlink.c to resolve kernel test robot errors.

Reported-by: kernel test robot lkp@intel.com Signed-off-by: M Chetan Kumar m.chetan.kumar@linux.intel.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/wwan/iosm/iosm_ipc_coredump.c | 1 + drivers/net/wwan/iosm/iosm_ipc_devlink.c | 1 + 2 files changed, 2 insertions(+)

diff --git a/drivers/net/wwan/iosm/iosm_ipc_coredump.c b/drivers/net/wwan/iosm/iosm_ipc_coredump.c index 9acd87724c9d..26ca30476f40 100644 --- a/drivers/net/wwan/iosm/iosm_ipc_coredump.c +++ b/drivers/net/wwan/iosm/iosm_ipc_coredump.c @@ -2,6 +2,7 @@ /* * Copyright (C) 2020-2021 Intel Corporation. */ +#include <linux/vmalloc.h>

#include "iosm_ipc_coredump.h"

diff --git a/drivers/net/wwan/iosm/iosm_ipc_devlink.c b/drivers/net/wwan/iosm/iosm_ipc_devlink.c index 17da85a8f337..2fe724d623c0 100644 --- a/drivers/net/wwan/iosm/iosm_ipc_devlink.c +++ b/drivers/net/wwan/iosm/iosm_ipc_devlink.c @@ -2,6 +2,7 @@ /* * Copyright (C) 2020-2021 Intel Corporation. */ +#include <linux/vmalloc.h>

#include "iosm_ipc_chnl_cfg.h" #include "iosm_ipc_coredump.h"

From: Chaitanya Dhere chaitanya.dhere@amd.com

[ Upstream commit 0d5c5c210a4d4e655feb93b379647f0b179cdafe ]

[Why] Recent backports from open source do not have header inclusion pattern that is consistent with inclusion style in the rest of the file. This breaks the internal tool builds as well. A recent commit erronously modified the original DML formula for calculating ActiveClockChangeLatencyHidingY. This resulted in a FCLK deviation from the golden values.

[How] Change the way in which display_mode_vba.h is included so that it is consistent with the inclusion style in rest of the file which also fixes the tool build. Restore the DML formula to its original state to fix the FCLK deviation.

Reviewed-by: Aurabindo Pillai Aurabindo.Pillai@amd.com Reviewed-by: Jun Lei Jun.Lei@amd.com Acked-by: Alan Liu HaoPing.Liu@amd.com Signed-off-by: Chaitanya Dhere chaitanya.dhere@amd.com Tested-by: Daniel Wheeler daniel.wheeler@amd.com Signed-off-by: Alex Deucher alexander.deucher@amd.com Signed-off-by: Sasha Levin sashal@kernel.org --- .../gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_util_32.c | 2 +- .../gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_util_32.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_util_32.c b/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_util_32.c index 67af8f4df8b8..d9141ef2fefd 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_util_32.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_util_32.c @@ -4396,7 +4396,7 @@ void dml32_CalculateWatermarksMALLUseAndDRAMSpeedChangeSupport(

if (v->NumberOfActiveSurfaces > 1) { ActiveClockChangeLatencyHidingY = ActiveClockChangeLatencyHidingY - - (1 - 1 / v->NumberOfActiveSurfaces) * SwathHeightY[k] * v->HTotal[k] + - (1.0 - 1.0 / v->NumberOfActiveSurfaces) * SwathHeightY[k] * v->HTotal[k] / v->PixelClock[k] / v->VRatio[k]; }

diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_util_32.h b/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_util_32.h index 0b427d89b3c5..f174f5c5ff92 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_util_32.h +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_util_32.h @@ -30,7 +30,7 @@ #include "os_types.h" #include "../dc_features.h" #include "../display_mode_structs.h" -#include "dml/display_mode_vba.h" +#include "../display_mode_vba.h"

unsigned int dml32_dscceComputeDelay( unsigned int bpc,

From: Asher Song Asher.Song@amd.com

[ Upstream commit 30b8e7b8ee3be003e0df85c857c5cd0e0bd58b82 ]

This reverts commit 4545ae2ed3f2f7c3f615a53399c9c8460ee5bca7.

The origin patch "drm/amdgpu: getting fan speed pwm for vega10 properly" works fine. Test failure is caused by test case self.

Signed-off-by: Asher Song Asher.Song@amd.com Reviewed-by: Guchun Chen guchun.chen@amd.com Signed-off-by: Alex Deucher alexander.deucher@amd.com Signed-off-by: Sasha Levin sashal@kernel.org --- .../amd/pm/powerplay/hwmgr/vega10_thermal.c | 25 +++++++++---------- 1 file changed, 12 insertions(+), 13 deletions(-)

diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega10_thermal.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega10_thermal.c index dad3e3741a4e..190af79f3236 100644 --- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega10_thermal.c +++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega10_thermal.c @@ -67,22 +67,21 @@ int vega10_fan_ctrl_get_fan_speed_info(struct pp_hwmgr *hwmgr, int vega10_fan_ctrl_get_fan_speed_pwm(struct pp_hwmgr *hwmgr, uint32_t *speed) { - uint32_t current_rpm; - uint32_t percent = 0; - - if (hwmgr->thermal_controller.fanInfo.bNoFan) - return 0; + struct amdgpu_device *adev = hwmgr->adev; + uint32_t duty100, duty; + uint64_t tmp64;

- if (vega10_get_current_rpm(hwmgr, &current_rpm)) - return -1; + duty100 = REG_GET_FIELD(RREG32_SOC15(THM, 0, mmCG_FDO_CTRL1), + CG_FDO_CTRL1, FMAX_DUTY100); + duty = REG_GET_FIELD(RREG32_SOC15(THM, 0, mmCG_THERMAL_STATUS), + CG_THERMAL_STATUS, FDO_PWM_DUTY);

- if (hwmgr->thermal_controller. - advanceFanControlParameters.usMaxFanRPM != 0) - percent = current_rpm * 255 / - hwmgr->thermal_controller. - advanceFanControlParameters.usMaxFanRPM; + if (!duty100) + return -EINVAL;

- *speed = MIN(percent, 255); + tmp64 = (uint64_t)duty * 255; + do_div(tmp64, duty100); + *speed = MIN((uint32_t)tmp64, 255);

return 0; }

From: Hamza Mahfooz hamza.mahfooz@amd.com

[ Upstream commit 675d84621a24490e1de3d59a4992a17fa9ff92b5 ]

Currently, we are calling fill_dc_dirty_rects() even if PSR isn't supported by the relevant link in amdgpu_dm_commit_planes(), this is undesirable especially because when drm.debug is enabled we are printing messages in fill_dc_dirty_rects() that are only useful for debugging PSR (and confusing otherwise). So, we can instead limit the filling of dirty rectangles to only when PSR is enabled.

Reviewed-by: Leo Li sunpeng.li@amd.com Signed-off-by: Hamza Mahfooz hamza.mahfooz@amd.com Signed-off-by: Alex Deucher alexander.deucher@amd.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c index 7f8eb09b0b7c..9ce100e315c5 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -7650,9 +7650,10 @@ static void amdgpu_dm_commit_planes(struct drm_atomic_state *state, bundle->surface_updates[planes_count].plane_info = &bundle->plane_infos[planes_count];

- fill_dc_dirty_rects(plane, old_plane_state, new_plane_state, - new_crtc_state, - &bundle->flip_addrs[planes_count]); + if (acrtc_state->stream->link->psr_settings.psr_feature_enabled) + fill_dc_dirty_rects(plane, old_plane_state, + new_plane_state, new_crtc_state, + &bundle->flip_addrs[planes_count]);

/* * Only allow immediate flips for fast updates that don't

From: Nathan Chancellor nathan@kernel.org

[ Upstream commit fcae44fd36d052e956e69a64642fc03820968d78 ]

Recently, ld.lld moved from '--undefined-version' to '--no-undefined-version' as the default, which breaks the compat vDSO build:

ld.lld: error: version script assignment of 'LINUX_4.15' to symbol '__vdso_gettimeofday' failed: symbol not defined ld.lld: error: version script assignment of 'LINUX_4.15' to symbol '__vdso_clock_gettime' failed: symbol not defined ld.lld: error: version script assignment of 'LINUX_4.15' to symbol '__vdso_clock_getres' failed: symbol not defined

These symbols are not present in the compat vDSO or the regular vDSO for 32-bit but they are unconditionally included in the version section of the linker script, which is prohibited with '--no-undefined-version'.

Fix this issue by only including the symbols that are actually exported in the version section of the linker script.

Link: https://github.com/ClangBuiltLinux/linux/issues/1756 Signed-off-by: Nathan Chancellor nathan@kernel.org Tested-by: Conor Dooley conor.dooley@microchip.com Link: https://lore.kernel.org/r/20221108171324.3377226-1-nathan@kernel.org/ Signed-off-by: Palmer Dabbelt palmer@rivosinc.com Signed-off-by: Sasha Levin sashal@kernel.org --- arch/riscv/kernel/vdso/Makefile | 3 +++ arch/riscv/kernel/vdso/vdso.lds.S | 2 ++ 2 files changed, 5 insertions(+)

diff --git a/arch/riscv/kernel/vdso/Makefile b/arch/riscv/kernel/vdso/Makefile index 84ac0fe612e7..db6548509bb3 100644 --- a/arch/riscv/kernel/vdso/Makefile +++ b/arch/riscv/kernel/vdso/Makefile @@ -28,6 +28,9 @@ obj-vdso := $(addprefix $(obj)/, $(obj-vdso))

obj-y += vdso.o CPPFLAGS_vdso.lds += -P -C -U$(ARCH) +ifneq ($(filter vgettimeofday, $(vdso-syms)),) +CPPFLAGS_vdso.lds += -DHAS_VGETTIMEOFDAY +endif

# Disable -pg to prevent insert call site CFLAGS_REMOVE_vgettimeofday.o = $(CC_FLAGS_FTRACE) diff --git a/arch/riscv/kernel/vdso/vdso.lds.S b/arch/riscv/kernel/vdso/vdso.lds.S index 01d94aae5bf5..150b1a572e61 100644 --- a/arch/riscv/kernel/vdso/vdso.lds.S +++ b/arch/riscv/kernel/vdso/vdso.lds.S @@ -68,9 +68,11 @@ VERSION LINUX_4.15 { global: __vdso_rt_sigreturn; +#ifdef HAS_VGETTIMEOFDAY __vdso_gettimeofday; __vdso_clock_gettime; __vdso_clock_getres; +#endif __vdso_getcpu; __vdso_flush_icache; local: *;

From: Pavel Begunkov asml.silence@gmail.com

[ Upstream commit 5576035f15dfcc6cb1cec236db40c2c0733b0ba4 ]

Add a lockdep annotation in io_poll_req_insert_locked().

Signed-off-by: Pavel Begunkov asml.silence@gmail.com Link: https://lore.kernel.org/r/8115d8e702733754d0aea119e9b5bb63d1eb8b24.166818465... Signed-off-by: Jens Axboe axboe@kernel.dk Signed-off-by: Sasha Levin sashal@kernel.org --- io_uring/poll.c | 2 ++ 1 file changed, 2 insertions(+)

diff --git a/io_uring/poll.c b/io_uring/poll.c index ba0f68466930..055632e9092a 100644 --- a/io_uring/poll.c +++ b/io_uring/poll.c @@ -116,6 +116,8 @@ static void io_poll_req_insert_locked(struct io_kiocb *req) struct io_hash_table *table = &req->ctx->cancel_table_locked; u32 index = hash_long(req->cqe.user_data, table->hash_bits);

+ lockdep_assert_held(&req->ctx->uring_lock); + hlist_add_head(&req->hash_node, &table->hbs[index].list); }

From: Lev Popov leo@nabam.net

[ Upstream commit 2dcd7e0c821fe9b663f7d3382b6d2faa8edf2129 ]

For "Quartz64 Model A" add missing RTS line to the UART interface used by bluetooth and swap bluetooth host-wakeup and device-wakeup gpio pins to match the boards physical layout. This changes are necessary to make bluetooth provided by the wireless module work.

Also set max-speed on the bluetooth device as it's not automatically detected.

Fixes: b33a22a1e7c4 ("arm64: dts: rockchip: add basic dts for Pine64 Quartz64-A") Signed-off-by: Lev Popov leo@nabam.net Link: https://lore.kernel.org/r/20220926125350.64783-1-leo@nabam.net Signed-off-by: Heiko Stuebner heiko@sntech.de Signed-off-by: Sasha Levin sashal@kernel.org --- arch/arm64/boot/dts/rockchip/rk3566-quartz64-a.dts | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/arch/arm64/boot/dts/rockchip/rk3566-quartz64-a.dts b/arch/arm64/boot/dts/rockchip/rk3566-quartz64-a.dts index a05460b92415..25a8c781f4e7 100644 --- a/arch/arm64/boot/dts/rockchip/rk3566-quartz64-a.dts +++ b/arch/arm64/boot/dts/rockchip/rk3566-quartz64-a.dts @@ -740,7 +740,7 @@ &uart0 {

&uart1 { pinctrl-names = "default"; - pinctrl-0 = <&uart1m0_xfer &uart1m0_ctsn>; + pinctrl-0 = <&uart1m0_xfer &uart1m0_ctsn &uart1m0_rtsn>; status = "okay"; uart-has-rtscts;

@@ -748,13 +748,14 @@ bluetooth { compatible = "brcm,bcm43438-bt"; clocks = <&rk817 1>; clock-names = "lpo"; - device-wakeup-gpios = <&gpio2 RK_PC1 GPIO_ACTIVE_HIGH>; - host-wakeup-gpios = <&gpio2 RK_PC0 GPIO_ACTIVE_HIGH>; + host-wakeup-gpios = <&gpio2 RK_PC1 GPIO_ACTIVE_HIGH>; + device-wakeup-gpios = <&gpio2 RK_PC0 GPIO_ACTIVE_HIGH>; shutdown-gpios = <&gpio2 RK_PB7 GPIO_ACTIVE_HIGH>; pinctrl-names = "default"; pinctrl-0 = <&bt_host_wake_l &bt_wake_l &bt_enable_h>; vbat-supply = <&vcc_sys>; vddio-supply = <&vcca1v8_pmu>; + max-speed = <3000000>; }; };

From: Herbert Xu herbert@gondor.apana.org.au

[ Upstream commit 7f57f8165cb6d2c206e2b9ada53b9e2d6d8af42f ]

The function pfkey_send_acquire may race with pfkey_register (which could even be in a different name space). This may result in a buffer overrun.

Allocating the maximum amount of memory that could be used prevents this.

Reported-by: syzbot+1e9af9185d8850e2c2fa@syzkaller.appspotmail.com Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Herbert Xu herbert@gondor.apana.org.au Reviewed-by: Sabrina Dubroca sd@queasysnail.net Reviewed-by: Eric Dumazet edumazet@google.com Signed-off-by: Steffen Klassert steffen.klassert@secunet.com Signed-off-by: Sasha Levin sashal@kernel.org --- net/key/af_key.c | 32 ++++++++++++++++++++++---------- 1 file changed, 22 insertions(+), 10 deletions(-)

diff --git a/net/key/af_key.c b/net/key/af_key.c index c85df5b958d2..213287814328 100644 --- a/net/key/af_key.c +++ b/net/key/af_key.c @@ -2905,7 +2905,7 @@ static int count_ah_combs(const struct xfrm_tmpl *t) break; if (!aalg->pfkey_supported) continue; - if (aalg_tmpl_set(t, aalg) && aalg->available) + if (aalg_tmpl_set(t, aalg)) sz += sizeof(struct sadb_comb); } return sz + sizeof(struct sadb_prop); @@ -2923,7 +2923,7 @@ static int count_esp_combs(const struct xfrm_tmpl *t) if (!ealg->pfkey_supported) continue;

- if (!(ealg_tmpl_set(t, ealg) && ealg->available)) + if (!(ealg_tmpl_set(t, ealg))) continue;

for (k = 1; ; k++) { @@ -2934,16 +2934,17 @@ static int count_esp_combs(const struct xfrm_tmpl *t) if (!aalg->pfkey_supported) continue;

- if (aalg_tmpl_set(t, aalg) && aalg->available) + if (aalg_tmpl_set(t, aalg)) sz += sizeof(struct sadb_comb); } } return sz + sizeof(struct sadb_prop); }

-static void dump_ah_combs(struct sk_buff *skb, const struct xfrm_tmpl *t) +static int dump_ah_combs(struct sk_buff *skb, const struct xfrm_tmpl *t) { struct sadb_prop *p; + int sz = 0; int i;

p = skb_put(skb, sizeof(struct sadb_prop)); @@ -2971,13 +2972,17 @@ static void dump_ah_combs(struct sk_buff *skb, const struct xfrm_tmpl *t) c->sadb_comb_soft_addtime = 20*60*60; c->sadb_comb_hard_usetime = 8*60*60; c->sadb_comb_soft_usetime = 7*60*60; + sz += sizeof(*c); } } + + return sz + sizeof(*p); }

-static void dump_esp_combs(struct sk_buff *skb, const struct xfrm_tmpl *t) +static int dump_esp_combs(struct sk_buff *skb, const struct xfrm_tmpl *t) { struct sadb_prop *p; + int sz = 0; int i, k;

p = skb_put(skb, sizeof(struct sadb_prop)); @@ -3019,8 +3024,11 @@ static void dump_esp_combs(struct sk_buff *skb, const struct xfrm_tmpl *t) c->sadb_comb_soft_addtime = 20*60*60; c->sadb_comb_hard_usetime = 8*60*60; c->sadb_comb_soft_usetime = 7*60*60; + sz += sizeof(*c); } } + + return sz + sizeof(*p); }

static int key_notify_policy_expire(struct xfrm_policy *xp, const struct km_event *c) @@ -3150,6 +3158,7 @@ static int pfkey_send_acquire(struct xfrm_state *x, struct xfrm_tmpl *t, struct struct sadb_x_sec_ctx *sec_ctx; struct xfrm_sec_ctx *xfrm_ctx; int ctx_size = 0; + int alg_size = 0;

sockaddr_size = pfkey_sockaddr_size(x->props.family); if (!sockaddr_size) @@ -3161,16 +3170,16 @@ static int pfkey_send_acquire(struct xfrm_state *x, struct xfrm_tmpl *t, struct sizeof(struct sadb_x_policy);

if (x->id.proto == IPPROTO_AH) - size += count_ah_combs(t); + alg_size = count_ah_combs(t); else if (x->id.proto == IPPROTO_ESP) - size += count_esp_combs(t); + alg_size = count_esp_combs(t);

if ((xfrm_ctx = x->security)) { ctx_size = PFKEY_ALIGN8(xfrm_ctx->ctx_len); size += sizeof(struct sadb_x_sec_ctx) + ctx_size; }

- skb = alloc_skb(size + 16, GFP_ATOMIC); + skb = alloc_skb(size + alg_size + 16, GFP_ATOMIC); if (skb == NULL) return -ENOMEM;

@@ -3224,10 +3233,13 @@ static int pfkey_send_acquire(struct xfrm_state *x, struct xfrm_tmpl *t, struct pol->sadb_x_policy_priority = xp->priority;

/* Set sadb_comb's. */ + alg_size = 0; if (x->id.proto == IPPROTO_AH) - dump_ah_combs(skb, t); + alg_size = dump_ah_combs(skb, t); else if (x->id.proto == IPPROTO_ESP) - dump_esp_combs(skb, t); + alg_size = dump_esp_combs(skb, t); + + hdr->sadb_msg_len += alg_size / 8;

/* security context */ if (xfrm_ctx) {

From: Linus Walleij linus.walleij@linaro.org

[ Upstream commit 767e684367e4759d9855b184045b7a9d6b19acd2 ]

The call thermal_zone_get_zone_by_name() used to return the thermal zone right away, but recent refactorings in the thermal core has changed this so the thermal zone used by the battery is probed later, and the call returns -ENODEV.

This was always quite fragile. If we get -ENODEV, then return a -EPROBE_DEFER and try again later.

Cc: phone-devel@vger.kernel.org Fixes: 2b0e7ac0841b ("power: supply: ab8500: Integrate thermal zone") Signed-off-by: Linus Walleij linus.walleij@linaro.org Signed-off-by: Sebastian Reichel sebastian.reichel@collabora.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/power/supply/ab8500_btemp.c | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-)

diff --git a/drivers/power/supply/ab8500_btemp.c b/drivers/power/supply/ab8500_btemp.c index 863fabe05bdc..307ee6f71042 100644 --- a/drivers/power/supply/ab8500_btemp.c +++ b/drivers/power/supply/ab8500_btemp.c @@ -725,7 +725,14 @@ static int ab8500_btemp_probe(struct platform_device *pdev) /* Get thermal zone and ADC */ di->tz = thermal_zone_get_zone_by_name("battery-thermal"); if (IS_ERR(di->tz)) { - return dev_err_probe(dev, PTR_ERR(di->tz), + ret = PTR_ERR(di->tz); + /* + * This usually just means we are probing before the thermal + * zone, so just defer. + */ + if (ret == -ENODEV) + ret = -EPROBE_DEFER; + return dev_err_probe(dev, ret, "failed to get battery thermal zone\n"); } di->bat_ctrl = devm_iio_channel_get(dev, "bat_ctrl");

From: Cezary Rojewski cezary.rojewski@intel.com

[ Upstream commit e4746d94d00c52918461bc169e009b6784a38e21 ]

Preliminary step in making snd_hda_codec_device_init() the only constructor for struct hda_codec instances. To do that, existing usage of hdac_ext equivalents has to be dropped.

Reviewed-by: Kai Vehmanen kai.vehmanen@linux.intel.com Reviewed-by: Pierre-Louis Bossart pierre-louis.bossart@linux.intel.com Signed-off-by: Cezary Rojewski cezary.rojewski@intel.com Acked-by: Mark Brown broonie@kernel.org Link: https://lore.kernel.org/r/20220816111727.3218543-2-cezary.rojewski@intel.com Signed-off-by: Takashi Iwai tiwai@suse.de Stable-dep-of: 37882100cd06 ("ASoC: hdac_hda: fix hda pcm buffer overflow issue") Signed-off-by: Sasha Levin sashal@kernel.org --- sound/soc/intel/skylake/skl.c | 29 +++++++++++++++++++++++++++++ 1 file changed, 29 insertions(+)

diff --git a/sound/soc/intel/skylake/skl.c b/sound/soc/intel/skylake/skl.c index aeca58246fc7..33b0ed6b0534 100644 --- a/sound/soc/intel/skylake/skl.c +++ b/sound/soc/intel/skylake/skl.c @@ -689,6 +689,35 @@ static void load_codec_module(struct hda_codec *codec)

#endif /* CONFIG_SND_SOC_INTEL_SKYLAKE_HDAUDIO_CODEC */

+static void skl_codec_device_exit(struct device *dev) +{ + snd_hdac_device_exit(dev_to_hdac_dev(dev)); +} + +static __maybe_unused struct hda_codec *skl_codec_device_init(struct hdac_bus *bus, int addr) +{ + struct hda_codec *codec; + int ret; + + codec = snd_hda_codec_device_init(to_hda_bus(bus), addr, "ehdaudio%dD%d", bus->idx, addr); + if (IS_ERR(codec)) { + dev_err(bus->dev, "device init failed for hdac device\n"); + return codec; + } + + codec->core.type = HDA_DEV_ASOC; + codec->core.dev.release = skl_codec_device_exit; + + ret = snd_hdac_device_register(&codec->core); + if (ret) { + dev_err(bus->dev, "failed to register hdac device\n"); + snd_hdac_device_exit(&codec->core); + return ERR_PTR(ret); + } + + return codec; +} + /* * Probe the given codec address */

From: Cezary Rojewski cezary.rojewski@intel.com

[ Upstream commit 3fd63658caed9494cca1d4789a66d3d2def2a0ab ]

To make snd_hda_codec_device_init() the only constructor for struct hda_codec instances remaining tasks are:

1) no struct may wrap struct hda_codec as its base type 2) bus drivers (skylake and sof) which are the current hdac_ext users need to be adjusted to make use of newly added codec init and exit routines instead 3) as bus drivers (skylake and sof) are to be responsible for creating codec device and assigning it to hdac_hda_priv->codec, hdac_hda_dev_probe() has to be freed of that job

To keep git bisect happy, all of these in made in one-go.

