From: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
To: linux-kernel@vger.kernel.org, akpm@linux-foundation.org,
torvalds@linux-foundation.org, stable@vger.kernel.org
Cc: lwn@lwn.net, jslaby@suse.cz,
Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Subject: Re: Linux 6.12.104
Date: Wed, 19 Aug 2026 18:52:17 +0200 [thread overview]
Message-ID: <2026081916-platform-come-496e@gregkh> (raw)
In-Reply-To: <2026081916-radiance-plenty-88b6@gregkh>
diff --git a/Documentation/devicetree/bindings/crypto/qcom,inline-crypto-engine.yaml b/Documentation/devicetree/bindings/crypto/qcom,inline-crypto-engine.yaml
index 0304f074cf08..2793afc7f85c 100644
--- a/Documentation/devicetree/bindings/crypto/qcom,inline-crypto-engine.yaml
+++ b/Documentation/devicetree/bindings/crypto/qcom,inline-crypto-engine.yaml
@@ -25,6 +25,16 @@ properties:
maxItems: 1
clocks:
+ minItems: 1
+ maxItems: 2
+
+ clock-names:
+ minItems: 1
+ items:
+ - const: core
+ - const: iface
+
+ power-domains:
maxItems: 1
required:
@@ -42,6 +52,10 @@ examples:
compatible = "qcom,sm8550-inline-crypto-engine",
"qcom,inline-crypto-engine";
reg = <0x01d88000 0x8000>;
- clocks = <&gcc GCC_UFS_PHY_ICE_CORE_CLK>;
+ clocks = <&gcc GCC_UFS_PHY_ICE_CORE_CLK>,
+ <&gcc GCC_UFS_PHY_AHB_CLK>;
+ clock-names = "core",
+ "iface";
+ power-domains = <&gcc UFS_PHY_GDSC>;
};
...
diff --git a/MAINTAINERS b/MAINTAINERS
index d765c62c80ea..d5d394a5ad6b 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -8849,6 +8849,11 @@ F: drivers/base/firmware_loader/
F: rust/kernel/firmware.rs
F: include/linux/firmware.h
+FIXED-LAYOUT NVMEM LAYOUT DRIVER
+M: Mathieu Dubois-Briand <mathieu.dubois-briand@bootlin.com>
+S: Maintained
+F: drivers/nvmem/layouts/fixed-layout.c
+
FLEXTIMER FTM-QUADDEC DRIVER
M: Patrick Havelange <patrick.havelange@essensium.com>
L: linux-iio@vger.kernel.org
diff --git a/Makefile b/Makefile
index f3bacdc021a4..69eb37d9d488 100644
--- a/Makefile
+++ b/Makefile
@@ -1,7 +1,7 @@
# SPDX-License-Identifier: GPL-2.0
VERSION = 6
PATCHLEVEL = 12
-SUBLEVEL = 103
+SUBLEVEL = 104
EXTRAVERSION =
NAME = Baby Opossum Posse
diff --git a/arch/arm/boot/dts/broadcom/bcm-ns.dtsi b/arch/arm/boot/dts/broadcom/bcm-ns.dtsi
index d0d5f7e52a91..f08d0a27de0b 100644
--- a/arch/arm/boot/dts/broadcom/bcm-ns.dtsi
+++ b/arch/arm/boot/dts/broadcom/bcm-ns.dtsi
@@ -138,7 +138,7 @@ axi@18000000 {
/* PCIe Controller 2 */
<0x00014000 0 &gic GIC_SPI 138 IRQ_TYPE_LEVEL_HIGH>,
- <0x00014000 1 &gic GIC_SPI 138 IRQ_TYPE_LEVEL_HIGH>,
+ <0x00014000 1 &gic GIC_SPI 139 IRQ_TYPE_LEVEL_HIGH>,
<0x00014000 2 &gic GIC_SPI 140 IRQ_TYPE_LEVEL_HIGH>,
<0x00014000 3 &gic GIC_SPI 141 IRQ_TYPE_LEVEL_HIGH>,
<0x00014000 4 &gic GIC_SPI 142 IRQ_TYPE_LEVEL_HIGH>,
diff --git a/arch/arm/mach-npcm/platsmp.c b/arch/arm/mach-npcm/platsmp.c
index 41891d3aa124..4c1fc9983746 100644
--- a/arch/arm/mach-npcm/platsmp.c
+++ b/arch/arm/mach-npcm/platsmp.c
@@ -32,6 +32,7 @@ static int npcm7xx_smp_boot_secondary(unsigned int cpu,
goto out;
}
gcr_base = of_iomap(gcr_np, 0);
+ of_node_put(gcr_np);
if (!gcr_base) {
pr_err("could not iomap gcr");
ret = -ENOMEM;
@@ -60,6 +61,7 @@ static void __init npcm7xx_smp_prepare_cpus(unsigned int max_cpus)
return;
}
scu_base = of_iomap(scu_np, 0);
+ of_node_put(scu_np);
if (!scu_base) {
pr_err("could not iomap scu");
return;
diff --git a/arch/arm64/boot/dts/broadcom/bcm2712.dtsi b/arch/arm64/boot/dts/broadcom/bcm2712.dtsi
index 209f99b1ceae..c8e809d77b3f 100644
--- a/arch/arm64/boot/dts/broadcom/bcm2712.dtsi
+++ b/arch/arm64/boot/dts/broadcom/bcm2712.dtsi
@@ -279,8 +279,6 @@ IRQ_TYPE_LEVEL_LOW)>,
<GIC_PPI 11 (GIC_CPU_MASK_SIMPLE(4) |
IRQ_TYPE_LEVEL_LOW)>,
<GIC_PPI 10 (GIC_CPU_MASK_SIMPLE(4) |
- IRQ_TYPE_LEVEL_LOW)>,
- <GIC_PPI 12 (GIC_CPU_MASK_SIMPLE(4) |
IRQ_TYPE_LEVEL_LOW)>;
};
};
diff --git a/arch/s390/kvm/pci.c b/arch/s390/kvm/pci.c
index 17fedfc7bb99..d9fcbf41025e 100644
--- a/arch/s390/kvm/pci.c
+++ b/arch/s390/kvm/pci.c
@@ -167,7 +167,7 @@ static int kvm_zpci_set_airq(struct zpci_dev *zdev)
fib.fmt0.noi = airq_iv_end(zdev->aibv);
fib.fmt0.aibv = virt_to_phys(zdev->aibv->vector);
fib.fmt0.aibvo = 0;
- fib.fmt0.aisb = virt_to_phys(aift->sbv->vector + (zdev->aisb / 64) * 8);
+ fib.fmt0.aisb = virt_to_phys(aift->sbv->vector) + (zdev->aisb / 64) * 8;
fib.fmt0.aisbo = zdev->aisb & 63;
fib.gd = zdev->gisa;
@@ -191,34 +191,54 @@ static int kvm_zpci_clear_airq(struct zpci_dev *zdev)
return cc ? -EIO : 0;
}
-static inline void unaccount_mem(unsigned long nr_pages)
+static inline void unaccount_mem(struct kvm_zdev *kzdev, unsigned long nr_pages)
{
- struct user_struct *user = get_uid(current_user());
+ struct user_struct *user = kzdev->user_account;
+ struct mm_struct *mm_account = kzdev->mm_account;
- if (user)
+ if (user) {
atomic_long_sub(nr_pages, &user->locked_vm);
- if (current->mm)
- atomic64_sub(nr_pages, ¤t->mm->pinned_vm);
+ free_uid(user);
+ kzdev->user_account = NULL;
+ }
+
+ if (mm_account) {
+ atomic64_sub(nr_pages, &mm_account->pinned_vm);
+ mmdrop(mm_account);
+ kzdev->mm_account = NULL;
+ }
}
-static inline int account_mem(unsigned long nr_pages)
+static inline int account_mem(struct kvm_zdev *kzdev, unsigned long nr_pages)
{
struct user_struct *user = get_uid(current_user());
unsigned long page_limit, cur_pages, new_pages;
+ int rc = 0;
page_limit = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT;
+ cur_pages = atomic_long_read(&user->locked_vm);
do {
- cur_pages = atomic_long_read(&user->locked_vm);
new_pages = cur_pages + nr_pages;
- if (new_pages > page_limit)
- return -ENOMEM;
- } while (atomic_long_cmpxchg(&user->locked_vm, cur_pages,
- new_pages) != cur_pages);
+ if (new_pages > page_limit) {
+ rc = -ENOMEM;
+ goto out;
+ }
+ } while (!atomic_long_try_cmpxchg(&user->locked_vm, &cur_pages, new_pages));
- atomic64_add(nr_pages, ¤t->mm->pinned_vm);
+ if (current->mm) {
+ mmgrab(current->mm);
+ atomic64_add(nr_pages, ¤t->mm->pinned_vm);
+ }
+
+ kzdev->user_account = user;
+ kzdev->mm_account = current->mm;
return 0;
+
+out:
+ free_uid(user);
+ return rc;
}
static int kvm_s390_pci_aif_enable(struct zpci_dev *zdev, struct zpci_fib *fib,
@@ -295,14 +315,17 @@ static int kvm_s390_pci_aif_enable(struct zpci_dev *zdev, struct zpci_fib *fib,
}
/* Account for pinned pages, roll back on failure */
- if (account_mem(pcount))
+ rc = account_mem(zdev->kzdev, pcount);
+ if (rc)
goto unpin2;
/* AISB must be allocated before we can fill in GAITE */
mutex_lock(&aift->aift_lock);
bit = airq_iv_alloc_bit(aift->sbv);
- if (bit == -1UL)
+ if (bit == -1UL) {
+ rc = -ENOMEM;
goto unlock;
+ }
zdev->aisb = bit; /* store the summary bit number */
zdev->aibv = airq_iv_create(msi_vecs, AIRQ_IV_DATA |
AIRQ_IV_BITLOCK |
@@ -336,24 +359,39 @@ static int kvm_s390_pci_aif_enable(struct zpci_dev *zdev, struct zpci_fib *fib,
aift->kzdev[zdev->aisb] = zdev->kzdev;
spin_unlock_irq(&aift->gait_lock);
- /* Update guest FIB for re-issue */
- fib->fmt0.aisbo = zdev->aisb & 63;
- fib->fmt0.aisb = virt_to_phys(aift->sbv->vector + (zdev->aisb / 64) * 8);
- fib->fmt0.isc = gisc;
-
/* Save some guest fib values in the host for later use */
- zdev->kzdev->fib.fmt0.isc = fib->fmt0.isc;
+ zdev->kzdev->fib.fmt0.isc = gisc;
zdev->kzdev->fib.fmt0.aibv = fib->fmt0.aibv;
- mutex_unlock(&aift->aift_lock);
/* Issue the clp to setup the irq now */
rc = kvm_zpci_set_airq(zdev);
- return rc;
+ if (!rc) {
+ mutex_unlock(&aift->aift_lock);
+ return rc;
+ }
+
+ /* Start cleanup */
+ zdev->kzdev->fib.fmt0.isc = 0;
+ zdev->kzdev->fib.fmt0.aibv = 0;
+
+ spin_lock_irq(&aift->gait_lock);
+ gaite->count--;
+ gaite->aisb = 0;
+ gaite->gisc = 0;
+ gaite->aisbo = 0;
+ gaite->gisa = 0;
+ aift->kzdev[zdev->aisb] = NULL;
+ spin_unlock_irq(&aift->gait_lock);
+
+ airq_iv_release(zdev->aibv);
+ zdev->aibv = NULL;
free_aisb:
airq_iv_free_bit(aift->sbv, zdev->aisb);
zdev->aisb = 0;
unlock:
+ if (pcount > 0)
+ unaccount_mem(zdev->kzdev, pcount);
mutex_unlock(&aift->aift_lock);
unpin2:
if (fib->fmt0.sum == 1)
@@ -424,7 +462,7 @@ static int kvm_s390_pci_aif_disable(struct zpci_dev *zdev, bool force)
pcount++;
}
if (pcount > 0)
- unaccount_mem(pcount);
+ unaccount_mem(kzdev, pcount);
out:
mutex_unlock(&aift->aift_lock);
diff --git a/arch/s390/kvm/pci.h b/arch/s390/kvm/pci.h
index ff0972dd5e71..fdf8c7bf4ed0 100644
--- a/arch/s390/kvm/pci.h
+++ b/arch/s390/kvm/pci.h
@@ -22,6 +22,8 @@ struct kvm_zdev {
struct kvm *kvm;
struct zpci_fib fib;
struct list_head entry;
+ struct user_struct *user_account;
+ struct mm_struct *mm_account;
};
struct zpci_gaite {
diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index 9be2b10ff4f0..b5a5e5c3cc5a 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -2291,6 +2291,9 @@ static union kvm_mmu_page_role kvm_mmu_child_role(u64 *sptep, bool direct,
role.direct = direct;
role.passthrough = 0;
+ WARN_ON_ONCE(role.invalid);
+ role.invalid = 0;
+
/*
* If the guest has 4-byte PTEs then that means it's using 32-bit,
* 2-level, non-PAE paging. KVM shadows such guests with PAE paging
diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c
index 6cec696461da..bd0344bacaf1 100644
--- a/arch/x86/kvm/svm/sev.c
+++ b/arch/x86/kvm/svm/sev.c
@@ -2972,6 +2972,7 @@ void __init sev_set_cpu_caps(void)
void __init sev_hardware_setup(void)
{
unsigned int eax, ebx, ecx, edx, sev_asid_count, sev_es_asid_count;
+ struct sev_platform_init_args init_args = {0};
bool sev_snp_supported = false;
bool sev_es_supported = false;
bool sev_supported = false;
@@ -3088,6 +3089,15 @@ void __init sev_hardware_setup(void)
sev_supported_vmsa_features = 0;
if (sev_es_debug_swap_enabled)
sev_supported_vmsa_features |= SVM_SEV_FEAT_DEBUG_SWAP;
+
+ if (!sev_enabled)
+ return;
+
+ /*
+ * Do both SNP and SEV initialization at KVM module load.
+ */
+ init_args.probe = true;
+ sev_platform_init(&init_args);
}
void sev_hardware_unsetup(void)
@@ -3103,6 +3113,8 @@ void sev_hardware_unsetup(void)
misc_cg_set_capacity(MISC_CG_RES_SEV, 0);
misc_cg_set_capacity(MISC_CG_RES_SEV_ES, 0);
+
+ sev_platform_shutdown();
}
int sev_cpu_init(struct svm_cpu_data *sd)
diff --git a/block/blk-mq.c b/block/blk-mq.c
index 5bfaa8e4b9cf..6af42682af7d 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -2989,7 +2989,7 @@ static struct request *blk_mq_get_new_requests(struct request_queue *q,
/*
* Check if there is a suitable cached request and return it.
*/
-static struct request *blk_mq_peek_cached_request(struct blk_plug *plug,
+static struct request *blk_mq_get_cached_request(struct blk_plug *plug,
struct request_queue *q, blk_opf_t opf)
{
enum hctx_type type = blk_mq_get_hctx_type(opf);
@@ -3005,27 +3005,10 @@ static struct request *blk_mq_peek_cached_request(struct blk_plug *plug,
return NULL;
if (op_is_flush(rq->cmd_flags) != op_is_flush(opf))
return NULL;
+ rq_list_pop(&plug->cached_rqs);
return rq;
}
-static void blk_mq_use_cached_rq(struct request *rq, struct blk_plug *plug,
- struct bio *bio)
-{
- if (rq_list_pop(&plug->cached_rqs) != rq)
- WARN_ON_ONCE(1);
-
- /*
- * If any qos ->throttle() end up blocking, we will have flushed the
- * plug and hence killed the cached_rq list as well. Pop this entry
- * before we throttle.
- */
- rq_qos_throttle(rq->q, bio);
-
- blk_mq_rq_time_init(rq, 0);
- rq->cmd_flags = bio->bi_opf;
- INIT_LIST_HEAD(&rq->queuelist);
-}
-
static bool bio_unaligned(const struct bio *bio, struct request_queue *q)
{
unsigned int bs_mask = queue_logical_block_size(q) - 1;
@@ -3063,7 +3046,7 @@ void blk_mq_submit_bio(struct bio *bio)
/*
* If the plug has a cached request for this queue, try to use it.
*/
- rq = blk_mq_peek_cached_request(plug, q, bio->bi_opf);
+ rq = blk_mq_get_cached_request(plug, q, bio->bi_opf);
/*
* A BIO that was released from a zone write plug has already been
@@ -3121,12 +3104,15 @@ void blk_mq_submit_bio(struct bio *bio)
}
new_request:
- if (!rq) {
+ if (rq) {
+ rq_qos_throttle(rq->q, bio);
+ blk_mq_rq_time_init(rq, blk_time_get_ns());
+ rq->cmd_flags = bio->bi_opf;
+ INIT_LIST_HEAD(&rq->queuelist);
+ } else {
rq = blk_mq_get_new_requests(q, plug, bio, nr_segs);
if (unlikely(!rq))
goto queue_exit;
- } else {
- blk_mq_use_cached_rq(rq, plug, bio);
}
trace_block_getrq(bio);
@@ -3165,12 +3151,10 @@ void blk_mq_submit_bio(struct bio *bio)
return;
queue_exit:
- /*
- * Don't drop the queue reference if we were trying to use a cached
- * request and thus didn't acquire one.
- */
if (!rq)
blk_queue_exit(q);
+ else
+ rq_list_add_head(&plug->cached_rqs, rq);
}
#ifdef CONFIG_BLK_MQ_STACKING
diff --git a/drivers/ata/pata_sl82c105.c b/drivers/ata/pata_sl82c105.c
index 93882e976ede..2a5ce46af5a0 100644
--- a/drivers/ata/pata_sl82c105.c
+++ b/drivers/ata/pata_sl82c105.c
@@ -264,6 +264,7 @@ static struct ata_port_operations sl82c105_port_ops = {
static int sl82c105_bridge_revision(struct pci_dev *pdev)
{
struct pci_dev *bridge;
+ u8 revision;
/*
* The bridge should be part of the same device, but function 0.
@@ -285,8 +286,9 @@ static int sl82c105_bridge_revision(struct pci_dev *pdev)
/*
* We need to find function 0's revision, not function 1
*/
+ revision = bridge->revision;
pci_dev_put(bridge);
- return bridge->revision;
+ return revision;
}
static void sl82c105_fixup(struct pci_dev *pdev)
diff --git a/drivers/counter/microchip-tcb-capture.c b/drivers/counter/microchip-tcb-capture.c
index 461f57f66631..fbd1afe178a3 100644
--- a/drivers/counter/microchip-tcb-capture.c
+++ b/drivers/counter/microchip-tcb-capture.c
@@ -309,7 +309,7 @@ static int mchp_tc_probe(struct platform_device *pdev)
char clk_name[7];
struct regmap *regmap;
struct clk *clk[3];
- int channel;
+ u32 channel;
int ret, i;
counter = devm_counter_alloc(&pdev->dev, sizeof(*priv));
@@ -343,7 +343,7 @@ static int mchp_tc_probe(struct platform_device *pdev)
priv->channel[i] = channel;
- snprintf(clk_name, sizeof(clk_name), "t%d_clk", channel);
+ snprintf(clk_name, sizeof(clk_name), "t%u_clk", channel);
clk[i] = of_clk_get_by_name(np->parent, clk_name);
if (IS_ERR(clk[i])) {
diff --git a/drivers/crypto/ccp/sev-dev.c b/drivers/crypto/ccp/sev-dev.c
index d668f9318c28..d6a0773d6da8 100644
--- a/drivers/crypto/ccp/sev-dev.c
+++ b/drivers/crypto/ccp/sev-dev.c
@@ -226,6 +226,7 @@ static int sev_cmd_buffer_len(int cmd)
case SEV_CMD_SNP_GUEST_REQUEST: return sizeof(struct sev_data_snp_guest_request);
case SEV_CMD_SNP_CONFIG: return sizeof(struct sev_user_data_snp_config);
case SEV_CMD_SNP_COMMIT: return sizeof(struct sev_data_snp_commit);
+ case SEV_CMD_SNP_VLEK_LOAD: return sizeof(struct sev_user_data_snp_vlek_load);
default: return 0;
}
@@ -1117,7 +1118,7 @@ static int __sev_snp_init_locked(int *error)
if (!sev_version_greater_or_equal(SNP_MIN_API_MAJOR, SNP_MIN_API_MINOR)) {
dev_dbg(sev->dev, "SEV-SNP support requires firmware version >= %d:%d\n",
SNP_MIN_API_MAJOR, SNP_MIN_API_MINOR);
- return 0;
+ return -EOPNOTSUPP;
}
/* SNP_INIT requires MSR_VM_HSAVE_PA to be cleared on all CPUs. */
@@ -1356,12 +1357,9 @@ static int _sev_platform_init_locked(struct sev_platform_init_args *args)
rc = __sev_snp_init_locked(&args->error);
if (rc && rc != -ENODEV) {
- /*
- * Don't abort the probe if SNP INIT failed,
- * continue to initialize the legacy SEV firmware.
- */
dev_err(sev->dev, "SEV-SNP: failed to INIT rc %d, error %#x\n",
rc, args->error);
+ return rc;
}
/* Defer legacy SEV/SEV-ES support if allowed by caller/module. */
@@ -2444,6 +2442,15 @@ static void sev_firmware_shutdown(struct sev_device *sev)
mutex_unlock(&sev_cmd_mutex);
}
+void sev_platform_shutdown(void)
+{
+ if (!psp_master || !psp_master->sev_data)
+ return;
+
+ sev_firmware_shutdown(psp_master->sev_data);
+}
+EXPORT_SYMBOL_GPL(sev_platform_shutdown);
+
void sev_dev_destroy(struct psp_device *psp)
{
struct sev_device *sev = psp->sev_data;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index df77afbd5462..2ec994a6dea6 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -4635,6 +4635,8 @@ static void amdgpu_device_unmap_mmio(struct amdgpu_device *adev)
iounmap(adev->rmmio);
adev->rmmio = NULL;
+ if (adev->mman.aper_base_kaddr)
+ iounmap(adev->mman.aper_base_kaddr);
adev->mman.aper_base_kaddr = NULL;
/* Memory manager related */
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
index 31f9fb3cfeaa..e161af6276b9 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
@@ -1909,23 +1909,17 @@ int amdgpu_ttm_init(struct amdgpu_device *adev)
/* Change the size here instead of the init above so only lpfn is affected */
amdgpu_ttm_set_buffer_funcs_status(adev, false);
#ifdef CONFIG_64BIT
- if (adev->gmc.xgmi.connected_to_cpu) {
- void *kaddr = devm_memremap(adev->dev, adev->gmc.aper_base,
- adev->gmc.visible_vram_size,
- MEMREMAP_WB);
- if (IS_ERR(kaddr))
- return PTR_ERR(kaddr);
- adev->mman.aper_base_kaddr = (__force void __iomem *)kaddr;
- } else if (adev->gmc.is_app_apu) {
+#ifdef CONFIG_X86
+ if (adev->gmc.xgmi.connected_to_cpu)
+ adev->mman.aper_base_kaddr = ioremap_cache(adev->gmc.aper_base,
+ adev->gmc.visible_vram_size);
+ else if (adev->gmc.is_app_apu)
DRM_DEBUG_DRIVER(
"No need to ioremap when real vram size is 0\n");
- } else {
- adev->mman.aper_base_kaddr = devm_ioremap_wc(adev->dev,
- adev->gmc.aper_base,
- adev->gmc.visible_vram_size);
- if (!adev->mman.aper_base_kaddr)
- return -ENOMEM;
- }
+ else
+#endif
+ adev->mman.aper_base_kaddr = ioremap_wc(adev->gmc.aper_base,
+ adev->gmc.visible_vram_size);
#endif
/*
@@ -2072,6 +2066,8 @@ int amdgpu_ttm_init(struct amdgpu_device *adev)
*/
void amdgpu_ttm_fini(struct amdgpu_device *adev)
{
+ int idx;
+
if (!adev->mman.initialized)
return;
@@ -2094,7 +2090,14 @@ void amdgpu_ttm_fini(struct amdgpu_device *adev)
amdgpu_ttm_fw_reserve_vram_fini(adev);
amdgpu_ttm_drv_reserve_vram_fini(adev);
- adev->mman.aper_base_kaddr = NULL;
+ if (drm_dev_enter(adev_to_drm(adev), &idx)) {
+
+ if (adev->mman.aper_base_kaddr)
+ iounmap(adev->mman.aper_base_kaddr);
+ adev->mman.aper_base_kaddr = NULL;
+
+ drm_dev_exit(idx);
+ }
amdgpu_vram_mgr_fini(adev);
amdgpu_gtt_mgr_fini(adev);
diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dce110/dce110_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dce110/dce110_hwseq.c
index 551638d9ff61..dcc78244dd7c 100644
--- a/drivers/gpu/drm/amd/display/dc/hwss/dce110/dce110_hwseq.c
+++ b/drivers/gpu/drm/amd/display/dc/hwss/dce110/dce110_hwseq.c
@@ -1256,8 +1256,30 @@ void dce110_blank_stream(struct pipe_ctx *pipe_ctx)
void dce110_set_avmute(struct pipe_ctx *pipe_ctx, bool enable)
{
- if (pipe_ctx != NULL && pipe_ctx->stream_res.stream_enc != NULL)
+ if (pipe_ctx == NULL || pipe_ctx->stream_res.stream_enc == NULL)
+ return;
+
+ if (dc_is_hdmi_signal(pipe_ctx->stream->signal)) {
pipe_ctx->stream_res.stream_enc->funcs->set_avmute(pipe_ctx->stream_res.stream_enc, enable);
+
+ /* Wait for three frames to make sure AV mute is sent out.
+ * Some HDMI sinks need additional GCP packets to properly
+ * process the mute state, especially after link re-establishment
+ * with HDMI 2.0 scrambling enabled.
+ */
+ if (enable && pipe_ctx->stream_res.tg &&
+ pipe_ctx->stream_res.tg->funcs->is_tg_enabled &&
+ pipe_ctx->stream_res.tg->funcs->wait_for_state &&
+ pipe_ctx->stream_res.tg->funcs->is_tg_enabled(pipe_ctx->stream_res.tg)) {
+ int i;
+
+ pipe_ctx->stream_res.tg->funcs->wait_for_state(pipe_ctx->stream_res.tg, CRTC_STATE_VACTIVE);
+ for (i = 0; i < 3; i++) {
+ pipe_ctx->stream_res.tg->funcs->wait_for_state(pipe_ctx->stream_res.tg, CRTC_STATE_VBLANK);
+ pipe_ctx->stream_res.tg->funcs->wait_for_state(pipe_ctx->stream_res.tg, CRTC_STATE_VACTIVE);
+ }
+ }
+ }
}
static enum audio_dto_source translate_to_dto_source(enum controller_id crtc_id)
diff --git a/drivers/gpu/drm/bridge/parade-ps8640.c b/drivers/gpu/drm/bridge/parade-ps8640.c
index 14d4dcf239da..61ea855e55d8 100644
--- a/drivers/gpu/drm/bridge/parade-ps8640.c
+++ b/drivers/gpu/drm/bridge/parade-ps8640.c
@@ -258,8 +258,14 @@ static ssize_t ps8640_aux_transfer_msg(struct drm_dp_aux *aux,
addr_len[PAGE0_SWAUX_LENGTH - base] = (len == 0) ? SWAUX_NO_PAYLOAD :
((len - 1) & SWAUX_LENGTH_MASK);
- regmap_bulk_write(map, PAGE0_SWAUX_ADDR_7_0, addr_len,
- ARRAY_SIZE(addr_len));
+ ret = regmap_bulk_write(map, PAGE0_SWAUX_ADDR_7_0, addr_len,
+ ARRAY_SIZE(addr_len));
+ if (ret) {
+ DRM_DEV_ERROR(dev,
+ "failed to write AUX address %#x, len %zu: %d\n",
+ msg->address, len, ret);
+ return ret;
+ }
if (len && (request == DP_AUX_NATIVE_WRITE ||
request == DP_AUX_I2C_WRITE)) {
@@ -275,13 +281,22 @@ static ssize_t ps8640_aux_transfer_msg(struct drm_dp_aux *aux,
}
}
- regmap_write(map, PAGE0_SWAUX_CTRL, SWAUX_SEND);
+ ret = regmap_write(map, PAGE0_SWAUX_CTRL, SWAUX_SEND);
+ if (ret) {
+ DRM_DEV_ERROR(dev, "failed to start AUX transfer: %d\n", ret);
+ return ret;
+ }
/* Zero delay loop because i2c transactions are slow already */
- regmap_read_poll_timeout(map, PAGE0_SWAUX_CTRL, data,
- !(data & SWAUX_SEND), 0, 50 * 1000);
+ ret = regmap_read_poll_timeout(map, PAGE0_SWAUX_CTRL, data,
+ !(data & SWAUX_SEND), 0, 50 * 1000);
+ if (ret) {
+ DRM_DEV_ERROR(dev, "failed to complete AUX transfer: %d\n",
+ ret);
+ return ret;
+ }
- regmap_read(map, PAGE0_SWAUX_STATUS, &data);
+ ret = regmap_read(map, PAGE0_SWAUX_STATUS, &data);
if (ret) {
DRM_DEV_ERROR(dev, "failed to read PAGE0_SWAUX_STATUS: %d\n",
ret);
diff --git a/drivers/hwmon/ads7828.c b/drivers/hwmon/ads7828.c
index 436637264056..20ef4992f5bb 100644
--- a/drivers/hwmon/ads7828.c
+++ b/drivers/hwmon/ads7828.c
@@ -106,12 +106,11 @@ static int ads7828_probe(struct i2c_client *client)
struct ads7828_data *data;
struct device *hwmon_dev;
unsigned int vref_mv = ADS7828_INT_VREF_MV;
- unsigned int vref_uv;
+ int vref_uv;
bool diff_input = false;
bool ext_vref = false;
unsigned int regval;
enum ads7828_chips chip;
- struct regulator *reg;
data = devm_kzalloc(dev, sizeof(struct ads7828_data), GFP_KERNEL);
if (!data)
@@ -125,9 +124,11 @@ static int ads7828_probe(struct i2c_client *client)
} else if (dev->of_node) {
diff_input = of_property_read_bool(dev->of_node,
"ti,differential-input");
- reg = devm_regulator_get_optional(dev, "vref");
- if (!IS_ERR(reg)) {
- vref_uv = regulator_get_voltage(reg);
+ vref_uv = devm_regulator_get_enable_read_voltage(dev, "vref");
+ if (vref_uv < 0) {
+ if (vref_uv != -ENODEV)
+ return vref_uv;
+ } else {
vref_mv = DIV_ROUND_CLOSEST(vref_uv, 1000);
if (vref_mv < ADS7828_EXT_VREF_MV_MIN ||
vref_mv > ADS7828_EXT_VREF_MV_MAX)
diff --git a/drivers/hwmon/corsair-psu.c b/drivers/hwmon/corsair-psu.c
index 4ab73bcef1d1..61d1b22bc63e 100644
--- a/drivers/hwmon/corsair-psu.c
+++ b/drivers/hwmon/corsair-psu.c
@@ -709,7 +709,7 @@ static int vendor_show(struct seq_file *seqf, void *unused)
{
struct corsairpsu_data *priv = seqf->private;
- seq_printf(seqf, "%s\n", priv->vendor);
+ seq_printf(seqf, "%.*s\n", REPLY_SIZE, priv->vendor);
return 0;
}
@@ -719,7 +719,7 @@ static int product_show(struct seq_file *seqf, void *unused)
{
struct corsairpsu_data *priv = seqf->private;
- seq_printf(seqf, "%s\n", priv->product);
+ seq_printf(seqf, "%.*s\n", REPLY_SIZE, priv->product);
return 0;
}
diff --git a/drivers/hwmon/ltc4282.c b/drivers/hwmon/ltc4282.c
index e1c0d02b564b..5f7ab813051c 100644
--- a/drivers/hwmon/ltc4282.c
+++ b/drivers/hwmon/ltc4282.c
@@ -15,6 +15,7 @@
#include <linux/hwmon-sysfs.h>
#include <linux/i2c.h>
#include <linux/math.h>
+#include <linux/math64.h>
#include <linux/minmax.h>
#include <linux/module.h>
#include <linux/mod_devicetable.h>
@@ -142,7 +143,7 @@ struct ltc4282_state {
*/
struct ltc4282_cache in0_1_cache[LTC4282_CHAN_VGPIO];
u32 vsense_max;
- long power_max;
+ s64 power_max;
u32 rsense;
u16 vdd;
u16 vfs_out;
@@ -621,13 +622,12 @@ static int ltc4282_read(struct device *dev, enum hwmon_sensor_types type,
}
static int ltc4282_write_power_byte(const struct ltc4282_state *st, u32 reg,
- long val)
+ s64 val)
{
u32 power;
u64 temp;
- if (val > st->power_max)
- val = st->power_max;
+ val = clamp(val, 0, st->power_max);
temp = val * int_pow(U8_MAX, 2) * st->rsense;
power = DIV64_U64_ROUND_CLOSEST(temp,
@@ -637,7 +637,7 @@ static int ltc4282_write_power_byte(const struct ltc4282_state *st, u32 reg,
}
static int ltc4282_write_power_word(const struct ltc4282_state *st, u32 reg,
- long val)
+ u64 val)
{
u64 temp = int_pow(U16_MAX, 2) * st->rsense, temp_2;
__be16 __raw;
@@ -946,8 +946,11 @@ static int ltc4282_curr_reset_hist(struct ltc4282_state *st)
static int ltc4282_write_curr(struct ltc4282_state *st, u32 attr,
long val)
{
+ s32 ulimit = min_t(u64, INT_MAX,
+ div_u64((u64)INT_MAX * DECA * MICRO, st->rsense));
+ u64 val64 = clamp(val, 0, ulimit);
/* need to pass it in millivolt */
- u32 in = DIV_ROUND_CLOSEST_ULL((u64)val * st->rsense, DECA * MICRO);
+ u32 in = DIV_ROUND_CLOSEST_ULL(val64 * st->rsense, DECA * MICRO);
switch (attr) {
case hwmon_curr_max:
@@ -1254,7 +1257,8 @@ static int ltc4282_set_max_limits(struct ltc4282_state *st)
return ret;
/* Power is given by ISENSE * Vout. */
- st->power_max = DIV_ROUND_CLOSEST(st->vsense_max * DECA * MILLI, st->rsense) * st->vfs_out;
+ st->power_max = DIV_ROUND_CLOSEST_ULL((u64)st->vsense_max * DECA * MILLI,
+ st->rsense) * st->vfs_out;
ret = ltc4282_write_power_byte(st, LTC4282_POWER_MAX, st->power_max);
if (ret)
return ret;
@@ -1421,7 +1425,7 @@ static int ltc4282_setup(struct ltc4282_state *st, struct device *dev)
if (!ret) {
int reg_val;
- switch (val) {
+ switch (st->vsense_max) {
case 12500:
reg_val = 0;
break;
diff --git a/drivers/hwmon/nzxt-smart2.c b/drivers/hwmon/nzxt-smart2.c
index 66c5886f411a..8ff3ebc1bb4c 100644
--- a/drivers/hwmon/nzxt-smart2.c
+++ b/drivers/hwmon/nzxt-smart2.c
@@ -760,7 +760,11 @@ static int nzxt_smart2_hid_probe(struct hid_device *hdev,
hid_device_io_start(hdev);
- init_device(drvdata, UPDATE_INTERVAL_DEFAULT_MS);
+ ret = init_device(drvdata, UPDATE_INTERVAL_DEFAULT_MS);
+ if (ret) {
+ dev_err(&hdev->dev, "init_device failed: %d\n", ret);
+ goto out_hw_close;
+ }
drvdata->hwmon =
hwmon_device_register_with_info(&hdev->dev, "nzxtsmart2", drvdata,
diff --git a/drivers/hwmon/pmbus/lm25066.c b/drivers/hwmon/pmbus/lm25066.c
index c36c124d1a2d..f0bf3b153331 100644
--- a/drivers/hwmon/pmbus/lm25066.c
+++ b/drivers/hwmon/pmbus/lm25066.c
@@ -14,6 +14,7 @@
#include <linux/slab.h>
#include <linux/i2c.h>
#include <linux/log2.h>
+#include <linux/math.h>
#include <linux/of.h>
#include "pmbus.h"
@@ -540,8 +541,8 @@ static int lm25066_probe(struct i2c_client *client)
if (of_property_read_u32(client->dev.of_node, "shunt-resistor-micro-ohms", &shunt))
shunt = 1000;
- info->m[PSC_CURRENT_IN] = info->m[PSC_CURRENT_IN] * shunt / 1000;
- info->m[PSC_POWER] = info->m[PSC_POWER] * shunt / 1000;
+ info->m[PSC_CURRENT_IN] = DIV_ROUND_CLOSEST_ULL((u64)info->m[PSC_CURRENT_IN] * shunt, 1000);
+ info->m[PSC_POWER] = DIV_ROUND_CLOSEST_ULL((u64)info->m[PSC_POWER] * shunt, 1000);
#if IS_ENABLED(CONFIG_SENSORS_LM25066_REGULATOR)
/* LM25056 doesn't support OPERATION */
diff --git a/drivers/input/evdev.c b/drivers/input/evdev.c
index b5cbb57ee5f6..2fa5b8a13131 100644
--- a/drivers/input/evdev.c
+++ b/drivers/input/evdev.c
@@ -21,6 +21,7 @@
#include <linux/init.h>
#include <linux/input/mt.h>
#include <linux/major.h>
+#include <linux/nospec.h>
#include <linux/device.h>
#include <linux/cdev.h>
#include "input-compat.h"
@@ -67,8 +68,10 @@ static size_t evdev_get_mask_cnt(unsigned int type)
[EV_SND] = SND_CNT,
[EV_FF] = FF_CNT,
};
+ unsigned long mask = array_index_mask_nospec(type, EV_CNT);
- return (type < EV_CNT) ? counts[type] : 0;
+ /* Returns 0 for out-of-bounds types, including speculatively */
+ return counts[type & mask] & mask;
}
/* requires the buffer lock to be held */
@@ -146,11 +149,11 @@ static void __evdev_queue_syn_dropped(struct evdev_client *client)
struct timespec64 ts = ktime_to_timespec64(ev_time[client->clk_type]);
struct input_event ev;
+ memset(&ev, 0, sizeof(ev));
ev.input_event_sec = ts.tv_sec;
ev.input_event_usec = ts.tv_nsec / NSEC_PER_USEC;
ev.type = EV_SYN;
ev.code = SYN_DROPPED;
- ev.value = 0;
client->buffer[client->head++] = ev;
client->head &= client->bufsize - 1;
@@ -218,20 +221,20 @@ static void __pass_event(struct evdev_client *client,
client->head &= client->bufsize - 1;
if (unlikely(client->head == client->tail)) {
+ struct input_event ev;
+
+ memset(&ev, 0, sizeof(ev));
+ ev.input_event_sec = event->input_event_sec;
+ ev.input_event_usec = event->input_event_usec;
+ ev.type = EV_SYN;
+ ev.code = SYN_DROPPED;
+
/*
* This effectively "drops" all unconsumed events, leaving
* EV_SYN/SYN_DROPPED plus the newest event in the queue.
