March 2024 - Linux-stable-mirror

[PATCH net v3] net: esp: fix bad handling of pages from page_pool

by Dragos Tatulea

When the skb is reorganized during esp_output (!esp->inline), the pages coming from the original skb fragments are supposed to be released back to the system through put_page. But if the skb fragment pages are originating from a page_pool, calling put_page on them will trigger a page_pool leak which will eventually result in a crash. This leak can be easily observed when using CONFIG_DEBUG_VM and doing ipsec + gre (non offloaded) forwarding: BUG: Bad page state in process ksoftirqd/16 pfn:1451b6 page:00000000de2b8d32 refcount:0 mapcount:0 mapping:0000000000000000 index:0x1451b6000 pfn:0x1451b6 flags: 0x200000000000000(node=0|zone=2) page_type: 0xffffffff() raw: 0200000000000000 dead000000000040 ffff88810d23c000 0000000000000000 raw: 00000001451b6000 0000000000000001 00000000ffffffff 0000000000000000 page dumped because: page_pool leak Modules linked in: ip_gre gre mlx5_ib mlx5_core xt_conntrack xt_MASQUERADE nf_conntrack_netlink nfnetlink iptable_nat nf_nat xt_addrtype br_netfilter rpcrdma rdma_ucm ib_iser libiscsi scsi_transport_iscsi ib_umad rdma_cm ib_ipoib iw_cm ib_cm ib_uverbs ib_core overlay zram zsmalloc fuse [last unloaded: mlx5_core] CPU: 16 PID: 96 Comm: ksoftirqd/16 Not tainted 6.8.0-rc4+ #22 Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS rel-1.13.0-0-gf21b5a4aeb02-prebuilt.qemu.org 04/01/2014 Call Trace: <TASK> dump_stack_lvl+0x36/0x50 bad_page+0x70/0xf0 free_unref_page_prepare+0x27a/0x460 free_unref_page+0x38/0x120 esp_ssg_unref.isra.0+0x15f/0x200 esp_output_tail+0x66d/0x780 esp_xmit+0x2c5/0x360 validate_xmit_xfrm+0x313/0x370 ? validate_xmit_skb+0x1d/0x330 validate_xmit_skb_list+0x4c/0x70 sch_direct_xmit+0x23e/0x350 __dev_queue_xmit+0x337/0xba0 ? nf_hook_slow+0x3f/0xd0 ip_finish_output2+0x25e/0x580 iptunnel_xmit+0x19b/0x240 ip_tunnel_xmit+0x5fb/0xb60 ipgre_xmit+0x14d/0x280 [ip_gre] dev_hard_start_xmit+0xc3/0x1c0 __dev_queue_xmit+0x208/0xba0 ? nf_hook_slow+0x3f/0xd0 ip_finish_output2+0x1ca/0x580 ip_sublist_rcv_finish+0x32/0x40 ip_sublist_rcv+0x1b2/0x1f0 ? ip_rcv_finish_core.constprop.0+0x460/0x460 ip_list_rcv+0x103/0x130 __netif_receive_skb_list_core+0x181/0x1e0 netif_receive_skb_list_internal+0x1b3/0x2c0 napi_gro_receive+0xc8/0x200 gro_cell_poll+0x52/0x90 __napi_poll+0x25/0x1a0 net_rx_action+0x28e/0x300 __do_softirq+0xc3/0x276 ? sort_range+0x20/0x20 run_ksoftirqd+0x1e/0x30 smpboot_thread_fn+0xa6/0x130 kthread+0xcd/0x100 ? kthread_complete_and_exit+0x20/0x20 ret_from_fork+0x31/0x50 ? kthread_complete_and_exit+0x20/0x20 ret_from_fork_asm+0x11/0x20 </TASK> The suggested fix is to introduce a new wrapper (skb_page_unref) that covers page refcounting for page_pool pages as well. Cc: stable(a)vger.kernel.org Fixes: 6a5bcd84e886 ("page_pool: Allow drivers to hint on SKB recycling") Reported-and-tested-by: Anatoli N.Chechelnickiy <Anatoli.Chechelnickiy(a)m.interpipe.biz> Reported-by: Ian Kumlien <ian.kumlien(a)gmail.com> Link: https://lore.kernel.org/netdev/CAA85sZvvHtrpTQRqdaOx6gd55zPAVsqMYk_Lwh4Md5k… Signed-off-by: Dragos Tatulea <dtatulea(a)nvidia.com> Reviewed-by: Mina Almasry <almasrymina(a)google.com> Reviewed-by: Jakub Kicinski <kuba(a)kernel.org> --- Changes in v2: - Fixes in tags. Changes in v3: - Rebased to ipsec tree. --- include/linux/skbuff.h | 10 ++++++++++ net/ipv4/esp4.c | 8 ++++---- net/ipv6/esp6.c | 8 ++++---- 3 files changed, 18 insertions(+), 8 deletions(-) diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 2dde34c29203..d9a1ccfb5708 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -3448,6 +3448,16 @@ static inline void skb_frag_ref(struct sk_buff *skb, int f) bool napi_pp_put_page(struct page *page, bool napi_safe); +static inline void +skb_page_unref(const struct sk_buff *skb, struct page *page, bool napi_safe) +{ +#ifdef CONFIG_PAGE_POOL + if (skb->pp_recycle && napi_pp_put_page(page, napi_safe)) + return; +#endif + put_page(page); +} + static inline void napi_frag_unref(skb_frag_t *frag, bool recycle, bool napi_safe) { diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c index 4dd9e5040672..d33d12421814 100644 --- a/net/ipv4/esp4.c +++ b/net/ipv4/esp4.c @@ -95,7 +95,7 @@ static inline struct scatterlist *esp_req_sg(struct crypto_aead *aead, __alignof__(struct scatterlist)); } -static void esp_ssg_unref(struct xfrm_state *x, void *tmp) +static void esp_ssg_unref(struct xfrm_state *x, void *tmp, struct sk_buff *skb) { struct crypto_aead *aead = x->data; int extralen = 0; @@ -114,7 +114,7 @@ static void esp_ssg_unref(struct xfrm_state *x, void *tmp) */ if (req->src != req->dst) for (sg = sg_next(req->src); sg; sg = sg_next(sg)) - put_page(sg_page(sg)); + skb_page_unref(skb, sg_page(sg), false); } #ifdef CONFIG_INET_ESPINTCP @@ -260,7 +260,7 @@ static void esp_output_done(void *data, int err) } tmp = ESP_SKB_CB(skb)->tmp; - esp_ssg_unref(x, tmp); + esp_ssg_unref(x, tmp, skb); kfree(tmp); if (xo && (xo->flags & XFRM_DEV_RESUME)) { @@ -639,7 +639,7 @@ int esp_output_tail(struct xfrm_state *x, struct sk_buff *skb, struct esp_info * } if (sg != dsg) - esp_ssg_unref(x, tmp); + esp_ssg_unref(x, tmp, skb); if (!err && x->encap && x->encap->encap_type == TCP_ENCAP_ESPINTCP) err = esp_output_tail_tcp(x, skb); diff --git a/net/ipv6/esp6.c b/net/ipv6/esp6.c index 6e6efe026cdc..7371886d4f9f 100644 --- a/net/ipv6/esp6.c +++ b/net/ipv6/esp6.c @@ -112,7 +112,7 @@ static inline struct scatterlist *esp_req_sg(struct crypto_aead *aead, __alignof__(struct scatterlist)); } -static void esp_ssg_unref(struct xfrm_state *x, void *tmp) +static void esp_ssg_unref(struct xfrm_state *x, void *tmp, struct sk_buff *skb) { struct crypto_aead *aead = x->data; int extralen = 0; @@ -131,7 +131,7 @@ static void esp_ssg_unref(struct xfrm_state *x, void *tmp) */ if (req->src != req->dst) for (sg = sg_next(req->src); sg; sg = sg_next(sg)) - put_page(sg_page(sg)); + skb_page_unref(skb, sg_page(sg), false); } #ifdef CONFIG_INET6_ESPINTCP @@ -294,7 +294,7 @@ static void esp_output_done(void *data, int err) } tmp = ESP_SKB_CB(skb)->tmp; - esp_ssg_unref(x, tmp); + esp_ssg_unref(x, tmp, skb); kfree(tmp); esp_output_encap_csum(skb); @@ -677,7 +677,7 @@ int esp6_output_tail(struct xfrm_state *x, struct sk_buff *skb, struct esp_info } if (sg != dsg) - esp_ssg_unref(x, tmp); + esp_ssg_unref(x, tmp, skb); if (!err && x->encap && x->encap->encap_type == TCP_ENCAP_ESPINTCP) err = esp_output_tail_tcp(x, skb); -- 2.42.0