Reviewed-by: Kai Vehmanen kai.vehmanen@linux.intel.com Reviewed-by: Pierre-Louis Bossart pierre-louis.bossart@linux.intel.com Signed-off-by: Cezary Rojewski cezary.rojewski@intel.com Acked-by: Mark Brown broonie@kernel.org Link: https://lore.kernel.org/r/20220816111727.3218543-4-cezary.rojewski@intel.com Signed-off-by: Takashi Iwai tiwai@suse.de Stable-dep-of: 37882100cd06 ("ASoC: hdac_hda: fix hda pcm buffer overflow issue") Signed-off-by: Sasha Levin sashal@kernel.org --- sound/soc/codecs/hdac_hda.c | 26 +++++++----------- sound/soc/codecs/hdac_hda.h | 2 +- sound/soc/intel/boards/hda_dsp_common.c | 2 +- sound/soc/intel/boards/skl_hda_dsp_generic.c | 2 +- sound/soc/intel/skylake/skl.c | 26 ++++++++---------- sound/soc/sof/intel/hda-codec.c | 29 ++++++++------------ 6 files changed, 36 insertions(+), 51 deletions(-)

diff --git a/sound/soc/codecs/hdac_hda.c b/sound/soc/codecs/hdac_hda.c index 8debcee59224..77df4c5b274a 100644 --- a/sound/soc/codecs/hdac_hda.c +++ b/sound/soc/codecs/hdac_hda.c @@ -246,7 +246,7 @@ static int hdac_hda_dai_hw_free(struct snd_pcm_substream *substream, return -EINVAL;

hda_stream = &pcm->stream[substream->stream]; - snd_hda_codec_cleanup(&hda_pvt->codec, hda_stream, substream); + snd_hda_codec_cleanup(hda_pvt->codec, hda_stream, substream);

return 0; } @@ -264,7 +264,7 @@ static int hdac_hda_dai_prepare(struct snd_pcm_substream *substream, int ret = 0;

hda_pvt = snd_soc_component_get_drvdata(component); - hdev = &hda_pvt->codec.core; + hdev = &hda_pvt->codec->core; pcm = snd_soc_find_pcm_from_dai(hda_pvt, dai); if (!pcm) return -EINVAL; @@ -274,7 +274,7 @@ static int hdac_hda_dai_prepare(struct snd_pcm_substream *substream, stream = hda_pvt->pcm[dai->id].stream_tag[substream->stream]; format_val = hda_pvt->pcm[dai->id].format_val[substream->stream];

- ret = snd_hda_codec_prepare(&hda_pvt->codec, hda_stream, + ret = snd_hda_codec_prepare(hda_pvt->codec, hda_stream, stream, format_val, substream); if (ret < 0) dev_err(&hdev->dev, "codec prepare failed %d\n", ret); @@ -299,7 +299,7 @@ static int hdac_hda_dai_open(struct snd_pcm_substream *substream,

hda_stream = &pcm->stream[substream->stream];

- return hda_stream->ops.open(hda_stream, &hda_pvt->codec, substream); + return hda_stream->ops.open(hda_stream, hda_pvt->codec, substream); }

static void hdac_hda_dai_close(struct snd_pcm_substream *substream, @@ -317,7 +317,7 @@ static void hdac_hda_dai_close(struct snd_pcm_substream *substream,

hda_stream = &pcm->stream[substream->stream];

- hda_stream->ops.close(hda_stream, &hda_pvt->codec, substream); + hda_stream->ops.close(hda_stream, hda_pvt->codec, substream);

snd_hda_codec_pcm_put(pcm); } @@ -325,7 +325,7 @@ static void hdac_hda_dai_close(struct snd_pcm_substream *substream, static struct hda_pcm *snd_soc_find_pcm_from_dai(struct hdac_hda_priv *hda_pvt, struct snd_soc_dai *dai) { - struct hda_codec *hcodec = &hda_pvt->codec; + struct hda_codec *hcodec = hda_pvt->codec; struct hda_pcm *cpcm; const char *pcm_name;

@@ -394,8 +394,8 @@ static int hdac_hda_codec_probe(struct snd_soc_component *component) snd_soc_component_get_drvdata(component); struct snd_soc_dapm_context *dapm = snd_soc_component_get_dapm(component); - struct hdac_device *hdev = &hda_pvt->codec.core; - struct hda_codec *hcodec = &hda_pvt->codec; + struct hdac_device *hdev = &hda_pvt->codec->core; + struct hda_codec *hcodec = hda_pvt->codec; struct hdac_ext_link *hlink; hda_codec_patch_t patch; int ret; @@ -515,8 +515,8 @@ static void hdac_hda_codec_remove(struct snd_soc_component *component) { struct hdac_hda_priv *hda_pvt = snd_soc_component_get_drvdata(component); - struct hdac_device *hdev = &hda_pvt->codec.core; - struct hda_codec *codec = &hda_pvt->codec; + struct hdac_device *hdev = &hda_pvt->codec->core; + struct hda_codec *codec = hda_pvt->codec; struct hdac_ext_link *hlink = NULL;

hlink = snd_hdac_ext_bus_get_link(hdev->bus, dev_name(&hdev->dev)); @@ -584,7 +584,6 @@ static const struct snd_soc_component_driver hdac_hda_codec = { static int hdac_hda_dev_probe(struct hdac_device *hdev) { struct hdac_ext_link *hlink; - struct hdac_hda_priv *hda_pvt; int ret;

/* hold the ref while we probe */ @@ -595,10 +594,6 @@ static int hdac_hda_dev_probe(struct hdac_device *hdev) } snd_hdac_ext_bus_link_get(hdev->bus, hlink);

- hda_pvt = hdac_to_hda_priv(hdev); - if (!hda_pvt) - return -ENOMEM; - /* ASoC specific initialization */ ret = devm_snd_soc_register_component(&hdev->dev, &hdac_hda_codec, hdac_hda_dais, @@ -608,7 +603,6 @@ static int hdac_hda_dev_probe(struct hdac_device *hdev) return ret; }

- dev_set_drvdata(&hdev->dev, hda_pvt); snd_hdac_ext_bus_link_put(hdev->bus, hlink);

return ret; diff --git a/sound/soc/codecs/hdac_hda.h b/sound/soc/codecs/hdac_hda.h index d0efc5e254ae..fc19c34ca00e 100644 --- a/sound/soc/codecs/hdac_hda.h +++ b/sound/soc/codecs/hdac_hda.h @@ -23,7 +23,7 @@ struct hdac_hda_pcm { };

struct hdac_hda_priv { - struct hda_codec codec; + struct hda_codec *codec; struct hdac_hda_pcm pcm[HDAC_LAST_DAI_ID]; bool need_display_power; }; diff --git a/sound/soc/intel/boards/hda_dsp_common.c b/sound/soc/intel/boards/hda_dsp_common.c index 83c7dfbccd9d..04b7d4f7f9e2 100644 --- a/sound/soc/intel/boards/hda_dsp_common.c +++ b/sound/soc/intel/boards/hda_dsp_common.c @@ -54,7 +54,7 @@ int hda_dsp_hdmi_build_controls(struct snd_soc_card *card, return -EINVAL;

hda_pvt = snd_soc_component_get_drvdata(comp); - hcodec = &hda_pvt->codec; + hcodec = hda_pvt->codec;

list_for_each_entry(hpcm, &hcodec->pcm_list_head, list) { spcm = hda_dsp_hdmi_pcm_handle(card, i); diff --git a/sound/soc/intel/boards/skl_hda_dsp_generic.c b/sound/soc/intel/boards/skl_hda_dsp_generic.c index 81144efb4b44..879ebba52832 100644 --- a/sound/soc/intel/boards/skl_hda_dsp_generic.c +++ b/sound/soc/intel/boards/skl_hda_dsp_generic.c @@ -190,7 +190,7 @@ static void skl_set_hda_codec_autosuspend_delay(struct snd_soc_card *card) * all codecs are on the same bus, so it's sufficient * to look up only the first one */ - snd_hda_set_power_save(hda_pvt->codec.bus, + snd_hda_set_power_save(hda_pvt->codec->bus, HDA_CODEC_AUTOSUSPEND_DELAY_MS); break; } diff --git a/sound/soc/intel/skylake/skl.c b/sound/soc/intel/skylake/skl.c index 33b0ed6b0534..c7c1cad2a753 100644 --- a/sound/soc/intel/skylake/skl.c +++ b/sound/soc/intel/skylake/skl.c @@ -694,7 +694,7 @@ static void skl_codec_device_exit(struct device *dev) snd_hdac_device_exit(dev_to_hdac_dev(dev)); }

-static __maybe_unused struct hda_codec *skl_codec_device_init(struct hdac_bus *bus, int addr) +static struct hda_codec *skl_codec_device_init(struct hdac_bus *bus, int addr) { struct hda_codec *codec; int ret; @@ -729,9 +729,8 @@ static int probe_codec(struct hdac_bus *bus, int addr) struct skl_dev *skl = bus_to_skl(bus); #if IS_ENABLED(CONFIG_SND_SOC_INTEL_SKYLAKE_HDAUDIO_CODEC) struct hdac_hda_priv *hda_codec; - int err; #endif - struct hdac_device *hdev; + struct hda_codec *codec;

mutex_lock(&bus->cmd_mutex); snd_hdac_bus_send_cmd(bus, cmd); @@ -747,25 +746,22 @@ static int probe_codec(struct hdac_bus *bus, int addr) if (!hda_codec) return -ENOMEM;

- hda_codec->codec.bus = skl_to_hbus(skl); - hdev = &hda_codec->codec.core; + codec = skl_codec_device_init(bus, addr); + if (IS_ERR(codec)) + return PTR_ERR(codec);

- err = snd_hdac_ext_bus_device_init(bus, addr, hdev, HDA_DEV_ASOC); - if (err < 0) - return err; + hda_codec->codec = codec; + dev_set_drvdata(&codec->core.dev, hda_codec);

/* use legacy bus only for HDA codecs, idisp uses ext bus */ if ((res & 0xFFFF0000) != IDISP_INTEL_VENDOR_ID) { - hdev->type = HDA_DEV_LEGACY; - load_codec_module(&hda_codec->codec); + codec->core.type = HDA_DEV_LEGACY; + load_codec_module(hda_codec->codec); } return 0; #else - hdev = devm_kzalloc(&skl->pci->dev, sizeof(*hdev), GFP_KERNEL); - if (!hdev) - return -ENOMEM; - - return snd_hdac_ext_bus_device_init(bus, addr, hdev, HDA_DEV_ASOC); + codec = skl_codec_device_init(bus, addr); + return PTR_ERR_OR_ZERO(codec); #endif /* CONFIG_SND_SOC_INTEL_SKYLAKE_HDAUDIO_CODEC */ }

diff --git a/sound/soc/sof/intel/hda-codec.c b/sound/soc/sof/intel/hda-codec.c index 4c128ba02340..73336648cd25 100644 --- a/sound/soc/sof/intel/hda-codec.c +++ b/sound/soc/sof/intel/hda-codec.c @@ -114,8 +114,7 @@ static void hda_codec_device_exit(struct device *dev) snd_hdac_device_exit(dev_to_hdac_dev(dev)); }

-static __maybe_unused struct hda_codec * -hda_codec_device_init(struct hdac_bus *bus, int addr, int type) +static struct hda_codec *hda_codec_device_init(struct hdac_bus *bus, int addr, int type) { struct hda_codec *codec; int ret; @@ -145,11 +144,10 @@ static int hda_codec_probe(struct snd_sof_dev *sdev, int address, { #if IS_ENABLED(CONFIG_SND_SOC_SOF_HDA_AUDIO_CODEC) struct hdac_hda_priv *hda_priv; - struct hda_codec *codec; int type = HDA_DEV_LEGACY; #endif struct hda_bus *hbus = sof_to_hbus(sdev); - struct hdac_device *hdev; + struct hda_codec *codec; u32 hda_cmd = (address << 28) | (AC_NODE_ROOT << 20) | (AC_VERB_PARAMETERS << 8) | AC_PAR_VENDOR_ID; u32 resp = -1; @@ -172,20 +170,20 @@ static int hda_codec_probe(struct snd_sof_dev *sdev, int address, if (!hda_priv) return -ENOMEM;

- hda_priv->codec.bus = hbus; - hdev = &hda_priv->codec.core; - codec = &hda_priv->codec; - /* only probe ASoC codec drivers for HDAC-HDMI */ if (!hda_codec_use_common_hdmi && (resp & 0xFFFF0000) == IDISP_VID_INTEL) type = HDA_DEV_ASOC;

- ret = snd_hdac_ext_bus_device_init(&hbus->core, address, hdev, type); + codec = hda_codec_device_init(&hbus->core, address, type); + ret = PTR_ERR_OR_ZERO(codec); if (ret < 0) return ret;

+ hda_priv->codec = codec; + dev_set_drvdata(&codec->core.dev, hda_priv); + if ((resp & 0xFFFF0000) == IDISP_VID_INTEL) { - if (!hdev->bus->audio_component) { + if (!hbus->core.audio_component) { dev_dbg(sdev->dev, "iDisp hw present but no driver\n"); ret = -ENOENT; @@ -211,15 +209,12 @@ static int hda_codec_probe(struct snd_sof_dev *sdev, int address,

out: if (ret < 0) { - snd_hdac_device_unregister(hdev); - put_device(&hdev->dev); + snd_hdac_device_unregister(&codec->core); + put_device(&codec->core.dev); } #else - hdev = devm_kzalloc(sdev->dev, sizeof(*hdev), GFP_KERNEL); - if (!hdev) - return -ENOMEM; - - ret = snd_hdac_ext_bus_device_init(&hbus->core, address, hdev, HDA_DEV_ASOC); + codec = hda_codec_device_init(&hbus->core, address); + ret = PTR_ERR_OR_ZERO(codec); #endif

return ret;

From: Detlev Casanova detlev.casanova@collabora.com

[ Upstream commit 0bb8e9b36b5b7f2e77892981ff6c27ee831d8026 ]

Since commit bf2aebccddef ("ASoC: sgtl5000: Fix noise on shutdown/remove"), the device power control registers are reset when the driver is removed/shutdown.

This is an issue when the device is configured to use the PLL clock. The device will stop responding if it is still configured to use the PLL clock but the PLL clock is powered down.

When rebooting linux, the probe function will show: sgtl5000 0-000a: Error reading chip id -11

Make sure that the CHIP_CLK_CTRL is reset to its default value before powering down the device.

Fixes: bf2aebccddef ("ASoC: sgtl5000: Fix noise on shutdown/remove") Signed-off-by: Detlev Casanova detlev.casanova@collabora.com Reviewed-by: Fabio Estevam festevam@gmail.com Link: https://lore.kernel.org/r/20221110190612.1341469-1-detlev.casanova@collabora... Signed-off-by: Mark Brown broonie@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- sound/soc/codecs/sgtl5000.c | 1 + 1 file changed, 1 insertion(+)

diff --git a/sound/soc/codecs/sgtl5000.c b/sound/soc/codecs/sgtl5000.c index 3fafd9fc5cfd..75a45ad55aa8 100644 --- a/sound/soc/codecs/sgtl5000.c +++ b/sound/soc/codecs/sgtl5000.c @@ -1794,6 +1794,7 @@ static int sgtl5000_i2c_remove(struct i2c_client *client) { struct sgtl5000_priv *sgtl5000 = i2c_get_clientdata(client);

+ regmap_write(sgtl5000->regmap, SGTL5000_CHIP_CLK_CTRL, SGTL5000_CHIP_CLK_CTRL_DEFAULT); regmap_write(sgtl5000->regmap, SGTL5000_CHIP_DIG_POWER, SGTL5000_DIG_POWER_DEFAULT); regmap_write(sgtl5000->regmap, SGTL5000_CHIP_ANA_POWER, SGTL5000_ANA_POWER_DEFAULT);

From: Vitaly Kuznetsov vkuznets@redhat.com

[ Upstream commit ee6815416380bc069b7dcbdff0682d4c53617527 ]

Commit e5d9b714fe40 ("x86/hyperv: fix root partition faults when writing to VP assist page MSR") moved 'wrmsrl(HV_X64_MSR_VP_ASSIST_PAGE)' under 'if (*hvp)' condition. This works for root partition as hv_cpu_die() does memunmap() and sets 'hv_vp_assist_page[cpu]' to NULL but breaks non-root partitions as hv_cpu_die() doesn't free 'hv_vp_assist_page[cpu]' for them. This causes VP assist page to remain unset after CPU offline/online cycle:

$ rdmsr -p 24 0x40000073 10212f001 $ echo 0 > /sys/devices/system/cpu/cpu24/online $ echo 1 > /sys/devices/system/cpu/cpu24/online $ rdmsr -p 24 0x40000073 0

Fix the issue by always writing to HV_X64_MSR_VP_ASSIST_PAGE in hv_cpu_init(). Note, checking 'if (!*hvp)', for root partition is pointless as hv_cpu_die() always sets 'hv_vp_assist_page[cpu]' to NULL (and it's also NULL initially).

Note: the fact that 'hv_vp_assist_page[cpu]' is reset to NULL may present a (potential) issue for KVM. While Hyper-V uses CPUHP_AP_ONLINE_DYN stage in CPU hotplug, KVM uses CPUHP_AP_KVM_STARTING which comes earlier in CPU teardown sequence. It is theoretically possible that Enlightened VMCS is still in use. It is unclear if the issue is real and if using KVM with Hyper-V root partition is even possible.

While on it, drop the unneeded smp_processor_id() call from hv_cpu_init().

Fixes: e5d9b714fe40 ("x86/hyperv: fix root partition faults when writing to VP assist page MSR") Signed-off-by: Vitaly Kuznetsov vkuznets@redhat.com Reviewed-by: Michael Kelley mikelley@microsoft.com Link: https://lore.kernel.org/r/20221103190601.399343-1-vkuznets@redhat.com Signed-off-by: Wei Liu wei.liu@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- arch/x86/hyperv/hv_init.c | 54 +++++++++++++++++++-------------------- 1 file changed, 26 insertions(+), 28 deletions(-)

diff --git a/arch/x86/hyperv/hv_init.c b/arch/x86/hyperv/hv_init.c index 3de6d8b53367..a0165df3c4d8 100644 --- a/arch/x86/hyperv/hv_init.c +++ b/arch/x86/hyperv/hv_init.c @@ -77,7 +77,7 @@ static int hyperv_init_ghcb(void) static int hv_cpu_init(unsigned int cpu) { union hv_vp_assist_msr_contents msr = { 0 }; - struct hv_vp_assist_page **hvp = &hv_vp_assist_page[smp_processor_id()]; + struct hv_vp_assist_page **hvp = &hv_vp_assist_page[cpu]; int ret;

ret = hv_common_cpu_init(cpu); @@ -87,34 +87,32 @@ static int hv_cpu_init(unsigned int cpu) if (!hv_vp_assist_page) return 0;

- if (!*hvp) { - if (hv_root_partition) { - /* - * For root partition we get the hypervisor provided VP assist - * page, instead of allocating a new page. - */ - rdmsrl(HV_X64_MSR_VP_ASSIST_PAGE, msr.as_uint64); - *hvp = memremap(msr.pfn << - HV_X64_MSR_VP_ASSIST_PAGE_ADDRESS_SHIFT, - PAGE_SIZE, MEMREMAP_WB); - } else { - /* - * The VP assist page is an "overlay" page (see Hyper-V TLFS's - * Section 5.2.1 "GPA Overlay Pages"). Here it must be zeroed - * out to make sure we always write the EOI MSR in - * hv_apic_eoi_write() *after* the EOI optimization is disabled - * in hv_cpu_die(), otherwise a CPU may not be stopped in the - * case of CPU offlining and the VM will hang. - */ + if (hv_root_partition) { + /* + * For root partition we get the hypervisor provided VP assist + * page, instead of allocating a new page. + */ + rdmsrl(HV_X64_MSR_VP_ASSIST_PAGE, msr.as_uint64); + *hvp = memremap(msr.pfn << HV_X64_MSR_VP_ASSIST_PAGE_ADDRESS_SHIFT, + PAGE_SIZE, MEMREMAP_WB); + } else { + /* + * The VP assist page is an "overlay" page (see Hyper-V TLFS's + * Section 5.2.1 "GPA Overlay Pages"). Here it must be zeroed + * out to make sure we always write the EOI MSR in + * hv_apic_eoi_write() *after* the EOI optimization is disabled + * in hv_cpu_die(), otherwise a CPU may not be stopped in the + * case of CPU offlining and the VM will hang. + */ + if (!*hvp) *hvp = __vmalloc(PAGE_SIZE, GFP_KERNEL | __GFP_ZERO); - if (*hvp) - msr.pfn = vmalloc_to_pfn(*hvp); - } - WARN_ON(!(*hvp)); - if (*hvp) { - msr.enable = 1; - wrmsrl(HV_X64_MSR_VP_ASSIST_PAGE, msr.as_uint64); - } + if (*hvp) + msr.pfn = vmalloc_to_pfn(*hvp); + + } + if (!WARN_ON(!(*hvp))) { + msr.enable = 1; + wrmsrl(HV_X64_MSR_VP_ASSIST_PAGE, msr.as_uint64); }

return hyperv_init_ghcb();

From: Dexuan Cui decui@microsoft.com

[ Upstream commit c234ba8042920fa83635808dc5673f36869ca280 ]

Jeffrey added Multi-MSI support to the pci-hyperv driver by the 4 patches: 08e61e861a0e ("PCI: hv: Fix multi-MSI to allow more than one MSI vector") 455880dfe292 ("PCI: hv: Fix hv_arch_irq_unmask() for multi-MSI") b4b77778ecc5 ("PCI: hv: Reuse existing IRTE allocation in compose_msi_msg()") a2bad844a67b ("PCI: hv: Fix interrupt mapping for multi-MSI")

It turns out that the third patch (b4b77778ecc5) causes a performance regression because all the interrupts now happen on 1 physical CPU (or two pCPUs, if one pCPU doesn't have enough vectors). When a guest has many PCI devices, it may suffer from soft lockups if the workload is heavy, e.g., see https://lwn.net/ml/linux-kernel/20220804025104.15673-1-decui@microsoft.com/

Commit b4b77778ecc5 itself is good. The real issue is that the hypercall in hv_irq_unmask() -> hv_arch_irq_unmask() -> hv_do_hypercall(HVCALL_RETARGET_INTERRUPT...) only changes the target virtual CPU rather than physical CPU; with b4b77778ecc5, the pCPU is determined only once in hv_compose_msi_msg() where only vCPU0 is specified; consequently the hypervisor only uses 1 target pCPU for all the interrupts.

Note: before b4b77778ecc5, the pCPU is determined twice, and when the pCPU is determined the second time, the vCPU in the effective affinity mask is used (i.e., it isn't always vCPU0), so the hypervisor chooses different pCPU for each interrupt.

The hypercall will be fixed in future to update the pCPU as well, but that will take quite a while, so let's restore the old behavior in hv_compose_msi_msg(), i.e., don't reuse the existing IRTE allocation for single-MSI and MSI-X; for multi-MSI, we choose the vCPU in a round-robin manner for each PCI device, so the interrupts of different devices can happen on different pCPUs, though the interrupts of each device happen on some single pCPU.

The hypercall fix may not be backported to all old versions of Hyper-V, so we want to have this guest side change forever (or at least till we're sure the old affected versions of Hyper-V are no longer supported).

