March 2025 - Linux-stable-mirror

[PATCH] usb: dwc3: Set SUSPENDENABLE soon after phy init

by Thinh Nguyen

After phy initialization, some phy operations can only be executed while in lower P states. Ensure GUSB3PIPECTL.SUSPENDENABLE and GUSB2PHYCFG.SUSPHY are set soon after initialization to avoid blocking phy ops. Previously the SUSPENDENABLE bits are only set after the controller initialization, which may not happen right away if there's no gadget driver or xhci driver bound. Revise this to clear SUSPENDENABLE bits only when there's mode switching (change in GCTL.PRTCAPDIR). Fixes: 6d735722063a ("usb: dwc3: core: Prevent phy suspend during init") Cc: stable(a)vger.kernel.org Signed-off-by: Thinh Nguyen <Thinh.Nguyen(a)synopsys.com> --- drivers/usb/dwc3/core.c | 69 +++++++++++++++++++++++++---------------- drivers/usb/dwc3/core.h | 2 +- drivers/usb/dwc3/drd.c | 4 +-- 3 files changed, 45 insertions(+), 30 deletions(-) diff --git a/drivers/usb/dwc3/core.c b/drivers/usb/dwc3/core.c index dfa1b5fe48dc..87b4c04a868c 100644 --- a/drivers/usb/dwc3/core.c +++ b/drivers/usb/dwc3/core.c @@ -131,11 +131,24 @@ void dwc3_enable_susphy(struct dwc3 *dwc, bool enable) } } -void dwc3_set_prtcap(struct dwc3 *dwc, u32 mode) +void dwc3_set_prtcap(struct dwc3 *dwc, u32 mode, bool ignore_susphy) { + unsigned int hw_mode; u32 reg; reg = dwc3_readl(dwc->regs, DWC3_GCTL); + + /* + * For DRD controllers, GUSB3PIPECTL.SUSPENDENABLE and + * GUSB2PHYCFG.SUSPHY should be cleared during mode switching, + * and they can be set after core initialization. + */ + hw_mode = DWC3_GHWPARAMS0_MODE(dwc->hwparams.hwparams0); + if (hw_mode == DWC3_GHWPARAMS0_MODE_DRD && !ignore_susphy) { + if (DWC3_GCTL_PRTCAP(reg) != mode) + dwc3_enable_susphy(dwc, false); + } + reg &= ~(DWC3_GCTL_PRTCAPDIR(DWC3_GCTL_PRTCAP_OTG)); reg |= DWC3_GCTL_PRTCAPDIR(mode); dwc3_writel(dwc->regs, DWC3_GCTL, reg); @@ -216,7 +229,7 @@ static void __dwc3_set_mode(struct work_struct *work) spin_lock_irqsave(&dwc->lock, flags); - dwc3_set_prtcap(dwc, desired_dr_role); + dwc3_set_prtcap(dwc, desired_dr_role, false); spin_unlock_irqrestore(&dwc->lock, flags); @@ -658,16 +671,7 @@ static int dwc3_ss_phy_setup(struct dwc3 *dwc, int index) */ reg &= ~DWC3_GUSB3PIPECTL_UX_EXIT_PX; - /* - * Above DWC_usb3.0 1.94a, it is recommended to set - * DWC3_GUSB3PIPECTL_SUSPHY to '0' during coreConsultant configuration. - * So default value will be '0' when the core is reset. Application - * needs to set it to '1' after the core initialization is completed. - * - * Similarly for DRD controllers, GUSB3PIPECTL.SUSPENDENABLE must be - * cleared after power-on reset, and it can be set after core - * initialization. - */ + /* Ensure the GUSB3PIPECTL.SUSPENDENABLE is cleared prior to phy init. */ reg &= ~DWC3_GUSB3PIPECTL_SUSPHY; if (dwc->u2ss_inp3_quirk) @@ -747,15 +751,7 @@ static int dwc3_hs_phy_setup(struct dwc3 *dwc, int index) break; } - /* - * Above DWC_usb3.0 1.94a, it is recommended to set - * DWC3_GUSB2PHYCFG_SUSPHY to '0' during coreConsultant configuration. - * So default value will be '0' when the core is reset. Application - * needs to set it to '1' after the core initialization is completed. - * - * Similarly for DRD controllers, GUSB2PHYCFG.SUSPHY must be cleared - * after power-on reset, and it can be set after core initialization. - */ + /* Ensure the GUSB2PHYCFG.SUSPHY is cleared prior to phy init. */ reg &= ~DWC3_GUSB2PHYCFG_SUSPHY; if (dwc->dis_enblslpm_quirk) @@ -830,6 +826,25 @@ static int dwc3_phy_init(struct dwc3 *dwc) goto err_exit_usb3_phy; } + /* + * Above DWC_usb3.0 1.94a, it is recommended to set + * DWC3_GUSB3PIPECTL_SUSPHY and DWC3_GUSB2PHYCFG_SUSPHY to '0' during + * coreConsultant configuration. So default value will be '0' when the + * core is reset. Application needs to set it to '1' after the core + * initialization is completed. + * + * Certain phy requires to be in P0 power state during initialization. + * Make sure GUSB3PIPECTL.SUSPENDENABLE and GUSB2PHYCFG.SUSPHY are clear + * prior to phy init to maintain in the P0 state. + * + * After phy initialization, some phy operations can only be executed + * while in lower P states. Ensure GUSB3PIPECTL.SUSPENDENABLE and + * GUSB2PHYCFG.SUSPHY are set soon after initialization to avoid + * blocking phy ops. + */ + if (!DWC3_VER_IS_WITHIN(DWC3, ANY, 194A)) + dwc3_enable_susphy(dwc, true); + return 0; err_exit_usb3_phy: @@ -1588,7 +1603,7 @@ static int dwc3_core_init_mode(struct dwc3 *dwc) switch (dwc->dr_mode) { case USB_DR_MODE_PERIPHERAL: - dwc3_set_prtcap(dwc, DWC3_GCTL_PRTCAP_DEVICE); + dwc3_set_prtcap(dwc, DWC3_GCTL_PRTCAP_DEVICE, false); if (dwc->usb2_phy) otg_set_vbus(dwc->usb2_phy->otg, false); @@ -1600,7 +1615,7 @@ static int dwc3_core_init_mode(struct dwc3 *dwc) return dev_err_probe(dev, ret, "failed to initialize gadget\n"); break; case USB_DR_MODE_HOST: - dwc3_set_prtcap(dwc, DWC3_GCTL_PRTCAP_HOST); + dwc3_set_prtcap(dwc, DWC3_GCTL_PRTCAP_HOST, false); if (dwc->usb2_phy) otg_set_vbus(dwc->usb2_phy->otg, true); @@ -1645,7 +1660,7 @@ static void dwc3_core_exit_mode(struct dwc3 *dwc) } /* de-assert DRVVBUS for HOST and OTG mode */ - dwc3_set_prtcap(dwc, DWC3_GCTL_PRTCAP_DEVICE); + dwc3_set_prtcap(dwc, DWC3_GCTL_PRTCAP_DEVICE, true); } static void dwc3_get_software_properties(struct dwc3 *dwc) @@ -2457,7 +2472,7 @@ static int dwc3_resume_common(struct dwc3 *dwc, pm_message_t msg) if (ret) return ret; - dwc3_set_prtcap(dwc, DWC3_GCTL_PRTCAP_DEVICE); + dwc3_set_prtcap(dwc, DWC3_GCTL_PRTCAP_DEVICE, true); dwc3_gadget_resume(dwc); break; case DWC3_GCTL_PRTCAP_HOST: @@ -2465,7 +2480,7 @@ static int dwc3_resume_common(struct dwc3 *dwc, pm_message_t msg) ret = dwc3_core_init_for_resume(dwc); if (ret) return ret; - dwc3_set_prtcap(dwc, DWC3_GCTL_PRTCAP_HOST); + dwc3_set_prtcap(dwc, DWC3_GCTL_PRTCAP_HOST, true); break; } /* Restore GUSB2PHYCFG bits that were modified in suspend */ @@ -2494,7 +2509,7 @@ static int dwc3_resume_common(struct dwc3 *dwc, pm_message_t msg) if (ret) return ret; - dwc3_set_prtcap(dwc, dwc->current_dr_role); + dwc3_set_prtcap(dwc, dwc->current_dr_role, true); dwc3_otg_init(dwc); if (dwc->current_otg_role == DWC3_OTG_ROLE_HOST) { diff --git a/drivers/usb/dwc3/core.h b/drivers/usb/dwc3/core.h index ac7c730f81ac..19ad5b6e1ede 100644 --- a/drivers/usb/dwc3/core.h +++ b/drivers/usb/dwc3/core.h @@ -1557,7 +1557,7 @@ struct dwc3_gadget_ep_cmd_params { #define DWC3_HAS_OTG BIT(3) /* prototypes */ -void dwc3_set_prtcap(struct dwc3 *dwc, u32 mode); +void dwc3_set_prtcap(struct dwc3 *dwc, u32 mode, bool ignore_susphy); void dwc3_set_mode(struct dwc3 *dwc, u32 mode); u32 dwc3_core_fifo_space(struct dwc3_ep *dep, u8 type); diff --git a/drivers/usb/dwc3/drd.c b/drivers/usb/dwc3/drd.c index d76ae676783c..7977860932b1 100644 --- a/drivers/usb/dwc3/drd.c +++ b/drivers/usb/dwc3/drd.c @@ -173,7 +173,7 @@ void dwc3_otg_init(struct dwc3 *dwc) * block "Initialize GCTL for OTG operation". */ /* GCTL.PrtCapDir=2'b11 */ - dwc3_set_prtcap(dwc, DWC3_GCTL_PRTCAP_OTG); + dwc3_set_prtcap(dwc, DWC3_GCTL_PRTCAP_OTG, true); /* GUSB2PHYCFG0.SusPHY=0 */ reg = dwc3_readl(dwc->regs, DWC3_GUSB2PHYCFG(0)); reg &= ~DWC3_GUSB2PHYCFG_SUSPHY; @@ -556,7 +556,7 @@ int dwc3_drd_init(struct dwc3 *dwc) dwc3_drd_update(dwc); } else { - dwc3_set_prtcap(dwc, DWC3_GCTL_PRTCAP_OTG); + dwc3_set_prtcap(dwc, DWC3_GCTL_PRTCAP_OTG, true); /* use OTG block to get ID event */ irq = dwc3_otg_get_irq(dwc); base-commit: 72deda0abee6e705ae71a93f69f55e33be5bca5c -- 2.28.0

