May 2025 - Linux-stable-mirror

FAILED: patch "[PATCH] uio_hv_generic: Fix sysfs creation path for ring buffer" failed to apply to 6.6-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 6.6-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-6.6.y git checkout FETCH_HEAD git cherry-pick -x f31fe8165d365379d858c53bef43254c7d6d1cfd # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2025051209-overturn-supreme-26f1@gregkh' --subject-prefix 'PATCH 6.6.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From f31fe8165d365379d858c53bef43254c7d6d1cfd Mon Sep 17 00:00:00 2001 From: Naman Jain <namjain(a)linux.microsoft.com> Date: Fri, 2 May 2025 13:18:10 +0530 Subject: [PATCH] uio_hv_generic: Fix sysfs creation path for ring buffer On regular bootup, devices get registered to VMBus first, so when uio_hv_generic driver for a particular device type is probed, the device is already initialized and added, so sysfs creation in hv_uio_probe() works fine. However, when the device is removed and brought back, the channel gets rescinded and the device again gets registered to VMBus. However this time, the uio_hv_generic driver is already registered to probe for that device and in this case sysfs creation is tried before the device's kobject gets initialized completely. Fix this by moving the core logic of sysfs creation of ring buffer, from uio_hv_generic to HyperV's VMBus driver, where the rest of the sysfs attributes for the channels are defined. While doing that, make use of attribute groups and macros, instead of creating sysfs directly, to ensure better error handling and code flow. Problematic path: vmbus_process_offer (A new offer comes for the VMBus device) vmbus_add_channel_work vmbus_device_register |-> device_register | |... | |-> hv_uio_probe | |... | |-> sysfs_create_bin_file (leads to a warning as | the primary channel's kobject, which is used to | create the sysfs file, is not yet initialized) |-> kset_create_and_add |-> vmbus_add_channel_kobj (initialization of the primary channel's kobject happens later) Above code flow is sequential and the warning is always reproducible in this path. Fixes: 9ab877a6ccf8 ("uio_hv_generic: make ring buffer attribute for primary channel") Cc: stable(a)kernel.org Suggested-by: Saurabh Sengar <ssengar(a)linux.microsoft.com> Suggested-by: Michael Kelley <mhklinux(a)outlook.com> Reviewed-by: Michael Kelley <mhklinux(a)outlook.com> Tested-by: Michael Kelley <mhklinux(a)outlook.com> Reviewed-by: Dexuan Cui <decui(a)microsoft.com> Signed-off-by: Naman Jain <namjain(a)linux.microsoft.com> Link: https://lore.kernel.org/r/20250502074811.2022-2-namjain@linux.microsoft.com Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> diff --git a/drivers/hv/hyperv_vmbus.h b/drivers/hv/hyperv_vmbus.h index 29780f3a7478..0b450e53161e 100644 --- a/drivers/hv/hyperv_vmbus.h +++ b/drivers/hv/hyperv_vmbus.h @@ -477,4 +477,10 @@ static inline int hv_debug_add_dev_dir(struct hv_device *dev) #endif /* CONFIG_HYPERV_TESTING */ +/* Create and remove sysfs entry for memory mapped ring buffers for a channel */ +int hv_create_ring_sysfs(struct vmbus_channel *channel, + int (*hv_mmap_ring_buffer)(struct vmbus_channel *channel, + struct vm_area_struct *vma)); +int hv_remove_ring_sysfs(struct vmbus_channel *channel); + #endif /* _HYPERV_VMBUS_H */ diff --git a/drivers/hv/vmbus_drv.c b/drivers/hv/vmbus_drv.c index 8d3cff42bdbb..0f16a83cc2d6 100644 --- a/drivers/hv/vmbus_drv.c +++ b/drivers/hv/vmbus_drv.c @@ -1802,6 +1802,27 @@ static ssize_t subchannel_id_show(struct vmbus_channel *channel, } static VMBUS_CHAN_ATTR_RO(subchannel_id); +static int hv_mmap_ring_buffer_wrapper(struct file *filp, struct kobject *kobj, + const struct bin_attribute *attr, + struct vm_area_struct *vma) +{ + struct vmbus_channel *channel = container_of(kobj, struct vmbus_channel, kobj); + + /* + * hv_(create|remove)_ring_sysfs implementation ensures that mmap_ring_buffer + * is not NULL. + */ + return channel->mmap_ring_buffer(channel, vma); +} + +static struct bin_attribute chan_attr_ring_buffer = { + .attr = { + .name = "ring", + .mode = 0600, + }, + .size = 2 * SZ_2M, + .mmap = hv_mmap_ring_buffer_wrapper, +}; static struct attribute *vmbus_chan_attrs[] = { &chan_attr_out_mask.attr, &chan_attr_in_mask.attr, @@ -1821,6 +1842,11 @@ static struct attribute *vmbus_chan_attrs[] = { NULL }; +static struct bin_attribute *vmbus_chan_bin_attrs[] = { + &chan_attr_ring_buffer, + NULL +}; + /* * Channel-level attribute_group callback function. Returns the permission for * each attribute, and returns 0 if an attribute is not visible. @@ -1841,9 +1867,24 @@ static umode_t vmbus_chan_attr_is_visible(struct kobject *kobj, return attr->mode; } +static umode_t vmbus_chan_bin_attr_is_visible(struct kobject *kobj, + const struct bin_attribute *attr, int idx) +{ + const struct vmbus_channel *channel = + container_of(kobj, struct vmbus_channel, kobj); + + /* Hide ring attribute if channel's ring_sysfs_visible is set to false */ + if (attr == &chan_attr_ring_buffer && !channel->ring_sysfs_visible) + return 0; + + return attr->attr.mode; +} + static const struct attribute_group vmbus_chan_group = { .attrs = vmbus_chan_attrs, - .is_visible = vmbus_chan_attr_is_visible + .bin_attrs = vmbus_chan_bin_attrs, + .is_visible = vmbus_chan_attr_is_visible, + .is_bin_visible = vmbus_chan_bin_attr_is_visible, }; static const struct kobj_type vmbus_chan_ktype = { @@ -1851,6 +1892,63 @@ static const struct kobj_type vmbus_chan_ktype = { .release = vmbus_chan_release, }; +/** + * hv_create_ring_sysfs() - create "ring" sysfs entry corresponding to ring buffers for a channel. + * @channel: Pointer to vmbus_channel structure + * @hv_mmap_ring_buffer: function pointer for initializing the function to be called