*/
client->tail = (client->head - 2) & (client->bufsize - 1);
-
- client->buffer[client->tail] = (struct input_event) {
- .input_event_sec = event->input_event_sec,
- .input_event_usec = event->input_event_usec,
- .type = EV_SYN,
- .code = SYN_DROPPED,
- .value = 0,
- };
-
+ client->buffer[client->tail] = ev;
client->packet_head = client->tail;
}
@@ -253,6 +256,8 @@ static void evdev_pass_values(struct evdev_client *client,
if (client->revoked)
return;
+ memset(&event, 0, sizeof(event));
+
ts = ktime_to_timespec64(ev_time[client->clk_type]);
event.input_event_sec = ts.tv_sec;
event.input_event_usec = ts.tv_nsec / NSEC_PER_USEC;
diff --git a/drivers/misc/fastrpc.c b/drivers/misc/fastrpc.c
index c0ef145c8297..576cd9e5b807 100644
--- a/drivers/misc/fastrpc.c
+++ b/drivers/misc/fastrpc.c
@@ -469,6 +469,7 @@ static void fastrpc_channel_ctx_free(struct kref *ref)
cctx = container_of(ref, struct fastrpc_channel_ctx, refcount);
+ idr_destroy(&cctx->ctx_idr);
kfree(cctx);
}
@@ -1279,10 +1280,12 @@ static int fastrpc_internal_invoke(struct fastrpc_user *fl, u32 kernel,
}
if (err == -ERESTARTSYS) {
+ spin_lock(&fl->lock);
list_for_each_entry_safe(buf, b, &fl->mmaps, node) {
list_del(&buf->node);
list_add_tail(&buf->node, &fl->cctx->invoke_interrupted_mmaps);
}
+ spin_unlock(&fl->lock);
}
if (err)
@@ -1643,7 +1646,7 @@ static int fastrpc_device_open(struct inode *inode, struct file *filp)
dev_err(&cctx->rpdev->dev, "No session available\n");
mutex_destroy(&fl->mutex);
kfree(fl);
-
+ fastrpc_channel_ctx_put(cctx);
return -EBUSY;
}
@@ -1871,9 +1874,6 @@ static int fastrpc_req_munmap_impl(struct fastrpc_user *fl, struct fastrpc_buf *
&args[0]);
if (!err) {
dev_dbg(dev, "unmmap\tpt 0x%09lx OK\n", buf->raddr);
- spin_lock(&fl->lock);
- list_del(&buf->node);
- spin_unlock(&fl->lock);
fastrpc_buf_free(buf);
} else {
dev_err(dev, "unmmap\tpt 0x%09lx ERROR\n", buf->raddr);
@@ -1887,6 +1887,7 @@ static int fastrpc_req_munmap(struct fastrpc_user *fl, char __user *argp)
struct fastrpc_buf *buf = NULL, *iter, *b;
struct fastrpc_req_munmap req;
struct device *dev = fl->sctx->dev;
+ int err;
if (copy_from_user(&req, argp, sizeof(req)))
return -EFAULT;
@@ -1894,6 +1895,7 @@ static int fastrpc_req_munmap(struct fastrpc_user *fl, char __user *argp)
spin_lock(&fl->lock);
list_for_each_entry_safe(iter, b, &fl->mmaps, node) {
if ((iter->raddr == req.vaddrout) && (iter->size == req.size)) {
+ list_del(&iter->node);
buf = iter;
break;
}
@@ -1906,7 +1908,14 @@ static int fastrpc_req_munmap(struct fastrpc_user *fl, char __user *argp)
return -EINVAL;
}
- return fastrpc_req_munmap_impl(fl, buf);
+ err = fastrpc_req_munmap_impl(fl, buf);
+ if (err) {
+ spin_lock(&fl->lock);
+ list_add_tail(&buf->node, &fl->mmaps);
+ spin_unlock(&fl->lock);
+ }
+
+ return err;
}
static int fastrpc_req_mmap(struct fastrpc_user *fl, char __user *argp)
diff --git a/drivers/misc/mei/client.c b/drivers/misc/mei/client.c
index be011cef12e5..ccc40f900830 100644
--- a/drivers/misc/mei/client.c
+++ b/drivers/misc/mei/client.c
@@ -447,18 +447,24 @@ static void mei_io_tx_list_free_cl(struct list_head *head,
}
/**
- * mei_io_list_free_fp - free cb from a list that matches file pointer
+ * mei_io_rd_list_free_fp - free cb from a rd_completed list that matches file pointer
*
- * @head: io list
+ * @cl: host client
* @fp: file pointer (matching cb file object), may be NULL
*/
-static void mei_io_list_free_fp(struct list_head *head, const struct file *fp)
+static void mei_io_rd_list_free_fp(struct mei_cl *cl, const struct file *fp)
{
struct mei_cl_cb *cb, *next;
+ LIST_HEAD(cmpl_list);
- list_for_each_entry_safe(cb, next, head, list)
+ spin_lock(&cl->rd_completed_lock);
+ list_for_each_entry_safe(cb, next, &cl->rd_completed, list)
if (!fp || fp == cb->fp)
- mei_io_cb_free(cb);
+ list_move(&cb->list, &cmpl_list);
+ spin_unlock(&cl->rd_completed_lock);
+
+ list_for_each_entry_safe(cb, next, &cmpl_list, list)
+ mei_io_cb_free(cb);
}
/**
@@ -587,9 +593,7 @@ int mei_cl_flush_queues(struct mei_cl *cl, const struct file *fp)
mei_io_list_flush_cl(&cl->dev->ctrl_rd_list, cl);
mei_cl_free_pending(cl);
}
- spin_lock(&cl->rd_completed_lock);
- mei_io_list_free_fp(&cl->rd_completed, fp);
- spin_unlock(&cl->rd_completed_lock);
+ mei_io_rd_list_free_fp(cl, fp);
return 0;
}
@@ -1426,7 +1430,7 @@ void mei_cl_add_rd_completed(struct mei_cl *cl, struct mei_cl_cb *cb)
}
/**
- * mei_cl_del_rd_completed - free read completed callback with lock
+ * mei_cl_del_rd_completed - unlink read completed callback with lock and free it
*
* @cl: host client
* @cb: callback block
@@ -1435,8 +1439,9 @@ void mei_cl_add_rd_completed(struct mei_cl *cl, struct mei_cl_cb *cb)
void mei_cl_del_rd_completed(struct mei_cl *cl, struct mei_cl_cb *cb)
{
spin_lock(&cl->rd_completed_lock);
- mei_io_cb_free(cb);
+ list_del_init(&cb->list);
spin_unlock(&cl->rd_completed_lock);
+ mei_io_cb_free(cb);
}
/**
diff --git a/drivers/mtd/nand/spi/core.c b/drivers/mtd/nand/spi/core.c
index 48ac009cbaad..bf16901b77b6 100644
--- a/drivers/mtd/nand/spi/core.c
+++ b/drivers/mtd/nand/spi/core.c
@@ -427,8 +427,16 @@ static int spinand_read_from_cache_op(struct spinand_device *spinand,
* Dirmap accesses are allowed to toggle the CS.
* Toggling the CS during a continuous read is forbidden.
*/
- if (nbytes && req->continuous)
- return -EIO;
+ if (nbytes && req->continuous) {
+ /*
+ * Spi controller with broken support of continuous
+ * reading was detected. Disable future use of
+ * continuous reading and return -EAGAIN to retry
+ * reading within regular mode.
+ */
+ spinand->cont_read_possible = false;
+ return -EAGAIN;
+ }
}
if (req->datalen)
@@ -849,10 +857,19 @@ static int spinand_mtd_read(struct mtd_info *mtd, loff_t from,
old_stats = mtd->ecc_stats;
- if (spinand_use_cont_read(mtd, from, ops))
+ if (spinand_use_cont_read(mtd, from, ops)) {
ret = spinand_mtd_continuous_page_read(mtd, from, ops, &max_bitflips);
- else
+ if (ret == -EAGAIN && !spinand->cont_read_possible) {
+ /*
+ * Spi controller with broken support of continuous
+ * reading was detected (see spinand_read_from_cache_op()),
+ * repeat reading in regular mode.
+ */
+ ret = spinand_mtd_regular_page_read(mtd, from, ops, &max_bitflips);
+ }
+ } else {
ret = spinand_mtd_regular_page_read(mtd, from, ops, &max_bitflips);
+ }
if (ops->stats) {
ops->stats->uncorrectable_errors +=
@@ -1032,22 +1049,50 @@ static int spinand_mtd_block_isreserved(struct mtd_info *mtd, loff_t offs)
return ret;
}
+static struct spi_mem_dirmap_desc *spinand_create_rdesc(
+ struct spinand_device *spinand,
+ struct spi_mem_dirmap_info *info)
+{
+ struct nand_device *nand = spinand_to_nand(spinand);
+ struct spi_mem_dirmap_desc *desc = NULL;
+
+ if (spinand->cont_read_possible) {
+ /*
+ * spi controller may return an error if info->length is
+ * too large
+ */
+ info->length = nanddev_eraseblock_size(nand);
+ desc = devm_spi_mem_dirmap_create(&spinand->spimem->spi->dev,
+ spinand->spimem, info);
+ }
+
+ if (IS_ERR_OR_NULL(desc)) {
+ /*
+ * continuous reading is not supported by flash or
+ * its spi controller, use regular reading
+ */
+ spinand->cont_read_possible = false;
+
+ info->length = nanddev_page_size(nand) +
+ nanddev_per_page_oobsize(nand);
+ desc = devm_spi_mem_dirmap_create(&spinand->spimem->spi->dev,
+ spinand->spimem, info);
+ }
+
+ return desc;
+}
+
static int spinand_create_dirmap(struct spinand_device *spinand,
unsigned int plane)
{
struct nand_device *nand = spinand_to_nand(spinand);
- struct spi_mem_dirmap_info info = {
- .length = nanddev_page_size(nand) +
- nanddev_per_page_oobsize(nand),
- };
+ struct spi_mem_dirmap_info info = { 0 };
struct spi_mem_dirmap_desc *desc;
- if (spinand->cont_read_possible)
- info.length = nanddev_eraseblock_size(nand);
-
/* The plane number is passed in MSB just above the column address */
info.offset = plane << fls(nand->memorg.pagesize);
+ info.length = nanddev_page_size(nand) + nanddev_per_page_oobsize(nand);
info.op_tmpl = *spinand->op_templates.update_cache;
desc = devm_spi_mem_dirmap_create(&spinand->spimem->spi->dev,
spinand->spimem, &info);
@@ -1057,8 +1102,7 @@ static int spinand_create_dirmap(struct spinand_device *spinand,
spinand->dirmaps[plane].wdesc = desc;
info.op_tmpl = *spinand->op_templates.read_cache;
- desc = devm_spi_mem_dirmap_create(&spinand->spimem->spi->dev,
- spinand->spimem, &info);
+ desc = spinand_create_rdesc(spinand, &info);
if (IS_ERR(desc))
return PTR_ERR(desc);
@@ -1071,6 +1115,7 @@ static int spinand_create_dirmap(struct spinand_device *spinand,
return 0;
}
+ info.length = nanddev_page_size(nand) + nanddev_per_page_oobsize(nand);
info.op_tmpl = *spinand->op_templates.update_cache;
info.op_tmpl.data.ecc = true;
desc = devm_spi_mem_dirmap_create(&spinand->spimem->spi->dev,
@@ -1082,8 +1127,7 @@ static int spinand_create_dirmap(struct spinand_device *spinand,
info.op_tmpl = *spinand->op_templates.read_cache;
info.op_tmpl.data.ecc = true;
- desc = devm_spi_mem_dirmap_create(&spinand->spimem->spi->dev,
- spinand->spimem, &info);
+ desc = spinand_create_rdesc(spinand, &info);
if (IS_ERR(desc))
return PTR_ERR(desc);
diff --git a/drivers/net/bonding/bond_alb.c b/drivers/net/bonding/bond_alb.c
index 7edf0fd58c34..ce6a3a0a2e15 100644
--- a/drivers/net/bonding/bond_alb.c
+++ b/drivers/net/bonding/bond_alb.c
@@ -1535,8 +1535,8 @@ void bond_alb_monitor(struct work_struct *work)
struct bonding *bond = container_of(work, struct bonding,
alb_work.work);
struct alb_bond_info *bond_info = &(BOND_ALB_INFO(bond));
+ struct slave *slave, *curr;
struct list_head *iter;
- struct slave *slave;
if (!bond_has_slaves(bond)) {
atomic_set(&bond_info->tx_rebalance_counter, 0);
@@ -1598,9 +1598,11 @@ void bond_alb_monitor(struct work_struct *work)
* because a slave was disabled then
* it can now leave promiscuous mode.
*/
- dev_set_promiscuity(rtnl_dereference(bond->curr_active_slave)->dev,
- -1);
- bond_info->primary_is_promisc = 0;
+ curr = rtnl_dereference(bond->curr_active_slave);
+ if (bond_info->primary_is_promisc && curr) {
+ dev_set_promiscuity(curr->dev, -1);
+ bond_info->primary_is_promisc = 0;
+ }
rtnl_unlock();
rcu_read_lock();
diff --git a/drivers/net/ethernet/amd/pds_core/core.h b/drivers/net/ethernet/amd/pds_core/core.h
index becd3104473c..4dbfe2373b3a 100644
--- a/drivers/net/ethernet/amd/pds_core/core.h
+++ b/drivers/net/ethernet/amd/pds_core/core.h
@@ -170,6 +170,7 @@ struct pdsc {
struct timer_list wdtimer;
unsigned int wdtimer_period;
struct work_struct health_work;
+ bool health_stopped;
struct devlink_health_reporter *fw_reporter;
u32 fw_recoveries;
diff --git a/drivers/net/ethernet/amd/pds_core/main.c b/drivers/net/ethernet/amd/pds_core/main.c
index c78b17d230a8..9526223a7297 100644
--- a/drivers/net/ethernet/amd/pds_core/main.c
+++ b/drivers/net/ethernet/amd/pds_core/main.c
@@ -464,8 +464,10 @@ static void pdsc_stop_health_thread(struct pdsc *pdsc)
return;
timer_shutdown_sync(&pdsc->wdtimer);
- if (pdsc->health_work.func)
- cancel_work_sync(&pdsc->health_work);
+ if (pdsc->health_work.func && !pdsc->health_stopped) {
+ disable_work_sync(&pdsc->health_work);
+ pdsc->health_stopped = true;
+ }
}
static void pdsc_restart_health_thread(struct pdsc *pdsc)
@@ -473,6 +475,10 @@ static void pdsc_restart_health_thread(struct pdsc *pdsc)
if (pdsc->pdev->is_virtfn)
return;
+ if (pdsc->health_stopped) {
+ enable_work(&pdsc->health_work);
+ pdsc->health_stopped = false;
+ }
timer_setup(&pdsc->wdtimer, pdsc_wdtimer_cb, 0);
mod_timer(&pdsc->wdtimer, jiffies + 1);
}
@@ -544,7 +550,11 @@ static pci_ers_result_t pdsc_pci_error_detected(struct pci_dev *pdev,
pci_channel_state_t error)
{
if (error == pci_channel_io_frozen) {
+ struct pdsc *pdsc = pci_get_drvdata(pdev);
+
pdsc_reset_prepare(pdev);
+ if (!pdev->is_virtfn)
+ cancel_work_sync(&pdsc->pci_reset_work);
return PCI_ERS_RESULT_NEED_RESET;
}
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_ring.c b/drivers/net/ethernet/aquantia/atlantic/aq_ring.c
index d23d23bed39f..1579b19c36a7 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_ring.c
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_ring.c
@@ -336,6 +336,35 @@ bool aq_ring_tx_clean(struct aq_ring_s *self)
return !!budget;
}
+void aq_ring_tx_deinit(struct aq_ring_s *self)
+{
+ if (!self)
+ return;
+
+ for (; self->sw_head != self->sw_tail;
+ self->sw_head = aq_ring_next_dx(self, self->sw_head)) {
+ struct aq_ring_buff_s *buff = &self->buff_ring[self->sw_head];
+ struct device *ndev = aq_nic_get_dev(self->aq_nic);
+
+ if (buff->is_mapped) {
+ if (buff->is_sop) {
+ dma_unmap_single(ndev, buff->pa, buff->len,
+ DMA_TO_DEVICE);
+ } else {
+ dma_unmap_page(ndev, buff->pa, buff->len,
+ DMA_TO_DEVICE);
+ }
+ }
+
+ if (buff->is_eop) {
+ if (buff->skb)
+ dev_kfree_skb_any(buff->skb);
+ else if (buff->xdpf)
+ xdp_return_frame(buff->xdpf);
+ }
+ }
+}
+
static void aq_rx_checksum(struct aq_ring_s *self,
struct aq_ring_buff_s *buff,
struct sk_buff *skb)
@@ -897,15 +926,29 @@ int aq_ring_rx_fill(struct aq_ring_s *self)
void aq_ring_rx_deinit(struct aq_ring_s *self)
{
- if (!self)
+ unsigned int i;
+
+ if (!self || !self->buff_ring)
return;
- for (; self->sw_head != self->sw_tail;
- self->sw_head = aq_ring_next_dx(self, self->sw_head)) {
- struct aq_ring_buff_s *buff = &self->buff_ring[self->sw_head];
+ /* Release every page still owned by the ring.
+ *
+ * Walking [sw_head, sw_tail) is not enough: refill is batched
+ * (aq_ring_rx_fill() waits for AQ_CFG_RX_REFILL_THRES free slots),
+ * so slots that were cleaned but not yet reposted accumulate in the
+ * [sw_tail, sw_head) gap, and they keep their page for reuse. Walk
+ * the whole ring and release whatever is left.
+ */
+ for (i = 0; i < self->size; i++) {
+ struct aq_ring_buff_s *buff = &self->buff_ring[i];
+
+ if (!buff->rxdata.page)
+ continue;
aq_free_rxpage(&buff->rxdata, aq_nic_get_dev(self->aq_nic));
}
+
+ self->sw_head = self->sw_tail;
}
void aq_ring_free(struct aq_ring_s *self)
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_ring.h b/drivers/net/ethernet/aquantia/atlantic/aq_ring.h
index d627ace850ff..67503c512676 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_ring.h
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_ring.h
@@ -199,6 +199,7 @@ void aq_ring_update_queue_state(struct aq_ring_s *ring);
void aq_ring_queue_wake(struct aq_ring_s *ring);
void aq_ring_queue_stop(struct aq_ring_s *ring);
bool aq_ring_tx_clean(struct aq_ring_s *self);
+void aq_ring_tx_deinit(struct aq_ring_s *self);
int aq_xdp_xmit(struct net_device *dev, int num_frames,
struct xdp_frame **frames, u32 flags);
int aq_ring_rx_clean(struct aq_ring_s *self,
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_vec.c b/drivers/net/ethernet/aquantia/atlantic/aq_vec.c
index 9769ab4f9bef..62b5967b6dcc 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_vec.c
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_vec.c
@@ -275,7 +275,7 @@ void aq_vec_deinit(struct aq_vec_s *self)
for (i = 0U; self->tx_rings > i; ++i) {
ring = self->ring[i];
- aq_ring_tx_clean(&ring[AQ_VEC_TX_ID]);
+ aq_ring_tx_deinit(&ring[AQ_VEC_TX_ID]);
aq_ring_rx_deinit(&ring[AQ_VEC_RX_ID]);
}
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 4970e20b2cb1..2356b7ba7fcf 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -6365,22 +6365,36 @@ int bnxt_get_nr_rss_ctxs(struct bnxt *bp, int rx_rings)
static void bnxt_fill_hw_rss_tbl(struct bnxt *bp, struct bnxt_vnic_info *vnic)
{
bool no_rss = !(vnic->flags & BNXT_VNIC_RSS_FLAG);
- u16 i, j;
+ u16 i, j, min_j = bp->rx_nr_rings - 1;
+
+ if (!vnic->rss_table)
+ goto skip_rss_tbl;
/* Fill the RSS indirection table with ring group ids */
for (i = 0, j = 0; i < HW_HASH_INDEX_SIZE; i++) {
if (!no_rss)
j = bp->rss_indir_tbl[i];
+ min_j = min(j, min_j);
vnic->rss_table[i] = cpu_to_le16(vnic->fw_grp_ids[j]);
}
+
+skip_rss_tbl:
+ if (vnic->rss_table && !no_rss)
+ vnic->default_rx_ring = min_j;
+ else if (vnic->flags & BNXT_VNIC_RFS_FLAG)
+ vnic->default_rx_ring = vnic->vnic_id - 1;
+ else if ((vnic->vnic_id == 1) && BNXT_CHIP_TYPE_NITRO_A0(bp))
+ vnic->default_rx_ring = bp->rx_nr_rings - 1;
+ else
+ vnic->default_rx_ring = 0;
}
static void bnxt_fill_hw_rss_tbl_p5(struct bnxt *bp,
struct bnxt_vnic_info *vnic)
{
+ u16 tbl_size, i, min_j = bp->rx_nr_rings - 1;
__le16 *ring_tbl = vnic->rss_table;
struct bnxt_rx_ring_info *rxr;
- u16 tbl_size, i;
tbl_size = bnxt_get_rxfh_indir_size(bp->dev);
@@ -6393,6 +6407,7 @@ static void bnxt_fill_hw_rss_tbl_p5(struct bnxt *bp,
j = ethtool_rxfh_context_indir(vnic->rss_ctx)[i];
else
j = bp->rss_indir_tbl[i];
+ min_j = min(j, min_j);
rxr = &bp->rx_ring[j];
ring_id = rxr->rx_ring_struct.fw_ring_id;
@@ -6400,19 +6415,15 @@ static void bnxt_fill_hw_rss_tbl_p5(struct bnxt *bp,
ring_id = bnxt_cp_ring_for_rx(bp, rxr);
*ring_tbl++ = cpu_to_le16(ring_id);
}
+ vnic->default_rx_ring = min_j;
}
static void
__bnxt_hwrm_vnic_set_rss(struct bnxt *bp, struct hwrm_vnic_rss_cfg_input *req,
struct bnxt_vnic_info *vnic)
{
- if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS) {
- bnxt_fill_hw_rss_tbl_p5(bp, vnic);
- if (bp->flags & BNXT_FLAG_CHIP_P7)
- req->flags |= VNIC_RSS_CFG_REQ_FLAGS_IPSEC_HASH_TYPE_CFG_SUPPORT;
- } else {
- bnxt_fill_hw_rss_tbl(bp, vnic);
- }
+ if (bp->flags & BNXT_FLAG_CHIP_P7)
+ req->flags |= VNIC_RSS_CFG_REQ_FLAGS_IPSEC_HASH_TYPE_CFG_SUPPORT;
if (bp->rss_hash_delta) {
req->hash_type = cpu_to_le32(bp->rss_hash_delta);
@@ -6464,6 +6475,7 @@ static int bnxt_hwrm_vnic_set_rss_p5(struct bnxt *bp,
if (!set_rss)
return hwrm_req_send(bp, req);
+ bnxt_fill_hw_rss_tbl_p5(bp, vnic);
__bnxt_hwrm_vnic_set_rss(bp, req, vnic);
ring_tbl_map = vnic->rss_table_dma_addr;
nr_ctxs = bnxt_get_nr_rss_ctxs(bp, bp->rx_nr_rings);
@@ -6601,8 +6613,9 @@ int bnxt_hwrm_vnic_cfg(struct bnxt *bp, struct bnxt_vnic_info *vnic)
return rc;
if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS) {
- struct bnxt_rx_ring_info *rxr = &bp->rx_ring[0];
+ struct bnxt_rx_ring_info *rxr;
+ rxr = &bp->rx_ring[vnic->default_rx_ring];
req->default_rx_ring_id =
cpu_to_le16(rxr->rx_ring_struct.fw_ring_id);
req->default_cmpl_ring_id =
@@ -6635,13 +6648,7 @@ int bnxt_hwrm_vnic_cfg(struct bnxt *bp, struct bnxt_vnic_info *vnic)
req->cos_rule = cpu_to_le16(0xffff);
}
- if (vnic->flags & BNXT_VNIC_RSS_FLAG)
- ring = 0;
- else if (vnic->flags & BNXT_VNIC_RFS_FLAG)
- ring = vnic->vnic_id - 1;
- else if ((vnic->vnic_id == 1) && BNXT_CHIP_TYPE_NITRO_A0(bp))
- ring = bp->rx_nr_rings - 1;
-
+ ring = vnic->default_rx_ring;
grp_idx = bp->rx_ring[ring].bnapi->index;
req->dflt_ring_grp = cpu_to_le16(bp->grp_info[grp_idx].fw_grp_id);
req->lb_rule = cpu_to_le16(0xffff);
@@ -10299,6 +10306,7 @@ static int __bnxt_setup_vnic(struct bnxt *bp, struct bnxt_vnic_info *vnic)
}
skip_rss_ctx:
+ bnxt_fill_hw_rss_tbl(bp, vnic);
/* configure default vnic, ring grp */
rc = bnxt_hwrm_vnic_cfg(bp, vnic);
if (rc) {
@@ -10523,6 +10531,11 @@ static int bnxt_set_vnic_mru_p5(struct bnxt *bp, struct bnxt_vnic_info *vnic,
vnic->vnic_id, rc);
return rc;
}
+ if (rxr_id == vnic->default_rx_ring) {
+ rc = bnxt_hwrm_vnic_cfg(bp, vnic);
+ if (rc)
+ return rc;
+ }
}
vnic->mru = mru;
bnxt_hwrm_vnic_update(bp, vnic,
@@ -10604,6 +10617,9 @@ static int bnxt_setup_nitroa0_vnic(struct bnxt *bp)
return rc;
}
+ /* Setup the proper default RX ring */
+ bnxt_fill_hw_rss_tbl(bp, vnic);
+
rc = bnxt_hwrm_vnic_cfg(bp, vnic);
if (rc) {
netdev_err(bp->dev, "Cannot allocate special vnic for NS2 A0: %x\n",
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
index 37fb74f18eee..f50fe72f83ac 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
@@ -1300,6 +1300,7 @@ struct bnxt_vnic_info {
#define BNXT_VNIC_RSSCTX_FLAG 0x40
struct ethtool_rxfh_context *rss_ctx;
u32 vnic_id;
+ u16 default_rx_ring;
};
struct bnxt_rss_ctx {
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c
index 6dfa0ab74c33..02276b9ac5c6 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c
@@ -494,12 +494,15 @@ static int bnxt_ptp_enable(struct ptp_clock_info *ptp_info,
return rc;
case PTP_CLK_REQ_PPS:
/* Configure PHC PPS IN */
- rc = bnxt_ptp_cfg_pin(bp, 0, BNXT_PPS_PIN_PPS_IN);
+ pin_id = 0;
+ if (!on)
+ break;
+ rc = bnxt_ptp_cfg_pin(bp, pin_id, BNXT_PPS_PIN_PPS_IN);
if (rc)
return rc;
rc = bnxt_ptp_cfg_event(bp, BNXT_PPS_EVENT_INTERNAL);
if (!rc)
- ptp->pps_info.pins[0].event = BNXT_PPS_EVENT_INTERNAL;
+ ptp->pps_info.pins[pin_id].event = BNXT_PPS_EVENT_INTERNAL;
return rc;
default:
netdev_err(ptp->bp->dev, "Unrecognized PIN function\n");
diff --git a/drivers/net/ethernet/cisco/enic/enic_main.c b/drivers/net/ethernet/cisco/enic/enic_main.c
index a432783756d8..e474cef72063 100644
--- a/drivers/net/ethernet/cisco/enic/enic_main.c
+++ b/drivers/net/ethernet/cisco/enic/enic_main.c
@@ -3141,8 +3141,9 @@ static void enic_remove(struct pci_dev *pdev)
if (netdev) {
struct enic *enic = netdev_priv(netdev);
- cancel_work_sync(&enic->reset);
- cancel_work_sync(&enic->change_mtu_work);
+ disable_work_sync(&enic->reset);
+ disable_work_sync(&enic->tx_hang_reset);
+ disable_work_sync(&enic->change_mtu_work);
unregister_netdev(netdev);
enic_dev_deinit(enic);
vnic_dev_close(enic->vdev);
diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c
index d8189c433847..22cd47d19ce2 100644
--- a/drivers/net/ethernet/freescale/fec_main.c
+++ b/drivers/net/ethernet/freescale/fec_main.c
@@ -3323,8 +3323,15 @@ static void fec_enet_free_buffers(struct net_device *ndev)
for (q = 0; q < fep->num_rx_queues; q++) {
rxq = fep->rx_queue[q];
- for (i = 0; i < rxq->bd.ring_size; i++)
- page_pool_put_full_page(rxq->page_pool, rxq->rx_skb_info[i].page, false);
+ for (i = 0; i < rxq->bd.ring_size; i++) {
+ struct page *page = rxq->rx_skb_info[i].page;
+
+ if (!page)
+ continue;
+
+ page_pool_put_full_page(rxq->page_pool, page, false);
+ rxq->rx_skb_info[i].page = NULL;
+ }
for (i = 0; i < XDP_STATS_TOTAL; i++)
rxq->stats[i] = 0;
diff --git a/drivers/net/ethernet/hisilicon/hix5hd2_gmac.c b/drivers/net/ethernet/hisilicon/hix5hd2_gmac.c
index 1a972b093a42..cc1d04d05e4b 100644
--- a/drivers/net/ethernet/hisilicon/hix5hd2_gmac.c
+++ b/drivers/net/ethernet/hisilicon/hix5hd2_gmac.c
@@ -1282,7 +1282,6 @@ static void hix5hd2_dev_remove(struct platform_device *pdev)
struct net_device *ndev = platform_get_drvdata(pdev);
struct hix5hd2_priv *priv = netdev_priv(ndev);
- netif_napi_del(&priv->napi);
unregister_netdev(ndev);
mdiobus_unregister(priv->bus);
mdiobus_free(priv->bus);
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
index 79858b06c97b..786aefc3d107 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
@@ -11930,12 +11930,8 @@ static int hclge_init_ae_dev(struct hnae3_ae_dev *ae_dev)
if (ret)
goto err_ptp_uninit;
- if (hdev->hw.mac.media_type != HNAE3_MEDIA_TYPE_COPPER) {
+ if (hdev->hw.mac.media_type != HNAE3_MEDIA_TYPE_COPPER)
hdev->hw.mac.req_autoneg = hdev->hw.mac.autoneg;
- if (hdev->hw.mac.autoneg == AUTONEG_DISABLE &&
- hdev->hw.mac.speed != SPEED_UNKNOWN)
- hdev->hw.mac.req_speed = hdev->hw.mac.speed;
- }
ret = hclge_set_autoneg_speed_dup(hdev);
if (ret) {
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_tc.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_tc.c
index b26fc848430f..14f3d01e440c 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_tc.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_tc.c
@@ -78,10 +78,12 @@ static void otx2_get_egress_burst_cfg(struct otx2_nic *nic, u32 burst,
if (burst) {
*burst_exp = ilog2(burst) ? ilog2(burst) - 1 : 0;
tmp = burst - rounddown_pow_of_two(burst);
- if (burst < max_mantissa)
+ if (burst <= max_mantissa) {
*burst_mantissa = tmp * 2;
- else
+ } else {
+ WARN_ON(*burst_exp < 7);
*burst_mantissa = tmp / (1ULL << (*burst_exp - 7));
+ }
} else {
*burst_exp = MAX_BURST_EXPONENT;
*burst_mantissa = max_mantissa;
diff --git a/drivers/net/ethernet/marvell/prestera/prestera_pci.c b/drivers/net/ethernet/marvell/prestera/prestera_pci.c
index 35857dc19542..5db2c9e5e077 100644
--- a/drivers/net/ethernet/marvell/prestera/prestera_pci.c
+++ b/drivers/net/ethernet/marvell/prestera/prestera_pci.c
@@ -684,6 +684,9 @@ static int prestera_fw_hdr_parse(struct prestera_fw *fw)
struct prestera_fw_header *hdr;
u32 magic;
+ if (fw->bin->size < sizeof(*hdr))
+ return -EINVAL;
+
hdr = (struct prestera_fw_header *)fw->bin->data;
magic = be32_to_cpu(hdr->magic_number);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c b/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c
index 0b82a6a133d6..74f68b70ad1c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c
@@ -1025,13 +1025,11 @@ struct mlx5_fw_tracer *mlx5_fw_tracer_create(struct mlx5_core_dev *dev)
tracer = kvzalloc(sizeof(*tracer), GFP_KERNEL);
if (!tracer)
- return ERR_PTR(-ENOMEM);
+ return NULL;
tracer->work_queue = create_singlethread_workqueue("mlx5_fw_tracer");
- if (!tracer->work_queue) {
- err = -ENOMEM;
+ if (!tracer->work_queue)
goto free_tracer;
- }
tracer->dev = dev;
@@ -1073,7 +1071,7 @@ struct mlx5_fw_tracer *mlx5_fw_tracer_create(struct mlx5_core_dev *dev)
destroy_workqueue(tracer->work_queue);
free_tracer:
kvfree(tracer);
- return ERR_PTR(err);
+ return NULL;
}
static int fw_tracer_event(struct notifier_block *nb, unsigned long action, void *data);
@@ -1084,7 +1082,7 @@ int mlx5_fw_tracer_init(struct mlx5_fw_tracer *tracer)
struct mlx5_core_dev *dev;
int err;
- if (IS_ERR_OR_NULL(tracer))
+ if (!tracer)
return 0;
if (!tracer->str_db.loaded)
@@ -1134,7 +1132,7 @@ int mlx5_fw_tracer_init(struct mlx5_fw_tracer *tracer)
/* Stop tracer + Cleanup HW resources */
void mlx5_fw_tracer_cleanup(struct mlx5_fw_tracer *tracer)
{
- if (IS_ERR_OR_NULL(tracer))
+ if (!tracer)
return;
mutex_lock(&tracer->state_lock);
@@ -1163,7 +1161,7 @@ void mlx5_fw_tracer_cleanup(struct mlx5_fw_tracer *tracer)
/* Free software resources (Buffers, etc ..) */
void mlx5_fw_tracer_destroy(struct mlx5_fw_tracer *tracer)
{
- if (IS_ERR_OR_NULL(tracer))
+ if (!tracer)
return;
mlx5_core_dbg(tracer->dev, "FWTracer: Destroy\n");
@@ -1215,7 +1213,7 @@ int mlx5_fw_tracer_reload(struct mlx5_fw_tracer *tracer)
struct mlx5_core_dev *dev;
int err;
- if (IS_ERR_OR_NULL(tracer))
+ if (!tracer)
return 0;
dev = tracer->dev;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_priv.h b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_priv.h
index efb34de4cb7a..692ac2f21d94 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_priv.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_priv.h
@@ -30,6 +30,7 @@ enum {
MLX5E_TC_FLOW_FLAG_FAILED = MLX5E_TC_FLOW_BASE + 9,
MLX5E_TC_FLOW_FLAG_SAMPLE = MLX5E_TC_FLOW_BASE + 10,
MLX5E_TC_FLOW_FLAG_USE_ACT_STATS = MLX5E_TC_FLOW_BASE + 11,
+ MLX5E_TC_FLOW_FLAG_PEER = MLX5E_TC_FLOW_BASE + 12,
};
struct mlx5e_tc_flow_parse_attr {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index 8878990254f4..a5ae17931067 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -2161,7 +2161,8 @@ static void mlx5e_tc_del_flow(struct mlx5e_priv *priv,
if (mlx5e_is_eswitch_flow(flow)) {
struct mlx5_devcom_comp_dev *devcom = flow->priv->mdev->priv.eswitch->devcom;
- if (!mlx5_devcom_for_each_peer_begin(devcom)) {
+ if (flow_flag_test(flow, PEER) ||
+ !mlx5_devcom_for_each_peer_begin(devcom)) {
mlx5e_tc_del_fdb_flow(priv, flow);
return;
}
@@ -4605,6 +4606,7 @@ static int mlx5e_tc_add_fdb_peer_flow(struct flow_cls_offload *f,
else
in_mdev = priv->mdev;
+ flow_flags |= BIT(MLX5E_TC_FLOW_FLAG_PEER);
parse_attr = flow->attr->parse_attr;
peer_flow = __mlx5e_add_fdb_flow(peer_priv, f, flow_flags,
parse_attr->filter_dev,
diff --git a/drivers/net/thunderbolt/main.c b/drivers/net/thunderbolt/main.c
index 5d7d11d75b0b..ceaba08cd378 100644
--- a/drivers/net/thunderbolt/main.c
+++ b/drivers/net/thunderbolt/main.c
@@ -389,11 +389,16 @@ static void tbnet_tear_down(struct tbnet *net, bool send_logout)
break;
}
- tb_ring_stop(net->rx_ring.ring);
- tb_ring_stop(net->tx_ring.ring);
- tbnet_free_buffers(&net->rx_ring);
- tbnet_free_buffers(&net->tx_ring);
-
+ /* Tear the paths down before stopping the rings. This mirrors
+ * tbnet_connected_work(), which enables the paths last so the
+ * Rx ring is primed before packets can arrive. Stopping a
+ * ring zeroes its descriptor base and tbnet_free_buffers()
+ * unmaps and frees the frame buffers, leaving anything still
+ * in flight with nowhere to drain to;
+ * __tb_path_deactivate_hop() then waits for the hop's
+ * 'pending' bit, which on some host routers never clears in
+ * that state.