9 months, 3 weeks

2
2
0 0

+ mm-migrate-fix-shmem-xarray-update-during-migration.patch added to mm-hotfixes-unstable branch

by Andrew Morton

The patch titled Subject: mm/migrate: fix shmem xarray update during migration has been added to the -mm mm-hotfixes-unstable branch. Its filename is mm-migrate-fix-shmem-xarray-update-during-migration.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: Zi Yan <ziy(a)nvidia.com> Subject: mm/migrate: fix shmem xarray update during migration Date: Fri, 28 Feb 2025 12:49:53 -0500 Pagecache uses multi-index entries for large folio, so does shmem. Only swap cache still stores multiple entries for a single large folio. Commit fc346d0a70a1 ("mm: migrate high-order folios in swap cache correctly") fixed swap cache but got shmem wrong by storing multiple entries for a large shmem folio. This results in a soft lockup as reported by Liu Shixin. Fix it by storing a single entry for a shmem folio. Link: https://lkml.kernel.org/r/20250228174953.2222831-1-ziy@nvidia.com Fixes: fc346d0a70a1 ("mm: migrate high-order folios in swap cache correctly") Signed-off-by: Zi Yan <ziy(a)nvidia.com> Reported-by: Liu Shixin <liushixin2(a)huawei.com> Closes: https://lore.kernel.org/all/28546fb4-5210-bf75-16d6-43e1f8646080@huawei.com/ Reviewed-by: Shivank Garg <shivankg(a)amd.com> Cc: Baolin Wang <baolin.wang(a)linux.alibaba.com> Cc: Barry Song <baohua(a)kernel.org> Cc: Charan Teja Kalla <quic_charante(a)quicinc.com> Cc: David Hildenbrand <david(a)redhat.com> Cc: Hugh Dickens <hughd(a)google.com> Cc: Kefeng Wang <wangkefeng.wang(a)huawei.com> Cc: Lance Yang <ioworker0(a)gmail.com> Cc: Matthew Wilcow (Oracle) <willy(a)infradead.org> Cc: Ryan Roberts <ryan.roberts(a)arm.com> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- mm/migrate.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) --- a/mm/migrate.c~mm-migrate-fix-shmem-xarray-update-during-migration +++ a/mm/migrate.c @@ -524,7 +524,11 @@ static int __folio_migrate_mapping(struc folio_set_swapcache(newfolio); newfolio->private = folio_get_private(folio); } - entries = nr; + /* shmem uses high-order entry */ + if (!folio_test_anon(folio)) + entries = 1; + else + entries = nr; } else { VM_BUG_ON_FOLIO(folio_test_swapcache(folio), folio); entries = 1; _ Patches currently in -mm which might be from ziy(a)nvidia.com are mm-migrate-fix-shmem-xarray-update-during-migration.patch selftests-mm-make-file-backed-thp-split-work-by-writing-pmd-size-data.patch mm-huge_memory-allow-split-shmem-large-folio-to-any-lower-order.patch selftests-mm-test-splitting-file-backed-thp-to-any-lower-order.patch xarray-add-xas_try_split-to-split-a-multi-index-entry.patch mm-huge_memory-add-two-new-not-yet-used-functions-for-folio_split.patch mm-huge_memory-move-folio-split-common-code-to-__folio_split.patch mm-huge_memory-add-buddy-allocator-like-non-uniform-folio_split.patch mm-huge_memory-remove-the-old-unused-__split_huge_page.patch mm-huge_memory-add-folio_split-to-debugfs-testing-interface.patch mm-truncate-use-buddy-allocator-like-folio-split-for-truncate-operation.patch mm-truncate-use-buddy-allocator-like-folio-split-for-truncate-operation-fix.patch selftests-mm-add-tests-for-folio_split-buddy-allocator-like-split.patch mm-filemap-use-xas_try_split-in-__filemap_add_folio.patch mm-shmem-use-xas_try_split-in-shmem_split_large_entry.patch