on mmap of + * channel's "ring" sysfs node, which is for the ring buffer of that channel. + * Function pointer is of below type: + * int (*hv_mmap_ring_buffer)(struct vmbus_channel *channel, + * struct vm_area_struct *vma)) + * This has a pointer to the channel and a pointer to vm_area_struct, + * used for mmap, as arguments. + * + * Sysfs node for ring buffer of a channel is created along with other fields, however its + * visibility is disabled by default. Sysfs creation needs to be controlled when the use-case + * is running. + * For example, HV_NIC device is used either by uio_hv_generic or hv_netvsc at any given point of + * time, and "ring" sysfs is needed only when uio_hv_generic is bound to that device. To avoid + * exposing the ring buffer by default, this function is reponsible to enable visibility of + * ring for userspace to use. + * Note: Race conditions can happen with userspace and it is not encouraged to create new + * use-cases for this. This was added to maintain backward compatibility, while solving + * one of the race conditions in uio_hv_generic while creating sysfs. + * + * Returns 0 on success or error code on failure. + */ +int hv_create_ring_sysfs(struct vmbus_channel *channel, + int (*hv_mmap_ring_buffer)(struct vmbus_channel *channel, + struct vm_area_struct *vma)) +{ + struct kobject *kobj = &channel->kobj; + + channel->mmap_ring_buffer = hv_mmap_ring_buffer; + channel->ring_sysfs_visible = true; + + return sysfs_update_group(kobj, &vmbus_chan_group); +} +EXPORT_SYMBOL_GPL(hv_create_ring_sysfs); + +/** + * hv_remove_ring_sysfs() - remove ring sysfs entry corresponding to ring buffers for a channel. + * @channel: Pointer to vmbus_channel structure + * + * Hide "ring" sysfs for a channel by changing its is_visible attribute and updating sysfs group. + * + * Returns 0 on success or error code on failure. + */ +int hv_remove_ring_sysfs(struct vmbus_channel *channel) +{ + struct kobject *kobj = &channel->kobj; + int ret; + + channel->ring_sysfs_visible = false; + ret = sysfs_update_group(kobj, &vmbus_chan_group); + channel->mmap_ring_buffer = NULL; + return ret; +} +EXPORT_SYMBOL_GPL(hv_remove_ring_sysfs); + /* * vmbus_add_channel_kobj - setup a sub-directory under device/channels */ diff --git a/drivers/uio/uio_hv_generic.c b/drivers/uio/uio_hv_generic.c index 1b19b5647495..69c1df0f4ca5 100644 --- a/drivers/uio/uio_hv_generic.c +++ b/drivers/uio/uio_hv_generic.c @@ -131,15 +131,12 @@ static void hv_uio_rescind(struct vmbus_channel *channel) vmbus_device_unregister(channel->device_obj); } -/* Sysfs API to allow mmap of the ring buffers +/* Function used for mmap of ring buffer sysfs interface. * The ring buffer is allocated as contiguous memory by vmbus_open */ -static int hv_uio_ring_mmap(struct file *filp, struct kobject *kobj, - const struct bin_attribute *attr, - struct vm_area_struct *vma) +static int +hv_uio_ring_mmap(struct vmbus_channel *channel, struct vm_area_struct *vma) { - struct vmbus_channel *channel - = container_of(kobj, struct vmbus_channel, kobj); void *ring_buffer = page_address(channel->ringbuffer_page); if (channel->state != CHANNEL_OPENED_STATE) @@ -149,15 +146,6 @@ static int hv_uio_ring_mmap(struct file *filp, struct kobject *kobj, channel->ringbuffer_pagecount << PAGE_SHIFT); } -static const struct bin_attribute ring_buffer_bin_attr = { - .attr = { - .name = "ring", - .mode = 0600, - }, - .size = 2 * SZ_2M, - .mmap = hv_uio_ring_mmap, -}; - /* Callback from VMBUS subsystem when new channel created. */ static void hv_uio_new_channel(struct vmbus_channel *new_sc) @@ -178,8 +166,7 @@ hv_uio_new_channel(struct vmbus_channel *new_sc) /* Disable interrupts on sub channel */ new_sc->inbound.ring_buffer->interrupt_mask = 1; set_channel_read_mode(new_sc, HV_CALL_ISR); - - ret = sysfs_create_bin_file(&new_sc->kobj, &ring_buffer_bin_attr); + ret = hv_create_ring_sysfs(new_sc, hv_uio_ring_mmap); if (ret) { dev_err(device, "sysfs create ring bin file failed; %d\n", ret); vmbus_close(new_sc); @@ -350,10 +337,18 @@ hv_uio_probe(struct hv_device *dev, goto fail_close; } - ret = sysfs_create_bin_file(&channel->kobj, &ring_buffer_bin_attr); - if (ret) - dev_notice(&dev->device, - "sysfs create ring bin file failed; %d\n", ret); + /* + * This internally calls sysfs_update_group, which returns a non-zero value if it executes + * before sysfs_create_group. This is expected as the 'ring' will be created later in + * vmbus_device_register() -> vmbus_add_channel_kobj(). Thus, no need to check the return + * value and print warning. + * + * Creating/exposing sysfs in driver probe is not encouraged as it can lead to race + * conditions with userspace. For backward compatibility, "ring" sysfs could not be removed + * or decoupled from uio_hv_generic probe. Userspace programs can make use of inotify + * APIs to make sure that ring is created. + */ + hv_create_ring_sysfs(channel, hv_uio_ring_mmap); hv_set_drvdata(dev, pdata); @@ -375,7 +370,7 @@ hv_uio_remove(struct hv_device *dev) if (!pdata) return; - sysfs_remove_bin_file(&dev->channel->kobj, &ring_buffer_bin_attr); + hv_remove_ring_sysfs(dev->channel); uio_unregister_device(&pdata->info); hv_uio_cleanup(dev, pdata); diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h index 675959fb97ba..d6ffe01962c2 100644 --- a/include/linux/hyperv.h +++ b/include/linux/hyperv.h @@ -1002,6 +1002,12 @@ struct vmbus_channel { /* The max size of a packet on this channel */ u32 max_pkt_size; + + /* function to mmap ring buffer memory to the channel's sysfs ring attribute */ + int (*mmap_ring_buffer)(struct vmbus_channel *channel, struct vm_area_struct *vma); + + /* boolean to control visibility of sysfs for ring buffer */ + bool ring_sysfs_visible; }; #define lock_requestor(channel, flags) \