+ */
ret = tb_xdomain_disable_paths(net->xd,
net->local_transmit_path,
net->tx_ring.ring->hop,
@@ -402,6 +407,11 @@ static void tbnet_tear_down(struct tbnet *net, bool send_logout)
if (ret)
netdev_warn(net->dev, "failed to disable DMA paths\n");
+ tb_ring_stop(net->rx_ring.ring);
+ tb_ring_stop(net->tx_ring.ring);
+ tbnet_free_buffers(&net->rx_ring);
+ tbnet_free_buffers(&net->tx_ring);
+
tb_xdomain_release_in_hopid(net->xd, net->remote_transmit_path);
net->remote_transmit_path = 0;
}
@@ -928,12 +938,8 @@ static int tbnet_open(struct net_device *dev)
netif_carrier_off(dev);
- flags = RING_FLAG_FRAME;
- /* Only enable full E2E if the other end supports it too */
- if (tbnet_e2e && net->svc->prtcstns & TBNET_E2E)
- flags |= RING_FLAG_E2E;
-
- ring = tb_ring_alloc_tx(xd->tb->nhi, -1, TBNET_RING_SIZE, flags);
+ ring = tb_ring_alloc_tx(xd->tb->nhi, -1, TBNET_RING_SIZE,
+ RING_FLAG_FRAME);
if (!ring) {
netdev_err(dev, "failed to allocate Tx ring\n");
return -ENOMEM;
@@ -952,6 +958,11 @@ static int tbnet_open(struct net_device *dev)
sof_mask = BIT(TBIP_PDF_FRAME_START);
eof_mask = BIT(TBIP_PDF_FRAME_END);
+ flags = RING_FLAG_FRAME;
+ /* Only enable full E2E if the other end supports it too */
+ if (tbnet_e2e && net->svc->prtcstns & TBNET_E2E)
+ flags |= RING_FLAG_E2E;
+
ring = tb_ring_alloc_rx(xd->tb->nhi, -1, TBNET_RING_SIZE, flags,
net->tx_ring.ring->hop, sof_mask,
eof_mask, tbnet_start_poll, net);
diff --git a/drivers/net/usb/ax88179_178a.c b/drivers/net/usb/ax88179_178a.c
index b034ef8a73ea..cf40b604f135 100644
--- a/drivers/net/usb/ax88179_178a.c
+++ b/drivers/net/usb/ax88179_178a.c
@@ -1493,8 +1493,10 @@ ax88179_tx_fixup(struct usbnet *dev, struct sk_buff *skb, gfp_t flags)
headroom = skb_headroom(skb) - 8;
- if ((dev->net->features & NETIF_F_SG) && skb_linearize(skb))
+ if ((dev->net->features & NETIF_F_SG) && skb_linearize(skb)) {
+ dev_kfree_skb_any(skb);
return NULL;
+ }
if ((skb_header_cloned(skb) || headroom < 0) &&
pskb_expand_head(skb, headroom < 0 ? 8 : 0, 0, GFP_ATOMIC)) {
diff --git a/drivers/net/usb/ipheth.c b/drivers/net/usb/ipheth.c
index a19789b57190..a86d0a4dbd28 100644
--- a/drivers/net/usb/ipheth.c
+++ b/drivers/net/usb/ipheth.c
@@ -490,6 +490,7 @@ static int ipheth_open(struct net_device *net)
if (retval)
return retval;
+ enable_delayed_work(&dev->carrier_work);
schedule_delayed_work(&dev->carrier_work, IPHETH_CARRIER_CHECK_TIMEOUT);
return retval;
}
@@ -499,7 +500,11 @@ static int ipheth_close(struct net_device *net)
struct ipheth_device *dev = netdev_priv(net);
netif_stop_queue(net);
- cancel_delayed_work_sync(&dev->carrier_work);
+ /* A TX URB can still complete with an error after this point and
+ * try to re-arm the carrier work. Disable it instead of cancelling
+ * it, so that such a schedule_delayed_work() is a no-op.
+ */
+ disable_delayed_work_sync(&dev->carrier_work);
return 0;
}
@@ -633,6 +638,10 @@ static int ipheth_probe(struct usb_interface *intf,
}
INIT_DELAYED_WORK(&dev->carrier_work, ipheth_carrier_check_work);
+ /* Armed only between ipheth_open() and ipheth_close(). Start out
+ * disabled so the enable/disable counts balance from the first open.
+ */
+ disable_delayed_work(&dev->carrier_work);
retval = ipheth_alloc_urbs(dev);
if (retval) {
diff --git a/drivers/net/veth.c b/drivers/net/veth.c
index 918a7130011d..2feb694f58bb 100644
--- a/drivers/net/veth.c
+++ b/drivers/net/veth.c
@@ -865,18 +865,24 @@ static struct sk_buff *veth_xdp_rcv_skb(struct veth_rq *rq,
skb_reset_mac_header(skb);
- /* check if bpf_xdp_adjust_tail was used */
- off = xdp->data_end - orig_data_end;
- if (off != 0)
- __skb_put(skb, off); /* positive on grow, negative on shrink */
-
/* XDP frag metadata (e.g. nr_frags) are updated in eBPF helpers
- * (e.g. bpf_xdp_adjust_tail), we need to update data_len here.
+ * (e.g. bpf_xdp_adjust_tail). Remove the old fragment contribution
+ * from skb->len before updating data_len, then add the new one back.
*/
- if (xdp_buff_has_frags(xdp))
+ skb->len -= skb->data_len;
+ if (xdp_buff_has_frags(xdp)) {
skb->data_len = skb_shinfo(skb)->xdp_frags_size;
- else
+ skb->len += skb->data_len;
+ } else {
skb->data_len = 0;
+ }
+
+ /* Synchronize the skb tail with XDP's updated linear area. */
+ off = xdp->data_end - orig_data_end;
+ if (off != 0) {
+ skb_set_tail_pointer(skb, xdp->data_end - xdp->data);
+ skb->len += off; /* positive on grow, negative on shrink */
+ }
skb->protocol = eth_type_trans(skb, rq->dev);
diff --git a/drivers/net/vxlan/vxlan_core.c b/drivers/net/vxlan/vxlan_core.c
index fdc46f52c7fc..3c62957907ba 100644
--- a/drivers/net/vxlan/vxlan_core.c
+++ b/drivers/net/vxlan/vxlan_core.c
@@ -4462,7 +4462,7 @@ static int vxlan_changelink(struct net_device *dev, struct nlattr *tb[],
if (change_igmp && vxlan_addr_multicast(&dst->remote_ip))
err = vxlan_multicast_leave(vxlan);
- if (conf.age_interval != vxlan->cfg.age_interval)
+ if (netif_running(dev) && conf.age_interval != vxlan->cfg.age_interval)
mod_timer(&vxlan->age_timer, jiffies);
netdev_adjacent_change_commit(dst->remote_dev, lowerdev, dev);
diff --git a/drivers/nvmem/core.c b/drivers/nvmem/core.c
index 2edc9cea2bda..2ba16adaf731 100644
--- a/drivers/nvmem/core.c
+++ b/drivers/nvmem/core.c
@@ -811,7 +811,7 @@ static int nvmem_validate_keepouts(struct nvmem_device *nvmem)
return 0;
}
-static int nvmem_add_cells_from_dt(struct nvmem_device *nvmem, struct device_node *np)
+int nvmem_add_cells_from_dt(struct nvmem_device *nvmem, struct device_node *np)
{
struct device *dev = &nvmem->dev;
struct device_node *child;
@@ -863,29 +863,13 @@ static int nvmem_add_cells_from_dt(struct nvmem_device *nvmem, struct device_nod
return 0;
}
+EXPORT_SYMBOL_GPL(nvmem_add_cells_from_dt);
static int nvmem_add_cells_from_legacy_of(struct nvmem_device *nvmem)
{
return nvmem_add_cells_from_dt(nvmem, nvmem->dev.of_node);
}
-static int nvmem_add_cells_from_fixed_layout(struct nvmem_device *nvmem)
-{
- struct device_node *layout_np;
- int err = 0;
-
- layout_np = of_nvmem_layout_get_container(nvmem);
- if (!layout_np)
- return 0;
-
- if (of_device_is_compatible(layout_np, "fixed-layout"))
- err = nvmem_add_cells_from_dt(nvmem, layout_np);
-
- of_node_put(layout_np);
-
- return err;
-}
-
int nvmem_layout_register(struct nvmem_layout *layout)
{
int ret;
@@ -1038,10 +1022,6 @@ struct nvmem_device *nvmem_register(const struct nvmem_config *config)
goto err_remove_cells;
}
- rval = nvmem_add_cells_from_fixed_layout(nvmem);
- if (rval)
- goto err_remove_cells;
-
dev_dbg(&nvmem->dev, "Registering nvmem device %s\n", config->name);
rval = device_add(&nvmem->dev);
diff --git a/drivers/nvmem/internals.h b/drivers/nvmem/internals.h
index 18fed57270e5..f6d452b6a28f 100644
--- a/drivers/nvmem/internals.h
+++ b/drivers/nvmem/internals.h
@@ -35,6 +35,8 @@ struct nvmem_device {
bool sysfs_cells_populated;
};
+int nvmem_add_cells_from_dt(struct nvmem_device *nvmem, struct device_node *np);
+
#if IS_ENABLED(CONFIG_OF)
int nvmem_layout_bus_register(void);
void nvmem_layout_bus_unregister(void);
diff --git a/drivers/nvmem/layouts.c b/drivers/nvmem/layouts.c
index 7ebe53249035..0e84d65b42d4 100644
--- a/drivers/nvmem/layouts.c
+++ b/drivers/nvmem/layouts.c
@@ -125,11 +125,6 @@ static int nvmem_layout_create_device(struct nvmem_device *nvmem,
return 0;
}
-static const struct of_device_id of_nvmem_layout_skip_table[] = {
- { .compatible = "fixed-layout", },
- {}
-};
-
static int nvmem_layout_bus_populate(struct nvmem_device *nvmem,
struct device_node *layout_dn)
{
@@ -142,12 +137,6 @@ static int nvmem_layout_bus_populate(struct nvmem_device *nvmem,
return 0;
}
- /* Fixed layouts are parsed manually somewhere else for now */
- if (of_match_node(of_nvmem_layout_skip_table, layout_dn)) {
- pr_debug("%s() - skipping %pOF node\n", __func__, layout_dn);
- return 0;
- }
-
if (of_node_check_flag(layout_dn, OF_POPULATED_BUS)) {
pr_debug("%s() - skipping %pOF, already populated\n",
__func__, layout_dn);
diff --git a/drivers/nvmem/layouts/Makefile b/drivers/nvmem/layouts/Makefile
index 4940c9db0665..dd6c6c70b1a9 100644
--- a/drivers/nvmem/layouts/Makefile
+++ b/drivers/nvmem/layouts/Makefile
@@ -3,6 +3,7 @@
# Makefile for nvmem layouts.
#
+obj-$(CONFIG_NVMEM_LAYOUTS) += fixed-layout.o
obj-$(CONFIG_NVMEM_LAYOUT_SL28_VPD) += sl28vpd.o
obj-$(CONFIG_NVMEM_LAYOUT_ONIE_TLV) += onie-tlv.o
obj-$(CONFIG_NVMEM_LAYOUT_U_BOOT_ENV) += u-boot-env.o
diff --git a/drivers/nvmem/layouts/fixed-layout.c b/drivers/nvmem/layouts/fixed-layout.c
new file mode 100644
index 000000000000..635d448b3dd2
--- /dev/null
+++ b/drivers/nvmem/layouts/fixed-layout.c
@@ -0,0 +1,58 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright 2026 Bootlin
+ *
+ * Authors: Mathieu Dubois-Briand <mathieu.dubois-briand@bootlin.com>
+ */
+
+#include <linux/nvmem-provider.h>
+#include <linux/of.h>
+
+#include "../internals.h"
+
+static int fixed_layout_add_cells(struct nvmem_layout *layout)
+{
+ struct device_node *np;
+ int ret;
+
+ np = of_nvmem_layout_get_container(layout->nvmem);
+ if (!np)
+ return -ENOENT;
+
+ ret = nvmem_add_cells_from_dt(layout->nvmem, np);
+ of_node_put(np);
+
+ return ret;
+}
+
+static int fixed_layout_probe(struct nvmem_layout *layout)
+{
+ layout->add_cells = fixed_layout_add_cells;
+
+ return nvmem_layout_register(layout);
+}
+
+static void fixed_layout_remove(struct nvmem_layout *layout)
+{
+ nvmem_layout_unregister(layout);
+}
+
+static const struct of_device_id fixed_layout_of_match_table[] = {
+ { .compatible = "fixed-layout", },
+ {},
+};
+
+static struct nvmem_layout_driver fixed_layout_layout = {
+ .driver = {
+ .name = "fixed-layout",
+ .of_match_table = fixed_layout_of_match_table,
+ },
+ .probe = fixed_layout_probe,
+ .remove = fixed_layout_remove,
+};
+module_nvmem_layout_driver(fixed_layout_layout);
+
+MODULE_AUTHOR("Mathieu Dubois-Briand");
+MODULE_LICENSE("GPL");
+MODULE_DEVICE_TABLE(of, fixed_layout_of_match_table);
+MODULE_DESCRIPTION("NVMEM fixed-layout driver");
diff --git a/drivers/pinctrl/renesas/pinctrl-rzg2l.c b/drivers/pinctrl/renesas/pinctrl-rzg2l.c
index 17e27879fd62..6fd79907f17e 100644
--- a/drivers/pinctrl/renesas/pinctrl-rzg2l.c
+++ b/drivers/pinctrl/renesas/pinctrl-rzg2l.c
@@ -1478,7 +1478,7 @@ static int rzg2l_pinctrl_pinconf_set(struct pinctrl_dev *pctldev,
break;
default:
- return -EOPNOTSUPP;
+ return -ENOTSUPP;
}
}
@@ -1560,7 +1560,7 @@ static int rzg2l_pinctrl_pinconf_group_get(struct pinctrl_dev *pctldev,
/* Check config matching between to pin */
if (i && prev_config != *config)
- return -EOPNOTSUPP;
+ return -ENOTSUPP;
prev_config = *config;
}
diff --git a/drivers/ptp/ptp_ocp.c b/drivers/ptp/ptp_ocp.c
index bd9919c01e50..fce46b88458f 100644
--- a/drivers/ptp/ptp_ocp.c
+++ b/drivers/ptp/ptp_ocp.c
@@ -1914,9 +1914,11 @@ ptp_ocp_devlink_info_get(struct devlink *devlink, struct devlink_info_req *req,
if (err)
return err;
+ snprintf(buf, sizeof(buf), "%.*s", OCP_BOARD_ID_LEN,
+ (const char *)bp->board_id);
err = devlink_info_version_fixed_put(req,
DEVLINK_INFO_VERSION_GENERIC_BOARD_ID,
- bp->board_id);
+ buf);
if (err)
return err;
diff --git a/drivers/s390/crypto/zcrypt_ccamisc.c b/drivers/s390/crypto/zcrypt_ccamisc.c
index 6790afd517ec..48d36d5a8711 100644
--- a/drivers/s390/crypto/zcrypt_ccamisc.c
+++ b/drivers/s390/crypto/zcrypt_ccamisc.c
@@ -938,7 +938,8 @@ static int _ip_cprb_helper(u16 cardnr, u16 domain,
const u8 *clr_key_value,
int clr_key_bit_size,
u8 *key_token,
- int *key_token_size)
+ int *key_token_size,
+ bool scrub)
{
int rc, n;
u8 *mem, *ptr;
@@ -1077,7 +1078,7 @@ static int _ip_cprb_helper(u16 cardnr, u16 domain,
*key_token_size = t->len;
out:
- free_cprbmem(mem, PARMBSIZE, 0);
+ free_cprbmem(mem, PARMBSIZE, scrub);
return rc;
}
@@ -1120,28 +1121,32 @@ int cca_clr2cipherkey(u16 card, u16 dom, u32 keybitsize, u32 keygenflags,
* 4/4 COMPLETE the secure cipher key import
*/
rc = _ip_cprb_helper(card, dom, "AES ", "FIRST ", "MIN3PART",
- exorbuf, keybitsize, token, &tokensize);
+ exorbuf, keybitsize, token, &tokensize,
+ true);
if (rc) {
ZCRYPT_DBF_ERR("%s clear key import 1/4 with CSNBKPI2 failed, rc=%d\n",
__func__, rc);
goto out;
}
rc = _ip_cprb_helper(card, dom, "AES ", "ADD-PART", NULL,
- clrkey, keybitsize, token, &tokensize);
+ clrkey, keybitsize, token, &tokensize,
+ true);
if (rc) {
ZCRYPT_DBF_ERR("%s clear key import 2/4 with CSNBKPI2 failed, rc=%d\n",
__func__, rc);
goto out;
}
rc = _ip_cprb_helper(card, dom, "AES ", "ADD-PART", NULL,
- exorbuf, keybitsize, token, &tokensize);
+ exorbuf, keybitsize, token, &tokensize,
+ true);
if (rc) {
ZCRYPT_DBF_ERR("%s clear key import 3/4 with CSNBKPI2 failed, rc=%d\n",
__func__, rc);
goto out;
}
rc = _ip_cprb_helper(card, dom, "AES ", "COMPLETE", NULL,
- NULL, keybitsize, token, &tokensize);
+ NULL, keybitsize, token, &tokensize,
+ true);
if (rc) {
ZCRYPT_DBF_ERR("%s clear key import 4/4 with CSNBKPI2 failed, rc=%d\n",
__func__, rc);
@@ -1158,7 +1163,8 @@ int cca_clr2cipherkey(u16 card, u16 dom, u32 keybitsize, u32 keygenflags,
*keybufsize = tokensize;
out:
- kfree(token);
+ memzero_explicit(exorbuf, sizeof(exorbuf));
+ kfree_sensitive(token);
return rc;
}
EXPORT_SYMBOL(cca_clr2cipherkey);
diff --git a/drivers/scsi/scsi_debug.c b/drivers/scsi/scsi_debug.c
index 9a194cf64528..de54596bbae9 100644
--- a/drivers/scsi/scsi_debug.c
+++ b/drivers/scsi/scsi_debug.c
@@ -3772,8 +3772,8 @@ static bool comp_write_worker(struct sdeb_store_info *sip, u64 lba, u32 num,
if (!res)
return res;
if (rest)
- res = memcmp(fsp, arr + ((num - rest) * lb_size),
- rest * lb_size);
+ res = !memcmp(fsp, arr + ((num - rest) * lb_size),
+ rest * lb_size);
if (!res)
return res;
if (compare_only)
diff --git a/drivers/spi/spi-fsl-dspi.c b/drivers/spi/spi-fsl-dspi.c
index e26363ae7489..bc7479c834ff 100644
--- a/drivers/spi/spi-fsl-dspi.c
+++ b/drivers/spi/spi-fsl-dspi.c
@@ -746,8 +746,12 @@ static void dspi_setup_accel(struct fsl_dspi *dspi)
struct spi_transfer *xfer = dspi->cur_transfer;
bool odd = !!(dspi->len & 1);
- /* No accel for frames not multiple of 8 bits at the moment */
- if (xfer->bits_per_word % 8)
+ /*
+ * No accel for DMA transfers or frames not multiples of 8 bits at the
+ * moment.
+ */
+ if (dspi->devtype_data->trans_mode == DSPI_DMA_MODE ||
+ xfer->bits_per_word % 8)
goto no_accel;
if (!odd && dspi->len <= dspi->devtype_data->fifo_size * 2) {
@@ -756,10 +760,7 @@ static void dspi_setup_accel(struct fsl_dspi *dspi)
dspi->oper_bits_per_word = 8;
} else {
/* Start off with maximum supported by hardware */
- if (dspi->devtype_data->trans_mode == DSPI_XSPI_MODE)
- dspi->oper_bits_per_word = 32;
- else
- dspi->oper_bits_per_word = 16;
+ dspi->oper_bits_per_word = 32;
/*
* And go down only if the buffer can't be sent with
diff --git a/drivers/staging/rtl8723bs/core/rtw_ieee80211.c b/drivers/staging/rtl8723bs/core/rtw_ieee80211.c
index fe458912e0ec..56938ff47235 100644
--- a/drivers/staging/rtl8723bs/core/rtw_ieee80211.c
+++ b/drivers/staging/rtl8723bs/core/rtw_ieee80211.c
@@ -372,6 +372,9 @@ unsigned char *rtw_get_wpa_ie(unsigned char *pie, int *wpa_ie_len, int limit)
pbuf = rtw_get_ie(pbuf, WLAN_EID_VENDOR_SPECIFIC, &len, limit_new);
if (pbuf) {
+ if (len < 6)
+ goto check_next_ie;
+
/* check if oui matches... */
if (memcmp((pbuf + 2), wpa_oui_type, sizeof(wpa_oui_type)))
goto check_next_ie;
diff --git a/drivers/staging/rtl8723bs/core/rtw_mlme_ext.c b/drivers/staging/rtl8723bs/core/rtw_mlme_ext.c
index 41fda671036b..22c29d1955f5 100644
--- a/drivers/staging/rtl8723bs/core/rtw_mlme_ext.c
+++ b/drivers/staging/rtl8723bs/core/rtw_mlme_ext.c
@@ -904,7 +904,7 @@ unsigned int OnAuthClient(struct adapter *padapter, union recv_frame *precv_fram
p = rtw_get_ie(pframe + WLAN_HDR_A3_LEN + _AUTH_IE_OFFSET_, WLAN_EID_CHALLENGE, (int *)&len,
pkt_len - WLAN_HDR_A3_LEN - _AUTH_IE_OFFSET_);
- if (!p)
+ if (!p || len != WLAN_AUTH_CHALLENGE_LEN)
goto authclnt_fail;
memcpy((void *)(pmlmeinfo->chg_txt), (void *)(p + 2), len);
diff --git a/drivers/staging/rtl8723bs/core/rtw_wlan_util.c b/drivers/staging/rtl8723bs/core/rtw_wlan_util.c
index c71394214c5f..57fb1f2c1152 100644
--- a/drivers/staging/rtl8723bs/core/rtw_wlan_util.c
+++ b/drivers/staging/rtl8723bs/core/rtw_wlan_util.c
@@ -730,6 +730,9 @@ int WMM_param_handler(struct adapter *padapter, struct ndis_80211_var_ie *pIE)
return false;
}
+ if (pIE->length != WLAN_WMM_LEN)
+ return false;
+
if (!memcmp(&(pmlmeinfo->WMM_param), (pIE->data + 6), sizeof(struct WMM_para_element)))
return false;
else
diff --git a/drivers/staging/rtl8723bs/os_dep/ioctl_cfg80211.c b/drivers/staging/rtl8723bs/os_dep/ioctl_cfg80211.c
index 96d4da546725..1b1b29e81de7 100644
--- a/drivers/staging/rtl8723bs/os_dep/ioctl_cfg80211.c
+++ b/drivers/staging/rtl8723bs/os_dep/ioctl_cfg80211.c
@@ -2041,6 +2041,8 @@ static netdev_tx_t rtw_cfg80211_monitor_if_xmit_entry(struct sk_buff *skb, struc
/* Skip the ratio tap header */
skb_pull(skb, rtap_len);
+ if (skb->len < dot11_hdr_len)
+ goto fail;
dot11_hdr = (struct ieee80211_hdr *)skb->data;
frame_control = le16_to_cpu(dot11_hdr->frame_control);
@@ -2053,6 +2055,8 @@ static netdev_tx_t rtw_cfg80211_monitor_if_xmit_entry(struct sk_buff *skb, struc
qos_len = 2;
if ((frame_control & 0x0300) == 0x0300)
dot11_hdr_len += 6;
+ if (skb->len < dot11_hdr_len + qos_len + snap_len)
+ goto fail;
memcpy(dst_mac_addr, dot11_hdr->addr1, sizeof(dst_mac_addr));
memcpy(src_mac_addr, dot11_hdr->addr2, sizeof(src_mac_addr));
diff --git a/drivers/thermal/thermal_hwmon.c b/drivers/thermal/thermal_hwmon.c
index 112188c15c30..3162a1a8cbb6 100644
--- a/drivers/thermal/thermal_hwmon.c
+++ b/drivers/thermal/thermal_hwmon.c
@@ -215,7 +215,8 @@ int thermal_add_hwmon_sysfs(struct thermal_zone_device *tz)
if (new_hwmon_device)
hwmon_device_unregister(hwmon->device);
free_mem:
- kfree(hwmon);
+ if (new_hwmon_device)
+ kfree(hwmon);
return result;
}
diff --git a/drivers/thunderbolt/eeprom.c b/drivers/thunderbolt/eeprom.c
index eb241b270f79..6e76c3432a9a 100644
--- a/drivers/thunderbolt/eeprom.c
+++ b/drivers/thunderbolt/eeprom.c
@@ -392,9 +392,16 @@ static int tb_drom_parse_entry_port(struct tb_switch *sw,
return -EIO;
}
port->link_nr = entry->link_nr;
- if (entry->has_dual_link_port)
+ if (entry->has_dual_link_port) {
+ if (entry->dual_link_port_nr > sw->config.max_port_number) {
+ tb_sw_warn(sw,
+ "port entry has invalid dual link port number %u\n",
+ entry->dual_link_port_nr);
+ return -EIO;
+ }
port->dual_link_port =
&port->sw->ports[entry->dual_link_port_nr];
+ }
}
return 0;
}
diff --git a/drivers/thunderbolt/icm.c b/drivers/thunderbolt/icm.c
index 7859bccc592d..a29cd07f5187 100644
--- a/drivers/thunderbolt/icm.c
+++ b/drivers/thunderbolt/icm.c
@@ -2291,7 +2291,7 @@ static int icm_usb4_switch_op(struct tb_switch *sw, u16 opcode, u32 *metadata,
if (tx_data_len) {
request.data_len_valid |= ICM_USB4_SWITCH_DATA_VALID;
if (tx_data_len < ARRAY_SIZE(request.data))
- request.data_len_valid =
+ request.data_len_valid |=
tx_data_len & ICM_USB4_SWITCH_DATA_LEN_MASK;
memcpy(request.data, tx_data, tx_data_len * sizeof(u32));
}
diff --git a/drivers/thunderbolt/tb.c b/drivers/thunderbolt/tb.c
index 4ef8e67e9987..afcba22f5013 100644
--- a/drivers/thunderbolt/tb.c
+++ b/drivers/thunderbolt/tb.c
@@ -597,7 +597,7 @@ static int tb_consumed_dp_bandwidth(struct tb *tb,
int *consumed_up,
int *consumed_down)
{
- int group_reserved[MAX_GROUPS] = {};
+ int group_reserved[MAX_GROUPS + 1] = {};
struct tb_cm *tcm = tb_priv(tb);
struct tb_tunnel *tunnel;
bool downstream;
diff --git a/drivers/tty/serial/8250/8250_dma.c b/drivers/tty/serial/8250/8250_dma.c
index 3b6452e759d5..5a83e5269b41 100644
--- a/drivers/tty/serial/8250/8250_dma.c
+++ b/drivers/tty/serial/8250/8250_dma.c
@@ -211,11 +211,12 @@ void serial8250_rx_dma_flush(struct uart_8250_port *p)
{
struct uart_8250_dma *dma = p->dma;
- if (dma->rx_running) {
- dmaengine_pause(dma->rxchan);
- __dma_rx_complete(p);
- dmaengine_terminate_async(dma->rxchan);
- }
+ if (!dma || !dma->rxchan || !dma->rx_running)
+ return;
+
+ dmaengine_pause(dma->rxchan);
+ __dma_rx_complete(p);
+ dmaengine_terminate_async(dma->rxchan);
}
EXPORT_SYMBOL_GPL(serial8250_rx_dma_flush);
@@ -324,6 +325,7 @@ void serial8250_release_dma(struct uart_8250_port *p)
/* Release RX resources */
dmaengine_terminate_sync(dma->rxchan);
+ dma->rx_running = 0;
dma_free_coherent(dma->rxchan->device->dev, dma->rx_size, dma->rx_buf,
dma->rx_addr);
dma_release_channel(dma->rxchan);
diff --git a/drivers/tty/serial/qcom_geni_serial.c b/drivers/tty/serial/qcom_geni_serial.c
index cf705b01e8bd..6e5b31ebd5d6 100644
--- a/drivers/tty/serial/qcom_geni_serial.c
+++ b/drivers/tty/serial/qcom_geni_serial.c
@@ -145,6 +145,7 @@ static const struct uart_ops qcom_geni_uart_pops;
static struct uart_driver qcom_geni_console_driver;
static struct uart_driver qcom_geni_uart_driver;
+static void qcom_geni_serial_stop_tx_dma(struct uart_port *uport);
static void __qcom_geni_serial_cancel_tx_cmd(struct uart_port *uport);
static void qcom_geni_serial_cancel_tx_cmd(struct uart_port *uport);
static int qcom_geni_serial_port_setup(struct uart_port *uport);
@@ -600,35 +601,34 @@ static unsigned int qcom_geni_serial_tx_empty(struct uart_port *uport)
return !readl(uport->membase + SE_GENI_TX_FIFO_STATUS);
}
+static void qcom_geni_serial_flush_buffer_dma(struct uart_port *uport)
+{
+ struct qcom_geni_serial_port *port = to_dev_port(uport);
+
+ qcom_geni_serial_stop_tx_dma(uport);
+ port->tx_remaining = 0;
+ port->tx_queued = 0;
+}
+
static void qcom_geni_serial_stop_tx_dma(struct uart_port *uport)
{
struct qcom_geni_serial_port *port = to_dev_port(uport);
- bool done;
- if (!qcom_geni_serial_main_active(uport))
- return;
+ if (qcom_geni_serial_main_active(uport))
+ __qcom_geni_serial_cancel_tx_cmd(uport);
if (port->tx_dma_addr) {
+ writel(1, uport->membase + SE_DMA_TX_FSM_RST);
+ if (!qcom_geni_serial_poll_bit(uport, SE_DMA_TX_IRQ_STAT,
+ TX_RESET_DONE, true))
+ dev_err_ratelimited(uport->dev, "TX DMA reset failed");
+ writel(TX_RESET_DONE | TX_DMA_DONE,
+ uport->membase + SE_DMA_TX_IRQ_CLR);
+
geni_se_tx_dma_unprep(&port->se, port->tx_dma_addr,
port->tx_remaining);
port->tx_dma_addr = 0;
- port->tx_remaining = 0;
}
-
- geni_se_cancel_m_cmd(&port->se);
-
- done = qcom_geni_serial_poll_bit(uport, SE_GENI_M_IRQ_STATUS,
- M_CMD_CANCEL_EN, true);
- if (!done) {
- geni_se_abort_m_cmd(&port->se);
- done = qcom_geni_serial_poll_bit(uport, SE_GENI_M_IRQ_STATUS,
- M_CMD_ABORT_EN, true);
- if (!done)
- dev_err_ratelimited(uport->dev, "M_CMD_ABORT_EN not set");
- writel(M_CMD_ABORT_EN, uport->membase + SE_GENI_M_IRQ_CLEAR);
- }
-
- writel(M_CMD_CANCEL_EN, uport->membase + SE_GENI_M_IRQ_CLEAR);
}
static void qcom_geni_serial_start_tx_dma(struct uart_port *uport)
@@ -1140,7 +1140,7 @@ static void qcom_geni_serial_shutdown(struct uart_port *uport)
uart_port_unlock_irq(uport);
}
-static void qcom_geni_serial_flush_buffer(struct uart_port *uport)
+static void qcom_geni_serial_flush_buffer_fifo(struct uart_port *uport)
{
qcom_geni_serial_cancel_tx_cmd(uport);
}
@@ -1614,7 +1614,7 @@ static const struct uart_ops qcom_geni_console_pops = {
.request_port = qcom_geni_serial_request_port,
.config_port = qcom_geni_serial_config_port,
.shutdown = qcom_geni_serial_shutdown,
- .flush_buffer = qcom_geni_serial_flush_buffer,
+ .flush_buffer = qcom_geni_serial_flush_buffer_fifo,
.type = qcom_geni_serial_get_type,
.set_mctrl = qcom_geni_serial_set_mctrl,
.get_mctrl = qcom_geni_serial_get_mctrl,
@@ -1637,6 +1637,7 @@ static const struct uart_ops qcom_geni_uart_pops = {
.request_port = qcom_geni_serial_request_port,
.config_port = qcom_geni_serial_config_port,
.shutdown = qcom_geni_serial_shutdown,
+ .flush_buffer = qcom_geni_serial_flush_buffer_dma,
.type = qcom_geni_serial_get_type,
.set_mctrl = qcom_geni_serial_set_mctrl,
.get_mctrl = qcom_geni_serial_get_mctrl,
diff --git a/drivers/tty/vt/keyboard.c b/drivers/tty/vt/keyboard.c
index 00caf1c2bcee..5d1e107574d1 100644
--- a/drivers/tty/vt/keyboard.c
+++ b/drivers/tty/vt/keyboard.c
@@ -1403,7 +1403,7 @@ static void kbd_keycode(unsigned int keycode, int down, bool hw_raw)
struct keyboard_notifier_param param = { .vc = vc, .value = keycode, .down = down };
int rc;
- tty = vc->port.tty;
+ tty = tty_port_tty_get(&vc->port);
if (tty && (!tty->driver_data)) {
/* No driver data? Strange. Okay we fix it then. */
@@ -1463,9 +1463,12 @@ static void kbd_keycode(unsigned int keycode, int down, bool hw_raw)
* characters get aren't echoed locally. This makes key repeat
* usable with slow applications and under heavy loads.
*/
+ tty_kref_put(tty);
return;
}
+ tty_kref_put(tty);
+
param.shift = shift_final = (shift_state | kbd->slockstate) ^ kbd->lockstate;
param.ledstate = kbd->ledflagstate;
key_map = key_maps[shift_final];
diff --git a/drivers/tty/vt/vt_ioctl.c b/drivers/tty/vt/vt_ioctl.c
index da82a79c1511..1e8e5c161124 100644
--- a/drivers/tty/vt/vt_ioctl.c
+++ b/drivers/tty/vt/vt_ioctl.c
@@ -408,6 +408,8 @@ static int vt_k_ioctl(struct tty_struct *tty, unsigned int cmd,
/* this could be folded into KDSKBMODE, but for compatibility
reasons it is not so easy to fold KDGKBMETA into KDGKBMODE */
case KDSKBMETA:
+ if (!perm)
+ return -EPERM;
return vt_do_kdskbmeta(console, arg);
case KDGKBMETA:
diff --git a/drivers/usb/atm/cxacru.c b/drivers/usb/atm/cxacru.c
index 08faf82ec31d..cf506afaaa0a 100644
--- a/drivers/usb/atm/cxacru.c
+++ b/drivers/usb/atm/cxacru.c
@@ -700,6 +700,8 @@ static int cxacru_cm(struct cxacru_data *instance, enum cxacru_cm_request cm,
ret = offd;
usb_dbg(instance->usbatm, "cm %#x\n", cm);
fail:
+ if (ret < 0)
+ usb_kill_urb(instance->rcv_urb);
mutex_unlock(&instance->cm_serialize);
err:
return ret;
diff --git a/drivers/usb/cdns3/cdnsp-gadget.c b/drivers/usb/cdns3/cdnsp-gadget.c
index fb192b120d77..89d3d8167e59 100644
--- a/drivers/usb/cdns3/cdnsp-gadget.c
+++ b/drivers/usb/cdns3/cdnsp-gadget.c
@@ -154,9 +154,9 @@ static void cdnsp_set_apb_timeout_value(struct cdnsp_device *pdev)
offset = cdnsp_find_next_ext_cap(base, offset, D_XEC_PRE_REGS_CAP);
reg = base + offset + REG_CHICKEN_BITS_3_OFFSET;
- val = le32_to_cpu(readl(reg));
+ val = readl(reg);
val = CHICKEN_APB_TIMEOUT_SET(val, cdns->override_apb_timeout);
- writel(cpu_to_le32(val), reg);
+ writel(val, reg);
}
static void cdnsp_set_chicken_bits_2(struct cdnsp_device *pdev, u32 bit)
diff --git a/drivers/usb/gadget/function/f_ncm.c b/drivers/usb/gadget/function/f_ncm.c
index a6a14500b650..1b47fbe989e1 100644
--- a/drivers/usb/gadget/function/f_ncm.c
+++ b/drivers/usb/gadget/function/f_ncm.c
@@ -1171,7 +1171,7 @@ static int ncm_unwrap_ntb(struct gether *port,
unsigned char *ntb_ptr = skb->data;
__le16 *tmp;
unsigned index, index2;
- int ndp_index;
+ unsigned int ndp_index;
unsigned dg_len, dg_len2;
unsigned ndp_len;
unsigned block_len;
diff --git a/drivers/vdpa/mlx5/core/mr.c b/drivers/vdpa/mlx5/core/mr.c
index c7a20278bc3c..27abbe69b55c 100644
--- a/drivers/vdpa/mlx5/core/mr.c
+++ b/drivers/vdpa/mlx5/core/mr.c
@@ -234,7 +234,8 @@ static int create_direct_keys(struct mlx5_vdpa_dev *mvdev, struct mlx5_vdpa_mr *
cmds[i].out = cmd_mem->out;
cmds[i].outlen = sizeof(cmd_mem->out);
cmds[i].in = cmd_mem->in;
- cmds[i].inlen = struct_size(cmd_mem, mtt, mttcount);
+ cmds[i].inlen = struct_size(cmd_mem, mtt, mttcount) -
+ offsetof(struct mlx5_create_mkey_mem, in);
fill_create_direct_mr(mvdev, dmr, cmd_mem);
diff --git a/drivers/vhost/vdpa.c b/drivers/vhost/vdpa.c
index 2464c9de6771..a47fdcb61bf3 100644
--- a/drivers/vhost/vdpa.c
+++ b/drivers/vhost/vdpa.c
@@ -1102,6 +1102,7 @@ static int vhost_vdpa_pa_map(struct vhost_vdpa *v,
unsigned int gup_flags = FOLL_LONGTERM;
unsigned long npages, cur_base, map_pfn, last_pfn = 0;
unsigned long lock_limit, sz2pin, nchunks, i;
+ unsigned long page_offset;
u64 start = iova;
long pinned;
int ret = 0;
@@ -1114,7 +1115,13 @@ static int vhost_vdpa_pa_map(struct vhost_vdpa *v,
if (perm & VHOST_ACCESS_WO)
gup_flags |= FOLL_WRITE;
- npages = PFN_UP(size + (iova & ~PAGE_MASK));
+ page_offset = iova & ~PAGE_MASK;
+ if (size > ULONG_MAX - page_offset) {
+ ret = -EINVAL;
+ goto free;
+ }
+
+ npages = PFN_UP(size + page_offset);
if (!npages) {
ret = -EINVAL;
goto free;
diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c
index 68027fd993e3..f966fc094f12 100644
--- a/drivers/vhost/vhost.c
+++ b/drivers/vhost/vhost.c
@@ -2125,6 +2125,14 @@ static long vhost_vring_set_num_addr(struct vhost_dev *d,
BUG();
}
+ /*
+ * The metadata cache holds the IOTLB mapping that backed the previous
+ * desc/avail/used addresses and vring size, both of which are being
+ * replaced here. iotlb_access_ok() takes a cache hit as proof that the
+ * region was validated, so the stale entries have to go.