9 months, 3 weeks

1
0
0 0

+ proc-fix-uaf-in-proc_get_inode.patch added to mm-hotfixes-unstable branch

by Andrew Morton

The patch titled Subject: proc: fix UAF in proc_get_inode() has been added to the -mm mm-hotfixes-unstable branch. Its filename is proc-fix-uaf-in-proc_get_inode.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: Ye Bin <yebin10(a)huawei.com> Subject: proc: fix UAF in proc_get_inode() Date: Sat, 1 Mar 2025 15:06:24 +0300 Fix race between rmmod and /proc/XXX's inode instantiation. The bug is that pde->proc_ops don't belong to /proc, it belongs to a module, therefore dereferencing it after /proc entry has been registered is a bug unless use_pde/unuse_pde() pair has been used. use_pde/unuse_pde can be avoided (2 atomic ops!) because pde->proc_ops never changes so information necessary for inode instantiation can be saved _before_ proc_register() in PDE itself and used later, avoiding pde->proc_ops->... dereference. rmmod lookup sys_delete_module proc_lookup_de pde_get(de); proc_get_inode(dir->i_sb, de); mod->exit() proc_remove remove_proc_subtree proc_entry_rundown(de); free_module(mod); if (S_ISREG(inode->i_mode)) if (de->proc_ops->proc_read_iter) --> As module is already freed, will trigger UAF BUG: unable to handle page fault for address: fffffbfff80a702b PGD 817fc4067 P4D 817fc4067 PUD 817fc0067 PMD 102ef4067 PTE 0 Oops: Oops: 0000 [#1] PREEMPT SMP KASAN PTI CPU: 26 UID: 0 PID: 2667 Comm: ls Tainted: G Hardware name: QEMU Standard PC (i440FX + PIIX, 1996) RIP: 0010:proc_get_inode+0x302/0x6e0 RSP: 0018:ffff88811c837998 EFLAGS: 00010a06 RAX: dffffc0000000000 RBX: ffffffffc0538140 RCX: 0000000000000007 RDX: 1ffffffff80a702b RSI: 0000000000000001 RDI: ffffffffc0538158 RBP: ffff8881299a6000 R08: 0000000067bbe1e5 R09: 1ffff11023906f20 R10: ffffffffb560ca07 R11: ffffffffb2b43a58 R12: ffff888105bb78f0 R13: ffff888100518048 R14: ffff8881299a6004 R15: 0000000000000001 FS: 00007f95b9686840(0000) GS:ffff8883af100000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: fffffbfff80a702b CR3: 0000000117dd2000 CR4: 00000000000006f0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: <TASK> proc_lookup_de+0x11f/0x2e0 __lookup_slow+0x188/0x350 walk_component+0x2ab/0x4f0 path_lookupat+0x120/0x660 filename_lookup+0x1ce/0x560 vfs_statx+0xac/0x150 __do_sys_newstat+0x96/0x110 do_syscall_64+0x5f/0x170 entry_SYSCALL_64_after_hwframe+0x76/0x7e [adobriyan(a)gmail.com: don't do 2 atomic ops on the common path] Link: https://lkml.kernel.org/r/3d25ded0-1739-447e-812b-e34da7990dcf@p183 Fixes: 778f3dd5a13c ("Fix procfs compat_ioctl regression") Signed-off-by: Ye Bin <yebin10(a)huawei.com> Signed-off-by: Alexey Dobriyan <adobriyan(a)gmail.com> Cc: Al Viro <viro(a)zeniv.linux.org.uk> Cc: David S. Miller <davem(a)davemloft.net> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- fs/proc/generic.c | 10 +++++++++- fs/proc/inode.c | 6 +++--- fs/proc/internal.h | 14 ++++++++++++++ include/linux/proc_fs.h | 7 +++++-- 4 files changed, 31 insertions(+), 6 deletions(-) --- a/fs/proc/generic.c~proc-fix-uaf-in-proc_get_inode +++ a/fs/proc/generic.c @@ -559,10 +559,16 @@ struct proc_dir_entry *proc_create_reg(c return p; } -static inline void pde_set_flags(struct proc_dir_entry *pde) +static void pde_set_flags(struct proc_dir_entry *pde) { if (pde->proc_ops->proc_flags & PROC_ENTRY_PERMANENT) pde->flags |= PROC_ENTRY_PERMANENT; + if (pde->proc_ops->proc_read_iter) + pde->flags |= PROC_ENTRY_proc_read_iter; +#ifdef CONFIG_COMPAT + if (pde->proc_ops->proc_compat_ioctl) + pde->flags |= PROC_ENTRY_proc_compat_ioctl; +#endif } struct proc_dir_entry *proc_create_data(const char *name, umode_t mode, @@ -626,6 +632,7 @@ struct proc_dir_entry *proc_create_seq_p p->proc_ops = &proc_seq_ops; p->seq_ops = ops; p->state_size = state_size; + pde_set_flags(p); return proc_register(parent, p); } EXPORT_SYMBOL(proc_create_seq_private); @@ -656,6 +663,7 @@ struct proc_dir_entry *proc_create_singl return NULL; p->proc_ops = &proc_single_ops; p->single_show = show; + pde_set_flags(p); return proc_register(parent, p); } EXPORT_SYMBOL(proc_create_single_data); --- a/fs/proc/inode.c~proc-fix-uaf-in-proc_get_inode +++ a/fs/proc/inode.c @@ -656,13 +656,13 @@ struct inode *proc_get_inode(struct supe if (S_ISREG(inode->i_mode)) { inode->i_op = de->proc_iops; - if (de->proc_ops->proc_read_iter) + if (pde_has_proc_read_iter(de)) inode->i_fop = &proc_iter_file_ops; else inode->i_fop = &proc_reg_file_ops; #ifdef CONFIG_COMPAT - if (de->proc_ops->proc_compat_ioctl) { - if (de->proc_ops->proc_read_iter) + if (pde_has_proc_compat_ioctl(de)) { + if (pde_has_proc_read_iter(de)) inode->i_fop = &proc_iter_file_ops_compat; else inode->i_fop = &proc_reg_file_ops_compat; --- a/fs/proc/internal.h~proc-fix-uaf-in-proc_get_inode +++ a/fs/proc/internal.h @@ -85,6 +85,20 @@ static inline void pde_make_permanent(st pde->flags |= PROC_ENTRY_PERMANENT; } +static inline bool pde_has_proc_read_iter(const struct proc_dir_entry *pde) +{ + return pde->flags & PROC_ENTRY_proc_read_iter; +} + +static inline bool pde_has_proc_compat_ioctl(const struct proc_dir_entry *pde) +{ +#ifdef CONFIG_COMPAT + return pde->flags & PROC_ENTRY_proc_compat_ioctl; +#else + return false; +#endif +} + extern struct kmem_cache *proc_dir_entry_cache; void pde_free(struct proc_dir_entry *pde); --- a/include/linux/proc_fs.h~proc-fix-uaf-in-proc_get_inode +++ a/include/linux/proc_fs.h @@ -20,10 +20,13 @@ enum { * If in doubt, ignore this flag. */ #ifdef MODULE - PROC_ENTRY_PERMANENT = 0U, + PROC_ENTRY_PERMANENT = 0U, #else - PROC_ENTRY_PERMANENT = 1U << 0, + PROC_ENTRY_PERMANENT = 1U << 0, #endif + + PROC_ENTRY_proc_read_iter = 1U << 1, + PROC_ENTRY_proc_compat_ioctl = 1U << 2, }; struct proc_ops { _ Patches currently in -mm which might be from yebin10(a)huawei.com are proc-fix-uaf-in-proc_get_inode.patch

