August 2024 - Linux-stable-mirror

[PATCHv5, REBASED 3/4] x86/tdx: Dynamically disable SEPT violations from causing #VEs

by Kirill A. Shutemov

Memory access #VE's are hard for Linux to handle in contexts like the entry code or NMIs. But other OSes need them for functionality. There's a static (pre-guest-boot) way for a VMM to choose one or the other. But VMMs don't always know which OS they are booting, so they choose to deliver those #VE's so the "other" OSes will work. That, unfortunately has left us in the lurch and exposed to these hard-to-handle #VEs. The TDX module has introduced a new feature. Even if the static configuration is "send nasty #VE's", the kernel can dynamically request that they be disabled. Check if the feature is available and disable SEPT #VE if possible. If the TD allowed to disable/enable SEPT #VEs, the ATTR_SEPT_VE_DISABLE attribute is no longer reliable. It reflects the initial state of the control for the TD, but it will not be updated if someone (e.g. bootloader) changes it before the kernel starts. Kernel must check TDCS_TD_CTLS bit to determine if SEPT #VEs are enabled or disabled. Signed-off-by: Kirill A. Shutemov <kirill.shutemov(a)linux.intel.com> Fixes: 373e715e31bf ("x86/tdx: Panic on bad configs that #VE on "private" memory access") Cc: stable(a)vger.kernel.org --- arch/x86/coco/tdx/tdx.c | 76 ++++++++++++++++++++++++------- arch/x86/include/asm/shared/tdx.h | 10 +++- 2 files changed, 69 insertions(+), 17 deletions(-) diff --git a/arch/x86/coco/tdx/tdx.c b/arch/x86/coco/tdx/tdx.c index 08ce488b54d0..ba3103877b21 100644 --- a/arch/x86/coco/tdx/tdx.c +++ b/arch/x86/coco/tdx/tdx.c @@ -78,7 +78,7 @@ static inline void tdcall(u64 fn, struct tdx_module_args *args) } /* Read TD-scoped metadata */ -static inline u64 __maybe_unused tdg_vm_rd(u64 field, u64 *value) +static inline u64 tdg_vm_rd(u64 field, u64 *value) { struct tdx_module_args args = { .rdx = field, @@ -193,6 +193,62 @@ static void __noreturn tdx_panic(const char *msg) __tdx_hypercall(&args); } +/* + * The kernel cannot handle #VEs when accessing normal kernel memory. Ensure + * that no #VE will be delivered for accesses to TD-private memory. + * + * TDX 1.0 does not allow the guest to disable SEPT #VE on its own. The VMM + * controls if the guest will receive such #VE with TD attribute + * ATTR_SEPT_VE_DISABLE. + * + * Newer TDX module allows the guest to control if it wants to receive SEPT + * violation #VEs. + * + * Check if the feature is available and disable SEPT #VE if possible. + * + * If the TD allowed to disable/enable SEPT #VEs, the ATTR_SEPT_VE_DISABLE + * attribute is no longer reliable. It reflects the initial state of the + * control for the TD, but it will not be updated if someone (e.g. bootloader) + * changes it before the kernel starts. Kernel must check TDCS_TD_CTLS bit to + * determine if SEPT #VEs are enabled or disabled. + */ +static void disable_sept_ve(u64 td_attr) +{ + const char *msg = "TD misconfiguration: SEPT #VE has to be disabled"; + bool debug = td_attr & ATTR_DEBUG; + u64 config, controls; + + /* Is this TD allowed to disable SEPT #VE */ + tdg_vm_rd(TDCS_CONFIG_FLAGS, &config); + if (!(config & TDCS_CONFIG_FLEXIBLE_PENDING_VE)) { + /* No SEPT #VE controls for the guest: check the attribute */ + if (td_attr & ATTR_SEPT_VE_DISABLE) + return; + + /* Relax SEPT_VE_DISABLE check for debug TD for backtraces */ + if (debug) + pr_warn("%s\n", msg); + else + tdx_panic(msg); + return; + } + + /* Check if SEPT #VE has been disabled before us */ + tdg_vm_rd(TDCS_TD_CTLS, &controls); + if (controls & TD_CTLS_PENDING_VE_DISABLE) + return; + + /* Keep #VEs enabled for splats in debugging environments */ + if (debug) + return; + + /* Disable SEPT #VEs */ + tdg_vm_wr(TDCS_TD_CTLS, TD_CTLS_PENDING_VE_DISABLE, + TD_CTLS_PENDING_VE_DISABLE); + + return; +} + static void tdx_setup(u64 *cc_mask) { struct tdx_module_args args = {}; @@ -218,24 +274,12 @@ static void tdx_setup(u64 *cc_mask) gpa_width = args.rcx & GENMASK(5, 0); *cc_mask = BIT_ULL(gpa_width - 1); + td_attr = args.rdx; + /* Kernel does not use NOTIFY_ENABLES and does not need random #VEs */ tdg_vm_wr(TDCS_NOTIFY_ENABLES, 0, -1ULL); - /* - * The kernel can not handle #VE's when accessing normal kernel - * memory. Ensure that no #VE will be delivered for accesses to - * TD-private memory. Only VMM-shared memory (MMIO) will #VE. - */ - td_attr = args.rdx; - if (!(td_attr & ATTR_SEPT_VE_DISABLE)) { - const char *msg = "TD misconfiguration: SEPT_VE_DISABLE attribute must be set."; - - /* Relax SEPT_VE_DISABLE check for debug TD. */ - if (td_attr & ATTR_DEBUG) - pr_warn("%s\n", msg); - else - tdx_panic(msg); - } + disable_sept_ve(td_attr); } /* diff --git a/arch/x86/include/asm/shared/tdx.h b/arch/x86/include/asm/shared/tdx.h index 7e12cfa28bec..fecb2a6e864b 100644 --- a/arch/x86/include/asm/shared/tdx.h +++ b/arch/x86/include/asm/shared/tdx.h @@ -19,9 +19,17 @@ #define TDG_VM_RD 7 #define TDG_VM_WR 8 -/* TDCS fields. To be used by TDG.VM.WR and TDG.VM.RD module calls */ +/* TDX TD-Scope Metadata. To be used by TDG.VM.WR and TDG.VM.RD */ +#define TDCS_CONFIG_FLAGS 0x1110000300000016 +#define TDCS_TD_CTLS 0x1110000300000017 #define TDCS_NOTIFY_ENABLES 0x9100000000000010 +/* TDCS_CONFIG_FLAGS bits */ +#define TDCS_CONFIG_FLEXIBLE_PENDING_VE BIT_ULL(1) + +/* TDCS_TD_CTLS bits */ +#define TD_CTLS_PENDING_VE_DISABLE BIT_ULL(0) + /* TDX hypercall Leaf IDs */ #define TDVMCALL_MAP_GPA 0x10001 #define TDVMCALL_GET_QUOTE 0x10002 -- 2.43.0