Fixes: b4b77778ecc5 ("PCI: hv: Reuse existing IRTE allocation in compose_msi_msg()") Co-developed-by: Jeffrey Hugo quic_jhugo@quicinc.com Signed-off-by: Jeffrey Hugo quic_jhugo@quicinc.com Co-developed-by: Carl Vanderlip quic_carlv@quicinc.com Signed-off-by: Carl Vanderlip quic_carlv@quicinc.com Signed-off-by: Dexuan Cui decui@microsoft.com Reviewed-by: Michael Kelley mikelley@microsoft.com Link: https://lore.kernel.org/r/20221104222953.11356-1-decui@microsoft.com Signed-off-by: Wei Liu wei.liu@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/pci/controller/pci-hyperv.c | 90 ++++++++++++++++++++++++----- 1 file changed, 75 insertions(+), 15 deletions(-)

diff --git a/drivers/pci/controller/pci-hyperv.c b/drivers/pci/controller/pci-hyperv.c index ba64284eaf9f..f1ec8931dfbc 100644 --- a/drivers/pci/controller/pci-hyperv.c +++ b/drivers/pci/controller/pci-hyperv.c @@ -1613,7 +1613,7 @@ static void hv_pci_compose_compl(void *context, struct pci_response *resp, }

static u32 hv_compose_msi_req_v1( - struct pci_create_interrupt *int_pkt, const struct cpumask *affinity, + struct pci_create_interrupt *int_pkt, u32 slot, u8 vector, u16 vector_count) { int_pkt->message_type.type = PCI_CREATE_INTERRUPT_MESSAGE; @@ -1631,6 +1631,35 @@ static u32 hv_compose_msi_req_v1( return sizeof(*int_pkt); }

+/* + * The vCPU selected by hv_compose_multi_msi_req_get_cpu() and + * hv_compose_msi_req_get_cpu() is a "dummy" vCPU because the final vCPU to be + * interrupted is specified later in hv_irq_unmask() and communicated to Hyper-V + * via the HVCALL_RETARGET_INTERRUPT hypercall. But the choice of dummy vCPU is + * not irrelevant because Hyper-V chooses the physical CPU to handle the + * interrupts based on the vCPU specified in message sent to the vPCI VSP in + * hv_compose_msi_msg(). Hyper-V's choice of pCPU is not visible to the guest, + * but assigning too many vPCI device interrupts to the same pCPU can cause a + * performance bottleneck. So we spread out the dummy vCPUs to influence Hyper-V + * to spread out the pCPUs that it selects. + * + * For the single-MSI and MSI-X cases, it's OK for hv_compose_msi_req_get_cpu() + * to always return the same dummy vCPU, because a second call to + * hv_compose_msi_msg() contains the "real" vCPU, causing Hyper-V to choose a + * new pCPU for the interrupt. But for the multi-MSI case, the second call to + * hv_compose_msi_msg() exits without sending a message to the vPCI VSP, so the + * original dummy vCPU is used. This dummy vCPU must be round-robin'ed so that + * the pCPUs are spread out. All interrupts for a multi-MSI device end up using + * the same pCPU, even though the vCPUs will be spread out by later calls + * to hv_irq_unmask(), but that is the best we can do now. + * + * With Hyper-V in Nov 2022, the HVCALL_RETARGET_INTERRUPT hypercall does *not* + * cause Hyper-V to reselect the pCPU based on the specified vCPU. Such an + * enhancement is planned for a future version. With that enhancement, the + * dummy vCPU selection won't matter, and interrupts for the same multi-MSI + * device will be spread across multiple pCPUs. + */ + /* * Create MSI w/ dummy vCPU set targeting just one vCPU, overwritten * by subsequent retarget in hv_irq_unmask(). @@ -1640,18 +1669,39 @@ static int hv_compose_msi_req_get_cpu(const struct cpumask *affinity) return cpumask_first_and(affinity, cpu_online_mask); }

-static u32 hv_compose_msi_req_v2( - struct pci_create_interrupt2 *int_pkt, const struct cpumask *affinity, - u32 slot, u8 vector, u16 vector_count) +/* + * Make sure the dummy vCPU values for multi-MSI don't all point to vCPU0. + */ +static int hv_compose_multi_msi_req_get_cpu(void) { + static DEFINE_SPINLOCK(multi_msi_cpu_lock); + + /* -1 means starting with CPU 0 */ + static int cpu_next = -1; + + unsigned long flags; int cpu;

+ spin_lock_irqsave(&multi_msi_cpu_lock, flags); + + cpu_next = cpumask_next_wrap(cpu_next, cpu_online_mask, nr_cpu_ids, + false); + cpu = cpu_next; + + spin_unlock_irqrestore(&multi_msi_cpu_lock, flags); + + return cpu; +} + +static u32 hv_compose_msi_req_v2( + struct pci_create_interrupt2 *int_pkt, int cpu, + u32 slot, u8 vector, u16 vector_count) +{ int_pkt->message_type.type = PCI_CREATE_INTERRUPT_MESSAGE2; int_pkt->wslot.slot = slot; int_pkt->int_desc.vector = vector; int_pkt->int_desc.vector_count = vector_count; int_pkt->int_desc.delivery_mode = DELIVERY_MODE; - cpu = hv_compose_msi_req_get_cpu(affinity); int_pkt->int_desc.processor_array[0] = hv_cpu_number_to_vp_number(cpu); int_pkt->int_desc.processor_count = 1; @@ -1660,18 +1710,15 @@ static u32 hv_compose_msi_req_v2( }

static u32 hv_compose_msi_req_v3( - struct pci_create_interrupt3 *int_pkt, const struct cpumask *affinity, + struct pci_create_interrupt3 *int_pkt, int cpu, u32 slot, u32 vector, u16 vector_count) { - int cpu; - int_pkt->message_type.type = PCI_CREATE_INTERRUPT_MESSAGE3; int_pkt->wslot.slot = slot; int_pkt->int_desc.vector = vector; int_pkt->int_desc.reserved = 0; int_pkt->int_desc.vector_count = vector_count; int_pkt->int_desc.delivery_mode = DELIVERY_MODE; - cpu = hv_compose_msi_req_get_cpu(affinity); int_pkt->int_desc.processor_array[0] = hv_cpu_number_to_vp_number(cpu); int_pkt->int_desc.processor_count = 1; @@ -1715,12 +1762,18 @@ static void hv_compose_msi_msg(struct irq_data *data, struct msi_msg *msg) struct pci_create_interrupt3 v3; } int_pkts; } __packed ctxt; + bool multi_msi; u64 trans_id; u32 size; int ret; + int cpu; + + msi_desc = irq_data_get_msi_desc(data); + multi_msi = !msi_desc->pci.msi_attrib.is_msix && + msi_desc->nvec_used > 1;

/* Reuse the previous allocation */ - if (data->chip_data) { + if (data->chip_data && multi_msi) { int_desc = data->chip_data; msg->address_hi = int_desc->address >> 32; msg->address_lo = int_desc->address & 0xffffffff; @@ -1728,7 +1781,6 @@ static void hv_compose_msi_msg(struct irq_data *data, struct msi_msg *msg) return; }

- msi_desc = irq_data_get_msi_desc(data); pdev = msi_desc_to_pci_dev(msi_desc); dest = irq_data_get_effective_affinity_mask(data); pbus = pdev->bus; @@ -1738,11 +1790,18 @@ static void hv_compose_msi_msg(struct irq_data *data, struct msi_msg *msg) if (!hpdev) goto return_null_message;

+ /* Free any previous message that might have already been composed. */ + if (data->chip_data && !multi_msi) { + int_desc = data->chip_data; + data->chip_data = NULL; + hv_int_desc_free(hpdev, int_desc); + } + int_desc = kzalloc(sizeof(*int_desc), GFP_ATOMIC); if (!int_desc) goto drop_reference;

- if (!msi_desc->pci.msi_attrib.is_msix && msi_desc->nvec_used > 1) { + if (multi_msi) { /* * If this is not the first MSI of Multi MSI, we already have * a mapping. Can exit early. @@ -1767,9 +1826,11 @@ static void hv_compose_msi_msg(struct irq_data *data, struct msi_msg *msg) */ vector = 32; vector_count = msi_desc->nvec_used; + cpu = hv_compose_multi_msi_req_get_cpu(); } else { vector = hv_msi_get_int_vector(data); vector_count = 1; + cpu = hv_compose_msi_req_get_cpu(dest); }

/* @@ -1785,7 +1846,6 @@ static void hv_compose_msi_msg(struct irq_data *data, struct msi_msg *msg) switch (hbus->protocol_version) { case PCI_PROTOCOL_VERSION_1_1: size = hv_compose_msi_req_v1(&ctxt.int_pkts.v1, - dest, hpdev->desc.win_slot.slot, (u8)vector, vector_count); @@ -1794,7 +1854,7 @@ static void hv_compose_msi_msg(struct irq_data *data, struct msi_msg *msg) case PCI_PROTOCOL_VERSION_1_2: case PCI_PROTOCOL_VERSION_1_3: size = hv_compose_msi_req_v2(&ctxt.int_pkts.v2, - dest, + cpu, hpdev->desc.win_slot.slot, (u8)vector, vector_count); @@ -1802,7 +1862,7 @@ static void hv_compose_msi_msg(struct irq_data *data, struct msi_msg *msg)

case PCI_PROTOCOL_VERSION_1_4: size = hv_compose_msi_req_v3(&ctxt.int_pkts.v3, - dest, + cpu, hpdev->desc.win_slot.slot, vector, vector_count);

From: Jiasheng Jiang jiasheng@iscas.ac.cn

[ Upstream commit 60591bbf6d5eb44f275eb733943b7757325c1b60 ]

As the devm_kcalloc may return NULL pointer, it should be better to check the return value in order to avoid NULL poineter dereference.

Fixes: 349dd23931d1 ("ASoC: max98373: don't access volatile registers in bias level off") Signed-off-by: Jiasheng Jiang jiasheng@iscas.ac.cn Link: https://lore.kernel.org/r/20221116082508.17418-1-jiasheng@iscas.ac.cn Signed-off-by: Mark Brown broonie@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- sound/soc/codecs/max98373-i2c.c | 4 ++++ 1 file changed, 4 insertions(+)

diff --git a/sound/soc/codecs/max98373-i2c.c b/sound/soc/codecs/max98373-i2c.c index 3e04c7f0cce4..ec0905df65d1 100644 --- a/sound/soc/codecs/max98373-i2c.c +++ b/sound/soc/codecs/max98373-i2c.c @@ -549,6 +549,10 @@ static int max98373_i2c_probe(struct i2c_client *i2c) max98373->cache = devm_kcalloc(&i2c->dev, max98373->cache_num, sizeof(*max98373->cache), GFP_KERNEL); + if (!max98373->cache) { + ret = -ENOMEM; + return ret; + }

for (i = 0; i < max98373->cache_num; i++) max98373->cache[i].reg = max98373_i2c_cache_reg[i];

From: Yang Yingliang yangyingliang@huawei.com

[ Upstream commit 7920e0fbced429ab18ad4402e3914146a6a0921b ]

I got the following OOB report:

BUG: KASAN: slab-out-of-bounds in validate_desc+0xba/0x109 Read of size 8 at addr ffff888107db8ff0 by task python3/253 Call Trace: <TASK> dump_stack_lvl+0x67/0x83 print_report+0x178/0x4b0 kasan_report+0x90/0x190 validate_desc+0xba/0x109 gpiod_set_value_cansleep+0x40/0x5a regulator_ena_gpio_ctrl+0x93/0xfc _regulator_do_enable.cold.61+0x89/0x163 set_machine_constraints+0x140a/0x159c regulator_register.cold.73+0x762/0x10cd devm_regulator_register+0x57/0xb0 rt5759_probe+0x3a0/0x4ac [rt5759_regulator]

The desc used in validate_desc() is passed from 'reg_cfg.ena_gpiod', which is not initialized. Fix this by initializing 'reg_cfg' to 0.

Fixes: 7b36ddb208bd ("regulator: rt5759: Add support for Richtek RT5759 DCDC converter") Signed-off-by: Yang Yingliang yangyingliang@huawei.com Link: https://lore.kernel.org/r/20221116092943.1668326-1-yangyingliang@huawei.com Signed-off-by: Mark Brown broonie@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/regulator/rt5759-regulator.c | 1 + 1 file changed, 1 insertion(+)

diff --git a/drivers/regulator/rt5759-regulator.c b/drivers/regulator/rt5759-regulator.c index 6b96899eb27e..8488417f4b2c 100644 --- a/drivers/regulator/rt5759-regulator.c +++ b/drivers/regulator/rt5759-regulator.c @@ -243,6 +243,7 @@ static int rt5759_regulator_register(struct rt5759_priv *priv) if (priv->chip_type == CHIP_TYPE_RT5759A) reg_desc->uV_step = RT5759A_STEP_UV;

+ memset(&reg_cfg, 0, sizeof(reg_cfg)); reg_cfg.dev = priv->dev; reg_cfg.of_node = np; reg_cfg.init_data = of_get_regulator_init_data(priv->dev, np, reg_desc);

From: Yang Yingliang yangyingliang@huawei.com

[ Upstream commit 1f386d6894d0f1b7de8ef640c41622ddd698e7ab ]

I got a UAF report as following:

================================================================== BUG: KASAN: use-after-free in __lock_acquire+0x935/0x2060 Read of size 8 at addr ffff88810e838220 by task python3/268 Call Trace: <TASK> dump_stack_lvl+0x67/0x83 print_report+0x178/0x4b0 kasan_report+0x90/0x190 __lock_acquire+0x935/0x2060 lock_acquire+0x156/0x400 _raw_spin_lock+0x2a/0x40 lockref_get+0x11/0x30 simple_recursive_removal+0x41/0x440 debugfs_remove.part.12+0x32/0x50 debugfs_remove+0x29/0x30 _regulator_put.cold.54+0x3e/0x27f regulator_put+0x1f/0x30 release_nodes+0x6a/0xa0 devres_release_all+0xf8/0x150

Allocated by task 37: kasan_save_stack+0x1c/0x40 kasan_set_track+0x21/0x30 __kasan_slab_alloc+0x5d/0x70 slab_post_alloc_hook+0x62/0x510 kmem_cache_alloc_lru+0x222/0x5a0 __d_alloc+0x31/0x440 d_alloc+0x30/0xf0 d_alloc_parallel+0xc4/0xd20 __lookup_slow+0x15e/0x2f0 lookup_one_len+0x13a/0x150 start_creating+0xea/0x190 debugfs_create_dir+0x1e/0x210 create_regulator+0x254/0x4e0 _regulator_get+0x2a1/0x467 _devm_regulator_get+0x5a/0xb0 regulator_virtual_probe+0xb9/0x1a0

Freed by task 30: kasan_save_stack+0x1c/0x40 kasan_set_track+0x21/0x30 kasan_save_free_info+0x2a/0x50 __kasan_slab_free+0x102/0x190 kmem_cache_free+0xf6/0x600 rcu_core+0x54c/0x12b0 __do_softirq+0xf2/0x5e3

Last potentially related work creation: kasan_save_stack+0x1c/0x40 __kasan_record_aux_stack+0x98/0xb0 call_rcu+0x42/0x700 dentry_free+0x6c/0xd0 __dentry_kill+0x23b/0x2d0 dput.part.31+0x431/0x780 simple_recursive_removal+0xa9/0x440 debugfs_remove.part.12+0x32/0x50 debugfs_remove+0x29/0x30 regulator_unregister+0xe3/0x230 release_nodes+0x6a/0xa0

==================================================================

Here is how happened:

processor A processor B regulator_register() rdev_init_debugfs() rdev->debugfs = debugfs_create_dir() devm_regulator_get() rdev = regulator_dev_lookup() create_regulator(rdev) // using rdev->debugfs as parent debugfs_create_dir(rdev->debugfs)

mfd_remove_devices_fn() release_nodes() regulator_unregister() // free rdev->debugfs debugfs_remove_recursive(rdev->debugfs) release_nodes() destroy_regulator() debugfs_remove_recursive() <- causes UAF

In devm_regulator_get(), after getting rdev, the refcount is get, so fix this by moving debugfs_remove_recursive() to regulator_dev_release(), then it can be proctected by the refcount, the 'rdev->debugfs' can not be freed until the refcount is 0.

Fixes: 5de705194e98 ("regulator: Add basic per consumer debugfs") Signed-off-by: Yang Yingliang yangyingliang@huawei.com Link: https://lore.kernel.org/r/20221116033706.3595812-1-yangyingliang@huawei.com Signed-off-by: Mark Brown broonie@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/regulator/core.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/regulator/core.c b/drivers/regulator/core.c index 5f82a996dbea..c0f368f1b49f 100644 --- a/drivers/regulator/core.c +++ b/drivers/regulator/core.c @@ -5138,6 +5138,7 @@ static void regulator_dev_release(struct device *dev) { struct regulator_dev *rdev = dev_get_drvdata(dev);

+ debugfs_remove_recursive(rdev->debugfs); kfree(rdev->constraints); of_node_put(rdev->dev.of_node); kfree(rdev); @@ -5653,7 +5654,6 @@ void regulator_unregister(struct regulator_dev *rdev)

mutex_lock(&regulator_list_mutex);

- debugfs_remove_recursive(rdev->debugfs); WARN_ON(rdev->open_count); regulator_remove_coupling(rdev); unset_regulator_supplies(rdev);

From: Samuel Holland samuel@sholland.org

[ Upstream commit 077686da0e2162c4ea5ae0df205849c2a7a84479 ]

When communicating with a PMIC during system poweroff (pm_power_off()), IRQs are disabled and we are in a RCU read-side critical section, so we cannot use wait_for_completion_io_timeout(). Instead, poll the status register for transfer completion.

Fixes: d787dcdb9c8f ("bus: sunxi-rsb: Add driver for Allwinner Reduced Serial Bus") Signed-off-by: Samuel Holland samuel@sholland.org Reviewed-by: Jernej Skrabec jernej.skrabec@gmail.com Link: https://lore.kernel.org/r/20221114015749.28490-3-samuel@sholland.org Signed-off-by: Jernej Skrabec jernej.skrabec@gmail.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/bus/sunxi-rsb.c | 29 +++++++++++++++++++++-------- 1 file changed, 21 insertions(+), 8 deletions(-)

diff --git a/drivers/bus/sunxi-rsb.c b/drivers/bus/sunxi-rsb.c index 17343cd75338..3aa91aed3bf7 100644 --- a/drivers/bus/sunxi-rsb.c +++ b/drivers/bus/sunxi-rsb.c @@ -267,6 +267,9 @@ EXPORT_SYMBOL_GPL(sunxi_rsb_driver_register); /* common code that starts a transfer */ static int _sunxi_rsb_run_xfer(struct sunxi_rsb *rsb) { + u32 int_mask, status; + bool timeout; + if (readl(rsb->regs + RSB_CTRL) & RSB_CTRL_START_TRANS) { dev_dbg(rsb->dev, "RSB transfer still in progress\n"); return -EBUSY; @@ -274,13 +277,23 @@ static int _sunxi_rsb_run_xfer(struct sunxi_rsb *rsb)

reinit_completion(&rsb->complete);

- writel(RSB_INTS_LOAD_BSY | RSB_INTS_TRANS_ERR | RSB_INTS_TRANS_OVER, - rsb->regs + RSB_INTE); + int_mask = RSB_INTS_LOAD_BSY | RSB_INTS_TRANS_ERR | RSB_INTS_TRANS_OVER; + writel(int_mask, rsb->regs + RSB_INTE); writel(RSB_CTRL_START_TRANS | RSB_CTRL_GLOBAL_INT_ENB, rsb->regs + RSB_CTRL);

- if (!wait_for_completion_io_timeout(&rsb->complete, - msecs_to_jiffies(100))) { + if (irqs_disabled()) { + timeout = readl_poll_timeout_atomic(rsb->regs + RSB_INTS, + status, (status & int_mask), + 10, 100000); + writel(status, rsb->regs + RSB_INTS); + } else { + timeout = !wait_for_completion_io_timeout(&rsb->complete, + msecs_to_jiffies(100)); + status = rsb->status; + } + + if (timeout) { dev_dbg(rsb->dev, "RSB timeout\n");

/* abort the transfer */ @@ -292,18 +305,18 @@ static int _sunxi_rsb_run_xfer(struct sunxi_rsb *rsb) return -ETIMEDOUT; }

- if (rsb->status & RSB_INTS_LOAD_BSY) { + if (status & RSB_INTS_LOAD_BSY) { dev_dbg(rsb->dev, "RSB busy\n"); return -EBUSY; }

- if (rsb->status & RSB_INTS_TRANS_ERR) { - if (rsb->status & RSB_INTS_TRANS_ERR_ACK) { + if (status & RSB_INTS_TRANS_ERR) { + if (status & RSB_INTS_TRANS_ERR_ACK) { dev_dbg(rsb->dev, "RSB slave nack\n"); return -EINVAL; }

- if (rsb->status & RSB_INTS_TRANS_ERR_DATA) { + if (status & RSB_INTS_TRANS_ERR_DATA) { dev_dbg(rsb->dev, "RSB transfer data error\n"); return -EIO; }

From: Krishna Yarlagadda kyarlagadda@nvidia.com

[ Upstream commit 2197aa6b0aa236b9896a09b9d08d6924d18b84f6 ]

controller data alloc is done with client device data causing duplicate resource error. Allocate memory using controller device when using devm

Fixes: f89d2cc3967a ("spi: tegra210-quad: use devm call for cdata memory")

Signed-off-by: Krishna Yarlagadda kyarlagadda@nvidia.com Reviewed-by: Jon Hunter jonathanh@nvidia.com Tested-by: Jon Hunter jonathanh@nvidia.com Link: https://lore.kernel.org/r/20221117070320.18720-1-kyarlagadda@nvidia.com Signed-off-by: Mark Brown broonie@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/spi/spi-tegra210-quad.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/spi/spi-tegra210-quad.c b/drivers/spi/spi-tegra210-quad.c index 10f0c5a6e0dc..9f356612ba7e 100644 --- a/drivers/spi/spi-tegra210-quad.c +++ b/drivers/spi/spi-tegra210-quad.c @@ -924,8 +924,9 @@ static int tegra_qspi_start_transfer_one(struct spi_device *spi, static struct tegra_qspi_client_data *tegra_qspi_parse_cdata_dt(struct spi_device *spi) { struct tegra_qspi_client_data *cdata; + struct tegra_qspi *tqspi = spi_master_get_devdata(spi->master);

- cdata = devm_kzalloc(&spi->dev, sizeof(*cdata), GFP_KERNEL); + cdata = devm_kzalloc(tqspi->dev, sizeof(*cdata), GFP_KERNEL); if (!cdata) return NULL;

From: Paolo Abeni pabeni@redhat.com

[ Upstream commit 22b29557aef3c9d673c887911b504c6d47009de4 ]

On slow or busy VM, some test-cases still fail because the data transfer completes before the endpoint manipulation actually took effect.

Address the issue by artificially increasing the runtime for the relevant test-cases.

Fixes: ef360019db40 ("selftests: mptcp: signal addresses testcases") Closes: https://github.com/multipath-tcp/mptcp_net-next/issues/309 Reviewed-by: Mat Martineau mathew.j.martineau@linux.intel.com Signed-off-by: Paolo Abeni pabeni@redhat.com Signed-off-by: Mat Martineau mathew.j.martineau@linux.intel.com Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- tools/testing/selftests/net/mptcp/mptcp_join.sh | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh index ff83ef426df5..e52b79440123 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_join.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh @@ -2105,7 +2105,7 @@ remove_tests() pm_nl_set_limits $ns2 1 3 pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow pm_nl_add_endpoint $ns2 10.0.4.2 flags subflow - run_tests $ns1 $ns2 10.0.1.1 0 -1 -2 slow + run_tests $ns1 $ns2 10.0.1.1 0 -1 -2 speed_10 chk_join_nr 3 3 3 chk_add_nr 1 1 chk_rm_nr 2 2 @@ -2118,7 +2118,7 @@ remove_tests() pm_nl_add_endpoint $ns1 10.0.3.1 flags signal pm_nl_add_endpoint $ns1 10.0.4.1 flags signal pm_nl_set_limits $ns2 3 3 - run_tests $ns1 $ns2 10.0.1.1 0 -3 0 slow + run_tests $ns1 $ns2 10.0.1.1 0 -3 0 speed_10 chk_join_nr 3 3 3 chk_add_nr 3 3 chk_rm_nr 3 3 invert @@ -2131,7 +2131,7 @@ remove_tests() pm_nl_add_endpoint $ns1 10.0.3.1 flags signal pm_nl_add_endpoint $ns1 10.0.14.1 flags signal pm_nl_set_limits $ns2 3 3 - run_tests $ns1 $ns2 10.0.1.1 0 -3 0 slow + run_tests $ns1 $ns2 10.0.1.1 0 -3 0 speed_10 chk_join_nr 1 1 1 chk_add_nr 3 3 chk_rm_nr 3 1 invert

From: Matthieu Baerts matthieu.baerts@tessares.net

[ Upstream commit 3de88b95c4d436d78afc0266a0bed76c35ddeb62 ]

The estimated time was supposing the rate was expressed in mibit (bit * 1024^2) but it is in mbit (bit * 1000^2).

This makes the threshold higher but in a more realistic way to avoid false positives reported by CI instances.

Before this patch, the thresholds were at 7561/4005ms and now they are at 7906/4178ms.

While at it, also fix a typo in the linked comment, spotted by Mat.

Closes: https://github.com/multipath-tcp/mptcp_net-next/issues/310 Fixes: 1a418cb8e888 ("mptcp: simult flow self-tests") Suggested-by: Paolo Abeni pabeni@redhat.com Reviewed-by: Mat Martineau mathew.j.martineau@linux.intel.com Signed-off-by: Matthieu Baerts matthieu.baerts@tessares.net Signed-off-by: Mat Martineau mathew.j.martineau@linux.intel.com Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- tools/testing/selftests/net/mptcp/simult_flows.sh | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/tools/testing/selftests/net/mptcp/simult_flows.sh b/tools/testing/selftests/net/mptcp/simult_flows.sh index ffa13a957a36..40aeb5a71a2a 100755 --- a/tools/testing/selftests/net/mptcp/simult_flows.sh +++ b/tools/testing/selftests/net/mptcp/simult_flows.sh @@ -247,9 +247,10 @@ run_test() tc -n $ns2 qdisc add dev ns2eth1 root netem rate ${rate1}mbit $delay1 tc -n $ns2 qdisc add dev ns2eth2 root netem rate ${rate2}mbit $delay2

- # time is measured in ms, account for transfer size, affegated link speed + # time is measured in ms, account for transfer size, aggregated link speed # and header overhead (10%) - local time=$((size * 8 * 1000 * 10 / (( $rate1 + $rate2) * 1024 *1024 * 9) )) + # ms byte -> bit 10% mbit -> kbit -> bit 10% + local time=$((1000 * size * 8 * 10 / ((rate1 + rate2) * 1000 * 1000 * 9) ))

# mptcp_connect will do some sleeps to allow the mp_join handshake # completion (see mptcp_connect): 200ms on each side, add some slack

From: Thomas Zeitlhofer thomas.zeitlhofer+lkml@ze-it.at

[ Upstream commit 8207f253a097fe15c93d85ac15ebb73c5e39e1e1 ]

Commit 0ff4eb3d5ebb ("neighbour: make proxy_queue.qlen limit per-device") introduced the length counter qlen in struct neigh_parms. There are separate neigh_parms instances for IPv4/ARP and IPv6/ND, and while the family specific qlen is incremented in pneigh_enqueue(), the mentioned commit decrements always the IPv4/ARP specific qlen, regardless of the currently processed family, in pneigh_queue_purge() and neigh_proxy_process().

As a result, with IPv6/ND, the family specific qlen is only incremented (and never decremented) until it exceeds PROXY_QLEN, and then, according to the check in pneigh_enqueue(), neighbor solicitations are not answered anymore. As an example, this is noted when using the subnet-router anycast address to access a Linux router. After a certain amount of time (in the observed case, qlen exceeded PROXY_QLEN after two days), the Linux router stops answering neighbor solicitations for its subnet-router anycast address and effectively becomes unreachable.

Another result with IPv6/ND is that the IPv4/ARP specific qlen is decremented more often than incremented. This leads to negative qlen values, as a signed integer has been used for the length counter qlen, and potentially to an integer overflow.

Fix this by introducing the helper function neigh_parms_qlen_dec(), which decrements the family specific qlen. Thereby, make use of the existing helper function neigh_get_dev_parms_rcu(), whose definition therefore needs to be placed earlier in neighbour.c. Take the family member from struct neigh_table to determine the currently processed family and appropriately call neigh_parms_qlen_dec() from pneigh_queue_purge() and neigh_proxy_process().