+ */
+ __vhost_vq_meta_reset(vq);
+
mutex_unlock(&vq->mutex);
return r;
diff --git a/drivers/video/fbdev/core/bitblit.c b/drivers/video/fbdev/core/bitblit.c
index bed8ba18222b..8f6a2d1736d3 100644
--- a/drivers/video/fbdev/core/bitblit.c
+++ b/drivers/video/fbdev/core/bitblit.c
@@ -274,9 +274,14 @@ static void bit_cursor(struct vc_data *vc, struct fb_info *info, bool enable,
if (!vc->vc_font.data)
return;
- c = scr_readw((u16 *) vc->vc_pos);
+ c = scr_readw((u16 *) vc->vc_pos);
attribute = get_attribute(info, c);
- src = vc->vc_font.data + ((c & charmask) * (w * vc->vc_font.height));
+ c &= charmask;
+
+ /* Clamp to font size, same as bit_putcs_aligned() */
+ if (c >= vc->vc_font.charcount)
+ c = 0;
+ src = vc->vc_font.data + (c * (w * vc->vc_font.height));
if (par->cursor_state.image.data != src ||
par->cursor_reset) {
diff --git a/drivers/watchdog/bd96801_wdt.c b/drivers/watchdog/bd96801_wdt.c
index 12b74fd2bc05..a25b7cf1488b 100644
--- a/drivers/watchdog/bd96801_wdt.c
+++ b/drivers/watchdog/bd96801_wdt.c
@@ -169,7 +169,6 @@ static int bd96801_set_wdt_mode(struct wdtbd96801 *w, unsigned int hw_margin,
int fastng, slowng, type, ret, reg, mask;
struct device *dev = w->dev;
-
if (hw_margin_min * 1000 > FASTNG_MAX_US) {
dev_err(dev, "Unsupported fast timeout %u uS [max %u]\n",
hw_margin_min * 1000, FASTNG_MAX_US);
@@ -258,10 +257,10 @@ static int bd96801_set_heartbeat_from_hw(struct wdtbd96801 *w,
fast = FASTNG_MIN << sel;
sel = (val & BD96801_WD_RATIO_MASK) + 1;
- w->wdt.max_hw_heartbeat_ms = (fast << sel) / USEC_PER_MSEC;
+ w->wdt.max_hw_heartbeat_ms = (fast << sel) / 10;
if ((conf_reg & BD96801_WD_TYPE_MASK) == BD96801_WD_TYPE_WIN)
- w->wdt.min_hw_heartbeat_ms = fast / USEC_PER_MSEC;
+ w->wdt.min_hw_heartbeat_ms = fast / 10;
return 0;
}
diff --git a/fs/binfmt_misc.c b/fs/binfmt_misc.c
index f85ee577c34d..3c4852bb8ccc 100644
--- a/fs/binfmt_misc.c
+++ b/fs/binfmt_misc.c
@@ -983,7 +983,8 @@ static int bm_fill_super(struct super_block *sb, struct fs_context *fc)
/* last one */ {""}
};
- if (WARN_ON(user_ns != current_user_ns()))
+ /* The fscontext fd may have been passed to another user namespace. */
+ if (user_ns != current_user_ns())
return -EINVAL;
/* Never exec off this instance and never let anything stack on it. */
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index f60f8bf38dc5..ab7f19ca2145 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -9684,6 +9684,7 @@ ssize_t btrfs_do_encoded_write(struct kiocb *iocb, struct iov_iter *from,
}
kvfree(folios);
out:
+ extent_changeset_free(data_reserved);
if (ret >= 0)
iocb->ki_pos += encoded->len;
return ret;
diff --git a/fs/crypto/policy.c b/fs/crypto/policy.c
index 701259991277..6fc526d7f424 100644
--- a/fs/crypto/policy.c
+++ b/fs/crypto/policy.c
@@ -532,7 +532,7 @@ int fscrypt_ioctl_set_policy(struct file *filp, const void __user *arg)
return -EFAULT;
policy.version = version;
- if (!inode_owner_or_capable(&nop_mnt_idmap, inode))
+ if (!inode_owner_or_capable(file_mnt_idmap(filp), inode))
return -EACCES;
ret = mnt_want_write_file(filp);
diff --git a/fs/namespace.c b/fs/namespace.c
index 94c06c842902..a596381dba1c 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -4229,6 +4229,11 @@ SYSCALL_DEFINE3(fsmount, int, fs_fd, unsigned int, flags,
ret = PTR_ERR(newmount.mnt);
goto err_unlock;
}
+ if (newmount.mnt->mnt_sb->s_flags & SB_NOUSER) {
+ mntput(newmount.mnt);
+ ret = -EINVAL;
+ goto err_unlock;
+ }
newmount.dentry = dget(fc->root);
newmount.mnt->mnt_flags = mnt_flags;
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 840789e182ef..facd4e28770b 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -10585,6 +10585,7 @@ static void nfs41_free_stateid_release(void *calldata)
struct nfs_free_stateid_data *data = calldata;
struct nfs_client *clp = data->server->nfs_client;
+ nfs_sb_deactive(data->server->super);
nfs_put_client(clp);
kfree(calldata);
}
@@ -10626,6 +10627,10 @@ static int nfs41_free_stateid(struct nfs_server *server,
if (!refcount_inc_not_zero(&clp->cl_count))
return -EIO;
+ if (!nfs_sb_active(server->super)) {
+ nfs_put_client(clp);
+ return -EIO;
+ }
nfs4_state_protect(server->nfs_client, NFS_SP4_MACH_CRED_STATEID,
&task_setup.rpc_client, &msg);
diff --git a/fs/overlayfs/super.c b/fs/overlayfs/super.c
index c3d84eafde9f..bd0c548cf1ee 100644
--- a/fs/overlayfs/super.c
+++ b/fs/overlayfs/super.c
@@ -1299,7 +1299,8 @@ int ovl_fill_super(struct super_block *sb, struct fs_context *fc)
int err;
err = -EIO;
- if (WARN_ON(fc->user_ns != current_user_ns()))
+ /* The fscontext fd may have been passed to another user namespace. */
+ if (fc->user_ns != current_user_ns())
goto out_err;
sb->s_d_op = &ovl_dentry_operations;
diff --git a/fs/smb/client/sess.c b/fs/smb/client/sess.c
index a11a6ebae386..458d6922826f 100644
--- a/fs/smb/client/sess.c
+++ b/fs/smb/client/sess.c
@@ -259,9 +259,9 @@ int cifs_try_adding_channels(struct cifs_ses *ses)
cifs_dbg(VFS, "failed to open extra channel on iface:%pIS rc=%d\n",
&iface->sockaddr,
rc);
- kref_put(&iface->refcount, release_iface);
/* failure to add chan should increase weight */
iface->weight_fulfilled++;
+ kref_put(&iface->refcount, release_iface);
continue;
}
diff --git a/fs/tracefs/event_inode.c b/fs/tracefs/event_inode.c
index 02d56ed6ad20..ad182f9fbb48 100644
--- a/fs/tracefs/event_inode.c
+++ b/fs/tracefs/event_inode.c
@@ -849,7 +849,7 @@ struct eventfs_inode *eventfs_create_events_dir(const char *name, struct dentry
*/
static void eventfs_remove_rec(struct eventfs_inode *ei, int level)
{
- struct eventfs_inode *ei_child;
+ struct eventfs_inode *ei_child, *tmp;
/*
* Check recursion depth. It should never be greater than 3:
@@ -862,7 +862,7 @@ static void eventfs_remove_rec(struct eventfs_inode *ei, int level)
return;
/* search for nested folders or files */
- list_for_each_entry(ei_child, &ei->children, list)
+ list_for_each_entry_safe(ei_child, tmp, &ei->children, list)
eventfs_remove_rec(ei_child, level + 1);
list_del_rcu(&ei->list);
diff --git a/fs/verity/measure.c b/fs/verity/measure.c
index 175d2f1bc089..91ce39ced77b 100644
--- a/fs/verity/measure.c
+++ b/fs/verity/measure.c
@@ -121,11 +121,11 @@ __bpf_kfunc int bpf_get_fsverity_digest(struct file *file, struct bpf_dynptr *di
{
struct bpf_dynptr_kern *digest_ptr = (struct bpf_dynptr_kern *)digest_p;
const struct inode *inode = file_inode(file);
- u32 dynptr_sz = __bpf_dynptr_size(digest_ptr);
+ u64 dynptr_sz = __bpf_dynptr_size(digest_ptr);
struct fsverity_digest *arg;
const struct fsverity_info *vi;
const struct fsverity_hash_alg *hash_alg;
- int out_digest_sz;
+ u64 out_digest_sz;
if (dynptr_sz < sizeof(struct fsverity_digest))
return -EINVAL;
@@ -143,17 +143,20 @@ __bpf_kfunc int bpf_get_fsverity_digest(struct file *file, struct bpf_dynptr *di
hash_alg = vi->tree_params.hash_alg;
+ out_digest_sz = dynptr_sz - sizeof(struct fsverity_digest);
+ if (out_digest_sz < hash_alg->digest_size)
+ return -EOVERFLOW;
+
arg->digest_algorithm = hash_alg - fsverity_hash_algs;
arg->digest_size = hash_alg->digest_size;
- out_digest_sz = dynptr_sz - sizeof(struct fsverity_digest);
-
/* copy digest */
- memcpy(arg->digest, vi->file_digest, min_t(int, hash_alg->digest_size, out_digest_sz));
+ memcpy(arg->digest, vi->file_digest, hash_alg->digest_size);
/* fill the extra buffer with zeros */
if (out_digest_sz > hash_alg->digest_size)
- memset(arg->digest + arg->digest_size, 0, out_digest_sz - hash_alg->digest_size);
+ memset(arg->digest + hash_alg->digest_size, 0,
+ out_digest_sz - hash_alg->digest_size);
return 0;
}
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index ea9b40b196de..5c5e1c814ff2 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -297,9 +297,11 @@ struct hh_cache {
* We could use other alignment values, but we must maintain the
* relationship HH alignment <= LL alignment.
*/
-#define LL_RESERVED_SPACE(dev) \
- ((((dev)->hard_header_len + READ_ONCE((dev)->needed_headroom)) \
+#define LL_RESERVED_SPACE_EX(dev, hlen) \
+ ((((hlen) + READ_ONCE((dev)->needed_headroom)) \
& ~(HH_DATA_MOD - 1)) + HH_DATA_MOD)
+#define LL_RESERVED_SPACE(dev) \
+ LL_RESERVED_SPACE_EX(dev, (dev)->hard_header_len)
#define LL_RESERVED_SPACE_EXTRA(dev,extra) \
((((dev)->hard_header_len + READ_ONCE((dev)->needed_headroom) + (extra)) \
& ~(HH_DATA_MOD - 1)) + HH_DATA_MOD)
@@ -3189,11 +3191,6 @@ static inline bool dev_validate_header(const struct net_device *dev,
if (len < dev->min_header_len)
return false;
- if (capable(CAP_SYS_RAWIO)) {
- memset(ll_header + len, 0, dev->hard_header_len - len);
- return true;
- }
-
if (dev->header_ops && dev->header_ops->validate)
return dev->header_ops->validate(ll_header, len);
diff --git a/include/linux/netfilter/ipset/ip_set.h b/include/linux/netfilter/ipset/ip_set.h
index b98331572ad2..cadae9b2578f 100644
--- a/include/linux/netfilter/ipset/ip_set.h
+++ b/include/linux/netfilter/ipset/ip_set.h
@@ -273,7 +273,7 @@ struct ip_set {
/* Number of elements (vs timeout) */
u32 elements;
/* Size of the dynamic extensions (vs timeout) */
- size_t ext_size;
+ atomic64_t ext_size;
/* Element data size */
size_t dsize;
/* Offsets to extensions in elements */
diff --git a/include/linux/nvmem-provider.h b/include/linux/nvmem-provider.h
index 3ebeaa0ded00..2eb3edc638db 100644
--- a/include/linux/nvmem-provider.h
+++ b/include/linux/nvmem-provider.h
@@ -238,6 +238,12 @@ static inline int nvmem_layout_register(struct nvmem_layout *layout)
static inline void nvmem_layout_unregister(struct nvmem_layout *layout) {}
+static inline int nvmem_add_cells_from_dt(struct nvmem_device *nvmem,
+ struct device_node *np)
+{
+ return -EOPNOTSUPP;
+}
+
#endif /* CONFIG_NVMEM */
#if IS_ENABLED(CONFIG_NVMEM) && IS_ENABLED(CONFIG_OF)
diff --git a/include/linux/psp-sev.h b/include/linux/psp-sev.h
index 613a8209bed2..6a4435cfa977 100644
--- a/include/linux/psp-sev.h
+++ b/include/linux/psp-sev.h
@@ -947,6 +947,7 @@ int sev_do_cmd(int cmd, void *data, int *psp_ret);
void *psp_copy_user_blob(u64 uaddr, u32 len);
void *snp_alloc_firmware_page(gfp_t mask);
void snp_free_firmware_page(void *addr);
+void sev_platform_shutdown(void);
#else /* !CONFIG_CRYPTO_DEV_SP_PSP */
@@ -981,6 +982,8 @@ static inline void *snp_alloc_firmware_page(gfp_t mask)
static inline void snp_free_firmware_page(void *addr) { }
+static inline void sev_platform_shutdown(void) { }
+
#endif /* CONFIG_CRYPTO_DEV_SP_PSP */
#endif /* __PSP_SEV_H__ */
diff --git a/include/net/act_api.h b/include/net/act_api.h
index 539ea6693a24..76c31ce80fe5 100644
--- a/include/net/act_api.h
+++ b/include/net/act_api.h
@@ -270,6 +270,25 @@ int tcf_action_check_ctrlact(int action, struct tcf_proto *tp,
struct tcf_chain *tcf_action_set_ctrlact(struct tc_action *a, int action,
struct tcf_chain *newchain);
+/* Range check for a control action supplied by user space.
+ *
+ * This is the same test tcf_action_check_ctrlact() applies to the primary
+ * control action, factored out for the *fallback* control actions
+ * (act_gact's TCA_GACT_PROB.paction and act_police's TCA_POLICE_RESULT),
+ * which must not reach tcf_action_check_ctrlact() because they have no
+ * goto_chain to allocate. Without it, user space can store kernel-internal
+ * verdicts such as TC_ACT_CONSUMED, which is TC_ACT_VALUE_MAX + 1 and is
+ * deliberately not part of the UAPI value range.
+ */
+static inline bool tcf_action_valid(int action)
+{
+ int opcode = TC_ACT_EXT_OPCODE(action);
+
+ if (!opcode)
+ return action <= TC_ACT_VALUE_MAX;
+ return opcode <= TC_ACT_EXT_OPCODE_MAX || action == TC_ACT_UNSPEC;
+}
+
#ifdef CONFIG_INET
DECLARE_STATIC_KEY_FALSE(tcf_frag_xmit_count);
#endif
diff --git a/include/net/addrconf.h b/include/net/addrconf.h
index 3650adc635ad..e7dc5175e236 100644
--- a/include/net/addrconf.h
+++ b/include/net/addrconf.h
@@ -382,8 +382,8 @@ static inline struct inet6_dev *in6_dev_get(const struct net_device *dev)
rcu_read_lock();
idev = rcu_dereference(dev->ip6_ptr);
- if (idev)
- refcount_inc(&idev->refcnt);
+ if (idev && !refcount_inc_not_zero(&idev->refcnt))
+ idev = NULL;
rcu_read_unlock();
return idev;
}
diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h
index 6935ec09af24..e0077fd28ad1 100644
--- a/include/net/ip_vs.h
+++ b/include/net/ip_vs.h
@@ -24,9 +24,7 @@
#include <linux/netfilter.h> /* for union nf_inet_addr */
#include <linux/ip.h>
#include <linux/ipv6.h> /* for struct ipv6hdr */
-#include <net/route.h>
#include <net/ipv6.h>
-#include <net/ip6_fib.h>
#if IS_ENABLED(CONFIG_NF_CONNTRACK)
#include <net/netfilter/nf_conntrack.h>
#endif
@@ -738,10 +736,11 @@ struct ip_vs_dest {
/* connection counters and thresholds */
atomic_t activeconns; /* active connections */
- atomic_t inactconns; /* inactive connections */
+ atomic_t totalconns; /* total connections */
atomic_t persistconns; /* persistent connections */
__u32 u_threshold; /* upper threshold */
__u32 l_threshold; /* lower threshold */
+ __u32 l_threshold_val;/* used lower threshold */
/* for destination cache */
spinlock_t dst_lock; /* lock of dst_cache */
@@ -1569,6 +1568,8 @@ static inline void ip_vs_dest_put_and_free(struct ip_vs_dest *dest)
kfree(dest);
}
+void ip_vs_dest_update_overload(struct ip_vs_dest *dest, int mode);
+
/* IPVS sync daemon data and function prototypes
* (from ip_vs_sync.c)
*/
@@ -1707,7 +1708,7 @@ static inline char ip_vs_fwd_tag(struct ip_vs_conn *cp)
void ip_vs_nat_icmp(struct sk_buff *skb, struct ip_vs_protocol *pp,
struct ip_vs_conn *cp, int dir, unsigned int toff,
- bool has_ports);
+ bool has_ports, struct ip_vs_iphdr *ciph);
#ifdef CONFIG_IP_VS_IPV6
void ip_vs_nat_icmp_v6(struct sk_buff *skb, struct ip_vs_protocol *pp,
@@ -1740,30 +1741,23 @@ static inline __wsum ip_vs_check_diff2(__be16 old, __be16 new, __wsum oldsum)
return csum_partial(diff, sizeof(diff), oldsum);
}
-static inline bool ip_vs_checksum_needed(struct sk_buff *skb, int af)
+static inline bool ip_vs_checksum_needed(struct sk_buff *skb)
{
/* Checksum unnecessary or already validated? */
if (skb_csum_unnecessary(skb))
return false;
- /* LOCAL_OUT ? */
- if (!skb->dev || skb->dev->flags & IFF_LOOPBACK)
+ /* Locally generated ? */
+ if (!skb->dev)
return false;
- /* !LOCAL_IN (FORWARD) ? */
- if (af == AF_INET6) {
- if (!(dst_rt6_info(skb_dst(skb))->rt6i_flags & RTF_LOCAL))
- return false;
- } else {
- if (!(skb_rtable(skb)->rt_flags & RTCF_LOCAL))
- return false;
- }
return true;
}
static inline bool ip_vs_checksum_common_check(struct sk_buff *skb,
int offset, int proto, int af)
{
- if (!ip_vs_checksum_needed(skb, af))
+ if (!ip_vs_checksum_needed(skb))
return true;
+ /* Validate csum even for FORWARD */
return !nf_checksum(skb, NF_INET_LOCAL_IN, offset, proto, af);
}
@@ -1874,14 +1868,21 @@ void ip_vs_unregister_hooks(struct netns_ipvs *ipvs, unsigned int af);
static inline int
ip_vs_dest_conn_overhead(struct ip_vs_dest *dest)
{
- /* We think the overhead of processing active connections is 256
+ /* We think the overhead of processing active connections is 257
* times higher than that of inactive connections in average. (This
- * 256 times might not be accurate, we will change it later) We
+ * 257 times might not be accurate, we will change it later) We
* use the following formula to estimate the overhead now:
- * dest->activeconns*256 + dest->inactconns
+ * dest->activeconns*256 + dest->totalconns
*/
return (atomic_read(&dest->activeconns) << 8) +
- atomic_read(&dest->inactconns);
+ atomic_read(&dest->totalconns);
+}
+
+static inline int
+ip_vs_dest_inactconns(const struct ip_vs_dest *dest)
+{
+ return max(atomic_read(&dest->totalconns) -
+ atomic_read(&dest->activeconns), 0);
}
#ifdef CONFIG_IP_VS_PROTO_TCP
diff --git a/include/net/route.h b/include/net/route.h
index cbb4d5523062..76f526e051aa 100644
--- a/include/net/route.h
+++ b/include/net/route.h
@@ -258,6 +258,8 @@ int fib_dump_info_fnhe(struct sk_buff *skb, struct netlink_callback *cb,
u32 table_id, struct fib_info *fi,
int *fa_index, int fa_start, unsigned int flags);
+void fnhe_update_pmtu(struct fib_nh_exception *fnhe, u32 new, u32 orig);
+
static inline void ip_rt_put(struct rtable *rt)
{
/* dst_release() accepts a NULL parameter.
diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h
index d3e1f91f81cd..1b461d181647 100644
--- a/include/net/sch_generic.h
+++ b/include/net/sch_generic.h
@@ -101,6 +101,7 @@ struct Qdisc {
struct hlist_node hash;
u32 handle;
u32 parent;
+ int depth;
struct netdev_queue *dev_queue;
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 77183b436da5..275c9fabc955 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -13565,11 +13565,12 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env,
return -EACCES;
}
- /* In case of 'scalar += pointer', dst_reg inherits pointer type and id.
- * The id may be overwritten later if we create a new variable offset.
+ /* For 'scalar += pointer', dst_reg inherits the complete pointer
+ * register state. Individual fields may be adjusted later by pointer
+ * arithmetic. Callers guarantee that below does not overwrite off_reg.
*/
- dst_reg->type = ptr_reg->type;
- dst_reg->id = ptr_reg->id;
+ if (dst_reg != ptr_reg)
+ *dst_reg = *ptr_reg;
if (!check_reg_sane_offset(env, off_reg, ptr_reg->type) ||
!check_reg_sane_offset(env, ptr_reg, ptr_reg->type))
@@ -13631,7 +13632,7 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env,
}
break;
case BPF_SUB:
- if (dst_reg == off_reg) {
+ if (dst_reg != ptr_reg) {
/* scalar -= pointer. Creates an unknown scalar */
verbose(env, "R%d tried to subtract pointer from scalar\n",
dst);
@@ -14490,8 +14491,8 @@ static int adjust_reg_min_max_vals(struct bpf_verifier_env *env,
err = mark_chain_precision(env, insn->dst_reg);
if (err)
return err;
- return adjust_ptr_min_max_vals(env, insn,
- src_reg, dst_reg);
+ off_reg = *dst_reg;
+ return adjust_ptr_min_max_vals(env, insn, src_reg, &off_reg);
}
} else if (ptr_reg) {
/* pointer += scalar */
diff --git a/kernel/futex/core.c b/kernel/futex/core.c
index 010607a99194..c37d2263c21f 100644
--- a/kernel/futex/core.c
+++ b/kernel/futex/core.c
@@ -674,8 +674,11 @@ static int handle_futex_death(u32 __user *uaddr, struct task_struct *curr,
return -1;
/*
- * Special case for regular (non PI) futexes. The unlock path in
- * user space has two race scenarios:
+ * Special case for regular (non PI) futexes. Ordinarily, we do
+ * not perform any processing here unless the current thread was
+ * the owner of the futex (by the TID check below).
+ *
+ * However, the unlock path has three race scenarios:
*
* 1. The unlock path releases the user space futex value and
* before it can execute the futex() syscall to wake up
@@ -684,42 +687,70 @@ static int handle_futex_death(u32 __user *uaddr, struct task_struct *curr,
* 2. A woken up waiter is killed before it can acquire the
* futex in user space.
*
- * In the second case, the wake up notification could be generated
- * by the unlock path in user space after setting the futex value
- * to zero or by the kernel after setting the OWNER_DIED bit below.
+ * 3. A woken up waiter is killed in user space after another
+ * thread has acquired the futex, but before it can set
+ * FUTEX_WAITERS.
+ *
+ * Note that, if userspace uses the FUTEX_ROBUST_UNLOCK flag, we
+ * will not see case 1 here.
+ *
+ * In the second and third case, the wake up notification could
+ * be generated from any of:
+ *
+ * i. An ordinary futex wakeup after unlock (with or
+ * without FUTEX_ROBUST_UNLOCK)
+ * ii. A robust wakeup from another thread's death
+ * iii. A previous round through this special case
+ *
+ * As a result, the futex world will be in one of four states:
+ *
+ * A. The futex word is 0 (unlocked)
+ * B. The futex word is owned by another thread
+ * (FUTEX_WAITERS is not set)
+ * C. The futex word is owned by another thread
+ * (FUTEX_WAITERS set)
+ * D. The futex's owner died and OWNER_DIED is set
+ * (the owner part of the word is 0)
*
- * In both cases the TID validation below prevents a wakeup of
- * potential waiters which can cause these waiters to block
- * forever.
+ * The key issue is that the kernel usually (at least from
+ * sources ii. and iii. or when so requested by userspace from
+ * source i.) only ever wakes *one* waiter at a time. If this
+ * waiter dies before acquiring the futex (or setting the
+ * FUTEX_WAITERS bit), the kernel *must* still wake the next
+ * waiter down the line to uphold the futex invariants and
+ * avoid lost wakeups. Note we do not need to handle state C,
+ * as it does not matter to us whether *we* successfully set
+ * the bit or a third thread did so in the meantime.
*
- * In both cases the following conditions are met:
+ * Therefore, in these cases we must issue an additional
+ * futex_wake(). Note however that we *must not* set OWNER_DIED
+ * here. Our thread is *not* the owner of the futex.
*
- * 1) task->robust_list->list_op_pending != NULL
- * @pending_op == true
- * 2) The owner part of user space futex value == 0
+ * Thus to summarize, the conditions for needing the additional
+ * futex_wake() are:
+ *
+ * 1) @pending_op == true (the thread has not finished the
+ * mutex operation)
+ * 2) The futex word is in one of the states A, B or D
* 3) Regular futex: @pi == false
*
- * If these conditions are met, it is safe to attempt waking up a
- * potential waiter without touching the user space futex value and
- * trying to set the OWNER_DIED bit. If the futex value is zero,
- * the rest of the user space mutex state is consistent, so a woken
- * waiter will just take over the uncontended futex. Setting the
- * OWNER_DIED bit would create inconsistent state and malfunction
- * of the user space owner died handling. Otherwise, the OWNER_DIED
- * bit is already set, and the woken waiter is expected to deal with
- * this.
+ * Note in particular that in all of the states A-D the owner
+ * portion of the futex word differs from our thread's TID
+ * (unless the actual owner has the same TID in another PID
+ * namespace, but we cannot currently distinguish that
+ * scenario), so this can be a special-case wakeup in the bail
+ * path of the ordinary TID check.
*/
owner = uval & FUTEX_TID_MASK;
- if (pending_op && !pi && !owner) {
- futex_wake(uaddr, FLAGS_SIZE_32 | FLAGS_SHARED, 1,
- FUTEX_BITSET_MATCH_ANY);
+ if (owner != task_pid_vnr(curr)) {
+ if (pending_op && !pi && (!owner || !(uval & FUTEX_WAITERS))) {
+ futex_wake(uaddr, FLAGS_SIZE_32 | FLAGS_SHARED, 1,
+ FUTEX_BITSET_MATCH_ANY);
+ }
return 0;
}
- if (owner != task_pid_vnr(curr))
- return 0;
-
/*
* Ok, this dying thread is truly holding a futex
* of interest. Set the OWNER_DIED bit atomically
diff --git a/kernel/sched/psi.c b/kernel/sched/psi.c
index 7d0f8fdd48a3..a6fc7ea51d2e 100644
--- a/kernel/sched/psi.c
+++ b/kernel/sched/psi.c
@@ -1130,6 +1130,12 @@ void psi_cgroup_free(struct cgroup *cgroup)
return;
cancel_delayed_work_sync(&cgroup->psi->avgs_work);
+ /*
+ * A psi_schedule_rtpoll_work() call racing the last trigger's
+ * destruction may have re-armed the timer after psi_trigger_destroy()
+ * deleted it. Spurious firing while the group is alive is harmless.