8 months, 3 weeks

2
3
0 0

[PATCH net 0/4] mptcp: close subflow when receiving TCP+FIN and misc.

by Matthieu Baerts (NGI0)

Here are different fixes: Patch 1 closes the subflow after having received a FIN, instead of leaving it half-closed until the end of the MPTCP connection. A fix for v5.12. Patch 2 validates the previous patch. Patch 3 is a fix for a recent fix to check both directions for the backup flag. It can follow the 'Fixes' commit and be backported up to v5.7. Patch 4 adds a missing \n at the end of pr_debug(), causing debug messages to be displayed with a delay, which confuses the debugger. A fix for v5.6. Signed-off-by: Matthieu Baerts (NGI0) <matttbe(a)kernel.org> --- Note: Peter's email address has been removed from the Cc list, because it is bouncing. --- Matthieu Baerts (NGI0) (4): mptcp: close subflow when receiving TCP+FIN selftests: mptcp: join: cannot rm sf if closed mptcp: sched: check both backup in retrans mptcp: pr_debug: add missing \n at the end net/mptcp/fastopen.c | 4 +- net/mptcp/options.c | 50 ++++++++++----------- net/mptcp/pm.c | 28 ++++++------ net/mptcp/pm_netlink.c | 20 ++++----- net/mptcp/protocol.c | 59 +++++++++++++------------ net/mptcp/protocol.h | 4 +- net/mptcp/sched.c | 4 +- net/mptcp/sockopt.c | 4 +- net/mptcp/subflow.c | 56 ++++++++++++----------- tools/testing/selftests/net/mptcp/mptcp_join.sh | 11 ++--- 10 files changed, 122 insertions(+), 118 deletions(-) --- base-commit: 31a972959ae57691a1e4f539399b2674ae576086 change-id: 20240826-net-mptcp-close-extra-sf-fin-19d4e5aa4c9c Best regards, -- Matthieu Baerts (NGI0) <matttbe(a)kernel.org>