Additionally, use an unsigned integer for the length counter qlen.

Fixes: 0ff4eb3d5ebb ("neighbour: make proxy_queue.qlen limit per-device") Signed-off-by: Thomas Zeitlhofer thomas.zeitlhofer+lkml@ze-it.at Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- include/net/neighbour.h | 2 +- net/core/neighbour.c | 58 +++++++++++++++++++++-------------------- 2 files changed, 31 insertions(+), 29 deletions(-)

diff --git a/include/net/neighbour.h b/include/net/neighbour.h index 3827a6b395fd..bce6b228cf56 100644 --- a/include/net/neighbour.h +++ b/include/net/neighbour.h @@ -83,7 +83,7 @@ struct neigh_parms { struct rcu_head rcu_head;

int reachable_time; - int qlen; + u32 qlen; int data[NEIGH_VAR_DATA_MAX]; DECLARE_BITMAP(data_state, NEIGH_VAR_DATA_MAX); }; diff --git a/net/core/neighbour.c b/net/core/neighbour.c index 84755db81e9d..35f5a3125808 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -307,7 +307,31 @@ static int neigh_del_timer(struct neighbour *n) return 0; }

-static void pneigh_queue_purge(struct sk_buff_head *list, struct net *net) +static struct neigh_parms *neigh_get_dev_parms_rcu(struct net_device *dev, + int family) +{ + switch (family) { + case AF_INET: + return __in_dev_arp_parms_get_rcu(dev); + case AF_INET6: + return __in6_dev_nd_parms_get_rcu(dev); + } + return NULL; +} + +static void neigh_parms_qlen_dec(struct net_device *dev, int family) +{ + struct neigh_parms *p; + + rcu_read_lock(); + p = neigh_get_dev_parms_rcu(dev, family); + if (p) + p->qlen--; + rcu_read_unlock(); +} + +static void pneigh_queue_purge(struct sk_buff_head *list, struct net *net, + int family) { struct sk_buff_head tmp; unsigned long flags; @@ -321,13 +345,7 @@ static void pneigh_queue_purge(struct sk_buff_head *list, struct net *net) struct net_device *dev = skb->dev;

if (net == NULL || net_eq(dev_net(dev), net)) { - struct in_device *in_dev; - - rcu_read_lock(); - in_dev = __in_dev_get_rcu(dev); - if (in_dev) - in_dev->arp_parms->qlen--; - rcu_read_unlock(); + neigh_parms_qlen_dec(dev, family); __skb_unlink(skb, list); __skb_queue_tail(&tmp, skb); } @@ -409,7 +427,8 @@ static int __neigh_ifdown(struct neigh_table *tbl, struct net_device *dev, write_lock_bh(&tbl->lock); neigh_flush_dev(tbl, dev, skip_perm); pneigh_ifdown_and_unlock(tbl, dev); - pneigh_queue_purge(&tbl->proxy_queue, dev ? dev_net(dev) : NULL); + pneigh_queue_purge(&tbl->proxy_queue, dev ? dev_net(dev) : NULL, + tbl->family); if (skb_queue_empty_lockless(&tbl->proxy_queue)) del_timer_sync(&tbl->proxy_timer); return 0; @@ -1621,13 +1640,8 @@ static void neigh_proxy_process(struct timer_list *t)

if (tdif <= 0) { struct net_device *dev = skb->dev; - struct in_device *in_dev;

- rcu_read_lock(); - in_dev = __in_dev_get_rcu(dev); - if (in_dev) - in_dev->arp_parms->qlen--; - rcu_read_unlock(); + neigh_parms_qlen_dec(dev, tbl->family); __skb_unlink(skb, &tbl->proxy_queue);

if (tbl->proxy_redo && netif_running(dev)) { @@ -1821,7 +1835,7 @@ int neigh_table_clear(int index, struct neigh_table *tbl) cancel_delayed_work_sync(&tbl->managed_work); cancel_delayed_work_sync(&tbl->gc_work); del_timer_sync(&tbl->proxy_timer); - pneigh_queue_purge(&tbl->proxy_queue, NULL); + pneigh_queue_purge(&tbl->proxy_queue, NULL, tbl->family); neigh_ifdown(tbl, NULL); if (atomic_read(&tbl->entries)) pr_crit("neighbour leakage\n"); @@ -3542,18 +3556,6 @@ static int proc_unres_qlen(struct ctl_table *ctl, int write, return ret; }

-static struct neigh_parms *neigh_get_dev_parms_rcu(struct net_device *dev, - int family) -{ - switch (family) { - case AF_INET: - return __in_dev_arp_parms_get_rcu(dev); - case AF_INET6: - return __in6_dev_nd_parms_get_rcu(dev); - } - return NULL; -} - static void neigh_copy_dflt_parms(struct net *net, struct neigh_parms *p, int index) {

From: Mahesh Bandewar maheshb@google.com

[ Upstream commit 40b9d1ab63f5c4f3cb69450044d07b45e5af72e1 ]

Recently syzkaller discovered the issue of disappearing lower device (NETDEV_UNREGISTER) while the virtual device (like macvlan) is still having it as a lower device. So it's just a matter of time similar discovery will be made for IPvlan device setup. So fixing it preemptively. Also while at it, add a refcount tracker.

Fixes: 2ad7bf363841 ("ipvlan: Initial check-in of the IPVLAN driver.") Signed-off-by: Mahesh Bandewar maheshb@google.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ipvlan/ipvlan.h | 1 + drivers/net/ipvlan/ipvlan_main.c | 2 ++ 2 files changed, 3 insertions(+)

diff --git a/drivers/net/ipvlan/ipvlan.h b/drivers/net/ipvlan/ipvlan.h index de94921cbef9..025e0c19ec25 100644 --- a/drivers/net/ipvlan/ipvlan.h +++ b/drivers/net/ipvlan/ipvlan.h @@ -98,6 +98,7 @@ struct ipvl_port { struct sk_buff_head backlog; int count; struct ida ida; + netdevice_tracker dev_tracker; };

struct ipvl_skb_cb { diff --git a/drivers/net/ipvlan/ipvlan_main.c b/drivers/net/ipvlan/ipvlan_main.c index 49ba8a50dfb1..9043bcd1b41d 100644 --- a/drivers/net/ipvlan/ipvlan_main.c +++ b/drivers/net/ipvlan/ipvlan_main.c @@ -83,6 +83,7 @@ static int ipvlan_port_create(struct net_device *dev) if (err) goto err;

+ netdev_hold(dev, &port->dev_tracker, GFP_KERNEL); return 0;

err: @@ -95,6 +96,7 @@ static void ipvlan_port_destroy(struct net_device *dev) struct ipvl_port *port = ipvlan_port_get_rtnl(dev); struct sk_buff *skb;

+ netdev_put(dev, &port->dev_tracker); if (port->mode == IPVLAN_MODE_L3S) ipvlan_l3s_unregister(port); netdev_rx_handler_unregister(dev);

From: Vladimir Oltean vladimir.oltean@nxp.com

[ Upstream commit 24deec6b9e4a051635f75777844ffc184644fec9 ]

You'd think people know that the internal 100BASE-TX PHY on the SJA1110 responds only to clause 22 MDIO transactions, but they don't :)

When a clause 45 transaction is attempted, sja1105_base_tx_mdio_read() and sja1105_base_tx_mdio_write() don't expect "reg" to contain bit 30 set (MII_ADDR_C45) and pack this value into the SPI transaction buffer.

But the field in the SPI buffer has a width smaller than 30 bits, so we see this confusing message from the packing() API rather than a proper rejection of C45 transactions:

Call trace: dump_stack+0x1c/0x38 sja1105_pack+0xbc/0xc0 [sja1105] sja1105_xfer+0x114/0x2b0 [sja1105] sja1105_xfer_u32+0x44/0xf4 [sja1105] sja1105_base_tx_mdio_read+0x44/0x7c [sja1105] mdiobus_read+0x44/0x80 get_phy_c45_ids+0x70/0x234 get_phy_device+0x68/0x15c fwnode_mdiobus_register_phy+0x74/0x240 of_mdiobus_register+0x13c/0x380 sja1105_mdiobus_register+0x368/0x490 [sja1105] sja1105_setup+0x94/0x119c [sja1105] Cannot store 401d2405 inside bits 24-4 (would truncate)

Fixes: 5a8f09748ee7 ("net: dsa: sja1105: register the MDIO buses for 100base-T1 and 100base-TX") Signed-off-by: Vladimir Oltean vladimir.oltean@nxp.com Reviewed-by: Andrew Lunn andrew@lunn.ch Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/dsa/sja1105/sja1105_mdio.c | 6 ++++++ 1 file changed, 6 insertions(+)

diff --git a/drivers/net/dsa/sja1105/sja1105_mdio.c b/drivers/net/dsa/sja1105/sja1105_mdio.c index 215dd17ca790..4059fcc8c832 100644 --- a/drivers/net/dsa/sja1105/sja1105_mdio.c +++ b/drivers/net/dsa/sja1105/sja1105_mdio.c @@ -256,6 +256,9 @@ static int sja1105_base_tx_mdio_read(struct mii_bus *bus, int phy, int reg) u32 tmp; int rc;

+ if (reg & MII_ADDR_C45) + return -EOPNOTSUPP; + rc = sja1105_xfer_u32(priv, SPI_READ, regs->mdio_100base_tx + reg, &tmp, NULL); if (rc < 0) @@ -272,6 +275,9 @@ static int sja1105_base_tx_mdio_write(struct mii_bus *bus, int phy, int reg, const struct sja1105_regs *regs = priv->info->regs; u32 tmp = val;

+ if (reg & MII_ADDR_C45) + return -EOPNOTSUPP; + return sja1105_xfer_u32(priv, SPI_WRITE, regs->mdio_100base_tx + reg, &tmp, NULL); }

From: Wang Hai wanghai38@huawei.com

[ Upstream commit 2360f9b8c4e81d242d4cbf99d630a2fffa681fab ]

In pch_gbe_xmit_frame(), NETDEV_TX_OK will be returned whether pch_gbe_tx_queue() sends data successfully or not, so pch_gbe_tx_queue() needs to free skb before returning. But pch_gbe_tx_queue() returns without freeing skb in case of dma_map_single() fails. Add dev_kfree_skb_any() to fix it.

Fixes: 77555ee72282 ("net: Add Gigabit Ethernet driver of Topcliff PCH") Signed-off-by: Wang Hai wanghai38@huawei.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c | 1 + 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c index 46da937ad27f..98792907a4c3 100644 --- a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c +++ b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c @@ -1143,6 +1143,7 @@ static void pch_gbe_tx_queue(struct pch_gbe_adapter *adapter, buffer_info->dma = 0; buffer_info->time_stamp = 0; tx_ring->next_to_use = ring_num; + dev_kfree_skb_any(skb); return; } buffer_info->mapped = true;

From: Daniel Xu dxu@dxuuu.xyz

[ Upstream commit 52d1aa8b8249ff477aaa38b6f74a8ced780d079c ]

nf_conn:mark can be read from and written to in parallel. Use READ_ONCE()/WRITE_ONCE() for reads and writes to prevent unwanted compiler optimizations.

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Daniel Xu dxu@dxuuu.xyz Signed-off-by: Pablo Neira Ayuso pablo@netfilter.org Signed-off-by: Sasha Levin sashal@kernel.org --- net/core/flow_dissector.c | 2 +- net/ipv4/netfilter/ipt_CLUSTERIP.c | 4 ++-- net/netfilter/nf_conntrack_core.c | 2 +- net/netfilter/nf_conntrack_netlink.c | 24 ++++++++++++++---------- net/netfilter/nf_conntrack_standalone.c | 2 +- net/netfilter/nft_ct.c | 6 +++--- net/netfilter/xt_connmark.c | 18 ++++++++++-------- net/openvswitch/conntrack.c | 8 ++++---- net/sched/act_connmark.c | 4 ++-- net/sched/act_ct.c | 8 ++++---- net/sched/act_ctinfo.c | 6 +++--- 11 files changed, 45 insertions(+), 39 deletions(-)

diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c index 7105529abb0f..c433b1fb961a 100644 --- a/net/core/flow_dissector.c +++ b/net/core/flow_dissector.c @@ -272,7 +272,7 @@ skb_flow_dissect_ct(const struct sk_buff *skb, key->ct_zone = ct->zone.id; #endif #if IS_ENABLED(CONFIG_NF_CONNTRACK_MARK) - key->ct_mark = ct->mark; + key->ct_mark = READ_ONCE(ct->mark); #endif

cl = nf_ct_labels_find(ct); diff --git a/net/ipv4/netfilter/ipt_CLUSTERIP.c b/net/ipv4/netfilter/ipt_CLUSTERIP.c index f8e176c77d1c..b3cc416ed292 100644 --- a/net/ipv4/netfilter/ipt_CLUSTERIP.c +++ b/net/ipv4/netfilter/ipt_CLUSTERIP.c @@ -435,7 +435,7 @@ clusterip_tg(struct sk_buff *skb, const struct xt_action_param *par)

switch (ctinfo) { case IP_CT_NEW: - ct->mark = hash; + WRITE_ONCE(ct->mark, hash); break; case IP_CT_RELATED: case IP_CT_RELATED_REPLY: @@ -452,7 +452,7 @@ clusterip_tg(struct sk_buff *skb, const struct xt_action_param *par) #ifdef DEBUG nf_ct_dump_tuple_ip(&ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple); #endif - pr_debug("hash=%u ct_hash=%u ", hash, ct->mark); + pr_debug("hash=%u ct_hash=%u ", hash, READ_ONCE(ct->mark)); if (!clusterip_responsible(cipinfo->config, hash)) { pr_debug("not responsible\n"); return NF_DROP; diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index 8f261cd5b3a5..60289c074eef 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -1781,7 +1781,7 @@ init_conntrack(struct net *net, struct nf_conn *tmpl, }

#ifdef CONFIG_NF_CONNTRACK_MARK - ct->mark = exp->master->mark; + ct->mark = READ_ONCE(exp->master->mark); #endif #ifdef CONFIG_NF_CONNTRACK_SECMARK ct->secmark = exp->master->secmark; diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index 7562b215b932..d71150a40fb0 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -328,9 +328,9 @@ ctnetlink_dump_timestamp(struct sk_buff *skb, const struct nf_conn *ct) }

#ifdef CONFIG_NF_CONNTRACK_MARK -static int ctnetlink_dump_mark(struct sk_buff *skb, const struct nf_conn *ct) +static int ctnetlink_dump_mark(struct sk_buff *skb, u32 mark) { - if (nla_put_be32(skb, CTA_MARK, htonl(ct->mark))) + if (nla_put_be32(skb, CTA_MARK, htonl(mark))) goto nla_put_failure; return 0;

@@ -543,7 +543,7 @@ static int ctnetlink_dump_extinfo(struct sk_buff *skb, static int ctnetlink_dump_info(struct sk_buff *skb, struct nf_conn *ct) { if (ctnetlink_dump_status(skb, ct) < 0 || - ctnetlink_dump_mark(skb, ct) < 0 || + ctnetlink_dump_mark(skb, READ_ONCE(ct->mark)) < 0 || ctnetlink_dump_secctx(skb, ct) < 0 || ctnetlink_dump_id(skb, ct) < 0 || ctnetlink_dump_use(skb, ct) < 0 || @@ -722,6 +722,7 @@ ctnetlink_conntrack_event(unsigned int events, const struct nf_ct_event *item) struct sk_buff *skb; unsigned int type; unsigned int flags = 0, group; + u32 mark; int err;

if (events & (1 << IPCT_DESTROY)) { @@ -826,8 +827,9 @@ ctnetlink_conntrack_event(unsigned int events, const struct nf_ct_event *item) }

#ifdef CONFIG_NF_CONNTRACK_MARK - if ((events & (1 << IPCT_MARK) || ct->mark) - && ctnetlink_dump_mark(skb, ct) < 0) + mark = READ_ONCE(ct->mark); + if ((events & (1 << IPCT_MARK) || mark) && + ctnetlink_dump_mark(skb, mark) < 0) goto nla_put_failure; #endif nlmsg_end(skb, nlh); @@ -1154,7 +1156,7 @@ static int ctnetlink_filter_match(struct nf_conn *ct, void *data) }

#ifdef CONFIG_NF_CONNTRACK_MARK - if ((ct->mark & filter->mark.mask) != filter->mark.val) + if ((READ_ONCE(ct->mark) & filter->mark.mask) != filter->mark.val) goto ignore_entry; #endif status = (u32)READ_ONCE(ct->status); @@ -2002,9 +2004,9 @@ static void ctnetlink_change_mark(struct nf_conn *ct, mask = ~ntohl(nla_get_be32(cda[CTA_MARK_MASK]));

mark = ntohl(nla_get_be32(cda[CTA_MARK])); - newmark = (ct->mark & mask) ^ mark; - if (newmark != ct->mark) - ct->mark = newmark; + newmark = (READ_ONCE(ct->mark) & mask) ^ mark; + if (newmark != READ_ONCE(ct->mark)) + WRITE_ONCE(ct->mark, newmark); } #endif

@@ -2669,6 +2671,7 @@ static int __ctnetlink_glue_build(struct sk_buff *skb, struct nf_conn *ct) { const struct nf_conntrack_zone *zone; struct nlattr *nest_parms; + u32 mark;

zone = nf_ct_zone(ct);

@@ -2730,7 +2733,8 @@ static int __ctnetlink_glue_build(struct sk_buff *skb, struct nf_conn *ct) goto nla_put_failure;

#ifdef CONFIG_NF_CONNTRACK_MARK - if (ct->mark && ctnetlink_dump_mark(skb, ct) < 0) + mark = READ_ONCE(ct->mark); + if (mark && ctnetlink_dump_mark(skb, mark) < 0) goto nla_put_failure; #endif if (ctnetlink_dump_labels(skb, ct) < 0) diff --git a/net/netfilter/nf_conntrack_standalone.c b/net/netfilter/nf_conntrack_standalone.c index 4ffe84c5a82c..bca839ab1ae8 100644 --- a/net/netfilter/nf_conntrack_standalone.c +++ b/net/netfilter/nf_conntrack_standalone.c @@ -366,7 +366,7 @@ static int ct_seq_show(struct seq_file *s, void *v) goto release;

#if defined(CONFIG_NF_CONNTRACK_MARK) - seq_printf(s, "mark=%u ", ct->mark); + seq_printf(s, "mark=%u ", READ_ONCE(ct->mark)); #endif

ct_show_secctx(s, ct); diff --git a/net/netfilter/nft_ct.c b/net/netfilter/nft_ct.c index a3f01f209a53..641dc21f92b4 100644 --- a/net/netfilter/nft_ct.c +++ b/net/netfilter/nft_ct.c @@ -98,7 +98,7 @@ static void nft_ct_get_eval(const struct nft_expr *expr, return; #ifdef CONFIG_NF_CONNTRACK_MARK case NFT_CT_MARK: - *dest = ct->mark; + *dest = READ_ONCE(ct->mark); return; #endif #ifdef CONFIG_NF_CONNTRACK_SECMARK @@ -297,8 +297,8 @@ static void nft_ct_set_eval(const struct nft_expr *expr, switch (priv->key) { #ifdef CONFIG_NF_CONNTRACK_MARK case NFT_CT_MARK: - if (ct->mark != value) { - ct->mark = value; + if (READ_ONCE(ct->mark) != value) { + WRITE_ONCE(ct->mark, value); nf_conntrack_event_cache(IPCT_MARK, ct); } break; diff --git a/net/netfilter/xt_connmark.c b/net/netfilter/xt_connmark.c index e5ebc0810675..ad3c033db64e 100644 --- a/net/netfilter/xt_connmark.c +++ b/net/netfilter/xt_connmark.c @@ -30,6 +30,7 @@ connmark_tg_shift(struct sk_buff *skb, const struct xt_connmark_tginfo2 *info) u_int32_t new_targetmark; struct nf_conn *ct; u_int32_t newmark; + u_int32_t oldmark;

ct = nf_ct_get(skb, &ctinfo); if (ct == NULL) @@ -37,14 +38,15 @@ connmark_tg_shift(struct sk_buff *skb, const struct xt_connmark_tginfo2 *info)

switch (info->mode) { case XT_CONNMARK_SET: - newmark = (ct->mark & ~info->ctmask) ^ info->ctmark; + oldmark = READ_ONCE(ct->mark); + newmark = (oldmark & ~info->ctmask) ^ info->ctmark; if (info->shift_dir == D_SHIFT_RIGHT) newmark >>= info->shift_bits; else newmark <<= info->shift_bits;

- if (ct->mark != newmark) { - ct->mark = newmark; + if (READ_ONCE(ct->mark) != newmark) { + WRITE_ONCE(ct->mark, newmark); nf_conntrack_event_cache(IPCT_MARK, ct); } break; @@ -55,15 +57,15 @@ connmark_tg_shift(struct sk_buff *skb, const struct xt_connmark_tginfo2 *info) else new_targetmark <<= info->shift_bits;

- newmark = (ct->mark & ~info->ctmask) ^ + newmark = (READ_ONCE(ct->mark) & ~info->ctmask) ^ new_targetmark; - if (ct->mark != newmark) { - ct->mark = newmark; + if (READ_ONCE(ct->mark) != newmark) { + WRITE_ONCE(ct->mark, newmark); nf_conntrack_event_cache(IPCT_MARK, ct); } break; case XT_CONNMARK_RESTORE: - new_targetmark = (ct->mark & info->ctmask); + new_targetmark = (READ_ONCE(ct->mark) & info->ctmask); if (info->shift_dir == D_SHIFT_RIGHT) new_targetmark >>= info->shift_bits; else @@ -126,7 +128,7 @@ connmark_mt(const struct sk_buff *skb, struct xt_action_param *par) if (ct == NULL) return false;

- return ((ct->mark & info->mask) == info->mark) ^ info->invert; + return ((READ_ONCE(ct->mark) & info->mask) == info->mark) ^ info->invert; }

static int connmark_mt_check(const struct xt_mtchk_param *par) diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c index 4e70df91d0f2..fc5b374fe568 100644 --- a/net/openvswitch/conntrack.c +++ b/net/openvswitch/conntrack.c @@ -152,7 +152,7 @@ static u8 ovs_ct_get_state(enum ip_conntrack_info ctinfo) static u32 ovs_ct_get_mark(const struct nf_conn *ct) { #if IS_ENABLED(CONFIG_NF_CONNTRACK_MARK) - return ct ? ct->mark : 0; + return ct ? READ_ONCE(ct->mark) : 0; #else return 0; #endif @@ -340,9 +340,9 @@ static int ovs_ct_set_mark(struct nf_conn *ct, struct sw_flow_key *key, #if IS_ENABLED(CONFIG_NF_CONNTRACK_MARK) u32 new_mark;

- new_mark = ct_mark | (ct->mark & ~(mask)); - if (ct->mark != new_mark) { - ct->mark = new_mark; + new_mark = ct_mark | (READ_ONCE(ct->mark) & ~(mask)); + if (READ_ONCE(ct->mark) != new_mark) { + WRITE_ONCE(ct->mark, new_mark); if (nf_ct_is_confirmed(ct)) nf_conntrack_event_cache(IPCT_MARK, ct); key->ct.mark = new_mark; diff --git a/net/sched/act_connmark.c b/net/sched/act_connmark.c index 09e2aafc8943..0deb4e96a6c2 100644 --- a/net/sched/act_connmark.c +++ b/net/sched/act_connmark.c @@ -62,7 +62,7 @@ static int tcf_connmark_act(struct sk_buff *skb, const struct tc_action *a,

c = nf_ct_get(skb, &ctinfo); if (c) { - skb->mark = c->mark; + skb->mark = READ_ONCE(c->mark); /* using overlimits stats to count how many packets marked */ ca->tcf_qstats.overlimits++; goto out; @@ -82,7 +82,7 @@ static int tcf_connmark_act(struct sk_buff *skb, const struct tc_action *a, c = nf_ct_tuplehash_to_ctrack(thash); /* using overlimits stats to count how many packets marked */ ca->tcf_qstats.overlimits++; - skb->mark = c->mark; + skb->mark = READ_ONCE(c->mark); nf_ct_put(c);

out: diff --git a/net/sched/act_ct.c b/net/sched/act_ct.c index 5950974ae8f6..a015915e5b72 100644 --- a/net/sched/act_ct.c +++ b/net/sched/act_ct.c @@ -178,7 +178,7 @@ static void tcf_ct_flow_table_add_action_meta(struct nf_conn *ct, entry = tcf_ct_flow_table_flow_action_get_next(action); entry->id = FLOW_ACTION_CT_METADATA; #if IS_ENABLED(CONFIG_NF_CONNTRACK_MARK) - entry->ct_metadata.mark = ct->mark; + entry->ct_metadata.mark = READ_ONCE(ct->mark); #endif ctinfo = dir == IP_CT_DIR_ORIGINAL ? IP_CT_ESTABLISHED : IP_CT_ESTABLISHED_REPLY; @@ -940,9 +940,9 @@ static void tcf_ct_act_set_mark(struct nf_conn *ct, u32 mark, u32 mask) if (!mask) return;

- new_mark = mark | (ct->mark & ~(mask)); - if (ct->mark != new_mark) { - ct->mark = new_mark; + new_mark = mark | (READ_ONCE(ct->mark) & ~(mask)); + if (READ_ONCE(ct->mark) != new_mark) { + WRITE_ONCE(ct->mark, new_mark); if (nf_ct_is_confirmed(ct)) nf_conntrack_event_cache(IPCT_MARK, ct); } diff --git a/net/sched/act_ctinfo.c b/net/sched/act_ctinfo.c index 0281e45987a4..65a20f3c9514 100644 --- a/net/sched/act_ctinfo.c +++ b/net/sched/act_ctinfo.c @@ -33,7 +33,7 @@ static void tcf_ctinfo_dscp_set(struct nf_conn *ct, struct tcf_ctinfo *ca, { u8 dscp, newdscp;

- newdscp = (((ct->mark & cp->dscpmask) >> cp->dscpmaskshift) << 2) & + newdscp = (((READ_ONCE(ct->mark) & cp->dscpmask) >> cp->dscpmaskshift) << 2) & ~INET_ECN_MASK;

switch (proto) { @@ -73,7 +73,7 @@ static void tcf_ctinfo_cpmark_set(struct nf_conn *ct, struct tcf_ctinfo *ca, struct sk_buff *skb) { ca->stats_cpmark_set++; - skb->mark = ct->mark & cp->cpmarkmask; + skb->mark = READ_ONCE(ct->mark) & cp->cpmarkmask; }

static int tcf_ctinfo_act(struct sk_buff *skb, const struct tc_action *a, @@ -131,7 +131,7 @@ static int tcf_ctinfo_act(struct sk_buff *skb, const struct tc_action *a, }

if (cp->mode & CTINFO_MODE_DSCP) - if (!cp->dscpstatemask || (ct->mark & cp->dscpstatemask)) + if (!cp->dscpstatemask || (READ_ONCE(ct->mark) & cp->dscpstatemask)) tcf_ctinfo_dscp_set(ct, ca, cp, skb, wlen, proto);

if (cp->mode & CTINFO_MODE_CPMARK)

From: Ivan Vecera ivecera@redhat.com

[ Upstream commit c678669d6b13b77de3b99b97526aaf23c3088d0a ]

Recent commit aa626da947e9 ("iavf: Detach device during reset task") removed netif_tx_stop_all_queues() with an assumption that Tx queues are already stopped by netif_device_detach() in the beginning of reset task. This assumption is incorrect because during reset task a potential link event can start Tx queues again. Revert this change to fix this issue.