3 months, 4 weeks

3
2
0 0

[PATCH 6.14] x86/its: Fix build errors when CONFIG_MODULES=n

by Pawan Gupta

From: Eric Biggers <ebiggers(a)google.com> commit 9f35e33144ae5377d6a8de86dd3bd4d995c6ac65 upstream. Fix several build errors when CONFIG_MODULES=n, including the following: ../arch/x86/kernel/alternative.c:195:25: error: incomplete definition of type 'struct module' 195 | for (int i = 0; i < mod->its_num_pages; i++) { Fixes: 872df34d7c51 ("x86/its: Use dynamic thunks for indirect branches") Cc: stable(a)vger.kernel.org Signed-off-by: Eric Biggers <ebiggers(a)google.com> Acked-by: Dave Hansen <dave.hansen(a)intel.com> Tested-by: Steven Rostedt (Google) <rostedt(a)goodmis.org> Reviewed-by: Alexandre Chartre <alexandre.chartre(a)oracle.com> Signed-off-by: Linus Torvalds <torvalds(a)linux-foundation.org> Signed-off-by: Pawan Gupta <pawan.kumar.gupta(a)linux.intel.com> --- arch/x86/kernel/alternative.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c index 1cdcd79f302d15be44477c7350bf6537a5e42c22..c9b4f388a533530ca59846aea972fded66a37734 100644 --- a/arch/x86/kernel/alternative.c +++ b/arch/x86/kernel/alternative.c @@ -129,7 +129,9 @@ const unsigned char * const x86_nops[ASM_NOP_MAX+1] = #ifdef CONFIG_MITIGATION_ITS +#ifdef CONFIG_MODULES static struct module *its_mod; +#endif static void *its_page; static unsigned int its_offset; @@ -150,6 +152,7 @@ static void *its_init_thunk(void *thunk, int reg) return thunk; } +#ifdef CONFIG_MODULES void its_init_mod(struct module *mod) { if (!cpu_feature_enabled(X86_FEATURE_INDIRECT_THUNK_ITS)) @@ -188,6 +191,7 @@ void its_free_mod(struct module *mod) } kfree(mod->its_page_array); } +#endif /* CONFIG_MODULES */ static void *its_alloc(void) { @@ -196,6 +200,7 @@ static void *its_alloc(void) if (!page) return NULL; +#ifdef CONFIG_MODULES if (its_mod) { void *tmp = krealloc(its_mod->its_page_array, (its_mod->its_num_pages+1) * sizeof(void *), @@ -206,6 +211,7 @@ static void *its_alloc(void) its_mod->its_page_array = tmp; its_mod->its_page_array[its_mod->its_num_pages++] = page; } +#endif /* CONFIG_MODULES */ return no_free_ptr(page); } --- base-commit: 982c0c8bc78be18914f38ae20ea0f55e268b88ca change-id: 20250513-its-fixes-6-14-53d0a7946250 Best regards, -- Thanks, Pawan