8 months, 3 weeks

4
7
0 0

[PATCH v4 6/7] vdpa: solidrun: Fix UB bug with devres

by Philipp Stanner

In psnet_open_pf_bar() and snet_open_vf_bar() a string later passed to pcim_iomap_regions() is placed on the stack. Neither pcim_iomap_regions() nor the functions it calls copy that string. Should the string later ever be used, this, consequently, causes undefined behavior since the stack frame will by then have disappeared. Fix the bug by allocating the strings on the heap through devm_kasprintf(). Cc: stable(a)vger.kernel.org # v6.3 Fixes: 51a8f9d7f587 ("virtio: vdpa: new SolidNET DPU driver.") Reported-by: Christophe JAILLET <christophe.jaillet(a)wanadoo.fr> Closes: https://lore.kernel.org/all/74e9109a-ac59-49e2-9b1d-d825c9c9f891@wanadoo.fr/ Suggested-by: Andy Shevchenko <andy(a)kernel.org> Signed-off-by: Philipp Stanner <pstanner(a)redhat.com> --- drivers/vdpa/solidrun/snet_main.c | 14 ++++++++++---- 1 file changed, 10 insertions(+), 4 deletions(-) diff --git a/drivers/vdpa/solidrun/snet_main.c b/drivers/vdpa/solidrun/snet_main.c index 99428a04068d..c8b74980dbd1 100644 --- a/drivers/vdpa/solidrun/snet_main.c +++ b/drivers/vdpa/solidrun/snet_main.c @@ -555,7 +555,7 @@ static const struct vdpa_config_ops snet_config_ops = { static int psnet_open_pf_bar(struct pci_dev *pdev, struct psnet *psnet) { - char name[50]; + char *name; int ret, i, mask = 0; /* We don't know which BAR will be used to communicate.. * We will map every bar with len > 0. @@ -573,7 +573,10 @@ static int psnet_open_pf_bar(struct pci_dev *pdev, struct psnet *psnet) return -ENODEV; } - snprintf(name, sizeof(name), "psnet[%s]-bars", pci_name(pdev)); + name = devm_kasprintf(&pdev->dev, GFP_KERNEL, "psnet[%s]-bars", pci_name(pdev)); + if (!name) + return -ENOMEM; + ret = pcim_iomap_regions(pdev, mask, name); if (ret) { SNET_ERR(pdev, "Failed to request and map PCI BARs\n"); @@ -590,10 +593,13 @@ static int psnet_open_pf_bar(struct pci_dev *pdev, struct psnet *psnet) static int snet_open_vf_bar(struct pci_dev *pdev, struct snet *snet) { - char name[50]; + char *name; int ret; - snprintf(name, sizeof(name), "snet[%s]-bar", pci_name(pdev)); + name = devm_kasprintf(&pdev->dev, GFP_KERNEL, "snet[%s]-bars", pci_name(pdev)); + if (!name) + return -ENOMEM; + /* Request and map BAR */ ret = pcim_iomap_regions(pdev, BIT(snet->psnet->cfg.vf_bar), name); if (ret) { -- 2.46.0

