- Linux-stable-mirror - lists.linaro.org

FAILED: patch "[PATCH] f2fs: use global inline_xattr_slab instead of per-sb slab" failed to apply to 5.10-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 5.10-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-5.10.y git checkout FETCH_HEAD git cherry-pick -x 1f27ef42bb0b7c0740c5616ec577ec188b8a1d05 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2025122924-placidly-rehire-4364@gregkh' --subject-prefix 'PATCH 5.10.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 1f27ef42bb0b7c0740c5616ec577ec188b8a1d05 Mon Sep 17 00:00:00 2001 From: Chao Yu <chao(a)kernel.org> Date: Tue, 21 Oct 2025 11:48:56 +0800 Subject: [PATCH] f2fs: use global inline_xattr_slab instead of per-sb slab cache MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit As Hong Yun reported in mailing list: loop7: detected capacity change from 0 to 131072 ------------[ cut here ]------------ kmem_cache of name 'f2fs_xattr_entry-7:7' already exists WARNING: CPU: 0 PID: 24426 at mm/slab_common.c:110 kmem_cache_sanity_check mm/slab_common.c:109 [inline] WARNING: CPU: 0 PID: 24426 at mm/slab_common.c:110 __kmem_cache_create_args+0xa6/0x320 mm/slab_common.c:307 CPU: 0 UID: 0 PID: 24426 Comm: syz.7.1370 Not tainted 6.17.0-rc4 #1 PREEMPT(full) Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.13.0-1ubuntu1.1 04/01/2014 RIP: 0010:kmem_cache_sanity_check mm/slab_common.c:109 [inline] RIP: 0010:__kmem_cache_create_args+0xa6/0x320 mm/slab_common.c:307 Call Trace: __kmem_cache_create include/linux/slab.h:353 [inline] f2fs_kmem_cache_create fs/f2fs/f2fs.h:2943 [inline] f2fs_init_xattr_caches+0xa5/0xe0 fs/f2fs/xattr.c:843 f2fs_fill_super+0x1645/0x2620 fs/f2fs/super.c:4918 get_tree_bdev_flags+0x1fb/0x260 fs/super.c:1692 vfs_get_tree+0x43/0x140 fs/super.c:1815 do_new_mount+0x201/0x550 fs/namespace.c:3808 do_mount fs/namespace.c:4136 [inline] __do_sys_mount fs/namespace.c:4347 [inline] __se_sys_mount+0x298/0x2f0 fs/namespace.c:4324 do_syscall_x64 arch/x86/entry/syscall_64.c:63 [inline] do_syscall_64+0x8e/0x3a0 arch/x86/entry/syscall_64.c:94 entry_SYSCALL_64_after_hwframe+0x76/0x7e The bug can be reproduced w/ below scripts: - mount /dev/vdb /mnt1 - mount /dev/vdc /mnt2 - umount /mnt1 - mounnt /dev/vdb /mnt1 The reason is if we created two slab caches, named f2fs_xattr_entry-7:3 and f2fs_xattr_entry-7:7, and they have the same slab size. Actually, slab system will only create one slab cache core structure which has slab name of "f2fs_xattr_entry-7:3", and two slab caches share the same structure and cache address. So, if we destroy f2fs_xattr_entry-7:3 cache w/ cache address, it will decrease reference count of slab cache, rather than release slab cache entirely, since there is one more user has referenced the cache. Then, if we try to create slab cache w/ name "f2fs_xattr_entry-7:3" again, slab system will find that there is existed cache which has the same name and trigger the warning. Let's changes to use global inline_xattr_slab instead of per-sb slab cache for fixing. Fixes: a999150f4fe3 ("f2fs: use kmem_cache pool during inline xattr lookups") Cc: stable(a)kernel.org Reported-by: Hong Yun <yhong(a)link.cuhk.edu.hk> Tested-by: Hong Yun <yhong(a)link.cuhk.edu.hk> Signed-off-by: Chao Yu <chao(a)kernel.org> Signed-off-by: Jaegeuk Kim <jaegeuk(a)kernel.org> diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h index e69b01c1173a..9ca2124aac84 100644 --- a/fs/f2fs/f2fs.h +++ b/fs/f2fs/f2fs.h @@ -1885,9 +1885,6 @@ struct f2fs_sb_info { spinlock_t error_lock; /* protect errors/stop_reason array */ bool error_dirty; /* errors of sb is dirty */ - struct kmem_cache *inline_xattr_slab; /* inline xattr entry */ - unsigned int inline_xattr_slab_size; /* default inline xattr slab size */ - /* For reclaimed segs statistics per each GC mode */ unsigned int gc_segment_mode; /* GC state for reclaimed segments */ unsigned int gc_reclaimed_segs[MAX_GC_MODE]; /* Reclaimed segs for each mode */ diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c index d0b5791a1f8c..f76ba2b08be0 100644 --- a/fs/f2fs/super.c +++ b/fs/f2fs/super.c @@ -2027,7 +2027,6 @@ static void f2fs_put_super(struct super_block *sb) kfree(sbi->raw_super); f2fs_destroy_page_array_cache(sbi); - f2fs_destroy_xattr_caches(sbi); #ifdef CONFIG_QUOTA for (i = 0; i < MAXQUOTAS; i++) kfree(F2FS_OPTION(sbi).s_qf_names[i]); @@ -4975,13 +4974,9 @@ static int f2fs_fill_super(struct super_block *sb, struct fs_context *fc) if (err) goto free_iostat; - /* init per sbi slab cache */ - err = f2fs_init_xattr_caches(sbi); - if (err) - goto free_percpu; err = f2fs_init_page_array_cache(sbi); if (err) - goto free_xattr_cache; + goto free_percpu; /* get an inode for meta space */ sbi->meta_inode = f2fs_iget(sb, F2FS_META_INO(sbi)); @@ -5310,8 +5305,6 @@ static int f2fs_fill_super(struct super_block *sb, struct fs_context *fc) sbi->meta_inode = NULL; free_page_array_cache: f2fs_destroy_page_array_cache(sbi); -free_xattr_cache: - f2fs_destroy_xattr_caches(sbi); free_percpu: destroy_percpu_info(sbi); free_iostat: @@ -5514,10 +5507,15 @@ static int __init init_f2fs_fs(void) err = f2fs_create_casefold_cache(); if (err) goto free_compress_cache; - err = register_filesystem(&f2fs_fs_type); + err = f2fs_init_xattr_cache(); if (err) goto free_casefold_cache; + err = register_filesystem(&f2fs_fs_type); + if (err) + goto free_xattr_cache; return 0; +free_xattr_cache: + f2fs_destroy_xattr_cache(); free_casefold_cache: f2fs_destroy_casefold_cache(); free_compress_cache: @@ -5558,6 +5556,7 @@ static int __init init_f2fs_fs(void) static void __exit exit_f2fs_fs(void) { unregister_filesystem(&f2fs_fs_type); + f2fs_destroy_xattr_cache(); f2fs_destroy_casefold_cache(); f2fs_destroy_compress_cache(); f2fs_destroy_compress_mempool(); diff --git a/fs/f2fs/xattr.c b/fs/f2fs/xattr.c index 58632a2b6613..b4e5c406632f 100644 --- a/fs/f2fs/xattr.c +++ b/fs/f2fs/xattr.c @@ -23,11 +23,12 @@ #include "xattr.h" #include "segment.h" +static struct kmem_cache *inline_xattr_slab; static void *xattr_alloc(struct f2fs_sb_info *sbi, int size, bool *is_inline) { - if (likely(size == sbi->inline_xattr_slab_size)) { + if (likely(size == DEFAULT_XATTR_SLAB_SIZE)) { *is_inline = true; - return f2fs_kmem_cache_alloc(sbi->inline_xattr_slab, + return f2fs_kmem_cache_alloc(inline_xattr_slab, GFP_F2FS_ZERO, false, sbi); } *is_inline = false; @@ -38,7 +39,7 @@ static void xattr_free(struct f2fs_sb_info *sbi, void *xattr_addr, bool is_inline) { if (is_inline) - kmem_cache_free(sbi->inline_xattr_slab, xattr_addr); + kmem_cache_free(inline_xattr_slab, xattr_addr); else kfree(xattr_addr); } @@ -830,25 +831,14 @@ int f2fs_setxattr(struct inode *inode, int index, const char *name, return err; } -int f2fs_init_xattr_caches(struct f2fs_sb_info *sbi) +int __init f2fs_init_xattr_cache(void) { - dev_t dev = sbi->sb->s_bdev->bd_dev; - char slab_name[32]; - - sprintf(slab_name, "f2fs_xattr_entry-%u:%u", MAJOR(dev), MINOR(dev)); - - sbi->inline_xattr_slab_size = F2FS_OPTION(sbi).inline_xattr_size * - sizeof(__le32) + XATTR_PADDING_SIZE; - - sbi->inline_xattr_slab = f2fs_kmem_cache_create(slab_name, - sbi->inline_xattr_slab_size); - if (!sbi->inline_xattr_slab) - return -ENOMEM; - - return 0; + inline_xattr_slab = f2fs_kmem_cache_create("f2fs_xattr_entry", + DEFAULT_XATTR_SLAB_SIZE); + return inline_xattr_slab ? 0 : -ENOMEM; } -void f2fs_destroy_xattr_caches(struct f2fs_sb_info *sbi) +void f2fs_destroy_xattr_cache(void) { - kmem_cache_destroy(sbi->inline_xattr_slab); -} + kmem_cache_destroy(inline_xattr_slab); +} \ No newline at end of file diff --git a/fs/f2fs/xattr.h b/fs/f2fs/xattr.h index 4fc0b2305fbd..bce3d93e4755 100644 --- a/fs/f2fs/xattr.h +++ b/fs/f2fs/xattr.h @@ -89,6 +89,8 @@ struct f2fs_xattr_entry { F2FS_TOTAL_EXTRA_ATTR_SIZE / sizeof(__le32) - \ DEF_INLINE_RESERVED_SIZE - \ MIN_INLINE_DENTRY_SIZE / sizeof(__le32)) +#define DEFAULT_XATTR_SLAB_SIZE (DEFAULT_INLINE_XATTR_ADDRS * \ + sizeof(__le32) + XATTR_PADDING_SIZE) /* * On-disk structure of f2fs_xattr @@ -132,8 +134,8 @@ int f2fs_setxattr(struct inode *, int, const char *, const void *, int f2fs_getxattr(struct inode *, int, const char *, void *, size_t, struct folio *); ssize_t f2fs_listxattr(struct dentry *, char *, size_t); -int f2fs_init_xattr_caches(struct f2fs_sb_info *); -void f2fs_destroy_xattr_caches(struct f2fs_sb_info *); +int __init f2fs_init_xattr_cache(void); +void f2fs_destroy_xattr_cache(void); #else #define f2fs_xattr_handlers NULL @@ -150,8 +152,8 @@ static inline int f2fs_getxattr(struct inode *inode, int index, { return -EOPNOTSUPP; } -static inline int f2fs_init_xattr_caches(struct f2fs_sb_info *sbi) { return 0; } -static inline void f2fs_destroy_xattr_caches(struct f2fs_sb_info *sbi) { } +static inline int __init f2fs_init_xattr_cache(void) { return 0; } +static inline void f2fs_destroy_xattr_cache(void) { } #endif #ifdef CONFIG_F2FS_FS_SECURITY