Reproducer: 1. Run some Tx traffic (e.g. iperf3) over iavf interface 2. Switch MTU of this interface in a loop

[root@host ~]# cat repro.sh

IF=enp2s0f0v0

iperf3 -c 192.168.0.1 -t 600 --logfile /dev/null & sleep 2

while :; do for i in 1280 1500 2000 900 ; do ip link set $IF mtu $i sleep 2 done done [root@host ~]# ./repro.sh

Result: [ 306.199917] iavf 0000:02:02.0 enp2s0f0v0: NIC Link is Up Speed is 40 Gbps Full Duplex [ 308.205944] iavf 0000:02:02.0 enp2s0f0v0: NIC Link is Up Speed is 40 Gbps Full Duplex [ 310.103223] BUG: kernel NULL pointer dereference, address: 0000000000000008 [ 310.110179] #PF: supervisor write access in kernel mode [ 310.115396] #PF: error_code(0x0002) - not-present page [ 310.120526] PGD 0 P4D 0 [ 310.123057] Oops: 0002 [#1] PREEMPT SMP NOPTI [ 310.127408] CPU: 24 PID: 183 Comm: kworker/u64:9 Kdump: loaded Not tainted 6.1.0-rc3+ #2 [ 310.135485] Hardware name: Abacus electric, s.r.o. - servis@abacus.cz Super Server/H12SSW-iN, BIOS 2.4 04/13/2022 [ 310.145728] Workqueue: iavf iavf_reset_task [iavf] [ 310.150520] RIP: 0010:iavf_xmit_frame_ring+0xd1/0xf70 [iavf] [ 310.156180] Code: d0 0f 86 da 00 00 00 83 e8 01 0f b7 fa 29 f8 01 c8 39 c6 0f 8f a0 08 00 00 48 8b 45 20 48 8d 14 92 bf 01 00 00 00 4c 8d 3c d0 <49> 89 5f 08 8b 43 70 66 41 89 7f 14 41 89 47 10 f6 83 82 00 00 00 [ 310.174918] RSP: 0018:ffffbb5f0082caa0 EFLAGS: 00010293 [ 310.180137] RAX: 0000000000000000 RBX: ffff92345471a6e8 RCX: 0000000000000200 [ 310.187259] RDX: 0000000000000000 RSI: 000000000000000d RDI: 0000000000000001 [ 310.194385] RBP: ffff92341d249000 R08: ffff92434987fcac R09: 0000000000000001 [ 310.201509] R10: 0000000011f683b9 R11: 0000000011f50641 R12: 0000000000000008 [ 310.208631] R13: ffff923447500000 R14: 0000000000000000 R15: 0000000000000000 [ 310.215756] FS: 0000000000000000(0000) GS:ffff92434ee00000(0000) knlGS:0000000000000000 [ 310.223835] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 310.229572] CR2: 0000000000000008 CR3: 0000000fbc210004 CR4: 0000000000770ee0 [ 310.236696] PKRU: 55555554 [ 310.239399] Call Trace: [ 310.241844] <IRQ> [ 310.243855] ? dst_alloc+0x5b/0xb0 [ 310.247260] dev_hard_start_xmit+0x9e/0x1f0 [ 310.251439] sch_direct_xmit+0xa0/0x370 [ 310.255276] __qdisc_run+0x13e/0x580 [ 310.258848] __dev_queue_xmit+0x431/0xd00 [ 310.262851] ? selinux_ip_postroute+0x147/0x3f0 [ 310.267377] ip_finish_output2+0x26c/0x540

Fixes: aa626da947e9 ("iavf: Detach device during reset task") Cc: Jacob Keller jacob.e.keller@intel.com Cc: Patryk Piotrowski patryk.piotrowski@intel.com Cc: SlawomirX Laba slawomirx.laba@intel.com Signed-off-by: Ivan Vecera ivecera@redhat.com Tested-by: Konrad Jankowski konrad0.jankowski@intel.com Signed-off-by: Tony Nguyen anthony.l.nguyen@intel.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/intel/iavf/iavf_main.c | 1 + 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/intel/iavf/iavf_main.c b/drivers/net/ethernet/intel/iavf/iavf_main.c index 79fef8c59d65..7d349ca708c7 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_main.c +++ b/drivers/net/ethernet/intel/iavf/iavf_main.c @@ -3033,6 +3033,7 @@ static void iavf_reset_task(struct work_struct *work)

if (running) { netif_carrier_off(netdev); + netif_tx_stop_all_queues(netdev); adapter->link_up = false; iavf_napi_disable_all(adapter); }

From: Stefan Assmann sassmann@kpanic.de

[ Upstream commit bb861c14f1b8cb9cbf03a132db7f22ec4e692b91 ]

IAVF_FLAG_INITIAL_MAC_SET prevents waiting on iavf_is_mac_set_handled() the first time the MAC is set. This breaks gratuitous ARP because the MAC address has not been updated yet when the gARP packet is sent out.

Current behaviour: $ echo 1 > /sys/class/net/ens4f0/device/sriov_numvfs iavf 0000:88:02.0: MAC address: ee:04:19:14:ec:ea $ ip addr add 192.168.1.1/24 dev ens4f0v0 $ ip link set dev ens4f0v0 up $ echo 1 > /proc/sys/net/ipv4/conf/ens4f0v0/arp_notify $ ip link set ens4f0v0 addr 00:11:22:33:44:55 07:23:41.676611 ee:04:19:14:ec:ea > ff:ff:ff:ff:ff:ff, ethertype ARP (0x0806), length 42: Request who-has 192.168.1.1 tell 192.168.1.1, length 28

With IAVF_FLAG_INITIAL_MAC_SET removed: $ echo 1 > /sys/class/net/ens4f0/device/sriov_numvfs iavf 0000:88:02.0: MAC address: 3e:8a:16:a2:37:6d $ ip addr add 192.168.1.1/24 dev ens4f0v0 $ ip link set dev ens4f0v0 up $ echo 1 > /proc/sys/net/ipv4/conf/ens4f0v0/arp_notify $ ip link set ens4f0v0 addr 00:11:22:33:44:55 07:28:01.836608 00:11:22:33:44:55 > ff:ff:ff:ff:ff:ff, ethertype ARP (0x0806), length 42: Request who-has 192.168.1.1 tell 192.168.1.1, length 28

Fixes: 35a2443d0910 ("iavf: Add waiting for response from PF in set mac") Signed-off-by: Stefan Assmann sassmann@kpanic.de Tested-by: Konrad Jankowski konrad0.jankowski@intel.com Signed-off-by: Tony Nguyen anthony.l.nguyen@intel.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/intel/iavf/iavf.h | 1 - drivers/net/ethernet/intel/iavf/iavf_main.c | 8 -------- 2 files changed, 9 deletions(-)

diff --git a/drivers/net/ethernet/intel/iavf/iavf.h b/drivers/net/ethernet/intel/iavf/iavf.h index 3f6187c16424..0d1bab4ac1b0 100644 --- a/drivers/net/ethernet/intel/iavf/iavf.h +++ b/drivers/net/ethernet/intel/iavf/iavf.h @@ -298,7 +298,6 @@ struct iavf_adapter { #define IAVF_FLAG_QUEUES_DISABLED BIT(17) #define IAVF_FLAG_SETUP_NETDEV_FEATURES BIT(18) #define IAVF_FLAG_REINIT_MSIX_NEEDED BIT(20) -#define IAVF_FLAG_INITIAL_MAC_SET BIT(23) /* duplicates for common code */ #define IAVF_FLAG_DCB_ENABLED 0 /* flags for admin queue service task */ diff --git a/drivers/net/ethernet/intel/iavf/iavf_main.c b/drivers/net/ethernet/intel/iavf/iavf_main.c index f59b725785eb..005bb8378c76 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_main.c +++ b/drivers/net/ethernet/intel/iavf/iavf_main.c @@ -1087,12 +1087,6 @@ static int iavf_set_mac(struct net_device *netdev, void *p) if (ret) return ret;

- /* If this is an initial set MAC during VF spawn do not wait */ - if (adapter->flags & IAVF_FLAG_INITIAL_MAC_SET) { - adapter->flags &= ~IAVF_FLAG_INITIAL_MAC_SET; - return 0; - } - ret = wait_event_interruptible_timeout(adapter->vc_waitqueue, iavf_is_mac_set_handled(netdev, addr->sa_data), msecs_to_jiffies(2500)); @@ -2605,8 +2599,6 @@ static void iavf_init_config_adapter(struct iavf_adapter *adapter) ether_addr_copy(netdev->perm_addr, adapter->hw.mac.addr); }

- adapter->flags |= IAVF_FLAG_INITIAL_MAC_SET; - adapter->tx_desc_count = IAVF_DEFAULT_TXD; adapter->rx_desc_count = IAVF_DEFAULT_RXD; err = iavf_init_interrupt_scheme(adapter);

From: Fabio Estevam festevam@denx.de

[ Upstream commit e68be7b39f21d8a9291a5a3019787cd3ca999dd7 ]

make dtbs_check gives the following errors:

ref-clock-frequency: size (9) error for type uint32 tcxo-clock-frequency: size (9) error for type uint32

Fix it by passing the frequencies inside < > as documented in Documentation/devicetree/bindings/net/wireless/ti,wlcore.yaml.

Signed-off-by: Fabio Estevam festevam@denx.de Fixes: 0d446a505592 ("ARM: dts: add Protonic PRTI6Q board") Signed-off-by: Shawn Guo shawnguo@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- arch/arm/boot/dts/imx6q-prti6q.dts | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/arch/arm/boot/dts/imx6q-prti6q.dts b/arch/arm/boot/dts/imx6q-prti6q.dts index b4605edfd2ab..d8fa83effd63 100644 --- a/arch/arm/boot/dts/imx6q-prti6q.dts +++ b/arch/arm/boot/dts/imx6q-prti6q.dts @@ -364,8 +364,8 @@ wifi { pinctrl-names = "default"; pinctrl-0 = <&pinctrl_wifi>; interrupts-extended = <&gpio1 30 IRQ_TYPE_LEVEL_HIGH>; - ref-clock-frequency = "38400000"; - tcxo-clock-frequency = "19200000"; + ref-clock-frequency = <38400000>; + tcxo-clock-frequency = <19200000>; }; };

From: Peter Kosyh pkosyh@yandex.ru

[ Upstream commit 594c61ffc77de0a197934aa0f1df9285c68801c6 ]

If mlx4_bitmap_init fails, mlx4_bitmap_alloc_range will dereference the NULL pointer (bitmap->table).

Make sure, that mlx4_bitmap_alloc_range called in no error case.

Found by Linux Verification Center (linuxtesting.org) with SVACE.

Fixes: d57febe1a478 ("net/mlx4: Add A0 hybrid steering") Reviewed-by: Tariq Toukan tariqt@nvidia.com Signed-off-by: Peter Kosyh pkosyh@yandex.ru Link: https://lore.kernel.org/r/20221117152806.278072-1-pkosyh@yandex.ru Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/mellanox/mlx4/qp.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx4/qp.c b/drivers/net/ethernet/mellanox/mlx4/qp.c index b149e601f673..48cfaa7eaf50 100644 --- a/drivers/net/ethernet/mellanox/mlx4/qp.c +++ b/drivers/net/ethernet/mellanox/mlx4/qp.c @@ -697,7 +697,8 @@ static int mlx4_create_zones(struct mlx4_dev *dev, err = mlx4_bitmap_init(*bitmap + k, 1, MLX4_QP_TABLE_RAW_ETH_SIZE - 1, 0, 0); - mlx4_bitmap_alloc_range(*bitmap + k, 1, 1, 0); + if (!err) + mlx4_bitmap_alloc_range(*bitmap + k, 1, 1, 0); }

if (err)

From: Zhang Changzhong zhangchangzhong@huawei.com

[ Upstream commit 62a7311fb96c61d281da9852dbee4712fc8c3277 ]

The ql3xxx_send() returns NETDEV_TX_OK without freeing skb in error handling case, add dev_kfree_skb_any() to fix it.

Fixes: bd36b0ac5d06 ("qla3xxx: Add support for Qlogic 4032 chip.") Signed-off-by: Zhang Changzhong zhangchangzhong@huawei.com Link: https://lore.kernel.org/r/1668675039-21138-1-git-send-email-zhangchangzhong@... Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/qlogic/qla3xxx.c | 1 + 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/qlogic/qla3xxx.c b/drivers/net/ethernet/qlogic/qla3xxx.c index 06f4d9a9e938..5a2d70a91868 100644 --- a/drivers/net/ethernet/qlogic/qla3xxx.c +++ b/drivers/net/ethernet/qlogic/qla3xxx.c @@ -2471,6 +2471,7 @@ static netdev_tx_t ql3xxx_send(struct sk_buff *skb, skb_shinfo(skb)->nr_frags); if (tx_cb->seg_count == -1) { netdev_err(ndev, "%s: invalid segment count!\n", __func__); + dev_kfree_skb_any(skb); return NETDEV_TX_OK; }

From: Yang Yingliang yangyingliang@huawei.com

[ Upstream commit 5619537284f1017e9f6c7500b02b859b3830a06d ]

As comment of pci_get_domain_bus_and_slot() says, it returns a pci device with refcount increment, when finish using it, the caller must decrement the reference count by calling pci_dev_put().

In pch_gbe_probe(), pci_get_domain_bus_and_slot() is called, so in error path in probe() and remove() function, pci_dev_put() should be called to avoid refcount leak. Compile tested only.

Fixes: 1a0bdadb4e36 ("net/pch_gbe: supports eg20t ptp clock") Signed-off-by: Yang Yingliang yangyingliang@huawei.com Link: https://lore.kernel.org/r/20221117135148.301014-1-yangyingliang@huawei.com Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c index 98792907a4c3..63b6b7d86ccb 100644 --- a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c +++ b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c @@ -2460,6 +2460,7 @@ static void pch_gbe_remove(struct pci_dev *pdev) unregister_netdev(netdev);

pch_gbe_phy_hw_reset(&adapter->hw); + pci_dev_put(adapter->ptp_pdev);

free_netdev(netdev); } @@ -2535,7 +2536,7 @@ static int pch_gbe_probe(struct pci_dev *pdev, /* setup the private structure */ ret = pch_gbe_sw_init(adapter); if (ret) - goto err_free_netdev; + goto err_put_dev;

/* Initialize PHY */ ret = pch_gbe_init_phy(adapter); @@ -2593,6 +2594,8 @@ static int pch_gbe_probe(struct pci_dev *pdev,

err_free_adapter: pch_gbe_phy_hw_reset(&adapter->hw); +err_put_dev: + pci_dev_put(adapter->ptp_pdev); err_free_netdev: free_netdev(netdev); return ret;

From: Jaco Coetzee jaco.coetzee@corigine.com

[ Upstream commit 0873016d46f6dfafd1bdf4d9b935b3331b226f7c ]

Setting of the port flag `NFP_PORT_CHANGED`, introduced to ensure the correct reading of EEPROM data, causes a fatal kernel NULL pointer dereference in cases where the target netdev type cannot be determined.

Add validation of port struct pointer before attempting to set the `NFP_PORT_CHANGED` flag. Return that operation is not supported if the netdev type cannot be determined.

Fixes: 4ae97cae07e1 ("nfp: ethtool: fix the display error of `ethtool -m DEVNAME`") Signed-off-by: Jaco Coetzee jaco.coetzee@corigine.com Reviewed-by: Louis Peens louis.peens@corigine.com Signed-off-by: Simon Horman simon.horman@corigine.com Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c | 3 +++ 1 file changed, 3 insertions(+)

diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c b/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c index b19bff0db1fd..400b22ad6a34 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c @@ -1395,6 +1395,9 @@ nfp_port_get_module_info(struct net_device *netdev, u8 data;

port = nfp_port_from_netdev(netdev); + if (!port) + return -EOPNOTSUPP; + /* update port state to get latest interface */ set_bit(NFP_PORT_CHANGED, &port->flags); eth_port = nfp_port_get_eth_port(port);

From: YueHaibing yuehaibing@huawei.com

[ Upstream commit 7cef6b73fba96abef731a53501924fc3c4a0f947 ]

'ret' is defined twice in macsec_changelink(), when it is set in macsec_is_offloaded case, it will be invalid before return.

Fixes: 3cf3227a21d1 ("net: macsec: hardware offloading infrastructure") Signed-off-by: YueHaibing yuehaibing@huawei.com Reviewed-by: Saeed Mahameed saeed@kernel.org Reviewed-by: Antoine Tenart atenart@kernel.org Link: https://lore.kernel.org/r/20221118011249.48112-1-yuehaibing@huawei.com Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/macsec.c | 1 - 1 file changed, 1 deletion(-)

diff --git a/drivers/net/macsec.c b/drivers/net/macsec.c index d145ad189778..104fc564a766 100644 --- a/drivers/net/macsec.c +++ b/drivers/net/macsec.c @@ -3855,7 +3855,6 @@ static int macsec_changelink(struct net_device *dev, struct nlattr *tb[], if (macsec_is_offloaded(macsec)) { const struct macsec_ops *ops; struct macsec_context ctx; - int ret;

ops = macsec_get_ops(netdev_priv(dev), &ctx); if (!ops) {

From: Yang Yingliang yangyingliang@huawei.com

[ Upstream commit f92a4b50f0bd7fd52391dc4bb9a309085d278f91 ]

In the error path of vmbus_device_register(), device_unregister() is called, which calls vmbus_device_release(). The latter frees the struct hv_device that was passed in to vmbus_device_register(). So remove the kfree() in vmbus_add_channel_work() to avoid a double free.

Fixes: c2e5df616e1a ("vmbus: add per-channel sysfs info") Suggested-by: Michael Kelley mikelley@microsoft.com Signed-off-by: Yang Yingliang yangyingliang@huawei.com Reviewed-by: Michael Kelley mikelley@microsoft.com Link: https://lore.kernel.org/r/20221119081135.1564691-2-yangyingliang@huawei.com Signed-off-by: Wei Liu wei.liu@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/hv/channel_mgmt.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/drivers/hv/channel_mgmt.c b/drivers/hv/channel_mgmt.c index 5b120402d405..cc23b90cae02 100644 --- a/drivers/hv/channel_mgmt.c +++ b/drivers/hv/channel_mgmt.c @@ -533,13 +533,17 @@ static void vmbus_add_channel_work(struct work_struct *work) * Add the new device to the bus. This will kick off device-driver * binding which eventually invokes the device driver's AddDevice() * method. + * + * If vmbus_device_register() fails, the 'device_obj' is freed in + * vmbus_device_release() as called by device_unregister() in the + * error path of vmbus_device_register(). In the outside error + * path, there's no need to free it. */ ret = vmbus_device_register(newchannel->device_obj);

if (ret != 0) { pr_err("unable to add child device object (relid %d)\n", newchannel->offermsg.child_relid); - kfree(newchannel->device_obj); goto err_deq_chan; }

From: Vishwanath Pai vpai@akamai.com

[ Upstream commit c7aa1a76d4a0a3c401025b60c401412bbb60f8c6 ]

This patch introduced a regression: commit 48596a8ddc46 ("netfilter: ipset: Fix adding an IPv4 range containing more than 2^31 addresses")

The variable e.ip is passed to adtfn() function which finally adds the ip address to the set. The patch above refactored the for loop and moved e.ip = htonl(ip) to the end of the for loop.

What this means is that if the value of "ip" changes between the first assignement of e.ip and the forloop, then e.ip is pointing to a different ip address than "ip".

Test case: $ ipset create jdtest_tmp hash:ip family inet hashsize 2048 maxelem 100000 $ ipset add jdtest_tmp 10.0.1.1/31 ipset v6.21.1: Element cannot be added to the set: it's already added

The value of ip gets updated inside the "else if (tb[IPSET_ATTR_CIDR])" block but e.ip is still pointing to the old value.

Fixes: 48596a8ddc46 ("netfilter: ipset: Fix adding an IPv4 range containing more than 2^31 addresses") Reviewed-by: Joshua Hunt johunt@akamai.com Signed-off-by: Vishwanath Pai vpai@akamai.com Signed-off-by: Pablo Neira Ayuso pablo@netfilter.org Signed-off-by: Sasha Levin sashal@kernel.org --- net/netfilter/ipset/ip_set_hash_ip.c | 8 +++----- 1 file changed, 3 insertions(+), 5 deletions(-)

diff --git a/net/netfilter/ipset/ip_set_hash_ip.c b/net/netfilter/ipset/ip_set_hash_ip.c index dd30c03d5a23..75d556d71652 100644 --- a/net/netfilter/ipset/ip_set_hash_ip.c +++ b/net/netfilter/ipset/ip_set_hash_ip.c @@ -151,18 +151,16 @@ hash_ip4_uadt(struct ip_set *set, struct nlattr *tb[], if (((u64)ip_to - ip + 1) >> (32 - h->netmask) > IPSET_MAX_RANGE) return -ERANGE;

- if (retried) { + if (retried) ip = ntohl(h->next.ip); - e.ip = htonl(ip); - } for (; ip <= ip_to;) { + e.ip = htonl(ip); ret = adtfn(set, &e, &ext, &ext, flags); if (ret && !ip_set_eexist(ret, flags)) return ret;

ip += hosts; - e.ip = htonl(ip); - if (e.ip == 0) + if (ip == 0) return 0;

ret = 0;

From: Moshe Shemesh moshe@nvidia.com

[ Upstream commit 61db3d7b99a367416e489ccf764cc5f9b00d62a1 ]

Fix a bug in calculation of FW tracer timestamp. Decreasing one in the calculation should effect only bits 52_7 and not effect bits 6_0 of the timestamp, otherwise bits 6_0 are always set in this calculation.

Fixes: 70dd6fdb8987 ("net/mlx5: FW tracer, parse traces and kernel tracing support") Signed-off-by: Moshe Shemesh moshe@nvidia.com Reviewed-by: Feras Daoud ferasda@nvidia.com Signed-off-by: Saeed Mahameed saeedm@nvidia.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c b/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c index 978a2bb8e122..21831386b26e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c @@ -638,7 +638,7 @@ static void mlx5_tracer_handle_timestamp_trace(struct mlx5_fw_tracer *tracer, trace_timestamp = (timestamp_event.timestamp & MASK_52_7) | (str_frmt->timestamp & MASK_6_0); else - trace_timestamp = ((timestamp_event.timestamp & MASK_52_7) - 1) | + trace_timestamp = ((timestamp_event.timestamp - 1) & MASK_52_7) | (str_frmt->timestamp & MASK_6_0);

mlx5_tracer_print_trace(str_frmt, dev, trace_timestamp);

From: Moshe Shemesh moshe@nvidia.com

[ Upstream commit 870c2481174b839e7159555127bc8b5a5d0699ba ]

While moving to new CMD API (quiet API), some pre-existing flows may call the new API function that in case of error, returns the error instead of printing it as previously done. For such flows we bring back the print but to tracepoint this time for sys admins to have the ability to check for errors especially for commands using the new quiet API.