8 months, 3 weeks

1
0
0 0

[PATCH 6.1.y] KVM: x86: fire timer when it is migrated and expired, and in oneshot mode

by David Hunter

From: Li RongQing <lirongqing(a)baidu.com> [ Upstream Commit 8e6ed96cdd5001c55fccc80a17f651741c1ca7d2] when the vCPU was migrated, if its timer is expired, KVM _should_ fire the timer ASAP, zeroing the deadline here will cause the timer to immediately fire on the destination Cc: Sean Christopherson <seanjc(a)google.com> Cc: Peter Shier <pshier(a)google.com> Cc: Jim Mattson <jmattson(a)google.com> Cc: Wanpeng Li <wanpengli(a)tencent.com> Cc: Paolo Bonzini <pbonzini(a)redhat.com> Signed-off-by: Li RongQing <lirongqing(a)baidu.com> Link: https://lore.kernel.org/r/20230106040625.8404-1-lirongqing@baidu.com Signed-off-by: Sean Christopherson <seanjc(a)google.com> (cherry picked from commit 8e6ed96cdd5001c55fccc80a17f651741c1ca7d2) The code was able to compile without errors or warnings. Signed-off-by: David Hunter <david.hunter.linux(a)gmail.com> --- arch/x86/kvm/lapic.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index c90fef0258c5..3cd590ace95a 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -1843,8 +1843,12 @@ static bool set_target_expiration(struct kvm_lapic *apic, u32 count_reg) if (unlikely(count_reg != APIC_TMICT)) { deadline = tmict_to_ns(apic, kvm_lapic_get_reg(apic, count_reg)); - if (unlikely(deadline <= 0)) - deadline = apic->lapic_timer.period; + if (unlikely(deadline <= 0)) { + if (apic_lvtt_period(apic)) + deadline = apic->lapic_timer.period; + else + deadline = 0; + } else if (unlikely(deadline > apic->lapic_timer.period)) { pr_info_ratelimited( "kvm: vcpu %i: requested lapic timer restore with " -- 2.43.0