9 months, 3 weeks

1
0
0 0

[PATCH net 2/2] net: phy: nxp-c45-tja11xx: add TJA112XB SGMII PCS restart errata

by Andrei Botila

TJA1120B/TJA1121B can achieve a stable operation of SGMII after a startup event by putting the SGMII PCS into power down mode and restart afterwards. It is necessary to put the SGMII PCS into power down mode and back up. Cc: stable(a)vger.kernel.org Fixes: f1fe5dff2b8a ("net: phy: nxp-c45-tja11xx: add TJA1120 support") Signed-off-by: Andrei Botila <andrei.botila(a)oss.nxp.com> --- drivers/net/phy/nxp-c45-tja11xx.c | 20 ++++++++++++++++++-- 1 file changed, 18 insertions(+), 2 deletions(-) diff --git a/drivers/net/phy/nxp-c45-tja11xx.c b/drivers/net/phy/nxp-c45-tja11xx.c index e083b1a714fd..d142e0a02327 100644 --- a/drivers/net/phy/nxp-c45-tja11xx.c +++ b/drivers/net/phy/nxp-c45-tja11xx.c @@ -114,6 +114,9 @@ #define MII_BASIC_CONFIG_RMII 0x5 #define MII_BASIC_CONFIG_MII 0x4 +#define VEND1_SGMII_BASIC_CONTROL 0xB000 +#define SGMII_LPM BIT(11) + #define VEND1_SYMBOL_ERROR_CNT_XTD 0x8351 #define EXTENDED_CNT_EN BIT(15) #define VEND1_MONITOR_STATUS 0xAC80 @@ -1598,11 +1601,11 @@ static int nxp_c45_set_phy_mode(struct phy_device *phydev) return 0; } -/* Errata: ES_TJA1120 and ES_TJA1121 Rev. 1.0 — 28 November 2024 Section 3.1 */ +/* Errata: ES_TJA1120 and ES_TJA1121 Rev. 1.0 — 28 November 2024 Section 3.1 & 3.2 */ static void nxp_c45_tja1120_errata(struct phy_device *phydev) { + bool macsec_ability, sgmii_ability; int silicon_version, sample_type; - bool macsec_ability; int phy_abilities; int ret = 0; @@ -1619,6 +1622,7 @@ static void nxp_c45_tja1120_errata(struct phy_device *phydev) phy_abilities = phy_read_mmd(phydev, MDIO_MMD_VEND1, VEND1_PORT_ABILITIES); macsec_ability = !!(phy_abilities & MACSEC_ABILITY); + sgmii_ability = !!(phy_abilities & SGMII_ABILITY); if ((!macsec_ability && silicon_version == 2) || (macsec_ability && silicon_version == 1)) { /* TJA1120/TJA1121 PHY configuration errata workaround. @@ -1639,6 +1643,18 @@ static void nxp_c45_tja1120_errata(struct phy_device *phydev) phy_write_mmd(phydev, MDIO_MMD_VEND1, 0x01F8, 0x0); phy_write_mmd(phydev, MDIO_MMD_VEND1, 0x01F9, 0x0); + + if (sgmii_ability) { + /* TJA1120B/TJA1121B SGMII PCS restart errata workaround. + * Put SGMII PCS into power down mode and back up. + */ + phy_set_bits_mmd(phydev, MDIO_MMD_VEND1, + VEND1_SGMII_BASIC_CONTROL, + SGMII_LPM); + phy_clear_bits_mmd(phydev, MDIO_MMD_VEND1, + VEND1_SGMII_BASIC_CONTROL, + SGMII_LPM); + } } } -- 2.48.1

9 months, 3 weeks

1
0
0 0

[PATCH net 2/2] net: phy: nxp-c45-tja11xx: add TJA112XB SGMII PCS restart errata

by Andrei Botila

TJA1120B/TJA1121B can achieve a stable operation of SGMII after a startup event by putting the SGMII PCS into power down mode and restart afterwards. It is necessary to put the SGMII PCS into power down mode and back up. Cc: stable(a)vger.kernel.org Fixes: f1fe5dff2b8a ("net: phy: nxp-c45-tja11xx: add TJA1120 support") Signed-off-by: Andrei Botila <andrei.botila(a)oss.nxp.com> --- drivers/net/phy/nxp-c45-tja11xx.c | 20 ++++++++++++++++++-- 1 file changed, 18 insertions(+), 2 deletions(-) diff --git a/drivers/net/phy/nxp-c45-tja11xx.c b/drivers/net/phy/nxp-c45-tja11xx.c index e083b1a714fd..d142e0a02327 100644 --- a/drivers/net/phy/nxp-c45-tja11xx.c +++ b/drivers/net/phy/nxp-c45-tja11xx.c @@ -114,6 +114,9 @@ #define MII_BASIC_CONFIG_RMII 0x5 #define MII_BASIC_CONFIG_MII 0x4 +#define VEND1_SGMII_BASIC_CONTROL 0xB000 +#define SGMII_LPM BIT(11) + #define VEND1_SYMBOL_ERROR_CNT_XTD 0x8351 #define EXTENDED_CNT_EN BIT(15) #define VEND1_MONITOR_STATUS 0xAC80 @@ -1598,11 +1601,11 @@ static int nxp_c45_set_phy_mode(struct phy_device *phydev) return 0; } -/* Errata: ES_TJA1120 and ES_TJA1121 Rev. 1.0 — 28 November 2024 Section 3.1 */ +/* Errata: ES_TJA1120 and ES_TJA1121 Rev. 1.0 — 28 November 2024 Section 3.1 & 3.2 */ static void nxp_c45_tja1120_errata(struct phy_device *phydev) { + bool macsec_ability, sgmii_ability; int silicon_version, sample_type; - bool macsec_ability; int phy_abilities; int ret = 0; @@ -1619,6 +1622,7 @@ static void nxp_c45_tja1120_errata(struct phy_device *phydev) phy_abilities = phy_read_mmd(phydev, MDIO_MMD_VEND1, VEND1_PORT_ABILITIES); macsec_ability = !!(phy_abilities & MACSEC_ABILITY); + sgmii_ability = !!(phy_abilities & SGMII_ABILITY); if ((!macsec_ability && silicon_version == 2) || (macsec_ability && silicon_version == 1)) { /* TJA1120/TJA1121 PHY configuration errata workaround. @@ -1639,6 +1643,18 @@ static void nxp_c45_tja1120_errata(struct phy_device *phydev) phy_write_mmd(phydev, MDIO_MMD_VEND1, 0x01F8, 0x0); phy_write_mmd(phydev, MDIO_MMD_VEND1, 0x01F9, 0x0); + + if (sgmii_ability) { + /* TJA1120B/TJA1121B SGMII PCS restart errata workaround. + * Put SGMII PCS into power down mode and back up. + */ + phy_set_bits_mmd(phydev, MDIO_MMD_VEND1, + VEND1_SGMII_BASIC_CONTROL, + SGMII_LPM); + phy_clear_bits_mmd(phydev, MDIO_MMD_VEND1, + VEND1_SGMII_BASIC_CONTROL, + SGMII_LPM); + } } } -- 2.48.1