13 hours, 47 minutes

2
1
0 0

FAILED: patch "[PATCH] pinctrl: renesas: rzg2l: Fix ISEL restore on resume" failed to apply to 6.12-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 6.12-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-6.12.y git checkout FETCH_HEAD git cherry-pick -x 44bf66122c12ef6d3382a9b84b9be1802e5f0e95 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2025122907-jujitsu-boneless-55a8@gregkh' --subject-prefix 'PATCH 6.12.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 44bf66122c12ef6d3382a9b84b9be1802e5f0e95 Mon Sep 17 00:00:00 2001 From: Claudiu Beznea <claudiu.beznea.uj(a)bp.renesas.com> Date: Fri, 12 Sep 2025 12:53:08 +0300 Subject: [PATCH] pinctrl: renesas: rzg2l: Fix ISEL restore on resume Commit 1d2da79708cb ("pinctrl: renesas: rzg2l: Avoid configuring ISEL in gpio_irq_{en,dis}able*()") dropped the configuration of ISEL from struct irq_chip::{irq_enable, irq_disable} APIs and moved it to struct gpio_chip::irq::{child_to_parent_hwirq, child_irq_domain_ops::free} APIs to fix spurious IRQs. After commit 1d2da79708cb ("pinctrl: renesas: rzg2l: Avoid configuring ISEL in gpio_irq_{en,dis}able*()"), ISEL was no longer configured properly on resume. This is because the pinctrl resume code used struct irq_chip::irq_enable (called from rzg2l_gpio_irq_restore()) to reconfigure the wakeup interrupts. Some drivers (e.g. Ethernet) may also reconfigure non-wakeup interrupts on resume through their own code, eventually calling struct irq_chip::irq_enable. Fix this by adding ISEL configuration back into the struct irq_chip::irq_enable API and on resume path for wakeup interrupts. As struct irq_chip::irq_enable needs now to lock to update the ISEL, convert the struct rzg2l_pinctrl::lock to a raw spinlock and replace the locking API calls with the raw variants. Otherwise the lockdep reports invalid wait context when probing the adv7511 module on RZ/G2L: [ BUG: Invalid wait context ] 6.17.0-rc5-next-20250911-00001-gfcfac22533c9 #18 Not tainted ----------------------------- (udev-worker)/165 is trying to lock: ffff00000e3664a8 (&pctrl->lock){....}-{3:3}, at: rzg2l_gpio_irq_enable+0x38/0x78 other info that might help us debug this: context-{5:5} 3 locks held by (udev-worker)/165: #0: ffff00000e890108 (&dev->mutex){....}-{4:4}, at: __driver_attach+0x90/0x1ac #1: ffff000011c07240 (request_class){+.+.}-{4:4}, at: __setup_irq+0xb4/0x6dc #2: ffff000011c070c8 (lock_class){....}-{2:2}, at: __setup_irq+0xdc/0x6dc stack backtrace: CPU: 1 UID: 0 PID: 165 Comm: (udev-worker) Not tainted 6.17.0-rc5-next-20250911-00001-gfcfac22533c9 #18 PREEMPT Hardware name: Renesas SMARC EVK based on r9a07g044l2 (DT) Call trace: show_stack+0x18/0x24 (C) dump_stack_lvl+0x90/0xd0 dump_stack+0x18/0x24 __lock_acquire+0xa14/0x20b4 lock_acquire+0x1c8/0x354 _raw_spin_lock_irqsave+0x60/0x88 rzg2l_gpio_irq_enable+0x38/0x78 irq_enable+0x40/0x8c __irq_startup+0x78/0xa4 irq_startup+0x108/0x16c __setup_irq+0x3c0/0x6dc request_threaded_irq+0xec/0x1ac devm_request_threaded_irq+0x80/0x134 adv7511_probe+0x928/0x9a4 [adv7511] i2c_device_probe+0x22c/0x3dc really_probe+0xbc/0x2a0 __driver_probe_device+0x78/0x12c driver_probe_device+0x40/0x164 __driver_attach+0x9c/0x1ac bus_for_each_dev+0x74/0xd0 driver_attach+0x24/0x30 bus_add_driver+0xe4/0x208 driver_register+0x60/0x128 i2c_register_driver+0x48/0xd0 adv7511_init+0x5c/0x1000 [adv7511] do_one_initcall+0x64/0x30c do_init_module+0x58/0x23c load_module+0x1bcc/0x1d40 init_module_from_file+0x88/0xc4 idempotent_init_module+0x188/0x27c __arm64_sys_finit_module+0x68/0xac invoke_syscall+0x48/0x110 el0_svc_common.constprop.0+0xc0/0xe0 do_el0_svc+0x1c/0x28 el0_svc+0x4c/0x160 el0t_64_sync_handler+0xa0/0xe4 el0t_64_sync+0x198/0x19c Having ISEL configuration back into the struct irq_chip::irq_enable API should be safe with respect to spurious IRQs, as in the probe case IRQs are enabled anyway in struct gpio_chip::irq::child_to_parent_hwirq. No spurious IRQs were detected on suspend/resume, boot, ethernet link insert/remove tests (executed on RZ/G3S). Boot, ethernet link insert/remove tests were also executed successfully on RZ/G2L. Fixes: 1d2da79708cb ("pinctrl: renesas: rzg2l: Avoid configuring ISEL in gpio_irq_{en,dis}able*(") Cc: stable(a)vger.kernel.org Signed-off-by: Claudiu Beznea <claudiu.beznea.uj(a)bp.renesas.com> Reviewed-by: Geert Uytterhoeven <geert+renesas(a)glider.be> Link: https://patch.msgid.link/20250912095308.3603704-1-claudiu.beznea.uj@bp.rene… Signed-off-by: Geert Uytterhoeven <geert+renesas(a)glider.be> diff --git a/drivers/pinctrl/renesas/pinctrl-rzg2l.c b/drivers/pinctrl/renesas/pinctrl-rzg2l.c index f524af6f586f..c360e473488c 100644 --- a/drivers/pinctrl/renesas/pinctrl-rzg2l.c +++ b/drivers/pinctrl/renesas/pinctrl-rzg2l.c @@ -359,7 +359,7 @@ struct rzg2l_pinctrl { spinlock_t bitmap_lock; /* protect tint_slot bitmap */ unsigned int hwirq[RZG2L_TINT_MAX_INTERRUPT]; - spinlock_t lock; /* lock read/write registers */ + raw_spinlock_t lock; /* lock read/write registers */ struct mutex mutex; /* serialize adding groups and functions */ struct rzg2l_pinctrl_pin_settings *settings; @@ -543,7 +543,7 @@ static void rzg2l_pinctrl_set_pfc_mode(struct rzg2l_pinctrl *pctrl, unsigned long flags; u32 reg; - spin_lock_irqsave(&pctrl->lock, flags); + raw_spin_lock_irqsave(&pctrl->lock, flags); /* Set pin to 'Non-use (Hi-Z input protection)' */ reg = readw(pctrl->base + PM(off)); @@ -567,7 +567,7 @@ static void rzg2l_pinctrl_set_pfc_mode(struct rzg2l_pinctrl *pctrl, pctrl->data->pwpr_pfc_lock_unlock(pctrl, true); - spin_unlock_irqrestore(&pctrl->lock, flags); + raw_spin_unlock_irqrestore(&pctrl->lock, flags); }; static int rzg2l_pinctrl_set_mux(struct pinctrl_dev *pctldev, @@ -882,10 +882,10 @@ static void rzg2l_rmw_pin_config(struct rzg2l_pinctrl *pctrl, u32 offset, addr += 4; } - spin_lock_irqsave(&pctrl->lock, flags); + raw_spin_lock_irqsave(&pctrl->lock, flags); reg = readl(addr) & ~(mask << (bit * 8)); writel(reg | (val << (bit * 8)), addr); - spin_unlock_irqrestore(&pctrl->lock, flags); + raw_spin_unlock_irqrestore(&pctrl->lock, flags); } static int rzg2l_caps_to_pwr_reg(const struct rzg2l_register_offsets *regs, u32 caps) @@ -1121,7 +1121,7 @@ static int rzg2l_write_oen(struct rzg2l_pinctrl *pctrl, unsigned int _pin, u8 oe if (bit < 0) return -EINVAL; - spin_lock_irqsave(&pctrl->lock, flags); + raw_spin_lock_irqsave(&pctrl->lock, flags); val = readb(pctrl->base + oen_offset); if (oen) val &= ~BIT(bit); @@ -1134,7 +1134,7 @@ static int rzg2l_write_oen(struct rzg2l_pinctrl *pctrl, unsigned int _pin, u8 oe writeb(val, pctrl->base + oen_offset); if (pctrl->data->hwcfg->oen_pwpr_lock) writeb(pwpr & ~PWPR_REGWE_B, pctrl->base + regs->pwpr); - spin_unlock_irqrestore(&pctrl->lock, flags); + raw_spin_unlock_irqrestore(&pctrl->lock, flags); return 0; } @@ -1687,14 +1687,14 @@ static int rzg2l_gpio_request(struct gpio_chip *chip, unsigned int offset) if (ret) return ret; - spin_lock_irqsave(&pctrl->lock, flags); + raw_spin_lock_irqsave(&pctrl->lock, flags); /* Select GPIO mode in PMC Register */ reg8 = readb(pctrl->base + PMC(off)); reg8 &= ~BIT(bit); pctrl->data->pmc_writeb(pctrl, reg8, PMC(off)); - spin_unlock_irqrestore(&pctrl->lock, flags); + raw_spin_unlock_irqrestore(&pctrl->lock, flags); return 0; } @@ -1709,7 +1709,7 @@ static void rzg2l_gpio_set_direction(struct rzg2l_pinctrl *pctrl, u32 offset, unsigned long flags; u16 reg16; - spin_lock_irqsave(&pctrl->lock, flags); + raw_spin_lock_irqsave(&pctrl->lock, flags); reg16 = readw(pctrl->base + PM(off)); reg16 &= ~(PM_MASK << (bit * 2)); @@ -1717,7 +1717,7 @@ static void rzg2l_gpio_set_direction(struct rzg2l_pinctrl *pctrl, u32 offset, reg16 |= (output ? PM_OUTPUT : PM_INPUT) << (bit * 2); writew(reg16, pctrl->base + PM(off)); - spin_unlock_irqrestore(&pctrl->lock, flags); + raw_spin_unlock_irqrestore(&pctrl->lock, flags); } static int rzg2l_gpio_get_direction(struct gpio_chip *chip, unsigned int offset) @@ -1761,7 +1761,7 @@ static int rzg2l_gpio_set(struct gpio_chip *chip, unsigned int offset, unsigned long flags; u8 reg8; - spin_lock_irqsave(&pctrl->lock, flags); + raw_spin_lock_irqsave(&pctrl->lock, flags); reg8 = readb(pctrl->base + P(off)); @@ -1770,7 +1770,7 @@ static int rzg2l_gpio_set(struct gpio_chip *chip, unsigned int offset, else writeb(reg8 & ~BIT(bit), pctrl->base + P(off)); - spin_unlock_irqrestore(&pctrl->lock, flags); + raw_spin_unlock_irqrestore(&pctrl->lock, flags); return 0; } @@ -2429,14 +2429,13 @@ static int rzg2l_gpio_get_gpioint(unsigned int virq, struct rzg2l_pinctrl *pctrl return gpioint; } -static void rzg2l_gpio_irq_endisable(struct rzg2l_pinctrl *pctrl, - unsigned int hwirq, bool enable) +static void __rzg2l_gpio_irq_endisable(struct rzg2l_pinctrl *pctrl, + unsigned int hwirq, bool enable) { const struct pinctrl_pin_desc *pin_desc = &pctrl->desc.pins[hwirq]; u64 *pin_data = pin_desc->drv_data; u32 off = RZG2L_PIN_CFG_TO_PORT_OFFSET(*pin_data); u8 bit = RZG2L_PIN_ID_TO_PIN(hwirq); - unsigned long flags; void __iomem *addr; addr = pctrl->base + ISEL(off); @@ -2445,12 +2444,20 @@ static void rzg2l_gpio_irq_endisable(struct rzg2l_pinctrl *pctrl, addr += 4; } - spin_lock_irqsave(&pctrl->lock, flags); if (enable) writel(readl(addr) | BIT(bit * 8), addr); else writel(readl(addr) & ~BIT(bit * 8), addr); - spin_unlock_irqrestore(&pctrl->lock, flags); +} + +static void rzg2l_gpio_irq_endisable(struct rzg2l_pinctrl *pctrl, + unsigned int hwirq, bool enable) +{ + unsigned long flags; + + raw_spin_lock_irqsave(&pctrl->lock, flags); + __rzg2l_gpio_irq_endisable(pctrl, hwirq, enable); + raw_spin_unlock_irqrestore(&pctrl->lock, flags); } static void rzg2l_gpio_irq_disable(struct irq_data *d) @@ -2462,15 +2469,25 @@ static void rzg2l_gpio_irq_disable(struct irq_data *d) gpiochip_disable_irq(gc, hwirq); } -static void rzg2l_gpio_irq_enable(struct irq_data *d) +static void __rzg2l_gpio_irq_enable(struct irq_data *d, bool lock) { struct gpio_chip *gc = irq_data_get_irq_chip_data(d); + struct rzg2l_pinctrl *pctrl = container_of(gc, struct rzg2l_pinctrl, gpio_chip); unsigned int hwirq = irqd_to_hwirq(d); gpiochip_enable_irq(gc, hwirq); + if (lock) + rzg2l_gpio_irq_endisable(pctrl, hwirq, true); + else + __rzg2l_gpio_irq_endisable(pctrl, hwirq, true); irq_chip_enable_parent(d); } +static void rzg2l_gpio_irq_enable(struct irq_data *d) +{ + __rzg2l_gpio_irq_enable(d, true); +} + static int rzg2l_gpio_irq_set_type(struct irq_data *d, unsigned int type) { return irq_chip_set_type_parent(d, type); @@ -2616,11 +2633,11 @@ static void rzg2l_gpio_irq_restore(struct rzg2l_pinctrl *pctrl) * This has to be atomically executed to protect against a concurrent * interrupt. */ - spin_lock_irqsave(&pctrl->lock, flags); + raw_spin_lock_irqsave(&pctrl->lock, flags); ret = rzg2l_gpio_irq_set_type(data, irqd_get_trigger_type(data)); if (!ret && !irqd_irq_disabled(data)) - rzg2l_gpio_irq_enable(data); - spin_unlock_irqrestore(&pctrl->lock, flags); + __rzg2l_gpio_irq_enable(data, false); + raw_spin_unlock_irqrestore(&pctrl->lock, flags); if (ret) dev_crit(pctrl->dev, "Failed to set IRQ type for virq=%u\n", virq); @@ -2950,7 +2967,7 @@ static int rzg2l_pinctrl_probe(struct platform_device *pdev) "failed to enable GPIO clk\n"); } - spin_lock_init(&pctrl->lock); + raw_spin_lock_init(&pctrl->lock); spin_lock_init(&pctrl->bitmap_lock); mutex_init(&pctrl->mutex); atomic_set(&pctrl->wakeup_path, 0); @@ -3093,7 +3110,7 @@ static void rzg2l_pinctrl_pm_setup_pfc(struct rzg2l_pinctrl *pctrl) u32 nports = pctrl->data->n_port_pins / RZG2L_PINS_PER_PORT; unsigned long flags; - spin_lock_irqsave(&pctrl->lock, flags); + raw_spin_lock_irqsave(&pctrl->lock, flags); pctrl->data->pwpr_pfc_lock_unlock(pctrl, false); /* Restore port registers. */ @@ -3138,7 +3155,7 @@ static void rzg2l_pinctrl_pm_setup_pfc(struct rzg2l_pinctrl *pctrl) } pctrl->data->pwpr_pfc_lock_unlock(pctrl, true); - spin_unlock_irqrestore(&pctrl->lock, flags); + raw_spin_unlock_irqrestore(&pctrl->lock, flags); } static int rzg2l_pinctrl_suspend_noirq(struct device *dev) @@ -3187,14 +3204,14 @@ static int rzg2l_pinctrl_resume_noirq(struct device *dev) writeb(cache->qspi, pctrl->base + QSPI); if (pctrl->data->hwcfg->oen_pwpr_lock) { - spin_lock_irqsave(&pctrl->lock, flags); + raw_spin_lock_irqsave(&pctrl->lock, flags); pwpr = readb(pctrl->base + regs->pwpr); writeb(pwpr | PWPR_REGWE_B, pctrl->base + regs->pwpr); } writeb(cache->oen, pctrl->base + pctrl->data->hwcfg->regs.oen); if (pctrl->data->hwcfg->oen_pwpr_lock) { writeb(pwpr & ~PWPR_REGWE_B, pctrl->base + regs->pwpr); - spin_unlock_irqrestore(&pctrl->lock, flags); + raw_spin_unlock_irqrestore(&pctrl->lock, flags); } for (u8 i = 0; i < 2; i++) { if (regs->sd_ch)

