6.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Xin Li (Intel) xin@zytor.com

commit fa7d0f83c5c4223a01598876352473cb3d3bd4d7 upstream.

Initialize DR7 by writing its architectural reset value to always set bit 10, which is reserved to '1', when "clearing" DR7 so as not to trigger unanticipated behavior if said bit is ever unreserved, e.g. as a feature enabling flag with inverted polarity.

Signed-off-by: Xin Li (Intel) xin@zytor.com Signed-off-by: Dave Hansen dave.hansen@linux.intel.com Reviewed-by: H. Peter Anvin (Intel) hpa@zytor.com Reviewed-by: Sohil Mehta sohil.mehta@intel.com Acked-by: Peter Zijlstra (Intel) peterz@infradead.org Acked-by: Sean Christopherson seanjc@google.com Tested-by: Sohil Mehta sohil.mehta@intel.com Cc:stable@vger.kernel.org Link: https://lore.kernel.org/all/20250620231504.2676902-3-xin%40zytor.com [ context adjusted: no KVM_DEBUGREG_AUTO_SWITCH flag test" ] Signed-off-by: Sasha Levin sashal@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- arch/x86/include/asm/debugreg.h | 19 +++++++++++++++---- arch/x86/include/asm/kvm_host.h | 2 +- arch/x86/kernel/cpu/common.c | 2 +- arch/x86/kernel/kgdb.c | 2 +- arch/x86/kernel/process_32.c | 2 +- arch/x86/kernel/process_64.c | 2 +- arch/x86/kvm/x86.c | 4 ++-- 7 files changed, 22 insertions(+), 11 deletions(-)

--- a/arch/x86/include/asm/debugreg.h +++ b/arch/x86/include/asm/debugreg.h @@ -9,6 +9,14 @@ #include <asm/cpufeature.h> #include <asm/msr.h>

+/* + * Define bits that are always set to 1 in DR7, only bit 10 is + * architecturally reserved to '1'. + * + * This is also the init/reset value for DR7. + */ +#define DR7_FIXED_1 0x00000400 + DECLARE_PER_CPU(unsigned long, cpu_dr7);

#ifndef CONFIG_PARAVIRT_XXL @@ -100,8 +108,8 @@ static __always_inline void native_set_d

static inline void hw_breakpoint_disable(void) { - /* Zero the control register for HW Breakpoint */ - set_debugreg(0UL, 7); + /* Reset the control register for HW Breakpoint */ + set_debugreg(DR7_FIXED_1, 7);

/* Zero-out the individual HW breakpoint address registers */ set_debugreg(0UL, 0); @@ -125,9 +133,12 @@ static __always_inline unsigned long loc return 0;

get_debugreg(dr7, 7); - dr7 &= ~0x400; /* architecturally set bit */ + + /* Architecturally set bit */ + dr7 &= ~DR7_FIXED_1; if (dr7) - set_debugreg(0, 7); + set_debugreg(DR7_FIXED_1, 7); + /* * Ensure the compiler doesn't lower the above statements into * the critical section; disabling breakpoints late would not --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -31,6 +31,7 @@

#include <asm/apic.h> #include <asm/pvclock-abi.h> +#include <asm/debugreg.h> #include <asm/desc.h> #include <asm/mtrr.h> #include <asm/msr-index.h> @@ -247,7 +248,6 @@ enum x86_intercept_stage; #define DR7_BP_EN_MASK 0x000000ff #define DR7_GE (1 << 9) #define DR7_GD (1 << 13) -#define DR7_FIXED_1 0x00000400 #define DR7_VOLATILE 0xffff2bff

#define KVM_GUESTDBG_VALID_MASK \ --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -2220,7 +2220,7 @@ EXPORT_PER_CPU_SYMBOL(__stack_chk_guard) static void initialize_debug_regs(void) { /* Control register first -- to make sure everything is disabled. */ - set_debugreg(0, 7); + set_debugreg(DR7_FIXED_1, 7); set_debugreg(DR6_RESERVED, 6); /* dr5 and dr4 don't exist */ set_debugreg(0, 3); --- a/arch/x86/kernel/kgdb.c +++ b/arch/x86/kernel/kgdb.c @@ -385,7 +385,7 @@ static void kgdb_disable_hw_debug(struct struct perf_event *bp;

/* Disable hardware debugging while we are in kgdb: */ - set_debugreg(0UL, 7); + set_debugreg(DR7_FIXED_1, 7); for (i = 0; i < HBP_NUM; i++) { if (!breakinfo[i].enabled) continue; --- a/arch/x86/kernel/process_32.c +++ b/arch/x86/kernel/process_32.c @@ -93,7 +93,7 @@ void __show_regs(struct pt_regs *regs, e

/* Only print out debug registers if they are in their non-default state. */ if ((d0 == 0) && (d1 == 0) && (d2 == 0) && (d3 == 0) && - (d6 == DR6_RESERVED) && (d7 == 0x400)) + (d6 == DR6_RESERVED) && (d7 == DR7_FIXED_1)) return;

printk("%sDR0: %08lx DR1: %08lx DR2: %08lx DR3: %08lx\n", --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -132,7 +132,7 @@ void __show_regs(struct pt_regs *regs, e

/* Only print out debug registers if they are in their non-default state. */ if (!((d0 == 0) && (d1 == 0) && (d2 == 0) && (d3 == 0) && - (d6 == DR6_RESERVED) && (d7 == 0x400))) { + (d6 == DR6_RESERVED) && (d7 == DR7_FIXED_1))) { printk("%sDR0: %016lx DR1: %016lx DR2: %016lx\n", log_lvl, d0, d1, d2); printk("%sDR3: %016lx DR6: %016lx DR7: %016lx\n", --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -10979,7 +10979,7 @@ static int vcpu_enter_guest(struct kvm_v wrmsrl(MSR_IA32_XFD_ERR, vcpu->arch.guest_fpu.xfd_err);

if (unlikely(vcpu->arch.switch_db_regs)) { - set_debugreg(0, 7); + set_debugreg(DR7_FIXED_1, 7); set_debugreg(vcpu->arch.eff_db[0], 0); set_debugreg(vcpu->arch.eff_db[1], 1); set_debugreg(vcpu->arch.eff_db[2], 2); @@ -10988,7 +10988,7 @@ static int vcpu_enter_guest(struct kvm_v if (unlikely(vcpu->arch.switch_db_regs & KVM_DEBUGREG_WONT_EXIT)) kvm_x86_call(set_dr6)(vcpu, vcpu->arch.dr6); } else if (unlikely(hw_breakpoint_active())) { - set_debugreg(0, 7); + set_debugreg(DR7_FIXED_1, 7); }

vcpu->arch.host_debugctl = get_debugctlmsr();

6.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Laurent Vivier lvivier@redhat.com

[ Upstream commit 45ebc7e6c125ce93d2ddf82cd5bea20121bb0258 ]

The virtqueue_resize() function was not correctly propagating error codes from its internal resize helper functions, specifically virtqueue_resize_packet() and virtqueue_resize_split(). If these helpers returned an error, but the subsequent call to virtqueue_enable_after_reset() succeeded, the original error from the resize operation would be masked. Consequently, virtqueue_resize() could incorrectly report success to its caller despite an underlying resize failure.

This change restores the original code behavior:

if (vdev->config->enable_vq_after_reset(_vq)) return -EBUSY;

return err;

Fix: commit ad48d53b5b3f ("virtio_ring: separate the logic of reset/enable from virtqueue_resize") Cc: xuanzhuo@linux.alibaba.com Signed-off-by: Laurent Vivier lvivier@redhat.com Acked-by: Jason Wang jasowang@redhat.com Link: https://patch.msgid.link/20250521092236.661410-2-lvivier@redhat.com Tested-by: Lei Yang leiyang@redhat.com Acked-by: Michael S. Tsirkin mst@redhat.com Signed-off-by: Paolo Abeni pabeni@redhat.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/virtio/virtio_ring.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/drivers/virtio/virtio_ring.c b/drivers/virtio/virtio_ring.c index b784aab668670..4397392bfef00 100644 --- a/drivers/virtio/virtio_ring.c +++ b/drivers/virtio/virtio_ring.c @@ -2797,7 +2797,7 @@ int virtqueue_resize(struct virtqueue *_vq, u32 num, void (*recycle_done)(struct virtqueue *vq)) { struct vring_virtqueue *vq = to_vvq(_vq); - int err; + int err, err_reset;

if (num > vq->vq.num_max) return -E2BIG; @@ -2819,7 +2819,11 @@ int virtqueue_resize(struct virtqueue *_vq, u32 num, else err = virtqueue_resize_split(_vq, num);

- return virtqueue_enable_after_reset(_vq); + err_reset = virtqueue_enable_after_reset(_vq); + if (err_reset) + return err_reset; + + return err; } EXPORT_SYMBOL_GPL(virtqueue_resize);

6.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Alessandro Carminati acarmina@redhat.com

[ Upstream commit ca46946a482238b0cdea459fb82fc837fb36260e ]

Failing to reset coupling_desc.n_coupled after freeing coupled_rdevs can lead to NULL pointer dereference when regulators are accessed post-unbind.

This can happen during runtime PM or other regulator operations that rely on coupling metadata.

For example, on ridesx4, unbinding the 'reg-dummy' platform device triggers a panic in regulator_lock_recursive() due to stale coupling state.

Ensure n_coupled is set to 0 to prevent access to invalid pointers.

Signed-off-by: Alessandro Carminati acarmina@redhat.com Link: https://patch.msgid.link/20250626083809.314842-1-acarmina@redhat.com Signed-off-by: Mark Brown broonie@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/regulator/core.c | 1 + 1 file changed, 1 insertion(+)

diff --git a/drivers/regulator/core.c b/drivers/regulator/core.c index 90629a7566932..4ecad5c6c8390 100644 --- a/drivers/regulator/core.c +++ b/drivers/regulator/core.c @@ -5639,6 +5639,7 @@ static void regulator_remove_coupling(struct regulator_dev *rdev) ERR_PTR(err)); }

+ rdev->coupling_desc.n_coupled = 0; kfree(rdev->coupling_desc.coupled_rdevs); rdev->coupling_desc.coupled_rdevs = NULL; }

6.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Maor Gottlieb maorg@nvidia.com

[ Upstream commit 333e4d79316c9ed5877d7aac8b8ed22efc74e96d ]

The GID cache warning messages can flood the kernel log when there are multiple failed attempts to add GIDs. This can happen when creating many virtual interfaces without having enough space for their GIDs in the GID table.

Change pr_warn to pr_warn_ratelimited to prevent log flooding while still maintaining visibility of the issue.

Link: https://patch.msgid.link/r/fd45ed4a1078e743f498b234c3ae816610ba1b18.17500623... Signed-off-by: Maor Gottlieb maorg@nvidia.com Signed-off-by: Leon Romanovsky leonro@nvidia.com Signed-off-by: Jason Gunthorpe jgg@nvidia.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/infiniband/core/cache.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/infiniband/core/cache.c b/drivers/infiniband/core/cache.c index 9979a351577f1..81cf3c902e819 100644 --- a/drivers/infiniband/core/cache.c +++ b/drivers/infiniband/core/cache.c @@ -582,8 +582,8 @@ static int __ib_cache_gid_add(struct ib_device *ib_dev, u32 port, out_unlock: mutex_unlock(&table->lock); if (ret) - pr_warn("%s: unable to add gid %pI6 error=%d\n", - __func__, gid->raw, ret); + pr_warn_ratelimited("%s: unable to add gid %pI6 error=%d\n", + __func__, gid->raw, ret); return ret; }

6.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Xilin Wu sophon@radxa.com

[ Upstream commit 886a94f008dd1a1702ee66dd035c266f70fd9e90 ]

This allows adding interconnect paths for PCIe 1 in device tree later.

Fixes: 46bdcac533cc ("interconnect: qcom: Add SC7280 interconnect provider driver") Signed-off-by: Xilin Wu sophon@radxa.com Reviewed-by: Dmitry Baryshkov dmitry.baryshkov@oss.qualcomm.com Link: https://lore.kernel.org/r/20250613-sc7280-icc-pcie1-fix-v1-1-0b09813e3b09@ra... Signed-off-by: Georgi Djakov djakov@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/interconnect/qcom/sc7280.c | 1 + 1 file changed, 1 insertion(+)

diff --git a/drivers/interconnect/qcom/sc7280.c b/drivers/interconnect/qcom/sc7280.c index 346f18d70e9e5..905403a3a930a 100644 --- a/drivers/interconnect/qcom/sc7280.c +++ b/drivers/interconnect/qcom/sc7280.c @@ -238,6 +238,7 @@ static struct qcom_icc_node xm_pcie3_1 = { .id = SC7280_MASTER_PCIE_1, .channels = 1, .buswidth = 8, + .num_links = 1, .links = { SC7280_SLAVE_ANOC_PCIE_GEM_NOC }, };

6.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: David Lechner dlechner@baylibre.com

[ Upstream commit 7b86482632788acd48d7b9ee1867f5ad3a32ccbb ]

Use spi_is_bpw_supported() instead of directly accessing spi->controller ->bits_per_word_mask. bits_per_word_mask may be 0, which implies that 8-bits-per-word is supported. spi_is_bpw_supported() takes this into account while spi_ctrl_mask == SPI_BPW_MASK(8) does not.

Fixes: 0b2a740b424e ("iio: adc: ad7949: enable use with non 14/16-bit controllers") Closes: https://lore.kernel.org/linux-spi/c8b8a963-6cef-4c9b-bfef-dab2b7bd0b0f@siren... Signed-off-by: David Lechner dlechner@baylibre.com Reviewed-by: Andy Shevchenko andy@kernel.org Link: https://patch.msgid.link/20250611-iio-adc-ad7949-use-spi_is_bpw_supported-v1... Signed-off-by: Jonathan Cameron Jonathan.Cameron@huawei.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/iio/adc/ad7949.c | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-)

diff --git a/drivers/iio/adc/ad7949.c b/drivers/iio/adc/ad7949.c index edd0c3a35ab73..202561cad4012 100644 --- a/drivers/iio/adc/ad7949.c +++ b/drivers/iio/adc/ad7949.c @@ -308,7 +308,6 @@ static void ad7949_disable_reg(void *reg)

static int ad7949_spi_probe(struct spi_device *spi) { - u32 spi_ctrl_mask = spi->controller->bits_per_word_mask; struct device *dev = &spi->dev; const struct ad7949_adc_spec *spec; struct ad7949_adc_chip *ad7949_adc; @@ -337,11 +336,11 @@ static int ad7949_spi_probe(struct spi_device *spi) ad7949_adc->resolution = spec->resolution;

/* Set SPI bits per word */ - if (spi_ctrl_mask & SPI_BPW_MASK(ad7949_adc->resolution)) { + if (spi_is_bpw_supported(spi, ad7949_adc->resolution)) { spi->bits_per_word = ad7949_adc->resolution; - } else if (spi_ctrl_mask == SPI_BPW_MASK(16)) { + } else if (spi_is_bpw_supported(spi, 16)) { spi->bits_per_word = 16; - } else if (spi_ctrl_mask == SPI_BPW_MASK(8)) { + } else if (spi_is_bpw_supported(spi, 8)) { spi->bits_per_word = 8; } else { dev_err(dev, "unable to find common BPW with spi controller\n");

6.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Shravan Kumar Ramani shravankr@nvidia.com

[ Upstream commit 44e6ca8faeeed12206f3e7189c5ac618b810bb9c ]

Since the input string passed via the command line appends a newline char, it needs to be removed before comparison with the event_list.

Fixes: 1a218d312e65 ("platform/mellanox: mlxbf-pmc: Add Mellanox BlueField PMC driver") Signed-off-by: Shravan Kumar Ramani shravankr@nvidia.com Reviewed-by: David Thompson davthompson@nvidia.com Link: https://lore.kernel.org/r/4978c18e33313b48fa2ae7f3aa6dbcfce40877e4.175138018... Reviewed-by: Ilpo Järvinen ilpo.jarvinen@linux.intel.com Signed-off-by: Ilpo Järvinen ilpo.jarvinen@linux.intel.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/platform/mellanox/mlxbf-pmc.c | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-)

diff --git a/drivers/platform/mellanox/mlxbf-pmc.c b/drivers/platform/mellanox/mlxbf-pmc.c index 771a24c397c12..b8fe51e6d4d3f 100644 --- a/drivers/platform/mellanox/mlxbf-pmc.c +++ b/drivers/platform/mellanox/mlxbf-pmc.c @@ -15,6 +15,7 @@ #include <linux/hwmon.h> #include <linux/platform_device.h> #include <linux/string.h> +#include <linux/string_helpers.h> #include <uapi/linux/psci.h>

#define MLXBF_PMC_WRITE_REG_32 0x82000009 @@ -1666,6 +1667,7 @@ static ssize_t mlxbf_pmc_event_store(struct device *dev, attr, struct mlxbf_pmc_attribute, dev_attr); unsigned int blk_num, cnt_num; bool is_l3 = false; + char *evt_name; int evt_num; int err;

@@ -1673,8 +1675,14 @@ static ssize_t mlxbf_pmc_event_store(struct device *dev, cnt_num = attr_event->index;

if (isalpha(buf[0])) { + /* Remove the trailing newline character if present */ + evt_name = kstrdup_and_replace(buf, '\n', '\0', GFP_KERNEL); + if (!evt_name) + return -ENOMEM; + evt_num = mlxbf_pmc_get_event_num(pmc->block_name[blk_num], - buf); + evt_name); + kfree(evt_name); if (evt_num < 0) return -EINVAL; } else {

6.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Shravan Kumar Ramani shravankr@nvidia.com

[ Upstream commit 0e2cebd72321caeef84b6ba7084e85be0287fb4b ]

For setting the enable value, the input should be 0 or 1 only. Use kstrtobool() in place of kstrtoint() in mlxbf_pmc_enable_store() to accept only valid input.

Fixes: 423c3361855c ("platform/mellanox: mlxbf-pmc: Add support for BlueField-3") Signed-off-by: Shravan Kumar Ramani shravankr@nvidia.com Reviewed-by: David Thompson davthompson@nvidia.com Link: https://lore.kernel.org/r/2ee618c59976bcf1379d5ddce2fc60ab5014b3a9.175138018... [ij: split kstrbool() change to own commit.] Reviewed-by: Ilpo Järvinen ilpo.jarvinen@linux.intel.com Signed-off-by: Ilpo Järvinen ilpo.jarvinen@linux.intel.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/platform/mellanox/mlxbf-pmc.c | 10 ++++------ 1 file changed, 4 insertions(+), 6 deletions(-)

diff --git a/drivers/platform/mellanox/mlxbf-pmc.c b/drivers/platform/mellanox/mlxbf-pmc.c index 76966b3dc4ff6..1135d2cf335c8 100644 --- a/drivers/platform/mellanox/mlxbf-pmc.c +++ b/drivers/platform/mellanox/mlxbf-pmc.c @@ -1772,13 +1772,14 @@ static ssize_t mlxbf_pmc_enable_store(struct device *dev, { struct mlxbf_pmc_attribute *attr_enable = container_of( attr, struct mlxbf_pmc_attribute, dev_attr); - unsigned int en, blk_num; + unsigned int blk_num; u32 word; int err; + bool en;

blk_num = attr_enable->nr;

- err = kstrtouint(buf, 0, &en); + err = kstrtobool(buf, &en); if (err < 0) return err;

@@ -1798,14 +1799,11 @@ static ssize_t mlxbf_pmc_enable_store(struct device *dev, MLXBF_PMC_CRSPACE_PERFMON_CTL(pmc->block[blk_num].counters), MLXBF_PMC_WRITE_REG_32, word); } else { - if (en && en != 1) - return -EINVAL; - err = mlxbf_pmc_config_l3_counters(blk_num, false, !!en); if (err) return err;

- if (en == 1) { + if (en) { err = mlxbf_pmc_config_l3_counters(blk_num, true, false); if (err) return err;

6.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Nuno Das Neves nunodasneves@linux.microsoft.com

[ Upstream commit bb169f80ed5a156ec3405e0e49c6b8e9ae264718 ]

Accessing cpu_online_mask here is problematic because the cpus read lock is not held in this context.