9 months, 3 weeks

1
0
0 0

[PATCH net 1/2] net: phy: nxp-c45-tja11xx: add TJA112X PHY configuration errata

by Andrei Botila

The most recent sillicon versions of TJA1120 and TJA1121 can achieve full silicon performance by putting the PHY in managed mode. It is necessary to apply these PHY writes before link gets established. Application of this fix is required after restart of device and wakeup from sleep. Cc: stable(a)vger.kernel.org Fixes: f1fe5dff2b8a ("net: phy: nxp-c45-tja11xx: add TJA1120 support") Signed-off-by: Andrei Botila <andrei.botila(a)oss.nxp.com> --- drivers/net/phy/nxp-c45-tja11xx.c | 52 +++++++++++++++++++++++++++++++ 1 file changed, 52 insertions(+) diff --git a/drivers/net/phy/nxp-c45-tja11xx.c b/drivers/net/phy/nxp-c45-tja11xx.c index 34231b5b9175..e083b1a714fd 100644 --- a/drivers/net/phy/nxp-c45-tja11xx.c +++ b/drivers/net/phy/nxp-c45-tja11xx.c @@ -22,6 +22,11 @@ #define PHY_ID_TJA_1103 0x001BB010 #define PHY_ID_TJA_1120 0x001BB031 +#define VEND1_DEVICE_ID3 0x0004 +#define TJA1120_DEV_ID3_SILICON_VERSION GENMASK(15, 12) +#define TJA1120_DEV_ID3_SAMPLE_TYPE GENMASK(11, 8) +#define DEVICE_ID3_SAMPLE_TYPE_R 0x9 + #define VEND1_DEVICE_CONTROL 0x0040 #define DEVICE_CONTROL_RESET BIT(15) #define DEVICE_CONTROL_CONFIG_GLOBAL_EN BIT(14) @@ -1593,6 +1598,50 @@ static int nxp_c45_set_phy_mode(struct phy_device *phydev) return 0; } +/* Errata: ES_TJA1120 and ES_TJA1121 Rev. 1.0 — 28 November 2024 Section 3.1 */ +static void nxp_c45_tja1120_errata(struct phy_device *phydev) +{ + int silicon_version, sample_type; + bool macsec_ability; + int phy_abilities; + int ret = 0; + + ret = phy_read_mmd(phydev, MDIO_MMD_VEND1, VEND1_DEVICE_ID3); + if (ret < 0) + return; + + sample_type = FIELD_GET(TJA1120_DEV_ID3_SAMPLE_TYPE, ret); + if (sample_type != DEVICE_ID3_SAMPLE_TYPE_R) + return; + + silicon_version = FIELD_GET(TJA1120_DEV_ID3_SILICON_VERSION, ret); + + phy_abilities = phy_read_mmd(phydev, MDIO_MMD_VEND1, + VEND1_PORT_ABILITIES); + macsec_ability = !!(phy_abilities & MACSEC_ABILITY); + if ((!macsec_ability && silicon_version == 2) || + (macsec_ability && silicon_version == 1)) { + /* TJA1120/TJA1121 PHY configuration errata workaround. + * Apply PHY writes sequence before link up. + */ + if (!macsec_ability) { + phy_write_mmd(phydev, MDIO_MMD_VEND1, 0x01F8, 0x4b95); + phy_write_mmd(phydev, MDIO_MMD_VEND1, 0x01F9, 0xf3cd); + } else { + phy_write_mmd(phydev, MDIO_MMD_VEND1, 0x01F8, 0x89c7); + phy_write_mmd(phydev, MDIO_MMD_VEND1, 0x01F9, 0x0893); + } + + phy_write_mmd(phydev, MDIO_MMD_VEND1, 0x0476, 0x58a0); + + phy_write_mmd(phydev, MDIO_MMD_PMAPMD, 0x8921, 0xa3a); + phy_write_mmd(phydev, MDIO_MMD_PMAPMD, 0x89F1, 0x16c1); + + phy_write_mmd(phydev, MDIO_MMD_VEND1, 0x01F8, 0x0); + phy_write_mmd(phydev, MDIO_MMD_VEND1, 0x01F9, 0x0); + } +} + static int nxp_c45_config_init(struct phy_device *phydev) { int ret; @@ -1609,6 +1658,9 @@ static int nxp_c45_config_init(struct phy_device *phydev) phy_write_mmd(phydev, MDIO_MMD_VEND1, 0x01F8, 1); phy_write_mmd(phydev, MDIO_MMD_VEND1, 0x01F9, 2); + if (phydev->drv->phy_id == PHY_ID_TJA_1120) + nxp_c45_tja1120_errata(phydev); + phy_set_bits_mmd(phydev, MDIO_MMD_VEND1, VEND1_PHY_CONFIG, PHY_CONFIG_AUTO); -- 2.48.1

9 months, 3 weeks

1
0
0 0

+ mm-mremap-correctly-handle-partial-mremap-of-vma-starting-at-0.patch added to mm-unstable branch