13 hours, 48 minutes

2
1
0 0

[PATCH RESEND v3 4/4] mm/hugetlb: fix excessive IPI broadcasts when unsharing PMD tables using mmu_gather

by David Hildenbrand (Red Hat)

As reported, ever since commit 1013af4f585f ("mm/hugetlb: fix huge_pmd_unshare() vs GUP-fast race") we can end up in some situations where we perform so many IPI broadcasts when unsharing hugetlb PMD page tables that it severely regresses some workloads. In particular, when we fork()+exit(), or when we munmap() a large area backed by many shared PMD tables, we perform one IPI broadcast per unshared PMD table. There are two optimizations to be had: (1) When we process (unshare) multiple such PMD tables, such as during exit(), it is sufficient to send a single IPI broadcast (as long as we respect locking rules) instead of one per PMD table. Locking prevents that any of these PMD tables could get reused before we drop the lock. (2) When we are not the last sharer (> 2 users including us), there is no need to send the IPI broadcast. The shared PMD tables cannot become exclusive (fully unshared) before an IPI will be broadcasted by the last sharer. Concurrent GUP-fast could walk into a PMD table just before we unshared it. It could then succeed in grabbing a page from the shared page table even after munmap() etc succeeded (and supressed an IPI). But there is not difference compared to GUP-fast just sleeping for a while after grabbing the page and re-enabling IRQs. Most importantly, GUP-fast will never walk into page tables that are no-longer shared, because the last sharer will issue an IPI broadcast. (if ever required, checking whether the PUD changed in GUP-fast after grabbing the page like we do in the PTE case could handle this) So let's rework PMD sharing TLB flushing + IPI sync to use the mmu_gather infrastructure so we can implement these optimizations and demystify the code at least a bit. Extend the mmu_gather infrastructure to be able to deal with our special hugetlb PMD table sharing implementation. To make initialization of the mmu_gather easier when working on a single VMA (in particular, when dealing with hugetlb), provide tlb_gather_mmu_vma(). We'll consolidate the handling for (full) unsharing of PMD tables in tlb_unshare_pmd_ptdesc() and tlb_flush_unshared_tables(), and track in "struct mmu_gather" whether we had (full) unsharing of PMD tables. Because locking is very special (concurrent unsharing+reuse must be prevented), we disallow deferring flushing to tlb_finish_mmu() and instead require an explicit earlier call to tlb_flush_unshared_tables(). From hugetlb code, we call huge_pmd_unshare_flush() where we make sure that the expected lock protecting us from concurrent unsharing+reuse is still held. Check with a VM_WARN_ON_ONCE() in tlb_finish_mmu() that tlb_flush_unshared_tables() was properly called earlier. Document it all properly. Notes about tlb_remove_table_sync_one() interaction with unsharing: There are two fairly tricky things: (1) tlb_remove_table_sync_one() is a NOP on architectures without CONFIG_MMU_GATHER_RCU_TABLE_FREE. Here, the assumption is that the previous TLB flush would send an IPI to all relevant CPUs. Careful: some architectures like x86 only send IPIs to all relevant CPUs when tlb->freed_tables is set. The relevant architectures should be selecting MMU_GATHER_RCU_TABLE_FREE, but x86 might not do that in stable kernels and it might have been problematic before this patch. Also, the arch flushing behavior (independent of IPIs) is different when tlb->freed_tables is set. Do we have to enlighten them to also take care of tlb->unshared_tables? So far we didn't care, so hopefully we are fine. Of course, we could be setting tlb->freed_tables as well, but that might then unnecessarily flush too much, because the semantics of tlb->freed_tables are a bit fuzzy. This patch changes nothing in this regard. (2) tlb_remove_table_sync_one() is not a NOP on architectures with CONFIG_MMU_GATHER_RCU_TABLE_FREE that actually don't need a sync. Take x86 as an example: in the common case (!pv, !X86_FEATURE_INVLPGB) we still issue IPIs during TLB flushes and don't actually need the second tlb_remove_table_sync_one(). This optimized can be implemented on top of this, by checking e.g., in tlb_remove_table_sync_one() whether we really need IPIs. But as described in (1), it really must honor tlb->freed_tables then to send IPIs to all relevant CPUs. Notes on TLB flushing changes: (1) Flushing for non-shared PMD tables We're converting from flush_hugetlb_tlb_range() to tlb_remove_huge_tlb_entry(). Given that we properly initialize the MMU gather in tlb_gather_mmu_vma() to be hugetlb aware, similar to __unmap_hugepage_range(), that should be fine. (2) Flushing for shared PMD tables We're converting from various things (flush_hugetlb_tlb_range(), tlb_flush_pmd_range(), flush_tlb_range()) to tlb_flush_pmd_range(). tlb_flush_pmd_range() achieves the same that tlb_remove_huge_tlb_entry() would achieve in these scenarios. Note that tlb_remove_huge_tlb_entry() also calls __tlb_remove_tlb_entry(), however that is only implemented on powerpc, which does not support PMD table sharing. Similar to (1), tlb_gather_mmu_vma() should make sure that TLB flushing keeps on working as expected. Further, note that the ptdesc_pmd_pts_dec() in huge_pmd_share() is not a concern, as we are holding the i_mmap_lock the whole time, preventing concurrent unsharing. That ptdesc_pmd_pts_dec() usage will be removed separately as a cleanup later. There are plenty more cleanups to be had, but they have to wait until this is fixed. Fixes: 1013af4f585f ("mm/hugetlb: fix huge_pmd_unshare() vs GUP-fast race") Reported-by: Uschakow, Stanislav" <suschako(a)amazon.de> Closes: https://lore.kernel.org/all/4d3878531c76479d9f8ca9789dc6485d@amazon.de/ Tested-by: Laurence Oberman <loberman(a)redhat.com> Cc: <stable(a)vger.kernel.org> Signed-off-by: David Hildenbrand (Red Hat) <david(a)kernel.org> --- include/asm-generic/tlb.h | 77 +++++++++++++++++++++++- include/linux/hugetlb.h | 15 +++-- include/linux/mm_types.h | 1 + mm/hugetlb.c | 123 ++++++++++++++++++++++---------------- mm/mmu_gather.c | 33 ++++++++++ mm/rmap.c | 25 +++++--- 6 files changed, 208 insertions(+), 66 deletions(-) diff --git a/include/asm-generic/tlb.h b/include/asm-generic/tlb.h index 1fff717cae510..4d679d2a206b4 100644 --- a/include/asm-generic/tlb.h +++ b/include/asm-generic/tlb.h @@ -46,7 +46,8 @@ * * The mmu_gather API consists of: * - * - tlb_gather_mmu() / tlb_gather_mmu_fullmm() / tlb_finish_mmu() + * - tlb_gather_mmu() / tlb_gather_mmu_fullmm() / tlb_gather_mmu_vma() / + * tlb_finish_mmu() * * start and finish a mmu_gather * @@ -364,6 +365,20 @@ struct mmu_gather { unsigned int vma_huge : 1; unsigned int vma_pfn : 1; + /* + * Did we unshare (unmap) any shared page tables? For now only + * used for hugetlb PMD table sharing. + */ + unsigned int unshared_tables : 1; + + /* + * Did we unshare any page tables such that they are now exclusive + * and could get reused+modified by the new owner? When setting this + * flag, "unshared_tables" will be set as well. For now only used + * for hugetlb PMD table sharing. + */ + unsigned int fully_unshared_tables : 1; + unsigned int batch_count; #ifndef CONFIG_MMU_GATHER_NO_GATHER @@ -400,6 +415,7 @@ static inline void __tlb_reset_range(struct mmu_gather *tlb) tlb->cleared_pmds = 0; tlb->cleared_puds = 0; tlb->cleared_p4ds = 0; + tlb->unshared_tables = 0; /* * Do not reset mmu_gather::vma_* fields here, we do not * call into tlb_start_vma() again to set them if there is an @@ -484,7 +500,7 @@ static inline void tlb_flush_mmu_tlbonly(struct mmu_gather *tlb) * these bits. */ if (!