However, cpu_online_mask isn't needed here since the effective affinity mask is guaranteed to be valid in this callback. So, just use cpumask_first() to get the cpu instead of ANDing it with cpus_online_mask unnecessarily.

Fixes: e39397d1fd68 ("x86/hyperv: implement an MSI domain for root partition") Reported-by: Michael Kelley mhklinux@outlook.com Closes: https://lore.kernel.org/linux-hyperv/SN6PR02MB4157639630F8AD2D8FD8F52FD475A@... Suggested-by: Thomas Gleixner tglx@linutronix.de Signed-off-by: Nuno Das Neves nunodasneves@linux.microsoft.com Reviewed-by: Michael Kelley mhklinux@outlook.com Link: https://lore.kernel.org/r/1751582677-30930-4-git-send-email-nunodasneves@lin... Signed-off-by: Wei Liu wei.liu@kernel.org Message-ID: 1751582677-30930-4-git-send-email-nunodasneves@linux.microsoft.com Signed-off-by: Sasha Levin sashal@kernel.org --- arch/x86/hyperv/irqdomain.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/arch/x86/hyperv/irqdomain.c b/arch/x86/hyperv/irqdomain.c index 31f0d29cbc5e3..e28c317ac9e81 100644 --- a/arch/x86/hyperv/irqdomain.c +++ b/arch/x86/hyperv/irqdomain.c @@ -192,7 +192,6 @@ static void hv_irq_compose_msi_msg(struct irq_data *data, struct msi_msg *msg) struct pci_dev *dev; struct hv_interrupt_entry out_entry, *stored_entry; struct irq_cfg *cfg = irqd_cfg(data); - const cpumask_t *affinity; int cpu; u64 status;

@@ -204,8 +203,7 @@ static void hv_irq_compose_msi_msg(struct irq_data *data, struct msi_msg *msg) return; }

- affinity = irq_data_get_effective_affinity_mask(data); - cpu = cpumask_first_and(affinity, cpu_online_mask); + cpu = cpumask_first(irq_data_get_effective_affinity_mask(data));

if (data->chip_data) { /*

6.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Stefan Wahren wahrenst@gmx.net

[ Upstream commit f2b8ebfb867011ddbefbdf7b04ad62626cbc2afd ]

Most of the users of vchiq_shutdown ignore the return value, which is bad because this could lead to resource leaks. So instead of changing all calls to vchiq_shutdown, it's easier to make vchiq_shutdown never fail.

Fixes: 71bad7f08641 ("staging: add bcm2708 vchiq driver") Signed-off-by: Stefan Wahren wahrenst@gmx.net Link: https://lore.kernel.org/r/20250715161108.3411-4-wahrenst@gmx.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/staging/vc04_services/interface/vchiq_arm/vchiq_arm.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_arm.c b/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_arm.c index 6434cbdc1a6ef..721b15b7e13b9 100644 --- a/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_arm.c +++ b/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_arm.c @@ -393,8 +393,7 @@ int vchiq_shutdown(struct vchiq_instance *instance) struct vchiq_state *state = instance->state; int ret = 0;

- if (mutex_lock_killable(&state->mutex)) - return -EAGAIN; + mutex_lock(&state->mutex);

/* Remove all services */ vchiq_shutdown_internal(state, instance);

6.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Sabrina Dubroca sd@queasysnail.net

[ Upstream commit 7eb11c0ab70777b9e5145a5ba1c0a2312c3980b2 ]

If we get preempted during xfrm_state_find, we could run xfrm_state_look_at using a different pcpu_id than the one xfrm_state_find saw. This could lead to ignoring states that should have matched, and triggering acquires on a CPU that already has a pcpu state.

xfrm_state_find starts on CPU1 pcpu_id = 1 lookup starts <preemption, we're now on CPU2> xfrm_state_look_at pcpu_id = 2 finds a state found: best->pcpu_num != pcpu_id (2 != 1) if (!x && !error && !acquire_in_progress) { ... xfrm_state_alloc xfrm_init_tempstate ...

This can be avoided by passing the original pcpu_id down to all xfrm_state_look_at() calls.

Also switch to raw_smp_processor_id, disabling preempting just to re-enable it immediately doesn't really make sense.

Fixes: 1ddf9916ac09 ("xfrm: Add support for per cpu xfrm state handling.") Signed-off-by: Sabrina Dubroca sd@queasysnail.net Reviewed-by: Florian Westphal fw@strlen.de Signed-off-by: Steffen Klassert steffen.klassert@secunet.com Signed-off-by: Sasha Levin sashal@kernel.org --- net/xfrm/xfrm_state.c | 19 ++++++------------- 1 file changed, 6 insertions(+), 13 deletions(-)

diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c index a5a3bf25fd1d4..cef8d3c20f652 100644 --- a/net/xfrm/xfrm_state.c +++ b/net/xfrm/xfrm_state.c @@ -1307,14 +1307,8 @@ static void xfrm_hash_grow_check(struct net *net, int have_hash_collision) static void xfrm_state_look_at(struct xfrm_policy *pol, struct xfrm_state *x, const struct flowi *fl, unsigned short family, struct xfrm_state **best, int *acq_in_progress, - int *error) + int *error, unsigned int pcpu_id) { - /* We need the cpu id just as a lookup key, - * we don't require it to be stable. - */ - unsigned int pcpu_id = get_cpu(); - put_cpu(); - /* Resolution logic: * 1. There is a valid state with matching selector. Done. * 2. Valid state with inappropriate selector. Skip. @@ -1381,8 +1375,7 @@ xfrm_state_find(const xfrm_address_t *daddr, const xfrm_address_t *saddr, /* We need the cpu id just as a lookup key, * we don't require it to be stable. */ - pcpu_id = get_cpu(); - put_cpu(); + pcpu_id = raw_smp_processor_id();

to_put = NULL;

@@ -1402,7 +1395,7 @@ xfrm_state_find(const xfrm_address_t *daddr, const xfrm_address_t *saddr, tmpl->id.proto == x->id.proto && (tmpl->id.spi == x->id.spi || !tmpl->id.spi)) xfrm_state_look_at(pol, x, fl, encap_family, - &best, &acquire_in_progress, &error); + &best, &acquire_in_progress, &error, pcpu_id); }

if (best) @@ -1419,7 +1412,7 @@ xfrm_state_find(const xfrm_address_t *daddr, const xfrm_address_t *saddr, tmpl->id.proto == x->id.proto && (tmpl->id.spi == x->id.spi || !tmpl->id.spi)) xfrm_state_look_at(pol, x, fl, family, - &best, &acquire_in_progress, &error); + &best, &acquire_in_progress, &error, pcpu_id); }

cached: @@ -1460,7 +1453,7 @@ xfrm_state_find(const xfrm_address_t *daddr, const xfrm_address_t *saddr, tmpl->id.proto == x->id.proto && (tmpl->id.spi == x->id.spi || !tmpl->id.spi)) xfrm_state_look_at(pol, x, fl, family, - &best, &acquire_in_progress, &error); + &best, &acquire_in_progress, &error, pcpu_id); } if (best || acquire_in_progress) goto found; @@ -1495,7 +1488,7 @@ xfrm_state_find(const xfrm_address_t *daddr, const xfrm_address_t *saddr, tmpl->id.proto == x->id.proto && (tmpl->id.spi == x->id.spi || !tmpl->id.spi)) xfrm_state_look_at(pol, x, fl, family, - &best, &acquire_in_progress, &error); + &best, &acquire_in_progress, &error, pcpu_id); }

found:

6.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Tobias Brunner tobias@strongswan.org

[ Upstream commit 3ac9e29211fa2df5539ba0d742c8fe9fe95fdc79 ]

The referenced commit replaced a call to __xfrm4|6_udp_encap_rcv() with a custom check for non-ESP markers. But what the called function also did was setting the transport header to the ESP header. The function that follows, esp4|6_gro_receive(), relies on that being set when it calls xfrm_parse_spi(). We have to set the full offset as the skb's head was not moved yet so adding just the UDP header length won't work.

Fixes: e3fd05777685 ("xfrm: Fix UDP GRO handling for some corner cases") Signed-off-by: Tobias Brunner tobias@strongswan.org Signed-off-by: Steffen Klassert steffen.klassert@secunet.com Signed-off-by: Sasha Levin sashal@kernel.org --- net/ipv4/xfrm4_input.c | 3 +++ net/ipv6/xfrm6_input.c | 3 +++ 2 files changed, 6 insertions(+)

diff --git a/net/ipv4/xfrm4_input.c b/net/ipv4/xfrm4_input.c index 0d31a8c108d4f..f28cfd88eaf59 100644 --- a/net/ipv4/xfrm4_input.c +++ b/net/ipv4/xfrm4_input.c @@ -202,6 +202,9 @@ struct sk_buff *xfrm4_gro_udp_encap_rcv(struct sock *sk, struct list_head *head, if (len <= sizeof(struct ip_esp_hdr) || udpdata32[0] == 0) goto out;

+ /* set the transport header to ESP */ + skb_set_transport_header(skb, offset); + NAPI_GRO_CB(skb)->proto = IPPROTO_UDP;

pp = call_gro_receive(ops->callbacks.gro_receive, head, skb); diff --git a/net/ipv6/xfrm6_input.c b/net/ipv6/xfrm6_input.c index 841c81abaaf4f..9005fc156a20e 100644 --- a/net/ipv6/xfrm6_input.c +++ b/net/ipv6/xfrm6_input.c @@ -202,6 +202,9 @@ struct sk_buff *xfrm6_gro_udp_encap_rcv(struct sock *sk, struct list_head *head, if (len <= sizeof(struct ip_esp_hdr) || udpdata32[0] == 0) goto out;

+ /* set the transport header to ESP */ + skb_set_transport_header(skb, offset); + NAPI_GRO_CB(skb)->proto = IPPROTO_UDP;

pp = call_gro_receive(ops->callbacks.gro_receive, head, skb);

6.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Eyal Birger eyal.birger@gmail.com

[ Upstream commit a90b2a1aaacbcf0f91d7e4868ad6c51c5dee814b ]

collect_md property on xfrm interfaces can only be set on device creation, thus xfrmi_changelink() should fail when called on such interfaces.

The check to enforce this was done only in the case where the xi was returned from xfrmi_locate() which doesn't look for the collect_md interface, and thus the validation was never reached.

Calling changelink would thus errornously place the special interface xi in the xfrmi_net->xfrmi hash, but since it also exists in the xfrmi_net->collect_md_xfrmi pointer it would lead to a double free when the net namespace was taken down [1].

Change the check to use the xi from netdev_priv which is available earlier in the function to prevent changes in xfrm collect_md interfaces.

[1] resulting oops: [ 8.516540] kernel BUG at net/core/dev.c:12029! [ 8.516552] Oops: invalid opcode: 0000 [#1] SMP NOPTI [ 8.516559] CPU: 0 UID: 0 PID: 12 Comm: kworker/u80:0 Not tainted 6.15.0-virtme #5 PREEMPT(voluntary) [ 8.516565] Hardware name: QEMU Ubuntu 24.04 PC (i440FX + PIIX, 1996), BIOS 1.16.3-debian-1.16.3-2 04/01/2014 [ 8.516569] Workqueue: netns cleanup_net [ 8.516579] RIP: 0010:unregister_netdevice_many_notify+0x101/0xab0 [ 8.516590] Code: 90 0f 0b 90 48 8b b0 78 01 00 00 48 8b 90 80 01 00 00 48 89 56 08 48 89 32 4c 89 80 78 01 00 00 48 89 b8 80 01 00 00 eb ac 90 <0f> 0b 48 8b 45 00 4c 8d a0 88 fe ff ff 48 39 c5 74 5c 41 80 bc 24 [ 8.516593] RSP: 0018:ffffa93b8006bd30 EFLAGS: 00010206 [ 8.516598] RAX: ffff98fe4226e000 RBX: ffffa93b8006bd58 RCX: ffffa93b8006bc60 [ 8.516601] RDX: 0000000000000004 RSI: 0000000000000000 RDI: dead000000000122 [ 8.516603] RBP: ffffa93b8006bdd8 R08: dead000000000100 R09: ffff98fe4133c100 [ 8.516605] R10: 0000000000000000 R11: 00000000000003d2 R12: ffffa93b8006be00 [ 8.516608] R13: ffffffff96c1a510 R14: ffffffff96c1a510 R15: ffffa93b8006be00 [ 8.516615] FS: 0000000000000000(0000) GS:ffff98fee73b7000(0000) knlGS:0000000000000000 [ 8.516619] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 8.516622] CR2: 00007fcd2abd0700 CR3: 000000003aa40000 CR4: 0000000000752ef0 [ 8.516625] PKRU: 55555554 [ 8.516627] Call Trace: [ 8.516632] <TASK> [ 8.516635] ? rtnl_is_locked+0x15/0x20 [ 8.516641] ? unregister_netdevice_queue+0x29/0xf0 [ 8.516650] ops_undo_list+0x1f2/0x220 [ 8.516659] cleanup_net+0x1ad/0x2e0 [ 8.516664] process_one_work+0x160/0x380 [ 8.516673] worker_thread+0x2aa/0x3c0 [ 8.516679] ? __pfx_worker_thread+0x10/0x10 [ 8.516686] kthread+0xfb/0x200 [ 8.516690] ? __pfx_kthread+0x10/0x10 [ 8.516693] ? __pfx_kthread+0x10/0x10 [ 8.516697] ret_from_fork+0x82/0xf0 [ 8.516705] ? __pfx_kthread+0x10/0x10 [ 8.516709] ret_from_fork_asm+0x1a/0x30 [ 8.516718] </TASK>

Fixes: abc340b38ba2 ("xfrm: interface: support collect metadata mode") Reported-by: Lonial Con kongln9170@gmail.com Signed-off-by: Eyal Birger eyal.birger@gmail.com Signed-off-by: Steffen Klassert steffen.klassert@secunet.com Signed-off-by: Sasha Levin sashal@kernel.org --- net/xfrm/xfrm_interface_core.c | 7 +------ 1 file changed, 1 insertion(+), 6 deletions(-)

diff --git a/net/xfrm/xfrm_interface_core.c b/net/xfrm/xfrm_interface_core.c index 622445f041d32..fed96bedd54e3 100644 --- a/net/xfrm/xfrm_interface_core.c +++ b/net/xfrm/xfrm_interface_core.c @@ -875,7 +875,7 @@ static int xfrmi_changelink(struct net_device *dev, struct nlattr *tb[], return -EINVAL; }

- if (p.collect_md) { + if (p.collect_md || xi->p.collect_md) { NL_SET_ERR_MSG(extack, "collect_md can't be changed"); return -EINVAL; } @@ -886,11 +886,6 @@ static int xfrmi_changelink(struct net_device *dev, struct nlattr *tb[], } else { if (xi->dev != dev) return -EEXIST; - if (xi->p.collect_md) { - NL_SET_ERR_MSG(extack, - "device can't be changed to collect_md"); - return -EINVAL; - } }

return xfrmi_update(xi, &p);

6.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Himanshu Mittal h-mittal1@ti.com

[ Upstream commit 6e86fb73de0fe3ec5cdcd5873ad1d6005f295b64 ]

Fixes overlapping buffer allocation for ICSSG peripheral used for storing packets to be received/transmitted. There are 3 buffers: 1. Buffer for Locally Injected Packets 2. Buffer for Forwarding Packets 3. Buffer for Host Egress Packets

In existing allocation buffers for 2. and 3. are overlapping causing packet corruption.

Packet corruption observations: During tcp iperf testing, due to overlapping buffers the received ack packet overwrites the packet to be transmitted. So, we see packets on wire with the ack packet content inside the content of next TCP packet from sender device.

Details for AM64x switch mode: -> Allocation by existing driver: +---------+-------------------------------------------------------------+ | | SLICE 0 | SLICE 1 | | +------+--------------+--------+------+--------------+--------+ | | Slot | Base Address | Size | Slot | Base Address | Size | |---------+------+--------------+--------+------+--------------+--------+ | | 0 | 70000000 | 0x2000 | 0 | 70010000 | 0x2000 | | | 1 | 70002000 | 0x2000 | 1 | 70012000 | 0x2000 | | | 2 | 70004000 | 0x2000 | 2 | 70014000 | 0x2000 | | FWD | 3 | 70006000 | 0x2000 | 3 | 70016000 | 0x2000 | | Buffers | 4 | 70008000 | 0x2000 | 4 | 70018000 | 0x2000 | | | 5 | 7000A000 | 0x2000 | 5 | 7001A000 | 0x2000 | | | 6 | 7000C000 | 0x2000 | 6 | 7001C000 | 0x2000 | | | 7 | 7000E000 | 0x2000 | 7 | 7001E000 | 0x2000 | +---------+------+--------------+--------+------+--------------+--------+ | | 8 | 70020000 | 0x1000 | 8 | 70028000 | 0x1000 | | | 9 | 70021000 | 0x1000 | 9 | 70029000 | 0x1000 | | | 10 | 70022000 | 0x1000 | 10 | 7002A000 | 0x1000 | | Our | 11 | 70023000 | 0x1000 | 11 | 7002B000 | 0x1000 | | LI | 12 | 00000000 | 0x0 | 12 | 00000000 | 0x0 | | Buffers | 13 | 00000000 | 0x0 | 13 | 00000000 | 0x0 | | | 14 | 00000000 | 0x0 | 14 | 00000000 | 0x0 | | | 15 | 00000000 | 0x0 | 15 | 00000000 | 0x0 | +---------+------+--------------+--------+------+--------------+--------+ | | 16 | 70024000 | 0x1000 | 16 | 7002C000 | 0x1000 | | | 17 | 70025000 | 0x1000 | 17 | 7002D000 | 0x1000 | | | 18 | 70026000 | 0x1000 | 18 | 7002E000 | 0x1000 | | Their | 19 | 70027000 | 0x1000 | 19 | 7002F000 | 0x1000 | | LI | 20 | 00000000 | 0x0 | 20 | 00000000 | 0x0 | | Buffers | 21 | 00000000 | 0x0 | 21 | 00000000 | 0x0 | | | 22 | 00000000 | 0x0 | 22 | 00000000 | 0x0 | | | 23 | 00000000 | 0x0 | 23 | 00000000 | 0x0 | +---------+------+--------------+--------+------+--------------+--------+ --> here 16, 17, 18, 19 overlapping with below express buffer

+-----+-----------------------------------------------+ | | SLICE 0 | SLICE 1 | | +------------+----------+------------+----------+ | | Start addr | End addr | Start addr | End addr | +-----+------------+----------+------------+----------+ | EXP | 70024000 | 70028000 | 7002C000 | 70030000 | <-- Overlapping | PRE | 70030000 | 70033800 | 70034000 | 70037800 | +-----+------------+----------+------------+----------+

+---------------------+----------+----------+ | | SLICE 0 | SLICE 1 | +---------------------+----------+----------+ | Default Drop Offset | 00000000 | 00000000 | <-- Field not configured +---------------------+----------+----------+

-> Allocation this patch brings: +---------+-------------------------------------------------------------+ | | SLICE 0 | SLICE 1 | | +------+--------------+--------+------+--------------+--------+ | | Slot | Base Address | Size | Slot | Base Address | Size | |---------+------+--------------+--------+------+--------------+--------+ | | 0 | 70000000 | 0x2000 | 0 | 70040000 | 0x2000 | | | 1 | 70002000 | 0x2000 | 1 | 70042000 | 0x2000 | | | 2 | 70004000 | 0x2000 | 2 | 70044000 | 0x2000 | | FWD | 3 | 70006000 | 0x2000 | 3 | 70046000 | 0x2000 | | Buffers | 4 | 70008000 | 0x2000 | 4 | 70048000 | 0x2000 | | | 5 | 7000A000 | 0x2000 | 5 | 7004A000 | 0x2000 | | | 6 | 7000C000 | 0x2000 | 6 | 7004C000 | 0x2000 | | | 7 | 7000E000 | 0x2000 | 7 | 7004E000 | 0x2000 | +---------+------+--------------+--------+------+--------------+--------+ | | 8 | 70010000 | 0x1000 | 8 | 70050000 | 0x1000 | | | 9 | 70011000 | 0x1000 | 9 | 70051000 | 0x1000 | | | 10 | 70012000 | 0x1000 | 10 | 70052000 | 0x1000 | | Our | 11 | 70013000 | 0x1000 | 11 | 70053000 | 0x1000 | | LI | 12 | 00000000 | 0x0 | 12 | 00000000 | 0x0 | | Buffers | 13 | 00000000 | 0x0 | 13 | 00000000 | 0x0 | | | 14 | 00000000 | 0x0 | 14 | 00000000 | 0x0 | | | 15 | 00000000 | 0x0 | 15 | 00000000 | 0x0 | +---------+------+--------------+--------+------+--------------+--------+ | | 16 | 70014000 | 0x1000 | 16 | 70054000 | 0x1000 | | | 17 | 70015000 | 0x1000 | 17 | 70055000 | 0x1000 | | | 18 | 70016000 | 0x1000 | 18 | 70056000 | 0x1000 | | Their | 19 | 70017000 | 0x1000 | 19 | 70057000 | 0x1000 | | LI | 20 | 00000000 | 0x0 | 20 | 00000000 | 0x0 | | Buffers | 21 | 00000000 | 0x0 | 21 | 00000000 | 0x0 | | | 22 | 00000000 | 0x0 | 22 | 00000000 | 0x0 | | | 23 | 00000000 | 0x0 | 23 | 00000000 | 0x0 | +---------+------+--------------+--------+------+--------------+--------+

+-----+-----------------------------------------------+ | | SLICE 0 | SLICE 1 | | +------------+----------+------------+----------+ | | Start addr | End addr | Start addr | End addr | +-----+------------+----------+------------+----------+ | EXP | 70018000 | 7001C000 | 70058000 | 7005C000 | | PRE | 7001C000 | 7001F800 | 7005C000 | 7005F800 | +-----+------------+----------+------------+----------+

+---------------------+----------+----------+ | | SLICE 0 | SLICE 1 | +---------------------+----------+----------+ | Default Drop Offset | 7001F800 | 7005F800 | +---------------------+----------+----------+

Rootcause: missing buffer configuration for Express frames in function: prueth_fw_offload_buffer_setup()

Details: Driver implements two distinct buffer configuration functions that are invoked based on the driver state and ICSSG firmware:- - prueth_fw_offload_buffer_setup() - prueth_emac_buffer_setup()

During initialization, driver creates standard network interfaces (netdevs) and configures buffers via prueth_emac_buffer_setup(). This function properly allocates and configures all required memory regions including: - LI buffers - Express packet buffers - Preemptible packet buffers

However, when the driver transitions to an offload mode (switch/HSR/PRP), buffer reconfiguration is handled by prueth_fw_offload_buffer_setup(). This function does not reconfigure the buffer regions required for Express packets, leading to incorrect buffer allocation.