1 year, 1 month

3
4
0 0

[PATCH] net/mlx5: offset comp irq index in name by one

by Michael Liang

The mlx5 comp irq name scheme is changed a little bit between commit 3663ad34bc70 ("net/mlx5: Shift control IRQ to the last index") and commit 3354822cde5a ("net/mlx5: Use dynamic msix vectors allocation"). The index in the comp irq name used to start from 0 but now it starts from 1. There is nothing critical here, but it's harmless to change back to the old behavior, a.k.a starting from 0. Fixes: 3354822cde5a ("net/mlx5: Use dynamic msix vectors allocation") Reviewed-by: Mohamed Khalfella <mkhalfella(a)purestorage.com> Reviewed-by: Yuanyuan Zhong <yzhong(a)purestorage.com> Signed-off-by: Michael Liang <mliang(a)purestorage.com> --- drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c b/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c index 4dcf995cb1a2..6bac8ad70ba6 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c @@ -19,6 +19,7 @@ #define MLX5_IRQ_CTRL_SF_MAX 8 /* min num of vectors for SFs to be enabled */ #define MLX5_IRQ_VEC_COMP_BASE_SF 2 +#define MLX5_IRQ_VEC_COMP_BASE 1 #define MLX5_EQ_SHARE_IRQ_MAX_COMP (8) #define MLX5_EQ_SHARE_IRQ_MAX_CTRL (UINT_MAX) @@ -246,6 +247,7 @@ static void irq_set_name(struct mlx5_irq_pool *pool, char *name, int vecidx) return; } + vecidx -= MLX5_IRQ_VEC_COMP_BASE; snprintf(name, MLX5_MAX_IRQ_NAME, "mlx5_comp%d", vecidx); } @@ -585,7 +587,7 @@ struct mlx5_irq *mlx5_irq_request_vector(struct mlx5_core_dev *dev, u16 cpu, struct mlx5_irq_table *table = mlx5_irq_table_get(dev); struct mlx5_irq_pool *pool = table->pcif_pool; struct irq_affinity_desc af_desc; - int offset = 1; + int offset = MLX5_IRQ_VEC_COMP_BASE; if (!pool->xa_num_irqs.max) offset = 0; -- 2.34.1

1 year, 1 month

3
2
0 0

[PATCH 01/43] drm/fbdev-generic: Do not set physical framebuffer address

by Thomas Zimmermann

Framebuffer memory is allocated via vmalloc() from non-contiguous physical pages. The physical framebuffer start address is therefore meaningless. Do not set it. The value is not used within the kernel and only exported to userspace on dedicated ARM configs. No functional change is expected. Signed-off-by: Thomas Zimmermann <tzimmermann(a)suse.de> Fixes: a5b44c4adb16 ("drm/fbdev-generic: Always use shadow buffering") Cc: Thomas Zimmermann <tzimmermann(a)suse.de> Cc: Javier Martinez Canillas <javierm(a)redhat.com> Cc: Zack Rusin <zackr(a)vmware.com> Cc: Maarten Lankhorst <maarten.lankhorst(a)linux.intel.com> Cc: Maxime Ripard <mripard(a)kernel.org> Cc: <stable(a)vger.kernel.org> # v6.4+ --- drivers/gpu/drm/drm_fbdev_generic.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/gpu/drm/drm_fbdev_generic.c b/drivers/gpu/drm/drm_fbdev_generic.c index d647d89764cb9..b4659cd6285ab 100644 --- a/drivers/gpu/drm/drm_fbdev_generic.c +++ b/drivers/gpu/drm/drm_fbdev_generic.c @@ -113,7 +113,6 @@ static int drm_fbdev_generic_helper_fb_probe(struct drm_fb_helper *fb_helper, /* screen */ info->flags |= FBINFO_VIRTFB | FBINFO_READS_FAST; info->screen_buffer = screen_buffer; - info->fix.smem_start = page_to_phys(vmalloc_to_page(info->screen_buffer)); info->fix.smem_len = screen_size; /* deferred I/O */ -- 2.44.0