by Andrew Morton

The patch titled Subject: mm/mremap: correctly handle partial mremap() of VMA starting at 0 has been added to the -mm mm-unstable branch. Its filename is mm-mremap-correctly-handle-partial-mremap-of-vma-starting-at-0.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-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: Lorenzo Stoakes <lorenzo.stoakes(a)oracle.com> Subject: mm/mremap: correctly handle partial mremap() of VMA starting at 0 Date: Mon, 3 Mar 2025 11:08:31 +0000 Patch series "refactor mremap and fix bug". The existing mremap() logic has grown organically over a very long period of time, resulting in code that is in many parts, very difficult to follow and full of subtleties and sources of confusion. In addition, it is difficult to thread state through the operation correctly, as function arguments have expanded, some parameters are expected to be temporarily altered during the operation, others are intended to remain static and some can be overridden. This series completely refactors the mremap implementation, sensibly separating functions, adding comments to explain the more subtle aspects of the implementation and making use of small structs to thread state through everything. The reason for doing so is to lay the groundwork for planned future changes to the mremap logic, changes which require the ability to easily pass around state. Additionally, it would be unhelpful to add yet more logic to code that is already difficult to follow without first refactoring it like this. The first patch in this series additionally fixes a bug when a VMA with start address zero is partially remapped. This patch (of 7): Consider the case of a partial mremap() (that results in a VMA split) of an accountable VMA (i.e. which has the VM_ACCOUNT flag set) whose start address is zero, with the MREMAP_MAYMOVE flag specified and a scenario where a move does in fact occur: addr end | | v v |-------------| | vma | |-------------| 0 This move is affected by unmapping the range [addr, end). In order to prevent an incorrect decrement of accounted memory which has already been determined, the mremap() code in move_vma() clears VM_ACCOUNT from the VMA prior to doing so, before reestablishing it in each of the VMAs post-split: addr end | | v v |---| |---| | A | | B | |---| |---| Commit 6b73cff239e5 ("mm: change munmap splitting order and move_vma()") changed this logic such as to determine whether there is a need to do so by establishing account_start and account_end and, in the instance where such an operation is required, assigning them to vma->vm_start and vma->vm_end. Later the code checks if the operation is required for 'A' referenced above thusly: if (account_start) { ... } However, if the VMA described above has vma->vm_start == 0, which is now assigned to account_start, this branch will not be executed. As a result, the VMA 'A' above will remain stripped of its VM_ACCOUNT flag, incorrectly. The fix is to simply convert these variables to booleans and set them as required. Link: https://lkml.kernel.org/r/cover.1740911247.git.lorenzo.stoakes@oracle.com Link: https://lkml.kernel.org/r/195c3956c70a142b12465e09b4aa5e33a898b789.17409112… Fixes: 6b73cff239e5 ("mm: change munmap splitting order and move_vma()") Signed-off-by: Lorenzo Stoakes <lorenzo.stoakes(a)oracle.com> Reviewed-by: Harry Yoo <harry.yoo(a)oracle.com> Reviewed-by: Liam R. Howlett <Liam.Howlett(a)oracle.com> Cc: Jann Horn <jannh(a)google.com> Cc: Liam Howlett <liam.howlett(a)oracle.com> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- mm/mremap.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) --- a/mm/mremap.c~mm-mremap-correctly-handle-partial-mremap-of-vma-starting-at-0 +++ a/mm/mremap.c @@ -705,8 +705,8 @@ static unsigned long move_vma(struct vm_ unsigned long vm_flags = vma->vm_flags; unsigned long new_pgoff; unsigned long moved_len; - unsigned long account_start = 0; - unsigned long account_end = 0; + bool account_start = false; + bool account_end = false; unsigned long hiwater_vm; int err = 0; bool need_rmap_locks; @@ -790,9 +790,9 @@ static unsigned long move_vma(struct vm_ if (vm_flags & VM_ACCOUNT && !(flags & MREMAP_DONTUNMAP)) { vm_flags_clear(vma, VM_ACCOUNT); if (vma->vm_start < old_addr) - account_start = vma->vm_start; + account_start = true; if (vma->vm_end > old_addr + old_len) - account_end = vma->vm_end; + account_end = true; } /* @@ -832,7 +832,7 @@ static unsigned long move_vma(struct vm_ /* OOM: unable to split vma, just get accounts right */ if (vm_flags & VM_ACCOUNT && !(flags & MREMAP_DONTUNMAP)) vm_acct_memory(old_len >> PAGE_SHIFT); - account_start = account_end = 0; + account_start = account_end = false; } if (vm_flags & VM_LOCKED) { _ Patches currently in -mm which might be from lorenzo.stoakes(a)oracle.com are mm-abort-vma_modify-on-merge-out-of-memory-failure.patch mm-simplify-vma-merge-structure-and-expand-comments.patch mm-further-refactor-commit_merge.patch mm-eliminate-adj_start-parameter-from-commit_merge.patch mm-make-vmg-target-consistent-and-further-simplify-commit_merge.patch mm-completely-abstract-unnecessary-adj_start-calculation.patch mm-madvise-split-out-mmap-locking-operations-for-madvise-fix.patch mm-use-read-write_once-for-vma-vm_flags-on-migrate-mprotect.patch mm-refactor-rmap_walk_file-to-separate-out-traversal-logic.patch mm-provide-mapping_wrprotect_range-function.patch fb_defio-do-not-use-deprecated-page-mapping-index-fields.patch fb_defio-do-not-use-deprecated-page-mapping-index-fields-fix.patch mm-allow-guard-regions-in-file-backed-and-read-only-mappings.patch selftests-mm-rename-guard-pages-to-guard-regions.patch tools-selftests-expand-all-guard-region-tests-to-file-backed.patch tools-selftests-add-file-shmem-backed-mapping-guard-region-tests.patch fs-proc-task_mmu-add-guard-region-bit-to-pagemap.patch tools-selftests-add-guard-region-test-for-proc-pid-pagemap.patch tools-selftests-add-guard-region-test-for-proc-pid-pagemap-fix.patch mm-mremap-correctly-handle-partial-mremap-of-vma-starting-at-0.patch mm-mremap-refactor-mremap-system-call-implementation.patch mm-mremap-introduce-and-use-vma_remap_struct-threaded-state.patch mm-mremap-initial-refactor-of-move_vma.patch mm-mremap-complete-refactor-of-move_vma.patch mm-mremap-refactor-move_page_tables-abstracting-state.patch mm-mremap-thread-state-through-move-page-table-operation.patch

9 months, 3 weeks

1
0
0 0

+ sparc-mm-avoid-calling-arch_enter-leave_lazy_mmu-in-set_ptes.patch added to mm-unstable branch