Fixes: abd5576b9c57 ("net: ti: icssg-prueth: Add support for ICSSG switch firmware") Signed-off-by: Himanshu Mittal h-mittal1@ti.com Reviewed-by: Simon Horman horms@kernel.org Link: https://patch.msgid.link/20250717094220.546388-1-h-mittal1@ti.com Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/ti/icssg/icssg_config.c | 158 ++++++++++++------ drivers/net/ethernet/ti/icssg/icssg_config.h | 80 +++++++-- drivers/net/ethernet/ti/icssg/icssg_prueth.c | 20 ++- drivers/net/ethernet/ti/icssg/icssg_prueth.h | 2 + .../net/ethernet/ti/icssg/icssg_switch_map.h | 3 + 5 files changed, 190 insertions(+), 73 deletions(-)

diff --git a/drivers/net/ethernet/ti/icssg/icssg_config.c b/drivers/net/ethernet/ti/icssg/icssg_config.c index ddfd1c02a8854..da53eb04b0a43 100644 --- a/drivers/net/ethernet/ti/icssg/icssg_config.c +++ b/drivers/net/ethernet/ti/icssg/icssg_config.c @@ -288,8 +288,12 @@ static int prueth_fw_offload_buffer_setup(struct prueth_emac *emac) int i;

addr = lower_32_bits(prueth->msmcram.pa); - if (slice) - addr += PRUETH_NUM_BUF_POOLS * PRUETH_EMAC_BUF_POOL_SIZE; + if (slice) { + if (prueth->pdata.banked_ms_ram) + addr += MSMC_RAM_BANK_SIZE; + else + addr += PRUETH_SW_TOTAL_BUF_SIZE_PER_SLICE; + }

if (addr % SZ_64K) { dev_warn(prueth->dev, "buffer pool needs to be 64KB aligned\n"); @@ -297,43 +301,66 @@ static int prueth_fw_offload_buffer_setup(struct prueth_emac *emac) }

bpool_cfg = emac->dram.va + BUFFER_POOL_0_ADDR_OFFSET; - /* workaround for f/w bug. bpool 0 needs to be initialized */ - for (i = 0; i < PRUETH_NUM_BUF_POOLS; i++) { + + /* Configure buffer pools for forwarding buffers + * - used by firmware to store packets to be forwarded to other port + * - 8 total pools per slice + */ + for (i = 0; i < PRUETH_NUM_FWD_BUF_POOLS_PER_SLICE; i++) { writel(addr, &bpool_cfg[i].addr); - writel(PRUETH_EMAC_BUF_POOL_SIZE, &bpool_cfg[i].len); - addr += PRUETH_EMAC_BUF_POOL_SIZE; + writel(PRUETH_SW_FWD_BUF_POOL_SIZE, &bpool_cfg[i].len); + addr += PRUETH_SW_FWD_BUF_POOL_SIZE; }

- if (!slice) - addr += PRUETH_NUM_BUF_POOLS * PRUETH_EMAC_BUF_POOL_SIZE; - else - addr += PRUETH_SW_NUM_BUF_POOLS_HOST * PRUETH_SW_BUF_POOL_SIZE_HOST; - - for (i = PRUETH_NUM_BUF_POOLS; - i < 2 * PRUETH_SW_NUM_BUF_POOLS_HOST + PRUETH_NUM_BUF_POOLS; - i++) { - /* The driver only uses first 4 queues per PRU so only initialize them */ - if (i % PRUETH_SW_NUM_BUF_POOLS_HOST < PRUETH_SW_NUM_BUF_POOLS_PER_PRU) { - writel(addr, &bpool_cfg[i].addr); - writel(PRUETH_SW_BUF_POOL_SIZE_HOST, &bpool_cfg[i].len); - addr += PRUETH_SW_BUF_POOL_SIZE_HOST; + /* Configure buffer pools for Local Injection buffers + * - used by firmware to store packets received from host core + * - 16 total pools per slice + */ + for (i = 0; i < PRUETH_NUM_LI_BUF_POOLS_PER_SLICE; i++) { + int cfg_idx = i + PRUETH_NUM_FWD_BUF_POOLS_PER_SLICE; + + /* The driver only uses first 4 queues per PRU, + * so only initialize buffer for them + */ + if ((i % PRUETH_NUM_LI_BUF_POOLS_PER_PORT_PER_SLICE) + < PRUETH_SW_USED_LI_BUF_POOLS_PER_PORT_PER_SLICE) { + writel(addr, &bpool_cfg[cfg_idx].addr); + writel(PRUETH_SW_LI_BUF_POOL_SIZE, + &bpool_cfg[cfg_idx].len); + addr += PRUETH_SW_LI_BUF_POOL_SIZE; } else { - writel(0, &bpool_cfg[i].addr); - writel(0, &bpool_cfg[i].len); + writel(0, &bpool_cfg[cfg_idx].addr); + writel(0, &bpool_cfg[cfg_idx].len); } }

- if (!slice) - addr += PRUETH_SW_NUM_BUF_POOLS_HOST * PRUETH_SW_BUF_POOL_SIZE_HOST; - else - addr += PRUETH_EMAC_RX_CTX_BUF_SIZE; + /* Express RX buffer queue + * - used by firmware to store express packets to be transmitted + * to the host core + */ + rxq_ctx = emac->dram.va + HOST_RX_Q_EXP_CONTEXT_OFFSET; + for (i = 0; i < 3; i++) + writel(addr, &rxq_ctx->start[i]); + + addr += PRUETH_SW_HOST_EXP_BUF_POOL_SIZE; + writel(addr, &rxq_ctx->end);

+ /* Pre-emptible RX buffer queue + * - used by firmware to store preemptible packets to be transmitted + * to the host core + */ rxq_ctx = emac->dram.va + HOST_RX_Q_PRE_CONTEXT_OFFSET; for (i = 0; i < 3; i++) writel(addr, &rxq_ctx->start[i]);

- addr += PRUETH_EMAC_RX_CTX_BUF_SIZE; - writel(addr - SZ_2K, &rxq_ctx->end); + addr += PRUETH_SW_HOST_PRE_BUF_POOL_SIZE; + writel(addr, &rxq_ctx->end); + + /* Set pointer for default dropped packet write + * - used by firmware to temporarily store packet to be dropped + */ + rxq_ctx = emac->dram.va + DEFAULT_MSMC_Q_OFFSET; + writel(addr, &rxq_ctx->start[0]);

return 0; } @@ -347,13 +374,13 @@ static int prueth_emac_buffer_setup(struct prueth_emac *emac) u32 addr; int i;

- /* Layout to have 64KB aligned buffer pool - * |BPOOL0|BPOOL1|RX_CTX0|RX_CTX1| - */ - addr = lower_32_bits(prueth->msmcram.pa); - if (slice) - addr += PRUETH_NUM_BUF_POOLS * PRUETH_EMAC_BUF_POOL_SIZE; + if (slice) { + if (prueth->pdata.banked_ms_ram) + addr += MSMC_RAM_BANK_SIZE; + else + addr += PRUETH_EMAC_TOTAL_BUF_SIZE_PER_SLICE; + }

if (addr % SZ_64K) { dev_warn(prueth->dev, "buffer pool needs to be 64KB aligned\n"); @@ -361,39 +388,66 @@ static int prueth_emac_buffer_setup(struct prueth_emac *emac) }

bpool_cfg = emac->dram.va + BUFFER_POOL_0_ADDR_OFFSET; - /* workaround for f/w bug. bpool 0 needs to be initilalized */ - writel(addr, &bpool_cfg[0].addr); - writel(0, &bpool_cfg[0].len);

- for (i = PRUETH_EMAC_BUF_POOL_START; - i < PRUETH_EMAC_BUF_POOL_START + PRUETH_NUM_BUF_POOLS; - i++) { - writel(addr, &bpool_cfg[i].addr); - writel(PRUETH_EMAC_BUF_POOL_SIZE, &bpool_cfg[i].len); - addr += PRUETH_EMAC_BUF_POOL_SIZE; + /* Configure buffer pools for forwarding buffers + * - in mac mode - no forwarding so initialize all pools to 0 + * - 8 total pools per slice + */ + for (i = 0; i < PRUETH_NUM_FWD_BUF_POOLS_PER_SLICE; i++) { + writel(0, &bpool_cfg[i].addr); + writel(0, &bpool_cfg[i].len); }

- if (!slice) - addr += PRUETH_NUM_BUF_POOLS * PRUETH_EMAC_BUF_POOL_SIZE; - else - addr += PRUETH_EMAC_RX_CTX_BUF_SIZE * 2; + /* Configure buffer pools for Local Injection buffers + * - used by firmware to store packets received from host core + * - 16 total pools per slice + */ + bpool_cfg = emac->dram.va + BUFFER_POOL_0_ADDR_OFFSET; + for (i = 0; i < PRUETH_NUM_LI_BUF_POOLS_PER_SLICE; i++) { + int cfg_idx = i + PRUETH_NUM_FWD_BUF_POOLS_PER_SLICE; + + /* In EMAC mode, only first 4 buffers are used, + * as 1 slice needs to handle only 1 port + */ + if (i < PRUETH_EMAC_USED_LI_BUF_POOLS_PER_PORT_PER_SLICE) { + writel(addr, &bpool_cfg[cfg_idx].addr); + writel(PRUETH_EMAC_LI_BUF_POOL_SIZE, + &bpool_cfg[cfg_idx].len); + addr += PRUETH_EMAC_LI_BUF_POOL_SIZE; + } else { + writel(0, &bpool_cfg[cfg_idx].addr); + writel(0, &bpool_cfg[cfg_idx].len); + } + }

- /* Pre-emptible RX buffer queue */ - rxq_ctx = emac->dram.va + HOST_RX_Q_PRE_CONTEXT_OFFSET; + /* Express RX buffer queue + * - used by firmware to store express packets to be transmitted + * to host core + */ + rxq_ctx = emac->dram.va + HOST_RX_Q_EXP_CONTEXT_OFFSET; for (i = 0; i < 3; i++) writel(addr, &rxq_ctx->start[i]);

- addr += PRUETH_EMAC_RX_CTX_BUF_SIZE; + addr += PRUETH_EMAC_HOST_EXP_BUF_POOL_SIZE; writel(addr, &rxq_ctx->end);

- /* Express RX buffer queue */ - rxq_ctx = emac->dram.va + HOST_RX_Q_EXP_CONTEXT_OFFSET; + /* Pre-emptible RX buffer queue + * - used by firmware to store preemptible packets to be transmitted + * to host core + */ + rxq_ctx = emac->dram.va + HOST_RX_Q_PRE_CONTEXT_OFFSET; for (i = 0; i < 3; i++) writel(addr, &rxq_ctx->start[i]);

- addr += PRUETH_EMAC_RX_CTX_BUF_SIZE; + addr += PRUETH_EMAC_HOST_PRE_BUF_POOL_SIZE; writel(addr, &rxq_ctx->end);

+ /* Set pointer for default dropped packet write + * - used by firmware to temporarily store packet to be dropped + */ + rxq_ctx = emac->dram.va + DEFAULT_MSMC_Q_OFFSET; + writel(addr, &rxq_ctx->start[0]); + return 0; }

diff --git a/drivers/net/ethernet/ti/icssg/icssg_config.h b/drivers/net/ethernet/ti/icssg/icssg_config.h index c884e9fa099e6..60d69744ffae2 100644 --- a/drivers/net/ethernet/ti/icssg/icssg_config.h +++ b/drivers/net/ethernet/ti/icssg/icssg_config.h @@ -26,21 +26,71 @@ struct icssg_flow_cfg { #define PRUETH_MAX_RX_FLOWS 1 /* excluding default flow */ #define PRUETH_RX_FLOW_DATA 0

-#define PRUETH_EMAC_BUF_POOL_SIZE SZ_8K -#define PRUETH_EMAC_POOLS_PER_SLICE 24 -#define PRUETH_EMAC_BUF_POOL_START 8 -#define PRUETH_NUM_BUF_POOLS 8 -#define PRUETH_EMAC_RX_CTX_BUF_SIZE SZ_16K /* per slice */ -#define MSMC_RAM_SIZE \ - (2 * (PRUETH_EMAC_BUF_POOL_SIZE * PRUETH_NUM_BUF_POOLS + \ - PRUETH_EMAC_RX_CTX_BUF_SIZE * 2)) - -#define PRUETH_SW_BUF_POOL_SIZE_HOST SZ_4K -#define PRUETH_SW_NUM_BUF_POOLS_HOST 8 -#define PRUETH_SW_NUM_BUF_POOLS_PER_PRU 4 -#define MSMC_RAM_SIZE_SWITCH_MODE \ - (MSMC_RAM_SIZE + \ - (2 * PRUETH_SW_BUF_POOL_SIZE_HOST * PRUETH_SW_NUM_BUF_POOLS_HOST)) +/* Defines for forwarding path buffer pools: + * - used by firmware to store packets to be forwarded to other port + * - 8 total pools per slice + * - only used in switch mode (as no forwarding in mac mode) + */ +#define PRUETH_NUM_FWD_BUF_POOLS_PER_SLICE 8 +#define PRUETH_SW_FWD_BUF_POOL_SIZE (SZ_8K) + +/* Defines for local injection path buffer pools: + * - used by firmware to store packets received from host core + * - 16 total pools per slice + * - 8 pools per port per slice and each slice handles both ports + * - only 4 out of 8 pools used per port (as only 4 real QoS levels in ICSSG) + * - switch mode: 8 total pools used + * - mac mode: 4 total pools used + */ +#define PRUETH_NUM_LI_BUF_POOLS_PER_SLICE 16 +#define PRUETH_NUM_LI_BUF_POOLS_PER_PORT_PER_SLICE 8 +#define PRUETH_SW_LI_BUF_POOL_SIZE SZ_4K +#define PRUETH_SW_USED_LI_BUF_POOLS_PER_SLICE 8 +#define PRUETH_SW_USED_LI_BUF_POOLS_PER_PORT_PER_SLICE 4 +#define PRUETH_EMAC_LI_BUF_POOL_SIZE SZ_8K +#define PRUETH_EMAC_USED_LI_BUF_POOLS_PER_SLICE 4 +#define PRUETH_EMAC_USED_LI_BUF_POOLS_PER_PORT_PER_SLICE 4 + +/* Defines for host egress path - express and preemptible buffers + * - used by firmware to store express and preemptible packets + * to be transmitted to host core + * - used by both mac/switch modes + */ +#define PRUETH_SW_HOST_EXP_BUF_POOL_SIZE SZ_16K +#define PRUETH_SW_HOST_PRE_BUF_POOL_SIZE (SZ_16K - SZ_2K) +#define PRUETH_EMAC_HOST_EXP_BUF_POOL_SIZE PRUETH_SW_HOST_EXP_BUF_POOL_SIZE +#define PRUETH_EMAC_HOST_PRE_BUF_POOL_SIZE PRUETH_SW_HOST_PRE_BUF_POOL_SIZE + +/* Buffer used by firmware to temporarily store packet to be dropped */ +#define PRUETH_SW_DROP_PKT_BUF_SIZE SZ_2K +#define PRUETH_EMAC_DROP_PKT_BUF_SIZE PRUETH_SW_DROP_PKT_BUF_SIZE + +/* Total switch mode memory usage for buffers per slice */ +#define PRUETH_SW_TOTAL_BUF_SIZE_PER_SLICE \ + (PRUETH_SW_FWD_BUF_POOL_SIZE * PRUETH_NUM_FWD_BUF_POOLS_PER_SLICE + \ + PRUETH_SW_LI_BUF_POOL_SIZE * PRUETH_SW_USED_LI_BUF_POOLS_PER_SLICE + \ + PRUETH_SW_HOST_EXP_BUF_POOL_SIZE + \ + PRUETH_SW_HOST_PRE_BUF_POOL_SIZE + \ + PRUETH_SW_DROP_PKT_BUF_SIZE) + +/* Total switch mode memory usage for all buffers */ +#define PRUETH_SW_TOTAL_BUF_SIZE \ + (2 * PRUETH_SW_TOTAL_BUF_SIZE_PER_SLICE) + +/* Total mac mode memory usage for buffers per slice */ +#define PRUETH_EMAC_TOTAL_BUF_SIZE_PER_SLICE \ + (PRUETH_EMAC_LI_BUF_POOL_SIZE * \ + PRUETH_EMAC_USED_LI_BUF_POOLS_PER_SLICE + \ + PRUETH_EMAC_HOST_EXP_BUF_POOL_SIZE + \ + PRUETH_EMAC_HOST_PRE_BUF_POOL_SIZE + \ + PRUETH_EMAC_DROP_PKT_BUF_SIZE) + +/* Total mac mode memory usage for all buffers */ +#define PRUETH_EMAC_TOTAL_BUF_SIZE \ + (2 * PRUETH_EMAC_TOTAL_BUF_SIZE_PER_SLICE) + +/* Size of 1 bank of MSMC/OC_SRAM memory */ +#define MSMC_RAM_BANK_SIZE SZ_256K