(tlb->freed_tables || tlb->cleared_ptes || tlb->cleared_pmds || - tlb->cleared_puds || tlb->cleared_p4ds)) + tlb->cleared_puds || tlb->cleared_p4ds || tlb->unshared_tables)) return; tlb_flush(tlb); @@ -773,6 +789,63 @@ static inline bool huge_pmd_needs_flush(pmd_t oldpmd, pmd_t newpmd) } #endif +#ifdef CONFIG_HUGETLB_PMD_PAGE_TABLE_SHARING +static inline void tlb_unshare_pmd_ptdesc(struct mmu_gather *tlb, struct ptdesc *pt, + unsigned long addr) +{ + /* + * The caller must make sure that concurrent unsharing + exclusive + * reuse is impossible until tlb_flush_unshared_tables() was called. + */ + VM_WARN_ON_ONCE(!ptdesc_pmd_is_shared(pt)); + ptdesc_pmd_pts_dec(pt); + + /* Clearing a PUD pointing at a PMD table with PMD leaves. */ + tlb_flush_pmd_range(tlb, addr & PUD_MASK, PUD_SIZE); + + /* + * If the page table is now exclusively owned, we fully unshared + * a page table. + */ + if (!ptdesc_pmd_is_shared(pt)) + tlb->fully_unshared_tables = true; + tlb->unshared_tables = true; +} + +static inline void tlb_flush_unshared_tables(struct mmu_gather *tlb) +{ + /* + * As soon as the caller drops locks to allow for reuse of + * previously-shared tables, these tables could get modified and + * even reused outside of hugetlb context, so we have to make sure that + * any page table walkers (incl. TLB, GUP-fast) are aware of that + * change. + * + * Even if we are not fully unsharing a PMD table, we must + * flush the TLB for the unsharer now. + */ + if (tlb->unshared_tables) + tlb_flush_mmu_tlbonly(tlb); + + /* + * Similarly, we must make sure that concurrent GUP-fast will not + * walk previously-shared page tables that are getting modified+reused + * elsewhere. So broadcast an IPI to wait for any concurrent GUP-fast. + * + * We only perform this when we are the last sharer of a page table, + * as the IPI will reach all CPUs: any GUP-fast. + * + * Note that on configs where tlb_remove_table_sync_one() is a NOP, + * the expectation is that the tlb_flush_mmu_tlbonly() would have issued + * required IPIs already for us. + */ + if (tlb->fully_unshared_tables) { + tlb_remove_table_sync_one(); + tlb->fully_unshared_tables = false; + } +} +#endif /* CONFIG_HUGETLB_PMD_PAGE_TABLE_SHARING */ + #endif /* CONFIG_MMU */ #endif /* _ASM_GENERIC__TLB_H */ diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 03c8725efa289..e51b8ef0cebd9 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -240,8 +240,9 @@ pte_t *huge_pte_alloc(struct mm_struct *mm, struct vm_area_struct *vma, pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr, unsigned long sz); unsigned long hugetlb_mask_last_page(struct hstate *h); -int huge_pmd_unshare(struct mm_struct *mm, struct vm_area_struct *vma, - unsigned long addr, pte_t *ptep); +int huge_pmd_unshare(struct mmu_gather *tlb, struct vm_area_struct *vma, + unsigned long addr, pte_t *ptep); +void huge_pmd_unshare_flush(struct mmu_gather *tlb, struct vm_area_struct *vma); void adjust_range_if_pmd_sharing_possible(struct vm_area_struct *vma, unsigned long *start, unsigned long *end); @@ -300,13 +301,17 @@ static inline struct address_space *hugetlb_folio_mapping_lock_write( return NULL; } -static inline int huge_pmd_unshare(struct mm_struct *mm, - struct vm_area_struct *vma, - unsigned long addr, pte_t *ptep) +static inline int huge_pmd_unshare(struct mmu_gather *tlb, + struct vm_area_struct *vma, unsigned long addr, pte_t *ptep) { return 0; } +static inline void huge_pmd_unshare_flush(struct mmu_gather *tlb, + struct vm_area_struct *vma) +{ +} + static inline void adjust_range_if_pmd_sharing_possible( struct vm_area_struct *vma, unsigned long *start, unsigned long *end) diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 42af2292951d4..d1053b2c1f800 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -1522,6 +1522,7 @@ static inline unsigned int mm_cid_size(void) struct mmu_gather; extern void tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm); extern void tlb_gather_mmu_fullmm(struct mmu_gather *tlb, struct mm_struct *mm); +void tlb_gather_mmu_vma(struct mmu_gather *tlb, struct vm_area_struct *vma); extern void tlb_finish_mmu(struct mmu_gather *tlb); struct vm_fault; diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 3c77cdef12a32..2609b6d58f99e 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -5096,7 +5096,7 @@ int move_hugetlb_page_tables(struct vm_area_struct *vma, unsigned long last_addr_mask; pte_t *src_pte, *dst_pte; struct mmu_notifier_range range; - bool shared_pmd = false; + struct mmu_gather tlb; mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, mm, old_addr, old_end); @@ -5106,6 +5106,7 @@ int move_hugetlb_page_tables(struct vm_area_struct *vma, * range. */ flush_cache_range(vma, range.start, range.end); + tlb_gather_mmu_vma(&tlb, vma); mmu_notifier_invalidate_range_start(&range); last_addr_mask = hugetlb_mask_last_page(h); @@ -5122,8 +5123,7 @@ int move_hugetlb_page_tables(struct vm_area_struct *vma, if (huge_pte_none(huge_ptep_get(mm, old_addr, src_pte))) continue; - if (huge_pmd_unshare(mm, vma, old_addr, src_pte)) { - shared_pmd = true; + if (huge_pmd_unshare(&tlb, vma, old_addr, src_pte)) { old_addr |= last_addr_mask; new_addr |= last_addr_mask; continue; @@ -5134,15 +5134,16 @@ int move_hugetlb_page_tables(struct vm_area_struct *vma, break; move_huge_pte(vma, old_addr, new_addr, src_pte, dst_pte, sz); + tlb_remove_huge_tlb_entry(h, &tlb, src_pte, old_addr); } - if (shared_pmd) - flush_hugetlb_tlb_range(vma, range.start, range.end); - else - flush_hugetlb_tlb_range(vma, old_end - len, old_end); + tlb_flush_mmu_tlbonly(&tlb); + huge_pmd_unshare_flush(&tlb, vma); + mmu_notifier_invalidate_range_end(&range); i_mmap_unlock_write(mapping); hugetlb_vma_unlock_write(vma); + tlb_finish_mmu(&tlb); return len + old_addr - old_end; } @@ -5161,7 +5162,6 @@ void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma, unsigned long sz = huge_page_size(h); bool adjust_reservation; unsigned long last_addr_mask; - bool force_flush = false; WARN_ON(!is_vm_hugetlb_page(vma)); BUG_ON(start & ~huge_page_mask(h)); @@ -5184,10 +5184,8 @@ void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma, } ptl = huge_pte_lock(h, mm, ptep); - if (huge_pmd_unshare(mm, vma, address, ptep)) { + if (huge_pmd_unshare(tlb, vma, address, ptep)) { spin_unlock(ptl); - tlb_flush_pmd_range(tlb, address & PUD_MASK, PUD_SIZE); - force_flush = true; address |= last_addr_mask; continue; } @@ -5303,14 +5301,7 @@ void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma, } tlb_end_vma(tlb, vma); - /* - * There is nothing protecting a previously-shared page table that we - * unshared through huge_pmd_unshare() from getting freed after we - * release i_mmap_rwsem, so flush the TLB now. If huge_pmd_unshare() - * succeeded, flush the range corresponding to the pud. - */ - if (force_flush) - tlb_flush_mmu_tlbonly(tlb); + huge_pmd_unshare_flush(tlb, vma); } void __hugetlb_zap_begin(struct vm_area_struct *vma, @@ -6409,11 +6400,11 @@ long hugetlb_change_protection(struct vm_area_struct *vma, pte_t pte; struct hstate *h = hstate_vma(vma); long pages = 0, psize = huge_page_size(h); - bool shared_pmd = false; struct mmu_notifier_range range; unsigned long last_addr_mask; bool uffd_wp = cp_flags & MM_CP_UFFD_WP; bool uffd_wp_resolve = cp_flags & MM_CP_UFFD_WP_RESOLVE; + struct mmu_gather tlb; /* * In the case of shared PMDs, the area to flush could be beyond @@ -6426,6 +6417,7 @@ long hugetlb_change_protection(struct vm_area_struct *vma, BUG_ON(address >= end); flush_cache_range(vma, range.start, range.end); + tlb_gather_mmu_vma(&tlb, vma); mmu_notifier_invalidate_range_start(&range); hugetlb_vma_lock_write(vma); @@ -6452,7 +6444,7 @@ long hugetlb_change_protection(struct vm_area_struct *vma, } } ptl = huge_pte_lock(h, mm, ptep); - if (huge_pmd_unshare(mm, vma, address, ptep)) { + if (huge_pmd_unshare(&tlb, vma, address, ptep)) { /* * When uffd-wp is enabled on the vma, unshare * shouldn't happen at all. Warn about it if it @@ -6461,7 +6453,6 @@ long hugetlb_change_protection(struct vm_area_struct *vma, WARN_ON_ONCE(uffd_wp || uffd_wp_resolve); pages++; spin_unlock(ptl); - shared_pmd = true; address |= last_addr_mask; continue; } @@ -6522,22 +6513,16 @@ long hugetlb_change_protection(struct vm_area_struct *vma, pte = huge_pte_clear_uffd_wp(pte); huge_ptep_modify_prot_commit(vma, address, ptep, old_pte, pte); pages++; + tlb_remove_huge_tlb_entry(h, &tlb, ptep, address); } next: spin_unlock(ptl); cond_resched(); } - /* - * There is nothing protecting a previously-shared page table that we - * unshared through huge_pmd_unshare() from getting freed after we - * release i_mmap_rwsem, so flush the TLB now. If huge_pmd_unshare() - * succeeded, flush the range corresponding to the pud. - */ - if (shared_pmd) - flush_hugetlb_tlb_range(vma, range.start, range.end); - else - flush_hugetlb_tlb_range(vma, start, end); + + tlb_flush_mmu_tlbonly(&tlb); + huge_pmd_unshare_flush(&tlb, vma); /* * No need to call mmu_notifier_arch_invalidate_secondary_tlbs() we are * downgrading page table protection not changing it to point to a new @@ -6548,6 +6533,7 @@ long hugetlb_change_protection(struct vm_area_struct *vma, i_mmap_unlock_write(vma->vm_file->f_mapping); hugetlb_vma_unlock_write(vma); mmu_notifier_invalidate_range_end(&range); + tlb_finish_mmu(&tlb); return pages > 0 ? (pages << h->order) : pages; } @@ -6904,18 +6890,27 @@ pte_t *huge_pmd_share(struct mm_struct *mm, struct vm_area_struct *vma, return pte; } -/* - * unmap huge page backed by shared pte. +/** + * huge_pmd_unshare - Unmap a pmd