8 months, 3 weeks

4
7
0 0

[PATCH v5 3/3] x86/sgx: Resolve EREMOVE page vs EAUG page data race

by Dmitrii Kuvaiskii

Two enclave threads may try to add and remove the same enclave page simultaneously (e.g., if the SGX runtime supports both lazy allocation and MADV_DONTNEED semantics). Consider some enclave page added to the enclave. User space decides to temporarily remove this page (e.g., emulating the MADV_DONTNEED semantics) on CPU1. At the same time, user space performs a memory access on the same page on CPU2, which results in a #PF and ultimately in sgx_vma_fault(). Scenario proceeds as follows: /* * CPU1: User space performs * ioctl(SGX_IOC_ENCLAVE_REMOVE_PAGES) * on enclave page X */ sgx_encl_remove_pages() { mutex_lock(&encl->lock); entry = sgx_encl_load_page(encl); /* * verify that page is * trimmed and accepted */ mutex_unlock(&encl->lock); /* * remove PTE entry; cannot * be performed under lock */ sgx_zap_enclave_ptes(encl); /* * Fault on CPU2 on same page X */ sgx_vma_fault() { /* * PTE entry was removed, but the * page is still in enclave's xarray */ xa_load(&encl->page_array) != NULL -> /* * SGX driver thinks that this page * was swapped out and loads it */ mutex_lock(&encl->lock); /* * this is effectively a no-op */ entry = sgx_encl_load_page_in_vma(); /* * add PTE entry * * *BUG*: a PTE is installed for a * page in process of being removed */ vmf_insert_pfn(...); mutex_unlock(&encl->lock); return VM_FAULT_NOPAGE; } /* * continue with page removal */ mutex_lock(&encl->lock); sgx_encl_free_epc_page(epc_page) { /* * remove page via EREMOVE */ /* * free EPC page */ sgx_free_epc_page(epc_page); } xa_erase(&encl->page_array); mutex_unlock(&encl->lock); } Here, CPU1 removed the page. However CPU2 installed the PTE entry on the same page. This enclave page becomes perpetually inaccessible (until another SGX_IOC_ENCLAVE_REMOVE_PAGES ioctl). This is because the page is marked accessible in the PTE entry but is not EAUGed, and any subsequent access to this page raises a fault: with the kernel believing there to be a valid VMA, the unlikely error code X86_PF_SGX encountered by code path do_user_addr_fault() -> access_error() causes the SGX driver's sgx_vma_fault() to be skipped and user space receives a SIGSEGV instead. The userspace SIGSEGV handler cannot perform EACCEPT because the page was not EAUGed. Thus, the user space is stuck with the inaccessible page. Fix this race by forcing the fault handler on CPU2 to back off if the page is currently being removed (on CPU1). This is achieved by setting SGX_ENCL_PAGE_BUSY flag right-before the first mutex_unlock() in sgx_encl_remove_pages(). Upon loading the page, CPU2 checks whether this page is busy, and if yes then CPU2 backs off and waits until the page is completely removed. After that, any memory access to this page results in a normal "allocate and EAUG a page on #PF" flow. Additionally fix a similar race: user space converts a normal enclave page to a TCS page (via SGX_IOC_ENCLAVE_MODIFY_TYPES) on CPU1, and at the same time, user space performs a memory access on the same page on CPU2. This fix is not strictly necessary (this particular race would indicate a bug in a user space application), but it gives a consistent rule: if an enclave page is under certain operation by the kernel with the mapping removed, then other threads trying to access that page are temporarily blocked and should retry. Fixes: 9849bb27152c ("x86/sgx: Support complete page removal") Cc: stable(a)vger.kernel.org Signed-off-by: Dmitrii Kuvaiskii <dmitrii.kuvaiskii(a)intel.com> --- arch/x86/kernel/cpu/sgx/encl.h | 3 ++- arch/x86/kernel/cpu/sgx/ioctl.c | 17 +++++++++++++++++ 2 files changed, 19 insertions(+), 1 deletion(-) diff --git a/arch/x86/kernel/cpu/sgx/encl.h b/arch/x86/kernel/cpu/sgx/encl.h index b566b8ad5f33..96b11e8fb770 100644 --- a/arch/x86/kernel/cpu/sgx/encl.h +++ b/arch/x86/kernel/cpu/sgx/encl.h @@ -22,7 +22,8 @@ /* 'desc' bits holding the offset in the VA (version array) page. */ #define SGX_ENCL_PAGE_VA_OFFSET_MASK GENMASK_ULL(11, 3) -/* 'desc' bit indicating that the page is busy (being reclaimed). */ +/* 'desc' bit indicating that the page is busy (being reclaimed, removed or + * converted to a TCS page). */ #define SGX_ENCL_PAGE_BUSY BIT(2) /* diff --git a/arch/x86/kernel/cpu/sgx/ioctl.c b/arch/x86/kernel/cpu/sgx/ioctl.c index 5d390df21440..ee619f2b3414 100644 --- a/arch/x86/kernel/cpu/sgx/ioctl.c +++ b/arch/x86/kernel/cpu/sgx/ioctl.c @@ -969,12 +969,22 @@ static long sgx_enclave_modify_types(struct sgx_encl *encl, /* * Do not keep encl->lock because of dependency on * mmap_lock acquired in sgx_zap_enclave_ptes(). + * + * Releasing encl->lock leads to a data race: while CPU1 + * performs sgx_zap_enclave_ptes() and removes the PTE + * entry for the enclave page, CPU2 may attempt to load + * this page (because the page is still in enclave's + * xarray). To prevent CPU2 from loading the page, mark + * the page as busy before unlock and unmark after lock + * again. */ + entry->desc |= SGX_ENCL_PAGE_BUSY; mutex_unlock(&encl->lock); sgx_zap_enclave_ptes(encl, addr); mutex_lock(&encl->lock); + entry->desc &= ~SGX_ENCL_PAGE_BUSY; sgx_mark_page_reclaimable(entry->epc_page); } @@ -1141,7 +1151,14 @@ static long sgx_encl_remove_pages(struct sgx_encl *encl, /* * Do not keep encl->lock because of dependency on * mmap_lock acquired in sgx_zap_enclave_ptes(). + * + * Releasing encl->lock leads to a data race: while CPU1 + * performs sgx_zap_enclave_ptes() and removes the PTE entry + * for the enclave page, CPU2 may attempt to load this page + * (because the page is still in enclave's xarray). To prevent + * CPU2 from loading the page, mark the page as busy. */ + entry->desc |= SGX_ENCL_PAGE_BUSY; mutex_unlock(&encl->lock); sgx_zap_enclave_ptes(encl, addr); -- 2.43.0