#define PRUETH_SWITCH_FDB_MASK ((SIZE_OF_FDB / NUMBER_OF_FDB_BUCKET_ENTRIES) - 1)

diff --git a/drivers/net/ethernet/ti/icssg/icssg_prueth.c b/drivers/net/ethernet/ti/icssg/icssg_prueth.c index 86fc1278127c7..2f5c4335dec38 100644 --- a/drivers/net/ethernet/ti/icssg/icssg_prueth.c +++ b/drivers/net/ethernet/ti/icssg/icssg_prueth.c @@ -1764,10 +1764,15 @@ static int prueth_probe(struct platform_device *pdev) goto put_mem; }

- msmc_ram_size = MSMC_RAM_SIZE; prueth->is_switchmode_supported = prueth->pdata.switch_mode; - if (prueth->is_switchmode_supported) - msmc_ram_size = MSMC_RAM_SIZE_SWITCH_MODE; + if (prueth->pdata.banked_ms_ram) { + /* Reserve 2 MSMC RAM banks for buffers to avoid arbitration */ + msmc_ram_size = (2 * MSMC_RAM_BANK_SIZE); + } else { + msmc_ram_size = PRUETH_EMAC_TOTAL_BUF_SIZE; + if (prueth->is_switchmode_supported) + msmc_ram_size = PRUETH_SW_TOTAL_BUF_SIZE; + }

/* NOTE: FW bug needs buffer base to be 64KB aligned */ prueth->msmcram.va = @@ -1924,7 +1929,8 @@ static int prueth_probe(struct platform_device *pdev)

free_pool: gen_pool_free(prueth->sram_pool, - (unsigned long)prueth->msmcram.va, msmc_ram_size); + (unsigned long)prueth->msmcram.va, + prueth->msmcram.size);

put_mem: pruss_release_mem_region(prueth->pruss, &prueth->shram); @@ -1976,8 +1982,8 @@ static void prueth_remove(struct platform_device *pdev) icss_iep_put(prueth->iep0);

gen_pool_free(prueth->sram_pool, - (unsigned long)prueth->msmcram.va, - MSMC_RAM_SIZE); + (unsigned long)prueth->msmcram.va, + prueth->msmcram.size);

pruss_release_mem_region(prueth->pruss, &prueth->shram);

@@ -1994,12 +2000,14 @@ static const struct prueth_pdata am654_icssg_pdata = { .fdqring_mode = K3_RINGACC_RING_MODE_MESSAGE, .quirk_10m_link_issue = 1, .switch_mode = 1, + .banked_ms_ram = 0, };

static const struct prueth_pdata am64x_icssg_pdata = { .fdqring_mode = K3_RINGACC_RING_MODE_RING, .quirk_10m_link_issue = 1, .switch_mode = 1, + .banked_ms_ram = 1, };

static const struct of_device_id prueth_dt_match[] = { diff --git a/drivers/net/ethernet/ti/icssg/icssg_prueth.h b/drivers/net/ethernet/ti/icssg/icssg_prueth.h index b6be4aa57a615..0ca8ea0560e52 100644 --- a/drivers/net/ethernet/ti/icssg/icssg_prueth.h +++ b/drivers/net/ethernet/ti/icssg/icssg_prueth.h @@ -251,11 +251,13 @@ struct prueth_emac { * @fdqring_mode: Free desc queue mode * @quirk_10m_link_issue: 10M link detect errata * @switch_mode: switch firmware support + * @banked_ms_ram: banked memory support */ struct prueth_pdata { enum k3_ring_mode fdqring_mode; u32 quirk_10m_link_issue:1; u32 switch_mode:1; + u32 banked_ms_ram:1; };

struct icssg_firmwares { diff --git a/drivers/net/ethernet/ti/icssg/icssg_switch_map.h b/drivers/net/ethernet/ti/icssg/icssg_switch_map.h index 424a7e945ea84..12541a12ebd67 100644 --- a/drivers/net/ethernet/ti/icssg/icssg_switch_map.h +++ b/drivers/net/ethernet/ti/icssg/icssg_switch_map.h @@ -180,6 +180,9 @@ /* Used to notify the FW of the current link speed */ #define PORT_LINK_SPEED_OFFSET 0x00A8

+/* 2k memory pointer reserved for default writes by PRU0*/ +#define DEFAULT_MSMC_Q_OFFSET 0x00AC + /* TAS gate mask for windows list0 */ #define TAS_GATE_MASK_LIST0 0x0100

6.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Shahar Shitrit shshitrit@nvidia.com

[ Upstream commit 5b4c56ad4da0aa00b258ab50b1f5775b7d3108c7 ]

In the original design, it is assumed local and peer eswitches have the same number of vfs. However, in new firmware, local and peer eswitches can have different number of vfs configured by mlxconfig. In such configuration, it is incorrect to derive the number of vfs from the local device's eswitch.

Fix this by updating the peer miss rules add and delete functions to use the peer device's eswitch and vf count instead of the local device's information, ensuring correct behavior regardless of vf configuration differences.

Fixes: ac004b832128 ("net/mlx5e: E-Switch, Add peer miss rules") Signed-off-by: Shahar Shitrit shshitrit@nvidia.com Reviewed-by: Mark Bloch mbloch@nvidia.com Signed-off-by: Tariq Toukan tariqt@nvidia.com Reviewed-by: Simon Horman horms@kernel.org Link: https://patch.msgid.link/1752753970-261832-3-git-send-email-tariqt@nvidia.co... Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- .../mellanox/mlx5/core/eswitch_offloads.c | 108 +++++++++--------- 1 file changed, 54 insertions(+), 54 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c index 0e3a977d53329..bee906661282a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c @@ -1182,19 +1182,19 @@ static void esw_set_peer_miss_rule_source_port(struct mlx5_eswitch *esw, static int esw_add_fdb_peer_miss_rules(struct mlx5_eswitch *esw, struct mlx5_core_dev *peer_dev) { + struct mlx5_eswitch *peer_esw = peer_dev->priv.eswitch; struct mlx5_flow_destination dest = {}; struct mlx5_flow_act flow_act = {0}; struct mlx5_flow_handle **flows; - /* total vports is the same for both e-switches */ - int nvports = esw->total_vports; struct mlx5_flow_handle *flow; + struct mlx5_vport *peer_vport; struct mlx5_flow_spec *spec; - struct mlx5_vport *vport; int err, pfindex; unsigned long i; void *misc;

- if (!MLX5_VPORT_MANAGER(esw->dev) && !mlx5_core_is_ecpf_esw_manager(esw->dev)) + if (!MLX5_VPORT_MANAGER(peer_dev) && + !mlx5_core_is_ecpf_esw_manager(peer_dev)) return 0;

spec = kvzalloc(sizeof(*spec), GFP_KERNEL); @@ -1203,7 +1203,7 @@ static int esw_add_fdb_peer_miss_rules(struct mlx5_eswitch *esw,

peer_miss_rules_setup(esw, peer_dev, spec, &dest);

- flows = kvcalloc(nvports, sizeof(*flows), GFP_KERNEL); + flows = kvcalloc(peer_esw->total_vports, sizeof(*flows), GFP_KERNEL); if (!flows) { err = -ENOMEM; goto alloc_flows_err; @@ -1213,10 +1213,10 @@ static int esw_add_fdb_peer_miss_rules(struct mlx5_eswitch *esw, misc = MLX5_ADDR_OF(fte_match_param, spec->match_value, misc_parameters);

- if (mlx5_core_is_ecpf_esw_manager(esw->dev)) { - vport = mlx5_eswitch_get_vport(esw, MLX5_VPORT_PF); - esw_set_peer_miss_rule_source_port(esw, peer_dev->priv.eswitch, - spec, MLX5_VPORT_PF); + if (mlx5_core_is_ecpf_esw_manager(peer_dev)) { + peer_vport = mlx5_eswitch_get_vport(peer_esw, MLX5_VPORT_PF); + esw_set_peer_miss_rule_source_port(esw, peer_esw, spec, + MLX5_VPORT_PF);

flow = mlx5_add_flow_rules(mlx5_eswitch_get_slow_fdb(esw), spec, &flow_act, &dest, 1); @@ -1224,11 +1224,11 @@ static int esw_add_fdb_peer_miss_rules(struct mlx5_eswitch *esw, err = PTR_ERR(flow); goto add_pf_flow_err; } - flows[vport->index] = flow; + flows[peer_vport->index] = flow; }

- if (mlx5_ecpf_vport_exists(esw->dev)) { - vport = mlx5_eswitch_get_vport(esw, MLX5_VPORT_ECPF); + if (mlx5_ecpf_vport_exists(peer_dev)) { + peer_vport = mlx5_eswitch_get_vport(peer_esw, MLX5_VPORT_ECPF); MLX5_SET(fte_match_set_misc, misc, source_port, MLX5_VPORT_ECPF); flow = mlx5_add_flow_rules(mlx5_eswitch_get_slow_fdb(esw), spec, &flow_act, &dest, 1); @@ -1236,13 +1236,14 @@ static int esw_add_fdb_peer_miss_rules(struct mlx5_eswitch *esw, err = PTR_ERR(flow); goto add_ecpf_flow_err; } - flows[vport->index] = flow; + flows[peer_vport->index] = flow; }

- mlx5_esw_for_each_vf_vport(esw, i, vport, mlx5_core_max_vfs(esw->dev)) { + mlx5_esw_for_each_vf_vport(peer_esw, i, peer_vport, + mlx5_core_max_vfs(peer_dev)) { esw_set_peer_miss_rule_source_port(esw, - peer_dev->priv.eswitch, - spec, vport->vport); + peer_esw, + spec, peer_vport->vport);

flow = mlx5_add_flow_rules(mlx5_eswitch_get_slow_fdb(esw), spec, &flow_act, &dest, 1); @@ -1250,22 +1251,22 @@ static int esw_add_fdb_peer_miss_rules(struct mlx5_eswitch *esw, err = PTR_ERR(flow); goto add_vf_flow_err; } - flows[vport->index] = flow; + flows[peer_vport->index] = flow; }

- if (mlx5_core_ec_sriov_enabled(esw->dev)) { - mlx5_esw_for_each_ec_vf_vport(esw, i, vport, mlx5_core_max_ec_vfs(esw->dev)) { - if (i >= mlx5_core_max_ec_vfs(peer_dev)) - break; - esw_set_peer_miss_rule_source_port(esw, peer_dev->priv.eswitch, - spec, vport->vport); + if (mlx5_core_ec_sriov_enabled(peer_dev)) { + mlx5_esw_for_each_ec_vf_vport(peer_esw, i, peer_vport, + mlx5_core_max_ec_vfs(peer_dev)) { + esw_set_peer_miss_rule_source_port(esw, peer_esw, + spec, + peer_vport->vport); flow = mlx5_add_flow_rules(esw->fdb_table.offloads.slow_fdb, spec, &flow_act, &dest, 1); if (IS_ERR(flow)) { err = PTR_ERR(flow); goto add_ec_vf_flow_err; } - flows[vport->index] = flow; + flows[peer_vport->index] = flow; } }

@@ -1282,25 +1283,27 @@ static int esw_add_fdb_peer_miss_rules(struct mlx5_eswitch *esw, return 0;

add_ec_vf_flow_err: - mlx5_esw_for_each_ec_vf_vport(esw, i, vport, mlx5_core_max_ec_vfs(esw->dev)) { - if (!flows[vport->index]) + mlx5_esw_for_each_ec_vf_vport(peer_esw, i, peer_vport, + mlx5_core_max_ec_vfs(peer_dev)) { + if (!flows[peer_vport->index]) continue; - mlx5_del_flow_rules(flows[vport->index]); + mlx5_del_flow_rules(flows[peer_vport->index]); } add_vf_flow_err: - mlx5_esw_for_each_vf_vport(esw, i, vport, mlx5_core_max_vfs(esw->dev)) { - if (!flows[vport->index]) + mlx5_esw_for_each_vf_vport(peer_esw, i, peer_vport, + mlx5_core_max_vfs(peer_dev)) { + if (!flows[peer_vport->index]) continue; - mlx5_del_flow_rules(flows[vport->index]); + mlx5_del_flow_rules(flows[peer_vport->index]); } - if (mlx5_ecpf_vport_exists(esw->dev)) { - vport = mlx5_eswitch_get_vport(esw, MLX5_VPORT_ECPF); - mlx5_del_flow_rules(flows[vport->index]); + if (mlx5_ecpf_vport_exists(peer_dev)) { + peer_vport = mlx5_eswitch_get_vport(peer_esw, MLX5_VPORT_ECPF); + mlx5_del_flow_rules(flows[peer_vport->index]); } add_ecpf_flow_err: - if (mlx5_core_is_ecpf_esw_manager(esw->dev)) { - vport = mlx5_eswitch_get_vport(esw, MLX5_VPORT_PF); - mlx5_del_flow_rules(flows[vport->index]); + if (mlx5_core_is_ecpf_esw_manager(peer_dev)) { + peer_vport = mlx5_eswitch_get_vport(peer_esw, MLX5_VPORT_PF); + mlx5_del_flow_rules(flows[peer_vport->index]); } add_pf_flow_err: esw_warn(esw->dev, "FDB: Failed to add peer miss flow rule err %d\n", err); @@ -1313,37 +1316,34 @@ static int esw_add_fdb_peer_miss_rules(struct mlx5_eswitch *esw, static void esw_del_fdb_peer_miss_rules(struct mlx5_eswitch *esw, struct mlx5_core_dev *peer_dev) { + struct mlx5_eswitch *peer_esw = peer_dev->priv.eswitch; u16 peer_index = mlx5_get_dev_index(peer_dev); struct mlx5_flow_handle **flows; - struct mlx5_vport *vport; + struct mlx5_vport *peer_vport; unsigned long i;

flows = esw->fdb_table.offloads.peer_miss_rules[peer_index]; if (!flows) return;

- if (mlx5_core_ec_sriov_enabled(esw->dev)) { - mlx5_esw_for_each_ec_vf_vport(esw, i, vport, mlx5_core_max_ec_vfs(esw->dev)) { - /* The flow for a particular vport could be NULL if the other ECPF - * has fewer or no VFs enabled - */ - if (!flows[vport->index]) - continue; - mlx5_del_flow_rules(flows[vport->index]); - } + if (mlx5_core_ec_sriov_enabled(peer_dev)) { + mlx5_esw_for_each_ec_vf_vport(peer_esw, i, peer_vport, + mlx5_core_max_ec_vfs(peer_dev)) + mlx5_del_flow_rules(flows[peer_vport->index]); }

- mlx5_esw_for_each_vf_vport(esw, i, vport, mlx5_core_max_vfs(esw->dev)) - mlx5_del_flow_rules(flows[vport->index]); + mlx5_esw_for_each_vf_vport(peer_esw, i, peer_vport, + mlx5_core_max_vfs(peer_dev)) + mlx5_del_flow_rules(flows[peer_vport->index]);

- if (mlx5_ecpf_vport_exists(esw->dev)) { - vport = mlx5_eswitch_get_vport(esw, MLX5_VPORT_ECPF); - mlx5_del_flow_rules(flows[vport->index]); + if (mlx5_ecpf_vport_exists(peer_dev)) { + peer_vport = mlx5_eswitch_get_vport(peer_esw, MLX5_VPORT_ECPF); + mlx5_del_flow_rules(flows[peer_vport->index]); }

- if (mlx5_core_is_ecpf_esw_manager(esw->dev)) { - vport = mlx5_eswitch_get_vport(esw, MLX5_VPORT_PF); - mlx5_del_flow_rules(flows[vport->index]); + if (mlx5_core_is_ecpf_esw_manager(peer_dev)) { + peer_vport = mlx5_eswitch_get_vport(peer_esw, MLX5_VPORT_PF); + mlx5_del_flow_rules(flows[peer_vport->index]); }

kvfree(flows);

6.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Jamie Bainbridge jamie.bainbridge@gmail.com

[ Upstream commit 5a0df02999dbe838c3feed54b1d59e9445f68b89 ]

When the PF is processing an Admin Queue message to delete a VF's MACs from the MAC filter, we currently check if the PF set the MAC and if the VF is trusted.

This results in undesirable behaviour, where if a trusted VF with a PF-set MAC sets itself down (which sends an AQ message to delete the VF's MAC filters) then the VF MAC is erased from the interface.

This results in the VF losing its PF-set MAC which should not happen.

There is no need to check for trust at all, because an untrusted VF cannot change its own MAC. The only check needed is whether the PF set the MAC. If the PF set the MAC, then don't erase the MAC on link-down.

Resolve this by changing the deletion check only for PF-set MAC.

(the out-of-tree driver has also intentionally removed the check for VF trust here with OOT driver version 2.26.8, this changes the Linux kernel driver behaviour and comment to match the OOT driver behaviour)

Fixes: ea2a1cfc3b201 ("i40e: Fix VF MAC filter removal") Signed-off-by: Jamie Bainbridge jamie.bainbridge@gmail.com Reviewed-by: Simon Horman horms@kernel.org Tested-by: Rafal Romanowski rafal.romanowski@intel.com Signed-off-by: Tony Nguyen anthony.l.nguyen@intel.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c index 2dbe38eb94941..7ccfc1191ae56 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c +++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c @@ -3137,10 +3137,10 @@ static int i40e_vc_del_mac_addr_msg(struct i40e_vf *vf, u8 *msg) const u8 *addr = al->list[i].addr;

/* Allow to delete VF primary MAC only if it was not set - * administratively by PF or if VF is trusted. + * administratively by PF. */ if (ether_addr_equal(addr, vf->default_lan_addr.addr)) { - if (i40e_can_vf_change_mac(vf)) + if (!vf->pf_set_mac) was_unimac_deleted = true; else continue;

6.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Xiang Mei xmei5@asu.edu

[ Upstream commit cf074eca0065bc5142e6004ae236bb35a2687fdf ]

might_sleep could be trigger in the atomic context in qfq_delete_class.

qfq_destroy_class was moved into atomic context locked by sch_tree_lock to avoid a race condition bug on qfq_aggregate. However, might_sleep could be triggered by qfq_destroy_class, which introduced sleeping in atomic context (path: qfq_destroy_class->qdisc_put->__qdisc_destroy->lockdep_unregister_key ->might_sleep).

Considering the race is on the qfq_aggregate objects, keeping qfq_rm_from_agg in the lock but moving the left part out can solve this issue.

Fixes: 5e28d5a3f774 ("net/sched: sch_qfq: Fix race condition on qfq_aggregate") Reported-by: Dan Carpenter dan.carpenter@linaro.org Signed-off-by: Xiang Mei xmei5@asu.edu Link: https://patch.msgid.link/4a04e0cc-a64b-44e7-9213-2880ed641d77@sabinyo.mounta... Reviewed-by: Cong Wang xiyou.wangcong@gmail.com Reviewed-by: Dan Carpenter dan.carpenter@linaro.org Link: https://patch.msgid.link/20250717230128.159766-1-xmei5@asu.edu Signed-off-by: Paolo Abeni pabeni@redhat.com Signed-off-by: Sasha Levin sashal@kernel.org --- net/sched/sch_qfq.c | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-)

diff --git a/net/sched/sch_qfq.c b/net/sched/sch_qfq.c index 2b1b025c31a33..51cc2cfb40936 100644 --- a/net/sched/sch_qfq.c +++ b/net/sched/sch_qfq.c @@ -536,9 +536,6 @@ static int qfq_change_class(struct Qdisc *sch, u32 classid, u32 parentid,

static void qfq_destroy_class(struct Qdisc *sch, struct qfq_class *cl) { - struct qfq_sched *q = qdisc_priv(sch); - - qfq_rm_from_agg(q, cl); gen_kill_estimator(&cl->rate_est); qdisc_put(cl->qdisc); kfree(cl); @@ -559,10 +556,11 @@ static int qfq_delete_class(struct Qdisc *sch, unsigned long arg,

qdisc_purge_queue(cl->qdisc); qdisc_class_hash_remove(&q->clhash, &cl->common); - qfq_destroy_class(sch, cl); + qfq_rm_from_agg(q, cl);

sch_tree_unlock(sch);

+ qfq_destroy_class(sch, cl); return 0; }

@@ -1503,6 +1501,7 @@ static void qfq_destroy_qdisc(struct Qdisc *sch) for (i = 0; i < q->clhash.hashsize; i++) { hlist_for_each_entry_safe(cl, next, &q->clhash.hash[i], common.hnode) { + qfq_rm_from_agg(q, cl); qfq_destroy_class(sch, cl); } }

6.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Douglas Anderson dianders@chromium.org

[ Upstream commit 15a7ca747d9538c2ad8b0c81dd4c1261e0736c82 ]

As reported by the kernel test robot, a recent patch introduced an unnecessary semicolon. Remove it.