3 months, 4 weeks

2
1
0 0

[PATCH 5.15.y] ibmvnic: Don't reference skb after sending to VIOS

by bin.lan.cn＠windriver.com

From: Nick Child <nnac123(a)linux.ibm.com> [ Upstream commit bdf5d13aa05ec314d4385b31ac974d6c7e0997c9 ] Previously, after successfully flushing the xmit buffer to VIOS, the tx_bytes stat was incremented by the length of the skb. It is invalid to access the skb memory after sending the buffer to the VIOS because, at any point after sending, the VIOS can trigger an interrupt to free this memory. A race between reading skb->len and freeing the skb is possible (especially during LPM) and will result in use-after-free: ================================================================== BUG: KASAN: slab-use-after-free in ibmvnic_xmit+0x75c/0x1808 [ibmvnic] Read of size 4 at addr c00000024eb48a70 by task hxecom/14495 <...> Call Trace: [c000000118f66cf0] [c0000000018cba6c] dump_stack_lvl+0x84/0xe8 (unreliable) [c000000118f66d20] [c0000000006f0080] print_report+0x1a8/0x7f0 [c000000118f66df0] [c0000000006f08f0] kasan_report+0x128/0x1f8 [c000000118f66f00] [c0000000006f2868] __asan_load4+0xac/0xe0 [c000000118f66f20] [c0080000046eac84] ibmvnic_xmit+0x75c/0x1808 [ibmvnic] [c000000118f67340] [c0000000014be168] dev_hard_start_xmit+0x150/0x358 <...> Freed by task 0: kasan_save_stack+0x34/0x68 kasan_save_track+0x2c/0x50 kasan_save_free_info+0x64/0x108 __kasan_mempool_poison_object+0x148/0x2d4 napi_skb_cache_put+0x5c/0x194 net_tx_action+0x154/0x5b8 handle_softirqs+0x20c/0x60c do_softirq_own_stack+0x6c/0x88 <...> The buggy address belongs to the object at c00000024eb48a00 which belongs to the cache skbuff_head_cache of size 224 ================================================================== Fixes: 032c5e82847a ("Driver for IBM System i/p VNIC protocol") Signed-off-by: Nick Child <nnac123(a)linux.ibm.com> Reviewed-by: Simon Horman <horms(a)kernel.org> Link: https://patch.msgid.link/20250214155233.235559-1-nnac123@linux.ibm.com Signed-off-by: Jakub Kicinski <kuba(a)kernel.org> [Minor context change fixed.] Signed-off-by: Bin Lan <bin.lan.cn(a)windriver.com> Signed-off-by: He Zhe <zhe.he(a)windriver.com> --- Build test passed. --- drivers/net/ethernet/ibm/ibmvnic.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c index 7f4539a2e551..4b87d9f59628 100644 --- a/drivers/net/ethernet/ibm/ibmvnic.c +++ b/drivers/net/ethernet/ibm/ibmvnic.c @@ -1758,6 +1758,7 @@ static netdev_tx_t ibmvnic_xmit(struct sk_buff *skb, struct net_device *netdev) dma_addr_t data_dma_addr; struct netdev_queue *txq; unsigned long lpar_rc; + unsigned int skblen; union sub_crq tx_crq; unsigned int offset; int num_entries = 1; @@ -1843,6 +1844,7 @@ static netdev_tx_t ibmvnic_xmit(struct sk_buff *skb, struct net_device *netdev) tx_buff->skb = skb; tx_buff->index = index; tx_buff->pool_index = queue_num; + skblen = skb->len; memset(&tx_crq, 0, sizeof(tx_crq)); tx_crq.v1.first = IBMVNIC_CRQ_CMD; @@ -1919,7 +1921,7 @@ static netdev_tx_t ibmvnic_xmit(struct sk_buff *skb, struct net_device *netdev) } tx_packets++; - tx_bytes += skb->len; + tx_bytes += skblen; txq->trans_start = jiffies; ret = NETDEV_TX_OK; goto out; -- 2.34.1

3 months, 4 weeks

2
1
0 0

[PATCH 5.10.y] ibmvnic: Don't reference skb after sending to VIOS

by bin.lan.cn＠windriver.com

From: Nick Child <nnac123(a)linux.ibm.com> [ Upstream commit bdf5d13aa05ec314d4385b31ac974d6c7e0997c9 ] Previously, after successfully flushing the xmit buffer to VIOS, the tx_bytes stat was incremented by the length of the skb. It is invalid to access the skb memory after sending the buffer to the VIOS because, at any point after sending, the VIOS can trigger an interrupt to free this memory. A race between reading skb->len and freeing the skb is possible (especially during LPM) and will result in use-after-free: ================================================================== BUG: KASAN: slab-use-after-free in ibmvnic_xmit+0x75c/0x1808 [ibmvnic] Read of size 4 at addr c00000024eb48a70 by task hxecom/14495 <...> Call Trace: [c000000118f66cf0] [c0000000018cba6c] dump_stack_lvl+0x84/0xe8 (unreliable) [c000000118f66d20] [c0000000006f0080] print_report+0x1a8/0x7f0 [c000000118f66df0] [c0000000006f08f0] kasan_report+0x128/0x1f8 [c000000118f66f00] [c0000000006f2868] __asan_load4+0xac/0xe0 [c000000118f66f20] [c0080000046eac84] ibmvnic_xmit+0x75c/0x1808 [ibmvnic] [c000000118f67340] [c0000000014be168] dev_hard_start_xmit+0x150/0x358 <...> Freed by task 0: kasan_save_stack+0x34/0x68 kasan_save_track+0x2c/0x50 kasan_save_free_info+0x64/0x108 __kasan_mempool_poison_object+0x148/0x2d4 napi_skb_cache_put+0x5c/0x194 net_tx_action+0x154/0x5b8 handle_softirqs+0x20c/0x60c do_softirq_own_stack+0x6c/0x88 <...> The buggy address belongs to the object at c00000024eb48a00 which belongs to the cache skbuff_head_cache of size 224 ================================================================== Fixes: 032c5e82847a ("Driver for IBM System i/p VNIC protocol") Signed-off-by: Nick Child <nnac123(a)linux.ibm.com> Reviewed-by: Simon Horman <horms(a)kernel.org> Link: https://patch.msgid.link/20250214155233.235559-1-nnac123@linux.ibm.com Signed-off-by: Jakub Kicinski <kuba(a)kernel.org> [Minor context change fixed.] Signed-off-by: Bin Lan <bin.lan.cn(a)windriver.com> Signed-off-by: He Zhe <zhe.he(a)windriver.com> --- Build test passed. --- drivers/net/ethernet/ibm/ibmvnic.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c index 84da6ccaf339..73e3165aa9ae 100644 --- a/drivers/net/ethernet/ibm/ibmvnic.c +++ b/drivers/net/ethernet/ibm/ibmvnic.c @@ -1548,6 +1548,7 @@ static netdev_tx_t ibmvnic_xmit(struct sk_buff *skb, struct net_device *netdev) dma_addr_t data_dma_addr; struct netdev_queue *txq; unsigned long lpar_rc; + unsigned int skblen; union sub_crq tx_crq; unsigned int offset; int num_entries = 1; @@ -1631,6 +1632,7 @@ static netdev_tx_t ibmvnic_xmit(struct sk_buff *skb, struct net_device *netdev) tx_buff->index = index; tx_buff->pool_index = queue_num; tx_buff->last_frag = true; + skblen = skb->len; memset(&tx_crq, 0, sizeof(tx_crq)); tx_crq.v1.first = IBMVNIC_CRQ_CMD; @@ -1733,7 +1735,7 @@ static netdev_tx_t ibmvnic_xmit(struct sk_buff *skb, struct net_device *netdev) } tx_packets++; - tx_bytes += skb->len; + tx_bytes += skblen; txq->trans_start = jiffies; ret = NETDEV_TX_OK; goto out; -- 2.34.1