by Andrew Morton

The patch titled Subject: sparc/mm: avoid calling arch_enter/leave_lazy_mmu() in set_ptes has been added to the -mm mm-unstable branch. Its filename is sparc-mm-avoid-calling-arch_enter-leave_lazy_mmu-in-set_ptes.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-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: Ryan Roberts <ryan.roberts(a)arm.com> Subject: sparc/mm: avoid calling arch_enter/leave_lazy_mmu() in set_ptes Date: Mon, 3 Mar 2025 14:15:38 +0000 With commit 1a10a44dfc1d ("sparc64: implement the new page table range API") set_ptes was added to the sparc architecture. The implementation included calling arch_enter/leave_lazy_mmu() calls. The patch removes the usage of arch_enter/leave_lazy_mmu() since this implies nesting of lazy mmu regions which is not supported. Without this fix, lazy mmu mode is effectively disabled because we exit the mode after the first set_ptes: remap_pte_range() -> arch_enter_lazy_mmu() -> set_ptes() -> arch_enter_lazy_mmu() -> arch_leave_lazy_mmu() -> arch_leave_lazy_mmu() Powerpc suffered the same problem and fixed it in a corresponding way with commit 47b8def9358c ("powerpc/mm: Avoid calling arch_enter/leave_lazy_mmu() in set_ptes"). Link: https://lkml.kernel.org/r/20250303141542.3371656-5-ryan.roberts@arm.com Fixes: 1a10a44dfc1d ("sparc64: implement the new page table range API") Signed-off-by: Ryan Roberts <ryan.roberts(a)arm.com> Acked-by: David Hildenbrand <david(a)redhat.com> Acked-by: Andreas Larsson <andreas(a)gaisler.com> Cc: <stable(a)vger.kernel.org> Cc: Borislav Betkov <bp(a)alien8.de> Cc: Boris Ostrovsky <boris.ostrovsky(a)oracle.com> Cc: Catalin Marinas <catalin.marinas(a)arm.com> Cc: Dave Hansen <dave.hansen(a)linux.intel.com> Cc: David S. Miller <davem(a)davemloft.net> Cc: "H. Peter Anvin" <hpa(a)zytor.com> Cc: Ingo Molnar <mingo(a)redhat.com> Cc: Juegren Gross <jgross(a)suse.com> Cc: Matthew Wilcow (Oracle) <willy(a)infradead.org> Cc: Thomas Gleinxer <tglx(a)linutronix.de> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- arch/sparc/include/asm/pgtable_64.h | 2 -- 1 file changed, 2 deletions(-) --- a/arch/sparc/include/asm/pgtable_64.h~sparc-mm-avoid-calling-arch_enter-leave_lazy_mmu-in-set_ptes +++ a/arch/sparc/include/asm/pgtable_64.h @@ -936,7 +936,6 @@ static inline void __set_pte_at(struct m static inline void set_ptes(struct mm_struct *mm, unsigned long addr, pte_t *ptep, pte_t pte, unsigned int nr) { - arch_enter_lazy_mmu_mode(); for (;;) { __set_pte_at(mm, addr, ptep, pte, 0); if (--nr == 0) @@ -945,7 +944,6 @@ static inline void set_ptes(struct mm_st pte_val(pte) += PAGE_SIZE; addr += PAGE_SIZE; } - arch_leave_lazy_mmu_mode(); } #define set_ptes set_ptes _ Patches currently in -mm which might be from ryan.roberts(a)arm.com are mm-dont-skip-arch_sync_kernel_mappings-in-error-paths.patch mm-ioremap-pass-pgprot_t-to-ioremap_prot-instead-of-unsigned-long.patch mm-fix-lazy-mmu-docs-and-usage.patch fs-proc-task_mmu-reduce-scope-of-lazy-mmu-region.patch sparc-mm-disable-preemption-in-lazy-mmu-mode.patch sparc-mm-avoid-calling-arch_enter-leave_lazy_mmu-in-set_ptes.patch revert-x86-xen-allow-nesting-of-same-lazy-mode.patch

9 months, 3 weeks

1
0
0 0

+ sparc-mm-disable-preemption-in-lazy-mmu-mode.patch added to mm-unstable branch

by Andrew Morton

The patch titled Subject: sparc/mm: disable preemption in lazy mmu mode has been added to the -mm mm-unstable branch. Its filename is sparc-mm-disable-preemption-in-lazy-mmu-mode.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-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: Ryan Roberts <ryan.roberts(a)arm.com> Subject: sparc/mm: disable preemption in lazy mmu mode Date: Mon, 3 Mar 2025 14:15:37 +0000 Since commit 38e0edb15bd0 ("mm/apply_to_range: call pte function with lazy updates") it's been possible for arch_[enter|leave]_lazy_mmu_mode() to be called without holding a page table lock (for the kernel mappings case), and therefore it is possible that preemption may occur while in the lazy mmu mode. The Sparc lazy mmu implementation is not robust to preemption since it stores the lazy mode state in a per-cpu structure and does not attempt to manage that state on task switch. Powerpc had the same issue and fixed it by explicitly disabling preemption in arch_enter_lazy_mmu_mode() and re-enabling in arch_leave_lazy_mmu_mode(). See commit b9ef323ea168 ("powerpc/64s: Disable preemption in hash lazy mmu mode"). Given Sparc's lazy mmu mode is based on powerpc's, let's fix it in the same way here. Link: https://lkml.kernel.org/r/20250303141542.3371656-4-ryan.roberts@arm.com Fixes: 38e0edb15bd0 ("mm/apply_to_range: call pte function with lazy updates") Signed-off-by: Ryan Roberts <ryan.roberts(a)arm.com> Acked-by: David Hildenbrand <david(a)redhat.com> Acked-by: Andreas Larsson <andreas(a)gaisler.com> Cc: Borislav Betkov <bp(a)alien8.de> Cc: Boris Ostrovsky <boris.ostrovsky(a)oracle.com> Cc: Catalin Marinas <catalin.marinas(a)arm.com> Cc: Dave Hansen <dave.hansen(a)linux.intel.com> Cc: David S. Miller <davem(a)davemloft.net> Cc: "H. Peter Anvin" <hpa(a)zytor.com> Cc: Ingo Molnar <mingo(a)redhat.com> Cc: Juegren Gross <jgross(a)suse.com> Cc: Matthew Wilcow (Oracle) <willy(a)infradead.org> Cc: Thomas Gleinxer <tglx(a)linutronix.de> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- arch/sparc/mm/tlb.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) --- a/arch/sparc/mm/tlb.c~sparc-mm-disable-preemption-in-lazy-mmu-mode +++ a/arch/sparc/mm/tlb.c @@ -52,8 +52,10 @@ out: void arch_enter_lazy_mmu_mode(void) { - struct tlb_batch *tb = this_cpu_ptr(&tlb_batch); + struct tlb_batch *tb; + preempt_disable(); + tb = this_cpu_ptr(&tlb_batch); tb->active = 1; } @@ -64,6 +66,7 @@ void arch_leave_lazy_mmu_mode(void) if (tb->tlb_nr) flush_tlb_pending(); tb->active = 0; + preempt_enable(); } static void tlb_batch_add_one(struct mm_struct *mm, unsigned long vaddr, _ Patches currently in -mm which might be from ryan.roberts(a)arm.com are mm-dont-skip-arch_sync_kernel_mappings-in-error-paths.patch mm-ioremap-pass-pgprot_t-to-ioremap_prot-instead-of-unsigned-long.patch mm-fix-lazy-mmu-docs-and-usage.patch fs-proc-task_mmu-reduce-scope-of-lazy-mmu-region.patch sparc-mm-disable-preemption-in-lazy-mmu-mode.patch sparc-mm-avoid-calling-arch_enter-leave_lazy_mmu-in-set_ptes.patch revert-x86-xen-allow-nesting-of-same-lazy-mode.patch