Fixes: 55e8ff842051 ("drm/bridge: ti-sn65dsi86: Add HPD for DisplayPort connector type") Reported-by: kernel test robot lkp@intel.com Closes: https://lore.kernel.org/oe-kbuild-all/202506301704.0SBj6ply-lkp@intel.com/ Reviewed-by: Devarsh Thakkar devarsht@ti.com Signed-off-by: Douglas Anderson dianders@chromium.org Link: https://lore.kernel.org/r/20250714130631.1.I1cfae3222e344a3b3c770d079ee6b6f7... Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/gpu/drm/bridge/ti-sn65dsi86.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/bridge/ti-sn65dsi86.c b/drivers/gpu/drm/bridge/ti-sn65dsi86.c index 4ea13e5a3a54a..48766b6abd29a 100644 --- a/drivers/gpu/drm/bridge/ti-sn65dsi86.c +++ b/drivers/gpu/drm/bridge/ti-sn65dsi86.c @@ -1351,7 +1351,7 @@ static int ti_sn_bridge_probe(struct auxiliary_device *adev, regmap_update_bits(pdata->regmap, SN_HPD_DISABLE_REG, HPD_DISABLE, 0); mutex_unlock(&pdata->comms_mutex); - }; + }

drm_bridge_add(&pdata->bridge);

6.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Nimrod Oren noren@nvidia.com

[ Upstream commit 86941382508850d58c11bdafe0fec646dfd31b09 ]

A few packets may still be sent out during the termination of iperf processes. These late packets cause failures in rss_ctx.py when they arrive on queues expected to be empty.

Example failure observed:

Check failed 2 != 0 traffic on inactive queues (context 1): [0, 0, 1, 1, 386385, 397196, 0, 0, 0, 0, ...]

Check failed 4 != 0 traffic on inactive queues (context 2): [0, 0, 0, 0, 2, 2, 247152, 253013, 0, 0, ...]

Check failed 2 != 0 traffic on inactive queues (context 3): [0, 0, 0, 0, 0, 0, 1, 1, 282434, 283070, ...]

To avoid such failures, wait until all client sockets for the requested port are either closed or in the TIME_WAIT state.

Fixes: 847aa551fa78 ("selftests: drv-net: rss_ctx: factor out send traffic and check") Signed-off-by: Nimrod Oren noren@nvidia.com Reviewed-by: Gal Pressman gal@nvidia.com Reviewed-by: Carolina Jubran cjubran@nvidia.com Reviewed-by: Simon Horman horms@kernel.org Link: https://patch.msgid.link/20250722122655.3194442-1-noren@nvidia.com Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- .../selftests/drivers/net/lib/py/load.py | 23 +++++++++++++++---- 1 file changed, 18 insertions(+), 5 deletions(-)

diff --git a/tools/testing/selftests/drivers/net/lib/py/load.py b/tools/testing/selftests/drivers/net/lib/py/load.py index da5af2c680faa..1a9d57c3efa3c 100644 --- a/tools/testing/selftests/drivers/net/lib/py/load.py +++ b/tools/testing/selftests/drivers/net/lib/py/load.py @@ -1,5 +1,6 @@ # SPDX-License-Identifier: GPL-2.0

+import re import time

from lib.py import ksft_pr, cmd, ip, rand_port, wait_port_listen, bkg @@ -10,12 +11,11 @@ class GenerateTraffic:

self.env = env

- if port is None: - port = rand_port() - self._iperf_server = cmd(f"iperf3 -s -1 -p {port}", background=True) - wait_port_listen(port) + self.port = rand_port() if port is None else port + self._iperf_server = cmd(f"iperf3 -s -1 -p {self.port}", background=True) + wait_port_listen(self.port) time.sleep(0.1) - self._iperf_client = cmd(f"iperf3 -c {env.addr} -P 16 -p {port} -t 86400", + self._iperf_client = cmd(f"iperf3 -c {env.addr} -P 16 -p {self.port} -t 86400", background=True, host=env.remote)

# Wait for traffic to ramp up @@ -74,3 +74,16 @@ class GenerateTraffic: ksft_pr(">> Server:") ksft_pr(self._iperf_server.stdout) ksft_pr(self._iperf_server.stderr) + self._wait_client_stopped() + + def _wait_client_stopped(self, sleep=0.005, timeout=5): + end = time.monotonic() + timeout + + live_port_pattern = re.compile(fr":{self.port:04X} 0[^6] ") + + while time.monotonic() < end: + data = cmd("cat /proc/net/tcp*", host=self.env.remote).stdout + if not live_port_pattern.search(data): + return + time.sleep(sleep) + raise Exception(f"Waiting for client to stop timed out after {timeout}s")

6.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Jian Shen shenjian15@huawei.com

[ Upstream commit 4555f8f8b6aa46940f55feb6a07704c2935b6d6e ]

The vport->req_vlan_fltr_en may be changed concurrently by function hclge_sync_vlan_fltr_state() called in periodic work task and function hclge_enable_vport_vlan_filter() called by user configuration. It may cause the user configuration inoperative. Fixes it by protect the vport->req_vlan_fltr by vport_lock.

Fixes: 2ba306627f59 ("net: hns3: add support for modify VLAN filter state") Signed-off-by: Jian Shen shenjian15@huawei.com Signed-off-by: Jijie Shao shaojijie@huawei.com Reviewed-by: Simon Horman horms@kernel.org Link: https://patch.msgid.link/20250722125423.1270673-2-shaojijie@huawei.com Signed-off-by: Paolo Abeni pabeni@redhat.com Signed-off-by: Sasha Levin sashal@kernel.org --- .../hisilicon/hns3/hns3pf/hclge_main.c | 36 +++++++++++-------- 1 file changed, 21 insertions(+), 15 deletions(-)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c index 3e28a08934abd..4ea19c089578e 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c @@ -9576,33 +9576,36 @@ static bool hclge_need_enable_vport_vlan_filter(struct hclge_vport *vport) return false; }

-int hclge_enable_vport_vlan_filter(struct hclge_vport *vport, bool request_en) +static int __hclge_enable_vport_vlan_filter(struct hclge_vport *vport, + bool request_en) { - struct hclge_dev *hdev = vport->back; bool need_en; int ret;

- mutex_lock(&hdev->vport_lock); - - vport->req_vlan_fltr_en = request_en; - need_en = hclge_need_enable_vport_vlan_filter(vport); - if (need_en == vport->cur_vlan_fltr_en) { - mutex_unlock(&hdev->vport_lock); + if (need_en == vport->cur_vlan_fltr_en) return 0; - }

ret = hclge_set_vport_vlan_filter(vport, need_en); - if (ret) { - mutex_unlock(&hdev->vport_lock); + if (ret) return ret; - }

vport->cur_vlan_fltr_en = need_en;

+ return 0; +} + +int hclge_enable_vport_vlan_filter(struct hclge_vport *vport, bool request_en) +{ + struct hclge_dev *hdev = vport->back; + int ret; + + mutex_lock(&hdev->vport_lock); + vport->req_vlan_fltr_en = request_en; + ret = __hclge_enable_vport_vlan_filter(vport, request_en); mutex_unlock(&hdev->vport_lock);

- return 0; + return ret; }

static int hclge_enable_vlan_filter(struct hnae3_handle *handle, bool enable) @@ -10623,16 +10626,19 @@ static void hclge_sync_vlan_fltr_state(struct hclge_dev *hdev) &vport->state)) continue;

- ret = hclge_enable_vport_vlan_filter(vport, - vport->req_vlan_fltr_en); + mutex_lock(&hdev->vport_lock); + ret = __hclge_enable_vport_vlan_filter(vport, + vport->req_vlan_fltr_en); if (ret) { dev_err(&hdev->pdev->dev, "failed to sync vlan filter state for vport%u, ret = %d\n", vport->vport_id, ret); set_bit(HCLGE_VPORT_STATE_VLAN_FLTR_CHANGE, &vport->state); + mutex_unlock(&hdev->vport_lock); return; } + mutex_unlock(&hdev->vport_lock); } }

6.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Jian Shen shenjian15@huawei.com

[ Upstream commit b3e75c0bcc53f647311960bc1b0970b9b480ca5a ]

Currently, the queried maximum of vf channels is the maximum of channels supported by each TC. However, the actual maximum of channels is the maximum of channels supported by the device.

Fixes: 849e46077689 ("net: hns3: add ethtool_ops.get_channels support for VF") Signed-off-by: Jian Shen shenjian15@huawei.com Signed-off-by: Hao Lan lanhao@huawei.com Signed-off-by: Jijie Shao shaojijie@huawei.com Reviewed-by: Simon Horman horms@kernel.org Link: https://patch.msgid.link/20250722125423.1270673-4-shaojijie@huawei.com Signed-off-by: Paolo Abeni pabeni@redhat.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c | 6 +----- 1 file changed, 1 insertion(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c index dada42e7e0ec9..27d10aeafb2b1 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c @@ -3094,11 +3094,7 @@ static void hclgevf_uninit_ae_dev(struct hnae3_ae_dev *ae_dev)

static u32 hclgevf_get_max_channels(struct hclgevf_dev *hdev) { - struct hnae3_handle *nic = &hdev->nic; - struct hnae3_knic_private_info *kinfo = &nic->kinfo; - - return min_t(u32, hdev->rss_size_max, - hdev->num_tqps / kinfo->tc_info.num_tc); + return min(hdev->rss_size_max, hdev->num_tqps); }

/**

6.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Kurt Borja kuurtb@gmail.com

commit 8346c6af27f1c1410eb314f4be5875fdf1579a10 upstream.

Add missing empty member to `awcc_dmi_table`.

Cc: stable@vger.kernel.org Fixes: 6d7f1b1a5db6 ("platform/x86: alienware-wmi: Split DMI table") Signed-off-by: Kurt Borja kuurtb@gmail.com Reviewed-by: Hans de Goede hansg@kernel.org Link: https://lore.kernel.org/r/20250707-dmi-fix-v1-1-6730835d824d@gmail.com Reviewed-by: Ilpo Järvinen ilpo.jarvinen@linux.intel.com Signed-off-by: Ilpo Järvinen ilpo.jarvinen@linux.intel.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/platform/x86/dell/alienware-wmi-wmax.c | 1 + 1 file changed, 1 insertion(+)

--- a/drivers/platform/x86/dell/alienware-wmi-wmax.c +++ b/drivers/platform/x86/dell/alienware-wmi-wmax.c @@ -205,6 +205,7 @@ static const struct dmi_system_id awcc_d }, .driver_data = &g_series_quirks, }, + {} };

enum WMAX_THERMAL_INFORMATION_OPERATIONS {

6.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Rong Zhang i@rong.moe

commit e10981075adce203eac0be866389309eeb8ef11e upstream.

On some models supported by ideapad-laptop, the HW/FW can remember the state of keyboard backlight among boots. However, it is always turned off while shutting down, as a side effect of the LED class device unregistering sequence.

This is inconvenient for users who always prefer turning on the keyboard backlight. Thus, set LED_RETAIN_AT_SHUTDOWN on the LED class device so that the state of keyboard backlight gets remembered, which also aligns with the behavior of manufacturer utilities on Windows.

Fixes: 503325f84bc0 ("platform/x86: ideapad-laptop: add keyboard backlight control support") Cc: stable@vger.kernel.org Signed-off-by: Rong Zhang i@rong.moe Reviewed-by: Hans de Goede hansg@kernel.org Link: https://lore.kernel.org/r/20250707163808.155876-3-i@rong.moe Reviewed-by: Ilpo Järvinen ilpo.jarvinen@linux.intel.com Signed-off-by: Ilpo Järvinen ilpo.jarvinen@linux.intel.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/platform/x86/ideapad-laptop.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

--- a/drivers/platform/x86/ideapad-laptop.c +++ b/drivers/platform/x86/ideapad-laptop.c @@ -1669,7 +1669,7 @@ static int ideapad_kbd_bl_init(struct id priv->kbd_bl.led.name = "platform::" LED_FUNCTION_KBD_BACKLIGHT; priv->kbd_bl.led.brightness_get = ideapad_kbd_bl_led_cdev_brightness_get; priv->kbd_bl.led.brightness_set_blocking = ideapad_kbd_bl_led_cdev_brightness_set; - priv->kbd_bl.led.flags = LED_BRIGHT_HW_CHANGED; + priv->kbd_bl.led.flags = LED_BRIGHT_HW_CHANGED | LED_RETAIN_AT_SHUTDOWN;

err = led_classdev_register(&priv->platform_device->dev, &priv->kbd_bl.led); if (err)

6.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Thomas Zimmermann tzimmermann@suse.de

commit fb4ef4a52b79a22ad382bfe77332642d02aef773 upstream.

This reverts commit f83a9b8c7fd0557b0c50784bfdc1bbe9140c9bf8.

The dma_buf field in struct drm_gem_object is not stable over the object instance's lifetime. The field becomes NULL when user space releases the final GEM handle on the buffer object. This resulted in a NULL-pointer deref.

Workarounds in commit 5307dce878d4 ("drm/gem: Acquire references on GEM handles for framebuffers") and commit f6bfc9afc751 ("drm/framebuffer: Acquire internal references on GEM handles") only solved the problem partially. They especially don't work for buffer objects without a DRM framebuffer associated.

Hence, this revert to going back to using .import_attach->dmabuf.

v3: - cc stable

Signed-off-by: Thomas Zimmermann tzimmermann@suse.de Reviewed-by: Simona Vetter simona.vetter@ffwll.ch Acked-by: Christian König christian.koenig@amd.com Acked-by: Zack Rusin zack.rusin@broadcom.com Cc: stable@vger.kernel.org # v6.15+ Link: https://lore.kernel.org/r/20250715155934.150656-5-tzimmermann@suse.de Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/gpu/drm/drm_prime.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/drm_prime.c b/drivers/gpu/drm/drm_prime.c index d828502268b8..a0a5d725eab0 100644 --- a/drivers/gpu/drm/drm_prime.c +++ b/drivers/gpu/drm/drm_prime.c @@ -453,7 +453,13 @@ struct dma_buf *drm_gem_prime_handle_to_dmabuf(struct drm_device *dev, }

mutex_lock(&dev->object_name_lock); - /* re-export the original imported/exported object */ + /* re-export the original imported object */ + if (obj->import_attach) { + dmabuf = obj->import_attach->dmabuf; + get_dma_buf(dmabuf); + goto out_have_obj; + } + if (obj->dma_buf) { get_dma_buf(obj->dma_buf); dmabuf = obj->dma_buf;

6.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Thomas Zimmermann tzimmermann@suse.de

commit 1918e79be908b8a2c8757640289bc196c14d928a upstream.

This reverts commit e8afa1557f4f963c9a511bd2c6074a941c308685.

The dma_buf field in struct drm_gem_object is not stable over the object instance's lifetime. The field becomes NULL when user space releases the final GEM handle on the buffer object. This resulted in a NULL-pointer deref.

Workarounds in commit 5307dce878d4 ("drm/gem: Acquire references on GEM handles for framebuffers") and commit f6bfc9afc751 ("drm/framebuffer: Acquire internal references on GEM handles") only solved the problem partially. They especially don't work for buffer objects without a DRM framebuffer associated.

Hence, this revert to going back to using .import_attach->dmabuf.

v3: - cc stable

Signed-off-by: Thomas Zimmermann tzimmermann@suse.de Reviewed-by: Simona Vetter simona.vetter@ffwll.ch Acked-by: Christian König christian.koenig@amd.com Acked-by: Zack Rusin zack.rusin@broadcom.com Cc: stable@vger.kernel.org # v6.15+ Link: https://lore.kernel.org/r/20250715155934.150656-8-tzimmermann@suse.de Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/gpu/drm/drm_gem_dma_helper.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

--- a/drivers/gpu/drm/drm_gem_dma_helper.c +++ b/drivers/gpu/drm/drm_gem_dma_helper.c @@ -230,7 +230,7 @@ void drm_gem_dma_free(struct drm_gem_dma

if (drm_gem_is_imported(gem_obj)) { if (dma_obj->vaddr) - dma_buf_vunmap_unlocked(gem_obj->dma_buf, &map); + dma_buf_vunmap_unlocked(gem_obj->import_attach->dmabuf, &map); drm_prime_gem_destroy(gem_obj, dma_obj->sgt); } else if (dma_obj->vaddr) { if (dma_obj->map_noncoherent)

6.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Lin.Cao lincao12@amd.com

commit 15f77764e90a713ee3916ca424757688e4f565b9 upstream.

When application A submits jobs and application B submits a job with a dependency on A's fence, the normal flow wakes up the scheduler after processing each job. However, the optimization in drm_sched_entity_add_dependency_cb() uses a callback that only clears dependencies without waking up the scheduler.

When application A is killed before its jobs can run, the callback gets triggered but only clears the dependency without waking up the scheduler, causing the scheduler to enter sleep state and application B to hang.

Remove the optimization by deleting drm_sched_entity_clear_dep() and its usage, ensuring the scheduler is always woken up when dependencies are cleared.

Fixes: 777dbd458c89 ("drm/amdgpu: drop a dummy wakeup scheduler") Cc: stable@vger.kernel.org # v4.6+ Signed-off-by: Lin.Cao lincao12@amd.com Reviewed-by: Christian König christian.koenig@amd.com Signed-off-by: Philipp Stanner phasta@kernel.org Link: https://lore.kernel.org/r/20250717084453.921097-1-lincao12@amd.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/gpu/drm/scheduler/sched_entity.c | 21 ++------------------- 1 file changed, 2 insertions(+), 19 deletions(-)

--- a/drivers/gpu/drm/scheduler/sched_entity.c +++ b/drivers/gpu/drm/scheduler/sched_entity.c @@ -355,17 +355,6 @@ void drm_sched_entity_destroy(struct drm } EXPORT_SYMBOL(drm_sched_entity_destroy);

-/* drm_sched_entity_clear_dep - callback to clear the entities dependency */ -static void drm_sched_entity_clear_dep(struct dma_fence *f, - struct dma_fence_cb *cb) -{ - struct drm_sched_entity *entity = - container_of(cb, struct drm_sched_entity, cb); - - entity->dependency = NULL; - dma_fence_put(f); -} - /* * drm_sched_entity_wakeup - callback to clear the entity's dependency and * wake up the scheduler @@ -376,7 +365,8 @@ static void drm_sched_entity_wakeup(stru struct drm_sched_entity *entity = container_of(cb, struct drm_sched_entity, cb);

- drm_sched_entity_clear_dep(f, cb); + entity->dependency = NULL; + dma_fence_put(f); drm_sched_wakeup(entity->rq->sched); }

@@ -429,13 +419,6 @@ static bool drm_sched_entity_add_depende fence = dma_fence_get(&s_fence->scheduled); dma_fence_put(entity->dependency); entity->dependency = fence; - if (!dma_fence_add_callback(fence, &entity->cb, - drm_sched_entity_clear_dep)) - return true; - - /* Ignore it when it is already scheduled */ - dma_fence_put(fence); - return false; }

if (!dma_fence_add_callback(entity->dependency, &entity->cb,

6.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Nathan Chancellor nathan@kernel.org

commit 87c4e1459e80bf65066f864c762ef4dc932fad4b upstream.

After commit d5c8d6e0fa61 ("kbuild: Update assembler calls to use proper flags and language target"), which updated as-instr to use the 'assembler-with-cpp' language option, the Kbuild version of as-instr always fails internally for arch/arm with

<command-line>: fatal error: asm/unified.h: No such file or directory compilation terminated.

because '-include' flags are now taken into account by the compiler driver and as-instr does not have '$(LINUXINCLUDE)', so unified.h is not found.