3 months, 4 weeks

2
1
0 0

[PATCH] x86/its: Fix build errors when CONFIG_MODULES=n

by Pawan Gupta

From: Eric Biggers <ebiggers(a)google.com> commit 9f35e33144ae5377d6a8de86dd3bd4d995c6ac65 upstream. Fix several build errors when CONFIG_MODULES=n, including the following: ../arch/x86/kernel/alternative.c:195:25: error: incomplete definition of type 'struct module' 195 | for (int i = 0; i < mod->its_num_pages; i++) { Fixes: 872df34d7c51 ("x86/its: Use dynamic thunks for indirect branches") Cc: stable(a)vger.kernel.org Signed-off-by: Eric Biggers <ebiggers(a)google.com> Acked-by: Dave Hansen <dave.hansen(a)intel.com> Tested-by: Steven Rostedt (Google) <rostedt(a)goodmis.org> Reviewed-by: Alexandre Chartre <alexandre.chartre(a)oracle.com> Signed-off-by: Linus Torvalds <torvalds(a)linux-foundation.org> Signed-off-by: Pawan Gupta <pawan.kumar.gupta(a)linux.intel.com> --- This patch applies on top of patches in stable-queue with ITS mitigation. arch/x86/kernel/alternative.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c index 01aa5a73c82fd8fe33a14a73ebace6d4e3b6b169..29482c52086577757d512942147db7f8d65a34bd 100644 --- a/arch/x86/kernel/alternative.c +++ b/arch/x86/kernel/alternative.c @@ -129,7 +129,9 @@ const unsigned char * const x86_nops[ASM_NOP_MAX+1] = #ifdef CONFIG_MITIGATION_ITS +#ifdef CONFIG_MODULES static struct module *its_mod; +#endif static void *its_page; static unsigned int its_offset; @@ -150,6 +152,7 @@ static void *its_init_thunk(void *thunk, int reg) return thunk; } +#ifdef CONFIG_MODULES void its_init_mod(struct module *mod) { if (!cpu_feature_enabled(X86_FEATURE_INDIRECT_THUNK_ITS)) @@ -188,6 +191,7 @@ void its_free_mod(struct module *mod) } kfree(mod->its_page_array); } +#endif /* CONFIG_MODULES */ static void *its_alloc(void) { @@ -196,6 +200,7 @@ static void *its_alloc(void) if (!page) return NULL; +#ifdef CONFIG_MODULES if (its_mod) { void *tmp = krealloc(its_mod->its_page_array, (its_mod->its_num_pages+1) * sizeof(void *), @@ -206,6 +211,7 @@ static void *its_alloc(void) its_mod->its_page_array = tmp; its_mod->its_page_array[its_mod->its_num_pages++] = page; } +#endif /* CONFIG_MODULES */ return no_free_ptr(page); } --- change-id: 20250513-its-fixes-6-12-0a495cd71de4

3 months, 4 weeks

2
1
0 0

[PATCH] xhci: dbc: Avoid event polling busyloop if pending rx transfers are inactive.