1 year, 1 month

5
7
0 0

[PATCH 3/7] KVM: SVM: Add support for allowing zero SEV ASIDs

by Paolo Bonzini

From: Ashish Kalra <ashish.kalra(a)amd.com> Some BIOSes allow the end user to set the minimum SEV ASID value (CPUID 0x8000001F_EDX) to be greater than the maximum number of encrypted guests, or maximum SEV ASID value (CPUID 0x8000001F_ECX) in order to dedicate all the SEV ASIDs to SEV-ES or SEV-SNP. The SEV support, as coded, does not handle the case where the minimum SEV ASID value can be greater than the maximum SEV ASID value. As a result, the following confusing message is issued: [ 30.715724] kvm_amd: SEV enabled (ASIDs 1007 - 1006) Fix the support to properly handle this case. Fixes: 916391a2d1dc ("KVM: SVM: Add support for SEV-ES capability in KVM") Suggested-by: Sean Christopherson <seanjc(a)google.com> Signed-off-by: Ashish Kalra <ashish.kalra(a)amd.com> Cc: stable(a)vger.kernel.org Acked-by: Tom Lendacky <thomas.lendacky(a)amd.com> Link: https://lore.kernel.org/r/20240104190520.62510-1-Ashish.Kalra@amd.com Link: https://lore.kernel.org/r/20240131235609.4161407-4-seanjc@google.com Signed-off-by: Sean Christopherson <seanjc(a)google.com> --- arch/x86/kvm/svm/sev.c | 29 +++++++++++++++++++---------- 1 file changed, 19 insertions(+), 10 deletions(-) diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c index eeef43c795d8..5f8312edee36 100644 --- a/arch/x86/kvm/svm/sev.c +++ b/arch/x86/kvm/svm/sev.c @@ -144,10 +144,21 @@ static void sev_misc_cg_uncharge(struct kvm_sev_info *sev) static int sev_asid_new(struct kvm_sev_info *sev) { - unsigned int asid, min_asid, max_asid; + /* + * SEV-enabled guests must use asid from min_sev_asid to max_sev_asid. + * SEV-ES-enabled guest can use from 1 to min_sev_asid - 1. + * Note: min ASID can end up larger than the max if basic SEV support is + * effectively disabled by disallowing use of ASIDs for SEV guests. + */ + unsigned int min_asid = sev->es_active ? 1 : min_sev_asid; + unsigned int max_asid = sev->es_active ? min_sev_asid - 1 : max_sev_asid; + unsigned int asid; bool retry = true; int ret; + if (min_asid > max_asid) + return -ENOTTY; + WARN_ON(sev->misc_cg); sev->misc_cg = get_current_misc_cg(); ret = sev_misc_cg_try_charge(sev); @@ -159,12 +170,6 @@ static int sev_asid_new(struct kvm_sev_info *sev) mutex_lock(&sev_bitmap_lock); - /* - * SEV-enabled guests must use asid from min_sev_asid to max_sev_asid. - * SEV-ES-enabled guest can use from 1 to min_sev_asid - 1. - */ - min_asid = sev->es_active ? 1 : min_sev_asid; - max_asid = sev->es_active ? min_sev_asid - 1 : max_sev_asid; again: asid = find_next_zero_bit(sev_asid_bitmap, max_asid + 1, min_asid); if (asid > max_asid) { @@ -2234,8 +2239,10 @@ void __init sev_hardware_setup(void) goto out; } - sev_asid_count = max_sev_asid - min_sev_asid + 1; - WARN_ON_ONCE(misc_cg_set_capacity(MISC_CG_RES_SEV, sev_asid_count)); + if (min_sev_asid <= max_sev_asid) { + sev_asid_count = max_sev_asid - min_sev_asid + 1; + WARN_ON_ONCE(misc_cg_set_capacity(MISC_CG_RES_SEV, sev_asid_count)); + } sev_supported = true; /* SEV-ES support requested? */ @@ -2266,7 +2273,9 @@ void __init sev_hardware_setup(void) out: if (boot_cpu_has(X86_FEATURE_SEV)) pr_info("SEV %s (ASIDs %u - %u)\n", - sev_supported ? "enabled" : "disabled", + sev_supported ? min_sev_asid <= max_sev_asid ? "enabled" : + "unusable" : + "disabled", min_sev_asid, max_sev_asid); if (boot_cpu_has(X86_FEATURE_SEV_ES)) pr_info("SEV-ES %s (ASIDs %u - %u)\n", -- 2.43.0

1 year, 1 month

1
0
0 0

[PATCH 2/7] btrfs: reduce the log level for btrfs_dev_stat_inc_and_print()

by Qu Wenruo

Currently when we increase the device statistics, it would always lead to an error message in the kernel log. I would argue this behavior is not ideal: - It would flood the dmesg and bury real important messages One common scenario is scrub. If scrub hit some errors, it would cause both scrub and btrfs_dev_stat_inc_and_print() to print error messages. And in that case, btrfs_dev_stat_inc_and_print() is completely useless. - The results of btrfs_dev_stat_inc_and_print() is mostly for history monitoring, doesn't has enough details If we trigger the errors during regular read, such messages from btrfs_dev_stat_inc_and_print() won't help us to locate the cause either. The real usage for the btrfs device statistics is for some user space daemon to check if there is any new errors, acting like some checks on SMART, thus we don't really need/want those messages in dmesg. This patch would reduce the log level to debug (disabled by default) for btrfs_dev_stat_inc_and_print(). For users really want to utilize btrfs devices statistics, they should go check "btrfs device stats" periodically, and we should focus the kernel error messages to more important things. CC: stable(a)vger.kernel.org Signed-off-by: Qu Wenruo <wqu(a)suse.com> --- fs/btrfs/volumes.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index e49935a54da0..126145950ed3 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -7828,7 +7828,7 @@ void btrfs_dev_stat_inc_and_print(struct btrfs_device *dev, int index) if (!dev->dev_stats_valid) return; - btrfs_err_rl_in_rcu(dev->fs_info, + btrfs_debug_rl_in_rcu(dev->fs_info, "bdev %s errs: wr %u, rd %u, flush %u, corrupt %u, gen %u", btrfs_dev_name(dev), btrfs_dev_stat_read(dev, BTRFS_DEV_STAT_WRITE_ERRS), -- 2.44.0