This went unnoticed at the time of the Kbuild change because the last use of as-instr in Kbuild that arch/arm could reach was removed in 5.7 by commit 541ad0150ca4 ("arm: Remove 32bit KVM host support") but a stable backport of the Kbuild change to before that point exposed this potential issue if one were to be reintroduced.

Follow the general pattern of '-include' paths throughout the tree and make unified.h absolute using '$(srctree)' to ensure KBUILD_AFLAGS can be used independently.

Closes: https://lore.kernel.org/CACo-S-1qbCX4WAVFA63dWfHtrRHZBTyyr2js8Lx=Az03XHTTHg@...

Cc: stable@vger.kernel.org Fixes: d5c8d6e0fa61 ("kbuild: Update assembler calls to use proper flags and language target") Reported-by: KernelCI bot bot@kernelci.org Reviewed-by: Masahiro Yamada masahiroy@kernel.org Signed-off-by: Nathan Chancellor nathan@kernel.org Signed-off-by: Russell King (Oracle) rmk+kernel@armlinux.org.uk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- arch/arm/Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

--- a/arch/arm/Makefile +++ b/arch/arm/Makefile @@ -149,7 +149,7 @@ endif # Need -Uarm for gcc < 3.x KBUILD_CPPFLAGS +=$(cpp-y) KBUILD_CFLAGS +=$(CFLAGS_ABI) $(CFLAGS_ISA) $(arch-y) $(tune-y) $(call cc-option,-mshort-load-bytes,$(call cc-option,-malignment-traps,)) -msoft-float -Uarm -KBUILD_AFLAGS +=$(CFLAGS_ABI) $(AFLAGS_ISA) -Wa,$(arch-y) $(tune-y) -include asm/unified.h -msoft-float +KBUILD_AFLAGS +=$(CFLAGS_ABI) $(AFLAGS_ISA) -Wa,$(arch-y) $(tune-y) -include $(srctree)/arch/arm/include/asm/unified.h -msoft-float KBUILD_RUSTFLAGS += --target=arm-unknown-linux-gnueabi

CHECKFLAGS += -D__arm__

6.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Markus Blöchl markus@blochl.de

commit 67c632b4a7fbd6b76a08b86f4950f0f84de93439 upstream.

Most drivers only populate the fields cycles and cs_id of system_counterval in their get_time_fn() callback for get_device_system_crosststamp(), unless they explicitly provide nanosecond values.

When the use_nsecs field was added to struct system_counterval, most drivers did not care. Clock sources other than CSID_GENERIC could then get converted in convert_base_to_cs() based on an uninitialized use_nsecs field, which usually results in -EINVAL during the following range check.

Pass in a fully zero initialized system_counterval_t to cure that.

Fixes: 6b2e29977518 ("timekeeping: Provide infrastructure for converting to/from a base clock") Signed-off-by: Markus Blöchl markus@blochl.de Signed-off-by: Thomas Gleixner tglx@linutronix.de Acked-by: John Stultz jstultz@google.com Cc: stable@vger.kernel.org Link: https://lore.kernel.org/all/20250720-timekeeping_uninit_crossts-v2-1-f513c88... Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- kernel/time/timekeeping.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

--- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -1256,7 +1256,7 @@ int get_device_system_crosststamp(int (* struct system_time_snapshot *history_begin, struct system_device_crosststamp *xtstamp) { - struct system_counterval_t system_counterval; + struct system_counterval_t system_counterval = {}; struct timekeeper *tk = &tk_core.timekeeper; u64 cycles, now, interval_start; unsigned int clock_was_set_seq = 0;

6.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Akhil R akhilrajeev@nvidia.com

commit 56344e241c543f17e8102fa13466ad5c3e7dc9ff upstream.

The acpi_evaluate_object() returns an ACPI error code and not Linux one. For the some platforms the err will have positive code which may be interpreted incorrectly. Use device_reset() for reset control which handles it correctly.

Fixes: bd2fdedbf2ba ("i2c: tegra: Add the ACPI support") Reported-by: Andy Shevchenko andriy.shevchenko@linux.intel.com Signed-off-by: Akhil R akhilrajeev@nvidia.com Cc: stable@vger.kernel.org # v5.17+ Reviewed-by: Andy Shevchenko andriy.shevchenko@linux.intel.com Signed-off-by: Andi Shyti andi.shyti@kernel.org Link: https://lore.kernel.org/r/20250710131206.2316-2-akhilrajeev@nvidia.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/i2c/busses/i2c-tegra.c | 24 +----------------------- 1 file changed, 1 insertion(+), 23 deletions(-)

--- a/drivers/i2c/busses/i2c-tegra.c +++ b/drivers/i2c/busses/i2c-tegra.c @@ -607,7 +607,6 @@ static int tegra_i2c_wait_for_config_loa static int tegra_i2c_init(struct tegra_i2c_dev *i2c_dev) { u32 val, clk_divisor, clk_multiplier, tsu_thd, tlow, thigh, non_hs_mode; - acpi_handle handle = ACPI_HANDLE(i2c_dev->dev); struct i2c_timings *t = &i2c_dev->timings; int err;

@@ -619,11 +618,7 @@ static int tegra_i2c_init(struct tegra_i * emit a noisy warning on error, which won't stay unnoticed and * won't hose machine entirely. */ - if (handle) - err = acpi_evaluate_object(handle, "_RST", NULL, NULL); - else - err = reset_control_reset(i2c_dev->rst); - + err = device_reset(i2c_dev->dev); WARN_ON_ONCE(err);

if (IS_DVC(i2c_dev)) @@ -1666,19 +1661,6 @@ static void tegra_i2c_parse_dt(struct te i2c_dev->is_vi = true; }

-static int tegra_i2c_init_reset(struct tegra_i2c_dev *i2c_dev) -{ - if (ACPI_HANDLE(i2c_dev->dev)) - return 0; - - i2c_dev->rst = devm_reset_control_get_exclusive(i2c_dev->dev, "i2c"); - if (IS_ERR(i2c_dev->rst)) - return dev_err_probe(i2c_dev->dev, PTR_ERR(i2c_dev->rst), - "failed to get reset control\n"); - - return 0; -} - static int tegra_i2c_init_clocks(struct tegra_i2c_dev *i2c_dev) { int err; @@ -1788,10 +1770,6 @@ static int tegra_i2c_probe(struct platfo

tegra_i2c_parse_dt(i2c_dev);

- err = tegra_i2c_init_reset(i2c_dev); - if (err) - return err; - err = tegra_i2c_init_clocks(i2c_dev); if (err) return err;

6.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Ma Ke make24@iscas.ac.cn

commit bddbe13d36a02d5097b99cf02354d5752ad1ac60 upstream.

The fsl_mc_get_endpoint() function may call fsl_mc_device_lookup() twice, which would increment the device's reference count twice if both lookups find a device. This could lead to a reference count leak.

Found by code review.

Cc: stable@vger.kernel.org Fixes: 1ac210d128ef ("bus: fsl-mc: add the fsl_mc_get_endpoint function") Signed-off-by: Ma Ke make24@iscas.ac.cn Tested-by: Ioana Ciornei ioana.ciornei@nxp.com Reviewed-by: Simon Horman horms@kernel.org Fixes: 8567494cebe5 ("bus: fsl-mc: rescan devices if endpoint not found") Link: https://patch.msgid.link/20250717022309.3339976-1-make24@iscas.ac.cn Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/bus/fsl-mc/fsl-mc-bus.c | 19 +++++++++---------- 1 file changed, 9 insertions(+), 10 deletions(-)

--- a/drivers/bus/fsl-mc/fsl-mc-bus.c +++ b/drivers/bus/fsl-mc/fsl-mc-bus.c @@ -943,6 +943,7 @@ struct fsl_mc_device *fsl_mc_get_endpoin struct fsl_mc_obj_desc endpoint_desc = {{ 0 }}; struct dprc_endpoint endpoint1 = {{ 0 }}; struct dprc_endpoint endpoint2 = {{ 0 }}; + struct fsl_mc_bus *mc_bus; int state, err;

mc_bus_dev = to_fsl_mc_device(mc_dev->dev.parent); @@ -966,6 +967,8 @@ struct fsl_mc_device *fsl_mc_get_endpoin strcpy(endpoint_desc.type, endpoint2.type); endpoint_desc.id = endpoint2.id; endpoint = fsl_mc_device_lookup(&endpoint_desc, mc_bus_dev); + if (endpoint) + return endpoint;

/* * We know that the device has an endpoint because we verified by @@ -973,17 +976,13 @@ struct fsl_mc_device *fsl_mc_get_endpoin * yet discovered by the fsl-mc bus, thus the lookup returned NULL. * Force a rescan of the devices in this container and retry the lookup. */ - if (!endpoint) { - struct fsl_mc_bus *mc_bus = to_fsl_mc_bus(mc_bus_dev); - - if (mutex_trylock(&mc_bus->scan_mutex)) { - err = dprc_scan_objects(mc_bus_dev, true); - mutex_unlock(&mc_bus->scan_mutex); - } - - if (err < 0) - return ERR_PTR(err); + mc_bus = to_fsl_mc_bus(mc_bus_dev); + if (mutex_trylock(&mc_bus->scan_mutex)) { + err = dprc_scan_objects(mc_bus_dev, true); + mutex_unlock(&mc_bus->scan_mutex); } + if (err < 0) + return ERR_PTR(err);

endpoint = fsl_mc_device_lookup(&endpoint_desc, mc_bus_dev); /*

6.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Dawid Rezler dawidrezler.patches@gmail.com

commit 9744ede7099e8a69c04aa23fbea44c15bc390c04 upstream.

The mute LED on the HP Pavilion Laptop 15-eg0xxx, which uses the ALC287 codec, didn't work. This patch fixes the issue by enabling the ALC287_FIXUP_HP_GPIO_LED quirk.

Tested on a physical device, the LED now works as intended.

Signed-off-by: Dawid Rezler dawidrezler.patches@gmail.com Cc: stable@vger.kernel.org Link: https://patch.msgid.link/20250720154907.80815-2-dawidrezler.patches@gmail.co... Signed-off-by: Takashi Iwai tiwai@suse.de Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- sound/pci/hda/patch_realtek.c | 1 + 1 file changed, 1 insertion(+)

--- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -10668,6 +10668,7 @@ static const struct hda_quirk alc269_fix SND_PCI_QUIRK(0x103c, 0x8788, "HP OMEN 15", ALC285_FIXUP_HP_MUTE_LED), SND_PCI_QUIRK(0x103c, 0x87b7, "HP Laptop 14-fq0xxx", ALC236_FIXUP_HP_MUTE_LED_COEFBIT2), SND_PCI_QUIRK(0x103c, 0x87c8, "HP", ALC287_FIXUP_HP_GPIO_LED), + SND_PCI_QUIRK(0x103c, 0x87cc, "HP Pavilion 15-eg0xxx", ALC287_FIXUP_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x87d3, "HP Laptop 15-gw0xxx", ALC236_FIXUP_HP_MUTE_LED_COEFBIT2), SND_PCI_QUIRK(0x103c, 0x87df, "HP ProBook 430 G8 Notebook PC", ALC236_FIXUP_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x87e5, "HP ProBook 440 G8 Notebook PC", ALC236_FIXUP_HP_GPIO_LED),

6.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Ada Couprie Diaz ada.coupriediaz@arm.com

commit d42e6c20de6192f8e4ab4cf10be8c694ef27e8cb upstream.

`cpu_switch_to()` and `call_on_irq_stack()` manipulate SP to change to different stacks along with the Shadow Call Stack if it is enabled. Those two stack changes cannot be done atomically and both functions can be interrupted by SErrors or Debug Exceptions which, though unlikely, is very much broken : if interrupted, we can end up with mismatched stacks and Shadow Call Stack leading to clobbered stacks.

In `cpu_switch_to()`, it can happen when SP_EL0 points to the new task, but x18 stills points to the old task's SCS. When the interrupt handler tries to save the task's SCS pointer, it will save the old task SCS pointer (x18) into the new task struct (pointed to by SP_EL0), clobbering it.

In `call_on_irq_stack()`, it can happen when switching from the task stack to the IRQ stack and when switching back. In both cases, we can be interrupted when the SCS pointer points to the IRQ SCS, but SP points to the task stack. The nested interrupt handler pushes its return addresses on the IRQ SCS. It then detects that SP points to the task stack, calls `call_on_irq_stack()` and clobbers the task SCS pointer with the IRQ SCS pointer, which it will also use !

This leads to tasks returning to addresses on the wrong SCS, or even on the IRQ SCS, triggering kernel panics via CONFIG_VMAP_STACK or FPAC if enabled.

This is possible on a default config, but unlikely. However, when enabling CONFIG_ARM64_PSEUDO_NMI, DAIF is unmasked and instead the GIC is responsible for filtering what interrupts the CPU should receive based on priority. Given the goal of emulating NMIs, pseudo-NMIs can be received by the CPU even in `cpu_switch_to()` and `call_on_irq_stack()`, possibly *very* frequently depending on the system configuration and workload, leading to unpredictable kernel panics.

Completely mask DAIF in `cpu_switch_to()` and restore it when returning. Do the same in `call_on_irq_stack()`, but restore and mask around the branch. Mask DAIF even if CONFIG_SHADOW_CALL_STACK is not enabled for consistency of behaviour between all configurations.

Introduce and use an assembly macro for saving and masking DAIF, as the existing one saves but only masks IF.

Cc: stable@vger.kernel.org Signed-off-by: Ada Couprie Diaz ada.coupriediaz@arm.com Reported-by: Cristian Prundeanu cpru@amazon.com Fixes: 59b37fe52f49 ("arm64: Stash shadow stack pointer in the task struct on interrupt") Tested-by: Cristian Prundeanu cpru@amazon.com Acked-by: Will Deacon will@kernel.org Link: https://lore.kernel.org/r/20250718142814.133329-1-ada.coupriediaz@arm.com Signed-off-by: Will Deacon will@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- arch/arm64/include/asm/assembler.h | 5 +++++ arch/arm64/kernel/entry.S | 6 ++++++ 2 files changed, 11 insertions(+)

--- a/arch/arm64/include/asm/assembler.h +++ b/arch/arm64/include/asm/assembler.h @@ -41,6 +41,11 @@ /* * Save/restore interrupts. */ + .macro save_and_disable_daif, flags + mrs \flags, daif + msr daifset, #0xf + .endm + .macro save_and_disable_irq, flags mrs \flags, daif msr daifset, #3 --- a/arch/arm64/kernel/entry.S +++ b/arch/arm64/kernel/entry.S @@ -825,6 +825,7 @@ SYM_CODE_END(__bp_harden_el1_vectors) * */ SYM_FUNC_START(cpu_switch_to) + save_and_disable_daif x11 mov x10, #THREAD_CPU_CONTEXT add x8, x0, x10 mov x9, sp @@ -848,6 +849,7 @@ SYM_FUNC_START(cpu_switch_to) ptrauth_keys_install_kernel x1, x8, x9, x10 scs_save x0 scs_load_current + restore_irq x11 ret SYM_FUNC_END(cpu_switch_to) NOKPROBE(cpu_switch_to) @@ -874,6 +876,7 @@ NOKPROBE(ret_from_fork) * Calls func(regs) using this CPU's irq stack and shadow irq stack. */ SYM_FUNC_START(call_on_irq_stack) + save_and_disable_daif x9 #ifdef CONFIG_SHADOW_CALL_STACK get_current_task x16 scs_save x16 @@ -888,8 +891,10 @@ SYM_FUNC_START(call_on_irq_stack)

/* Move to the new stack and call the function there */ add sp, x16, #IRQ_STACK_SIZE + restore_irq x9 blr x1

+ save_and_disable_daif x9 /* * Restore the SP from the FP, and restore the FP and LR from the frame * record. @@ -897,6 +902,7 @@ SYM_FUNC_START(call_on_irq_stack) mov sp, x29 ldp x29, x30, [sp], #16 scs_load_current + restore_irq x9 ret SYM_FUNC_END(call_on_irq_stack) NOKPROBE(call_on_irq_stack)

6.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Ma Ke make24@iscas.ac.cn

commit ee9f3a81ab08dfe0538dbd1746f81fd4d5147fdc upstream.

The fsl_mc_get_endpoint() function uses device_find_child() for localization, which implicitly calls get_device() to increment the device's reference count before returning the pointer. However, the caller dpaa2_eth_connect_mac() fails to properly release this reference in multiple scenarios. We should call put_device() to decrement reference count properly.

As comment of device_find_child() says, 'NOTE: you will need to drop the reference with put_device() after use'.

Found by code review.

Cc: stable@vger.kernel.org Fixes: 719479230893 ("dpaa2-eth: add MAC/PHY support through phylink") Signed-off-by: Ma Ke make24@iscas.ac.cn Tested-by: Ioana Ciornei ioana.ciornei@nxp.com Reviewed-by: Ioana Ciornei ioana.ciornei@nxp.com Reviewed-by: Simon Horman horms@kernel.org Link: https://patch.msgid.link/20250717022309.3339976-2-make24@iscas.ac.cn Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c | 15 ++++++++++++--- 1 file changed, 12 insertions(+), 3 deletions(-)

--- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c +++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c @@ -4655,12 +4655,19 @@ static int dpaa2_eth_connect_mac(struct return PTR_ERR(dpmac_dev); }

- if (IS_ERR(dpmac_dev) || dpmac_dev->dev.type != &fsl_mc_bus_dpmac_type) + if (IS_ERR(dpmac_dev)) return 0;

+ if (dpmac_dev->dev.type != &fsl_mc_bus_dpmac_type) { + err = 0; + goto out_put_device; + } + mac = kzalloc(sizeof(struct dpaa2_mac), GFP_KERNEL); - if (!mac) - return -ENOMEM; + if (!mac) { + err = -ENOMEM; + goto out_put_device; + }

mac->mc_dev = dpmac_dev; mac->mc_io = priv->mc_io; @@ -4694,6 +4701,8 @@ err_close_mac: dpaa2_mac_close(mac); err_free_mac: kfree(mac); +out_put_device: + put_device(&dpmac_dev->dev); return err; }

6.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Jacek Kowalski jacek@jacekk.info

commit 536fd741c7ac907d63166cdae1081b1febfab613 upstream.

As described by Vitaly Lifshits:

Starting from Tiger Lake, LAN NVM is locked for writes by SW, so the driver cannot perform checksum validation and correction. This means that all NVM images must leave the factory with correct checksum and checksum valid bit set. Since Tiger Lake devices were the first to have this lock, some systems in the field did not meet this requirement. Therefore, for these transitional devices we skip checksum update and verification, if the valid bit is not set.

Signed-off-by: Jacek Kowalski jacek@jacekk.info Reviewed-by: Simon Horman horms@kernel.org Reviewed-by: Vitaly Lifshits vitaly.lifshits@intel.com Fixes: 4051f68318ca9 ("e1000e: Do not take care about recovery NVM checksum") Cc: stable@vger.kernel.org Tested-by: Mor Bar-Gabay morx.bar.gabay@intel.com Signed-off-by: Tony Nguyen anthony.l.nguyen@intel.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/net/ethernet/intel/e1000e/ich8lan.c | 2 ++ 1 file changed, 2 insertions(+)

--- a/drivers/net/ethernet/intel/e1000e/ich8lan.c +++ b/drivers/net/ethernet/intel/e1000e/ich8lan.c @@ -4274,6 +4274,8 @@ static s32 e1000_validate_nvm_checksum_i ret_val = e1000e_update_nvm_checksum(hw); if (ret_val) return ret_val; + } else if (hw->mac.type == e1000_pch_tgp) { + return 0; } }

6.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Praveen Kaligineedi pkaligineedi@google.com

commit b03f15c0192b184078206760c839054ae6eb4eaa upstream.

gve_tx_timeout was calculating missed completions in a way that is only relevant in the GQ queue format. Additionally, it was attempting to disable device interrupts, which is not needed in either GQ or DQ queue formats.