by Mathias Nyman

[ Upstream commit cab63934c33b12c0d1e9f4da7450928057f2c142 ] Backport for linux-6.12.y stable 6.12 kernel used older poll_interval of 1ms instead of 0 as described in the original commit message below. CPU hogging is not that bad with 1ms delay, fix it anyways, but don't touch poll_interval. Event polling delay is set to 0 if there are any pending requests in either rx or tx requests lists. Checking for pending requests does not work well for "IN" transfers as the tty driver always queues requests to the list and TRBs to the ring, preparing to receive data from the host. This causes unnecessary busylooping and cpu hogging. Only set the event polling delay to 0 if there are pending tx "write" transfers, or if it was less than 10ms since last active data transfer in any direction. Cc: Łukasz Bartosik <ukaszb(a)chromium.org> Fixes: fb18e5bb9660 ("xhci: dbc: poll at different rate depending on data transfer activity") Signed-off-by: Mathias Nyman <mathias.nyman(a)linux.intel.com> --- drivers/usb/host/xhci-dbgcap.c | 19 ++++++++++++++++--- drivers/usb/host/xhci-dbgcap.h | 3 +++ 2 files changed, 19 insertions(+), 3 deletions(-) diff --git a/drivers/usb/host/xhci-dbgcap.c b/drivers/usb/host/xhci-dbgcap.c index 241d7aa1fbc2..b12273f72c93 100644 --- a/drivers/usb/host/xhci-dbgcap.c +++ b/drivers/usb/host/xhci-dbgcap.c @@ -822,6 +822,7 @@ static enum evtreturn xhci_dbc_do_handle_events(struct xhci_dbc *dbc) { dma_addr_t deq; union xhci_trb *evt; + enum evtreturn ret = EVT_DONE; u32 ctrl, portsc; bool update_erdp = false; @@ -906,6 +907,7 @@ static enum evtreturn xhci_dbc_do_handle_events(struct xhci_dbc *dbc) break; case TRB_TYPE(TRB_TRANSFER): dbc_handle_xfer_event(dbc, evt); + ret = EVT_XFER_DONE; break; default: break; @@ -924,7 +926,7 @@ static enum evtreturn xhci_dbc_do_handle_events(struct xhci_dbc *dbc) lo_hi_writeq(deq, &dbc->regs->erdp); } - return EVT_DONE; + return ret; } static void xhci_dbc_handle_events(struct work_struct *work) @@ -933,6 +935,7 @@ static void xhci_dbc_handle_events(struct work_struct *work) struct xhci_dbc *dbc; unsigned long flags; unsigned int poll_interval; + unsigned long busypoll_timelimit; dbc = container_of(to_delayed_work(work), struct xhci_dbc, event_work); poll_interval = dbc->poll_interval; @@ -951,11 +954,21 @@ static void xhci_dbc_handle_events(struct work_struct *work) dbc->driver->disconnect(dbc); break; case EVT_DONE: - /* set fast poll rate if there are pending data transfers */ + /* + * Set fast poll rate if there are pending out transfers, or + * a transfer was recently processed + */ + busypoll_timelimit = dbc->xfer_timestamp + + msecs_to_jiffies(DBC_XFER_INACTIVITY_TIMEOUT); + if (!list_empty(&dbc->eps[BULK_OUT].list_pending) || - !list_empty(&dbc->eps[BULK_IN].list_pending)) + time_is_after_jiffies(busypoll_timelimit)) poll_interval = 1; break; + case EVT_XFER_DONE: + dbc->xfer_timestamp = jiffies; + poll_interval = 1; + break; default: dev_info(dbc->dev, "stop handling dbc events\n"); return; diff --git a/drivers/usb/host/xhci-dbgcap.h b/drivers/usb/host/xhci-dbgcap.h index 9dc8f4d8077c..47ac72c2286d 100644 --- a/drivers/usb/host/xhci-dbgcap.h +++ b/drivers/usb/host/xhci-dbgcap.h @@ -96,6 +96,7 @@ struct dbc_ep { #define DBC_WRITE_BUF_SIZE 8192 #define DBC_POLL_INTERVAL_DEFAULT 64 /* milliseconds */ #define DBC_POLL_INTERVAL_MAX 5000 /* milliseconds */ +#define DBC_XFER_INACTIVITY_TIMEOUT 10 /* milliseconds */ /* * Private structure for DbC hardware state: */ @@ -142,6 +143,7 @@ struct xhci_dbc { enum dbc_state state; struct delayed_work event_work; unsigned int poll_interval; /* ms */ + unsigned long xfer_timestamp; unsigned resume_required:1; struct dbc_ep eps[2]; @@ -187,6 +189,7 @@ struct dbc_request { enum evtreturn { EVT_ERR = -1, EVT_DONE, + EVT_XFER_DONE, EVT_GSER, EVT_DISC, }; -- 2.43.0