1 year, 1 month

3
3
0 0

+ mm-cachestat-fix-two-shmem-bugs.patch added to mm-hotfixes-unstable branch

by Andrew Morton

The patch titled Subject: mm: cachestat: fix two shmem bugs has been added to the -mm mm-hotfixes-unstable branch. Its filename is mm-cachestat-fix-two-shmem-bugs.patch This patch will shortly appear at https://git.kernel.org/pub/scm/linux/kernel/git/akpm/25-new.git/tree/patche… This patch will later appear in the mm-hotfixes-unstable branch at git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm Before you just go and hit "reply", please: a) Consider who else should be cc'ed b) Prefer to cc a suitable mailing list as well c) Ideally: find the original patch on the mailing list and do a reply-to-all to that, adding suitable additional cc's *** Remember to use Documentation/process/submit-checklist.rst when testing your code *** The -mm tree is included into linux-next via the mm-everything branch at git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm and is updated there every 2-3 working days ------------------------------------------------------ From: Johannes Weiner <hannes(a)cmpxchg.org> Subject: mm: cachestat: fix two shmem bugs Date: Fri, 15 Mar 2024 05:55:56 -0400 When cachestat on shmem races with swapping and invalidation, there are two possible bugs: 1) A swapin error can have resulted in a poisoned swap entry in the shmem inode's xarray. Calling get_shadow_from_swap_cache() on it will result in an out-of-bounds access to swapper_spaces[]. Validate the entry with non_swap_entry() before going further. 2) When we find a valid swap entry in the shmem's inode, the shadow entry in the swapcache might not exist yet: swap IO is still in progress and we're before __remove_mapping; swapin, invalidation, or swapoff have removed the shadow from swapcache after we saw the shmem swap entry. This will send a NULL to workingset_test_recent(). The latter purely operates on pointer bits, so it won't crash - node 0, memcg ID 0, eviction timestamp 0, etc. are all valid inputs - but it's a bogus test. In theory that could result in a false "recently evicted" count. Such a false positive wouldn't be the end of the world. But for code clarity and (future) robustness, be explicit about this case. Bail on get_shadow_from_swap_cache() returning NULL. Link: https://lkml.kernel.org/r/20240315095556.GC581298@cmpxchg.org Fixes: cf264e1329fb ("cachestat: implement cachestat syscall") Signed-off-by: Johannes Weiner <hannes(a)cmpxchg.org> Reported-by: Chengming Zhou <chengming.zhou(a)linux.dev> [Bug #1] Reported-by: Jann Horn <jannh(a)google.com> [Bug #2] Reviewed-by: Chengming Zhou <chengming.zhou(a)linux.dev> Reviewed-by: Nhat Pham <nphamcs(a)gmail.com> Cc: <stable(a)vger.kernel.org> [v6.5+] Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- mm/filemap.c | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) --- a/mm/filemap.c~mm-cachestat-fix-two-shmem-bugs +++ a/mm/filemap.c @@ -4197,7 +4197,23 @@ static void filemap_cachestat(struct add /* shmem file - in swap cache */ swp_entry_t swp = radix_to_swp_entry(folio); + /* swapin error results in poisoned entry */ + if (non_swap_entry(swp)) + goto resched; + + /* + * Getting a swap entry from the shmem + * inode means we beat + * shmem_unuse(). rcu_read_lock() + * ensures swapoff waits for us before + * freeing the swapper space. However, + * we can race with swapping and + * invalidation, so there might not be + * a shadow in the swapcache (yet). + */ shadow = get_shadow_from_swap_cache(swp); + if (!shadow) + goto resched; } #endif if (workingset_test_recent(shadow, true, &workingset)) _ Patches currently in -mm which might be from hannes(a)cmpxchg.org are mm-cachestat-fix-two-shmem-bugs.patch

1 year, 1 month

1
0
0 0

+ init-open-initrdimage-with-o_largefile.patch added to mm-hotfixes-unstable branch