As a result, TX timeouts with the DQ queue format likely would have triggered early resets without kicking the queue at all.

This patch drops the check for pending work altogether and always kicks the queue after validating the queue has not seen a TX timeout too recently.

Cc: stable@vger.kernel.org Fixes: 87a7f321bb6a ("gve: Recover from queue stall due to missed IRQ") Co-developed-by: Tim Hostetler thostet@google.com Signed-off-by: Tim Hostetler thostet@google.com Signed-off-by: Praveen Kaligineedi pkaligineedi@google.com Signed-off-by: Harshitha Ramamurthy hramamurthy@google.com Link: https://patch.msgid.link/20250717192024.1820931-1-hramamurthy@google.com Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/net/ethernet/google/gve/gve_main.c | 71 +++++++++++++++-------------- 1 file changed, 39 insertions(+), 32 deletions(-)

--- a/drivers/net/ethernet/google/gve/gve_main.c +++ b/drivers/net/ethernet/google/gve/gve_main.c @@ -1916,49 +1916,56 @@ static void gve_turnup_and_check_status( gve_handle_link_status(priv, GVE_DEVICE_STATUS_LINK_STATUS_MASK & status); }

-static void gve_tx_timeout(struct net_device *dev, unsigned int txqueue) +static struct gve_notify_block *gve_get_tx_notify_block(struct gve_priv *priv, + unsigned int txqueue) { - struct gve_notify_block *block; - struct gve_tx_ring *tx = NULL; - struct gve_priv *priv; - u32 last_nic_done; - u32 current_time; u32 ntfy_idx;

- netdev_info(dev, "Timeout on tx queue, %d", txqueue); - priv = netdev_priv(dev); if (txqueue > priv->tx_cfg.num_queues) - goto reset; + return NULL;

ntfy_idx = gve_tx_idx_to_ntfy(priv, txqueue); if (ntfy_idx >= priv->num_ntfy_blks) - goto reset; + return NULL; + + return &priv->ntfy_blocks[ntfy_idx]; +} + +static bool gve_tx_timeout_try_q_kick(struct gve_priv *priv, + unsigned int txqueue) +{ + struct gve_notify_block *block; + u32 current_time;

- block = &priv->ntfy_blocks[ntfy_idx]; - tx = block->tx; + block = gve_get_tx_notify_block(priv, txqueue); + + if (!block) + return false;

current_time = jiffies_to_msecs(jiffies); - if (tx->last_kick_msec + MIN_TX_TIMEOUT_GAP > current_time) - goto reset; + if (block->tx->last_kick_msec + MIN_TX_TIMEOUT_GAP > current_time) + return false; + + netdev_info(priv->dev, "Kicking queue %d", txqueue); + napi_schedule(&block->napi); + block->tx->last_kick_msec = current_time; + return true; +} + +static void gve_tx_timeout(struct net_device *dev, unsigned int txqueue) +{ + struct gve_notify_block *block; + struct gve_priv *priv; + + netdev_info(dev, "Timeout on tx queue, %d", txqueue); + priv = netdev_priv(dev); + + if (!gve_tx_timeout_try_q_kick(priv, txqueue)) + gve_schedule_reset(priv);

- /* Check to see if there are missed completions, which will allow us to - * kick the queue. - */ - last_nic_done = gve_tx_load_event_counter(priv, tx); - if (last_nic_done - tx->done) { - netdev_info(dev, "Kicking queue %d", txqueue); - iowrite32be(GVE_IRQ_MASK, gve_irq_doorbell(priv, block)); - napi_schedule(&block->napi); - tx->last_kick_msec = current_time; - goto out; - } // Else reset. - -reset: - gve_schedule_reset(priv); - -out: - if (tx) - tx->queue_timeout++; + block = gve_get_tx_notify_block(priv, txqueue); + if (block) + block->tx->queue_timeout++; priv->tx_timeo_cnt++; }

6.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Marco Elver elver@google.com

commit 6ade153349c6bb990d170cecc3e8bdd8628119ab upstream.

Since 6ee9b3d84775 ("kasan: remove kasan_find_vm_area() to prevent possible deadlock"), more detailed info about the vmalloc mapping and the origin was dropped due to potential deadlocks.

While fixing the deadlock is necessary, that patch was too quick in killing an otherwise useful feature, and did no due-diligence in understanding if an alternative option is available.

Restore printing more helpful vmalloc allocation info in KASAN reports with the help of vmalloc_dump_obj(). Example report:

| BUG: KASAN: vmalloc-out-of-bounds in vmalloc_oob+0x4c9/0x610 | Read of size 1 at addr ffffc900002fd7f3 by task kunit_try_catch/493 | | CPU: [...] | Call Trace: | <TASK> | dump_stack_lvl+0xa8/0xf0 | print_report+0x17e/0x810 | kasan_report+0x155/0x190 | vmalloc_oob+0x4c9/0x610 | [...] | | The buggy address belongs to a 1-page vmalloc region starting at 0xffffc900002fd000 allocated at vmalloc_oob+0x36/0x610 | The buggy address belongs to the physical page: | page: refcount:1 mapcount:0 mapping:0000000000000000 index:0x0 pfn:0x126364 | flags: 0x200000000000000(node=0|zone=2) | raw: 0200000000000000 0000000000000000 dead000000000122 0000000000000000 | raw: 0000000000000000 0000000000000000 00000001ffffffff 0000000000000000 | page dumped because: kasan: bad access detected | | [..]

Link: https://lkml.kernel.org/r/20250716152448.3877201-1-elver@google.com Fixes: 6ee9b3d84775 ("kasan: remove kasan_find_vm_area() to prevent possible deadlock") Signed-off-by: Marco Elver elver@google.com Suggested-by: Uladzislau Rezki urezki@gmail.com Acked-by: Uladzislau Rezki (Sony) urezki@gmail.com Cc: Alexander Potapenko glider@google.com Cc: Andrey Konovalov andreyknvl@gmail.com Cc: Andrey Ryabinin ryabinin.a.a@gmail.com Cc: Sebastian Andrzej Siewior bigeasy@linutronix.de Cc: Yeoreum Yun yeoreum.yun@arm.com Cc: Yunseong Kim ysk@kzalloc.com Cc: stable@vger.kernel.org Signed-off-by: Andrew Morton akpm@linux-foundation.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- mm/kasan/report.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-)

--- a/mm/kasan/report.c +++ b/mm/kasan/report.c @@ -399,7 +399,9 @@ static void print_address_description(vo }

if (is_vmalloc_addr(addr)) { - pr_err("The buggy address %px belongs to a vmalloc virtual mapping\n", addr); + pr_err("The buggy address belongs to a"); + if (!vmalloc_dump_obj(addr)) + pr_cont(" vmalloc virtual mapping\n"); page = vmalloc_to_page(addr); }

6.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Manivannan Sadhasivam manivannan.sadhasivam@linaro.org

commit 8c493cc91f3a1102ad2f8c75ae0cf80f0a057488 upstream.

If devicetree describes power supplies related to a PCI device, we unnecessarily created a pwrctrl device even if CONFIG_PCI_PWRCTL was not enabled.

We only need pci_pwrctrl_create_device() when CONFIG_PCI_PWRCTRL is enabled. Compile it out when CONFIG_PCI_PWRCTRL is not enabled.

When pci_pwrctrl_create_device() creates and returns a pwrctrl device, pci_scan_device() doesn't enumerate the PCI device. It assumes the pwrctrl core will rescan the bus after turning on the power. However, if CONFIG_PCI_PWRCTRL is not enabled, the rescan never happens, which breaks PCI enumeration on any system that describes power supplies in devicetree but does not use pwrctrl.

Jim reported that some brcmstb platforms break this way. The brcmstb driver is still broken if CONFIG_PCI_PWRCTRL is enabled, but this commit at least allows brcmstb to work when it's NOT enabled.

Fixes: 957f40d039a9 ("PCI/pwrctrl: Move creation of pwrctrl devices to pci_scan_device()") Reported-by: Jim Quinlan james.quinlan@broadcom.com Link: https://lore.kernel.org/r/CA+-6iNwgaByXEYD3j=-+H_PKAxXRU78svPMRHDKKci8AGXAUP... Signed-off-by: Manivannan Sadhasivam manivannan.sadhasivam@linaro.org [bhelgaas: commit log] Signed-off-by: Bjorn Helgaas bhelgaas@google.com Reviewed-by: Lukas Wunner lukas@wunner.de Cc: stable@vger.kernel.org # v6.15 Link: https://patch.msgid.link/20250701064731.52901-1-manivannan.sadhasivam@linaro... Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/pci/probe.c | 7 +++++++ 1 file changed, 7 insertions(+)

--- a/drivers/pci/probe.c +++ b/drivers/pci/probe.c @@ -2508,6 +2508,7 @@ bool pci_bus_read_dev_vendor_id(struct p } EXPORT_SYMBOL(pci_bus_read_dev_vendor_id);

+#if IS_ENABLED(CONFIG_PCI_PWRCTRL) static struct platform_device *pci_pwrctrl_create_device(struct pci_bus *bus, int devfn) { struct pci_host_bridge *host = pci_find_host_bridge(bus); @@ -2537,6 +2538,12 @@ static struct platform_device *pci_pwrct

return pdev; } +#else +static struct platform_device *pci_pwrctrl_create_device(struct pci_bus *bus, int devfn) +{ + return NULL; +} +#endif

/* * Read the config data for a PCI device, sanity-check it,

6.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Matthieu Baerts (NGI0) matttbe@kernel.org

commit 37848a456fc38c191aedfe41f662cc24db8c23d9 upstream.

The "mmap" and "sendfile" alternate modes for mptcp_connect.sh/.c are available from the beginning, but only tested when mptcp_connect.sh is manually launched with "-m mmap" or "-m sendfile", not via the kselftests helpers.

The MPTCP CI was manually running "mptcp_connect.sh -m mmap", but not "-m sendfile". Plus other CIs, especially the ones validating the stable releases, were not validating these alternate modes.

To make sure these modes are validated by these CIs, add two new test programs executing mptcp_connect.sh with the alternate modes.

Fixes: 048d19d444be ("mptcp: add basic kselftest for mptcp") Cc: stable@vger.kernel.org Reviewed-by: Geliang Tang geliang@kernel.org Signed-off-by: Matthieu Baerts (NGI0) matttbe@kernel.org Link: https://patch.msgid.link/20250715-net-mptcp-sft-connect-alt-v2-1-8230ddd8245... Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- tools/testing/selftests/net/mptcp/Makefile | 3 ++- tools/testing/selftests/net/mptcp/mptcp_connect_mmap.sh | 5 +++++ tools/testing/selftests/net/mptcp/mptcp_connect_sendfile.sh | 5 +++++ 3 files changed, 12 insertions(+), 1 deletion(-) create mode 100755 tools/testing/selftests/net/mptcp/mptcp_connect_mmap.sh create mode 100755 tools/testing/selftests/net/mptcp/mptcp_connect_sendfile.sh

--- a/tools/testing/selftests/net/mptcp/Makefile +++ b/tools/testing/selftests/net/mptcp/Makefile @@ -4,7 +4,8 @@ top_srcdir = ../../../../..

CFLAGS += -Wall -Wl,--no-as-needed -O2 -g -I$(top_srcdir)/usr/include $(KHDR_INCLUDES)

-TEST_PROGS := mptcp_connect.sh pm_netlink.sh mptcp_join.sh diag.sh \ +TEST_PROGS := mptcp_connect.sh mptcp_connect_mmap.sh mptcp_connect_sendfile.sh \ + pm_netlink.sh mptcp_join.sh diag.sh \ simult_flows.sh mptcp_sockopt.sh userspace_pm.sh

TEST_GEN_FILES = mptcp_connect pm_nl_ctl mptcp_sockopt mptcp_inq mptcp_diag --- /dev/null +++ b/tools/testing/selftests/net/mptcp/mptcp_connect_mmap.sh @@ -0,0 +1,5 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +MPTCP_LIB_KSFT_TEST="$(basename "${0}" .sh)" \ + "$(dirname "${0}")/mptcp_connect.sh" -m mmap "${@}" --- /dev/null +++ b/tools/testing/selftests/net/mptcp/mptcp_connect_sendfile.sh @@ -0,0 +1,5 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +MPTCP_LIB_KSFT_TEST="$(basename "${0}" .sh)" \ + "$(dirname "${0}")/mptcp_connect.sh" -m sendfile "${@}"

6.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Zi Yan ziy@nvidia.com

commit 7563fcbfd484b347b776aeed4d7dac78b30884aa upstream.

PID_FMT does not have an offset field, so folio_split() tests are not performed. Add PID_FMT_OFFSET with an offset field and use it to perform folio_split() tests.

Link: https://lkml.kernel.org/r/20250709012800.3225727-1-ziy@nvidia.com Fixes: 80a5c494c89f ("selftests/mm: add tests for folio_split(), buddy allocator like split") Signed-off-by: Zi Yan ziy@nvidia.com Tested-by: Baolin Wang baolin.wang@linux.alibaba.com Reviewed-by: Lorenzo Stoakes lorenzo.stoakes@oracle.com Reviewed-by: Donet Tom donettom@linux.ibm.com Tested-by : Donet Tom donettom@linux.ibm.com Cc: Barry Song baohua@kernel.org Cc: David Hildenbrand david@redhat.com Cc: Dev Jain dev.jain@arm.com Cc: Liam Howlett liam.howlett@oracle.com Cc: Mariano Pache npache@redhat.com Cc: Ryan Roberts ryan.roberts@arm.com Cc: Shuah Khan shuah@kernel.org Cc: stable@vger.kernel.org Signed-off-by: Andrew Morton akpm@linux-foundation.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- tools/testing/selftests/mm/split_huge_page_test.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/tools/testing/selftests/mm/split_huge_page_test.c b/tools/testing/selftests/mm/split_huge_page_test.c index aa7400ed0e99..f0d9c035641d 100644 --- a/tools/testing/selftests/mm/split_huge_page_test.c +++ b/tools/testing/selftests/mm/split_huge_page_test.c @@ -31,6 +31,7 @@ uint64_t pmd_pagesize; #define INPUT_MAX 80

#define PID_FMT "%d,0x%lx,0x%lx,%d" +#define PID_FMT_OFFSET "%d,0x%lx,0x%lx,%d,%d" #define PATH_FMT "%s,0x%lx,0x%lx,%d"

#define PFN_MASK ((1UL<<55)-1) @@ -483,7 +484,7 @@ void split_thp_in_pagecache_to_order_at(size_t fd_size, const char *fs_loc, write_debugfs(PID_FMT, getpid(), (uint64_t)addr, (uint64_t)addr + fd_size, order); else - write_debugfs(PID_FMT, getpid(), (uint64_t)addr, + write_debugfs(PID_FMT_OFFSET, getpid(), (uint64_t)addr, (uint64_t)addr + fd_size, order, offset);

for (i = 0; i < fd_size; i++)

6.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Harry Yoo harry.yoo@oracle.com

commit 694d6b99923eb05a8fd188be44e26077d19f0e21 upstream.

Commit 48b4800a1c6a ("zsmalloc: page migration support") added support for migrating zsmalloc pages using the movable_operations migration framework. However, the commit did not take into account that zsmalloc supports migration only when CONFIG_COMPACTION is enabled. Tracing shows that zsmalloc was still passing the __GFP_MOVABLE flag even when compaction is not supported.

This can result in unmovable pages being allocated from movable page blocks (even without stealing page blocks), ZONE_MOVABLE and CMA area.

Possible user visible effects: - Some ZONE_MOVABLE memory can be not actually movable - CMA allocation can fail because of this - Increased memory fragmentation due to ignoring the page mobility grouping feature I'm not really sure who uses kernels without compaction support, though :(

To fix this, clear the __GFP_MOVABLE flag when !IS_ENABLED(CONFIG_COMPACTION).

Link: https://lkml.kernel.org/r/20250704103053.6913-1-harry.yoo@oracle.com Fixes: 48b4800a1c6a ("zsmalloc: page migration support") Signed-off-by: Harry Yoo harry.yoo@oracle.com Acked-by: David Hildenbrand david@redhat.com Reviewed-by: Sergey Senozhatsky senozhatsky@chromium.org Cc: Minchan Kim minchan@kernel.org Cc: stable@vger.kernel.org Signed-off-by: Andrew Morton akpm@linux-foundation.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- mm/zsmalloc.c | 3 +++ 1 file changed, 3 insertions(+)

--- a/mm/zsmalloc.c +++ b/mm/zsmalloc.c @@ -1053,6 +1053,9 @@ static struct zspage *alloc_zspage(struc if (!zspage) return NULL;

+ if (!IS_ENABLED(CONFIG_COMPACTION)) + gfp &= ~__GFP_MOVABLE; + zspage->magic = ZSPAGE_MAGIC; zspage->pool = pool; zspage->class = class->index;

6.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Matthew Brost matthew.brost@intel.com

commit afcad92411772a1f361339f22c49f855c6cc7d0f upstream.

No idea why, but without this GuC context switches randomly fail when running IGTs in a loop. Need to follow up why this fixes the aforementioned issue but can live with a stable driver for now.