+ */
+ timer_shutdown_sync(&cgroup->psi->rtpoll_timer);
free_percpu(cgroup->psi->pcpu);
/* All triggers must be removed by now */
WARN_ONCE(cgroup->psi->rtpoll_states, "psi: trigger leak\n");
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index fcd2363d1296..3f90c7f752eb 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -6756,7 +6756,7 @@ int ring_buffer_subbuf_order_set(struct trace_buffer *buffer, int order)
cpu_buffer = buffer->buffers[cpu];
- if (cpu_buffer->mapped) {
+ if (atomic_read(&cpu_buffer->resize_disabled)) {
err = -EBUSY;
goto error;
}
@@ -7604,7 +7604,7 @@ static __init int test_ringbuffer(void)
out_free:
for_each_online_cpu(cpu) {
- if (!rb_threads[cpu])
+ if (IS_ERR_OR_NULL(rb_threads[cpu]))
break;
kthread_stop(rb_threads[cpu]);
}
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index 1630d2b7fbc4..ac50babaeea0 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -3072,6 +3072,7 @@ void trace_event_eval_update(struct trace_eval_map **map, int len)
int last_i;
int i;
+ mutex_lock(&event_mutex);
down_write(&trace_event_sem);
list_for_each_entry_safe(call, p, &ftrace_events, list) {
/* events are usually grouped together with systems */
@@ -3105,6 +3106,7 @@ void trace_event_eval_update(struct trace_eval_map **map, int len)
cond_resched();
}
up_write(&trace_event_sem);
+ mutex_unlock(&event_mutex);
}
static bool event_in_systems(struct trace_event_call *call,
diff --git a/lib/fortify_kunit.c b/lib/fortify_kunit.c
index ecb638d4cde1..d0810e4e65e5 100644
--- a/lib/fortify_kunit.c
+++ b/lib/fortify_kunit.c
@@ -394,8 +394,6 @@ struct fortify_padding {
char buf[32];
unsigned long bytes_after;
};
-/* Force compiler into not being able to resolve size at compile-time. */
-static volatile int unconst;
static void fortify_test_strlen(struct kunit *test)
{
@@ -520,57 +518,56 @@ static void fortify_test_strncpy(struct kunit *test)
{
struct fortify_padding pad = { };
char src[] = "Copy me fully into a small buffer and I will overflow!";
+ size_t sizeof_buf = sizeof(pad.buf);
+
+ OPTIMIZER_HIDE_VAR(sizeof_buf);
/* Destination is %NUL-filled to start with. */
KUNIT_EXPECT_EQ(test, pad.bytes_before, 0);
- KUNIT_EXPECT_EQ(test, pad.buf[sizeof(pad.buf) - 1], '\0');
- KUNIT_EXPECT_EQ(test, pad.buf[sizeof(pad.buf) - 2], '\0');
- KUNIT_EXPECT_EQ(test, pad.buf[sizeof(pad.buf) - 3], '\0');
+ KUNIT_EXPECT_EQ(test, pad.buf[sizeof_buf - 1], '\0');
+ KUNIT_EXPECT_EQ(test, pad.buf[sizeof_buf - 2], '\0');
+ KUNIT_EXPECT_EQ(test, pad.buf[sizeof_buf - 3], '\0');
KUNIT_EXPECT_EQ(test, pad.bytes_after, 0);
/* Legitimate strncpy() 1 less than of max size. */
- KUNIT_ASSERT_TRUE(test, strncpy(pad.buf, src,
- sizeof(pad.buf) + unconst - 1)
+ KUNIT_ASSERT_TRUE(test, strncpy(pad.buf, src, sizeof_buf - 1)
== pad.buf);
KUNIT_EXPECT_EQ(test, fortify_write_overflows, 0);
/* Only last byte should be %NUL */
- KUNIT_EXPECT_EQ(test, pad.buf[sizeof(pad.buf) - 1], '\0');
- KUNIT_EXPECT_NE(test, pad.buf[sizeof(pad.buf) - 2], '\0');
- KUNIT_EXPECT_NE(test, pad.buf[sizeof(pad.buf) - 3], '\0');
+ KUNIT_EXPECT_EQ(test, pad.buf[sizeof_buf - 1], '\0');
+ KUNIT_EXPECT_NE(test, pad.buf[sizeof_buf - 2], '\0');
+ KUNIT_EXPECT_NE(test, pad.buf[sizeof_buf - 3], '\0');
/* Legitimate (though unterminated) max-size strncpy. */
- KUNIT_ASSERT_TRUE(test, strncpy(pad.buf, src,
- sizeof(pad.buf) + unconst)
+ KUNIT_ASSERT_TRUE(test, strncpy(pad.buf, src, sizeof_buf)
== pad.buf);
KUNIT_EXPECT_EQ(test, fortify_write_overflows, 0);
/* No trailing %NUL -- thanks strncpy API. */
- KUNIT_EXPECT_NE(test, pad.buf[sizeof(pad.buf) - 1], '\0');
- KUNIT_EXPECT_NE(test, pad.buf[sizeof(pad.buf) - 2], '\0');
- KUNIT_EXPECT_NE(test, pad.buf[sizeof(pad.buf) - 2], '\0');
+ KUNIT_EXPECT_NE(test, pad.buf[sizeof_buf - 1], '\0');
+ KUNIT_EXPECT_NE(test, pad.buf[sizeof_buf - 2], '\0');
+ KUNIT_EXPECT_NE(test, pad.buf[sizeof_buf - 2], '\0');
/* But we will not have gone beyond. */
KUNIT_EXPECT_EQ(test, pad.bytes_after, 0);
/* Now verify that FORTIFY is working... */
- KUNIT_ASSERT_TRUE(test, strncpy(pad.buf, src,
- sizeof(pad.buf) + unconst + 1)
+ KUNIT_ASSERT_TRUE(test, strncpy(pad.buf, src, sizeof_buf + 1)
== pad.buf);
/* Should catch the overflow. */
KUNIT_EXPECT_EQ(test, fortify_write_overflows, 1);
- KUNIT_EXPECT_NE(test, pad.buf[sizeof(pad.buf) - 1], '\0');
- KUNIT_EXPECT_NE(test, pad.buf[sizeof(pad.buf) - 2], '\0');
- KUNIT_EXPECT_NE(test, pad.buf[sizeof(pad.buf) - 2], '\0');
+ KUNIT_EXPECT_NE(test, pad.buf[sizeof_buf - 1], '\0');
+ KUNIT_EXPECT_NE(test, pad.buf[sizeof_buf - 2], '\0');
+ KUNIT_EXPECT_NE(test, pad.buf[sizeof_buf - 2], '\0');
/* And we will not have gone beyond. */
KUNIT_EXPECT_EQ(test, pad.bytes_after, 0);
/* And further... */
- KUNIT_ASSERT_TRUE(test, strncpy(pad.buf, src,
- sizeof(pad.buf) + unconst + 2)
+ KUNIT_ASSERT_TRUE(test, strncpy(pad.buf, src, sizeof_buf + 2)
== pad.buf);
/* Should catch the overflow. */
KUNIT_EXPECT_EQ(test, fortify_write_overflows, 2);
- KUNIT_EXPECT_NE(test, pad.buf[sizeof(pad.buf) - 1], '\0');
- KUNIT_EXPECT_NE(test, pad.buf[sizeof(pad.buf) - 2], '\0');
- KUNIT_EXPECT_NE(test, pad.buf[sizeof(pad.buf) - 2], '\0');
+ KUNIT_EXPECT_NE(test, pad.buf[sizeof_buf - 1], '\0');
+ KUNIT_EXPECT_NE(test, pad.buf[sizeof_buf - 2], '\0');
+ KUNIT_EXPECT_NE(test, pad.buf[sizeof_buf - 2], '\0');
/* And we will not have gone beyond. */
KUNIT_EXPECT_EQ(test, pad.bytes_after, 0);
}
@@ -579,55 +576,56 @@ static void fortify_test_strscpy(struct kunit *test)
{
struct fortify_padding pad = { };
char src[] = "Copy me fully into a small buffer and I will overflow!";
+ size_t sizeof_buf = sizeof(pad.buf);
+ size_t sizeof_src = sizeof(src);
+
+ OPTIMIZER_HIDE_VAR(sizeof_buf);
+ OPTIMIZER_HIDE_VAR(sizeof_src);
/* Destination is %NUL-filled to start with. */
KUNIT_EXPECT_EQ(test, pad.bytes_before, 0);
- KUNIT_EXPECT_EQ(test, pad.buf[sizeof(pad.buf) - 1], '\0');
- KUNIT_EXPECT_EQ(test, pad.buf[sizeof(pad.buf) - 2], '\0');
- KUNIT_EXPECT_EQ(test, pad.buf[sizeof(pad.buf) - 3], '\0');
+ KUNIT_EXPECT_EQ(test, pad.buf[sizeof_buf - 1], '\0');
+ KUNIT_EXPECT_EQ(test, pad.buf[sizeof_buf - 2], '\0');
+ KUNIT_EXPECT_EQ(test, pad.buf[sizeof_buf - 3], '\0');
KUNIT_EXPECT_EQ(test, pad.bytes_after, 0);
/* Legitimate strscpy() 1 less than of max size. */
- KUNIT_ASSERT_EQ(test, strscpy(pad.buf, src,
- sizeof(pad.buf) + unconst - 1),
+ KUNIT_ASSERT_EQ(test, strscpy(pad.buf, src, sizeof_buf - 1),
-E2BIG);
KUNIT_EXPECT_EQ(test, fortify_write_overflows, 0);
/* Keeping space for %NUL, last two bytes should be %NUL */
- KUNIT_EXPECT_EQ(test, pad.buf[sizeof(pad.buf) - 1], '\0');
- KUNIT_EXPECT_EQ(test, pad.buf[sizeof(pad.buf) - 2], '\0');
- KUNIT_EXPECT_NE(test, pad.buf[sizeof(pad.buf) - 3], '\0');
+ KUNIT_EXPECT_EQ(test, pad.buf[sizeof_buf - 1], '\0');
+ KUNIT_EXPECT_EQ(test, pad.buf[sizeof_buf - 2], '\0');
+ KUNIT_EXPECT_NE(test, pad.buf[sizeof_buf - 3], '\0');
/* Legitimate max-size strscpy. */
- KUNIT_ASSERT_EQ(test, strscpy(pad.buf, src,
- sizeof(pad.buf) + unconst),
+ KUNIT_ASSERT_EQ(test, strscpy(pad.buf, src, sizeof_buf),
-E2BIG);
KUNIT_EXPECT_EQ(test, fortify_write_overflows, 0);
/* A trailing %NUL will exist. */
- KUNIT_EXPECT_EQ(test, pad.buf[sizeof(pad.buf) - 1], '\0');
- KUNIT_EXPECT_NE(test, pad.buf[sizeof(pad.buf) - 2], '\0');
- KUNIT_EXPECT_NE(test, pad.buf[sizeof(pad.buf) - 2], '\0');
+ KUNIT_EXPECT_EQ(test, pad.buf[sizeof_buf - 1], '\0');
+ KUNIT_EXPECT_NE(test, pad.buf[sizeof_buf - 2], '\0');
+ KUNIT_EXPECT_NE(test, pad.buf[sizeof_buf - 2], '\0');
/* Now verify that FORTIFY is working... */
- KUNIT_ASSERT_EQ(test, strscpy(pad.buf, src,
- sizeof(pad.buf) + unconst + 1),
+ KUNIT_ASSERT_EQ(test, strscpy(pad.buf, src, sizeof_buf + 1),
-E2BIG);
/* Should catch the overflow. */
KUNIT_EXPECT_EQ(test, fortify_write_overflows, 1);
- KUNIT_EXPECT_EQ(test, pad.buf[sizeof(pad.buf) - 1], '\0');
- KUNIT_EXPECT_NE(test, pad.buf[sizeof(pad.buf) - 2], '\0');
- KUNIT_EXPECT_NE(test, pad.buf[sizeof(pad.buf) - 2], '\0');
+ KUNIT_EXPECT_EQ(test, pad.buf[sizeof_buf - 1], '\0');
+ KUNIT_EXPECT_NE(test, pad.buf[sizeof_buf - 2], '\0');
+ KUNIT_EXPECT_NE(test, pad.buf[sizeof_buf - 2], '\0');
/* And we will not have gone beyond. */
KUNIT_EXPECT_EQ(test, pad.bytes_after, 0);
/* And much further... */
- KUNIT_ASSERT_EQ(test, strscpy(pad.buf, src,
- sizeof(src) * 2 + unconst),
+ KUNIT_ASSERT_EQ(test, strscpy(pad.buf, src, sizeof_src * 2),
-E2BIG);
/* Should catch the overflow. */
KUNIT_EXPECT_EQ(test, fortify_write_overflows, 2);
- KUNIT_EXPECT_EQ(test, pad.buf[sizeof(pad.buf) - 1], '\0');
- KUNIT_EXPECT_NE(test, pad.buf[sizeof(pad.buf) - 2], '\0');
- KUNIT_EXPECT_NE(test, pad.buf[sizeof(pad.buf) - 2], '\0');
+ KUNIT_EXPECT_EQ(test, pad.buf[sizeof_buf - 1], '\0');
+ KUNIT_EXPECT_NE(test, pad.buf[sizeof_buf - 2], '\0');
+ KUNIT_EXPECT_NE(test, pad.buf[sizeof_buf - 2], '\0');
/* And we will not have gone beyond. */
KUNIT_EXPECT_EQ(test, pad.bytes_after, 0);
}
@@ -767,7 +765,9 @@ static void fortify_test_strlcat(struct kunit *test)
struct fortify_padding pad = { };
char src[sizeof(pad.buf)] = { };
int i, partial;
- int len = sizeof(pad.buf) + unconst;
+ int len = sizeof(pad.buf);
+
+ OPTIMIZER_HIDE_VAR(len);
/* Fill 15 bytes with valid characters. */
partial = sizeof(src) / 2 - 1;
@@ -857,28 +857,32 @@ struct fortify_zero_sized {
#define __fortify_test(memfunc) \
static void fortify_test_##memfunc(struct kunit *test) \
{ \
- struct fortify_zero_sized zero = { }; \
+ struct fortify_zero_sized empty = { }; \
struct fortify_padding pad = { }; \
char srcA[sizeof(pad.buf) + 2]; \
char srcB[sizeof(pad.buf) + 2]; \
- size_t len = sizeof(pad.buf) + unconst; \
+ size_t len = sizeof(pad.buf); \
+ size_t zero = 0; \
+ \
+ OPTIMIZER_HIDE_VAR(len); \
+ OPTIMIZER_HIDE_VAR(zero); \
\
memset(srcA, 'A', sizeof(srcA)); \
KUNIT_ASSERT_EQ(test, srcA[0], 'A'); \
memset(srcB, 'B', sizeof(srcB)); \
KUNIT_ASSERT_EQ(test, srcB[0], 'B'); \
\
- memfunc(pad.buf, srcA, 0 + unconst); \
+ memfunc(pad.buf, srcA, zero); \
KUNIT_EXPECT_EQ(test, pad.buf[0], '\0'); \
KUNIT_EXPECT_EQ(test, fortify_read_overflows, 0); \
KUNIT_EXPECT_EQ(test, fortify_write_overflows, 0); \
- memfunc(pad.buf + 1, srcB, 1 + unconst); \
+ memfunc(pad.buf + 1, srcB, zero + 1); \
KUNIT_EXPECT_EQ(test, pad.buf[0], '\0'); \
KUNIT_EXPECT_EQ(test, pad.buf[1], 'B'); \
KUNIT_EXPECT_EQ(test, pad.buf[2], '\0'); \
KUNIT_EXPECT_EQ(test, fortify_read_overflows, 0); \
KUNIT_EXPECT_EQ(test, fortify_write_overflows, 0); \
- memfunc(pad.buf, srcA, 1 + unconst); \
+ memfunc(pad.buf, srcA, zero + 1); \
KUNIT_EXPECT_EQ(test, pad.buf[0], 'A'); \
KUNIT_EXPECT_EQ(test, pad.buf[1], 'B'); \
KUNIT_EXPECT_EQ(test, fortify_read_overflows, 0); \
@@ -904,10 +908,10 @@ static void fortify_test_##memfunc(struct kunit *test) \
/* Reset error counter. */ \
fortify_write_overflows = 0; \
/* Copy nothing into nothing: no errors. */ \
- memfunc(zero.buf, srcB, 0 + unconst); \
+ memfunc(empty.buf, srcB, zero); \
KUNIT_EXPECT_EQ(test, fortify_read_overflows, 0); \
KUNIT_EXPECT_EQ(test, fortify_write_overflows, 0); \
- memfunc(zero.buf, srcB, 1 + unconst); \
+ memfunc(empty.buf, srcB, zero + 1); \
KUNIT_EXPECT_EQ(test, fortify_read_overflows, 0); \
KUNIT_EXPECT_EQ(test, fortify_write_overflows, 1); \
}
@@ -919,7 +923,9 @@ static void fortify_test_memscan(struct kunit *test)
char haystack[] = "Where oh where is my memory range?";
char *mem = haystack + strlen("Where oh where is ");
char needle = 'm';
- size_t len = sizeof(haystack) + unconst;
+ size_t len = sizeof(haystack);
+
+ OPTIMIZER_HIDE_VAR(len);
KUNIT_ASSERT_PTR_EQ(test, memscan(haystack, needle, len),
mem);
@@ -938,7 +944,9 @@ static void fortify_test_memchr(struct kunit *test)
char haystack[] = "Where oh where is my memory range?";
char *mem = haystack + strlen("Where oh where is ");
char needle = 'm';
- size_t len = sizeof(haystack) + unconst;
+ size_t len = sizeof(haystack);
+
+ OPTIMIZER_HIDE_VAR(len);
KUNIT_ASSERT_PTR_EQ(test, memchr(haystack, needle, len),
mem);
@@ -957,7 +965,9 @@ static void fortify_test_memchr_inv(struct kunit *test)
char haystack[] = "Where oh where is my memory range?";
char *mem = haystack + 1;
char needle = 'W';
- size_t len = sizeof(haystack) + unconst;
+ size_t len = sizeof(haystack);
+
+ OPTIMIZER_HIDE_VAR(len);
/* Normal search is okay. */
KUNIT_ASSERT_PTR_EQ(test, memchr_inv(haystack, needle, len),
@@ -976,8 +986,11 @@ static void fortify_test_memcmp(struct kunit *test)
{
char one[] = "My mind is going ...";
char two[] = "My mind is going ... I can feel it.";
- size_t one_len = sizeof(one) + unconst - 1;
- size_t two_len = sizeof(two) + unconst - 1;
+ volatile size_t one_len = sizeof(one) - 1;
+ volatile size_t two_len = sizeof(two) - 1;
+
+ OPTIMIZER_HIDE_VAR(one_len);
+ OPTIMIZER_HIDE_VAR(two_len);
/* We match the first string (ignoring the %NUL). */
KUNIT_ASSERT_EQ(test, memcmp(one, two, one_len), 0);
@@ -998,7 +1011,9 @@ static void fortify_test_kmemdup(struct kunit *test)
{
char src[] = "I got Doom running on it!";
char *copy;
- size_t len = sizeof(src) + unconst;
+ size_t len = sizeof(src);
+
+ OPTIMIZER_HIDE_VAR(len);
/* Copy is within bounds. */
copy = kmemdup(src, len, GFP_KERNEL);
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index b2daa1767d90..29cbe43b60a4 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -41,6 +41,7 @@
#include <linux/compat.h>
#include <linux/pgalloc_tag.h>
#include <linux/pagewalk.h>
+#include <linux/cleanup.h>
#include <asm/tlb.h>
#include <asm/pgalloc.h>
@@ -77,6 +78,7 @@ static unsigned long deferred_split_scan(struct shrinker *shrink,
static bool split_underused_thp = true;
static atomic_t huge_zero_refcount;
+static DEFINE_SPINLOCK(huge_zero_lock);
struct folio *huge_zero_folio __read_mostly;
unsigned long huge_zero_pfn __read_mostly = ~0UL;
unsigned long huge_anon_orders_always __read_mostly;
@@ -197,7 +199,8 @@ unsigned long __thp_vma_allowable_orders(struct vm_area_struct *vma,
static bool get_huge_zero_page(void)
{
struct folio *zero_folio;
-retry:
+
+ /* Paired with atomic_set_release(). */
if (likely(atomic_inc_not_zero(&huge_zero_refcount)))
return true;
@@ -209,17 +212,22 @@ static bool get_huge_zero_page(void)
}
/* Ensure zero folio won't have large_rmappable flag set. */
folio_clear_large_rmappable(zero_folio);
- preempt_disable();
- if (cmpxchg(&huge_zero_folio, NULL, zero_folio)) {
- preempt_enable();
+
+ /* Paired with critical section in shrink_huge_zero_folio_scan(). */
+ spin_lock(&huge_zero_lock);
+ if (huge_zero_folio) {
+ /* Somebody else already installed it. */
+ atomic_inc(&huge_zero_refcount);
+ spin_unlock(&huge_zero_lock);
folio_put(zero_folio);
- goto retry;
+ return true;
}
+ WRITE_ONCE(huge_zero_folio, zero_folio);
WRITE_ONCE(huge_zero_pfn, folio_pfn(zero_folio));
+ /* Paired with atomic_inc_not_zero(). +1 for shrinker pin. */
+ atomic_set_release(&huge_zero_refcount, 2);
+ spin_unlock(&huge_zero_lock);
- /* We take additional reference here. It will be put back by shrinker */
- atomic_set(&huge_zero_refcount, 2);
- preempt_enable();
count_vm_event(THP_ZERO_PAGE_ALLOC);
return true;
}
@@ -263,15 +271,22 @@ static unsigned long shrink_huge_zero_page_count(struct shrinker *shrink,
static unsigned long shrink_huge_zero_page_scan(struct shrinker *shrink,
struct shrink_control *sc)
{
- if (atomic_cmpxchg(&huge_zero_refcount, 1, 0) == 1) {
- struct folio *zero_folio = xchg(&huge_zero_folio, NULL);
- BUG_ON(zero_folio == NULL);
+ struct folio *zero_folio;
+
+ /* Paired with critical section in get_huge_zero_folio(). */
+ scoped_guard(spinlock, &huge_zero_lock) {
+ /* Paired with atomic_inc_not_zero() in get_huge_zero_folio(). */
+ if (atomic_cmpxchg(&huge_zero_refcount, 1, 0) != 1)
+ return 0;
+
+ zero_folio = huge_zero_folio;
+ VM_WARN_ON_ONCE(!zero_folio);
+ WRITE_ONCE(huge_zero_folio, NULL);
WRITE_ONCE(huge_zero_pfn, ~0UL);
- folio_put(zero_folio);
- return HPAGE_PMD_NR;
}
- return 0;
+ folio_put(zero_folio);
+ return HPAGE_PMD_NR;
}
static struct shrinker *huge_zero_page_shrinker;
diff --git a/mm/swapfile.c b/mm/swapfile.c
index 552df432c37f..ed0a5ed25e65 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -770,11 +770,11 @@ static void swap_reclaim_full_clusters(struct swap_info_struct *si, bool force)
}
offset++;
}
+ cond_resched();
spin_lock(&si->lock);
if (to_scan <= 0)
break;
- cond_resched();
}
}
diff --git a/mm/vmscan.c b/mm/vmscan.c
index deeb4310fd54..20f4cb33d8e8 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -4313,6 +4313,7 @@ static bool sort_folio(struct lruvec *lruvec, struct folio *folio, struct scan_c
int tier_idx)
{
bool success;
+ bool dirty, writeback;
int gen = folio_lru_gen(folio);
int type = folio_is_file_lru(folio);
int zone = folio_zonenum(folio);
@@ -4358,9 +4359,17 @@ static bool sort_folio(struct lruvec *lruvec, struct folio *folio, struct scan_c
return true;
}
+ dirty = folio_test_dirty(folio);
+ writeback = folio_test_writeback(folio);
+ if (type == LRU_GEN_FILE && dirty) {
+ sc->nr.file_taken += delta;
+ if (!writeback)
+ sc->nr.unqueued_dirty += delta;
+ }
+
/* waiting for writeback */
- if (folio_test_locked(folio) || folio_test_writeback(folio) ||
- (type == LRU_GEN_FILE && folio_test_dirty(folio))) {
+ if (folio_test_locked(folio) || writeback ||
+ (type == LRU_GEN_FILE && dirty)) {
gen = folio_inc_gen(lruvec, folio, true);
list_move(&folio->lru, &lrugen->folios[gen][type][zone]);
return true;
@@ -4476,7 +4485,8 @@ static int scan_folios(struct lruvec *lruvec, struct scan_control *sc,
trace_mm_vmscan_lru_isolate(sc->reclaim_idx, sc->order, MAX_LRU_BATCH,
scanned, skipped, isolated,
type ? LRU_INACTIVE_FILE : LRU_INACTIVE_ANON);
-
+ if (type == LRU_GEN_FILE)
+ sc->nr.file_taken += isolated;
/*
* There might not be eligible folios due to reclaim_idx. Check the
* remaining to prevent livelock if it's not making progress.
@@ -4610,6 +4620,7 @@ static int evict_folios(struct lruvec *lruvec, struct scan_control *sc, int swap
return scanned;
retry:
reclaimed = shrink_folio_list(&list, pgdat, sc, &stat, false);
+ sc->nr.unqueued_dirty += stat.nr_unqueued_dirty;
sc->nr_reclaimed += reclaimed;
trace_mm_vmscan_lru_shrink_inactive(pgdat->node_id,
scanned, reclaimed, &stat, sc->priority,
@@ -4821,6 +4832,13 @@ static bool try_to_shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc)
cond_resched();
}
+ /*
+ * If too many file cache in the coldest generation can't be evicted
+ * due to being dirty, wake up the flusher.
+ */
+ if (sc->nr.unqueued_dirty && sc->nr.unqueued_dirty == sc->nr.file_taken)
+ wakeup_flusher_threads(WB_REASON_VMSCAN);
+
/* whether this lruvec should be rotated */
return nr_to_scan < 0;
}
@@ -5966,6 +5984,7 @@ static void shrink_node(pg_data_t *pgdat, struct scan_control *sc)
bool reclaimable = false;
if (lru_gen_enabled() && root_reclaim(sc)) {
+ memset(&sc->nr, 0, sizeof(sc->nr));
lru_gen_shrink_node(pgdat, sc);
return;
}
diff --git a/net/atm/common.c b/net/atm/common.c
index 196c36269b34..413863861bca 100644
--- a/net/atm/common.c
+++ b/net/atm/common.c
@@ -760,7 +760,7 @@ int vcc_setsockopt(struct socket *sock, int level, int optname,
sockptr_t optval, unsigned int optlen)
{
struct atm_vcc *vcc;
- unsigned long value;
+ int value;
int error;
if (__SO_LEVEL_MATCH(optname, level) && optlen != __SO_SIZE(optname))
@@ -772,8 +772,10 @@ int vcc_setsockopt(struct socket *sock, int level, int optname,
{
struct atm_qos qos;
- if (copy_from_sockptr(&qos, optval, sizeof(qos)))
- return -EFAULT;
+ error = copy_safe_from_sockptr(&qos, sizeof(qos), optval,
+ optlen);
+ if (error)
+ return error;
error = check_qos(&qos);
if (error)
return error;
@@ -786,8 +788,10 @@ int vcc_setsockopt(struct socket *sock, int level, int optname,
return 0;
}
case SO_SETCLP:
- if (copy_from_sockptr(&value, optval, sizeof(value)))
- return -EFAULT;
+ error = copy_safe_from_sockptr(&value, sizeof(value), optval,
+ optlen);
+ if (error)
+ return error;
if (value)
vcc->atm_options |= ATM_ATMOPT_CLP;
else
diff --git a/net/bridge/br_mrp.c b/net/bridge/br_mrp.c
index 5fd22bb4f5b6..a837ff7d6f36 100644
--- a/net/bridge/br_mrp.c
+++ b/net/bridge/br_mrp.c
@@ -224,11 +224,9 @@ static struct sk_buff *br_mrp_alloc_test_skb(struct br_mrp *mrp,
sub_opt = skb_put(skb, sizeof(*sub_opt));
memset(sub_opt, 0x0, sizeof(*sub_opt));
- sub_tlv = skb_put(skb, sizeof(*sub_tlv));
- sub_tlv->type = BR_MRP_SUB_TLV_HEADER_TEST_AUTO_MGR;
-
/* 32 bit alligment shall be ensured therefore add 2 bytes */
- skb_put(skb, MRP_OPT_PADDING);
+ sub_tlv = skb_put_zero(skb, sizeof(*sub_tlv) + MRP_OPT_PADDING);
+ sub_tlv->type = BR_MRP_SUB_TLV_HEADER_TEST_AUTO_MGR;
}
br_mrp_skb_tlv(skb, BR_MRP_TLV_HEADER_END, 0x0);
diff --git a/net/bridge/netfilter/ebt_nflog.c b/net/bridge/netfilter/ebt_nflog.c
index 61bf8f4465ab..426f8adc912c 100644
--- a/net/bridge/netfilter/ebt_nflog.c
+++ b/net/bridge/netfilter/ebt_nflog.c
@@ -41,11 +41,25 @@ ebt_nflog_tg(struct sk_buff *skb, const struct xt_action_param *par)
static int ebt_nflog_tg_check(const struct xt_tgchk_param *par)
{
struct ebt_nflog_info *info = par->targinfo;
+ int ret;
if (info->flags & ~EBT_NFLOG_MASK)
return -EINVAL;
info->prefix[EBT_NFLOG_PREFIX_SIZE - 1] = '\0';
- return 0;
+
+ ret = nf_logger_find_get(par->family, NF_LOG_TYPE_ULOG);
+ if (ret != 0 && !par->nft_compat) {
+ request_module("%s", "nfnetlink_log");
+
+ ret = nf_logger_find_get(par->family, NF_LOG_TYPE_ULOG);
+ }
+
+ return ret;
+}
+
+static void ebt_nflog_tg_destroy(const struct xt_tgdtor_param *par)
+{
+ nf_logger_put(par->family, NF_LOG_TYPE_ULOG);
}
static struct xt_target ebt_nflog_tg_reg __read_mostly = {
@@ -54,6 +68,7 @@ static struct xt_target ebt_nflog_tg_reg __read_mostly = {
.family = NFPROTO_BRIDGE,
.target = ebt_nflog_tg,
.checkentry = ebt_nflog_tg_check,
+ .destroy = ebt_nflog_tg_destroy,
.targetsize = sizeof(struct ebt_nflog_info),
.me = THIS_MODULE,
};
diff --git a/net/bridge/netfilter/nf_conntrack_bridge.c b/net/bridge/netfilter/nf_conntrack_bridge.c
index 6482de4d8750..e4dae5fe0b0d 100644
--- a/net/bridge/netfilter/nf_conntrack_bridge.c
+++ b/net/bridge/netfilter/nf_conntrack_bridge.c
@@ -281,6 +281,7 @@ static unsigned int nf_ct_bridge_pre(void *priv, struct sk_buff *skb,
ret = nf_ct_br_defrag6(skb, &bridge_state);
break;
default:
+ nf_reset_ct(skb);
nf_ct_set(skb, NULL, IP_CT_UNTRACKED);
return NF_ACCEPT;
}
diff --git a/net/core/dev.c b/net/core/dev.c
index ce5a1ab86ab5..5c037fe70d48 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -5116,12 +5116,16 @@ u32 bpf_prog_run_generic_xdp(struct sk_buff *skb, struct xdp_buff *xdp,
}
/* XDP frag metadata (e.g. nr_frags) are updated in eBPF helpers
- * (e.g. bpf_xdp_adjust_tail), we need to update data_len here.
+ * (e.g. bpf_xdp_adjust_tail). Remove the old fragment contribution
+ * from skb->len before updating data_len, then add the new one back.
*/
- if (xdp_buff_has_frags(xdp))
+ skb->len -= skb->data_len;
+ if (xdp_buff_has_frags(xdp)) {
skb->data_len = skb_shinfo(skb)->xdp_frags_size;
- else
+ skb->len += skb->data_len;
+ } else {
skb->data_len = 0;
+ }
/* check if XDP changed eth hdr such SKB needs update */
eth = (struct ethhdr *)xdp->data;
diff --git a/net/core/sock.c b/net/core/sock.c
index 4a09e780406f..e8b03cf3a428 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -773,7 +773,6 @@ bool sk_mc_loop(const struct sock *sk)
return inet6_test_bit(MC6_LOOP, sk);
#endif
}
- WARN_ON_ONCE(1);
return true;
}
EXPORT_SYMBOL(sk_mc_loop);
diff --git a/net/core/xdp.c b/net/core/xdp.c
index 8a3ea90e8cf9..251708f648e1 100644
--- a/net/core/xdp.c
+++ b/net/core/xdp.c
@@ -731,7 +731,7 @@ struct xdp_frame *xdpf_clone(struct xdp_frame *xdpf)
headroom = xdpf->headroom + sizeof(*xdpf);
totalsize = headroom + xdpf->len;
- if (unlikely(totalsize > PAGE_SIZE))
+ if (unlikely(totalsize > SKB_WITH_OVERHEAD(PAGE_SIZE)))
return NULL;
page = dev_alloc_page();
if (!page)
diff --git a/net/devlink/dev.c b/net/devlink/dev.c
index 13c73f50da3d..fc109acd4e84 100644
--- a/net/devlink/dev.c
+++ b/net/devlink/dev.c
@@ -579,6 +579,7 @@ int devlink_nl_reload_doit(struct sk_buff *skb, struct genl_info *info)
action != DEVLINK_RELOAD_ACTION_DRIVER_REINIT) {
NL_SET_ERR_MSG_MOD(info->extack,
"Changing namespace is only supported for reinit action");
+ put_net(dest_net);
return -EOPNOTSUPP;
}
}
diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index ba2df3d2ac15..687fe2c281c5 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -462,6 +462,34 @@ int ip_fib_check_default(__be32 gw, struct net_device *dev)
return -1;
}
+static size_t fib_nexthop_nlmsg_size(const struct fib_nh_common *nhc,
+ bool skip_oif)
+{
+ size_t nhsize = 0;
+
+ switch (nhc->nhc_gw_family) {
+ case AF_INET:
+ nhsize += nla_total_size(4); /* RTA_GATEWAY */
+ break;
+ case AF_INET6:
+ nhsize += nla_total_size(sizeof(struct rtvia) +
+ sizeof(struct in6_addr));
+ break;
+ }
+
+ if (!skip_oif && nhc->nhc_dev)
+ nhsize += nla_total_size(4); /* RTA_OIF */
+
+ if (nhc->nhc_lwtstate) {
+ /* RTA_ENCAP */
+ nhsize += lwtunnel_get_encap_size(nhc->nhc_lwtstate);
+ /* RTA_ENCAP_TYPE */
+ nhsize += nla_total_size(2);
+ }
+
+ return nhsize;
+}
+
size_t fib_nlmsg_size(struct fib_info *fi)
{
size_t payload = NLMSG_ALIGN(sizeof(struct rtmsg))
@@ -479,32 +507,35 @@ size_t fib_nlmsg_size(struct fib_info *fi)
payload += nla_total_size(4); /* RTA_NH_ID */
if (nhs) {
- size_t nh_encapsize = 0;
- /* Also handles the special case nhs == 1 */
-
- /* each nexthop is packed in an attribute */
- size_t nhsize = nla_total_size(sizeof(struct rtnexthop));
+ size_t mpsize = 0;
unsigned int i;
- /* may contain flow and gateway attribute */
- nhsize += 2 * nla_total_size(4);
-
- /* grab encap info */
for (i = 0; i < fib_info_num_path(fi); i++) {
struct fib_nh_common *nhc = fib_info_nhc(fi, i);
+ size_t nhsize;
+
+ nhsize = fib_nexthop_nlmsg_size(nhc, nhs != 1);
+
+ if (nhs != 1)
+ nhsize += NLA_ALIGN(sizeof(struct rtnexthop));
+
+#ifdef CONFIG_IP_ROUTE_CLASSID
+ if (nhc->nhc_family == AF_INET) {
+ struct fib_nh *nh;
- if (nhc->nhc_lwtstate) {
- /* RTA_ENCAP_TYPE */
- nh_encapsize += lwtunnel_get_encap_size(
- nhc->nhc_lwtstate);
- /* RTA_ENCAP */
- nh_encapsize += nla_total_size(2);
+ nh = container_of(nhc, struct fib_nh, nh_common);
+ if (nh->nh_tclassid)
+ nhsize += nla_total_size(4);
}
+#endif
+ if (nhs == 1)
+ payload += nhsize;
+ else
+ mpsize += nhsize;
}
- /* all nexthops are packed in a nested attribute */
- payload += nla_total_size((nhs * nhsize) + nh_encapsize);
-
+ if (nhs != 1)
+ payload += nla_total_size(mpsize);
}
return payload;
@@ -1925,42 +1956,30 @@ static int call_fib_nh_notifiers(struct fib_nh *nh,
return NOTIFY_DONE;
}
-/* Update the PMTU of exceptions when:
- * - the new MTU of the first hop becomes smaller than the PMTU
- * - the old MTU was the same as the PMTU, and it limited discovery of
- * larger MTUs on the path. With that limit raised, we can now
- * discover larger MTUs
- * A special case is locked exceptions, for which the PMTU is smaller
- * than the minimal accepted PMTU:
- * - if the new MTU is greater than the PMTU, don't make any change
- * - otherwise, unlock and set PMTU
+/* Walk the exceptions of a nexthop after its first hop MTU changed. The
+ * chain is RCU protected here, while fnhe_update_pmtu() takes fnhe_lock
+ * for the update of each entry.
*/
void fib_nhc_update_mtu(struct fib_nh_common *nhc, u32 new, u32 orig)
{
struct fnhe_hash_bucket *bucket;
int i;
- bucket = rcu_dereference_protected(nhc->nhc_exceptions, 1);
+ rcu_read_lock();
+ bucket = rcu_dereference(nhc->nhc_exceptions);
if (!bucket)
- return;
+ goto out;
for (i = 0; i < FNHE_HASH_SIZE; i++) {
struct fib_nh_exception *fnhe;
- for (fnhe = rcu_dereference_protected(bucket[i].chain, 1);
+ for (fnhe = rcu_dereference(bucket[i].chain);
fnhe;
- fnhe = rcu_dereference_protected(fnhe->fnhe_next, 1)) {
- if (fnhe->fnhe_mtu_locked) {
- if (new <= fnhe->fnhe_pmtu) {
- fnhe->fnhe_pmtu = new;
- fnhe->fnhe_mtu_locked = false;
- }
- } else if (new < fnhe->fnhe_pmtu ||
- orig == fnhe->fnhe_pmtu) {
- fnhe->fnhe_pmtu = new;
- }
- }
+ fnhe = rcu_dereference(fnhe->fnhe_next))
+ fnhe_update_pmtu(fnhe, new, orig);
}
+out:
+ rcu_read_unlock();
}
void fib_sync_mtu(struct net_device *dev, u32 orig_mtu)
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index 5ff45bc85442..91dcdb7567ac 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -987,11 +987,23 @@ static struct request_sock *inet_reqsk_clone(struct request_sock *req,
nreq->rsk_listener = sk;
- /* We need not acquire fastopenq->lock
- * because the child socket is locked in inet_csk_listen_stop().
- */
- if (sk->sk_protocol == IPPROTO_TCP && tcp_rsk(nreq)->tfo_listener)
+ if (sk->sk_protocol == IPPROTO_TCP && tcp_rsk(nreq)->tfo_listener) {
+ struct fastopen_queue *fastopenq;
+
+ /* reqsk_fastopen_remove() will uncharge nreq->rsk_listener,
+ * that is @sk, so charge it here. Unlike the listener
+ * being closed, @sk is live and needs its lock.
+ */
+ fastopenq = &inet_csk(sk)->icsk_accept_queue.fastopenq;
+ spin_lock_bh(&fastopenq->lock);
+ fastopenq->qlen++;
+ spin_unlock_bh(&fastopenq->lock);
+
+ /* We need not acquire fastopenq->lock
+ * because the child socket is locked in inet_csk_listen_stop().
+ */
rcu_assign_pointer(tcp_sk(nreq->sk)->fastopen_rsk, nreq);
+ }
return nreq;
}
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 2b8c29a29c4a..28d83b3baae3 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -739,6 +739,35 @@ static void update_or_create_fnhe(struct fib_nh_common *nhc, __be32 daddr,
spin_unlock_bh(&fnhe_lock);
}
+/* Update the PMTU of an exception when:
+ * - the new MTU of the first hop becomes smaller than the PMTU
+ * - the old MTU was the same as the PMTU, and it limited discovery of
+ * larger MTUs on the path. With that limit raised, we can now
+ * discover larger MTUs
+ * A special case is locked exceptions, for which the PMTU is smaller
+ * than the minimal accepted PMTU:
+ * - if the new MTU is greater than the PMTU, don't make any change
+ * - otherwise, unlock and set PMTU
+ *
+ * fnhe_lock keeps fnhe_pmtu and fnhe_mtu_locked consistent against
+ * update_or_create_fnhe(), which sets both under the same lock.
+ */
+void fnhe_update_pmtu(struct fib_nh_exception *fnhe, u32 new, u32 orig)
+{
+ spin_lock_bh(&fnhe_lock);
+
+ if (fnhe->fnhe_mtu_locked) {
+ if (new <= fnhe->fnhe_pmtu) {
+ fnhe->fnhe_pmtu = new;
+ fnhe->fnhe_mtu_locked = false;
+ }
+ } else if (new < fnhe->fnhe_pmtu || orig == fnhe->fnhe_pmtu) {
+ fnhe->fnhe_pmtu = new;
+ }
+
+ spin_unlock_bh(&fnhe_lock);
+}
+
static void __ip_do_redirect(struct rtable *rt, struct sk_buff *skb, struct flowi4 *fl4,
bool kill_route)
{
diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c
index 132ffc13087f..0e7e12117913 100644
--- a/net/ipv4/tcp_bpf.c
+++ b/net/ipv4/tcp_bpf.c
@@ -455,6 +455,7 @@ static int tcp_bpf_send_verdict(struct sock *sk, struct sk_psock *psock,
case __SK_REDIRECT:
redir_ingress = psock->redir_ingress;
sk_redir = psock->sk_redir;
+ sock_hold(sk_redir);
sk_msg_apply_bytes(psock, tosend);
if (!psock->apply_bytes) {
/* Clean up before releasing the sock lock. */
@@ -475,6 +476,7 @@ static int tcp_bpf_send_verdict(struct sock *sk, struct sk_psock *psock,
if (eval == __SK_REDIRECT)
sock_put(sk_redir);
+ sock_put(sk_redir);
lock_sock(sk);
sk_mem_uncharge(sk, sent);
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index e57917aefd50..2fb68455679a 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -247,7 +247,7 @@ static void tcp_measure_rcv_mss(struct sock *sk, const struct sk_buff *skb)
struct tcp_sock *tp = tcp_sk(sk);
val = tcp_win_from_space(sk, sk->sk_rcvbuf);
- tcp_set_window_clamp(sk, val);
+ WRITE_ONCE(tp->window_clamp, val);
if (tp->window_clamp < tp->rcvq_space.space)
tp->rcvq_space.space = tp->window_clamp;
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index a9f3ee89302c..40b73e97d5fb 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -58,6 +58,7 @@
#include <linux/times.h>
#include <linux/slab.h>
#include <linux/sched.h>
+#include <linux/sock_diag.h>
#include <net/net_namespace.h>
#include <net/icmp.h>
@@ -2998,13 +2999,17 @@ static int tcp4_seq_show(struct seq_file *seq, void *v)
}
#ifdef CONFIG_BPF_SYSCALL
+union bpf_tcp_iter_batch_item {
+ struct sock *sk;
+ __u64 cookie;
+};
+
struct bpf_tcp_iter_state {
struct tcp_iter_state state;
unsigned int cur_sk;
unsigned int end_sk;
unsigned int max_sk;
- struct sock **batch;
- bool st_bucket_done;
+ union bpf_tcp_iter_batch_item *batch;
};
struct bpf_iter__tcp {
@@ -3027,21 +3032,32 @@ static int tcp_prog_seq_show(struct bpf_prog *prog, struct bpf_iter_meta *meta,
static void bpf_iter_tcp_put_batch(struct bpf_tcp_iter_state *iter)
{
- while (iter->cur_sk < iter->end_sk)
- sock_gen_put(iter->batch[iter->cur_sk++]);
+ union bpf_tcp_iter_batch_item *item;
+ unsigned int cur_sk = iter->cur_sk;
+ __u64 cookie;
+
+ /* Remember the cookies of the sockets we haven't seen yet, so we can
+ * pick up where we left off next time around.