table if it is shared by multiple users + * @tlb: the current mmu_gather. + * @vma: the vma covering the pmd table. + * @addr: the address we are trying to unshare. + * @ptep: pointer into the (pmd) page table. + * + * Called with the page table lock held, the i_mmap_rwsem held in write mode + * and the hugetlb vma lock held in write mode. * - * Called with page table lock held. + * Note: The caller must call huge_pmd_unshare_flush() before dropping the + * i_mmap_rwsem. * - * returns: 1 successfully unmapped a shared pte page - * 0 the underlying pte page is not shared, or it is the last user + * Returns: 1 if it was a shared PMD table and it got unmapped, or 0 if it + * was not a shared PMD table. */ -int huge_pmd_unshare(struct mm_struct *mm, struct vm_area_struct *vma, - unsigned long addr, pte_t *ptep) +int huge_pmd_unshare(struct mmu_gather *tlb, struct vm_area_struct *vma, + unsigned long addr, pte_t *ptep) { unsigned long sz = huge_page_size(hstate_vma(vma)); + struct mm_struct *mm = vma->vm_mm; pgd_t *pgd = pgd_offset(mm, addr); p4d_t *p4d = p4d_offset(pgd, addr); pud_t *pud = pud_offset(p4d, addr); @@ -6927,18 +6922,36 @@ int huge_pmd_unshare(struct mm_struct *mm, struct vm_area_struct *vma, i_mmap_assert_write_locked(vma->vm_file->f_mapping); hugetlb_vma_assert_locked(vma); pud_clear(pud); - /* - * Once our caller drops the rmap lock, some other process might be - * using this page table as a normal, non-hugetlb page table. - * Wait for pending gup_fast() in other threads to finish before letting - * that happen. - */ - tlb_remove_table_sync_one(); - ptdesc_pmd_pts_dec(virt_to_ptdesc(ptep)); + + tlb_unshare_pmd_ptdesc(tlb, virt_to_ptdesc(ptep), addr); + mm_dec_nr_pmds(mm); return 1; } +/* + * huge_pmd_unshare_flush - Complete a sequence of huge_pmd_unshare() calls + * @tlb: the current mmu_gather. + * @vma: the vma covering the pmd table. + * + * Perform necessary TLB flushes or IPI broadcasts to synchronize PMD table + * unsharing with concurrent page table walkers. + * + * This function must be called after a sequence of huge_pmd_unshare() + * calls while still holding the i_mmap_rwsem. + */ +void huge_pmd_unshare_flush(struct mmu_gather *tlb, struct vm_area_struct *vma) +{ + /* + * We must synchronize page table unsharing such that nobody will + * try reusing a previously-shared page table while it might still + * be in use by previous sharers (TLB, GUP_fast). + */ + i_mmap_assert_write_locked(vma->vm_file->f_mapping); + + tlb_flush_unshared_tables(tlb); +} + #else /* !CONFIG_HUGETLB_PMD_PAGE_TABLE_SHARING */ pte_t *huge_pmd_share(struct mm_struct *mm, struct vm_area_struct *vma, @@ -6947,12 +6960,16 @@ pte_t *huge_pmd_share(struct mm_struct *mm, struct vm_area_struct *vma, return NULL; } -int huge_pmd_unshare(struct mm_struct *mm, struct vm_area_struct *vma, - unsigned long addr, pte_t *ptep) +int huge_pmd_unshare(struct mmu_gather *tlb, struct vm_area_struct *vma, + unsigned long addr, pte_t *ptep) { return 0; } +void huge_pmd_unshare_flush(struct mmu_gather *tlb, struct vm_area_struct *vma) +{ +} + void adjust_range_if_pmd_sharing_possible(struct vm_area_struct *vma, unsigned long *start, unsigned long *end) { @@ -7219,6 +7236,7 @@ static void hugetlb_unshare_pmds(struct vm_area_struct *vma, unsigned long sz = huge_page_size(h); struct mm_struct *mm = vma->vm_mm; struct mmu_notifier_range range; + struct mmu_gather tlb; unsigned long address; spinlock_t *ptl; pte_t *ptep; @@ -7230,6 +7248,8 @@ static void hugetlb_unshare_pmds(struct vm_area_struct *vma, return; flush_cache_range(vma, start, end); + tlb_gather_mmu_vma(&tlb, vma); + /* * No need to call adjust_range_if_pmd_sharing_possible(), because * we have already done the PUD_SIZE alignment. @@ -7248,10 +7268,10 @@ static void hugetlb_unshare_pmds(struct vm_area_struct *vma, if (!ptep) continue; ptl = huge_pte_lock(h, mm, ptep); - huge_pmd_unshare(mm, vma, address, ptep); + huge_pmd_unshare(&tlb, vma, address, ptep); spin_unlock(ptl); } - flush_hugetlb_tlb_range(vma, start, end); + huge_pmd_unshare_flush(&tlb, vma); if (take_locks) { i_mmap_unlock_write(vma->vm_file->f_mapping); hugetlb_vma_unlock_write(vma); @@ -7261,6 +7281,7 @@ static void hugetlb_unshare_pmds(struct vm_area_struct *vma, * Documentation/mm/mmu_notifier.rst. */ mmu_notifier_invalidate_range_end(&range); + tlb_finish_mmu(&tlb); } /* diff --git a/mm/mmu_gather.c b/mm/mmu_gather.c index 247e3f9db6c7a..cd32c2dbf501b 100644 --- a/mm/mmu_gather.c +++ b/mm/mmu_gather.c @@ -10,6 +10,7 @@ #include <linux/swap.h> #include <linux/rmap.h> #include <linux/pgalloc.h> +#include <linux/hugetlb.h> #include <asm/tlb.h> @@ -426,6 +427,7 @@ static void __tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, #endif tlb->vma_pfn = 0; + tlb->fully_unshared_tables = 0; __tlb_reset_range(tlb); inc_tlb_flush_pending(tlb->mm); } @@ -459,6 +461,31 @@ void tlb_gather_mmu_fullmm(struct mmu_gather *tlb, struct mm_struct *mm) __tlb_gather_mmu(tlb, mm, true); } +/** + * tlb_gather_mmu - initialize an mmu_gather structure for operating on a single + * VMA + * @tlb: the mmu_gather structure to initialize + * @vma: the vm_area_struct + * + * Called to initialize an (on-stack) mmu_gather structure for operating on + * a single VMA. In contrast to tlb_gather_mmu(), calling this function will + * not require another call to tlb_start_vma(). In contrast to tlb_start_vma(), + * this function will *not* call flush_cache_range(). + * + * For hugetlb VMAs, this function will also initialize the mmu_gather + * page_size accordingly, not requiring a separate call to + * tlb_change_page_size(). + * + */ +void tlb_gather_mmu_vma(struct mmu_gather *tlb, struct vm_area_struct *vma) +{ + tlb_gather_mmu(tlb, vma->vm_mm); + tlb_update_vma_flags(tlb, vma); + if (is_vm_hugetlb_page(vma)) + /* All entries have the same size. */ + tlb_change_page_size(tlb, huge_page_size(hstate_vma(vma))); +} + /** * tlb_finish_mmu - finish an mmu_gather structure * @tlb: the mmu_gather structure to finish @@ -468,6 +495,12 @@ void tlb_gather_mmu_fullmm(struct mmu_gather *tlb, struct mm_struct *mm) */ void tlb_finish_mmu(struct mmu_gather *tlb) { + /* + * We expect an earlier huge_pmd_unshare_flush() call to sort this out, + * due to complicated locking requirements with page table unsharing. + */ + VM_WARN_ON_ONCE(tlb->fully_unshared_tables); + /* * If there are parallel threads are doing PTE changes on same range * under non-exclusive lock (e.g., mmap_lock read-side) but defer TLB diff --git a/mm/rmap.c b/mm/rmap.c index 748f48727a162..7b9879ef442d9 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -76,7 +76,7 @@ #include <linux/mm_inline.h> #include <linux/oom.h> -#include <asm/tlbflush.h> +#include <asm/tlb.h> #define CREATE_TRACE_POINTS #include <trace/events/migrate.h> @@ -2008,13 +2008,17 @@ static bool try_to_unmap_one(struct folio *folio, struct vm_area_struct *vma, * if unsuccessful. */ if (!anon) { + struct mmu_gather tlb; + VM_BUG_ON(!(flags & TTU_RMAP_LOCKED)); if (!hugetlb_vma_trylock_write(vma)) goto walk_abort; - if (huge_pmd_unshare(mm, vma, address, pvmw.pte)) { + + tlb_gather_mmu_vma(&tlb, vma); + if (huge_pmd_unshare(&tlb, vma, address, pvmw.pte)) { hugetlb_vma_unlock_write(vma); - flush_tlb_range(vma, - range.start, range.end); + huge_pmd_unshare_flush(&tlb, vma); + tlb_finish_mmu(&tlb); /* * The PMD table was unmapped, * consequently unmapping the folio. @@ -2022,6 +2026,7 @@ static bool try_to_unmap_one(struct folio *folio, struct vm_area_struct *vma, goto walk_done; } hugetlb_vma_unlock_write(vma); + tlb_finish_mmu(&tlb); } pteval = huge_ptep_clear_flush(vma, address, pvmw.pte); if (pte_dirty(pteval)) @@ -2398,17 +2403,20 @@ static bool try_to_migrate_one(struct folio *folio, struct vm_area_struct *vma, * fail if unsuccessful. */ if (!anon) { + struct mmu_gather tlb; + VM_BUG_ON(!(flags & TTU_RMAP_LOCKED)); if (!hugetlb_vma_trylock_write(vma)) { page_vma_mapped_walk_done(&pvmw); ret = false; break; } - if (huge_pmd_unshare(mm, vma, address, pvmw.pte)) { - hugetlb_vma_unlock_write(vma); - flush_tlb_range(vma, - range.start, range.end); + tlb_gather_mmu_vma(&tlb, vma); + if (huge_pmd_unshare(&tlb, vma, address, pvmw.pte)) { + hugetlb_vma_unlock_write(vma); + huge_pmd_unshare_flush(&tlb, vma); + tlb_finish_mmu(&tlb); /* * The PMD table was unmapped, * consequently unmapping the folio. @@ -2417,6 +2425,7 @@ static bool try_to_migrate_one(struct folio *folio, struct vm_area_struct *vma, break; } hugetlb_vma_unlock_write(vma); + tlb_finish_mmu(&tlb); } /* Nuke the hugetlb page table entry */ pteval = huge_ptep_clear_flush(vma, address, pvmw.pte); -- 2.52.0