by Andrew Morton

The patch titled Subject: init: open /initrd.image with O_LARGEFILE has been added to the -mm mm-hotfixes-unstable branch. Its filename is init-open-initrdimage-with-o_largefile.patch This patch will shortly appear at https://git.kernel.org/pub/scm/linux/kernel/git/akpm/25-new.git/tree/patche… This patch will later appear in the mm-hotfixes-unstable branch at git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm Before you just go and hit "reply", please: a) Consider who else should be cc'ed b) Prefer to cc a suitable mailing list as well c) Ideally: find the original patch on the mailing list and do a reply-to-all to that, adding suitable additional cc's *** Remember to use Documentation/process/submit-checklist.rst when testing your code *** The -mm tree is included into linux-next via the mm-everything branch at git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm and is updated there every 2-3 working days ------------------------------------------------------ From: John Sperbeck <jsperbeck(a)google.com> Subject: init: open /initrd.image with O_LARGEFILE Date: Sun, 17 Mar 2024 15:15:22 -0700 If initrd data is larger than 2Gb, we'll eventually fail to write to the /initrd.image file when we hit that limit, unless O_LARGEFILE is set. Link: https://lkml.kernel.org/r/20240317221522.896040-1-jsperbeck@google.com Signed-off-by: John Sperbeck <jsperbeck(a)google.com> Cc: Jens Axboe <axboe(a)kernel.dk> Cc: Nick Desaulniers <ndesaulniers(a)google.com> Cc: Peter Zijlstra <peterz(a)infradead.org> Cc: Thomas Gleixner <tglx(a)linutronix.de> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- init/initramfs.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) --- a/init/initramfs.c~init-open-initrdimage-with-o_largefile +++ a/init/initramfs.c @@ -682,7 +682,7 @@ static void __init populate_initrd_image printk(KERN_INFO "rootfs image is not initramfs (%s); looks like an initrd\n", err); - file = filp_open("/initrd.image", O_WRONLY | O_CREAT, 0700); + file = filp_open("/initrd.image", O_WRONLY|O_CREAT|O_LARGEFILE, 0700); if (IS_ERR(file)) return; _ Patches currently in -mm which might be from jsperbeck(a)google.com are init-open-initrdimage-with-o_largefile.patch