Fixes: 617d824c5323 ("drm/xe: Add WA BB to capture active context utilization") Cc: stable@vger.kernel.org Signed-off-by: Matthew Brost matthew.brost@intel.com Reviewed-by: Lucas De Marchi lucas.demarchi@intel.com Tested-by: Shuicheng Lin shuicheng.lin@intel.com Link: https://lore.kernel.org/r/20250612031925.4009701-1-matthew.brost@intel.com (cherry picked from commit 3a1edef8f4b58b0ba826bc68bf4bce4bdf59ecf3) Signed-off-by: Lucas De Marchi lucas.demarchi@intel.com [ adapted xe_bo_create_pin_map() call ] Signed-off-by: Sasha Levin sashal@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/gpu/drm/xe/xe_lrc.c | 37 +++++++++++++++++++------------------ drivers/gpu/drm/xe/xe_lrc_types.h | 3 --- 2 files changed, 19 insertions(+), 21 deletions(-)

--- a/drivers/gpu/drm/xe/xe_lrc.c +++ b/drivers/gpu/drm/xe/xe_lrc.c @@ -39,6 +39,7 @@ #define LRC_ENGINE_INSTANCE GENMASK_ULL(53, 48)

#define LRC_INDIRECT_RING_STATE_SIZE SZ_4K +#define LRC_WA_BB_SIZE SZ_4K

static struct xe_device * lrc_to_xe(struct xe_lrc *lrc) @@ -910,7 +911,11 @@ static void xe_lrc_finish(struct xe_lrc xe_bo_unpin(lrc->bo); xe_bo_unlock(lrc->bo); xe_bo_put(lrc->bo); - xe_bo_unpin_map_no_vm(lrc->bb_per_ctx_bo); +} + +static size_t wa_bb_offset(struct xe_lrc *lrc) +{ + return lrc->bo->size - LRC_WA_BB_SIZE; }

/* @@ -943,15 +948,16 @@ static void xe_lrc_finish(struct xe_lrc #define CONTEXT_ACTIVE 1ULL static int xe_lrc_setup_utilization(struct xe_lrc *lrc) { + const size_t max_size = LRC_WA_BB_SIZE; u32 *cmd, *buf = NULL;

- if (lrc->bb_per_ctx_bo->vmap.is_iomem) { - buf = kmalloc(lrc->bb_per_ctx_bo->size, GFP_KERNEL); + if (lrc->bo->vmap.is_iomem) { + buf = kmalloc(max_size, GFP_KERNEL); if (!buf) return -ENOMEM; cmd = buf; } else { - cmd = lrc->bb_per_ctx_bo->vmap.vaddr; + cmd = lrc->bo->vmap.vaddr + wa_bb_offset(lrc); }

*cmd++ = MI_STORE_REGISTER_MEM | MI_SRM_USE_GGTT | MI_SRM_ADD_CS_OFFSET; @@ -974,13 +980,14 @@ static int xe_lrc_setup_utilization(stru *cmd++ = MI_BATCH_BUFFER_END;

if (buf) { - xe_map_memcpy_to(gt_to_xe(lrc->gt), &lrc->bb_per_ctx_bo->vmap, 0, - buf, (cmd - buf) * sizeof(*cmd)); + xe_map_memcpy_to(gt_to_xe(lrc->gt), &lrc->bo->vmap, + wa_bb_offset(lrc), buf, + (cmd - buf) * sizeof(*cmd)); kfree(buf); }

- xe_lrc_write_ctx_reg(lrc, CTX_BB_PER_CTX_PTR, - xe_bo_ggtt_addr(lrc->bb_per_ctx_bo) | 1); + xe_lrc_write_ctx_reg(lrc, CTX_BB_PER_CTX_PTR, xe_bo_ggtt_addr(lrc->bo) + + wa_bb_offset(lrc) + 1);

return 0; } @@ -1016,20 +1023,13 @@ static int xe_lrc_init(struct xe_lrc *lr * FIXME: Perma-pinning LRC as we don't yet support moving GGTT address * via VM bind calls. */ - lrc->bo = xe_bo_create_pin_map(xe, tile, vm, lrc_size, + lrc->bo = xe_bo_create_pin_map(xe, tile, vm, + lrc_size + LRC_WA_BB_SIZE, ttm_bo_type_kernel, bo_flags); if (IS_ERR(lrc->bo)) return PTR_ERR(lrc->bo);

- lrc->bb_per_ctx_bo = xe_bo_create_pin_map(xe, tile, NULL, SZ_4K, - ttm_bo_type_kernel, - bo_flags); - if (IS_ERR(lrc->bb_per_ctx_bo)) { - err = PTR_ERR(lrc->bb_per_ctx_bo); - goto err_lrc_finish; - } - lrc->size = lrc_size; lrc->ring.size = ring_size; lrc->ring.tail = 0; @@ -1819,7 +1819,8 @@ struct xe_lrc_snapshot *xe_lrc_snapshot_ snapshot->seqno = xe_lrc_seqno(lrc); snapshot->lrc_bo = xe_bo_get(lrc->bo); snapshot->lrc_offset = xe_lrc_pphwsp_offset(lrc); - snapshot->lrc_size = lrc->bo->size - snapshot->lrc_offset; + snapshot->lrc_size = lrc->bo->size - snapshot->lrc_offset - + LRC_WA_BB_SIZE; snapshot->lrc_snapshot = NULL; snapshot->ctx_timestamp = lower_32_bits(xe_lrc_ctx_timestamp(lrc)); snapshot->ctx_job_timestamp = xe_lrc_ctx_job_timestamp(lrc); --- a/drivers/gpu/drm/xe/xe_lrc_types.h +++ b/drivers/gpu/drm/xe/xe_lrc_types.h @@ -53,9 +53,6 @@ struct xe_lrc {

/** @ctx_timestamp: readout value of CTX_TIMESTAMP on last update */ u64 ctx_timestamp; - - /** @bb_per_ctx_bo: buffer object for per context batch wa buffer */ - struct xe_bo *bb_per_ctx_bo; };

struct xe_lrc_snapshot;

6.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Jesse.zhang@amd.com Jesse.zhang@amd.com

commit 5c3e7c49538e2ddad10296a318c225bbb3d37d20 upstream.

This patch introduces a new function `amdgpu_sdma_soft_reset` to handle SDMA soft resets directly, rather than relying on the DPM interface.

1. **New `amdgpu_sdma_soft_reset` Function**: - Implements a soft reset for SDMA engines by directly writing to the hardware registers. - Handles SDMA versions 4.x and 5.x separately: - For SDMA 4.x, the existing `amdgpu_dpm_reset_sdma` function is used for backward compatibility. - For SDMA 5.x, the driver directly manipulates the `GRBM_SOFT_RESET` register to reset the specified SDMA instance.

2. **Integration into `amdgpu_sdma_reset_engine`**: - The `amdgpu_sdma_soft_reset` function is called during the SDMA reset process, replacing the previous call to `amdgpu_dpm_reset_sdma`.

v2: r should default to an error (Alex)

Suggested-by: Alex Deucher alexander.deucher@amd.com Signed-off-by: Jesse Zhang jesse.zhang@amd.com Reviewed-by: Alex Deucher alexander.deucher@amd.com Signed-off-by: Alex Deucher alexander.deucher@amd.com Stable-dep-of: 09b585592fa4 ("drm/amdgpu: Fix SDMA engine reset with logical instance ID") Signed-off-by: Sasha Levin sashal@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.c | 38 ++++++++++++++++++++++++++++++- 1 file changed, 37 insertions(+), 1 deletion(-)

--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.c @@ -26,6 +26,8 @@ #include "amdgpu_sdma.h" #include "amdgpu_ras.h" #include "amdgpu_reset.h" +#include "gc/gc_10_1_0_offset.h" +#include "gc/gc_10_3_0_sh_mask.h"

#define AMDGPU_CSA_SDMA_SIZE 64 /* SDMA CSA reside in the 3rd page of CSA */ @@ -561,6 +563,40 @@ void amdgpu_sdma_register_on_reset_callb list_add_tail(&funcs->list, &adev->sdma.reset_callback_list); }

+static int amdgpu_sdma_soft_reset(struct amdgpu_device *adev, u32 instance_id) +{ + struct amdgpu_sdma_instance *sdma_instance = &adev->sdma.instance[instance_id]; + int r = -EOPNOTSUPP; + + switch (amdgpu_ip_version(adev, SDMA0_HWIP, 0)) { + case IP_VERSION(4, 4, 2): + case IP_VERSION(4, 4, 4): + case IP_VERSION(4, 4, 5): + /* For SDMA 4.x, use the existing DPM interface for backward compatibility */ + r = amdgpu_dpm_reset_sdma(adev, 1 << instance_id); + break; + case IP_VERSION(5, 0, 0): + case IP_VERSION(5, 0, 1): + case IP_VERSION(5, 0, 2): + case IP_VERSION(5, 0, 5): + case IP_VERSION(5, 2, 0): + case IP_VERSION(5, 2, 2): + case IP_VERSION(5, 2, 4): + case IP_VERSION(5, 2, 5): + case IP_VERSION(5, 2, 6): + case IP_VERSION(5, 2, 3): + case IP_VERSION(5, 2, 1): + case IP_VERSION(5, 2, 7): + if (sdma_instance->funcs->soft_reset_kernel_queue) + r = sdma_instance->funcs->soft_reset_kernel_queue(adev, instance_id); + break; + default: + break; + } + + return r; +} + /** * amdgpu_sdma_reset_engine - Reset a specific SDMA engine * @adev: Pointer to the AMDGPU device @@ -611,7 +647,7 @@ int amdgpu_sdma_reset_engine(struct amdg }

/* Perform the SDMA reset for the specified instance */ - ret = amdgpu_dpm_reset_sdma(adev, 1 << instance_id); + ret = amdgpu_sdma_soft_reset(adev, instance_id); if (ret) { dev_err(adev->dev, "Failed to reset SDMA instance %u\n", instance_id); goto exit;

6.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Dmitry Osipenko dmitry.osipenko@collabora.com

commit eab10538073c3ff9e21c857bd462f79f2f6f7e00 upstream.

Everything that uses the mapped buffer should be agnostic to is_iomem. The only reason for the is_iomem test is that we're setting shmem->vaddr to the returned map->vaddr. Now that the shmem->vaddr code is gone, remove the obsoleted is_iomem test to clean up the code.

Acked-by: Maxime Ripard mripard@kernel.org Suggested-by: Thomas Zimmermann tzimmermann@suse.de Reviewed-by: Boris Brezillon boris.brezillon@collabora.com Acked-by: Thomas Zimmermann tzimmermann@suse.d Signed-off-by: Dmitry Osipenko dmitry.osipenko@collabora.com Link: https://patchwork.freedesktop.org/patch/msgid/20250322212608.40511-7-dmitry.... Stable-dep-of: 6d496e956998 ("Revert "drm/gem-shmem: Use dma_buf from GEM object instance"") Signed-off-by: Sasha Levin sashal@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/gpu/drm/drm_gem_shmem_helper.c | 6 ------ 1 file changed, 6 deletions(-)

--- a/drivers/gpu/drm/drm_gem_shmem_helper.c +++ b/drivers/gpu/drm/drm_gem_shmem_helper.c @@ -340,12 +340,6 @@ int drm_gem_shmem_vmap(struct drm_gem_sh

if (drm_gem_is_imported(obj)) { ret = dma_buf_vmap(obj->dma_buf, map); - if (!ret) { - if (drm_WARN_ON(obj->dev, map->is_iomem)) { - dma_buf_vunmap(obj->dma_buf, map); - return -EIO; - } - } } else { pgprot_t prot = PAGE_KERNEL;

6.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Michael Grzeschik m.grzeschik@pengutronix.de

commit 64843d0ba96d3eae297025562111d57585273366 upstream.

Since the function tcpm_acc_attach is not setting the data and role for for the sink case we extend it to check for it first.

Signed-off-by: Michael Grzeschik m.grzeschik@pengutronix.de Reviewed-by: Heikki Krogerus heikki.krogerus@linux.intel.com Link: https://lore.kernel.org/r/20250404-ml-topic-tcpm-v1-1-b99f44badce8@pengutron... Stable-dep-of: bec15191d523 ("usb: typec: tcpm: apply vbus before data bringup in tcpm_src_attach") Signed-off-by: Sasha Levin sashal@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/usb/typec/tcpm/tcpm.c | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-)

--- a/drivers/usb/typec/tcpm/tcpm.c +++ b/drivers/usb/typec/tcpm/tcpm.c @@ -4602,12 +4602,17 @@ static void tcpm_snk_detach(struct tcpm_ static int tcpm_acc_attach(struct tcpm_port *port) { int ret; + enum typec_role role; + enum typec_data_role data;

if (port->attached) return 0;

- ret = tcpm_set_roles(port, true, TYPEC_SOURCE, - tcpm_data_role_for_source(port)); + role = tcpm_port_is_sink(port) ? TYPEC_SINK : TYPEC_SOURCE; + data = tcpm_port_is_sink(port) ? tcpm_data_role_for_sink(port) + : tcpm_data_role_for_source(port); + + ret = tcpm_set_roles(port, true, role, data); if (ret < 0) return ret;

6.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: RD Babiera rdbabiera@google.com

commit bec15191d52300defa282e3fd83820f69e447116 upstream.

This patch fixes Type-C compliance test TD 4.7.6 - Try.SNK DRP Connect SNKAS.

tVbusON has a limit of 275ms when entering SRC_ATTACHED. Compliance testers can interpret the TryWait.Src to Attached.Src transition after Try.Snk as being in Attached.Src the entire time, so ~170ms is lost to the debounce timer.

Setting the data role can be a costly operation in host mode, and when completed after 100ms can cause Type-C compliance test check TD 4.7.5.V.4 to fail.

Turn VBUS on before tcpm_set_roles to meet timing requirement.

Fixes: f0690a25a140 ("staging: typec: USB Type-C Port Manager (tcpm)") Cc: stable stable@kernel.org Signed-off-by: RD Babiera rdbabiera@google.com Reviewed-by: Badhri Jagan Sridharan badhri@google.com Reviewed-by: Heikki Krogerus heikki.krogerus@linux.intel.com Link: https://lore.kernel.org/r/20250618230606.3272497-2-rdbabiera@google.com Signed-off-by: Sasha Levin sashal@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/usb/typec/tcpm/tcpm.c | 34 +++++++++++++++++----------------- 1 file changed, 17 insertions(+), 17 deletions(-)

--- a/drivers/usb/typec/tcpm/tcpm.c +++ b/drivers/usb/typec/tcpm/tcpm.c @@ -4404,17 +4404,6 @@ static int tcpm_src_attach(struct tcpm_p

tcpm_enable_auto_vbus_discharge(port, true);

- ret = tcpm_set_roles(port, true, TYPEC_STATE_USB, - TYPEC_SOURCE, tcpm_data_role_for_source(port)); - if (ret < 0) - return ret; - - if (port->pd_supported) { - ret = port->tcpc->set_pd_rx(port->tcpc, true); - if (ret < 0) - goto out_disable_mux; - } - /* * USB Type-C specification, version 1.2, * chapter 4.5.2.2.8.1 (Attached.SRC Requirements) @@ -4424,13 +4413,24 @@ static int tcpm_src_attach(struct tcpm_p (polarity == TYPEC_POLARITY_CC2 && port->cc1 == TYPEC_CC_RA)) { ret = tcpm_set_vconn(port, true); if (ret < 0) - goto out_disable_pd; + return ret; }

ret = tcpm_set_vbus(port, true); if (ret < 0) goto out_disable_vconn;

+ ret = tcpm_set_roles(port, true, TYPEC_STATE_USB, TYPEC_SOURCE, + tcpm_data_role_for_source(port)); + if (ret < 0) + goto out_disable_vbus; + + if (port->pd_supported) { + ret = port->tcpc->set_pd_rx(port->tcpc, true); + if (ret < 0) + goto out_disable_mux; + } + port->pd_capable = false;

port->partner = NULL; @@ -4441,14 +4441,14 @@ static int tcpm_src_attach(struct tcpm_p

return 0;

-out_disable_vconn: - tcpm_set_vconn(port, false); -out_disable_pd: - if (port->pd_supported) - port->tcpc->set_pd_rx(port->tcpc, false); out_disable_mux: tcpm_mux_set(port, TYPEC_STATE_SAFE, USB_ROLE_NONE, TYPEC_ORIENTATION_NONE); +out_disable_vbus: + tcpm_set_vbus(port, false); +out_disable_vconn: + tcpm_set_vconn(port, false); + return ret; }

6.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Mohan Kumar D mkumard@nvidia.com

commit 1c4193917eb3279788968639f24d72ffeebdec6b upstream.

Update HDA driver to support Tegra264 differences from legacy HDA, which includes: clocks/resets, always power on, and hardware-managed FPCI/IPFS initialization. The driver retrieves this chip-specific information from soc_data.

Signed-off-by: Mohan Kumar D mkumard@nvidia.com Signed-off-by: Sheetal sheetal@nvidia.com Signed-off-by: Takashi Iwai tiwai@suse.de Link: https://patch.msgid.link/20250512064258.1028331-4-sheetal@nvidia.com Stable-dep-of: e0a911ac8685 ("ALSA: hda: Add missing NVIDIA HDA codec IDs") Signed-off-by: Sasha Levin sashal@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- sound/pci/hda/hda_tegra.c | 51 +++++++++++++++++++++++++++++++++++++++------ sound/pci/hda/patch_hdmi.c | 1 2 files changed, 46 insertions(+), 6 deletions(-)

--- a/sound/pci/hda/hda_tegra.c +++ b/sound/pci/hda/hda_tegra.c @@ -72,6 +72,10 @@ struct hda_tegra_soc { bool has_hda2codec_2x_reset; bool has_hda2hdmi; + bool has_hda2codec_2x; + bool input_stream; + bool always_on; + bool requires_init; };

struct hda_tegra { @@ -187,7 +191,9 @@ static int hda_tegra_runtime_resume(stru if (rc != 0) return rc; if (chip->running) { - hda_tegra_init(hda); + if (hda->soc->requires_init) + hda_tegra_init(hda); + azx_init_chip(chip, 1); /* disable controller wake up event*/ azx_writew(chip, WAKEEN, azx_readw(chip, WAKEEN) & @@ -250,7 +256,8 @@ static int hda_tegra_init_chip(struct az bus->remap_addr = hda->regs + HDA_BAR0; bus->addr = res->start + HDA_BAR0;

- hda_tegra_init(hda); + if (hda->soc->requires_init) + hda_tegra_init(hda);

return 0; } @@ -323,7 +330,7 @@ static int hda_tegra_first_init(struct a * starts with offset 0 which is wrong as HW register for output stream * offset starts with 4. */ - if (of_device_is_compatible(np, "nvidia,tegra234-hda")) + if (!hda->soc->input_stream) chip->capture_streams = 4;

chip->playback_streams = (gcap >> 12) & 0x0f; @@ -419,7 +426,6 @@ static int hda_tegra_create(struct snd_c chip->driver_caps = driver_caps; chip->driver_type = driver_caps & 0xff; chip->dev_index = 0; - chip->jackpoll_interval = msecs_to_jiffies(5000); INIT_LIST_HEAD(&chip->pcm_list);

chip->codec_probe_mask = -1; @@ -436,7 +442,16 @@ static int hda_tegra_create(struct snd_c chip->bus.core.sync_write = 0; chip->bus.core.needs_damn_long_delay = 1; chip->bus.core.aligned_mmio = 1; - chip->bus.jackpoll_in_suspend = 1; + + /* + * HDA power domain and clocks are always on for Tegra264 and + * the jack detection logic would work always, so no need of + * jack polling mechanism running. + */ + if (!hda->soc->always_on) { + chip->jackpoll_interval = msecs_to_jiffies(5000); + chip->bus.jackpoll_in_suspend = 1; + }

err = snd_device_new(card, SNDRV_DEV_LOWLEVEL, chip, &ops); if (err < 0) { @@ -450,22 +465,44 @@ static int hda_tegra_create(struct snd_c static const struct hda_tegra_soc tegra30_data = { .has_hda2codec_2x_reset = true, .has_hda2hdmi = true, + .has_hda2codec_2x = true, + .input_stream = true, + .always_on = false, + .requires_init = true, };

static const struct hda_tegra_soc tegra194_data = { .has_hda2codec_2x_reset = false, .has_hda2hdmi = true, + .has_hda2codec_2x = true, + .input_stream = true, + .always_on = false, + .requires_init = true, };

static const struct hda_tegra_soc tegra234_data = { .has_hda2codec_2x_reset = true, .has_hda2hdmi = false, + .has_hda2codec_2x = true, + .input_stream = false, + .always_on = false, + .requires_init = true, +}; + +static const struct hda_tegra_soc tegra264_data = { + .has_hda2codec_2x_reset = true, + .has_hda2hdmi = false, + .has_hda2codec_2x = false, + .input_stream = false, + .always_on = true, + .requires_init = false, };

static const struct of_device_id hda_tegra_match[] = { { .compatible = "nvidia,tegra30-hda", .data = &tegra30_data }, { .compatible = "nvidia,tegra194-hda", .data = &tegra194_data }, { .compatible = "nvidia,tegra234-hda", .data = &tegra234_data }, + { .compatible = "nvidia,tegra264-hda", .data = &tegra264_data }, {}, }; MODULE_DEVICE_TABLE(of, hda_tegra_match); @@ -520,7 +557,9 @@ static int hda_tegra_probe(struct platfo hda->clocks[hda->nclocks++].id = "hda"; if (hda->soc->has_hda2hdmi) hda->clocks[hda->nclocks++].id = "hda2hdmi"; - hda->clocks[hda->nclocks++].id = "hda2codec_2x"; + + if (hda->soc->has_hda2codec_2x) + hda->clocks[hda->nclocks++].id = "hda2codec_2x";

err = devm_clk_bulk_get(&pdev->dev, hda->nclocks, hda->clocks); if (err < 0) --- a/sound/pci/hda/patch_hdmi.c +++ b/sound/pci/hda/patch_hdmi.c @@ -4551,6 +4551,7 @@ HDA_CODEC_ENTRY(0x10de002e, "Tegra186 HD HDA_CODEC_ENTRY(0x10de002f, "Tegra194 HDMI/DP2", patch_tegra_hdmi), HDA_CODEC_ENTRY(0x10de0030, "Tegra194 HDMI/DP3", patch_tegra_hdmi), HDA_CODEC_ENTRY(0x10de0031, "Tegra234 HDMI/DP", patch_tegra234_hdmi), +HDA_CODEC_ENTRY(0x10de0034, "Tegra264 HDMI/DP", patch_tegra234_hdmi), HDA_CODEC_ENTRY(0x10de0040, "GPU 40 HDMI/DP", patch_nvhdmi), HDA_CODEC_ENTRY(0x10de0041, "GPU 41 HDMI/DP", patch_nvhdmi), HDA_CODEC_ENTRY(0x10de0042, "GPU 42 HDMI/DP", patch_nvhdmi),