13 hours, 50 minutes

2
3
0 0

[PATCH 5.10,5.15,6.1,6.6] leds: spi-byte: Initialize device node before access

by Tiffany Yang

Commit 7f9ab862e05c ("leds: spi-byte: Call of_node_put() on error path") was merged in 6.11 and then backported to stable trees through 5.10. It relocates the line that initializes the variable 'child' to a later point in spi_byte_probe(). Versions < 6.9 do not have commit ccc35ff2fd29 ("leds: spi-byte: Use devm_led_classdev_register_ext()"), which removes a line that reads a property from 'child' before its new initialization point. Consequently, spi_byte_probe() reads from an uninitialized device node in stable kernels 6.6-5.10. Initialize 'child' before it is first accessed. Fixes: 7f9ab862e05c ("leds: spi-byte: Call of_node_put() on error path") Signed-off-by: Tiffany Yang <ynaffit(a)google.com> --- As an alternative to moving the initialization of 'child' up, Fedor Pchelkin proposed [1] backporting the change that removes the intermediate access. [1] https://lore.kernel.org/stable/20241029204128.527033-1-pchelkin@ispras.ru/ --- drivers/leds/leds-spi-byte.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/leds/leds-spi-byte.c b/drivers/leds/leds-spi-byte.c index afe9bff7c7c1..4520df1e2341 100644 --- a/drivers/leds/leds-spi-byte.c +++ b/drivers/leds/leds-spi-byte.c @@ -96,6 +96,7 @@ static int spi_byte_probe(struct spi_device *spi) if (!led) return -ENOMEM; + child = of_get_next_available_child(dev_of_node(dev), NULL); of_property_read_string(child, "label", &name); strscpy(led->name, name, sizeof(led->name)); led->spi = spi; @@ -106,7 +107,6 @@ static int spi_byte_probe(struct spi_device *spi) led->ldev.max_brightness = led->cdef->max_value - led->cdef->off_value; led->ldev.brightness_set_blocking = spi_byte_brightness_set_blocking; - child = of_get_next_available_child(dev_of_node(dev), NULL); state = of_get_property(child, "default-state", NULL); if (state) { if (!strcmp(state, "on")) { -- 2.52.0.351.gbe84eed79e-goog

14 hours, 29 minutes

1
0
0 0

+ x86-kexec-add-a-sanity-check-on-previous-kernels-ima-kexec-buffer.patch added to mm-nonmm-unstable branch

by Andrew Morton

The patch titled Subject: x86/kexec: add a sanity check on previous kernel's ima kexec buffer has been added to the -mm mm-nonmm-unstable branch. Its filename is x86-kexec-add-a-sanity-check-on-previous-kernels-ima-kexec-buffer.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-nonmm-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 various branches at git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm and is updated there most days ------------------------------------------------------ From: Harshit Mogalapalli <harshit.m.mogalapalli(a)oracle.com> Subject: x86/kexec: add a sanity check on previous kernel's ima kexec buffer Date: Mon, 29 Dec 2025 00:15:23 -0800 When the second-stage kernel is booted via kexec with a limiting command line such as "mem=<size>", the physical range that contains the carried over IMA measurement list may fall outside the truncated RAM leading to a kernel panic. BUG: unable to handle page fault for address: ffff97793ff47000 RIP: ima_restore_measurement_list+0xdc/0x45a #PF: error_code(0x0000) �� not-present page Other architectures already validate the range with page_is_ram(), as done in commit cbf9c4b9617b ("of: check previous kernel's ima-kexec-buffer against memory bounds") do a similar check on x86. Without carrying the measurement list across kexec, the attestation would fail. Link: https://lkml.kernel.org/r/20251229081523.622515-4-harshit.m.mogalapalli@ora… Fixes: b69a2afd5afc ("x86/kexec: Carry forward IMA measurement log on kexec") Signed-off-by: Harshit Mogalapalli <harshit.m.mogalapalli(a)oracle.com> Reported-by: Paul Webb <paul.x.webb(a)oracle.com> Cc: Alexander Graf <graf(a)amazon.com> Cc: Ard Biesheuvel <ardb(a)kernel.org> Cc: Borislav Betkov <bp(a)alien8.de> Cc: guoweikang <guoweikang.kernel(a)gmail.com> Cc: Henry Willard <henry.willard(a)oracle.com> Cc: "H. Peter Anvin" <hpa(a)zytor.com> Cc: Ingo Molnar <mingo(a)redhat.com> Cc: Jiri Bohac <jbohac(a)suse.cz> Cc: Joel Granados <joel.granados(a)kernel.org> Cc: Jonathan McDowell <noodles(a)fb.com> Cc: Mike Rapoport <rppt(a)kernel.org> Cc: Mimi Zohar <zohar(a)linux.ibm.com> Cc: Sohil Mehta <sohil.mehta(a)intel.com> Cc: Sourabh Jain <sourabhjain(a)linux.ibm.com> Cc: Thomas Gleinxer <tglx(a)linutronix.de> Cc: Yifei Liu <yifei.l.liu(a)oracle.com> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- arch/x86/kernel/setup.c | 6 ++++++ 1 file changed, 6 insertions(+) --- a/arch/x86/kernel/setup.c~x86-kexec-add-a-sanity-check-on-previous-kernels-ima-kexec-buffer +++ a/arch/x86/kernel/setup.c @@ -439,9 +439,15 @@ int __init ima_free_kexec_buffer(void) int __init ima_get_kexec_buffer(void **addr, size_t *size) { + int ret; + if (!ima_kexec_buffer_size) return -ENOENT; + ret = ima_validate_range(ima_kexec_buffer_phys, ima_kexec_buffer_size); + if (ret) + return ret; + *addr = __va(ima_kexec_buffer_phys); *size = ima_kexec_buffer_size; _ Patches currently in -mm which might be from harshit.m.mogalapalli(a)oracle.com are ima-add-ima_validate_range-for-previous-kernel-ima-buffer.patch of-kexec-refactor-ima_get_kexec_buffer-to-use-ima_validate_range.patch x86-kexec-add-a-sanity-check-on-previous-kernels-ima-kexec-buffer.patch