Tracepoint output example: devlink-1333 [001] ..... 822.746922: mlx5_cmd: ACCESS_REG(0x805) op_mod(0x0) failed, status bad resource(0x5), syndrome (0xb06e1f), err(-22)

Fixes: f23519e542e5 ("net/mlx5: cmdif, Add new api for command execution") Signed-off-by: Moshe Shemesh moshe@nvidia.com Reviewed-by: Shay Drory shayd@nvidia.com Reviewed-by: Maor Gottlieb maorg@nvidia.com Signed-off-by: Saeed Mahameed saeedm@nvidia.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/mellanox/mlx5/core/cmd.c | 41 +++++++++-------- .../mellanox/mlx5/core/diag/cmd_tracepoint.h | 45 +++++++++++++++++++ include/linux/mlx5/driver.h | 1 + 3 files changed, 68 insertions(+), 19 deletions(-) create mode 100644 drivers/net/ethernet/mellanox/mlx5/core/diag/cmd_tracepoint.h

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c index 2e0d59ca62b5..df3e284ca5c6 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c @@ -45,6 +45,8 @@ #include "mlx5_core.h" #include "lib/eq.h" #include "lib/tout.h" +#define CREATE_TRACE_POINTS +#include "diag/cmd_tracepoint.h"

enum { CMD_IF_REV = 5, @@ -785,27 +787,14 @@ EXPORT_SYMBOL(mlx5_cmd_out_err); static void cmd_status_print(struct mlx5_core_dev *dev, void *in, void *out) { u16 opcode, op_mod; - u32 syndrome; - u8 status; u16 uid; - int err; - - syndrome = MLX5_GET(mbox_out, out, syndrome); - status = MLX5_GET(mbox_out, out, status);

opcode = MLX5_GET(mbox_in, in, opcode); op_mod = MLX5_GET(mbox_in, in, op_mod); uid = MLX5_GET(mbox_in, in, uid);

- err = cmd_status_to_err(status); - if (!uid && opcode != MLX5_CMD_OP_DESTROY_MKEY) mlx5_cmd_out_err(dev, opcode, op_mod, out); - else - mlx5_core_dbg(dev, - "%s(0x%x) op_mod(0x%x) uid(%d) failed, status %s(0x%x), syndrome (0x%x), err(%d)\n", - mlx5_command_str(opcode), opcode, op_mod, uid, - cmd_status_str(status), status, syndrome, err); }

int mlx5_cmd_check(struct mlx5_core_dev *dev, int err, void *in, void *out) @@ -1892,6 +1881,16 @@ static int cmd_exec(struct mlx5_core_dev *dev, void *in, int in_size, void *out, return err; }

+static void mlx5_cmd_err_trace(struct mlx5_core_dev *dev, u16 opcode, u16 op_mod, void *out) +{ + u32 syndrome = MLX5_GET(mbox_out, out, syndrome); + u8 status = MLX5_GET(mbox_out, out, status); + + trace_mlx5_cmd(mlx5_command_str(opcode), opcode, op_mod, + cmd_status_str(status), status, syndrome, + cmd_status_to_err(status)); +} + static void cmd_status_log(struct mlx5_core_dev *dev, u16 opcode, u8 status, u32 syndrome, int err) { @@ -1914,7 +1913,7 @@ static void cmd_status_log(struct mlx5_core_dev *dev, u16 opcode, u8 status, }

/* preserve -EREMOTEIO for outbox.status != OK, otherwise return err as is */ -static int cmd_status_err(struct mlx5_core_dev *dev, int err, u16 opcode, void *out) +static int cmd_status_err(struct mlx5_core_dev *dev, int err, u16 opcode, u16 op_mod, void *out) { u32 syndrome = MLX5_GET(mbox_out, out, syndrome); u8 status = MLX5_GET(mbox_out, out, status); @@ -1922,8 +1921,10 @@ static int cmd_status_err(struct mlx5_core_dev *dev, int err, u16 opcode, void * if (err == -EREMOTEIO) /* -EREMOTEIO is preserved */ err = -EIO;

- if (!err && status != MLX5_CMD_STAT_OK) + if (!err && status != MLX5_CMD_STAT_OK) { err = -EREMOTEIO; + mlx5_cmd_err_trace(dev, opcode, op_mod, out); + }

cmd_status_log(dev, opcode, status, syndrome, err); return err; @@ -1951,9 +1952,9 @@ int mlx5_cmd_do(struct mlx5_core_dev *dev, void *in, int in_size, void *out, int { int err = cmd_exec(dev, in, in_size, out, out_size, NULL, NULL, false); u16 opcode = MLX5_GET(mbox_in, in, opcode); + u16 op_mod = MLX5_GET(mbox_in, in, op_mod);

- err = cmd_status_err(dev, err, opcode, out); - return err; + return cmd_status_err(dev, err, opcode, op_mod, out); } EXPORT_SYMBOL(mlx5_cmd_do);

@@ -1997,8 +1998,9 @@ int mlx5_cmd_exec_polling(struct mlx5_core_dev *dev, void *in, int in_size, { int err = cmd_exec(dev, in, in_size, out, out_size, NULL, NULL, true); u16 opcode = MLX5_GET(mbox_in, in, opcode); + u16 op_mod = MLX5_GET(mbox_in, in, op_mod);

- err = cmd_status_err(dev, err, opcode, out); + err = cmd_status_err(dev, err, opcode, op_mod, out); return mlx5_cmd_check(dev, err, in, out); } EXPORT_SYMBOL(mlx5_cmd_exec_polling); @@ -2034,7 +2036,7 @@ static void mlx5_cmd_exec_cb_handler(int status, void *_work) struct mlx5_async_ctx *ctx;

ctx = work->ctx; - status = cmd_status_err(ctx->dev, status, work->opcode, work->out); + status = cmd_status_err(ctx->dev, status, work->opcode, work->op_mod, work->out); work->user_callback(status, work); if (atomic_dec_and_test(&ctx->num_inflight)) complete(&ctx->inflight_done); @@ -2049,6 +2051,7 @@ int mlx5_cmd_exec_cb(struct mlx5_async_ctx *ctx, void *in, int in_size, work->ctx = ctx; work->user_callback = callback; work->opcode = MLX5_GET(mbox_in, in, opcode); + work->op_mod = MLX5_GET(mbox_in, in, op_mod); work->out = out; if (WARN_ON(!atomic_inc_not_zero(&ctx->num_inflight))) return -EIO; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/diag/cmd_tracepoint.h b/drivers/net/ethernet/mellanox/mlx5/core/diag/cmd_tracepoint.h new file mode 100644 index 000000000000..406ebe17405f --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/diag/cmd_tracepoint.h @@ -0,0 +1,45 @@ +/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */ +/* Copyright (c) 2022, NVIDIA CORPORATION & AFFILIATES. All rights reserved. */ + +#undef TRACE_SYSTEM +#define TRACE_SYSTEM mlx5 + +#if !defined(_MLX5_CMD_TP_H_) || defined(TRACE_HEADER_MULTI_READ) +#define _MLX5_CMD_TP_H_ + +#include <linux/tracepoint.h> +#include <linux/trace_seq.h> + +TRACE_EVENT(mlx5_cmd, + TP_PROTO(const char *command_str, u16 opcode, u16 op_mod, + const char *status_str, u8 status, u32 syndrome, int err), + TP_ARGS(command_str, opcode, op_mod, status_str, status, syndrome, err), + TP_STRUCT__entry(__string(command_str, command_str) + __field(u16, opcode) + __field(u16, op_mod) + __string(status_str, status_str) + __field(u8, status) + __field(u32, syndrome) + __field(int, err) + ), + TP_fast_assign(__assign_str(command_str, command_str); + __entry->opcode = opcode; + __entry->op_mod = op_mod; + __assign_str(status_str, status_str); + __entry->status = status; + __entry->syndrome = syndrome; + __entry->err = err; + ), + TP_printk("%s(0x%x) op_mod(0x%x) failed, status %s(0x%x), syndrome (0x%x), err(%d)", + __get_str(command_str), __entry->opcode, __entry->op_mod, + __get_str(status_str), __entry->status, __entry->syndrome, + __entry->err) +); + +#endif /* _MLX5_CMD_TP_H_ */ + +#undef TRACE_INCLUDE_PATH +#define TRACE_INCLUDE_PATH ./diag +#undef TRACE_INCLUDE_FILE +#define TRACE_INCLUDE_FILE cmd_tracepoint +#include <trace/define_trace.h> diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 454dab40baf6..2d56cfe0911d 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -984,6 +984,7 @@ struct mlx5_async_work { struct mlx5_async_ctx *ctx; mlx5_async_cbk_t user_callback; u16 opcode; /* cmd opcode */ + u16 op_mod; /* cmd op_mod */ void *out; /* pointer to the cmd output buffer */ };

From: Roi Dayan roid@nvidia.com

[ Upstream commit 6d942e40448931be9371f1ba8cb592778807ce18 ]

The cited commit moved from using reformat_id integer to packet_reformat pointer which introduced the possibility to null pointer dereference. When setting packet reformat flag and pkt_reformat pointer must exists so checking MLX5_ESW_DEST_ENCAP is not enough, we need to make sure the pkt_reformat is valid and check for MLX5_ESW_DEST_ENCAP_VALID. If the dest encap valid flag does not exists then pkt_reformat can be either invalid address or null. Also, to make sure we don't try to access invalid pkt_reformat set it to null when invalidated and invalidate it before calling add flow code as its logically more correct and to be safe.

Fixes: 2b688ea5efde ("net/mlx5: Add flow steering actions to fs_cmd shim layer") Signed-off-by: Roi Dayan roid@nvidia.com Reviewed-by: Chris Mi cmi@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_tun_encap.c | 10 ++++++---- .../net/ethernet/mellanox/mlx5/core/eswitch_offloads.c | 2 +- 2 files changed, 7 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c index 5aff97914367..5b6a79d2034e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c @@ -224,15 +224,16 @@ void mlx5e_tc_encap_flows_del(struct mlx5e_priv *priv, list_for_each_entry(flow, flow_list, tmp_list) { if (!mlx5e_is_offloaded_flow(flow) || flow_flag_test(flow, SLOW)) continue; - spec = &flow->attr->parse_attr->spec; - - /* update from encap rule to slow path rule */ - rule = mlx5e_tc_offload_to_slow_path(esw, flow, spec);

attr = mlx5e_tc_get_encap_attr(flow); esw_attr = attr->esw_attr; /* mark the flow's encap dest as non-valid */ esw_attr->dests[flow->tmp_entry_index].flags &= ~MLX5_ESW_DEST_ENCAP_VALID; + esw_attr->dests[flow->tmp_entry_index].pkt_reformat = NULL; + + /* update from encap rule to slow path rule */ + spec = &flow->attr->parse_attr->spec; + rule = mlx5e_tc_offload_to_slow_path(esw, flow, spec);

if (IS_ERR(rule)) { err = PTR_ERR(rule); @@ -251,6 +252,7 @@ void mlx5e_tc_encap_flows_del(struct mlx5e_priv *priv, /* we know that the encap is valid */ e->flags &= ~MLX5_ENCAP_ENTRY_VALID; mlx5_packet_reformat_dealloc(priv->mdev, e->pkt_reformat); + e->pkt_reformat = NULL; }

static void mlx5e_take_tmp_flow(struct mlx5e_tc_flow *flow, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c index 3c68cac4a9c2..061ac8799354 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c @@ -431,7 +431,7 @@ esw_setup_vport_dest(struct mlx5_flow_destination *dest, struct mlx5_flow_act *f mlx5_lag_mpesw_is_activated(esw->dev)) dest[dest_idx].type = MLX5_FLOW_DESTINATION_TYPE_UPLINK; } - if (esw_attr->dests[attr_idx].flags & MLX5_ESW_DEST_ENCAP) { + if (esw_attr->dests[attr_idx].flags & MLX5_ESW_DEST_ENCAP_VALID) { if (pkt_reformat) { flow_act->action |= MLX5_FLOW_CONTEXT_ACTION_PACKET_REFORMAT; flow_act->pkt_reformat = esw_attr->dests[attr_idx].pkt_reformat;

From: Chris Mi cmi@nvidia.com

[ Upstream commit f377422044b2093c835e5f3717f8c8c58da1db1f ]

The cited commit adds a for loop to support multiple encapsulations. But it only checks if the last encap is valid.

Fix it by setting slow path flag when one of the encap is invalid.

Fixes: f493f15534ec ("net/mlx5e: Move flow attr reformat action bit to per dest flags") Signed-off-by: Chris Mi cmi@nvidia.com Reviewed-by: Roi Dayan roid@nvidia.com Signed-off-by: Saeed Mahameed saeedm@nvidia.com Signed-off-by: Sasha Levin sashal@kernel.org --- .../mellanox/mlx5/core/en/tc_tun_encap.c | 6 ++---- .../mellanox/mlx5/core/en/tc_tun_encap.h | 3 +-- drivers/net/ethernet/mellanox/mlx5/core/en_tc.c | 17 ++++++----------- 3 files changed, 9 insertions(+), 17 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c index 5b6a79d2034e..ff73d25bc6eb 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c @@ -764,8 +764,7 @@ int mlx5e_attach_encap(struct mlx5e_priv *priv, struct net_device *mirred_dev, int out_index, struct netlink_ext_ack *extack, - struct net_device **encap_dev, - bool *encap_valid) + struct net_device **encap_dev) { struct mlx5_eswitch *esw = priv->mdev->priv.eswitch; struct mlx5e_tc_flow_parse_attr *parse_attr; @@ -880,9 +879,8 @@ int mlx5e_attach_encap(struct mlx5e_priv *priv, if (e->flags & MLX5_ENCAP_ENTRY_VALID) { attr->esw_attr->dests[out_index].pkt_reformat = e->pkt_reformat; attr->esw_attr->dests[out_index].flags |= MLX5_ESW_DEST_ENCAP_VALID; - *encap_valid = true; } else { - *encap_valid = false; + flow_flag_set(flow, SLOW); } mutex_unlock(&esw->offloads.encap_tbl_lock);

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.h b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.h index d542b8476491..8ad273dde40e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.h @@ -17,8 +17,7 @@ int mlx5e_attach_encap(struct mlx5e_priv *priv, struct net_device *mirred_dev, int out_index, struct netlink_ext_ack *extack, - struct net_device **encap_dev, - bool *encap_valid); + struct net_device **encap_dev);

int mlx5e_attach_decap(struct mlx5e_priv *priv, struct mlx5e_tc_flow *flow, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c index 229c14b1af00..949ef560df78 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -1620,7 +1620,6 @@ set_encap_dests(struct mlx5e_priv *priv, struct mlx5e_tc_flow *flow, struct mlx5_flow_attr *attr, struct netlink_ext_ack *extack, - bool *encap_valid, bool *vf_tun) { struct mlx5e_tc_flow_parse_attr *parse_attr; @@ -1637,7 +1636,6 @@ set_encap_dests(struct mlx5e_priv *priv, parse_attr = attr->parse_attr; esw_attr = attr->esw_attr; *vf_tun = false; - *encap_valid = true;

for (out_index = 0; out_index < MLX5_MAX_FLOW_FWD_VPORTS; out_index++) { struct net_device *out_dev; @@ -1654,7 +1652,7 @@ set_encap_dests(struct mlx5e_priv *priv, goto out; } err = mlx5e_attach_encap(priv, flow, attr, out_dev, out_index, - extack, &encap_dev, encap_valid); + extack, &encap_dev); dev_put(out_dev); if (err) goto out; @@ -1718,8 +1716,8 @@ mlx5e_tc_add_fdb_flow(struct mlx5e_priv *priv, struct mlx5e_tc_flow_parse_attr *parse_attr; struct mlx5_flow_attr *attr = flow->attr; struct mlx5_esw_flow_attr *esw_attr; - bool vf_tun, encap_valid; u32 max_prio, max_chain; + bool vf_tun; int err = 0;

parse_attr = attr->parse_attr; @@ -1809,7 +1807,7 @@ mlx5e_tc_add_fdb_flow(struct mlx5e_priv *priv, esw_attr->int_port = int_port; }

- err = set_encap_dests(priv, flow, attr, extack, &encap_valid, &vf_tun); + err = set_encap_dests(priv, flow, attr, extack, &vf_tun); if (err) goto err_out;

@@ -1839,7 +1837,7 @@ mlx5e_tc_add_fdb_flow(struct mlx5e_priv *priv, * (1) there's no error * (2) there's an encap action and we don't have valid neigh */ - if (!encap_valid || flow_flag_test(flow, SLOW)) + if (flow_flag_test(flow, SLOW)) flow->rule[0] = mlx5e_tc_offload_to_slow_path(esw, flow, &parse_attr->spec); else flow->rule[0] = mlx5e_tc_offload_fdb_rules(esw, flow, &parse_attr->spec, attr); @@ -3737,7 +3735,7 @@ alloc_flow_post_acts(struct mlx5e_tc_flow *flow, struct netlink_ext_ack *extack) struct mlx5e_post_act *post_act = get_post_action(flow->priv); struct mlx5_flow_attr *attr, *next_attr = NULL; struct mlx5e_post_act_handle *handle; - bool vf_tun, encap_valid = true; + bool vf_tun; int err;

/* This is going in reverse order as needed. @@ -3759,13 +3757,10 @@ alloc_flow_post_acts(struct mlx5e_tc_flow *flow, struct netlink_ext_ack *extack) if (list_is_last(&attr->list, &flow->attrs)) break;

- err = set_encap_dests(flow->priv, flow, attr, extack, &encap_valid, &vf_tun); + err = set_encap_dests(flow->priv, flow, attr, extack, &vf_tun); if (err) goto out_free;

- if (!encap_valid) - flow_flag_set(flow, SLOW); - err = actions_prepare_mod_hdr_actions(flow->priv, flow, attr, extack); if (err) goto out_free;

From: Xin Long lucien.xin@gmail.com

[ Upstream commit 0e5d56c64afcd6fd2d132ea972605b66f8a7d3c4 ]

A crash was reported by Wei Chen:

BUG: kernel NULL pointer dereference, address: 0000000000000018 RIP: 0010:tipc_conn_close+0x12/0x100 Call Trace: tipc_topsrv_exit_net+0x139/0x320 ops_exit_list.isra.9+0x49/0x80 cleanup_net+0x31a/0x540 process_one_work+0x3fa/0x9f0 worker_thread+0x42/0x5c0

It was caused by !con->sock in tipc_conn_close(). In tipc_topsrv_accept(), con is allocated in conn_idr then its sock is set:

con = tipc_conn_alloc(); ... <----[1] con->sock = newsock;

If tipc_conn_close() is called in anytime of [1], the null-pointer-def is triggered by con->sock->sk due to con->sock is not yet set.

This patch fixes it by moving the con->sock setting to tipc_conn_alloc() under s->idr_lock. So that con->sock can never be NULL when getting the con from s->conn_idr. It will be also safer to move con->server and flag CF_CONNECTED setting under s->idr_lock, as they should all be set before tipc_conn_alloc() is called.

Fixes: c5fa7b3cf3cb ("tipc: introduce new TIPC server infrastructure") Reported-by: Wei Chen harperchen1110@gmail.com Signed-off-by: Xin Long lucien.xin@gmail.com Acked-by: Jon Maloy jmaloy@redhat.com Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- net/tipc/topsrv.c | 11 +++++------ 1 file changed, 5 insertions(+), 6 deletions(-)

diff --git a/net/tipc/topsrv.c b/net/tipc/topsrv.c index d92ec92f0b71..b0f9aa521670 100644 --- a/net/tipc/topsrv.c +++ b/net/tipc/topsrv.c @@ -176,7 +176,7 @@ static void tipc_conn_close(struct tipc_conn *con) conn_put(con); }

-static struct tipc_conn *tipc_conn_alloc(struct tipc_topsrv *s) +static struct tipc_conn *tipc_conn_alloc(struct tipc_topsrv *s, struct socket *sock) { struct tipc_conn *con; int ret; @@ -202,10 +202,11 @@ static struct tipc_conn *tipc_conn_alloc(struct tipc_topsrv *s) } con->conid = ret; s->idr_in_use++; - spin_unlock_bh(&s->idr_lock);

set_bit(CF_CONNECTED, &con->flags); con->server = s; + con->sock = sock; + spin_unlock_bh(&s->idr_lock);

return con; } @@ -467,7 +468,7 @@ static void tipc_topsrv_accept(struct work_struct *work) ret = kernel_accept(lsock, &newsock, O_NONBLOCK); if (ret < 0) return; - con = tipc_conn_alloc(srv); + con = tipc_conn_alloc(srv, newsock); if (IS_ERR(con)) { ret = PTR_ERR(con); sock_release(newsock); @@ -479,7 +480,6 @@ static void tipc_topsrv_accept(struct work_struct *work) newsk->sk_data_ready = tipc_conn_data_ready; newsk->sk_write_space = tipc_conn_write_space; newsk->sk_user_data = con; - con->sock = newsock; write_unlock_bh(&newsk->sk_callback_lock);

/* Wake up receive process in case of 'SYN+' message */ @@ -577,12 +577,11 @@ bool tipc_topsrv_kern_subscr(struct net *net, u32 port, u32 type, u32 lower, sub.filter = filter; *(u64 *)&sub.usr_handle = (u64)port;

- con = tipc_conn_alloc(tipc_topsrv(net)); + con = tipc_conn_alloc(tipc_topsrv(net), NULL); if (IS_ERR(con)) return false;

*conid = con->conid; - con->sock = NULL; rc = tipc_conn_rcv_sub(tipc_topsrv(net), con, &sub); if (rc >= 0) return true;

From: YueHaibing yuehaibing@huawei.com

[ Upstream commit cd0f6421162201e4b22ce757a1966729323185eb ]

If skb_linearize() fails in tipc_disc_rcv(), we need to free the skb instead of handle it.

Fixes: 25b0b9c4e835 ("tipc: handle collisions of 32-bit node address hash values") Signed-off-by: YueHaibing yuehaibing@huawei.com Acked-by: Jon Maloy jmaloy@redhat.com Link: https://lore.kernel.org/r/20221119072832.7896-1-yuehaibing@huawei.com Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- net/tipc/discover.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/net/tipc/discover.c b/net/tipc/discover.c index e8630707901e..e8dcdf267c0c 100644 --- a/net/tipc/discover.c +++ b/net/tipc/discover.c @@ -211,7 +211,10 @@ void tipc_disc_rcv(struct net *net, struct sk_buff *skb, u32 self; int err;

- skb_linearize(skb); + if (skb_linearize(skb)) { + kfree_skb(skb); + return; + } hdr = buf_msg(skb);

if (caps & TIPC_NODE_ID128)

From: Thomas Jarosch thomas.jarosch@intra2net.com

[ Upstream commit b97df039a68b2f3e848e238df5d5d06343ea497b ]

Kernel 5.14 added a new "byseq" index to speed up xfrm_state lookups by sequence number in commit fe9f1d8779cb ("xfrm: add state hashtable keyed by seq")

While the patch was thorough, the function pfkey_send_new_mapping() in net/af_key.c also modifies x->km.seq and never added the current xfrm_state to the "byseq" index.

This leads to the following kernel Ooops: BUG: kernel NULL pointer dereference, address: 0000000000000000 .. RIP: 0010:__xfrm_state_delete+0xc9/0x1c0 .. Call Trace: <TASK> xfrm_state_delete+0x1e/0x40 xfrm_del_sa+0xb0/0x110 [xfrm_user] xfrm_user_rcv_msg+0x12d/0x270 [xfrm_user] ? remove_entity_load_avg+0x8a/0xa0 ? copy_to_user_state_extra+0x580/0x580 [xfrm_user] netlink_rcv_skb+0x51/0x100 xfrm_netlink_rcv+0x30/0x50 [xfrm_user] netlink_unicast+0x1a6/0x270 netlink_sendmsg+0x22a/0x480 __sys_sendto+0x1a6/0x1c0 ? __audit_syscall_entry+0xd8/0x130 ? __audit_syscall_exit+0x249/0x2b0 __x64_sys_sendto+0x23/0x30 do_syscall_64+0x3a/0x90 entry_SYSCALL_64_after_hwframe+0x61/0xcb

Exact location of the crash in __xfrm_state_delete(): if (x->km.seq) hlist_del_rcu(&x->byseq);

The hlist_node "byseq" was never populated.

The bug only triggers if a new NAT traversal mapping (changed IP or port) is detected in esp_input_done2() / esp6_input_done2(), which in turn indirectly calls pfkey_send_new_mapping() *if* the kernel is compiled with CONFIG_NET_KEY and "af_key" is active.

The PF_KEYv2 message SADB_X_NAT_T_NEW_MAPPING is not part of RFC 2367. Various implementations have been examined how they handle the "sadb_msg_seq" header field:

- racoon (Android): does not process SADB_X_NAT_T_NEW_MAPPING - strongswan: does not care about sadb_msg_seq - openswan: does not care about sadb_msg_seq

There is no standard how PF_KEYv2 sadb_msg_seq should be populated for SADB_X_NAT_T_NEW_MAPPING and it's not used in popular implementations either. Herbert Xu suggested we should just use the current km.seq value as is. This fixes the root cause of the oops since we no longer modify km.seq itself.

The update of "km.seq" looks like a copy'n'paste error from pfkey_send_acquire(). SADB_ACQUIRE must indeed assign a unique km.seq number according to RFC 2367. It has been verified that code paths involving pfkey_send_acquire() don't cause the same Oops.

PF_KEYv2 SADB_X_NAT_T_NEW_MAPPING support was originally added here: https://git.kernel.org/pub/scm/linux/kernel/git/tglx/history.git

commit cbc3488685b20e7b2a98ad387a1a816aada569d8 Author: Derek Atkins derek@ihtfp.com AuthorDate: Wed Apr 2 13:21:02 2003 -0800

[IPSEC]: Implement UDP Encapsulation framework.