3 months, 4 weeks

2
1
0 0

[PATCH] x86/its: Fix build errors when CONFIG_MODULES=n

by Pawan Gupta

From: Eric Biggers <ebiggers(a)google.com> commit 9f35e33144ae5377d6a8de86dd3bd4d995c6ac65 upstream. Fix several build errors when CONFIG_MODULES=n, including the following: ../arch/x86/kernel/alternative.c:195:25: error: incomplete definition of type 'struct module' 195 | for (int i = 0; i < mod->its_num_pages; i++) { Fixes: 872df34d7c51 ("x86/its: Use dynamic thunks for indirect branches") Cc: stable(a)vger.kernel.org Signed-off-by: Eric Biggers <ebiggers(a)google.com> Acked-by: Dave Hansen <dave.hansen(a)intel.com> Tested-by: Steven Rostedt (Google) <rostedt(a)goodmis.org> Reviewed-by: Alexandre Chartre <alexandre.chartre(a)oracle.com> Signed-off-by: Linus Torvalds <torvalds(a)linux-foundation.org> Signed-off-by: Pawan Gupta <pawan.kumar.gupta(a)linux.intel.com> --- arch/x86/kernel/alternative.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c index 6085919d3b3ebbf57b4c6f257eb30d0781569fe4..5a0b84e21285d16b7869b59c7d9e622a99c7ad7a 100644 --- a/arch/x86/kernel/alternative.c +++ b/arch/x86/kernel/alternative.c @@ -129,7 +129,9 @@ const unsigned char * const x86_nops[ASM_NOP_MAX+1] = #ifdef CONFIG_MITIGATION_ITS +#ifdef CONFIG_MODULES static struct module *its_mod; +#endif static void *its_page; static unsigned int its_offset; @@ -150,6 +152,7 @@ static void *its_init_thunk(void *thunk, int reg) return thunk; } +#ifdef CONFIG_MODULES void its_init_mod(struct module *mod) { if (!cpu_feature_enabled(X86_FEATURE_INDIRECT_THUNK_ITS)) @@ -188,6 +191,7 @@ void its_free_mod(struct module *mod) } kfree(mod->its_page_array); } +#endif /* CONFIG_MODULES */ DEFINE_FREE(its_execmem, void *, if (_T) module_memfree(_T)); @@ -198,6 +202,7 @@ static void *its_alloc(void) if (!page) return NULL; +#ifdef CONFIG_MODULES if (its_mod) { void *tmp = krealloc(its_mod->its_page_array, (its_mod->its_num_pages+1) * sizeof(void *), @@ -208,6 +213,7 @@ static void *its_alloc(void) its_mod->its_page_array = tmp; its_mod->its_page_array[its_mod->its_num_pages++] = page; } +#endif /* CONFIG_MODULES */ return no_free_ptr(page); } --- change-id: 20250513-its-fixes-6-6-990e444d4d67

3 months, 4 weeks

3
3
0 0

[PATCH 6.1.y] platform/x86/amd/pmc: Only disable IRQ1 wakeup where i8042 actually enabled it

by Zhaoyang Li

From: "Maciej S. Szmigiero" <mail(a)maciej.szmigiero.name> [ Upstream commit dd410d784402c5775f66faf8b624e85e41c38aaf ] Wakeup for IRQ1 should be disabled only in cases where i8042 had actually enabled it, otherwise "wake_depth" for this IRQ will try to drop below zero and there will be an unpleasant WARN() logged: kernel: atkbd serio0: Disabling IRQ1 wakeup source to avoid platform firmware bug kernel: ------------[ cut here ]------------ kernel: Unbalanced IRQ 1 wake disable kernel: WARNING: CPU: 10 PID: 6431 at kernel/irq/manage.c:920 irq_set_irq_wake+0x147/0x1a0 The PMC driver uses DEFINE_SIMPLE_DEV_PM_OPS() to define its dev_pm_ops which sets amd_pmc_suspend_handler() to the .suspend, .freeze, and .poweroff handlers. i8042_pm_suspend(), however, is only set as the .suspend handler. Fix the issue by call PMC suspend handler only from the same set of dev_pm_ops handlers as i8042_pm_suspend(), which currently means just the .suspend handler. To reproduce this issue try hibernating (S4) the machine after a fresh boot without putting it into s2idle first. Fixes: 8e60615e8932 ("platform/x86/amd: pmc: Disable IRQ1 wakeup for RN/CZN") Reviewed-by: Mario Limonciello <mario.limonciello(a)amd.com> Signed-off-by: Maciej S. Szmigiero <mail(a)maciej.szmigiero.name> Link: https://lore.kernel.org/r/c8f28c002ca3c66fbeeb850904a1f43118e17200.17361846… [ij: edited the commit message.] Reviewed-by: Ilpo Järvinen <ilpo.jarvinen(a)linux.intel.com> Signed-off-by: Ilpo Järvinen <ilpo.jarvinen(a)linux.intel.com> Signed-off-by: Zhaoyang Li <lizy04(a)hust.edu.cn> --- drivers/platform/x86/amd/pmc.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/drivers/platform/x86/amd/pmc.c b/drivers/platform/x86/amd/pmc.c index f237c1ea8d35..8eaeb1e8f975 100644 --- a/drivers/platform/x86/amd/pmc.c +++ b/drivers/platform/x86/amd/pmc.c @@ -834,6 +834,10 @@ static int __maybe_unused amd_pmc_suspend_handler(struct device *dev) { struct amd_pmc_dev *pdev = dev_get_drvdata(dev); + /* + * Must be called only from the same set of dev_pm_ops handlers + * as i8042_pm_suspend() is called: currently just from .suspend. + */ if (pdev->cpu_id == AMD_CPU_ID_CZN) { int rc = amd_pmc_czn_wa_irq1(pdev); @@ -846,7 +850,9 @@ static int __maybe_unused amd_pmc_suspend_handler(struct device *dev) return 0; } -static SIMPLE_DEV_PM_OPS(amd_pmc_pm, amd_pmc_suspend_handler, NULL); +static const struct dev_pm_ops amd_pmc_pm = { + .suspend = amd_pmc_suspend_handler, +}; #endif -- 2.25.1