+ */
+ while (cur_sk < iter->end_sk) {
+ item = &iter->batch[cur_sk++];
+ cookie = sock_gen_cookie(item->sk);
+ sock_gen_put(item->sk);
+ item->cookie = cookie;
+ }
}
static int bpf_iter_tcp_realloc_batch(struct bpf_tcp_iter_state *iter,
- unsigned int new_batch_sz)
+ unsigned int new_batch_sz, gfp_t flags)
{
- struct sock **new_batch;
+ union bpf_tcp_iter_batch_item *new_batch;
new_batch = kvmalloc(sizeof(*new_batch) * new_batch_sz,
- GFP_USER | __GFP_NOWARN);
+ flags | __GFP_NOWARN);
if (!new_batch)
return -ENOMEM;
- bpf_iter_tcp_put_batch(iter);
+ memcpy(new_batch, iter->batch, sizeof(*iter->batch) * iter->end_sk);
kvfree(iter->batch);
iter->batch = new_batch;
iter->max_sk = new_batch_sz;
@@ -3049,112 +3065,242 @@ static int bpf_iter_tcp_realloc_batch(struct bpf_tcp_iter_state *iter,
return 0;
}
-static unsigned int bpf_iter_tcp_listening_batch(struct seq_file *seq,
- struct sock *start_sk)
+static struct sock *bpf_iter_tcp_resume_bucket(struct sock *first_sk,
+ union bpf_tcp_iter_batch_item *cookies,
+ int n_cookies)
+{
+ struct hlist_nulls_node *node;
+ struct sock *sk;
+ int i;
+
+ for (i = 0; i < n_cookies; i++) {
+ sk = first_sk;
+ sk_nulls_for_each_from(sk, node)
+ if (cookies[i].cookie == atomic64_read(&sk->sk_cookie))
+ return sk;
+ }
+
+ return NULL;
+}
+
+static struct sock *bpf_iter_tcp_resume_listening(struct seq_file *seq)
{
struct inet_hashinfo *hinfo = seq_file_net(seq)->ipv4.tcp_death_row.hashinfo;
struct bpf_tcp_iter_state *iter = seq->private;
struct tcp_iter_state *st = &iter->state;
- struct hlist_nulls_node *node;
- unsigned int expected = 1;
+ unsigned int find_cookie = iter->cur_sk;
+ unsigned int end_cookie = iter->end_sk;
+ int resume_bucket = st->bucket;
struct sock *sk;
- sock_hold(start_sk);
- iter->batch[iter->end_sk++] = start_sk;
+ if (end_cookie && find_cookie == end_cookie)
+ ++st->bucket;
- sk = sk_nulls_next(start_sk);
- sk_nulls_for_each_from(sk, node) {
- if (seq_sk_match(seq, sk)) {
- if (iter->end_sk < iter->max_sk) {
- sock_hold(sk);
- iter->batch[iter->end_sk++] = sk;
- }
- expected++;
+ sk = listening_get_first(seq);
+ iter->cur_sk = 0;
+ iter->end_sk = 0;
+
+ if (sk && st->bucket == resume_bucket && end_cookie) {
+ sk = bpf_iter_tcp_resume_bucket(sk, &iter->batch[find_cookie],
+ end_cookie - find_cookie);
+ if (!sk) {
+ spin_unlock(&hinfo->lhash2[st->bucket].lock);
+ ++st->bucket;
+ sk = listening_get_first(seq);
}
}
- spin_unlock(&hinfo->lhash2[st->bucket].lock);
- return expected;
+ return sk;
}
-static unsigned int bpf_iter_tcp_established_batch(struct seq_file *seq,
- struct sock *start_sk)
+static struct sock *bpf_iter_tcp_resume_established(struct seq_file *seq)
{
struct inet_hashinfo *hinfo = seq_file_net(seq)->ipv4.tcp_death_row.hashinfo;
struct bpf_tcp_iter_state *iter = seq->private;
struct tcp_iter_state *st = &iter->state;
+ unsigned int find_cookie = iter->cur_sk;
+ unsigned int end_cookie = iter->end_sk;
+ int resume_bucket = st->bucket;
+ struct sock *sk;
+
+ if (end_cookie && find_cookie == end_cookie)
+ ++st->bucket;
+
+ sk = established_get_first(seq);
+ iter->cur_sk = 0;
+ iter->end_sk = 0;
+
+ if (sk && st->bucket == resume_bucket && end_cookie) {
+ sk = bpf_iter_tcp_resume_bucket(sk, &iter->batch[find_cookie],
+ end_cookie - find_cookie);
+ if (!sk) {
+ spin_unlock_bh(inet_ehash_lockp(hinfo, st->bucket));
+ ++st->bucket;
+ sk = established_get_first(seq);
+ }
+ }
+
+ return sk;
+}
+
+static struct sock *bpf_iter_tcp_resume(struct seq_file *seq)
+{
+ struct bpf_tcp_iter_state *iter = seq->private;
+ struct tcp_iter_state *st = &iter->state;
+ struct sock *sk = NULL;
+
+ switch (st->state) {
+ case TCP_SEQ_STATE_LISTENING:
+ sk = bpf_iter_tcp_resume_listening(seq);
+ if (sk)
+ break;
+ st->bucket = 0;
+ st->state = TCP_SEQ_STATE_ESTABLISHED;
+ fallthrough;
+ case TCP_SEQ_STATE_ESTABLISHED:
+ sk = bpf_iter_tcp_resume_established(seq);
+ break;
+ }
+
+ return sk;
+}
+
+static unsigned int bpf_iter_tcp_listening_batch(struct seq_file *seq,
+ struct sock **start_sk)
+{
+ struct bpf_tcp_iter_state *iter = seq->private;
struct hlist_nulls_node *node;
unsigned int expected = 1;
struct sock *sk;
- sock_hold(start_sk);
- iter->batch[iter->end_sk++] = start_sk;
+ sock_hold(*start_sk);
+ iter->batch[iter->end_sk++].sk = *start_sk;
- sk = sk_nulls_next(start_sk);
+ sk = sk_nulls_next(*start_sk);
+ *start_sk = NULL;
sk_nulls_for_each_from(sk, node) {
if (seq_sk_match(seq, sk)) {
if (iter->end_sk < iter->max_sk) {
sock_hold(sk);
- iter->batch[iter->end_sk++] = sk;
+ iter->batch[iter->end_sk++].sk = sk;
+ } else if (!*start_sk) {
+ /* Remember where we left off. */
+ *start_sk = sk;
}
expected++;
}
}
- spin_unlock_bh(inet_ehash_lockp(hinfo, st->bucket));
return expected;
}
-static struct sock *bpf_iter_tcp_batch(struct seq_file *seq)
+static unsigned int bpf_iter_tcp_established_batch(struct seq_file *seq,
+ struct sock **start_sk)
+{
+ struct bpf_tcp_iter_state *iter = seq->private;
+ struct hlist_nulls_node *node;
+ struct sock *sk = *start_sk;
+ unsigned int expected = 0;
+
+ *start_sk = NULL;
+ sk_nulls_for_each_from(sk, node) {
+ if (!seq_sk_match(seq, sk))
+ continue;
+ expected++;
+ if (iter->end_sk < iter->max_sk) {
+ /* reqsk_queue_hash_req() inserts with sk_refcnt == 0
+ * and refcount_set()s it after the bucket lock drops.
+ */
+ if (unlikely(!refcount_inc_not_zero(&sk->sk_refcnt)))
+ continue;
+ iter->batch[iter->end_sk++].sk = sk;
+ } else if (!*start_sk) {
+ /* Remember where we left off. */
+ *start_sk = sk;
+ }
+ }
+
+ return expected;
+}
+
+static unsigned int bpf_iter_fill_batch(struct seq_file *seq,
+ struct sock **start_sk)
+{
+ struct bpf_tcp_iter_state *iter = seq->private;
+ struct tcp_iter_state *st = &iter->state;
+
+ if (st->state == TCP_SEQ_STATE_LISTENING)
+ return bpf_iter_tcp_listening_batch(seq, start_sk);
+ else
+ return bpf_iter_tcp_established_batch(seq, start_sk);
+}
+
+static void bpf_iter_tcp_unlock_bucket(struct seq_file *seq)
{
struct inet_hashinfo *hinfo = seq_file_net(seq)->ipv4.tcp_death_row.hashinfo;
struct bpf_tcp_iter_state *iter = seq->private;
struct tcp_iter_state *st = &iter->state;
+
+ if (st->state == TCP_SEQ_STATE_LISTENING)
+ spin_unlock(&hinfo->lhash2[st->bucket].lock);
+ else
+ spin_unlock_bh(inet_ehash_lockp(hinfo, st->bucket));
+}
+
+static struct sock *bpf_iter_tcp_batch(struct seq_file *seq)
+{
+ struct bpf_tcp_iter_state *iter = seq->private;
unsigned int expected;
- bool resized = false;
struct sock *sk;
-
- /* The st->bucket is done. Directly advance to the next
- * bucket instead of having the tcp_seek_last_pos() to skip
- * one by one in the current bucket and eventually find out
- * it has to advance to the next bucket.
- */
- if (iter->st_bucket_done) {
- st->offset = 0;
- st->bucket++;
- if (st->state == TCP_SEQ_STATE_LISTENING &&
- st->bucket > hinfo->lhash2_mask) {
- st->state = TCP_SEQ_STATE_ESTABLISHED;
- st->bucket = 0;
- }
- }
+ int err;
again:
- /* Get a new batch */
- iter->cur_sk = 0;
- iter->end_sk = 0;
- iter->st_bucket_done = false;
+ sk = bpf_iter_tcp_resume(seq);
+ if (!sk)
+ return NULL; /* Done */
- sk = tcp_seek_last_pos(seq);
+ expected = bpf_iter_fill_batch(seq, &sk);
+ if (likely(!sk))
+ goto done;
+
+ /* Batch size was too small. */
+ bpf_iter_tcp_unlock_bucket(seq);
+ bpf_iter_tcp_put_batch(iter);
+ err = bpf_iter_tcp_realloc_batch(iter, expected * 3 / 2,
+ GFP_USER);
+ if (err) {
+ iter->cur_sk = 0;
+ iter->end_sk = 0;
+ return ERR_PTR(err);
+ }
+
+ sk = bpf_iter_tcp_resume(seq);
if (!sk)
return NULL; /* Done */
- if (st->state == TCP_SEQ_STATE_LISTENING)
- expected = bpf_iter_tcp_listening_batch(seq, sk);
- else
- expected = bpf_iter_tcp_established_batch(seq, sk);
+ expected = bpf_iter_fill_batch(seq, &sk);
+ if (likely(!sk))
+ goto done;
- if (iter->end_sk == expected) {
- iter->st_bucket_done = true;
- return sk;
+ /* Batch size was still too small. Hold onto the lock while we try
+ * again with a larger batch to make sure the current bucket's size
+ * does not change in the meantime.
+ */
+ err = bpf_iter_tcp_realloc_batch(iter, expected, GFP_NOWAIT);
+ if (err) {
+ bpf_iter_tcp_unlock_bucket(seq);
+ return ERR_PTR(err);
}
- if (!resized && !bpf_iter_tcp_realloc_batch(iter, expected * 3 / 2)) {
- resized = true;
+ bpf_iter_fill_batch(seq, &sk);
+ WARN_ON_ONCE(sk);
+done:
+ bpf_iter_tcp_unlock_bucket(seq);
+ if (unlikely(!iter->end_sk)) {
+ ++iter->state.bucket;
goto again;
}
-
- return sk;
+ return iter->batch[0].sk;
}
static void *bpf_iter_tcp_seq_start(struct seq_file *seq, loff_t *pos)
@@ -3184,16 +3330,11 @@ static void *bpf_iter_tcp_seq_next(struct seq_file *seq, void *v, loff_t *pos)
* meta.seq_num is used instead.
*/
st->num++;
- /* Move st->offset to the next sk in the bucket such that
- * the future start() will resume at st->offset in
- * st->bucket. See tcp_seek_last_pos().
- */
- st->offset++;
- sock_gen_put(iter->batch[iter->cur_sk++]);
+ sock_gen_put(iter->batch[iter->cur_sk++].sk);
}
if (iter->cur_sk < iter->end_sk)
- sk = iter->batch[iter->cur_sk];
+ sk = iter->batch[iter->cur_sk].sk;
else
sk = bpf_iter_tcp_batch(seq);
@@ -3259,10 +3400,8 @@ static void bpf_iter_tcp_seq_stop(struct seq_file *seq, void *v)
(void)tcp_prog_seq_show(prog, &meta, v, 0);
}
- if (iter->cur_sk < iter->end_sk) {
+ if (iter->cur_sk < iter->end_sk)
bpf_iter_tcp_put_batch(iter);
- iter->st_bucket_done = false;
- }
}
static const struct seq_operations bpf_iter_tcp_seq_ops = {
@@ -3578,7 +3717,7 @@ static int bpf_iter_init_tcp(void *priv_data, struct bpf_iter_aux_info *aux)
if (err)
return err;
- err = bpf_iter_tcp_realloc_batch(iter, INIT_BATCH_SZ);
+ err = bpf_iter_tcp_realloc_batch(iter, INIT_BATCH_SZ, GFP_USER);
if (err) {
bpf_iter_fini_seq_net(priv_data);
return err;
diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c
index 99688014901e..04246d1f8b3e 100644
--- a/net/ipv4/udp_offload.c
+++ b/net/ipv4/udp_offload.c
@@ -22,17 +22,19 @@ static struct sk_buff *__skb_udp_tunnel_segment(struct sk_buff *skb,
int tnl_hlen = skb_inner_mac_header(skb) - skb_transport_header(skb);
bool remcsum, need_csum, offload_csum, gso_partial;
struct sk_buff *segs = ERR_PTR(-EINVAL);
- struct udphdr *uh = udp_hdr(skb);
u16 mac_offset = skb->mac_header;
__be16 protocol = skb->protocol;
u16 mac_len = skb->mac_len;
int udp_offset, outer_hlen;
+ struct udphdr *uh;
__wsum partial;
bool need_ipsec;
if (unlikely(!pskb_may_pull(skb, tnl_hlen)))
goto out;
+ uh = udp_hdr(skb);
+
/* Adjust partial header checksum to negate old length.
* We cannot rely on the value contained in uh->len as it is
* possible that the actual value exceeds the boundaries of the
diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index b788a06bd3a5..1446c4eae681 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -677,6 +677,9 @@ ip6ip6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
if (!skb2)
return 0;
+ /* Remove debris left by outer IPv6 stack. */
+ memset(IP6CB(skb2), 0, sizeof(*IP6CB(skb2)));
+
skb_dst_drop(skb2);
skb_pull(skb2, offset);
skb_reset_network_header(skb2);
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 2ce05303e403..e602dd3e7ee3 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -988,13 +988,13 @@ int rt6_route_rcv(struct net_device *dev, u8 *opt, int len,
} else if (rinfo->prefix_len > 128) {
return -EINVAL;
} else if (rinfo->prefix_len > 64) {
- if (rinfo->length < 2) {
+ /* RFC 4191: Length MUST be 3 when Prefix Length > 64 */
+ if (rinfo->length < 3)
return -EINVAL;
- }
} else if (rinfo->prefix_len > 0) {
- if (rinfo->length < 1) {
+ /* RFC 4191: Length MUST be 2 or 3 when Prefix Length > 0 */
+ if (rinfo->length < 2)
return -EINVAL;
- }
}
pref = rinfo->route_pref;
diff --git a/net/mac802154/scan.c b/net/mac802154/scan.c
index 775809ee0206..c6f3748936cc 100644
--- a/net/mac802154/scan.c
+++ b/net/mac802154/scan.c
@@ -415,6 +415,7 @@ void mac802154_beacon_worker(struct work_struct *work)
container_of(work, struct ieee802154_local, beacon_work.work);
struct cfg802154_beacon_request *beacon_req;
struct ieee802154_sub_if_data *sdata;
+ netdevice_tracker dev_tracker;
struct wpan_dev *wpan_dev;
u8 interval;
int ret;
@@ -427,12 +428,14 @@ void mac802154_beacon_worker(struct work_struct *work)
}
sdata = IEEE802154_WPAN_DEV_TO_SUB_IF(beacon_req->wpan_dev);
+ netdev_hold(sdata->dev, &dev_tracker, GFP_ATOMIC);
/* Wait an arbitrary amount of time in case we cannot use the device */
if (local->suspended || !ieee802154_sdata_running(sdata)) {
rcu_read_unlock();
queue_delayed_work(local->mac_wq, &local->beacon_work,
msecs_to_jiffies(1000));
+ netdev_put(sdata->dev, &dev_tracker);
return;
}
@@ -450,6 +453,7 @@ void mac802154_beacon_worker(struct work_struct *work)
if (interval < IEEE802154_ACTIVE_SCAN_DURATION)
queue_delayed_work(local->mac_wq, &local->beacon_work,
local->beacon_interval);
+ netdev_put(sdata->dev, &dev_tracker);
}
int mac802154_stop_beacons_locked(struct ieee802154_local *local,
diff --git a/net/ncsi/ncsi-netlink.c b/net/ncsi/ncsi-netlink.c
index 2f872d064396..8cc538358f6a 100644
--- a/net/ncsi/ncsi-netlink.c
+++ b/net/ncsi/ncsi-netlink.c
@@ -461,6 +461,10 @@ static int ncsi_send_cmd_nl(struct sk_buff *msg, struct genl_info *info)
nca.req_flags = NCSI_REQ_FLAG_NETLINK_DRIVEN;
nca.info = info;
nca.payload = ntohs(hdr->length);
+ if (nca.payload > len - sizeof(*hdr)) {
+ ret = -EINVAL;
+ goto out_netlink;
+ }
nca.data = data + sizeof(*hdr);
ret = ncsi_xmit_cmd(&nca);
diff --git a/net/netfilter/ipset/ip_set_bitmap_gen.h b/net/netfilter/ipset/ip_set_bitmap_gen.h
index cb48a2b9cb9f..cf8468bf987d 100644
--- a/net/netfilter/ipset/ip_set_bitmap_gen.h
+++ b/net/netfilter/ipset/ip_set_bitmap_gen.h
@@ -77,7 +77,7 @@ mtype_flush(struct ip_set *set)
mtype_ext_cleanup(set);
bitmap_zero(map->members, map->elements);
set->elements = 0;
- set->ext_size = 0;
+ atomic64_set(&set->ext_size, 0);
}
/* Calculate the actual memory size of the set data */
@@ -93,7 +93,7 @@ mtype_head(struct ip_set *set, struct sk_buff *skb)
{
const struct mtype *map = set->data;
struct nlattr *nested;
- size_t memsize = mtype_memsize(map, set->dsize) + set->ext_size;
+ size_t memsize = mtype_memsize(map, set->dsize) + atomic64_read(&set->ext_size);
nested = nla_nest_start(skb, IPSET_ATTR_DATA);
if (!nested)
diff --git a/net/netfilter/ipset/ip_set_core.c b/net/netfilter/ipset/ip_set_core.c
index f51a1af31513..29bf5ee74fe3 100644
--- a/net/netfilter/ipset/ip_set_core.c
+++ b/net/netfilter/ipset/ip_set_core.c
@@ -350,7 +350,7 @@ ip_set_init_comment(struct ip_set *set, struct ip_set_comment *comment,
size_t len = ext->comment ? strlen(ext->comment) : 0;
if (unlikely(c)) {
- set->ext_size -= sizeof(*c) + strlen(c->str) + 1;
+ atomic64_sub(sizeof(*c) + strlen(c->str) + 1, &set->ext_size);
rcu_assign_pointer(comment->c, NULL);
kfree_rcu(c, rcu);
}
@@ -362,7 +362,7 @@ ip_set_init_comment(struct ip_set *set, struct ip_set_comment *comment,
if (unlikely(!c))
return;
strscpy(c->str, ext->comment, len + 1);
- set->ext_size += sizeof(*c) + strlen(c->str) + 1;
+ atomic64_add(sizeof(*c) + strlen(c->str) + 1, &set->ext_size);
rcu_assign_pointer(comment->c, c);
}
EXPORT_SYMBOL_GPL(ip_set_init_comment);
@@ -392,7 +392,7 @@ ip_set_comment_free(struct ip_set *set, void *ptr)
c = rcu_dereference_protected(comment->c, 1);
if (unlikely(!c))
return;
- set->ext_size -= sizeof(*c) + strlen(c->str) + 1;
+ atomic64_sub(sizeof(*c) + strlen(c->str) + 1, &set->ext_size);
rcu_assign_pointer(comment->c, NULL);
kfree_rcu(c, rcu);
}
diff --git a/net/netfilter/ipset/ip_set_hash_gen.h b/net/netfilter/ipset/ip_set_hash_gen.h
index 4c1082e38e3d..81d7f601ed06 100644
--- a/net/netfilter/ipset/ip_set_hash_gen.h
+++ b/net/netfilter/ipset/ip_set_hash_gen.h
@@ -1289,7 +1289,7 @@ mtype_head(struct ip_set *set, struct sk_buff *skb)
rcu_read_lock_bh();
t = rcu_dereference_bh(h->table);
mtype_ext_size(set, &elements, &ext_size);
- memsize = mtype_ahash_memsize(h, t) + ext_size + set->ext_size;
+ memsize = mtype_ahash_memsize(h, t) + ext_size + atomic64_read(&set->ext_size);
htable_bits = t->htable_bits;
rcu_read_unlock_bh();
diff --git a/net/netfilter/ipset/ip_set_list_set.c b/net/netfilter/ipset/ip_set_list_set.c
index 83e1fdcc752d..9d6ab69ca1a3 100644
--- a/net/netfilter/ipset/ip_set_list_set.c
+++ b/net/netfilter/ipset/ip_set_list_set.c
@@ -421,7 +421,7 @@ list_set_flush(struct ip_set *set)
list_for_each_entry_safe(e, n, &map->members, list)
list_set_del(set, e);
set->elements = 0;
- set->ext_size = 0;
+ atomic64_set(&set->ext_size, 0);
}
static void
@@ -455,7 +455,7 @@ list_set_head(struct ip_set *set, struct sk_buff *skb)
{
const struct list_set *map = set->data;
struct nlattr *nested;
- size_t memsize = list_set_memsize(map, set->dsize) + set->ext_size;
+ size_t memsize = list_set_memsize(map, set->dsize) + atomic64_read(&set->ext_size);
nested = nla_nest_start(skb, IPSET_ATTR_DATA);
if (!nested)
diff --git a/net/netfilter/ipvs/ip_vs_conn.c b/net/netfilter/ipvs/ip_vs_conn.c
index 5ed91a8a8fdf..f50fbcb13f89 100644
--- a/net/netfilter/ipvs/ip_vs_conn.c
+++ b/net/netfilter/ipvs/ip_vs_conn.c
@@ -570,12 +570,6 @@ static inline void ip_vs_bind_xmit_v6(struct ip_vs_conn *cp)
#endif
-static inline int ip_vs_dest_totalconns(struct ip_vs_dest *dest)
-{
- return atomic_read(&dest->activeconns)
- + atomic_read(&dest->inactconns);
-}
-
/*
* Bind a connection entry with a virtual service destination
* Called just after a new connection entry is created.
@@ -627,23 +621,22 @@ ip_vs_bind_dest(struct ip_vs_conn *cp, struct ip_vs_dest *dest)
/* Update the connection counters */
if (!(flags & IP_VS_CONN_F_TEMPLATE)) {
+ int tc;
+
/* It is a normal connection, so modify the counters
* according to the flags, later the protocol can
* update them on state change
*/
if (!(flags & IP_VS_CONN_F_INACTIVE))
atomic_inc(&dest->activeconns);
- else
- atomic_inc(&dest->inactconns);
+ tc = atomic_inc_return(&dest->totalconns);
+ if (tc == READ_ONCE(dest->u_threshold))
+ ip_vs_dest_update_overload(dest, 1);
} else {
/* It is a persistent connection/template, so increase
the persistent connection counter */
atomic_inc(&dest->persistconns);
}
-
- if (dest->u_threshold != 0 &&
- ip_vs_dest_totalconns(dest) >= dest->u_threshold)
- dest->flags |= IP_VS_DEST_F_OVERLOAD;
}
@@ -724,30 +717,20 @@ static inline void ip_vs_unbind_dest(struct ip_vs_conn *cp)
/* Update the connection counters */
if (!(cp->flags & IP_VS_CONN_F_TEMPLATE)) {
- /* It is a normal connection, so decrease the inactconns
- or activeconns counter */
- if (cp->flags & IP_VS_CONN_F_INACTIVE) {
- atomic_dec(&dest->inactconns);
- } else {
+ int tc;
+
+ /* It is a normal connection, so decrease the counters */
+ if (!(cp->flags & IP_VS_CONN_F_INACTIVE))
atomic_dec(&dest->activeconns);
- }
+ tc = atomic_fetch_dec(&dest->totalconns);
+ if (tc == READ_ONCE(dest->l_threshold_val))
+ ip_vs_dest_update_overload(dest, -1);
} else {
/* It is a persistent connection/template, so decrease
the persistent connection counter */
atomic_dec(&dest->persistconns);
}
- if (dest->l_threshold != 0) {
- if (ip_vs_dest_totalconns(dest) < dest->l_threshold)
- dest->flags &= ~IP_VS_DEST_F_OVERLOAD;
- } else if (dest->u_threshold != 0) {
- if (ip_vs_dest_totalconns(dest) * 4 < dest->u_threshold * 3)
- dest->flags &= ~IP_VS_DEST_F_OVERLOAD;
- } else {
- if (dest->flags & IP_VS_DEST_F_OVERLOAD)
- dest->flags &= ~IP_VS_DEST_F_OVERLOAD;
- }
-
ip_vs_dest_put(dest);
}
diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c
index 6207a91e93f3..d121ea3d16bc 100644
--- a/net/netfilter/ipvs/ip_vs_core.c
+++ b/net/netfilter/ipvs/ip_vs_core.c
@@ -747,28 +747,27 @@ static int ip_vs_route_me_harder(struct netns_ipvs *ipvs, int af,
*/
void ip_vs_nat_icmp(struct sk_buff *skb, struct ip_vs_protocol *pp,
struct ip_vs_conn *cp, int inout, unsigned int toff,
- bool has_ports)
+ bool has_ports, struct ip_vs_iphdr *ciph)
{
struct iphdr *iph = ip_hdr(skb);
struct icmphdr *icmph = (struct icmphdr *)(skb->data + toff);
- struct iphdr *ciph = (struct iphdr *)(icmph + 1);
- unsigned int coff __maybe_unused = toff + sizeof(struct icmphdr);
+ struct iphdr *cih = (struct iphdr *)(icmph + 1);
if (inout) {
iph->saddr = cp->vaddr.ip;
ip_send_check(iph);
- ciph->daddr = cp->vaddr.ip;
- ip_send_check(ciph);
+ cih->daddr = cp->vaddr.ip;
+ ip_send_check(cih);
} else {
iph->daddr = cp->daddr.ip;
ip_send_check(iph);
- ciph->saddr = cp->daddr.ip;
- ip_send_check(ciph);
+ cih->saddr = cp->daddr.ip;
+ ip_send_check(cih);
}
/* the TCP/UDP/SCTP port */
if (has_ports) {
- __be16 *ports = (void *)ciph + ciph->ihl*4;
+ __be16 *ports = (void *)(skb->data + ciph->len);
if (inout)
ports[1] = cp->vport;
@@ -782,10 +781,10 @@ void ip_vs_nat_icmp(struct sk_buff *skb, struct ip_vs_protocol *pp,
skb->ip_summed = CHECKSUM_UNNECESSARY;
if (inout)
- IP_VS_DBG_PKT(11, AF_INET, pp, skb, coff,
+ IP_VS_DBG_PKT(11, AF_INET, pp, skb, ciph->off,
"Forwarding altered outgoing ICMP");
else
- IP_VS_DBG_PKT(11, AF_INET, pp, skb, coff,
+ IP_VS_DBG_PKT(11, AF_INET, pp, skb, ciph->off,
"Forwarding altered incoming ICMP");
}
@@ -878,7 +877,7 @@ static int handle_response_icmp(int af, struct sk_buff *skb,
ip_vs_nat_icmp_v6(skb, pp, cp, 1, toff, has_ports, ciph);
else
#endif
- ip_vs_nat_icmp(skb, pp, cp, 1, toff, has_ports);
+ ip_vs_nat_icmp(skb, pp, cp, 1, toff, has_ports, ciph);
if (ip_vs_route_me_harder(cp->ipvs, af, skb, hooknum))
goto out;
@@ -914,7 +913,7 @@ static int ip_vs_out_icmp(struct netns_ipvs *ipvs, struct sk_buff *skb,
struct ip_vs_iphdr ciph;
struct ip_vs_conn *cp;
struct ip_vs_protocol *pp;
- unsigned int offset, ihl;
+ unsigned int offset;
union nf_inet_addr snet;
*related = 1;
@@ -927,7 +926,6 @@ static int ip_vs_out_icmp(struct netns_ipvs *ipvs, struct sk_buff *skb,
return NF_ACCEPT;
}
- ihl = ipvsh->len;
offset = ipvsh->len;
ic = skb_header_pointer(skb, offset, sizeof(_icmph), &_icmph);
if (ic == NULL)
@@ -953,11 +951,15 @@ static int ip_vs_out_icmp(struct netns_ipvs *ipvs, struct sk_buff *skb,
/* Now find the contained IP header */
offset += sizeof(_icmph);
+ if (!ip_vs_fill_iph_skb_icmp(AF_INET, skb, offset, true, &ciph))
+ return NF_ACCEPT; /* The packet looks wrong, ignore */
+
cih = skb_header_pointer(skb, offset, sizeof(_ciph), &_ciph);
- if (!(cih && cih->version == 4 && cih->ihl >= 5))
+ if (!(cih && cih->version == 4 &&
+ ciph.len - ciph.off >= sizeof(struct iphdr)))
return NF_ACCEPT; /* The packet looks wrong, ignore */
- pp = ip_vs_proto_get(cih->protocol);
+ pp = ip_vs_proto_get(ciph.protocol);
if (!pp)
return NF_ACCEPT;
@@ -968,8 +970,6 @@ static int ip_vs_out_icmp(struct netns_ipvs *ipvs, struct sk_buff *skb,
IP_VS_DBG_PKT(11, AF_INET, pp, skb, offset,
"Checking outgoing ICMP for");
- ip_vs_fill_iph_skb_icmp(AF_INET, skb, offset, true, &ciph);
-
/* The embedded headers contain source and dest in reverse order */
cp = INDIRECT_CALL_1(pp->conn_out_get, ip_vs_conn_out_get_proto,
ipvs, AF_INET, skb, &ciph);
@@ -977,8 +977,8 @@ static int ip_vs_out_icmp(struct netns_ipvs *ipvs, struct sk_buff *skb,
return NF_ACCEPT;
snet.ip = ipvsh->saddr.ip;
- return handle_response_icmp(AF_INET, skb, &snet, cp, pp, &ciph, ihl,
- hooknum);
+ return handle_response_icmp(AF_INET, skb, &snet, cp, pp, &ciph,
+ ipvsh->len, hooknum);
}
#ifdef CONFIG_IP_VS_IPV6
@@ -1625,10 +1625,12 @@ ip_vs_in_icmp(struct netns_ipvs *ipvs, struct sk_buff *skb, int *related,
/* Now find the contained IP header */
offset += sizeof(_icmph);
cih = skb_header_pointer(skb, offset, sizeof(_ciph), &_ciph);
- if (!(cih && cih->version == 4 && cih->ihl >= 5))
+ if (!cih)
return NF_ACCEPT; /* The packet looks wrong, ignore */
- raddr = (union nf_inet_addr *)&cih->daddr;
hlen_ipip = cih->ihl * 4;
+ if (!(cih->version == 4 && hlen_ipip >= sizeof(struct iphdr)))
+ return NF_ACCEPT; /* The packet looks wrong, ignore */
+ raddr = (union nf_inet_addr *)&cih->daddr;
/* Special case for errors for IPIP/UDP/GRE tunnel packets */
tunnel = false;
@@ -1645,9 +1647,6 @@ ip_vs_in_icmp(struct netns_ipvs *ipvs, struct sk_buff *skb, int *related,
if (!dest || dest->tun_type != IP_VS_CONN_F_TUNNEL_TYPE_IPIP)
return NF_ACCEPT;
offset += hlen_ipip;
- cih = skb_header_pointer(skb, offset, sizeof(_ciph), &_ciph);
- if (!(cih && cih->version == 4 && cih->ihl >= 5))
- return NF_ACCEPT; /* The packet looks wrong, ignore */
tunnel = true;
} else if ((cih->protocol == IPPROTO_UDP || /* Can be UDP encap */
cih->protocol == IPPROTO_GRE) && /* Can be GRE encap */
@@ -1672,21 +1671,25 @@ ip_vs_in_icmp(struct netns_ipvs *ipvs, struct sk_buff *skb, int *related,
/* Skip IP and UDP/GRE tunnel headers */
offset = offset2 + ulen;
/* Now we should be at the original IP header */
- cih = skb_header_pointer(skb, offset, sizeof(_ciph),
- &_ciph);
- if (cih && cih->version == 4 && cih->ihl >= 5 &&
- iproto == IPPROTO_IPIP)
+ if (iproto == IPPROTO_IPIP)
tunnel = true;
else
return NF_ACCEPT;
}
}
- pd = ip_vs_proto_data_get(ipvs, cih->protocol);
+ if (!ip_vs_fill_iph_skb_icmp(AF_INET, skb, offset, !tunnel, &ciph))
+ return NF_ACCEPT;
+ pd = ip_vs_proto_data_get(ipvs, ciph.protocol);
if (!pd)
return NF_ACCEPT;
pp = pd->pp;
+ cih = skb_header_pointer(skb, offset, sizeof(_ciph), &_ciph);
+ if (!(cih && cih->version == 4 &&
+ ciph.len - ciph.off >= sizeof(struct iphdr)))
+ return NF_ACCEPT; /* The packet looks wrong, ignore */
+
/* Is the embedded protocol header present? */
if (unlikely(cih->frag_off & htons(IP_OFFSET) && !pp->dont_defrag))
return NF_ACCEPT;
@@ -1694,9 +1697,6 @@ ip_vs_in_icmp(struct netns_ipvs *ipvs, struct sk_buff *skb, int *related,
IP_VS_DBG_PKT(11, AF_INET, pp, skb, offset,
"Checking incoming ICMP for");
- offset2 = offset;
- ip_vs_fill_iph_skb_icmp(AF_INET, skb, offset, !tunnel, &ciph);
-
/* The embedded headers contain source and dest in reverse order.
* For IPIP/UDP/GRE tunnel this is error for request, not for reply.