In particular, implement ESPinUDP encapsulation for IPsec Nat Traversal.

A note on triggering the bug: I was not able to trigger it using VMs. There is one VPN using a high latency link on our production VPN server that triggered it like once a day though.

Link: https://github.com/strongswan/strongswan/issues/992 Link: https://lore.kernel.org/netdev/00959f33ee52c4b3b0084d42c430418e502db554.1652... Link: https://lore.kernel.org/netdev/20221027142455.3975224-1-chenzhihao@meizu.com...

Fixes: fe9f1d8779cb ("xfrm: add state hashtable keyed by seq") Reported-by: Roth Mark rothm@mail.com Reported-by: Zhihao Chen chenzhihao@meizu.com Tested-by: Roth Mark rothm@mail.com Signed-off-by: Thomas Jarosch thomas.jarosch@intra2net.com Acked-by: Antony Antony antony.antony@secunet.com Acked-by: Herbert Xu herbert@gondor.apana.org.au Signed-off-by: Steffen Klassert steffen.klassert@secunet.com Signed-off-by: Sasha Levin sashal@kernel.org --- net/key/af_key.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/key/af_key.c b/net/key/af_key.c index 213287814328..95edcbedf6ef 100644 --- a/net/key/af_key.c +++ b/net/key/af_key.c @@ -3394,7 +3394,7 @@ static int pfkey_send_new_mapping(struct xfrm_state *x, xfrm_address_t *ipaddr, hdr->sadb_msg_len = size / sizeof(uint64_t); hdr->sadb_msg_errno = 0; hdr->sadb_msg_reserved = 0; - hdr->sadb_msg_seq = x->km.seq = get_acqseq(); + hdr->sadb_msg_seq = x->km.seq; hdr->sadb_msg_pid = 0;

/* SA */

From: Wang ShaoBo bobo.shaobowang@huawei.com

[ Upstream commit e541dd7763fc34aec2f93f652a396cc2e7b92d8d ]

acpi_evaluate_dsm() should be coupled with ACPI_FREE() to free the ACPI memory, because we need to track the allocation of acpi_object when ACPI_DBG_TRACK_ALLOCATIONS enabled, so use ACPI_FREE() instead of kfree().

Fixes: d38a648d2d6c ("net: wwan: iosm: fix memory leak in ipc_pcie_read_bios_cfg") Signed-off-by: Wang ShaoBo bobo.shaobowang@huawei.com Link: https://lore.kernel.org/r/20221118062447.2324881-1-bobo.shaobowang@huawei.co... Signed-off-by: Paolo Abeni pabeni@redhat.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/wwan/iosm/iosm_ipc_pcie.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/wwan/iosm/iosm_ipc_pcie.c b/drivers/net/wwan/iosm/iosm_ipc_pcie.c index 97cb6846c6ae..f604d4a01e1b 100644 --- a/drivers/net/wwan/iosm/iosm_ipc_pcie.c +++ b/drivers/net/wwan/iosm/iosm_ipc_pcie.c @@ -249,7 +249,7 @@ static enum ipc_pcie_sleep_state ipc_pcie_read_bios_cfg(struct device *dev) if (object->integer.value == 3) sleep_state = IPC_PCIE_D3L2;

- kfree(object); + ACPI_FREE(object);

default_ret: return sleep_state;

From: Liu Jian liujian56@huawei.com

[ Upstream commit 4305fe232b8aa59af3761adc9fe6b6aa40913960 ]

If phylink_of_phy_connect() fails, the port should be disabled. If sparx5_serdes_set()/phy_power_on() fails, the port should be disabled and the phylink should be stopped and disconnected.

Fixes: 946e7fd5053a ("net: sparx5: add port module support") Fixes: f3cad2611a77 ("net: sparx5: add hostmode with phylink support") Signed-off-by: Liu Jian liujian56@huawei.com Tested-by: Bjarni Jonasson bjarni.jonasson@microchip.com Reviewed-by: Steen Hegelund steen.hegelund@microchip.com Link: https://lore.kernel.org/r/20221117125918.203997-1-liujian56@huawei.com Signed-off-by: Paolo Abeni pabeni@redhat.com Signed-off-by: Sasha Levin sashal@kernel.org --- .../net/ethernet/microchip/sparx5/sparx5_netdev.c | 14 ++++++++++++-- 1 file changed, 12 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_netdev.c b/drivers/net/ethernet/microchip/sparx5/sparx5_netdev.c index af4d3e1f1a6d..3f112a897a60 100644 --- a/drivers/net/ethernet/microchip/sparx5/sparx5_netdev.c +++ b/drivers/net/ethernet/microchip/sparx5/sparx5_netdev.c @@ -103,7 +103,7 @@ static int sparx5_port_open(struct net_device *ndev) err = phylink_of_phy_connect(port->phylink, port->of_node, 0); if (err) { netdev_err(ndev, "Could not attach to PHY\n"); - return err; + goto err_connect; }

phylink_start(port->phylink); @@ -115,10 +115,20 @@ static int sparx5_port_open(struct net_device *ndev) err = sparx5_serdes_set(port->sparx5, port, &port->conf); else err = phy_power_on(port->serdes); - if (err) + if (err) { netdev_err(ndev, "%s failed\n", __func__); + goto out_power; + } }

+ return 0; + +out_power: + phylink_stop(port->phylink); + phylink_disconnect_phy(port->phylink); +err_connect: + sparx5_port_enable(port, false); + return err; }

From: Liu Shixin liushixin2@huawei.com

[ Upstream commit 53270fb0fd77fe786d8c07a0793981d797836b93 ]

Syzbot reported a memory leak about skb:

unreferenced object 0xffff88810e144e00 (size 240): comm "syz-executor284", pid 3701, jiffies 4294952403 (age 12.620s) hex dump (first 32 bytes): 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ backtrace: [<ffffffff83ab79a9>] __alloc_skb+0x1f9/0x270 net/core/skbuff.c:497 [<ffffffff82a5cf64>] alloc_skb include/linux/skbuff.h:1267 [inline] [<ffffffff82a5cf64>] virtual_ncidev_write+0x24/0xe0 drivers/nfc/virtual_ncidev.c:116 [<ffffffff815f6503>] do_loop_readv_writev fs/read_write.c:759 [inline] [<ffffffff815f6503>] do_loop_readv_writev fs/read_write.c:743 [inline] [<ffffffff815f6503>] do_iter_write+0x253/0x300 fs/read_write.c:863 [<ffffffff815f66ed>] vfs_writev+0xdd/0x240 fs/read_write.c:934 [<ffffffff815f68f6>] do_writev+0xa6/0x1c0 fs/read_write.c:977 [<ffffffff848802d5>] do_syscall_x64 arch/x86/entry/common.c:50 [inline] [<ffffffff848802d5>] do_syscall_64+0x35/0xb0 arch/x86/entry/common.c:80 [<ffffffff84a00087>] entry_SYSCALL_64_after_hwframe+0x63/0xcd

In nci_rx_data_packet(), if we don't get a valid conn_info, we will return directly but forget to release the skb.

Reported-by: syzbot+cdb9a427d1bc08815104@syzkaller.appspotmail.com Fixes: 4aeee6871e8c ("NFC: nci: Add dynamic logical connections support") Signed-off-by: Liu Shixin liushixin2@huawei.com Link: https://lore.kernel.org/r/20221118082419.239475-1-liushixin2@huawei.com Signed-off-by: Paolo Abeni pabeni@redhat.com Signed-off-by: Sasha Levin sashal@kernel.org --- net/nfc/nci/data.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/net/nfc/nci/data.c b/net/nfc/nci/data.c index aa5e712adf07..3d36ea5701f0 100644 --- a/net/nfc/nci/data.c +++ b/net/nfc/nci/data.c @@ -279,8 +279,10 @@ void nci_rx_data_packet(struct nci_dev *ndev, struct sk_buff *skb) nci_plen(skb->data));

conn_info = nci_get_conn_info_by_conn_id(ndev, nci_conn_id(skb->data)); - if (!conn_info) + if (!conn_info) { + kfree_skb(skb); return; + }

/* strip the nci data header */ skb_pull(skb, NCI_DATA_HDR_SIZE);

From: Yang Yingliang yangyingliang@huawei.com

[ Upstream commit 3637a29ccbb6461b7268c5c5db525935d510afc6 ]

As comment of pci_get_domain_bus_and_slot() says, it returns a pci device with refcount increment, when finish using it, the caller must decrement the reference count by calling pci_dev_put(). Call pci_dev_put() before returning from bnx2x_vf_is_pcie_pending() to avoid refcount leak.

Fixes: b56e9670ffa4 ("bnx2x: Prepare device and initialize VF database") Suggested-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Yang Yingliang yangyingliang@huawei.com Reviewed-by: Leon Romanovsky leonro@nvidia.com Link: https://lore.kernel.org/r/20221119070202.1407648-1-yangyingliang@huawei.com Signed-off-by: Paolo Abeni pabeni@redhat.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c | 12 ++++++++---- 1 file changed, 8 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c index 11d15cd03600..77d4cb4ad782 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c @@ -795,16 +795,20 @@ static void bnx2x_vf_enable_traffic(struct bnx2x *bp, struct bnx2x_virtf *vf)

static u8 bnx2x_vf_is_pcie_pending(struct bnx2x *bp, u8 abs_vfid) { - struct pci_dev *dev; struct bnx2x_virtf *vf = bnx2x_vf_by_abs_fid(bp, abs_vfid); + struct pci_dev *dev; + bool pending;

if (!vf) return false;

dev = pci_get_domain_bus_and_slot(vf->domain, vf->bus, vf->devfn); - if (dev) - return bnx2x_is_pcie_pending(dev); - return false; + if (!dev) + return false; + pending = bnx2x_is_pcie_pending(dev); + pci_dev_put(dev); + + return pending; }

int bnx2x_vf_flr_clnup_epilog(struct bnx2x *bp, u8 abs_vfid)

From: Gerhard Engleder gerhard@engleder-embedded.com

[ Upstream commit 2dc4ac91f845b690ddf2ad39172c3698b2769fa2 ]

If PTP synchronisation is done every second, then sporadic the interval is higher than one second:

ptp4l[696.582]: master offset -17 s2 freq -1891 path delay 573 ptp4l[697.582]: master offset -22 s2 freq -1901 path delay 573 ptp4l[699.368]: master offset -1 s2 freq -1887 path delay 573 ^^^^^^^ Should be 698.582!

This problem is caused by rotten packets, which are received after polling but before interrupts are enabled again. This can be fixed by checking for pending work and rescheduling if necessary after interrupts has been enabled again.

Fixes: 403f69bbdbad ("tsnep: Add TSN endpoint Ethernet MAC driver") Signed-off-by: Gerhard Engleder gerhard@engleder-embedded.com Link: https://lore.kernel.org/r/20221119211825.81805-1-gerhard@engleder-embedded.c... Signed-off-by: Paolo Abeni pabeni@redhat.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/engleder/tsnep_main.c | 57 +++++++++++++++++++++- 1 file changed, 56 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/engleder/tsnep_main.c b/drivers/net/ethernet/engleder/tsnep_main.c index a5f7152a1716..6a2617cc5490 100644 --- a/drivers/net/ethernet/engleder/tsnep_main.c +++ b/drivers/net/ethernet/engleder/tsnep_main.c @@ -504,6 +504,27 @@ static bool tsnep_tx_poll(struct tsnep_tx *tx, int napi_budget) return (budget != 0); }

+static bool tsnep_tx_pending(struct tsnep_tx *tx) +{ + unsigned long flags; + struct tsnep_tx_entry *entry; + bool pending = false; + + spin_lock_irqsave(&tx->lock, flags); + + if (tx->read != tx->write) { + entry = &tx->entry[tx->read]; + if ((__le32_to_cpu(entry->desc_wb->properties) & + TSNEP_TX_DESC_OWNER_MASK) == + (entry->properties & TSNEP_TX_DESC_OWNER_MASK)) + pending = true; + } + + spin_unlock_irqrestore(&tx->lock, flags); + + return pending; +} + static int tsnep_tx_open(struct tsnep_adapter *adapter, void __iomem *addr, struct tsnep_tx *tx) { @@ -751,6 +772,19 @@ static int tsnep_rx_poll(struct tsnep_rx *rx, struct napi_struct *napi, return done; }

+static bool tsnep_rx_pending(struct tsnep_rx *rx) +{ + struct tsnep_rx_entry *entry; + + entry = &rx->entry[rx->read]; + if ((__le32_to_cpu(entry->desc_wb->properties) & + TSNEP_DESC_OWNER_COUNTER_MASK) == + (entry->properties & TSNEP_DESC_OWNER_COUNTER_MASK)) + return true; + + return false; +} + static int tsnep_rx_open(struct tsnep_adapter *adapter, void __iomem *addr, struct tsnep_rx *rx) { @@ -795,6 +829,17 @@ static void tsnep_rx_close(struct tsnep_rx *rx) tsnep_rx_ring_cleanup(rx); }

+static bool tsnep_pending(struct tsnep_queue *queue) +{ + if (queue->tx && tsnep_tx_pending(queue->tx)) + return true; + + if (queue->rx && tsnep_rx_pending(queue->rx)) + return true; + + return false; +} + static int tsnep_poll(struct napi_struct *napi, int budget) { struct tsnep_queue *queue = container_of(napi, struct tsnep_queue, @@ -815,9 +860,19 @@ static int tsnep_poll(struct napi_struct *napi, int budget) if (!complete) return budget;

- if (likely(napi_complete_done(napi, done))) + if (likely(napi_complete_done(napi, done))) { tsnep_enable_irq(queue->adapter, queue->irq_mask);

+ /* reschedule if work is already pending, prevent rotten packets + * which are transmitted or received after polling but before + * interrupt enable + */ + if (tsnep_pending(queue)) { + tsnep_disable_irq(queue->adapter, queue->irq_mask); + napi_schedule(napi); + } + } + return min(done, budget - 1); }

From: Jozsef Kadlecsik kadlec@netfilter.org

[ Upstream commit 6a66ce44a51bdfc47721f0c591137df2d4b21247 ]

The commit 510841da1fcc ("netfilter: ipset: enforce documented limit to prevent allocating huge memory") was too strict and prevented to add up to 64 clashing elements to a hash:net,iface type of set. This patch fixes the issue and now the type behaves as documented.

Fixes: 510841da1fcc ("netfilter: ipset: enforce documented limit to prevent allocating huge memory") Signed-off-by: Jozsef Kadlecsik kadlec@netfilter.org Signed-off-by: Pablo Neira Ayuso pablo@netfilter.org Signed-off-by: Sasha Levin sashal@kernel.org --- net/netfilter/ipset/ip_set_hash_gen.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/netfilter/ipset/ip_set_hash_gen.h b/net/netfilter/ipset/ip_set_hash_gen.h index 3adc291d9ce1..7499192af586 100644 --- a/net/netfilter/ipset/ip_set_hash_gen.h +++ b/net/netfilter/ipset/ip_set_hash_gen.h @@ -916,7 +916,7 @@ mtype_add(struct ip_set *set, void *value, const struct ip_set_ext *ext, #ifdef IP_SET_HASH_WITH_MULTI if (h->bucketsize >= AHASH_MAX_TUNED) goto set_full; - else if (h->bucketsize < multi) + else if (h->bucketsize <= multi) h->bucketsize += AHASH_INIT_SIZE; #endif if (n->size >= AHASH_MAX(h)) {

From: Svyatoslav Feldsherov feldsherov@google.com

[ Upstream commit 4e3c51f4e805291b057d12f5dda5aeb50a538dc4 ]

After commit cbfecb927f42 ("fs: record I_DIRTY_TIME even if inode already has I_DIRTY_INODE") writeback_single_inode can push inode with I_DIRTY_TIME set to b_dirty_time list. In case of freeing inode with I_DIRTY_TIME set this can happen after deletion of inode from i_io_list at evict. Stack trace is following.

evict fat_evict_inode fat_truncate_blocks fat_flush_inodes writeback_inode sync_inode_metadata(inode, sync=0) writeback_single_inode(inode, wbc) <- wbc->sync_mode == WB_SYNC_NONE

This will lead to use after free in flusher thread.

Similar issue can be triggered if writeback_single_inode in the stack trace update inode->i_io_list. Add explicit check to avoid it.

Fixes: cbfecb927f42 ("fs: record I_DIRTY_TIME even if inode already has I_DIRTY_INODE") Reported-by: syzbot+6ba92bd00d5093f7e371@syzkaller.appspotmail.com Reviewed-by: Jan Kara jack@suse.cz Signed-off-by: Svyatoslav Feldsherov feldsherov@google.com Link: https://lore.kernel.org/r/20221115202001.324188-1-feldsherov@google.com Signed-off-by: Theodore Ts'o tytso@mit.edu Signed-off-by: Sasha Levin sashal@kernel.org --- fs/fs-writeback.c | 30 +++++++++++++++++++----------- 1 file changed, 19 insertions(+), 11 deletions(-)

diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index 443f83382b9b..9958d4020771 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -1712,18 +1712,26 @@ static int writeback_single_inode(struct inode *inode, wb = inode_to_wb_and_lock_list(inode); spin_lock(&inode->i_lock); /* - * If the inode is now fully clean, then it can be safely removed from - * its writeback list (if any). Otherwise the flusher threads are - * responsible for the writeback lists. + * If the inode is freeing, its i_io_list shoudn't be updated + * as it can be finally deleted at this moment. */ - if (!(inode->i_state & I_DIRTY_ALL)) - inode_cgwb_move_to_attached(inode, wb); - else if (!(inode->i_state & I_SYNC_QUEUED)) { - if ((inode->i_state & I_DIRTY)) - redirty_tail_locked(inode, wb); - else if (inode->i_state & I_DIRTY_TIME) { - inode->dirtied_when = jiffies; - inode_io_list_move_locked(inode, wb, &wb->b_dirty_time); + if (!(inode->i_state & I_FREEING)) { + /* + * If the inode is now fully clean, then it can be safely + * removed from its writeback list (if any). Otherwise the + * flusher threads are responsible for the writeback lists. + */ + if (!(inode->i_state & I_DIRTY_ALL)) + inode_cgwb_move_to_attached(inode, wb); + else if (!(inode->i_state & I_SYNC_QUEUED)) { + if ((inode->i_state & I_DIRTY)) + redirty_tail_locked(inode, wb); + else if (inode->i_state & I_DIRTY_TIME) { + inode->dirtied_when = jiffies; + inode_io_list_move_locked(inode, + wb, + &wb->b_dirty_time); + } } }

From: Li Hua hucool.lihua@huawei.com

[ Upstream commit de3db3f883a82c4800f4af0ae2cc3b96a408ee9b ]

If KPROBES_SANITY_TEST and ARCH_CORRECT_STACKTRACE_ON_KRETPROBE is enabled, but STACKTRACE is not set. Build failed as below:

lib/test_kprobes.c: In function `stacktrace_return_handler': lib/test_kprobes.c:228:8: error: implicit declaration of function `stack_trace_save'; did you mean `stacktrace_driver'? [-Werror=implicit-function-declaration] ret = stack_trace_save(stack_buf, STACK_BUF_SIZE, 0); ^~~~~~~~~~~~~~~~ stacktrace_driver cc1: all warnings being treated as errors scripts/Makefile.build:250: recipe for target 'lib/test_kprobes.o' failed make[2]: *** [lib/test_kprobes.o] Error 1

To fix this error, Select STACKTRACE if ARCH_CORRECT_STACKTRACE_ON_KRETPROBE is enabled.

Link: https://lkml.kernel.org/r/20221121030620.63181-1-hucool.lihua@huawei.com Fixes: 1f6d3a8f5e39 ("kprobes: Add a test case for stacktrace from kretprobe handler") Signed-off-by: Li Hua hucool.lihua@huawei.com Acked-by: Masami Hiramatsu (Google) mhiramat@kernel.org Cc: Steven Rostedt (VMware) rostedt@goodmis.org Signed-off-by: Andrew Morton akpm@linux-foundation.org Signed-off-by: Sasha Levin sashal@kernel.org --- lib/Kconfig.debug | 1 + 1 file changed, 1 insertion(+)

diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index cb131fad117c..997d23641448 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -2095,6 +2095,7 @@ config KPROBES_SANITY_TEST depends on DEBUG_KERNEL depends on KPROBES depends on KUNIT + select STACKTRACE if ARCH_CORRECT_STACKTRACE_ON_KRETPROBE default KUNIT_ALL_TESTS help This option provides for testing basic kprobes functionality on

From: Ziyang Xuan william.xuanziyang@huawei.com

[ Upstream commit 3213f808ae21be3891885de2f3a775afafcda987 ]

When fail to dma_map_single() in mtk_rx_alloc(), it returns directly. But the memory allocated for local variable data is not freed, and local variabel data has not been attached to ring->data[i] yet, so the memory allocated for local variable data will not be freed outside mtk_rx_alloc() too. Thus memory leak would occur in this scenario.

Add skb_free_frag(data) when dma_map_single() failed.

Fixes: 23233e577ef9 ("net: ethernet: mtk_eth_soc: rely on page_pool for single page buffers") Signed-off-by: Ziyang Xuan william.xuanziyang@huawei.com Acked-by: Lorenzo Bianconi lorenzo.bianconi@redhat.com Link: https://lore.kernel.org/r/20221120035405.1464341-1-william.xuanziyang@huawei... Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/mediatek/mtk_eth_soc.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.c b/drivers/net/ethernet/mediatek/mtk_eth_soc.c index a75f5931f746..916b570bdbf4 100644 --- a/drivers/net/ethernet/mediatek/mtk_eth_soc.c +++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.c @@ -2363,8 +2363,10 @@ static int mtk_rx_alloc(struct mtk_eth *eth, int ring_no, int rx_flag) data + NET_SKB_PAD + eth->ip_align, ring->buf_size, DMA_FROM_DEVICE); if (unlikely(dma_mapping_error(eth->dma_dev, - dma_addr))) + dma_addr))) { + skb_free_frag(data); return -ENOMEM; + } } rxd->rxd1 = (unsigned int)dma_addr; ring->data[i] = data;

From: Lorenzo Bianconi lorenzo@kernel.org

[ Upstream commit ba2fc48c5e1e9e1934939f0d12ff8b985dcc6e5d ]

This is a preliminary patch to introduce mt7986 hw packet engine.