1 year, 1 month

1
0
0 0

[PATCH v5] btrfs: do not skip re-registration for the mounted device

by Anand Jain

There are reports that since version 6.7 update-grub fails to find the device of the root on systems without initrd and on a single device. This looks like the device name changed in the output of /proc/self/mountinfo: 6.5-rc5 working 18 1 0:16 / / rw,noatime - btrfs /dev/sda8 ... 6.7 not working: 17 1 0:15 / / rw,noatime - btrfs /dev/root ... and "update-grub" shows this error: /usr/sbin/grub-probe: error: cannot find a device for / (is /dev mounted?) This looks like it's related to the device name, but grub-probe recognizes the "/dev/root" path and tries to find the underlying device. However there's a special case for some filesystems, for btrfs in particular. The generic root device detection heuristic is not done and it all relies on reading the device infos by a btrfs specific ioctl. This ioctl returns the device name as it was saved at the time of device scan (in this case it's /dev/root). The change in 6.7 for temp_fsid to allow several single device filesystem to exist with the same fsid (and transparently generate a new UUID at mount time) was to skip caching/registering such devices. This also skipped mounted device. One step of scanning is to check if the device name hasn't changed, and if yes then update the cached value. This broke the grub-probe as it always read the device /dev/root and couldn't find it in the system. A temporary workaround is to create a symlink but this does not survive reboot. The right fix is to allow updating the device path of a mounted filesystem even if this is a single device one. In the fix, check if the device's major:minor number matches with the cached device. If they do, then we can allow the scan to happen so that device_list_add() can take care of updating the device path. The file descriptor remains unchanged. This does not affect the temp_fsid feature, the UUID of the mounted filesystem remains the same and the matching is based on device major:minor which is unique per mounted filesystem. This covers the path when the device (that exists for all mounted devices) name changes, updating /dev/root to /dev/sdx. Any other single device with filesystem and is not mounted is still skipped. Note that if a system is booted and initial mount is done on the /dev/root device, this will be the cached name of the device. Only after the command "btrfs device scan" it will change as it triggers the rename. The fix was verified by users whose systems were affected. CC: stable(a)vger.kernel.org # 6.7+ Fixes: bc27d6f0aa0e ("btrfs: scan but don't register device on single device filesystem") Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=218353 Link: https://lore.kernel.org/lkml/CAKLYgeJ1tUuqLcsquwuFqjDXPSJpEiokrWK2gisPKDZLs… Tested-by: Alex Romosan <aromosan(a)gmail.com> Tested-by: CHECK_1234543212345(a)protonmail.com Reviewed-by: David Sterba <dsterba(a)suse.com> Signed-off-by: Anand Jain <anand.jain(a)oracle.com> --- v5: Fix the linux-next build failure reported here: https://lore.kernel.org/all/20240318091755.1d0f696f@canb.auug.org.au/ As the Linux-next branch no longer has the this commit, I've sent out the entire patch again. v4: (based on mainline master) I removed CC: stable(a)vger.kernel.org # 6.7+ as this is still in the RFC stage. I need this patch verified by the bug filer. Use devt from bdev->bd_dev Rebased on mainline kernel.org master branch v3: https://lore.kernel.org/linux-btrfs/e2add8d54fbbd813305ba014c11d21d297ad87d… fs/btrfs/volumes.c | 58 +++++++++++++++++++++++++++++++++++++--------- 1 file changed, 47 insertions(+), 11 deletions(-) diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index a2d07fa3cfdf..813c1c66b2db 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -1303,6 +1303,47 @@ int btrfs_forget_devices(dev_t devt) return ret; } +static bool btrfs_skip_registration(struct btrfs_super_block *disk_super, + const char *path, dev_t devt, + bool mount_arg_dev) +{ + struct btrfs_fs_devices *fs_devices; + + /* + * Do not skip device registration for mounted devices with matching + * maj:min but different paths. Booting without initrd relies on + * /dev/root initially, later replaced with the actual root device. + * A successful scan ensures update-grub selects the correct device. + */ + list_for_each_entry(fs_devices, &fs_uuids, fs_list) { + struct btrfs_device *device; + + mutex_lock(&fs_devices->device_list_mutex); + + if (!fs_devices->opened) { + mutex_unlock(&fs_devices->device_list_mutex); + continue; + } + + list_for_each_entry(device, &fs_devices->devices, dev_list) { + if ((device->devt == devt) && + strcmp(device->name->str, path)) { + mutex_unlock(&fs_devices->device_list_mutex); + + /* Do not skip registration */ + return false; + } + } + mutex_unlock(&fs_devices->device_list_mutex); + } + + if (!mount_arg_dev && btrfs_super_num_devices(disk_super) == 1 && + !(btrfs_super_flags(disk_super) & BTRFS_SUPER_FLAG_SEEDING)) + return true; + + return false; +} + /* * Look for a btrfs signature on a device. This may be called out of the mount path * and we are not allowed to call set_blocksize during the scan. The superblock @@ -1320,6 +1361,7 @@ struct btrfs_device *btrfs_scan_one_device(const char *path, blk_mode_t flags, struct btrfs_device *device = NULL; struct file *bdev_file; u64 bytenr, bytenr_orig; + dev_t devt; int ret; lockdep_assert_held(&uuid_mutex); @@ -1359,19 +1401,13 @@ struct btrfs_device *btrfs_scan_one_device(const char *path, blk_mode_t flags, goto error_bdev_put; } - if (!mount_arg_dev && btrfs_super_num_devices(disk_super) == 1 && - !(btrfs_super_flags(disk_super) & BTRFS_SUPER_FLAG_SEEDING)) { - dev_t devt; + devt = file_bdev(bdev_file)->bd_dev; + if (btrfs_skip_registration(disk_super, path, devt, mount_arg_dev)) { + pr_debug("BTRFS: skip registering single non-seed device %s (%d:%d)\n", + path, MAJOR(devt), MINOR(devt)); - ret = lookup_bdev(path, &devt); - if (ret) - btrfs_warn(NULL, "lookup bdev failed for path %s: %d", - path, ret); - else - btrfs_free_stale_devices(devt, NULL); + btrfs_free_stale_devices(devt, NULL); - pr_debug("BTRFS: skip registering single non-seed device %s (%d:%d)\n", - path, MAJOR(devt), MINOR(devt)); device = NULL; goto free_disk_super; } -- 2.38.1