15 hours, 9 minutes

1
0
0 0

+ of-kexec-refactor-ima_get_kexec_buffer-to-use-ima_validate_range.patch added to mm-nonmm-unstable branch

by Andrew Morton

The patch titled Subject: of/kexec: refactor ima_get_kexec_buffer() to use ima_validate_range() has been added to the -mm mm-nonmm-unstable branch. Its filename is of-kexec-refactor-ima_get_kexec_buffer-to-use-ima_validate_range.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-nonmm-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 various branches at git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm and is updated there most days ------------------------------------------------------ From: Harshit Mogalapalli <harshit.m.mogalapalli(a)oracle.com> Subject: of/kexec: refactor ima_get_kexec_buffer() to use ima_validate_range() Date: Mon, 29 Dec 2025 00:15:22 -0800 Refactor the OF/DT ima_get_kexec_buffer() to use a generic helper to validate the address range. No functional change intended. Link: https://lkml.kernel.org/r/20251229081523.622515-3-harshit.m.mogalapalli@ora… Fixes: b69a2afd5afc ("x86/kexec: Carry forward IMA measurement log on kexec") Signed-off-by: Harshit Mogalapalli <harshit.m.mogalapalli(a)oracle.com> Cc: Alexander Graf <graf(a)amazon.com> Cc: Ard Biesheuvel <ardb(a)kernel.org> Cc: Borislav Betkov <bp(a)alien8.de> Cc: guoweikang <guoweikang.kernel(a)gmail.com> Cc: Henry Willard <henry.willard(a)oracle.com> Cc: "H. Peter Anvin" <hpa(a)zytor.com> Cc: Ingo Molnar <mingo(a)redhat.com> Cc: Jiri Bohac <jbohac(a)suse.cz> Cc: Joel Granados <joel.granados(a)kernel.org> Cc: Jonathan McDowell <noodles(a)fb.com> Cc: Mike Rapoport <rppt(a)kernel.org> Cc: Mimi Zohar <zohar(a)linux.ibm.com> Cc: Paul Webb <paul.x.webb(a)oracle.com> Cc: Sohil Mehta <sohil.mehta(a)intel.com> Cc: Sourabh Jain <sourabhjain(a)linux.ibm.com> Cc: Thomas Gleinxer <tglx(a)linutronix.de> Cc: Yifei Liu <yifei.l.liu(a)oracle.com> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- drivers/of/kexec.c | 15 +++------------ 1 file changed, 3 insertions(+), 12 deletions(-) --- a/drivers/of/kexec.c~of-kexec-refactor-ima_get_kexec_buffer-to-use-ima_validate_range +++ a/drivers/of/kexec.c @@ -128,7 +128,6 @@ int __init ima_get_kexec_buffer(void **a { int ret, len; unsigned long tmp_addr; - unsigned long start_pfn, end_pfn; size_t tmp_size; const void *prop; @@ -144,17 +143,9 @@ int __init ima_get_kexec_buffer(void **a if (!tmp_size) return -ENOENT; - /* - * Calculate the PFNs for the buffer and ensure - * they are with in addressable memory. - */ - start_pfn = PHYS_PFN(tmp_addr); - end_pfn = PHYS_PFN(tmp_addr + tmp_size - 1); - if (!page_is_ram(start_pfn) || !page_is_ram(end_pfn)) { - pr_warn("IMA buffer at 0x%lx, size = 0x%zx beyond memory\n", - tmp_addr, tmp_size); - return -EINVAL; - } + ret = ima_validate_range(tmp_addr, tmp_size); + if (ret) + return ret; *addr = __va(tmp_addr); *size = tmp_size; _ Patches currently in -mm which might be from harshit.m.mogalapalli(a)oracle.com are ima-add-ima_validate_range-for-previous-kernel-ima-buffer.patch of-kexec-refactor-ima_get_kexec_buffer-to-use-ima_validate_range.patch x86-kexec-add-a-sanity-check-on-previous-kernels-ima-kexec-buffer.patch

15 hours, 9 minutes

1
0
0 0

+ ima-add-ima_validate_range-for-previous-kernel-ima-buffer.patch added to mm-nonmm-unstable branch

by Andrew Morton

The patch titled Subject: ima: add ima_validate_range() for previous kernel IMA buffer has been added to the -mm mm-nonmm-unstable branch. Its filename is ima-add-ima_validate_range-for-previous-kernel-ima-buffer.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-nonmm-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 various branches at git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm and is updated there most days ------------------------------------------------------ From: Harshit Mogalapalli <harshit.m.mogalapalli(a)oracle.com> Subject: ima: add ima_validate_range() for previous kernel IMA buffer Date: Mon, 29 Dec 2025 00:15:21 -0800 Patch series "Address page fault in ima_restore_measurement_list()", v2. When the second-stage kernel is booted via kexec with a limiting command line such as "mem=<size>" we observe a pafe fault that happens. BUG: unable to handle page fault for address: ffff97793ff47000 RIP: ima_restore_measurement_list+0xdc/0x45a #PF: error_code(0x0000) not-present page This happens on x86_64 only, as this is already fixed in aarch64 in commit: cbf9c4b9617b ("of: check previous kernel's ima-kexec-buffer against memory bounds") This patch (of 3): When the second-stage kernel is booted with a limiting command line (e.g. "mem=<size>"), the IMA measurement buffer handed over from the previous kernel may fall outside the addressable RAM of the new kernel. Accessing such a buffer can fault during early restore. Introduce a small generic helper, ima_validate_range(), which verifies that a physical [start, end] range for the previous-kernel IMA buffer lies within addressable memory: - On x86, use pfn_range_is_mapped(). - On OF based architectures, use page_is_ram(). Link: https://lkml.kernel.org/r/20251229081523.622515-1-harshit.m.mogalapalli@ora… Link: https://lkml.kernel.org/r/20251229081523.622515-2-harshit.m.mogalapalli@ora… Fixes: b69a2afd5afc ("x86/kexec: Carry forward IMA measurement log on kexec") Signed-off-by: Harshit Mogalapalli <harshit.m.mogalapalli(a)oracle.com> Cc: Alexander Graf <graf(a)amazon.com> Cc: Ard Biesheuvel <ardb(a)kernel.org> Cc: Borislav Betkov <bp(a)alien8.de> Cc: guoweikang <guoweikang.kernel(a)gmail.com> Cc: Henry Willard <henry.willard(a)oracle.com> Cc: "H. Peter Anvin" <hpa(a)zytor.com> Cc: Ingo Molnar <mingo(a)redhat.com> Cc: Jiri Bohac <jbohac(a)suse.cz> Cc: Joel Granados <joel.granados(a)kernel.org> Cc: Jonathan McDowell <noodles(a)fb.com> Cc: Mike Rapoport <rppt(a)kernel.org> Cc: Mimi Zohar <zohar(a)linux.ibm.com> Cc: Paul Webb <paul.x.webb(a)oracle.com> Cc: Sohil Mehta <sohil.mehta(a)intel.com> Cc: Sourabh Jain <sourabhjain(a)linux.ibm.com> Cc: Thomas Gleinxer <tglx(a)linutronix.de> Cc: Yifei Liu <yifei.l.liu(a)oracle.com> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- include/linux/ima.h | 1 security/integrity/ima/ima_kexec.c | 35 +++++++++++++++++++++++++++ 2 files changed, 36 insertions(+) --- a/include/linux/ima.h~ima-add-ima_validate_range-for-previous-kernel-ima-buffer +++ a/include/linux/ima.h @@ -69,6 +69,7 @@ static inline int ima_measure_critical_d #ifdef CONFIG_HAVE_IMA_KEXEC int __init ima_free_kexec_buffer(void); int __init ima_get_kexec_buffer(void **addr, size_t *size); +int ima_validate_range(phys_addr_t phys, size_t size); #endif #ifdef CONFIG_IMA_SECURE_AND_OR_TRUSTED_BOOT --- a/security/integrity/ima/ima_kexec.c~ima-add-ima_validate_range-for-previous-kernel-ima-buffer +++ a/security/integrity/ima/ima_kexec.c @@ -12,6 +12,8 @@ #include <linux/kexec.h> #include <linux/of.h> #include <linux/ima.h> +#include <linux/mm.h> +#include <linux/overflow.h> #include <linux/reboot.h> #include <asm/page.h> #include "ima.h" @@ -294,3 +296,36 @@ void __init ima_load_kexec_buffer(void) pr_debug("Error restoring the measurement list: %d\n", rc); } } + +/* + * ima_validate_range - verify a physical buffer lies in addressable RAM + * @phys: physical start address of the buffer from previous kernel + * @size: size of the buffer + * + * On success return 0. On failure returns -EINVAL so callers can skip + * restoring. + */ +int ima_validate_range(phys_addr_t phys, size_t size) +{ + unsigned long start_pfn, end_pfn; + phys_addr_t end_phys; + + if (check_add_overflow(phys, (phys_addr_t)size - 1, &end_phys)) + return -EINVAL; + + start_pfn = PHYS_PFN(phys); + end_pfn = PHYS_PFN(end_phys); + +#ifdef CONFIG_X86 + if (!pfn_range_is_mapped(start_pfn, end_pfn)) +#else + if (!page_is_ram(start_pfn) || !page_is_ram(end_pfn)) +#endif + { + pr_warn("IMA: previous kernel measurement buffer %pa (size 0x%zx) lies outside available memory\n", + &phys, size); + return -EINVAL; + } + + return 0; +} _ Patches currently in -mm which might be from harshit.m.mogalapalli(a)oracle.com are ima-add-ima_validate_range-for-previous-kernel-ima-buffer.patch of-kexec-refactor-ima_get_kexec_buffer-to-use-ima_validate_range.patch x86-kexec-add-a-sanity-check-on-previous-kernels-ima-kexec-buffer.patch

15 hours, 9 minutes

1
0
0 0

[to-be-updated] x86-kexec-add-a-sanity-check-on-previous-kernels-ima-kexec-buffer.patch removed from -mm tree

by Andrew Morton

The quilt patch titled Subject: x86/kexec: add a sanity check on previous kernel's ima kexec buffer has been removed from the -mm tree. Its filename was x86-kexec-add-a-sanity-check-on-previous-kernels-ima-kexec-buffer.patch This patch was dropped because an updated version will be issued ------------------------------------------------------ From: Harshit Mogalapalli <harshit.m.mogalapalli(a)oracle.com> Subject: x86/kexec: add a sanity check on previous kernel's ima kexec buffer Date: Wed, 12 Nov 2025 11:30:02 -0800 When the second-stage kernel is booted via kexec with a limiting command line such as "mem=<size>", the physical range that contains the carried over IMA measurement list may fall outside the truncated RAM leading to a kernel panic. BUG: unable to handle page fault for address: ffff97793ff47000 RIP: ima_restore_measurement_list+0xdc/0x45a #PF: error_code(0x0000) �� not-present page Other architectures already validate the range with page_is_ram(), as done in commit: cbf9c4b9617b ("of: check previous kernel's ima-kexec-buffer against memory bounds") do a similar check on x86. [akpm(a)linux-foundation.org: fix comment typo] Link: https://lkml.kernel.org/r/20251112193005.3772542-1-harshit.m.mogalapalli@or… Fixes: b69a2afd5afc ("x86/kexec: Carry forward IMA measurement log on kexec") Signed-off-by: Harshit Mogalapalli <harshit.m.mogalapalli(a)oracle.com> Reported-by: Paul Webb <paul.x.webb(a)oracle.com> Reviewed-by: Jonathan McDowell <noodles(a)meta.com> Tested-by: Mimi Zohar <zohar(a)linux.ibm.com> Cc: Alexander Graf <graf(a)amazon.com> Cc: Ard Biesheuvel <ardb(a)kernel.org> Cc: Borislav Betkov <bp(a)alien8.de> Cc: guoweikang <guoweikang.kernel(a)gmail.com> Cc: Henry Willard <henry.willard(a)oracle.com> Cc: "H. Peter Anvin" <hpa(a)zytor.com> Cc: Ingo Molnar <mingo(a)redhat.com> Cc: Jiri Bohac <jbohac(a)suse.cz> Cc: Joel Granados <joel.granados(a)kernel.org> Cc: Mike Rapoport <rppt(a)kernel.org> Cc: Sohil Mehta <sohil.mehta(a)intel.com> Cc: Sourabh Jain <sourabhjain(a)linux.ibm.com> Cc: Thomas Gleinxer <tglx(a)linutronix.de> Cc: Yifei Liu <yifei.l.liu(a)oracle.com> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- arch/x86/kernel/setup.c | 14 ++++++++++++++ 1 file changed, 14 insertions(+) --- a/arch/x86/kernel/setup.c~x86-kexec-add-a-sanity-check-on-previous-kernels-ima-kexec-buffer +++ a/arch/x86/kernel/setup.c @@ -439,9 +439,23 @@ int __init ima_free_kexec_buffer(void) int __init ima_get_kexec_buffer(void **addr, size_t *size) { + unsigned long start_pfn, end_pfn; + if (!ima_kexec_buffer_size) return -ENOENT; + /* + * Calculate the PFNs for the buffer and ensure + * they are within addressable memory. + */ + start_pfn = PFN_DOWN(ima_kexec_buffer_phys); + end_pfn = PFN_DOWN(ima_kexec_buffer_phys + ima_kexec_buffer_size - 1); + if (!pfn_range_is_mapped(start_pfn, end_pfn)) { + pr_warn("IMA buffer at 0x%llx, size = 0x%zx beyond memory\n", + ima_kexec_buffer_phys, ima_kexec_buffer_size); + return -EINVAL; + } + *addr = __va(ima_kexec_buffer_phys); *size = ima_kexec_buffer_size; _ Patches currently in -mm which might be from harshit.m.mogalapalli(a)oracle.com are