*/
@@ -1726,11 +1726,12 @@ ip_vs_in_icmp(struct netns_ipvs *ipvs, struct sk_buff *skb, int *related,
}
if (tunnel) {
- unsigned int hlen_orig = cih->ihl * 4;
+ unsigned int hlen_orig = ciph.len - ciph.off;
__be32 info = ic->un.gateway;
__u8 type = ic->type;
__u8 code = ic->code;
+ offset2 = offset;
/* Update the MTU */
if (ic->type == ICMP_DEST_UNREACH &&
ic->code == ICMP_FRAG_NEEDED) {
@@ -1771,6 +1772,7 @@ ip_vs_in_icmp(struct netns_ipvs *ipvs, struct sk_buff *skb, int *related,
if (pskb_pull(skb, offset2) == NULL)
goto ignore_tunnel;
skb_reset_network_header(skb);
+ memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt));
/* Ensure the IP header is present in headroom */
if (!pskb_may_pull(skb, hlen_orig))
goto ignore_tunnel;
diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c
index fb638758594d..8aa29596b36f 100644
--- a/net/netfilter/ipvs/ip_vs_ctl.c
+++ b/net/netfilter/ipvs/ip_vs_ctl.c
@@ -960,6 +960,40 @@ void ip_vs_stats_free(struct ip_vs_stats *stats)
}
}
+/* Update overload flag based on number of dest conns and lower/upper
+ * connection thresholds:
+ * - conns reach u_threshold and exceed it: set the flag
+ * - conns go below l_threshold (or 75% of u_threshold): clear the flag
+ */
+static void __ip_vs_dest_update_overload(struct ip_vs_dest *dest, int mode)
+{
+ int conns;
+ u32 l, u;
+
+ lockdep_assert_held(&dest->dst_lock);
+ u = READ_ONCE(dest->u_threshold);
+ if (!u)
+ goto unset;
+ l = READ_ONCE(dest->l_threshold_val);
+ conns = atomic_read(&dest->totalconns);
+ if (conns >= (mode > 0 ? l : u)) {
+ dest->flags |= IP_VS_DEST_F_OVERLOAD;
+ return;
+ }
+ if (conns >= (mode < 0 ? u : l))
+ return;
+
+unset:
+ dest->flags &= ~IP_VS_DEST_F_OVERLOAD;
+}
+
+void ip_vs_dest_update_overload(struct ip_vs_dest *dest, int mode)
+{
+ spin_lock_bh(&dest->dst_lock);
+ __ip_vs_dest_update_overload(dest, mode);
+ spin_unlock_bh(&dest->dst_lock);
+}
+
/*
* Update a destination in the given service
*/
@@ -1026,10 +1060,19 @@ __ip_vs_update_dest(struct ip_vs_service *svc, struct ip_vs_dest *dest,
/* set the dest status flags */
dest->flags |= IP_VS_DEST_F_AVAILABLE;
- if (udest->u_threshold == 0 || udest->u_threshold > dest->u_threshold)
- dest->flags &= ~IP_VS_DEST_F_OVERLOAD;
- dest->u_threshold = udest->u_threshold;
- dest->l_threshold = udest->l_threshold;
+ if (READ_ONCE(dest->u_threshold) != udest->u_threshold ||
+ READ_ONCE(dest->l_threshold) != udest->l_threshold) {
+ spin_lock_bh(&dest->dst_lock);
+ WRITE_ONCE(dest->u_threshold, udest->u_threshold);
+ WRITE_ONCE(dest->l_threshold, udest->l_threshold);
+ /* Low threshold defaults to 75% of upper threshold */
+ WRITE_ONCE(dest->l_threshold_val,
+ udest->l_threshold ? :
+ (udest->u_threshold -
+ (udest->u_threshold >> 2)));
+ __ip_vs_dest_update_overload(dest, 0);
+ spin_unlock_bh(&dest->dst_lock);
+ }
dest->af = udest->af;
@@ -1101,7 +1144,7 @@ ip_vs_new_dest(struct ip_vs_service *svc, struct ip_vs_dest_user_kern *udest)
dest->port = udest->port;
atomic_set(&dest->activeconns, 0);
- atomic_set(&dest->inactconns, 0);
+ atomic_set(&dest->totalconns, 0);
atomic_set(&dest->persistconns, 0);
refcount_set(&dest->refcnt, 1);
@@ -1142,6 +1185,9 @@ ip_vs_add_dest(struct ip_vs_service *svc, struct ip_vs_dest_user_kern *udest)
return -ERANGE;
}
+ if (udest->u_threshold > INT_MAX)
+ return -EINVAL;
+
if (udest->tun_type == IP_VS_CONN_F_TUNNEL_TYPE_GUE) {
if (udest->tun_port == 0) {
pr_err("%s(): tunnel port is zero\n", __func__);
@@ -1212,6 +1258,9 @@ ip_vs_edit_dest(struct ip_vs_service *svc, struct ip_vs_dest_user_kern *udest)
return -ERANGE;
}
+ if (udest->u_threshold > INT_MAX)
+ return -EINVAL;
+
if (udest->tun_type == IP_VS_CONN_F_TUNNEL_TYPE_GUE) {
if (udest->tun_port == 0) {
pr_err("%s(): tunnel port is zero\n", __func__);
@@ -2456,7 +2505,7 @@ static int ip_vs_info_seq_show(struct seq_file *seq, void *v)
ip_vs_fwd_name(atomic_read(&dest->conn_flags)),
atomic_read(&dest->weight),
atomic_read(&dest->activeconns),
- atomic_read(&dest->inactconns));
+ ip_vs_dest_inactconns(dest));
else
#endif
seq_printf(seq,
@@ -2467,7 +2516,7 @@ static int ip_vs_info_seq_show(struct seq_file *seq, void *v)
ip_vs_fwd_name(atomic_read(&dest->conn_flags)),
atomic_read(&dest->weight),
atomic_read(&dest->activeconns),
- atomic_read(&dest->inactconns));
+ ip_vs_dest_inactconns(dest));
}
}
@@ -2950,10 +2999,10 @@ __ip_vs_get_dest_entries(struct netns_ipvs *ipvs, const struct ip_vs_get_dests *
entry.port = dest->port;
entry.conn_flags = atomic_read(&dest->conn_flags);
entry.weight = atomic_read(&dest->weight);
- entry.u_threshold = dest->u_threshold;
- entry.l_threshold = dest->l_threshold;
+ entry.u_threshold = READ_ONCE(dest->u_threshold);
+ entry.l_threshold = READ_ONCE(dest->l_threshold);
entry.activeconns = atomic_read(&dest->activeconns);
- entry.inactconns = atomic_read(&dest->inactconns);
+ entry.inactconns = ip_vs_dest_inactconns(dest);
entry.persistconns = atomic_read(&dest->persistconns);
ip_vs_copy_stats(&kstats, &dest->stats);
ip_vs_export_stats_user(&entry.stats, &kstats);
@@ -3552,12 +3601,14 @@ static int ip_vs_genl_fill_dest(struct sk_buff *skb, struct ip_vs_dest *dest)
dest->tun_port) ||
nla_put_u16(skb, IPVS_DEST_ATTR_TUN_FLAGS,
dest->tun_flags) ||
- nla_put_u32(skb, IPVS_DEST_ATTR_U_THRESH, dest->u_threshold) ||
- nla_put_u32(skb, IPVS_DEST_ATTR_L_THRESH, dest->l_threshold) ||
+ nla_put_u32(skb, IPVS_DEST_ATTR_U_THRESH,
+ READ_ONCE(dest->u_threshold)) ||
+ nla_put_u32(skb, IPVS_DEST_ATTR_L_THRESH,
+ READ_ONCE(dest->l_threshold)) ||
nla_put_u32(skb, IPVS_DEST_ATTR_ACTIVE_CONNS,
atomic_read(&dest->activeconns)) ||
nla_put_u32(skb, IPVS_DEST_ATTR_INACT_CONNS,
- atomic_read(&dest->inactconns)) ||
+ ip_vs_dest_inactconns(dest)) ||
nla_put_u32(skb, IPVS_DEST_ATTR_PERSIST_CONNS,
atomic_read(&dest->persistconns)) ||
nla_put_u16(skb, IPVS_DEST_ATTR_ADDR_FAMILY, dest->af))
diff --git a/net/netfilter/ipvs/ip_vs_est.c b/net/netfilter/ipvs/ip_vs_est.c
index 3492108bb3b9..64fbf2aa4cce 100644
--- a/net/netfilter/ipvs/ip_vs_est.c
+++ b/net/netfilter/ipvs/ip_vs_est.c
@@ -187,8 +187,11 @@ static int ip_vs_estimation_kthread(void *data)
}
/* kthread 0 will handle the calc phase */
- if (ipvs->est_calc_phase)
+ if (ipvs->est_calc_phase) {
ip_vs_est_calc_phase(ipvs);
+ if (kthread_should_stop() || !READ_ONCE(ipvs->enable))
+ return 0;
+ }
}
while (1) {
@@ -263,6 +266,7 @@ int ip_vs_est_kthread_start(struct netns_ipvs *ipvs,
kd->task = NULL;
goto out;
}
+ get_task_struct(kd->task);
set_user_nice(kd->task, sysctl_est_nice(ipvs));
set_cpus_allowed_ptr(kd->task, sysctl_est_cpulist(ipvs));
@@ -278,7 +282,7 @@ void ip_vs_est_kthread_stop(struct ip_vs_est_kt_data *kd)
{
if (kd->task) {
pr_info("stopping estimator thread %d...\n", kd->id);
- kthread_stop(kd->task);
+ kthread_stop_put(kd->task);
kd->task = NULL;
}
}
@@ -510,7 +514,7 @@ static void ip_vs_est_kthread_destroy(struct ip_vs_est_kt_data *kd)
if (kd) {
if (kd->task) {
pr_info("stop unused estimator thread %d...\n", kd->id);
- kthread_stop(kd->task);
+ kthread_stop_put(kd->task);
}
ip_vs_stats_free(kd->calc_stats);
kfree(kd);
diff --git a/net/netfilter/ipvs/ip_vs_lc.c b/net/netfilter/ipvs/ip_vs_lc.c
index c2764505e380..cd1a860ebaec 100644
--- a/net/netfilter/ipvs/ip_vs_lc.c
+++ b/net/netfilter/ipvs/ip_vs_lc.c
@@ -31,7 +31,7 @@ ip_vs_lc_schedule(struct ip_vs_service *svc, const struct sk_buff *skb,
/*
* Simply select the server with the least number of
- * (activeconns<<5) + inactconns
+ * (activeconns*256) + totalconns
* Except whose weight is equal to zero.
* If the weight is equal to zero, it means that the server is
* quiesced, the existing connections to the server still get
@@ -57,7 +57,7 @@ ip_vs_lc_schedule(struct ip_vs_service *svc, const struct sk_buff *skb,
IP_VS_DBG_ADDR(least->af, &least->addr),
ntohs(least->port),
atomic_read(&least->activeconns),
- atomic_read(&least->inactconns));
+ ip_vs_dest_inactconns(least));
return least;
}
diff --git a/net/netfilter/ipvs/ip_vs_proto_sctp.c b/net/netfilter/ipvs/ip_vs_proto_sctp.c
index 3dbd3096e163..fb8af6b15a39 100644
--- a/net/netfilter/ipvs/ip_vs_proto_sctp.c
+++ b/net/netfilter/ipvs/ip_vs_proto_sctp.c
@@ -193,7 +193,7 @@ sctp_csum_check(int af, struct sk_buff *skb, struct ip_vs_protocol *pp,
struct sctphdr *sh;
__le32 cmp, val;
- if (!ip_vs_checksum_needed(skb, af))
+ if (!ip_vs_checksum_needed(skb))
return 1;
sh = (struct sctphdr *)(skb->data + sctphoff);
cmp = sh->checksum;
@@ -446,12 +446,10 @@ set_sctp_state(struct ip_vs_proto_data *pd, struct ip_vs_conn *cp,
if (!(cp->flags & IP_VS_CONN_F_INACTIVE) &&
(next_state != IP_VS_SCTP_S_ESTABLISHED)) {
atomic_dec(&dest->activeconns);
- atomic_inc(&dest->inactconns);
cp->flags |= IP_VS_CONN_F_INACTIVE;
} else if ((cp->flags & IP_VS_CONN_F_INACTIVE) &&
(next_state == IP_VS_SCTP_S_ESTABLISHED)) {
atomic_inc(&dest->activeconns);
- atomic_dec(&dest->inactconns);
cp->flags &= ~IP_VS_CONN_F_INACTIVE;
}
}
diff --git a/net/netfilter/ipvs/ip_vs_proto_tcp.c b/net/netfilter/ipvs/ip_vs_proto_tcp.c
index 1ac9c233537d..944efd34290c 100644
--- a/net/netfilter/ipvs/ip_vs_proto_tcp.c
+++ b/net/netfilter/ipvs/ip_vs_proto_tcp.c
@@ -527,12 +527,10 @@ set_tcp_state(struct ip_vs_proto_data *pd, struct ip_vs_conn *cp,
if (!(cp->flags & IP_VS_CONN_F_INACTIVE) &&
!tcp_state_active(new_state)) {
atomic_dec(&dest->activeconns);
- atomic_inc(&dest->inactconns);
cp->flags |= IP_VS_CONN_F_INACTIVE;
} else if ((cp->flags & IP_VS_CONN_F_INACTIVE) &&
tcp_state_active(new_state)) {
atomic_inc(&dest->activeconns);
- atomic_dec(&dest->inactconns);
cp->flags &= ~IP_VS_CONN_F_INACTIVE;
}
}
diff --git a/net/netfilter/ipvs/ip_vs_sync.c b/net/netfilter/ipvs/ip_vs_sync.c
index 3402675bf521..4c6e25398536 100644
--- a/net/netfilter/ipvs/ip_vs_sync.c
+++ b/net/netfilter/ipvs/ip_vs_sync.c
@@ -879,13 +879,10 @@ static void ip_vs_proc_conn(struct netns_ipvs *ipvs, struct ip_vs_conn_param *pa
spin_lock_bh(&cp->lock);
if ((cp->flags ^ flags) & IP_VS_CONN_F_INACTIVE &&
!(flags & IP_VS_CONN_F_TEMPLATE) && dest) {
- if (flags & IP_VS_CONN_F_INACTIVE) {
+ if (flags & IP_VS_CONN_F_INACTIVE)
atomic_dec(&dest->activeconns);
- atomic_inc(&dest->inactconns);
- } else {
+ else
atomic_inc(&dest->activeconns);
- atomic_dec(&dest->inactconns);
- }
}
flags &= IP_VS_CONN_F_BACKUP_UPD_MASK;
flags |= cp->flags & ~IP_VS_CONN_F_BACKUP_UPD_MASK;
diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c
index b85420a3a14c..240378e37741 100644
--- a/net/netfilter/ipvs/ip_vs_xmit.c
+++ b/net/netfilter/ipvs/ip_vs_xmit.c
@@ -1577,7 +1577,7 @@ ip_vs_icmp_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
if (skb_cow(skb, rt->dst.dev->hard_header_len))
goto tx_error;
- ip_vs_nat_icmp(skb, pp, cp, 0, toff, has_ports);
+ ip_vs_nat_icmp(skb, pp, cp, 0, toff, has_ports, ciph);
/* Another hack: avoid icmp_send in ip_fragment */
skb->ignore_df = 1;
diff --git a/net/netfilter/nf_conntrack_proto.c b/net/netfilter/nf_conntrack_proto.c
index f36727ed91e1..6ffa1f21d985 100644
--- a/net/netfilter/nf_conntrack_proto.c
+++ b/net/netfilter/nf_conntrack_proto.c
@@ -79,6 +79,12 @@ void nf_ct_l4proto_log_invalid(const struct sk_buff *skb,
struct net *net;
va_list args;
+ /* nfnetlink_log may re-enter conntrack attribute dumping and try to
+ * take ct->lock again via helpers such as tcp_to_nlattr(), so invalid
+ * conntrack logs must only be emitted after dropping ct->lock.
+ */
+ lockdep_assert_not_held(&ct->lock);
+
net = nf_ct_net(ct);
if (likely(net->ct.sysctl_log_invalid == 0))
return;
diff --git a/net/netfilter/nf_conntrack_proto_sctp.c b/net/netfilter/nf_conntrack_proto_sctp.c
index 0dd55d3fba38..ef51f0babf94 100644
--- a/net/netfilter/nf_conntrack_proto_sctp.c
+++ b/net/netfilter/nf_conntrack_proto_sctp.c
@@ -341,10 +341,12 @@ int nf_conntrack_sctp_packet(struct nf_conn *ct,
struct sctphdr _sctph;
const struct sctp_chunkhdr *sch;
struct sctp_chunkhdr _sch;
+ bool log_invalid = false;
u_int32_t offset, count;
unsigned int *timeouts;
unsigned long map[256 / sizeof(unsigned long)] = { 0 };
bool ignore = false;
+ u8 invalid_type = 0;
if (sctp_error(skb, dataoff, state))
return -NF_ACCEPT;
@@ -456,10 +458,8 @@ int nf_conntrack_sctp_packet(struct nf_conn *ct,
/* Invalid */
if (new_state == SCTP_CONNTRACK_MAX) {
- nf_ct_l4proto_log_invalid(skb, ct, state,
- "Invalid, old_state %d, dir %d, type %d",
- old_state, dir, sch->type);
-
+ log_invalid = true;
+ invalid_type = sch->type;
goto out_unlock;
}
@@ -534,6 +534,10 @@ int nf_conntrack_sctp_packet(struct nf_conn *ct,
out_unlock:
spin_unlock_bh(&ct->lock);
+ if (log_invalid)
+ nf_ct_l4proto_log_invalid(skb, ct, state,
+ "Invalid, old_state %d, dir %d, type %d",
+ old_state, dir, invalid_type);
out:
return -NF_ACCEPT;
}
diff --git a/net/netfilter/nf_conntrack_proto_tcp.c b/net/netfilter/nf_conntrack_proto_tcp.c
index e99ab1e88e9f..c289bec0c7c7 100644
--- a/net/netfilter/nf_conntrack_proto_tcp.c
+++ b/net/netfilter/nf_conntrack_proto_tcp.c
@@ -480,37 +480,81 @@ static void tcp_init_sender(struct ip_ct_tcp_state *sender,
}
}
-__printf(6, 7)
-static enum nf_ct_tcp_action nf_tcp_log_invalid(const struct sk_buff *skb,
- const struct nf_conn *ct,
- const struct nf_hook_state *state,
- const struct ip_ct_tcp_state *sender,
- enum nf_ct_tcp_action ret,
- const char *fmt, ...)
+enum nf_tcp_invalid_log_type {
+ NF_TCP_LOG_NONE,
+ NF_TCP_LOG_OVERSHOT,
+ NF_TCP_LOG_SEQ_OVER,
+ NF_TCP_LOG_ACK_OVER,
+ NF_TCP_LOG_SEQ_UNDER,
+ NF_TCP_LOG_ACK_UNDER,
+};
+
+struct nf_tcp_invalid_log {
+ enum nf_tcp_invalid_log_type type;
+ u32 value;
+};
+
+static enum nf_ct_tcp_action
+nf_tcp_store_invalid(const struct nf_conn *ct,
+ const struct ip_ct_tcp_state *sender,
+ struct nf_tcp_invalid_log *log,
+ enum nf_ct_tcp_action ret,
+ enum nf_tcp_invalid_log_type type,
+ u32 value)
{
const struct nf_tcp_net *tn = nf_tcp_pernet(nf_ct_net(ct));
- struct va_format vaf;
- va_list args;
bool be_liberal;
be_liberal = sender->flags & IP_CT_TCP_FLAG_BE_LIBERAL || tn->tcp_be_liberal;
if (be_liberal)
return NFCT_TCP_ACCEPT;
- va_start(args, fmt);
- vaf.fmt = fmt;
- vaf.va = &args;
- nf_ct_l4proto_log_invalid(skb, ct, state, "%pV", &vaf);
- va_end(args);
-
+ log->type = type;
+ log->value = value;
return ret;
}
+static void nf_tcp_log_invalid(const struct sk_buff *skb,
+ const struct nf_conn *ct,
+ const struct nf_hook_state *state,
+ const struct nf_tcp_invalid_log *log)
+{
+ switch (log->type) {
+ case NF_TCP_LOG_OVERSHOT:
+ nf_ct_l4proto_log_invalid(skb, ct, state,
+ "%u bytes more than expected",
+ log->value);
+ break;
+ case NF_TCP_LOG_SEQ_OVER:
+ nf_ct_l4proto_log_invalid(skb, ct, state,
+ "SEQ is over upper bound %u (over the window of the receiver)",
+ log->value);
+ break;
+ case NF_TCP_LOG_ACK_OVER:
+ nf_ct_l4proto_log_invalid(skb, ct, state,
+ "ACK is over upper bound %u (ACKed data not seen yet)",
+ log->value);
+ break;
+ case NF_TCP_LOG_SEQ_UNDER:
+ nf_ct_l4proto_log_invalid(skb, ct, state,
+ "SEQ is under lower bound %u (already ACKed data retransmitted)",
+ log->value);
+ break;
+ case NF_TCP_LOG_ACK_UNDER:
+ nf_ct_l4proto_log_invalid(skb, ct, state,
+ "ignored ACK under lower bound %u (possible overly delayed)",
+ log->value);
+ break;
+ case NF_TCP_LOG_NONE:
+ break;
+ }
+}
+
static enum nf_ct_tcp_action
tcp_in_window(struct nf_conn *ct, enum ip_conntrack_dir dir,
unsigned int index, const struct sk_buff *skb,
unsigned int dataoff, const struct tcphdr *tcph,
- const struct nf_hook_state *hook_state)
+ struct nf_tcp_invalid_log *log)
{
struct ip_ct_tcp *state = &ct->proto.tcp;
struct ip_ct_tcp_state *sender = &state->seen[dir];
@@ -640,31 +684,29 @@ tcp_in_window(struct nf_conn *ct, enum ip_conntrack_dir dir,
sender->td_end = end;
sender->flags |= IP_CT_TCP_FLAG_DATA_UNACKNOWLEDGED;
- return nf_tcp_log_invalid(skb, ct, hook_state, sender, NFCT_TCP_IGNORE,
- "%u bytes more than expected", overshot);
+ return nf_tcp_store_invalid(ct, sender, log, NFCT_TCP_IGNORE,
+ NF_TCP_LOG_OVERSHOT, overshot);
}
- return nf_tcp_log_invalid(skb, ct, hook_state, sender, NFCT_TCP_INVALID,
- "SEQ is over upper bound %u (over the window of the receiver)",
- sender->td_maxend + 1);
+ return nf_tcp_store_invalid(ct, sender, log, NFCT_TCP_INVALID,
+ NF_TCP_LOG_SEQ_OVER, sender->td_maxend + 1);
}
if (!before(sack, receiver->td_end + 1))
- return nf_tcp_log_invalid(skb, ct, hook_state, sender, NFCT_TCP_INVALID,
- "ACK is over upper bound %u (ACKed data not seen yet)",
- receiver->td_end + 1);
+ return nf_tcp_store_invalid(ct, sender, log, NFCT_TCP_INVALID,
+ NF_TCP_LOG_ACK_OVER, receiver->td_end + 1);
/* Is the ending sequence in the receive window (if available)? */
in_recv_win = !receiver->td_maxwin ||
after(end, sender->td_end - receiver->td_maxwin - 1);
if (!in_recv_win)
- return nf_tcp_log_invalid(skb, ct, hook_state, sender, NFCT_TCP_IGNORE,
- "SEQ is under lower bound %u (already ACKed data retransmitted)",
- sender->td_end - receiver->td_maxwin - 1);
+ return nf_tcp_store_invalid(ct, sender, log, NFCT_TCP_IGNORE,
+ NF_TCP_LOG_SEQ_UNDER,
+ sender->td_end - receiver->td_maxwin - 1);
if (!after(sack, receiver->td_end - MAXACKWINDOW(sender) - 1))
- return nf_tcp_log_invalid(skb, ct, hook_state, sender, NFCT_TCP_IGNORE,
- "ignored ACK under lower bound %u (possible overly delayed)",
- receiver->td_end - MAXACKWINDOW(sender) - 1);
+ return nf_tcp_store_invalid(ct, sender, log, NFCT_TCP_IGNORE,
+ NF_TCP_LOG_ACK_UNDER,
+ receiver->td_end - MAXACKWINDOW(sender) - 1);
/* Take into account window scaling (RFC 1323). */
if (!tcph->syn)
@@ -719,11 +761,8 @@ tcp_in_window(struct nf_conn *ct, enum ip_conntrack_dir dir,
return NFCT_TCP_ACCEPT;
}
-static void __cold nf_tcp_handle_invalid(struct nf_conn *ct,
- enum ip_conntrack_dir dir,
- int index,
- const struct sk_buff *skb,
- const struct nf_hook_state *hook_state)
+static bool __cold
+nf_tcp_handle_invalid(struct nf_conn *ct, enum ip_conntrack_dir dir, int index)
{
const unsigned int *timeouts;
const struct nf_tcp_net *tn;
@@ -732,7 +771,7 @@ static void __cold nf_tcp_handle_invalid(struct nf_conn *ct,
if (!test_bit(IPS_ASSURED_BIT, &ct->status) ||
test_bit(IPS_FIXED_TIMEOUT_BIT, &ct->status))
- return;
+ return false;
/* We don't want to have connections hanging around in ESTABLISHED
* state for long time 'just because' conntrack deemed a FIN/RST
@@ -747,7 +786,7 @@ static void __cold nf_tcp_handle_invalid(struct nf_conn *ct,
case TCP_FIN_SET:
break;
default:
- return;
+ return false;
}
if (ct->proto.tcp.last_dir != dir &&
@@ -755,7 +794,7 @@ static void __cold nf_tcp_handle_invalid(struct nf_conn *ct,
ct->proto.tcp.last_index == TCP_RST_SET)) {
expires = nf_ct_expires(ct);
if (expires < 120 * HZ)
- return;
+ return false;
tn = nf_tcp_pernet(nf_ct_net(ct));
timeouts = nf_ct_timeout_lookup(ct);
@@ -764,16 +803,15 @@ static void __cold nf_tcp_handle_invalid(struct nf_conn *ct,
timeout = READ_ONCE(timeouts[TCP_CONNTRACK_UNACK]);
if (expires > timeout) {
- nf_ct_l4proto_log_invalid(skb, ct, hook_state,
- "packet (index %d, dir %d) response for index %d lower timeout to %u",
- index, dir, ct->proto.tcp.last_index, timeout);
-
WRITE_ONCE(ct->timeout, timeout + nfct_time_stamp);
+ return true;
}
} else {
ct->proto.tcp.last_index = index;
ct->proto.tcp.last_dir = dir;
}
+
+ return false;
}
/* table of valid flag combinations - PUSH, ECE and CWR are always valid */
@@ -969,7 +1007,9 @@ int nf_conntrack_tcp_packet(struct nf_conn *ct,
struct net *net = nf_ct_net(ct);
struct nf_tcp_net *tn = nf_tcp_pernet(net);
enum tcp_conntrack new_state, old_state;
+ struct nf_tcp_invalid_log log = {};
unsigned int index, *timeouts;
+ bool lowered_timeout = false;
enum nf_ct_tcp_action res;
enum ip_conntrack_dir dir;
const struct tcphdr *th;
@@ -1252,14 +1292,18 @@ int nf_conntrack_tcp_packet(struct nf_conn *ct,
}
res = tcp_in_window(ct, dir, index,
- skb, dataoff, th, state);
+ skb, dataoff, th, &log);
switch (res) {
case NFCT_TCP_IGNORE:
spin_unlock_bh(&ct->lock);
+ nf_tcp_log_invalid(skb, ct, state, &log);
return NF_ACCEPT;
case NFCT_TCP_INVALID:
- nf_tcp_handle_invalid(ct, dir, index, skb, state);
+ lowered_timeout = nf_tcp_handle_invalid(ct, dir, index);
spin_unlock_bh(&ct->lock);
+ nf_tcp_log_invalid(skb, ct, state, &log);
+ if (lowered_timeout)
+ nf_ct_l4proto_log_invalid(skb, ct, state, "lowered timeout to UNACK");
return -NF_ACCEPT;
case NFCT_TCP_ACCEPT:
break;
diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c
index 7af539d63c06..8436a560ab1f 100644
--- a/net/openvswitch/datapath.c
+++ b/net/openvswitch/datapath.c
@@ -1083,9 +1083,8 @@ static int ovs_flow_cmd_new(struct sk_buff *skb, struct genl_info *info)
error = -EEXIST;
goto err_unlock_ovs;
}
- /* The flow identifier has to be the same for flow updates.
- * Look for any overlapping flow.
- */
+
+ /* Look for any overlapping flow. */
if (unlikely(!ovs_flow_cmp(flow, &match))) {
if (ovs_identifier_is_key(&flow->id))
flow = ovs_flow_tbl_lookup_exact(&dp->table,
@@ -1097,6 +1096,30 @@ static int ovs_flow_cmd_new(struct sk_buff *skb, struct genl_info *info)
goto err_unlock_ovs;
}
}
+
+ if (unlikely(reply)) {
+ size_t cur, req;
+
+ cur = ovs_flow_cmd_msg_size(acts, &new_flow->id,
+ ufid_flags);
+ req = ovs_flow_cmd_msg_size(acts, &flow->id,
+ ufid_flags);
+ if (cur < req) {
+ struct sk_buff *resized;
+
+ resized = ovs_flow_cmd_alloc_info(acts,
+ &flow->id,
+ info, false,
+ ufid_flags);
+ if (IS_ERR(resized)) {
+ error = PTR_ERR(resized);
+ goto err_unlock_ovs;
+ }
+ kfree_skb(reply);
+ reply = resized;
+ }
+ }
+
/* Update actions. */
old_acts = ovsl_dereference(flow->sf_acts);
rcu_assign_pointer(flow->sf_acts, acts);
diff --git a/net/openvswitch/flow.c b/net/openvswitch/flow.c
index b80bd3a90773..52e261ce91e8 100644
--- a/net/openvswitch/flow.c
+++ b/net/openvswitch/flow.c
@@ -893,8 +893,6 @@ static int key_extract_l3l4(struct sk_buff *skb, struct sw_flow_key *key)
* Ethernet header
* @key: output flow key
*
- * The caller must ensure that skb->len >= ETH_HLEN.
- *
* Initializes @skb header fields as follows:
*
* - skb->mac_header: the L2 header.
@@ -914,8 +912,6 @@ static int key_extract_l3l4(struct sk_buff *skb, struct sw_flow_key *key)
*/
static int key_extract(struct sk_buff *skb, struct sw_flow_key *key)
{
- struct ethhdr *eth;
-
/* Flags are always used as part of stats */
key->tp.flags = 0;
@@ -930,6 +926,13 @@ static int key_extract(struct sk_buff *skb, struct sw_flow_key *key)
skb_reset_network_header(skb);
key->eth.type = skb->protocol;
} else {
+ struct ethhdr *eth;
+ int err;
+
+ err = check_header(skb, ETH_HLEN);
+ if (unlikely(err))
+ return err;
+
eth = eth_hdr(skb);
ether_addr_copy(key->eth.src, eth->h_source);
ether_addr_copy(key->eth.dst, eth->h_dest);
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index c59007525226..102055a8c1d6 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -1367,13 +1367,25 @@ static int packet_rcv_has_room(struct packet_sock *po, struct sk_buff *skb)
return ret;
}
-static void packet_rcv_try_clear_pressure(struct packet_sock *po)
+static void __packet_rcv_try_clear_pressure(struct packet_sock *po)
{
if (packet_sock_flag(po, PACKET_SOCK_PRESSURE) &&
__packet_rcv_has_room(po, NULL) == ROOM_NORMAL)
packet_sock_flag_set(po, PACKET_SOCK_PRESSURE, false);
}
+static void packet_rcv_try_clear_pressure(struct packet_sock *po)
+{
+ struct sock *sk = &po->sk;
+
+ if (!packet_sock_flag(po, PACKET_SOCK_PRESSURE))
+ return;
+
+ spin_lock_bh(&sk->sk_receive_queue.lock);
+ __packet_rcv_try_clear_pressure(po);
+ spin_unlock_bh(&sk->sk_receive_queue.lock);
+}
+
static void packet_sock_destruct(struct sock *sk)
{
skb_queue_purge(&sk->sk_error_queue);
@@ -1976,11 +1988,12 @@ static void packet_parse_headers(struct sk_buff *skb, struct socket *sock)
{
int depth;
+ /* On TX skb->data is the L2 header; anchor it for all socket types. */
+ skb_reset_mac_header(skb);
+
if ((!skb->protocol || skb->protocol == htons(ETH_P_ALL)) &&
- sock->type == SOCK_RAW) {
- skb_reset_mac_header(skb);
+ sock->type == SOCK_RAW)
skb->protocol = dev_parse_header_protocol(skb);
- }
/* Move network header to the right position for VLAN tagged packets */
if (likely(skb->dev->type == ARPHRD_ETHER) &&
@@ -2005,8 +2018,9 @@ static int packet_sendmsg_spkt(struct socket *sock, struct msghdr *msg,
struct net_device *dev;
struct sockcm_cookie sockc;
__be16 proto = 0;
- int err;
+ int hard_header_len;
int extra_len = 0;
+ int err;
/*
* Get and verify the address.
@@ -2049,14 +2063,18 @@ static int packet_sendmsg_spkt(struct socket *sock, struct msghdr *msg,
extra_len = 4; /* We're doing our own CRC */
}
+ /* Keep the allocation-time header length across retry. */
+ if (!skb)
+ hard_header_len = READ_ONCE(dev->hard_header_len);
+
err = -EMSGSIZE;
- if (len > dev->mtu + dev->hard_header_len + VLAN_HLEN + extra_len)
+ if (len > dev->mtu + hard_header_len + VLAN_HLEN + extra_len)
goto out_unlock;
if (!skb) {
- size_t reserved = LL_RESERVED_SPACE(dev);
+ size_t reserved = LL_RESERVED_SPACE_EX(dev, hard_header_len);
int tlen = dev->needed_tailroom;
- unsigned int hhlen = dev->header_ops ? dev->hard_header_len : 0;
+ unsigned int hhlen = dev->header_ops ? hard_header_len : 0;
rcu_read_unlock();
skb = sock_wmalloc(sk, len + reserved + tlen, 0, GFP_KERNEL);
@@ -2086,7 +2104,7 @@ static int packet_sendmsg_spkt(struct socket *sock, struct msghdr *msg,
err = -EINVAL;
goto out_unlock;
}
- if (len > (dev->mtu + dev->hard_header_len + extra_len) &&
+ if (len > (dev->mtu + hard_header_len + extra_len) &&
!packet_extra_vlan_len_allowed(dev, skb)) {
err = -EMSGSIZE;
goto out_unlock;
@@ -2621,6 +2639,7 @@ static int packet_snd_vnet_parse(struct msghdr *msg, size_t *len,
static int tpacket_fill_skb(struct packet_sock *po, struct sk_buff *skb,
void *frame, struct net_device *dev, void *data, int tp_len,
__be16 proto, unsigned char *addr, int hlen, int copylen,
+ int hard_header_len,
const struct sockcm_cookie *sockc)
{
union tpacket_uhdr ph;
@@ -2652,8 +2671,8 @@ static int tpacket_fill_skb(struct packet_sock *po, struct sk_buff *skb,
} else if (copylen) {
int hdrlen = min_t(int, copylen, tp_len);
- skb_push(skb, dev->hard_header_len);
- skb_put(skb, copylen - dev->hard_header_len);
+ skb_push(skb, hard_header_len);
+ skb_put(skb, copylen - hard_header_len);
err = skb_store_bits(skb, 0, data, hdrlen);
if (unlikely(err))
return err;
@@ -2784,7 +2803,7 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg)
void *data;
int len_sum = 0;
int status = TP_STATUS_AVAILABLE;
- int hlen, tlen, copylen = 0;
+ int hard_header_len, hlen, tlen, copylen = 0;
long timeo;
mutex_lock(&po->pg_vec_lock);
@@ -2831,8 +2850,9 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg)
goto out_put;
}
+ hard_header_len = READ_ONCE(dev->hard_header_len);
if (po->sk.sk_socket->type == SOCK_RAW)
- reserve = dev->hard_header_len;
+ reserve = hard_header_len;
size_max = po->tx_ring.frame_size
- (po->tp_hdrlen - sizeof(struct sockaddr_ll));
@@ -2869,7 +2889,7 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg)
goto tpacket_error;
status = TP_STATUS_SEND_REQUEST;
- hlen = LL_RESERVED_SPACE(dev);
+ hlen = LL_RESERVED_SPACE_EX(dev, hard_header_len);
tlen = dev->needed_tailroom;
if (vnet_hdr_sz) {
data += vnet_hdr_sz;
@@ -2887,10 +2907,10 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg)
vnet_hdr.hdr_len);
has_vnet_hdr = true;
}
- copylen = max_t(int, copylen, dev->hard_header_len);
+ copylen = max_t(int, copylen, hard_header_len);
skb = sock_alloc_send_skb(&po->sk,
hlen + tlen + sizeof(struct sockaddr_ll) +
- (copylen - dev->hard_header_len),
+ (copylen - hard_header_len),
!need_wait, &err);
if (unlikely(skb == NULL)) {
@@ -2900,7 +2920,8 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg)
goto out_status;
}
tp_len = tpacket_fill_skb(po, skb, ph, dev, data, tp_len, proto,
- addr, hlen, copylen, &sockc);
+ addr, hlen, copylen, hard_header_len,
+ &sockc);
if (likely(tp_len >= 0) &&
tp_len > dev->mtu + reserve &&
!vnet_hdr_sz &&
@@ -3008,7 +3029,7 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len)
int offset = 0;
struct packet_sock *po = pkt_sk(sk);
int vnet_hdr_sz = READ_ONCE(po->vnet_hdr_sz);
- int hlen, tlen, linear;
+ int hard_header_len, hlen, tlen, linear;
int extra_len = 0;
/*
@@ -3049,8 +3070,9 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len)
goto out_unlock;
}
+ hard_header_len = READ_ONCE(dev->hard_header_len);
if (sock->type == SOCK_RAW)
- reserve = dev->hard_header_len;
+ reserve = hard_header_len;
if (vnet_hdr_sz) {
err = packet_snd_vnet_parse(msg, &len, &vnet_hdr, vnet_hdr_sz);
if (err)
@@ -3071,10 +3093,10 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len)
goto out_unlock;
err = -ENOBUFS;
- hlen = LL_RESERVED_SPACE(dev);
+ hlen = LL_RESERVED_SPACE_EX(dev, hard_header_len);
tlen = dev->needed_tailroom;
linear = __virtio16_to_cpu(vio_le(), vnet_hdr.hdr_len);
- linear = max(linear, min_t(int, len, dev->hard_header_len));
+ linear = max(linear, min_t(int, len, hard_header_len));
skb = packet_alloc_skb(sk, hlen + tlen, hlen, len, linear,
msg->msg_flags & MSG_DONTWAIT, &err);
if (skb == NULL)
@@ -3090,7 +3112,7 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len)
} else if (reserve) {
skb_reserve(skb, -reserve);
if (len < reserve + sizeof(struct ipv6hdr) &&
- dev->min_header_len != dev->hard_header_len)
+ dev->min_header_len != hard_header_len)
skb_reset_network_header(skb);
}
@@ -4347,7 +4369,7 @@ static __poll_t packet_poll(struct file *file, struct socket *sock,
TP_STATUS_KERNEL))
mask |= EPOLLIN | EPOLLRDNORM;
}
- packet_rcv_try_clear_pressure(po);
+ __packet_rcv_try_clear_pressure(po);
spin_unlock_bh(&sk->sk_receive_queue.lock);
spin_lock_bh(&sk->sk_write_queue.lock);
if (po->tx_ring.pg_vec) {
@@ -4587,14 +4609,14 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u,
rb->frame_max = (req->tp_frame_nr - 1);
rb->head = 0;
rb->frame_size = req->tp_frame_size;
+ po->prot_hook.func = (po->rx_ring.pg_vec) ?
+ tpacket_rcv : packet_rcv;
spin_unlock_bh(&rb_queue->lock);
swap(rb->pg_vec_order, order);
swap(rb->pg_vec_len, req->tp_block_nr);
rb->pg_vec_pages = req->tp_block_size/PAGE_SIZE;
- po->prot_hook.func = (po->rx_ring.pg_vec) ?
- tpacket_rcv : packet_rcv;
skb_queue_purge(rb_queue);
if (atomic_long_read(&po->mapped))
pr_err("packet_mmap: vma is busy: %ld\n",
diff --git a/net/sched/act_ct.c b/net/sched/act_ct.c
index a7bf52369cae..ba6d257abdc0 100644
--- a/net/sched/act_ct.c
+++ b/net/sched/act_ct.c
@@ -838,8 +838,15 @@ static int tcf_ct_ipv6_is_fragment(struct sk_buff *skb, bool *frag)
return 0;
}
+/* On error, tells the caller whether it still owns @skb and must free it
+ * itself. @skb is ours only when the header checks below reject the packet
+ * before it is handed to the defragmentation engine; once nf_ct_handle_
+ * fragments() has been called the skb is either queued (-EINPROGRESS) or has
+ * already been freed by it.