1 year, 1 month

3
2
0 0

[PATCH] perf/x86/intel/uncore: Fix the bits of the CHA extended umask for SPR

by kan.liang＠linux.intel.com

From: Kan Liang <kan.liang(a)linux.intel.com> The perf stat errors out with UNC_CHA_TOR_INSERTS.IA_HIT_CXL_ACC_LOCAL event. $perf stat -e uncore_cha_55/event=0x35,umask=0x10c0008101/ -a -- ls event syntax error: '..0x35,umask=0x10c0008101/' \___ Bad event or PMU The definition of the CHA umask is config:8-15,32-55, which is 32bit. However, the umask of the event is bigger than 32bit. This is an error in the original uncore spec. Add a new umask_ext5 for the new CHA umask range. Fixes: 949b11381f81 ("perf/x86/intel/uncore: Add Sapphire Rapids server CHA support") Closes: https://lore.kernel.org/linux-perf-users/alpine.LRH.2.20.2401300733310.1135… Signed-off-by: Kan Liang <kan.liang(a)linux.intel.com> Cc: stable(a)vger.kernel.org --- arch/x86/events/intel/uncore_snbep.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/arch/x86/events/intel/uncore_snbep.c b/arch/x86/events/intel/uncore_snbep.c index a96496bef678..7924f315269a 100644 --- a/arch/x86/events/intel/uncore_snbep.c +++ b/arch/x86/events/intel/uncore_snbep.c @@ -461,6 +461,7 @@ #define SPR_UBOX_DID 0x3250 /* SPR CHA */ +#define SPR_CHA_EVENT_MASK_EXT 0xffffffff #define SPR_CHA_PMON_CTL_TID_EN (1 << 16) #define SPR_CHA_PMON_EVENT_MASK (SNBEP_PMON_RAW_EVENT_MASK | \ SPR_CHA_PMON_CTL_TID_EN) @@ -477,6 +478,7 @@ DEFINE_UNCORE_FORMAT_ATTR(umask_ext, umask, "config:8-15,32-43,45-55"); DEFINE_UNCORE_FORMAT_ATTR(umask_ext2, umask, "config:8-15,32-57"); DEFINE_UNCORE_FORMAT_ATTR(umask_ext3, umask, "config:8-15,32-39"); DEFINE_UNCORE_FORMAT_ATTR(umask_ext4, umask, "config:8-15,32-55"); +DEFINE_UNCORE_FORMAT_ATTR(umask_ext5, umask, "config:8-15,32-63"); DEFINE_UNCORE_FORMAT_ATTR(qor, qor, "config:16"); DEFINE_UNCORE_FORMAT_ATTR(edge, edge, "config:18"); DEFINE_UNCORE_FORMAT_ATTR(tid_en, tid_en, "config:19"); @@ -5957,7 +5959,7 @@ static struct intel_uncore_ops spr_uncore_chabox_ops = { static struct attribute *spr_uncore_cha_formats_attr[] = { &format_attr_event.attr, - &format_attr_umask_ext4.attr, + &format_attr_umask_ext5.attr, &format_attr_tid_en2.attr, &format_attr_edge.attr, &format_attr_inv.attr, @@ -5993,7 +5995,7 @@ ATTRIBUTE_GROUPS(uncore_alias); static struct intel_uncore_type spr_uncore_chabox = { .name = "cha", .event_mask = SPR_CHA_PMON_EVENT_MASK, - .event_mask_ext = SPR_RAW_EVENT_MASK_EXT, + .event_mask_ext = SPR_CHA_EVENT_MASK_EXT, .num_shared_regs = 1, .constraints = skx_uncore_chabox_constraints, .ops = &spr_uncore_chabox_ops, -- 2.35.1

1 year, 1 month

3
2
0 0

[PATCH AUTOSEL 5.10 1/7] btrfs: add and use helper to check if block group is used

by Sasha Levin

From: Filipe Manana <fdmanana(a)suse.com> [ Upstream commit 1693d5442c458ae8d5b0d58463b873cd879569ed ] Add a helper function to determine if a block group is being used and make use of it at btrfs_delete_unused_bgs(). This helper will also be used in future code changes. Reviewed-by: Johannes Thumshirn <johannes.thumshirn(a)wdc.com> Reviewed-by: Josef Bacik <josef(a)toxicpanda.com> Reviewed-by: Boris Burkov <boris(a)bur.io> Signed-off-by: Filipe Manana <fdmanana(a)suse.com> Reviewed-by: David Sterba <dsterba(a)suse.com> Signed-off-by: David Sterba <dsterba(a)suse.com> Signed-off-by: Sasha Levin <sashal(a)kernel.org> --- fs/btrfs/block-group.c | 3 +-- fs/btrfs/block-group.h | 7 +++++++ 2 files changed, 8 insertions(+), 2 deletions(-) diff --git a/fs/btrfs/block-group.c b/fs/btrfs/block-group.c index c4e3c1a5de059..9a7c7e0f7c233 100644 --- a/fs/btrfs/block-group.c +++ b/fs/btrfs/block-group.c @@ -1393,8 +1393,7 @@ void btrfs_delete_unused_bgs(struct btrfs_fs_info *fs_info) } spin_lock(&block_group->lock); - if (block_group->reserved || block_group->pinned || - block_group->used || block_group->ro || + if (btrfs_is_block_group_used(block_group) || block_group->ro || list_is_singular(&block_group->list)) { /* * We want to bail if we made new allocations or have diff --git a/fs/btrfs/block-group.h b/fs/btrfs/block-group.h index 4c7614346f724..0d02b75f9e7e3 100644 --- a/fs/btrfs/block-group.h +++ b/fs/btrfs/block-group.h @@ -196,6 +196,13 @@ static inline u64 btrfs_block_group_end(struct btrfs_block_group *block_group) return (block_group->start + block_group->length); } +static inline bool btrfs_is_block_group_used(const struct btrfs_block_group *bg) +{ + lockdep_assert_held(&bg->lock); + + return (bg->used > 0 || bg->reserved > 0 || bg->pinned > 0); +} + static inline bool btrfs_is_block_group_data_only( struct btrfs_block_group *block_group) { -- 2.43.0

1 year, 1 month

3
9
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-stable-mirror March 2024