15 hours, 15 minutes

1
0
0 0

FAILED: patch "[PATCH] f2fs: fix to detect recoverable inode during dryrun of" failed to apply to 5.10-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 5.10-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-5.10.y git checkout FETCH_HEAD git cherry-pick -x 68d05693f8c031257a0822464366e1c2a239a512 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2025122953-federal-handclasp-1d09@gregkh' --subject-prefix 'PATCH 5.10.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 68d05693f8c031257a0822464366e1c2a239a512 Mon Sep 17 00:00:00 2001 From: Chao Yu <chao(a)kernel.org> Date: Wed, 5 Nov 2025 14:50:23 +0800 Subject: [PATCH] f2fs: fix to detect recoverable inode during dryrun of find_fsync_dnodes() mkfs.f2fs -f /dev/vdd mount /dev/vdd /mnt/f2fs touch /mnt/f2fs/foo sync # avoid CP_UMOUNT_FLAG in last f2fs_checkpoint.ckpt_flags touch /mnt/f2fs/bar f2fs_io fsync /mnt/f2fs/bar f2fs_io shutdown 2 /mnt/f2fs umount /mnt/f2fs blockdev --setro /dev/vdd mount /dev/vdd /mnt/f2fs mount: /mnt/f2fs: WARNING: source write-protected, mounted read-only. For the case if we create and fsync a new inode before sudden power-cut, without norecovery or disable_roll_forward mount option, the following mount will succeed w/o recovering last fsynced inode. The problem here is that we only check inode_list list after find_fsync_dnodes() in f2fs_recover_fsync_data() to find out whether there is recoverable data in the iamge, but there is a missed case, if last fsynced inode is not existing in last checkpoint, then, we will fail to get its inode due to nat of inode node is not existing in last checkpoint, so the inode won't be linked in inode_list. Let's detect such case in dyrun mode to fix this issue. After this change, mount will fail as expected below: mount: /mnt/f2fs: cannot mount /dev/vdd read-only. dmesg(1) may have more information after failed mount system call. demsg: F2FS-fs (vdd): Need to recover fsync data, but write access unavailable, please try mount w/ disable_roll_forward or norecovery Cc: stable(a)kernel.org Fixes: 6781eabba1bd ("f2fs: give -EINVAL for norecovery and rw mount") Signed-off-by: Chao Yu <chao(a)kernel.org> Signed-off-by: Jaegeuk Kim <jaegeuk(a)kernel.org> diff --git a/fs/f2fs/recovery.c b/fs/f2fs/recovery.c index 215e442db72c..d7faebaa3c6b 100644 --- a/fs/f2fs/recovery.c +++ b/fs/f2fs/recovery.c @@ -399,7 +399,7 @@ static int sanity_check_node_chain(struct f2fs_sb_info *sbi, block_t blkaddr, } static int find_fsync_dnodes(struct f2fs_sb_info *sbi, struct list_head *head, - bool check_only) + bool check_only, bool *new_inode) { struct curseg_info *curseg; block_t blkaddr, blkaddr_fast; @@ -447,16 +447,19 @@ static int find_fsync_dnodes(struct f2fs_sb_info *sbi, struct list_head *head, quota_inode = true; } - /* - * CP | dnode(F) | inode(DF) - * For this case, we should not give up now. - */ entry = add_fsync_inode(sbi, head, ino_of_node(folio), quota_inode); if (IS_ERR(entry)) { err = PTR_ERR(entry); - if (err == -ENOENT) + /* + * CP | dnode(F) | inode(DF) + * For this case, we should not give up now. + */ + if (err == -ENOENT) { + if (check_only) + *new_inode = true; goto next; + } f2fs_folio_put(folio, true); break; } @@ -875,6 +878,7 @@ int f2fs_recover_fsync_data(struct f2fs_sb_info *sbi, bool check_only) int ret = 0; unsigned long s_flags = sbi->sb->s_flags; bool need_writecp = false; + bool new_inode = false; f2fs_notice(sbi, "f2fs_recover_fsync_data: recovery fsync data, " "check_only: %d", check_only); @@ -890,8 +894,8 @@ int f2fs_recover_fsync_data(struct f2fs_sb_info *sbi, bool check_only) f2fs_down_write(&sbi->cp_global_sem); /* step #1: find fsynced inode numbers */ - err = find_fsync_dnodes(sbi, &inode_list, check_only); - if (err || list_empty(&inode_list)) + err = find_fsync_dnodes(sbi, &inode_list, check_only, &new_inode); + if (err < 0 || (list_empty(&inode_list) && (!check_only || !new_inode))) goto skip; if (check_only) {

15 hours, 20 minutes

2
1
0 0

FAILED: patch "[PATCH] f2fs: fix to detect recoverable inode during dryrun of" failed to apply to 5.15-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 5.15-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-5.15.y git checkout FETCH_HEAD git cherry-pick -x 68d05693f8c031257a0822464366e1c2a239a512 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2025122953-length-breeding-7553@gregkh' --subject-prefix 'PATCH 5.15.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 68d05693f8c031257a0822464366e1c2a239a512 Mon Sep 17 00:00:00 2001 From: Chao Yu <chao(a)kernel.org> Date: Wed, 5 Nov 2025 14:50:23 +0800 Subject: [PATCH] f2fs: fix to detect recoverable inode during dryrun of find_fsync_dnodes() mkfs.f2fs -f /dev/vdd mount /dev/vdd /mnt/f2fs touch /mnt/f2fs/foo sync # avoid CP_UMOUNT_FLAG in last f2fs_checkpoint.ckpt_flags touch /mnt/f2fs/bar f2fs_io fsync /mnt/f2fs/bar f2fs_io shutdown 2 /mnt/f2fs umount /mnt/f2fs blockdev --setro /dev/vdd mount /dev/vdd /mnt/f2fs mount: /mnt/f2fs: WARNING: source write-protected, mounted read-only. For the case if we create and fsync a new inode before sudden power-cut, without norecovery or disable_roll_forward mount option, the following mount will succeed w/o recovering last fsynced inode. The problem here is that we only check inode_list list after find_fsync_dnodes() in f2fs_recover_fsync_data() to find out whether there is recoverable data in the iamge, but there is a missed case, if last fsynced inode is not existing in last checkpoint, then, we will fail to get its inode due to nat of inode node is not existing in last checkpoint, so the inode won't be linked in inode_list. Let's detect such case in dyrun mode to fix this issue. After this change, mount will fail as expected below: mount: /mnt/f2fs: cannot mount /dev/vdd read-only. dmesg(1) may have more information after failed mount system call. demsg: F2FS-fs (vdd): Need to recover fsync data, but write access unavailable, please try mount w/ disable_roll_forward or norecovery Cc: stable(a)kernel.org Fixes: 6781eabba1bd ("f2fs: give -EINVAL for norecovery and rw mount") Signed-off-by: Chao Yu <chao(a)kernel.org> Signed-off-by: Jaegeuk Kim <jaegeuk(a)kernel.org> diff --git a/fs/f2fs/recovery.c b/fs/f2fs/recovery.c index 215e442db72c..d7faebaa3c6b 100644 --- a/fs/f2fs/recovery.c +++ b/fs/f2fs/recovery.c @@ -399,7 +399,7 @@ static int sanity_check_node_chain(struct f2fs_sb_info *sbi, block_t blkaddr, } static int find_fsync_dnodes(struct f2fs_sb_info *sbi, struct list_head *head, - bool check_only) + bool check_only, bool *new_inode) { struct curseg_info *curseg; block_t blkaddr, blkaddr_fast; @@ -447,16 +447,19 @@ static int find_fsync_dnodes(struct f2fs_sb_info *sbi, struct list_head *head, quota_inode = true; } - /* - * CP | dnode(F) | inode(DF) - * For this case, we should not give up now. - */ entry = add_fsync_inode(sbi, head, ino_of_node(folio), quota_inode); if (IS_ERR(entry)) { err = PTR_ERR(entry); - if (err == -ENOENT) + /* + * CP | dnode(F) | inode(DF) + * For this case, we should not give up now. + */ + if (err == -ENOENT) { + if (check_only) + *new_inode = true; goto next; + } f2fs_folio_put(folio, true); break; } @@ -875,6 +878,7 @@ int f2fs_recover_fsync_data(struct f2fs_sb_info *sbi, bool check_only) int ret = 0; unsigned long s_flags = sbi->sb->s_flags; bool need_writecp = false; + bool new_inode = false; f2fs_notice(sbi, "f2fs_recover_fsync_data: recovery fsync data, " "check_only: %d", check_only); @@ -890,8 +894,8 @@ int f2fs_recover_fsync_data(struct f2fs_sb_info *sbi, bool check_only) f2fs_down_write(&sbi->cp_global_sem); /* step #1: find fsynced inode numbers */ - err = find_fsync_dnodes(sbi, &inode_list, check_only); - if (err || list_empty(&inode_list)) + err = find_fsync_dnodes(sbi, &inode_list, check_only, &new_inode); + if (err < 0 || (list_empty(&inode_list) && (!check_only || !new_inode))) goto skip; if (check_only) {

15 hours, 43 minutes

2
1
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-stable-mirror