3 months, 4 weeks

2
1
0 0

[PATCH 5.10] bpf: Avoid overflows involving hash elem_size

by Daniil Dulov

From: Eric Dumazet <edumazet(a)google.com> commit e1868b9e36d0ca52e4e7c6c06953f191446e44df upstream. Use of bpf_map_charge_init() was making sure hash tables would not use more than 4GB of memory. Since the implicit check disappeared, we have to be more careful about overflows, to support big hash tables. syzbot triggers a panic using : bpf(BPF_MAP_CREATE, {map_type=BPF_MAP_TYPE_LRU_HASH, key_size=16384, value_size=8, max_entries=262200, map_flags=0, inner_map_fd=-1, map_name="", map_ifindex=0, btf_fd=-1, btf_key_type_id=0, btf_value_type_id=0, btf_vmlinux_value_type_id=0}, 64) = ... BUG: KASAN: vmalloc-out-of-bounds in bpf_percpu_lru_populate kernel/bpf/bpf_lru_list.c:594 [inline] BUG: KASAN: vmalloc-out-of-bounds in bpf_lru_populate+0x4ef/0x5e0 kernel/bpf/bpf_lru_list.c:611 Write of size 2 at addr ffffc90017e4a020 by task syz-executor.5/19786 CPU: 0 PID: 19786 Comm: syz-executor.5 Not tainted 5.10.0-rc3-syzkaller #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Call Trace: __dump_stack lib/dump_stack.c:77 [inline] dump_stack+0x107/0x163 lib/dump_stack.c:118 print_address_description.constprop.0.cold+0x5/0x4c8 mm/kasan/report.c:385 __kasan_report mm/kasan/report.c:545 [inline] kasan_report.cold+0x1f/0x37 mm/kasan/report.c:562 bpf_percpu_lru_populate kernel/bpf/bpf_lru_list.c:594 [inline] bpf_lru_populate+0x4ef/0x5e0 kernel/bpf/bpf_lru_list.c:611 prealloc_init kernel/bpf/hashtab.c:319 [inline] htab_map_alloc+0xf6e/0x1230 kernel/bpf/hashtab.c:507 find_and_alloc_map kernel/bpf/syscall.c:123 [inline] map_create kernel/bpf/syscall.c:829 [inline] __do_sys_bpf+0xa81/0x5170 kernel/bpf/syscall.c:4336 do_syscall_64+0x2d/0x70 arch/x86/entry/common.c:46 entry_SYSCALL_64_after_hwframe+0x44/0xa9 RIP: 0033:0x45deb9 Code: 0d b4 fb ff c3 66 2e 0f 1f 84 00 00 00 00 00 66 90 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 0f 83 db b3 fb ff c3 66 2e 0f 1f 84 00 00 00 00 RSP: 002b:00007fd93fbc0c78 EFLAGS: 00000246 ORIG_RAX: 0000000000000141 RAX: ffffffffffffffda RBX: 0000000000001a40 RCX: 000000000045deb9 RDX: 0000000000000040 RSI: 0000000020000280 RDI: 0000000000000000 RBP: 000000000119bf60 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000246 R12: 000000000119bf2c R13: 00007ffc08a7be8f R14: 00007fd93fbc19c0 R15: 000000000119bf2c Fixes: 755e5d55367a ("bpf: Eliminate rlimit-based memory accounting for hashtab maps") Reported-by: syzbot <syzkaller(a)googlegroups.com> Signed-off-by: Eric Dumazet <edumazet(a)google.com> Signed-off-by: Alexei Starovoitov <ast(a)kernel.org> Acked-by: Roman Gushchin <guro(a)fb.com> Link: https://lore.kernel.org/bpf/20201207182821.3940306-1-eric.dumazet@gmail.com Signed-off-by: Daniil Dulov <d.dulov(a)aladdin.ru> --- kernel/bpf/hashtab.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c index 4c7cab79d90e..829d6d3a8495 100644 --- a/kernel/bpf/hashtab.c +++ b/kernel/bpf/hashtab.c @@ -199,7 +199,7 @@ static void *fd_htab_map_get_ptr(const struct bpf_map *map, struct htab_elem *l) static struct htab_elem *get_htab_elem(struct bpf_htab *htab, int i) { - return (struct htab_elem *) (htab->elems + i * htab->elem_size); + return (struct htab_elem *) (htab->elems + i * (u64)htab->elem_size); } static void htab_free_elems(struct bpf_htab *htab) @@ -255,7 +255,7 @@ static int prealloc_init(struct bpf_htab *htab) if (!htab_is_percpu(htab) && !htab_is_lru(htab)) num_entries += num_possible_cpus(); - htab->elems = bpf_map_area_alloc(htab->elem_size * num_entries, + htab->elems = bpf_map_area_alloc((u64)htab->elem_size * num_entries, htab->map.numa_node); if (!htab->elems) return -ENOMEM; -- 2.34.1

3 months, 4 weeks

1
0
0 0

[RFC PATCH 1/7] efi: Add missing static initializer for efi_mm::cpus_allowed_lock

by Ard Biesheuvel

From: Ard Biesheuvel <ardb(a)kernel.org> Initialize the cpus_allowed_lock struct member of efi_mm. Cc: <stable(a)vger.kernel.org> Signed-off-by: Ard Biesheuvel <ardb(a)kernel.org> --- drivers/firmware/efi/efi.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/firmware/efi/efi.c b/drivers/firmware/efi/efi.c index 7309394b8fc9..59a56661937c 100644 --- a/drivers/firmware/efi/efi.c +++ b/drivers/firmware/efi/efi.c @@ -73,6 +73,9 @@ struct mm_struct efi_mm = { .page_table_lock = __SPIN_LOCK_UNLOCKED(efi_mm.page_table_lock), .mmlist = LIST_HEAD_INIT(efi_mm.mmlist), .cpu_bitmap = { [BITS_TO_LONGS(NR_CPUS)] = 0}, +#ifdef CONFIG_SCHED_MM_CID + .cpus_allowed_lock = __RAW_SPIN_LOCK_UNLOCKED(efi_mm.cpus_allowed_lock), +#endif }; struct workqueue_struct *efi_rts_wq; -- 2.49.0.1101.gccaa498523-goog

3 months, 4 weeks

1
0
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-stable-mirror May 2025