9 months, 3 weeks

1
0
0 0

+ mm-fix-lazy-mmu-docs-and-usage.patch added to mm-unstable branch

by Andrew Morton

The patch titled Subject: mm: fix lazy mmu docs and usage has been added to the -mm mm-unstable branch. Its filename is mm-fix-lazy-mmu-docs-and-usage.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-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: Ryan Roberts <ryan.roberts(a)arm.com> Subject: mm: fix lazy mmu docs and usage Date: Mon, 3 Mar 2025 14:15:35 +0000 Patch series "Fix lazy mmu mode", v2. I'm planning to implement lazy mmu mode for arm64 to optimize vmalloc. As part of that, I will extend lazy mmu mode to cover kernel mappings in vmalloc table walkers. While lazy mmu mode is already used for kernel mappings in a few places, this will extend it's use significantly. Having reviewed the existing lazy mmu implementations in powerpc, sparc and x86, it looks like there are a bunch of bugs, some of which may be more likely to trigger once I extend the use of lazy mmu. So this series attempts to clarify the requirements and fix all the bugs in advance of that series. See patch #1 commit log for all the details. This patch (of 5): The docs, implementations and use of arch_[enter|leave]_lazy_mmu_mode() is a bit of a mess (to put it politely). There are a number of issues related to nesting of lazy mmu regions and confusion over whether the task, when in a lazy mmu region, is preemptible or not. Fix all the issues relating to the core-mm. Follow up commits will fix the arch-specific implementations. 3 arches implement lazy mmu; powerpc, sparc and x86. When arch_[enter|leave]_lazy_mmu_mode() was first introduced by commit 6606c3e0da53 ("[PATCH] paravirt: lazy mmu mode hooks.patch"), it was expected that lazy mmu regions would never nest and that the appropriate page table lock(s) would be held while in the region, thus ensuring the region is non-preemptible. Additionally lazy mmu regions were only used during manipulation of user mappings. Commit 38e0edb15bd0 ("mm/apply_to_range: call pte function with lazy updates") started invoking the lazy mmu mode in apply_to_pte_range(), which is used for both user and kernel mappings. For kernel mappings the region is no longer protected by any lock so there is no longer any guarantee about non-preemptibility. Additionally, for RT configs, the holding the PTL only implies no CPU migration, it doesn't prevent preemption. Commit bcc6cc832573 ("mm: add default definition of set_ptes()") added arch_[enter|leave]_lazy_mmu_mode() to the default implementation of set_ptes(), used by x86. So after this commit, lazy mmu regions can be nested. Additionally commit 1a10a44dfc1d ("sparc64: implement the new page table range API") and commit 9fee28baa601 ("powerpc: implement the new page table range API") did the same for the sparc and powerpc set_ptes() overrides. powerpc couldn't deal with preemption so avoids it in commit b9ef323ea168 ("powerpc/64s: Disable preemption in hash lazy mmu mode"), which explicitly disables preemption for the whole region in its implementation. x86 can support preemption (or at least it could until it tried to add support nesting; more on this below). Sparc looks to be totally broken in the face of preemption, as far as I can tell. powerpc can't deal with nesting, so avoids it in commit 47b8def9358c ("powerpc/mm: Avoid calling arch_enter/leave_lazy_mmu() in set_ptes"), which removes the lazy mmu calls from its implementation of set_ptes(). x86 attempted to support nesting in commit 49147beb0ccb ("x86/xen: allow nesting of same lazy mode") but as far as I can tell, this breaks its support for preemption. In short, it's all a mess; the semantics for arch_[enter|leave]_lazy_mmu_mode() are not clearly defined and as a result the implementations all have different expectations, sticking plasters and bugs. arm64 is aiming to start using these hooks, so let's clean everything up before adding an arm64 implementation. Update the documentation to state that lazy mmu regions can never be nested, must not be called in interrupt context and preemption may or may not be enabled for the duration of the region. And fix the generic implementation of set_ptes() to avoid nesting. arch-specific fixes to conform to the new spec will proceed this one. These issues were spotted by code review and I have no evidence of issues being reported in the wild. Link: https://lkml.kernel.org/r/20250303141542.3371656-1-ryan.roberts@arm.com Link: https://lkml.kernel.org/r/20250303141542.3371656-2-ryan.roberts@arm.com Fixes: bcc6cc832573 ("mm: add default definition of set_ptes()") Signed-off-by: Ryan Roberts <ryan.roberts(a)arm.com> Acked-by: David Hildenbrand <david(a)redhat.com> Cc: Andreas Larsson <andreas(a)gaisler.com> Cc: Borislav Betkov <bp(a)alien8.de> Cc: Boris Ostrovsky <boris.ostrovsky(a)oracle.com> Cc: Catalin Marinas <catalin.marinas(a)arm.com> Cc: Dave Hansen <dave.hansen(a)linux.intel.com> Cc: David S. Miller <davem(a)davemloft.net> Cc: "H. Peter Anvin" <hpa(a)zytor.com> Cc: Ingo Molnar <mingo(a)redhat.com> Cc: Juegren Gross <jgross(a)suse.com> Cc: Matthew Wilcow (Oracle) <willy(a)infradead.org> Cc: Thomas Gleinxer <tglx(a)linutronix.de> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- include/linux/pgtable.h | 14 ++++++++------ 1 file changed, 8 insertions(+), 6 deletions(-) --- a/include/linux/pgtable.h~mm-fix-lazy-mmu-docs-and-usage +++ a/include/linux/pgtable.h @@ -222,10 +222,14 @@ static inline int pmd_dirty(pmd_t pmd) * hazard could result in the direct mode hypervisor case, since the actual * write to the page tables may not yet have taken place, so reads though * a raw PTE pointer after it has been modified are not guaranteed to be - * up to date. This mode can only be entered and left under the protection of - * the page table locks for all page tables which may be modified. In the UP - * case, this is required so that preemption is disabled, and in the SMP case, - * it must synchronize the delayed page table writes properly on other CPUs. + * up to date. + * + * In the general case, no lock is guaranteed to be held between entry and exit + * of the lazy mode. So the implementation must assume preemption may be enabled + * and cpu migration is possible; it must take steps to be robust against this. + * (In practice, for user PTE updates, the appropriate page table lock(s) are + * held, but for kernel PTE updates, no lock is held). Nesting is not permitted + * and the mode cannot be used in interrupt context. */ #ifndef __HAVE_ARCH_ENTER_LAZY_MMU_MODE #define arch_enter_lazy_mmu_mode() do {} while (0) @@ -287,7 +291,6 @@ static inline void set_ptes(struct mm_st { page_table_check_ptes_set(mm, ptep, pte, nr); - arch_enter_lazy_mmu_mode(); for (;;) { set_pte(ptep, pte); if (--nr == 0) @@ -295,7 +298,6 @@ static inline void set_ptes(struct mm_st ptep++; pte = pte_next_pfn(pte); } - arch_leave_lazy_mmu_mode(); } #endif #define set_pte_at(mm, addr, ptep, pte) set_ptes(mm, addr, ptep, pte, 1) _ Patches currently in -mm which might be from ryan.roberts(a)arm.com are mm-dont-skip-arch_sync_kernel_mappings-in-error-paths.patch mm-ioremap-pass-pgprot_t-to-ioremap_prot-instead-of-unsigned-long.patch mm-fix-lazy-mmu-docs-and-usage.patch fs-proc-task_mmu-reduce-scope-of-lazy-mmu-region.patch sparc-mm-disable-preemption-in-lazy-mmu-mode.patch sparc-mm-avoid-calling-arch_enter-leave_lazy_mmu-in-set_ptes.patch revert-x86-xen-allow-nesting-of-same-lazy-mode.patch

9 months, 3 weeks

1
0
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-stable-mirror March 2025