+ */
static int tcf_ct_handle_fragments(struct net *net, struct sk_buff *skb,
- u8 family, u16 zone, bool *defrag)
+ u8 family, u16 zone, bool *defrag,
+ bool *skb_is_ours)
{
enum ip_conntrack_info ctinfo;
struct tc_skb_cb cb;
@@ -857,8 +864,12 @@ static int tcf_ct_handle_fragments(struct net *net, struct sk_buff *skb,
err = tcf_ct_ipv4_is_fragment(skb, &frag);
else
err = tcf_ct_ipv6_is_fragment(skb, &frag);
- if (err || !frag)
+ if (err) {
+ *skb_is_ours = true;
return err;
+ }
+ if (!frag)
+ return 0;
cb = *tc_skb_cb(skb);
err = nf_ct_handle_fragments(net, skb, zone, family, &proto, &cb.mru);
@@ -975,6 +986,7 @@ TC_INDIRECT_SCOPE int tcf_ct_act(struct sk_buff *skb, const struct tc_action *a,
int nh_ofs, err, retval;
struct tcf_ct_params *p;
bool add_helper = false;
+ bool skb_is_ours = false;
bool skip_add = false;
bool defrag = false;
struct nf_conn *ct;
@@ -1010,9 +1022,18 @@ TC_INDIRECT_SCOPE int tcf_ct_act(struct sk_buff *skb, const struct tc_action *a,
*/
nh_ofs = skb_network_offset(skb);
skb_pull_rcsum(skb, nh_ofs);
- err = tcf_ct_handle_fragments(net, skb, family, p->zone, &defrag);
- if (err)
+ err = tcf_ct_handle_fragments(net, skb, family, p->zone, &defrag,
+ &skb_is_ours);
+ if (err) {
+ /* The skb is still ours only when the header checks rejected
+ * it; returning TC_ACT_CONSUMED for such a packet would leak
+ * it, since no caller frees an skb it was told it no longer
+ * owns.
+ */
+ if (skb_is_ours)
+ goto drop;
goto out_frag;
+ }
err = nf_ct_skb_network_trim(skb, family);
if (err)
diff --git a/net/sched/act_gact.c b/net/sched/act_gact.c
index e949280eb800..565860cccba6 100644
--- a/net/sched/act_gact.c
+++ b/net/sched/act_gact.c
@@ -89,6 +89,11 @@ static int tcf_gact_init(struct net *net, struct nlattr *nla,
p_parm = nla_data(tb[TCA_GACT_PROB]);
if (p_parm->ptype >= MAX_RAND)
return -EINVAL;
+ if (!tcf_action_valid(p_parm->paction)) {
+ NL_SET_ERR_MSG(extack,
+ "invalid fallback control action");
+ return -EINVAL;
+ }
if (TC_ACT_EXT_CMP(p_parm->paction, TC_ACT_GOTO_CHAIN)) {
NL_SET_ERR_MSG(extack,
"goto chain not allowed on fallback");
diff --git a/net/sched/act_police.c b/net/sched/act_police.c
index 8555125ed34d..81d5f61be17e 100644
--- a/net/sched/act_police.c
+++ b/net/sched/act_police.c
@@ -128,6 +128,12 @@ static int tcf_police_init(struct net *net, struct nlattr *nla,
if (tb[TCA_POLICE_RESULT]) {
tcfp_result = nla_get_u32(tb[TCA_POLICE_RESULT]);
+ if (!tcf_action_valid(tcfp_result)) {
+ NL_SET_ERR_MSG(extack,
+ "invalid fallback control action");
+ err = -EINVAL;
+ goto failure;
+ }
if (TC_ACT_EXT_CMP(tcfp_result, TC_ACT_GOTO_CHAIN)) {
NL_SET_ERR_MSG(extack,
"goto chain not allowed on fallback");
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index c5aeff709ca6..51a09d555310 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -443,7 +443,22 @@ static void tcf_chain_put(struct tcf_chain *chain);
static void tcf_proto_destroy(struct tcf_proto *tp, bool rtnl_held,
bool sig_destroy, struct netlink_ext_ack *extack)
{
- tp->ops->destroy(tp, rtnl_held, extack);
+ /* A locked classifier's destroy callback (e.g. u32_destroy) uses
+ * rtnl_dereference() and mutates shared structures (e.g. the
+ * tc_u_common hash list) that are only safe under rtnl_lock. When an
+ * unlocked classifier's request (e.g. flower on ingress) loses the
+ * tcf_chain_tp_insert_unique() race and ends up dropping the last
+ * reference on a locked classifier's proto, destroy() would run
+ * without rtnl held. Take it here in that case.
+ */
+ bool not_lockless = !rtnl_held &&
+ !(tp->ops->flags & TCF_PROTO_OPS_DOIT_UNLOCKED);
+
+ if (not_lockless)
+ rtnl_lock();
+ tp->ops->destroy(tp, rtnl_held || not_lockless, extack);
+ if (not_lockless)
+ rtnl_unlock();
tcf_proto_count_usesw(tp, false);
if (sig_destroy)
tcf_proto_signal_destroyed(tp->chain, tp);
diff --git a/net/sched/cls_route.c b/net/sched/cls_route.c
index b9c58c040c30..38469cdcb22d 100644
--- a/net/sched/cls_route.c
+++ b/net/sched/cls_route.c
@@ -52,6 +52,7 @@ struct route4_filter {
struct tcf_result res;
struct tcf_exts exts;
u32 handle;
+ bool dying;
struct route4_bucket *bkt;
struct tcf_proto *tp;
struct rcu_work rwork;
@@ -66,9 +67,11 @@ static inline int route4_fastmap_hash(u32 id, int iif)
static DEFINE_SPINLOCK(fastmap_lock);
static void
-route4_reset_fastmap(struct route4_head *head)
+route4_reset_fastmap(struct route4_head *head, struct route4_filter *f)
{
spin_lock_bh(&fastmap_lock);
+ if (f)
+ f->dying = true;
memset(head->fastmap, 0, sizeof(head->fastmap));
spin_unlock_bh(&fastmap_lock);
}
@@ -81,9 +84,11 @@ route4_set_fastmap(struct route4_head *head, u32 id, int iif,
/* fastmap updates must look atomic to aling id, iff, filter */
spin_lock_bh(&fastmap_lock);
- head->fastmap[h].id = id;
- head->fastmap[h].iif = iif;
- head->fastmap[h].filter = f;
+ if (f == ROUTE4_FAILURE || !f->dying) {
+ head->fastmap[h].id = id;
+ head->fastmap[h].iif = iif;
+ head->fastmap[h].filter = f;
+ }
spin_unlock_bh(&fastmap_lock);
}
@@ -297,6 +302,13 @@ static void route4_destroy(struct tcf_proto *tp, bool rtnl_held,
next = rtnl_dereference(f->next);
RCU_INIT_POINTER(b->ht[h2], next);
tcf_unbind_filter(tp, &f->res);
+ /* Mark the filter dying under fastmap_lock so
+ * any in-flight reader that still holds it
+ * will skip the republish in route4_set_fastmap().
+ */
+ spin_lock_bh(&fastmap_lock);
+ f->dying = true;
+ spin_unlock_bh(&fastmap_lock);
if (tcf_exts_get_net(&f->exts))
route4_queue_work(f);
else
@@ -307,6 +319,11 @@ static void route4_destroy(struct tcf_proto *tp, bool rtnl_held,
kfree_rcu(b, rcu);
}
}
+
+ /* All filters are unlinked and marked dying, so no in-flight
+ * reader can republish a stale entry after this reset.
+ */
+ route4_reset_fastmap(head, NULL);
kfree_rcu(head, rcu);
}
@@ -334,11 +351,11 @@ static int route4_delete(struct tcf_proto *tp, void *arg, bool *last,
/* unlink it */
RCU_INIT_POINTER(*fp, rtnl_dereference(f->next));
- /* Remove any fastmap lookups that might ref filter
- * notice we unlink'd the filter so we can't get it
- * back in the fastmap.
+ /* Clear any fastmap entries that may ref this filter and
+ * mark it dying so in-flight readers can't republish it
+ * after the reset.
*/
- route4_reset_fastmap(head);
+ route4_reset_fastmap(head, f);
/* Delete it */
tcf_unbind_filter(tp, &f->res);
@@ -558,7 +575,7 @@ static int route4_change(struct net *net, struct sk_buff *in_skb,
}
}
- route4_reset_fastmap(head);
+ route4_reset_fastmap(head, fold);
*arg = f;
if (fold) {
tcf_unbind_filter(tp, &fold->res);
diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c
index 709d851d0b1e..9a23fef527a2 100644
--- a/net/sched/sch_api.c
+++ b/net/sched/sch_api.c
@@ -1095,6 +1095,9 @@ static int qdisc_graft(struct net_device *dev, struct Qdisc *parent,
unsigned int i, num_q, ingress;
struct netdev_queue *dev_queue;
+ if (new)
+ new->depth = 0;
+
ingress = 0;
num_q = dev->num_tx_queues;
if ((q && q->flags & TCQ_F_INGRESS) ||
@@ -1192,9 +1195,15 @@ static int qdisc_graft(struct net_device *dev, struct Qdisc *parent,
NL_SET_ERR_MSG(extack, "STAB not supported on a non root");
return -EINVAL;
}
+ if (new && parent->depth >= 7) {
+ NL_SET_ERR_MSG(extack, "Qdisc hierarchy is too deep");
+ return -E2BIG;
+ }
err = cops->graft(parent, cl, new, &old, extack);
if (err)
return err;
+ if (new)
+ new->depth = parent->depth + 1;
notify_and_destroy(net, skb, n, classid, old, new, extack);
}
return 0;
diff --git a/net/sched/sch_cake.c b/net/sched/sch_cake.c
index 2f33739036bb..43908ec23169 100644
--- a/net/sched/sch_cake.c
+++ b/net/sched/sch_cake.c
@@ -1265,7 +1265,6 @@ static struct sk_buff *cake_ack_filter(struct cake_sched_data *q,
seglen = ntohs(ipv6h_check->payload_len);
} else {
- WARN_ON(1); /* shouldn't happen */
continue;
}
diff --git a/net/sctp/associola.c b/net/sctp/associola.c
index 44f06c5f1f25..f409b9f6b228 100644
--- a/net/sctp/associola.c
+++ b/net/sctp/associola.c
@@ -543,6 +543,9 @@ void sctp_assoc_rm_peer(struct sctp_association *asoc,
asoc->addip_last_asconf->transport == peer)
asoc->addip_last_asconf->transport = NULL;
+ if (asoc->new_transport == peer)
+ asoc->new_transport = NULL;
+
/* If we have something on the transmitted list, we have to
* save it off. The best place is the active path.
*/
@@ -573,6 +576,10 @@ void sctp_assoc_rm_peer(struct sctp_association *asoc,
if (ch->transport == peer)
ch->transport = NULL;
+ list_for_each_entry(ch, &asoc->outqueue.control_chunk_list, list)
+ if (ch->transport == peer)
+ ch->transport = NULL;
+
asoc->peer.transport_count--;
sctp_ulpevent_notify_peer_addr_change(peer, SCTP_ADDR_REMOVED, 0);
@@ -1727,6 +1734,8 @@ void sctp_asconf_queue_teardown(struct sctp_association *asoc)
sctp_assoc_free_asconf_queue(asoc);
/* Free any cached ASCONF chunk. */
- if (asoc->addip_last_asconf)
+ if (asoc->addip_last_asconf) {
sctp_chunk_free(asoc->addip_last_asconf);
+ asoc->addip_last_asconf = NULL;
+ }
}
diff --git a/net/sctp/outqueue.c b/net/sctp/outqueue.c
index 0dc6b8ab9963..242282a26425 100644
--- a/net/sctp/outqueue.c
+++ b/net/sctp/outqueue.c
@@ -650,6 +650,7 @@ static int __sctp_outq_flush_rtx(struct sctp_outq *q, struct sctp_packet *pkt,
if (chunk->tsn_gap_acked) {
list_move_tail(&chunk->transmitted_list,
&transport->transmitted);
+ chunk->transport = transport;
continue;
}
diff --git a/net/sctp/sm_make_chunk.c b/net/sctp/sm_make_chunk.c
index 27a7739a7d42..b6eb79ef6a55 100644
--- a/net/sctp/sm_make_chunk.c
+++ b/net/sctp/sm_make_chunk.c
@@ -3354,12 +3354,11 @@ struct sctp_chunk *sctp_process_asconf(struct sctp_association *asoc,
goto done;
}
done:
- asoc->peer.addip_serial++;
-
/* If we are sending a new ASCONF_ACK hold a reference to it in assoc
* after freeing the reference to old asconf ack if any.
*/
if (asconf_ack) {
+ asoc->peer.addip_serial++;
sctp_chunk_hold(asconf_ack);
list_add_tail(&asconf_ack->transmitted_list,
&asoc->asconf_ack_list);
diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c
index 818878f484a7..b9c7d06544c1 100644
--- a/net/sctp/sm_statefuns.c
+++ b/net/sctp/sm_statefuns.c
@@ -6110,8 +6110,12 @@ enum sctp_disposition sctp_sf_t4_timer_expire(
struct sctp_cmd_seq *commands)
{
struct sctp_chunk *chunk = asoc->addip_last_asconf;
- struct sctp_transport *transport = chunk->transport;
+ struct sctp_transport *transport;
+
+ if (!chunk)
+ return SCTP_DISPOSITION_CONSUME;
+ transport = chunk->transport;
SCTP_INC_STATS(net, SCTP_MIB_T4_RTO_EXPIREDS);
/* ADDIP 4.1 B1) Increment the error counters and perform path failure
diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c
index 8d740f588a77..8e95839161aa 100644
--- a/net/smc/af_smc.c
+++ b/net/smc/af_smc.c
@@ -1933,11 +1933,12 @@ static void smc_listen_out(struct smc_sock *new_smc)
atomic_dec(&lsmc->queued_smc_hs);
release_sock(newsmcsk); /* lock in smc_listen_work() */
+ lock_sock_nested(&lsmc->sk, SINGLE_DEPTH_NESTING);
if (lsmc->sk.sk_state == SMC_LISTEN) {
- lock_sock_nested(&lsmc->sk, SINGLE_DEPTH_NESTING);
smc_accept_enqueue(&lsmc->sk, newsmcsk);
release_sock(&lsmc->sk);
} else { /* no longer listening */
+ release_sock(&lsmc->sk);
smc_close_non_accepted(newsmcsk);
}
diff --git a/net/smc/smc_llc.c b/net/smc/smc_llc.c
index 018ce8133b02..149d63cff667 100644
--- a/net/smc/smc_llc.c
+++ b/net/smc/smc_llc.c
@@ -1918,7 +1918,8 @@ static void smc_llc_event_handler(struct smc_llc_qentry *qentry)
return;
case SMC_LLC_CONFIRM_LINK:
case SMC_LLC_ADD_LINK_CONT:
- if (lgr->llc_flow_lcl.type != SMC_LLC_FLOW_NONE) {
+ if (lgr->llc_flow_lcl.type != SMC_LLC_FLOW_NONE &&
+ !lgr->llc_flow_lcl.qentry) {
/* a flow is waiting for this message */
smc_llc_flow_qentry_set(&lgr->llc_flow_lcl, qentry);
wake_up(&lgr->llc_msg_waiter);
diff --git a/net/smc/smc_rx.c b/net/smc/smc_rx.c
index e7a6c2602e78..c5d96b116b55 100644
--- a/net/smc/smc_rx.c
+++ b/net/smc/smc_rx.c
@@ -150,7 +150,12 @@ static const struct pipe_buf_operations smc_pipe_ops = {
static void smc_rx_spd_release(struct splice_pipe_desc *spd,
unsigned int i)
{
+ struct smc_spd_priv *priv = (struct smc_spd_priv *)spd->partial[i].private;
+ struct sock *sk = &priv->smc->sk;
+
+ kfree(priv);
put_page(spd->pages[i]);
+ sock_put(sk);
}
static int smc_rx_splice(struct pipe_inode_info *pipe, char *src, size_t len,
@@ -209,6 +214,10 @@ static int smc_rx_splice(struct pipe_inode_info *pipe, char *src, size_t len,
offset = 0;
}
}
+ for (i = 0; i < nr_pages; i++) {
+ get_page(pages[i]);
+ sock_hold(&smc->sk);
+ }
spd.nr_pages_max = nr_pages;
spd.nr_pages = nr_pages;
spd.pages = pages;
@@ -217,16 +226,8 @@ static int smc_rx_splice(struct pipe_inode_info *pipe, char *src, size_t len,
spd.spd_release = smc_rx_spd_release;
bytes = splice_to_pipe(pipe, &spd);
- if (bytes > 0) {
- sock_hold(&smc->sk);
- if (!lgr->is_smcd && smc->conn.rmb_desc->is_vm) {
- for (i = 0; i < PAGE_ALIGN(bytes + offset) / PAGE_SIZE; i++)
- get_page(pages[i]);
- } else {
- get_page(smc->conn.rmb_desc->pages);
- }
+ if (bytes > 0)
atomic_add(bytes, &smc->conn.splice_pending);
- }
kfree(priv);
kfree(partial);
kfree(pages);
diff --git a/net/tipc/node.c b/net/tipc/node.c
index f3332d564c63..34c2c4e82517 100644
--- a/net/tipc/node.c
+++ b/net/tipc/node.c
@@ -1061,18 +1061,23 @@ static void __tipc_node_link_down(struct tipc_node *n, int *bearer_id,
static void tipc_node_link_down(struct tipc_node *n, int bearer_id, bool delete)
{
- struct tipc_link_entry *le = &n->links[bearer_id];
struct tipc_media_addr *maddr = NULL;
- struct tipc_link *l = le->link;
int old_bearer_id = bearer_id;
+ struct tipc_link_entry *le;
struct sk_buff_head xmitq;
-
- if (!l)
- return;
+ struct tipc_link *l;
__skb_queue_head_init(&xmitq);
+ /* Synchronize the link lookup with bearer teardown. */
tipc_node_write_lock(n);
+ le = &n->links[bearer_id];
+ l = le->link;
+ if (!l) {
+ tipc_node_write_unlock_fast(n);
+ return;
+ }
+
if (!tipc_link_is_establishing(l)) {
__tipc_node_link_down(n, &bearer_id, &xmitq, &maddr);
} else {
diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c
index 2b875369d523..ceca15b43f35 100644
--- a/net/tls/tls_sw.c
+++ b/net/tls/tls_sw.c
@@ -458,7 +458,7 @@ int tls_tx_records(struct sock *sk, int flags)
}
tx_err:
- if (rc < 0 && rc != -EAGAIN)
+ if (rc < 0 && rc != -EAGAIN && rc != -EINTR && rc != -ERESTARTSYS)
tls_err_abort(sk, rc);
return rc;
@@ -1116,6 +1116,14 @@ static int tls_sw_sendmsg_locked(struct sock *sk, struct msghdr *msg,
if (!sk_stream_memory_free(sk))
goto wait_for_sndbuf;
+ /* open record may be full if we couldn't push it in the last sendmsg call */
+ if (sk_msg_full(msg_pl)) {
+ full_record = true;
+ sk_msg_trim(sk, msg_en,
+ msg_pl->sg.size + prot->overhead_size);
+ goto copied;
+ }
+
alloc_encrypted:
ret = tls_alloc_encrypted_msg(sk, required_size);
if (ret) {
@@ -1216,6 +1224,12 @@ static int tls_sw_sendmsg_locked(struct sock *sk, struct msghdr *msg,
msg_pl, try_to_copy);
if (ret < 0)
goto trim_sgl;
+
+ if (sk_msg_full(msg_pl)) {
+ full_record = true;
+ sk_msg_trim(sk, msg_en,
+ msg_pl->sg.size + prot->overhead_size);
+ }
}
/* Open records defined only if successfully copied, otherwise
diff --git a/net/vmw_vsock/virtio_transport.c b/net/vmw_vsock/virtio_transport.c
index b6569b0ca2bb..e7dff5c3d4ac 100644
--- a/net/vmw_vsock/virtio_transport.c
+++ b/net/vmw_vsock/virtio_transport.c
@@ -343,12 +343,13 @@ static void virtio_transport_tx_work(struct work_struct *work)
struct virtqueue *vq;
bool added = false;
- vq = vsock->vqs[VSOCK_VQ_TX];
mutex_lock(&vsock->tx_lock);
if (!vsock->tx_run)
goto out;
+ vq = vsock->vqs[VSOCK_VQ_TX];
+
do {
struct sk_buff *skb;
unsigned int len;
@@ -448,13 +449,13 @@ static void virtio_transport_event_work(struct work_struct *work)
container_of(work, struct virtio_vsock, event_work);
struct virtqueue *vq;
- vq = vsock->vqs[VSOCK_VQ_EVENT];
-
mutex_lock(&vsock->event_lock);
if (!vsock->event_run)
goto out;
+ vq = vsock->vqs[VSOCK_VQ_EVENT];
+
do {
struct virtio_vsock_event *event;
unsigned int len;
@@ -614,12 +615,12 @@ static void virtio_transport_rx_work(struct work_struct *work)
container_of(work, struct virtio_vsock, rx_work);
struct virtqueue *vq;
- vq = vsock->vqs[VSOCK_VQ_RX];
-
mutex_lock(&vsock->rx_lock);
if (!vsock->rx_run)
- goto out;
+ goto out_nofill;
+
+ vq = vsock->vqs[VSOCK_VQ_RX];
do {
virtqueue_disable_cb(vq);
@@ -667,6 +668,7 @@ static void virtio_transport_rx_work(struct work_struct *work)
out:
if (vsock->rx_buf_nr < vsock->rx_buf_max_nr / 2)
virtio_vsock_rx_fill(vsock);
+out_nofill:
mutex_unlock(&vsock->rx_lock);
}
diff --git a/net/xdp/xdp_umem.c b/net/xdp/xdp_umem.c
index 9ec7bd948acc..81ffda550107 100644
--- a/net/xdp/xdp_umem.c
+++ b/net/xdp/xdp_umem.c
@@ -209,6 +209,8 @@ static int xdp_umem_reg(struct xdp_umem *umem, struct xdp_umem_reg *mr)
if (mr->flags & XDP_UMEM_TX_METADATA_LEN) {
if (mr->tx_metadata_len >= 256 || mr->tx_metadata_len % 8)
return -EINVAL;
+ if (mr->tx_metadata_len < 16)
+ return -EINVAL;
umem->tx_metadata_len = mr->tx_metadata_len;
}
diff --git a/security/integrity/ima/ima_appraise.c b/security/integrity/ima/ima_appraise.c
index f7770c24995b..b5c573332fa8 100644
--- a/security/integrity/ima/ima_appraise.c
+++ b/security/integrity/ima/ima_appraise.c
@@ -302,8 +302,13 @@ static int xattr_verify(enum ima_hooks func, struct ima_iint_cache *iint,
} else {
set_bit(IMA_DIGSIG, &iint->atomic_flags);
}
- if (xattr_len - sizeof(xattr_value->type) - hash_start >=
- iint->ima_hash->length)
+ /*
+ * Use addition, not subtraction: sizeof() forces unsigned
+ * math and a short xattr_len would wrap around, bypassing
+ * this bounds check.
+ */
+ if (xattr_len >= (int)sizeof(xattr_value->type) + hash_start +
+ (int)iint->ima_hash->length)
/*
* xattr length may be longer. md5 hash in previous
* version occupied 20 bytes in xattr, instead of 16
diff --git a/security/integrity/ima/ima_main.c b/security/integrity/ima/ima_main.c
index 2f3f267e7216..a0948057209e 100644
--- a/security/integrity/ima/ima_main.c
+++ b/security/integrity/ima/ima_main.c
@@ -587,6 +587,43 @@ static int ima_file_check(struct file *file, int mask)
MAY_APPEND), FILE_CHECK);
}
+/*
+ * ima_reset_action_flags - invalidate action flags after a content change
+ * @inode: inode of the file whose content is about to be truncated
+ *
+ * Clear IMA_DONE_MASK so the file is re-collected, re-measured,
+ * re-audited, and re-appraised on next access.
+ */
+static void ima_reset_action_flags(struct inode *inode)
+{
+ struct ima_iint_cache *iint;
+
+ if (!ima_policy_flag || !S_ISREG(inode->i_mode))
+ return;
+
+ iint = ima_iint_find(inode);
+ if (!iint)
+ return;
+
+ mutex_lock(&iint->mutex);
+ iint->flags &= ~IMA_DONE_MASK;
+ iint->measured_pcrs = 0;
+ mutex_unlock(&iint->mutex);
+ return;
+}
+
+static int ima_path_truncate(const struct path *path)
+{
+ ima_reset_action_flags(path->dentry->d_inode);
+ return 0;
+}
+
+static int ima_file_truncate(struct file *file)
+{
+ ima_reset_action_flags(file_inode(file));
+ return 0;
+}
+
static int __ima_inode_hash(struct inode *inode, struct file *file, char *buf,
size_t buf_size)
{
@@ -1195,11 +1232,13 @@ static struct security_hook_list ima_hooks[] __ro_after_init = {
LSM_HOOK_INIT(file_release, ima_file_free),
LSM_HOOK_INIT(mmap_file, ima_file_mmap),
LSM_HOOK_INIT(file_mprotect, ima_file_mprotect),
+ LSM_HOOK_INIT(file_truncate, ima_file_truncate),
LSM_HOOK_INIT(kernel_load_data, ima_load_data),
LSM_HOOK_INIT(kernel_post_load_data, ima_post_load_data),
LSM_HOOK_INIT(kernel_read_file, ima_read_file),
LSM_HOOK_INIT(kernel_post_read_file, ima_post_read_file),
LSM_HOOK_INIT(path_post_mknod, ima_post_path_mknod),
+ LSM_HOOK_INIT(path_truncate, ima_path_truncate),
#ifdef CONFIG_IMA_MEASURE_ASYMMETRIC_KEYS
LSM_HOOK_INIT(key_post_create_or_update, ima_post_key_create_or_update),
#endif
diff --git a/sound/usb/endpoint.c b/sound/usb/endpoint.c
index eeee2886dc21..c573d74641d4 100644
--- a/sound/usb/endpoint.c
+++ b/sound/usb/endpoint.c
@@ -388,13 +388,15 @@ static int prepare_inbound_urb(struct snd_usb_endpoint *ep,
case SND_USB_ENDPOINT_TYPE_DATA:
offs = 0;
for (i = 0; i < urb_ctx->packets; i++) {
+ if (offs + ep->curpacksize > urb_ctx->buffer_size)
+ break;
urb->iso_frame_desc[i].offset = offs;
urb->iso_frame_desc[i].length = ep->curpacksize;
offs += ep->curpacksize;
}
urb->transfer_buffer_length = offs;
- urb->number_of_packets = urb_ctx->packets;
+ urb->number_of_packets = i;
break;
case SND_USB_ENDPOINT_TYPE_SYNC:
@@ -1263,10 +1265,10 @@ static int data_ep_set_params(struct snd_usb_endpoint *ep)
u->index = i;
u->ep = ep;
u->packets = urb_packs;
- u->buffer_size = maxsize * u->packets;
if (fmt->fmt_type == UAC_FORMAT_TYPE_II)
u->packets++; /* for transfer delimiter */
+ u->buffer_size = maxsize * u->packets;
u->urb = usb_alloc_urb(u->packets, GFP_KERNEL);
if (!u->urb)
goto out_of_memory;
diff --git a/sound/usb/midi2.c b/sound/usb/midi2.c
index 19c979df36bb..e66b595ebde8 100644
--- a/sound/usb/midi2.c
+++ b/sound/usb/midi2.c
@@ -685,6 +685,14 @@ static int parse_midi_2_0_endpoints(struct snd_usb_midi2_interface *umidi)
return 0;
}
+static void free_ump_private_data(struct snd_ump_endpoint *ump)
+{
+ struct snd_usb_midi2_ump *rmidi = ump->private_data;
+
+ if (rmidi)
+ rmidi->ump = NULL;
+}
+
static void free_all_midi2_umps(struct snd_usb_midi2_interface *umidi)
{
struct snd_usb_midi2_ump *rmidi;
@@ -735,6 +743,7 @@ static int create_midi2_ump(struct snd_usb_midi2_interface *umidi,
ump->private_data = rmidi;
ump->ops = &snd_usb_midi_v2_ump_ops;
+ ump->private_free = free_ump_private_data;
rmidi->eps[STR_IN] = ep_in;
rmidi->eps[STR_OUT] = ep_out;
diff --git a/sound/usb/usx2y/usX2Yhwdep.c b/sound/usb/usx2y/usX2Yhwdep.c
index 9fd6a86cc08e..2cc0f90a23be 100644
--- a/sound/usb/usx2y/usX2Yhwdep.c
+++ b/sound/usb/usx2y/usX2Yhwdep.c
@@ -25,6 +25,8 @@ static vm_fault_t snd_us428ctls_vm_fault(struct vm_fault *vmf)
void *vaddr;
offset = vmf->pgoff << PAGE_SHIFT;
+ if (offset >= US428_SHAREDMEM_PAGES)
+ return VM_FAULT_SIGBUS;
vaddr = (char *)((struct usx2ydev *)vmf->vma->vm_private_data)->us428ctls_sharedmem + offset;
page = virt_to_page(vaddr);
get_page(page);
diff --git a/sound/usb/usx2y/usx2yhwdeppcm.c b/sound/usb/usx2y/usx2yhwdeppcm.c
index 1b1496adb47e..0b8dd9e3f984 100644
--- a/sound/usb/usx2y/usx2yhwdeppcm.c
+++ b/sound/usb/usx2y/usx2yhwdeppcm.c
@@ -681,6 +681,8 @@ static vm_fault_t snd_usx2y_hwdep_pcm_vm_fault(struct vm_fault *vmf)
void *vaddr;
offset = vmf->pgoff << PAGE_SHIFT;
+ if (offset >= USX2Y_HWDEP_PCM_PAGES)
+ return VM_FAULT_SIGBUS;
vaddr = (char *)((struct usx2ydev *)vmf->vma->vm_private_data)->hwdep_pcm_shm + offset;
vmf->page = virt_to_page(vaddr);
get_page(vmf->page);
diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c b/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c
index fb08c565d6aa..99522cf68dc8 100644
--- a/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c
+++ b/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c
@@ -703,7 +703,7 @@ static void test_sockmap_many_socket(void)
return;
}
- udp = xsocket(AF_INET, SOCK_DGRAM | SOCK_NONBLOCK, 0);
+ udp = socket_loopback(AF_INET, SOCK_DGRAM | SOCK_NONBLOCK);
if (udp < 0) {
close(dgram);
close(tcp);
@@ -772,7 +772,7 @@ static void test_sockmap_many_maps(void)
return;
}
- udp = xsocket(AF_INET, SOCK_DGRAM | SOCK_NONBLOCK, 0);
+ udp = socket_loopback(AF_INET, SOCK_DGRAM | SOCK_NONBLOCK);
if (udp < 0) {
close(dgram);
close(tcp);
@@ -843,7 +843,7 @@ static void test_sockmap_same_sock(void)
return;
}
- udp = xsocket(AF_INET, SOCK_DGRAM | SOCK_NONBLOCK, 0);
+ udp = socket_loopback(AF_INET, SOCK_DGRAM | SOCK_NONBLOCK);
if (udp < 0) {
close(dgram);
close(tcp);
diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c b/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c
index 1cfed83156b0..b04b8188b151 100644
--- a/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c
+++ b/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c
@@ -53,8 +53,8 @@ static void test_insert_opened(struct test_sockmap_listen *skel __always_unused,
int family, int sotype, int mapfd)
{
u32 key = 0;
- u64 value;
int err, s;
+ u64 value;
s = xsocket(family, sotype, 0);
if (s == -1)
@@ -63,11 +63,8 @@ static void test_insert_opened(struct test_sockmap_listen *skel __always_unused,
errno = 0;
value = s;
err = bpf_map_update_elem(mapfd, &key, &value, BPF_NOEXIST);
- if (sotype == SOCK_STREAM) {
- if (!err || errno != EOPNOTSUPP)
- FAIL_ERRNO("map_update: expected EOPNOTSUPP");
- } else if (err)
- FAIL_ERRNO("map_update: expected success");
+ ASSERT_ERR(err, "map_update");
+ ASSERT_EQ(errno, EOPNOTSUPP, "errno");
xclose(s);
}
@@ -77,8 +74,8 @@ static void test_insert_bound(struct test_sockmap_listen *skel __always_unused,
struct sockaddr_storage addr;
socklen_t len = 0;
u32 key = 0;
- u64 value;
int err, s;
+ u64 value;
init_addr_loopback(family, &addr, &len);
@@ -93,8 +90,12 @@ static void test_insert_bound(struct test_sockmap_listen *skel __always_unused,
errno = 0;
value = s;
err = bpf_map_update_elem(mapfd, &key, &value, BPF_NOEXIST);
- if (!err || errno != EOPNOTSUPP)
- FAIL_ERRNO("map_update: expected EOPNOTSUPP");
+ if (sotype == SOCK_STREAM) {
+ ASSERT_ERR(err, "map_update");
+ ASSERT_EQ(errno, EOPNOTSUPP, "errno");
+ } else {
+ ASSERT_OK(err, "map_update");
+ }
close:
xclose(s);
}
@@ -1289,7 +1290,7 @@ static void test_ops(struct test_sockmap_listen *skel, struct bpf_map *map,
/* insert */
TEST(test_insert_invalid),
TEST(test_insert_opened),
- TEST(test_insert_bound, SOCK_STREAM),
+ TEST(test_insert_bound),
TEST(test_insert),
/* delete */
TEST(test_delete_after_insert),
diff --git a/tools/testing/selftests/bpf/test_maps.c b/tools/testing/selftests/bpf/test_maps.c
index 905d5981ace1..6f080cc7eb96 100644
--- a/tools/testing/selftests/bpf/test_maps.c
+++ b/tools/testing/selftests/bpf/test_maps.c
@@ -752,16 +752,15 @@ static void test_sockmap(unsigned int tasks, void *data)
goto out_sockmap;
}
- /* Test update with unsupported UDP socket */
+ /* Test update with unsupported unbound UDP socket */
udp = socket(AF_INET, SOCK_DGRAM, 0);
- i = 0;
- err = bpf_map_update_elem(fd, &i, &udp, BPF_ANY);
- if (err) {
- printf("Failed socket update SOCK_DGRAM '%i:%i'\n",
- i, udp);
+ CHECK(udp < 0, "socket(AF_INET, SOCK_DGRAM)", "errno:%d\n", errno);
+ err = bpf_map_update_elem(fd, &(int){0}, &udp, BPF_ANY);
+ close(udp);
+ if (!err) {
+ printf("Unexpectedly succeeded unbound UDP update '0:%i'\n", udp);
goto out_sockmap;
}
- close(udp);
/* Test update without programs */
for (i = 0; i < 6; i++) {
diff --git a/tools/testing/selftests/ftrace/test.d/dynevent/add_remove_eprobe.tc b/tools/testing/selftests/ftrace/test.d/dynevent/add_remove_eprobe.tc
index c300eb020262..e2322693d0c3 100644
--- a/tools/testing/selftests/ftrace/test.d/dynevent/add_remove_eprobe.tc
+++ b/tools/testing/selftests/ftrace/test.d/dynevent/add_remove_eprobe.tc
@@ -1,16 +1,16 @@
#!/bin/sh
# SPDX-License-Identifier: GPL-2.0
# description: Generic dynamic event - add/remove eprobe events
-# requires: dynamic_events events/syscalls/sys_enter_openat "<attached-group>.<attached-event> [<args>]":README
+# requires: dynamic_events events/syscalls/sys_enter_chdir "<attached-group>.<attached-event> [<args>]":README
echo 0 > events/enable
clear_dynamic_events
SYSTEM="syscalls"
-EVENT="sys_enter_openat"
+EVENT="sys_enter_chdir"
FIELD="filename"
-EPROBE="eprobe_open"
+EPROBE="eprobe_chdir"
OPTIONS="file=+0(\$filename):ustring"
echo "e:$EPROBE $SYSTEM/$EVENT $OPTIONS" >> dynamic_events
@@ -18,20 +18,14 @@ grep -q "$EPROBE" dynamic_events
test -d events/eprobes/$EPROBE
echo 1 > events/eprobes/$EPROBE/enable
-ls
+cd /sys/kernel/tracing
echo 0 > events/eprobes/$EPROBE/enable
-content=`grep '^ *ls-' trace | grep 'file='`
-nocontent=`grep '^ *ls-' trace | grep 'file=' | grep -v -e '"/' -e '"."' -e '(fault)' ` || true
-
+content=`grep -e 'file="/sys/kernel/tracing"\|(fault)' trace`
if [ -z "$content" ]; then
exit_fail
fi
-if [ ! -z "$nocontent" ]; then
- exit_fail
-fi
-
echo "-:$EPROBE" >> dynamic_events
! grep -q "$EPROBE" dynamic_events
prev parent reply other threads:[~2026-08-19 16:52 UTC|newest]
Thread overview: 2+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-08-19 16:52 Linux 6.12.104 Greg Kroah-Hartman
2026-08-19 16:52 ` Greg Kroah-Hartman [this message]
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=2026081916-platform-come-496e@gregkh \
--to=gregkh@linuxfoundation.org \
--cc=akpm@linux-foundation.org \
--cc=jslaby@suse.cz \
--cc=linux-kernel@vger.kernel.org \
--cc=lwn@lwn.net \
--cc=stable@vger.kernel.org \
--cc=torvalds@linux-foundation.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.