Tested-by: Daniel Golle daniel@makrotopia.org Co-developed-by: Bo Jiao Bo.Jiao@mediatek.com Signed-off-by: Bo Jiao Bo.Jiao@mediatek.com Co-developed-by: Sujuan Chen sujuan.chen@mediatek.com Signed-off-by: Sujuan Chen sujuan.chen@mediatek.com Signed-off-by: Lorenzo Bianconi lorenzo@kernel.org Signed-off-by: Paolo Abeni pabeni@redhat.com Stable-dep-of: 8110437e5961 ("net: ethernet: mtk_eth_soc: fix resource leak in error path") Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/mediatek/mtk_eth_soc.c | 4 ++++ drivers/net/ethernet/mediatek/mtk_eth_soc.h | 2 ++ drivers/net/ethernet/mediatek/mtk_ppe.c | 24 +++++++++++++++------ drivers/net/ethernet/mediatek/mtk_ppe.h | 2 +- 4 files changed, 25 insertions(+), 7 deletions(-)

diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.c b/drivers/net/ethernet/mediatek/mtk_eth_soc.c index 83c636d44142..3db24ddd1261 100644 --- a/drivers/net/ethernet/mediatek/mtk_eth_soc.c +++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.c @@ -4210,6 +4210,7 @@ static const struct mtk_soc_data mt7621_data = { .required_clks = MT7621_CLKS_BITMAP, .required_pctl = false, .offload_version = 2, + .hash_offset = 2, .txrx = { .txd_size = sizeof(struct mtk_tx_dma), .rxd_size = sizeof(struct mtk_rx_dma), @@ -4228,6 +4229,7 @@ static const struct mtk_soc_data mt7622_data = { .required_clks = MT7622_CLKS_BITMAP, .required_pctl = false, .offload_version = 2, + .hash_offset = 2, .txrx = { .txd_size = sizeof(struct mtk_tx_dma), .rxd_size = sizeof(struct mtk_rx_dma), @@ -4245,6 +4247,7 @@ static const struct mtk_soc_data mt7623_data = { .required_clks = MT7623_CLKS_BITMAP, .required_pctl = true, .offload_version = 2, + .hash_offset = 2, .txrx = { .txd_size = sizeof(struct mtk_tx_dma), .rxd_size = sizeof(struct mtk_rx_dma), @@ -4278,6 +4281,7 @@ static const struct mtk_soc_data mt7986_data = { .caps = MT7986_CAPS, .required_clks = MT7986_CLKS_BITMAP, .required_pctl = false, + .hash_offset = 4, .txrx = { .txd_size = sizeof(struct mtk_tx_dma_v2), .rxd_size = sizeof(struct mtk_rx_dma_v2), diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.h b/drivers/net/ethernet/mediatek/mtk_eth_soc.h index 511752729f5c..26ed1c8b77c3 100644 --- a/drivers/net/ethernet/mediatek/mtk_eth_soc.h +++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.h @@ -969,6 +969,7 @@ struct mtk_reg_map { * the target SoC * @required_pctl A bool value to show whether the SoC requires * the extra setup for those pins used by GMAC. + * @hash_offset Flow table hash offset. * @txd_size Tx DMA descriptor size. * @rxd_size Rx DMA descriptor size. * @rx_irq_done_mask Rx irq done register mask. @@ -983,6 +984,7 @@ struct mtk_soc_data { u32 required_clks; bool required_pctl; u8 offload_version; + u8 hash_offset; netdev_features_t hw_features; struct { u32 txd_size; diff --git a/drivers/net/ethernet/mediatek/mtk_ppe.c b/drivers/net/ethernet/mediatek/mtk_ppe.c index 148ea636ef97..6ecac461fd76 100644 --- a/drivers/net/ethernet/mediatek/mtk_ppe.c +++ b/drivers/net/ethernet/mediatek/mtk_ppe.c @@ -88,7 +88,7 @@ static void mtk_ppe_cache_enable(struct mtk_ppe *ppe, bool enable) enable * MTK_PPE_CACHE_CTL_EN); }

-static u32 mtk_ppe_hash_entry(struct mtk_foe_entry *e) +static u32 mtk_ppe_hash_entry(struct mtk_eth *eth, struct mtk_foe_entry *e) { u32 hv1, hv2, hv3; u32 hash; @@ -122,7 +122,7 @@ static u32 mtk_ppe_hash_entry(struct mtk_foe_entry *e) hash = (hash >> 24) | ((hash & 0xffffff) << 8); hash ^= hv1 ^ hv2 ^ hv3; hash ^= hash >> 16; - hash <<= 1; + hash <<= (ffs(eth->soc->hash_offset) - 1); hash &= MTK_PPE_ENTRIES - 1;

return hash; @@ -540,15 +540,16 @@ mtk_foe_entry_commit_l2(struct mtk_ppe *ppe, struct mtk_flow_entry *entry) int mtk_foe_entry_commit(struct mtk_ppe *ppe, struct mtk_flow_entry *entry) { int type = FIELD_GET(MTK_FOE_IB1_PACKET_TYPE, entry->data.ib1); + const struct mtk_soc_data *soc = ppe->eth->soc; u32 hash;

if (type == MTK_PPE_PKT_TYPE_BRIDGE) return mtk_foe_entry_commit_l2(ppe, entry);

- hash = mtk_ppe_hash_entry(&entry->data); + hash = mtk_ppe_hash_entry(ppe->eth, &entry->data); entry->hash = 0xffff; spin_lock_bh(&ppe_lock); - hlist_add_head(&entry->list, &ppe->foe_flow[hash / 2]); + hlist_add_head(&entry->list, &ppe->foe_flow[hash / soc->hash_offset]); spin_unlock_bh(&ppe_lock);

return 0; @@ -558,6 +559,7 @@ static void mtk_foe_entry_commit_subflow(struct mtk_ppe *ppe, struct mtk_flow_entry *entry, u16 hash) { + const struct mtk_soc_data *soc = ppe->eth->soc; struct mtk_flow_entry *flow_info; struct mtk_foe_entry foe, *hwe; struct mtk_foe_mac_info *l2; @@ -572,7 +574,8 @@ mtk_foe_entry_commit_subflow(struct mtk_ppe *ppe, struct mtk_flow_entry *entry, flow_info->l2_data.base_flow = entry; flow_info->type = MTK_FLOW_TYPE_L2_SUBFLOW; flow_info->hash = hash; - hlist_add_head(&flow_info->list, &ppe->foe_flow[hash / 2]); + hlist_add_head(&flow_info->list, + &ppe->foe_flow[hash / soc->hash_offset]); hlist_add_head(&flow_info->l2_data.list, &entry->l2_flows);

hwe = &ppe->foe_table[hash]; @@ -596,7 +599,8 @@ mtk_foe_entry_commit_subflow(struct mtk_ppe *ppe, struct mtk_flow_entry *entry,

void __mtk_ppe_check_skb(struct mtk_ppe *ppe, struct sk_buff *skb, u16 hash) { - struct hlist_head *head = &ppe->foe_flow[hash / 2]; + const struct mtk_soc_data *soc = ppe->eth->soc; + struct hlist_head *head = &ppe->foe_flow[hash / soc->hash_offset]; struct mtk_foe_entry *hwe = &ppe->foe_table[hash]; struct mtk_flow_entry *entry; struct mtk_foe_bridge key = {}; @@ -680,9 +684,11 @@ int mtk_foe_entry_idle_time(struct mtk_ppe *ppe, struct mtk_flow_entry *entry) struct mtk_ppe *mtk_ppe_init(struct mtk_eth *eth, void __iomem *base, int version) { + const struct mtk_soc_data *soc = eth->soc; struct device *dev = eth->dev; struct mtk_foe_entry *foe; struct mtk_ppe *ppe; + u32 foe_flow_size;

ppe = devm_kzalloc(dev, sizeof(*ppe), GFP_KERNEL); if (!ppe) @@ -705,6 +711,12 @@ struct mtk_ppe *mtk_ppe_init(struct mtk_eth *eth, void __iomem *base,

ppe->foe_table = foe;

+ foe_flow_size = (MTK_PPE_ENTRIES / soc->hash_offset) * + sizeof(*ppe->foe_flow); + ppe->foe_flow = devm_kzalloc(dev, foe_flow_size, GFP_KERNEL); + if (!ppe->foe_flow) + return NULL; + mtk_ppe_debugfs_init(ppe);

return ppe; diff --git a/drivers/net/ethernet/mediatek/mtk_ppe.h b/drivers/net/ethernet/mediatek/mtk_ppe.h index ceb7dfe281de..7a16503690f3 100644 --- a/drivers/net/ethernet/mediatek/mtk_ppe.h +++ b/drivers/net/ethernet/mediatek/mtk_ppe.h @@ -270,7 +270,7 @@ struct mtk_ppe { dma_addr_t foe_phys;

u16 foe_check_time[MTK_PPE_ENTRIES]; - struct hlist_head foe_flow[MTK_PPE_ENTRIES / 2]; + struct hlist_head *foe_flow;

struct rhashtable l2_flows;

From: Ziyang Xuan william.xuanziyang@huawei.com

[ Upstream commit 568fe84940ac0e4e0b2cd7751b8b4911f7b9c215 ]

In fib_table_insert(), if the alias was already inserted, but node not exist, the error code should be set before return from error handling path.

Fixes: a6c76c17df02 ("ipv4: Notify route after insertion to the routing table") Signed-off-by: Ziyang Xuan william.xuanziyang@huawei.com Link: https://lore.kernel.org/r/20221120072838.2167047-1-william.xuanziyang@huawei... Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- net/ipv4/fib_trie.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index 452ff177e4da..f26d5ac117d6 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -1381,8 +1381,10 @@ int fib_table_insert(struct net *net, struct fib_table *tb,

/* The alias was already inserted, so the node must exist. */ l = l ? l : fib_find_node(t, &tp, key); - if (WARN_ON_ONCE(!l)) + if (WARN_ON_ONCE(!l)) { + err = -ENOENT; goto out_free_new_fa; + }

if (fib_find_alias(&l->leaf, new_fa->fa_slen, 0, 0, tb->tb_id, true) == new_fa) {

From: Yuan Can yuancan@huawei.com

[ Upstream commit bac81f40c2c1484a2bd416b3fbf983f6e76488cd ]

The dm9051_loop_rx() returns without release skb when dm9051_stop_mrcmd() returns error, free the skb to avoid this leak.

Fixes: 2dc95a4d30ed ("net: Add dm9051 driver") Signed-off-by: Yuan Can yuancan@huawei.com Reviewed-by: Maciej Fijalkowski maciej.fijalkowski@intel.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/davicom/dm9051.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/davicom/dm9051.c b/drivers/net/ethernet/davicom/dm9051.c index a523ddda7609..de7105a84747 100644 --- a/drivers/net/ethernet/davicom/dm9051.c +++ b/drivers/net/ethernet/davicom/dm9051.c @@ -798,8 +798,10 @@ static int dm9051_loop_rx(struct board_info *db) }

ret = dm9051_stop_mrcmd(db); - if (ret) + if (ret) { + dev_kfree_skb(skb); return ret; + }

skb->protocol = eth_type_trans(skb, db->ndev); if (db->ndev->features & NETIF_F_RXCSUM)

From: Wei Yongjun weiyongjun1@huawei.com

[ Upstream commit 9ac74f0666ceab0b1047e9d59be846a3345e4e98 ]

If kzalloc() for 'ap_qci_info_old' failed, 'ap_qci_info' shold be freed before return. Otherwise it is a memory leak.

Link: https://lore.kernel.org/r/20221114110830.542246-1-weiyongjun@huaweicloud.com Fixes: 283915850a44 ("s390/ap: notify drivers on config changed and scan complete callbacks") Signed-off-by: Wei Yongjun weiyongjun1@huawei.com Signed-off-by: Harald Freudenberger freude@linux.ibm.com Signed-off-by: Alexander Gordeev agordeev@linux.ibm.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/s390/crypto/ap_bus.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/s390/crypto/ap_bus.c b/drivers/s390/crypto/ap_bus.c index 59ac98f2bd27..b02c631f3b71 100644 --- a/drivers/s390/crypto/ap_bus.c +++ b/drivers/s390/crypto/ap_bus.c @@ -233,8 +233,11 @@ static void __init ap_init_qci_info(void) if (!ap_qci_info) return; ap_qci_info_old = kzalloc(sizeof(*ap_qci_info_old), GFP_KERNEL); - if (!ap_qci_info_old) + if (!ap_qci_info_old) { + kfree(ap_qci_info); + ap_qci_info = NULL; return; + } if (ap_fetch_qci_info(ap_qci_info) != 0) { kfree(ap_qci_info); kfree(ap_qci_info_old);

From: David Howells dhowells@redhat.com

[ Upstream commit 9f0933ac026f7e54fe096797af9de20724e79097 ]

The type of a->key[0] is char in fscache_volume_same(). If the length of cache volume key is greater than 127, the value of a->key[0] is less than 0. In this case, klen becomes much larger than 255 after type conversion, because the type of klen is size_t. As a result, memcmp() is read out of bounds.

This causes a slab-out-of-bounds Read in __fscache_acquire_volume(), as reported by Syzbot.

Fix this by changing the type of the stored key to "u8 *" rather than "char *" (it isn't a simple string anyway). Also put in a check that the volume name doesn't exceed NAME_MAX.

BUG: KASAN: slab-out-of-bounds in memcmp+0x16f/0x1c0 lib/string.c:757 Read of size 8 at addr ffff888016f3aa90 by task syz-executor344/3613 Call Trace: memcmp+0x16f/0x1c0 lib/string.c:757 memcmp include/linux/fortify-string.h:420 [inline] fscache_volume_same fs/fscache/volume.c:133 [inline] fscache_hash_volume fs/fscache/volume.c:171 [inline] __fscache_acquire_volume+0x76c/0x1080 fs/fscache/volume.c:328 fscache_acquire_volume include/linux/fscache.h:204 [inline] v9fs_cache_session_get_cookie+0x143/0x240 fs/9p/cache.c:34 v9fs_session_init+0x1166/0x1810 fs/9p/v9fs.c:473 v9fs_mount+0xba/0xc90 fs/9p/vfs_super.c:126 legacy_get_tree+0x105/0x220 fs/fs_context.c:610 vfs_get_tree+0x89/0x2f0 fs/super.c:1530 do_new_mount fs/namespace.c:3040 [inline] path_mount+0x1326/0x1e20 fs/namespace.c:3370 do_mount fs/namespace.c:3383 [inline] __do_sys_mount fs/namespace.c:3591 [inline] __se_sys_mount fs/namespace.c:3568 [inline] __x64_sys_mount+0x27f/0x300 fs/namespace.c:3568

Fixes: 62ab63352350 ("fscache: Implement volume registration") Reported-by: syzbot+a76f6a6e524cf2080aa3@syzkaller.appspotmail.com Signed-off-by: David Howells dhowells@redhat.com Reviewed-by: Zhang Peng zhangpeng362@huawei.com Reviewed-by: Jingbo Xu jefflexu@linux.alibaba.com cc: Dominique Martinet asmadeus@codewreck.org cc: Jeff Layton jlayton@kernel.org cc: v9fs-developer@lists.sourceforge.net cc: linux-cachefs@redhat.com Link: https://lore.kernel.org/r/Y3OH+Dmi0QIOK18n@codewreck.org/ # Zhang Peng's v1 fix Link: https://lore.kernel.org/r/20221115140447.2971680-1-zhangpeng362@huawei.com/ # Zhang Peng's v2 fix Link: https://lore.kernel.org/r/166869954095.3793579.8500020902371015443.stgit@war... # v1 Signed-off-by: Linus Torvalds torvalds@linux-foundation.org Signed-off-by: Sasha Levin sashal@kernel.org --- fs/fscache/volume.c | 7 +++++-- include/linux/fscache.h | 2 +- 2 files changed, 6 insertions(+), 3 deletions(-)

diff --git a/fs/fscache/volume.c b/fs/fscache/volume.c index a058e0136bfe..ab8ceddf9efa 100644 --- a/fs/fscache/volume.c +++ b/fs/fscache/volume.c @@ -203,7 +203,11 @@ static struct fscache_volume *fscache_alloc_volume(const char *volume_key, struct fscache_volume *volume; struct fscache_cache *cache; size_t klen, hlen; - char *key; + u8 *key; + + klen = strlen(volume_key); + if (klen > NAME_MAX) + return NULL;

if (!coherency_data) coherency_len = 0; @@ -229,7 +233,6 @@ static struct fscache_volume *fscache_alloc_volume(const char *volume_key, /* Stick the length on the front of the key and pad it out to make * hashing easier. */ - klen = strlen(volume_key); hlen = round_up(1 + klen + 1, sizeof(__le32)); key = kzalloc(hlen, GFP_KERNEL); if (!key) diff --git a/include/linux/fscache.h b/include/linux/fscache.h index 36e5dd84cf59..8e312c8323a8 100644 --- a/include/linux/fscache.h +++ b/include/linux/fscache.h @@ -75,7 +75,7 @@ struct fscache_volume { atomic_t n_accesses; /* Number of cache accesses in progress */ unsigned int debug_id; unsigned int key_hash; /* Hash of key string */ - char *key; /* Volume ID, eg. "afs@example.com@1234" */ + u8 *key; /* Volume ID, eg. "afs@example.com@1234" */ struct list_head proc_link; /* Link in /proc/fs/fscache/volumes */ struct hlist_bl_node hash_link; /* Link in hash table */ struct work_struct work;

From: Martin Faltesek mfaltesek@google.com

[ Upstream commit 440f2ae9c9f06e26f5dcea697a53717fc61a318c ]

Error path does not free previously allocated memory. Add devm_kfree() to the failure path.

Reported-by: Denis Efremov denis.e.efremov@oracle.com Reviewed-by: Guenter Roeck groeck@google.com Fixes: 5d1ceb7f5e56 ("NFC: st21nfcb: Add HCI transaction event support") Signed-off-by: Martin Faltesek mfaltesek@google.com Reviewed-by: Krzysztof Kozlowski krzysztof.kozlowski@linaro.org Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/nfc/st-nci/se.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/nfc/st-nci/se.c b/drivers/nfc/st-nci/se.c index 589e1dec78e7..fc59916ae5ae 100644 --- a/drivers/nfc/st-nci/se.c +++ b/drivers/nfc/st-nci/se.c @@ -339,8 +339,10 @@ static int st_nci_hci_connectivity_event_received(struct nci_dev *ndev,

/* Check next byte is PARAMETERS tag (82) */ if (skb->data[transaction->aid_len + 2] != - NFC_EVT_TRANSACTION_PARAMS_TAG) + NFC_EVT_TRANSACTION_PARAMS_TAG) { + devm_kfree(dev, transaction); return -EPROTO; + }

transaction->params_len = skb->data[transaction->aid_len + 3]; memcpy(transaction->params, skb->data +

From: Zhang Changzhong zhangchangzhong@huawei.com

[ Upstream commit 9a234a2a085ab9fd2be8d0c1eedfcd10f74b97eb ]

If prestera_port_sfp_bind() fails, unregister_netdev() should be called in error handling path.

Compile tested only.

Fixes: 52323ef75414 ("net: marvell: prestera: add phylink support") Signed-off-by: Zhang Changzhong zhangchangzhong@huawei.com Reviewed-by: Maciej Fijalkowski maciej.fijalkowski@intel.com Link: https://lore.kernel.org/r/1669115432-36841-1-git-send-email-zhangchangzhong@... Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/marvell/prestera/prestera_main.c | 1 + 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/marvell/prestera/prestera_main.c b/drivers/net/ethernet/marvell/prestera/prestera_main.c index a0ad0bcbf89f..9f588ecba93e 100644 --- a/drivers/net/ethernet/marvell/prestera/prestera_main.c +++ b/drivers/net/ethernet/marvell/prestera/prestera_main.c @@ -730,6 +730,7 @@ static int prestera_port_create(struct prestera_switch *sw, u32 id) return 0;

err_sfp_bind: + unregister_netdev(dev); err_register_netdev: prestera_port_list_del(port); err_port_init:

From: Vladimir Oltean vladimir.oltean@nxp.com

[ Upstream commit 290b5fe096e7dd0aad730d1af4f7f2d9fea43e11 ]

In the blamed commit, a rudimentary reallocation procedure for RX buffer descriptors was implemented, for the situation when their format changes between normal (no PTP) and extended (PTP).

enetc_hwtstamp_set() calls enetc_close() and enetc_open() in a sequence, and this sequence loses information which was previously configured in the TX BDR Mode Register, specifically via the enetc_set_bdr_prio() call. The TX ring priority is configured by tc-mqprio and tc-taprio, and affects important things for TSN such as the TX time of packets. The issue manifests itself most visibly by the fact that isochron --txtime reports premature packet transmissions when PTP is first enabled on an enetc interface.

Save the TX ring priority in a new field in struct enetc_bdr (occupies a 2 byte hole on arm64) in order to make this survive a ring reconfiguration.

Fixes: 434cebabd3a2 ("enetc: Add dynamic allocation of extended Rx BD rings") Signed-off-by: Vladimir Oltean vladimir.oltean@nxp.com Reviewed-by: Alexander Lobakin alexandr.lobakin@intel.com Link: https://lore.kernel.org/r/20221122130936.1704151-1-vladimir.oltean@nxp.com Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/freescale/enetc/enetc.c | 8 ++++--- drivers/net/ethernet/freescale/enetc/enetc.h | 1 + .../net/ethernet/freescale/enetc/enetc_qos.c | 21 ++++++++++++------- 3 files changed, 19 insertions(+), 11 deletions(-)

diff --git a/drivers/net/ethernet/freescale/enetc/enetc.c b/drivers/net/ethernet/freescale/enetc/enetc.c index e6dbc78f490c..1d8ec1b120a1 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc.c +++ b/drivers/net/ethernet/freescale/enetc/enetc.c @@ -2058,7 +2058,7 @@ static void enetc_setup_txbdr(struct enetc_hw *hw, struct enetc_bdr *tx_ring) /* enable Tx ints by setting pkt thr to 1 */ enetc_txbdr_wr(hw, idx, ENETC_TBICR0, ENETC_TBICR0_ICEN | 0x1);

- tbmr = ENETC_TBMR_EN; + tbmr = ENETC_TBMR_EN | ENETC_TBMR_SET_PRIO(tx_ring->prio); if (tx_ring->ndev->features & NETIF_F_HW_VLAN_CTAG_TX) tbmr |= ENETC_TBMR_VIH;

@@ -2461,7 +2461,8 @@ int enetc_setup_tc_mqprio(struct net_device *ndev, void *type_data) /* Reset all ring priorities to 0 */ for (i = 0; i < priv->num_tx_rings; i++) { tx_ring = priv->tx_ring[i]; - enetc_set_bdr_prio(hw, tx_ring->index, 0); + tx_ring->prio = 0; + enetc_set_bdr_prio(hw, tx_ring->index, tx_ring->prio); }

return 0; @@ -2480,7 +2481,8 @@ int enetc_setup_tc_mqprio(struct net_device *ndev, void *type_data) */ for (i = 0; i < num_tc; i++) { tx_ring = priv->tx_ring[i]; - enetc_set_bdr_prio(hw, tx_ring->index, i); + tx_ring->prio = i; + enetc_set_bdr_prio(hw, tx_ring->index, tx_ring->prio); }

/* Reset the number of netdev queues based on the TC count */ diff --git a/drivers/net/ethernet/freescale/enetc/enetc.h b/drivers/net/ethernet/freescale/enetc/enetc.h index 748677b2ce1f..bb1b3b0e40e4 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc.h +++ b/drivers/net/ethernet/freescale/enetc/enetc.h @@ -95,6 +95,7 @@ struct enetc_bdr { void __iomem *rcir; }; u16 index; + u16 prio; int bd_count; /* # of BDs */ int next_to_use; int next_to_clean; diff --git a/drivers/net/ethernet/freescale/enetc/enetc_qos.c b/drivers/net/ethernet/freescale/enetc/enetc_qos.c index 2e783ef73690..5fcb02b00699 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc_qos.c +++ b/drivers/net/ethernet/freescale/enetc/enetc_qos.c @@ -134,6 +134,7 @@ int enetc_setup_tc_taprio(struct net_device *ndev, void *type_data) struct tc_taprio_qopt_offload *taprio = type_data; struct enetc_ndev_priv *priv = netdev_priv(ndev); struct enetc_hw *hw = &priv->si->hw; + struct enetc_bdr *tx_ring; int err; int i;

@@ -142,16 +143,20 @@ int enetc_setup_tc_taprio(struct net_device *ndev, void *type_data) if (priv->tx_ring[i]->tsd_enable) return -EBUSY;

- for (i = 0; i < priv->num_tx_rings; i++) - enetc_set_bdr_prio(hw, priv->tx_ring[i]->index, - taprio->enable ? i : 0); + for (i = 0; i < priv->num_tx_rings; i++) { + tx_ring = priv->tx_ring[i]; + tx_ring->prio = taprio->enable ? i : 0; + enetc_set_bdr_prio(hw, tx_ring->index, tx_ring->prio); + }

err = enetc_setup_taprio(ndev, taprio); - - if (err) - for (i = 0; i < priv->num_tx_rings; i++) - enetc_set_bdr_prio(hw, priv->tx_ring[i]->index, - taprio->enable ? 0 : i); + if (err) { + for (i = 0; i < priv->num_tx_rings; i++) { + tx_ring = priv->tx_ring[i]; + tx_ring->prio = taprio->enable ? 0 : i; + enetc_set_bdr_prio(hw, tx_ring->index, tx_ring->prio); + } + }

return err; }

From: Hanjun Guo guohanjun@huawei.com

[ Upstream commit 08e8a949f684e1fbc4b1efd2337d72ec8f3613d9 ]

The ACPI buffer memory (buffer.pointer) should be freed as the buffer is not used after acpi_evaluate_object(), free it to prevent memory leak.

Fixes: 13e920d93e37 ("net: wwan: t7xx: Add core components") Signed-off-by: Hanjun Guo guohanjun@huawei.com Link: https://lore.kernel.org/r/1669119580-28977-1-git-send-email-guohanjun@huawei... Signed-off-by: Paolo Abeni pabeni@redhat.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/wwan/t7xx/t7xx_modem_ops.c | 2 ++ 1 file changed, 2 insertions(+)

diff --git a/drivers/net/wwan/t7xx/t7xx_modem_ops.c b/drivers/net/wwan/t7xx/t7xx_modem_ops.c index 3458af31e864..7d0f5e4f0a78 100644 --- a/drivers/net/wwan/t7xx/t7xx_modem_ops.c +++ b/drivers/net/wwan/t7xx/t7xx_modem_ops.c @@ -165,6 +165,8 @@ static int t7xx_acpi_reset(struct t7xx_pci_dev *t7xx_dev, char *fn_name) return -EFAULT; }

+ kfree(buffer.pointer); + #endif return 0; }

From: Xiongfeng Wang wangxiongfeng2@huawei.com

[ Upstream commit ad17c2a3f11b0f6b122e7842d8f7d9a5fcc7ac63 ]

pci_get_device() will decrease the reference count for the *from* parameter. So we don't need to call put_device() to decrease the reference. Let's remove the put_device() in the loop and only decrease the reference count of the returned 'pdev' for the last loop because it will not be passed to pci_get_device() as input parameter. We don't need to check if 'pdev' is NULL because it is already checked inside pci_dev_put(). Also add pci_dev_put() for the error path.

Fixes: fe1939bb2340 ("octeontx2-af: Add SDP interface support") Signed-off-by: Xiongfeng Wang wangxiongfeng2@huawei.com Reviewed-by: Saeed Mahameed saeed@kernel.org Link: https://lore.kernel.org/r/20221123065919.31499-1-wangxiongfeng2@huawei.com Signed-off-by: Paolo Abeni pabeni@redhat.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/marvell/octeontx2/af/rvu_sdp.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_sdp.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_sdp.c index b04fb226f708..ae50d56258ec 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_sdp.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_sdp.c @@ -62,15 +62,18 @@ int rvu_sdp_init(struct rvu *rvu) pfvf->sdp_info = devm_kzalloc(rvu->dev, sizeof(struct sdp_node_info), GFP_KERNEL); - if (!pfvf->sdp_info) + if (!pfvf->sdp_info) { + pci_dev_put(pdev); return -ENOMEM; + }

dev_info(rvu->dev, "SDP PF number:%d\n", sdp_pf_num[i]);

- put_device(&pdev->dev); i++; }