8 months, 3 weeks

3
2
0 0

[PATCH v5 2/3] x86/sgx: Resolve EAUG race where losing thread returns SIGBUS

by Dmitrii Kuvaiskii

Imagine an mmap()'d file. Two threads touch the same address at the same time and fault. Both allocate a physical page and race to install a PTE for that page. Only one will win the race. The loser frees its page, but still continues handling the fault as a success and returns VM_FAULT_NOPAGE from the fault handler. The same race can happen with SGX. But there's a bug: the loser in the SGX steers into a failure path. The loser EREMOVE's the winner's EPC page, then returns SIGBUS, likely killing the app. Fix the SGX loser's behavior. Check whether another thread already allocated the page and if yes, return with VM_FAULT_NOPAGE. The race can be illustrated as follows: /* /* * Fault on CPU1 * Fault on CPU2 * on enclave page X * on enclave page X */ */ sgx_vma_fault() { sgx_vma_fault() { xa_load(&encl->page_array) xa_load(&encl->page_array) == NULL --> == NULL --> sgx_encl_eaug_page() { sgx_encl_eaug_page() { ... ... /* /* * alloc encl_page * alloc encl_page */ */ mutex_lock(&encl->lock); /* * alloc EPC page */ epc_page = sgx_alloc_epc_page(...); /* * add page to enclave's xarray */ xa_insert(&encl->page_array, ...); /* * add page to enclave via EAUG * (page is in pending state) */ /* * add PTE entry */ vmf_insert_pfn(...); mutex_unlock(&encl->lock); return VM_FAULT_NOPAGE; } } /* * All good up to here: enclave page * successfully added to enclave, * ready for EACCEPT from user space */ mutex_lock(&encl->lock); /* * alloc EPC page */ epc_page = sgx_alloc_epc_page(...); /* * add page to enclave's xarray, * this fails with -EBUSY as this * page was already added by CPU2 */ xa_insert(&encl->page_array, ...); err_out_shrink: sgx_encl_free_epc_page(epc_page) { /* * remove page via EREMOVE * * *BUG*: page added by CPU2 is * yanked from enclave while it * remains accessible from OS * perspective (PTE installed) */ /* * free EPC page */ sgx_free_epc_page(epc_page); } mutex_unlock(&encl->lock); /* * *BUG*: SIGBUS is returned * for a valid enclave page */ return VM_FAULT_SIGBUS; } } Fixes: 5a90d2c3f5ef ("x86/sgx: Support adding of pages to an initialized enclave") Cc: stable(a)vger.kernel.org Reported-by: Marcelina Kościelnicka <mwk(a)invisiblethingslab.com> Suggested-by: Kai Huang <kai.huang(a)intel.com> Signed-off-by: Dmitrii Kuvaiskii <dmitrii.kuvaiskii(a)intel.com> --- arch/x86/kernel/cpu/sgx/encl.c | 36 ++++++++++++++++++++-------------- 1 file changed, 21 insertions(+), 15 deletions(-) diff --git a/arch/x86/kernel/cpu/sgx/encl.c b/arch/x86/kernel/cpu/sgx/encl.c index c0a3c00284c8..2aa7ced0e4a0 100644 --- a/arch/x86/kernel/cpu/sgx/encl.c +++ b/arch/x86/kernel/cpu/sgx/encl.c @@ -337,6 +337,16 @@ static vm_fault_t sgx_encl_eaug_page(struct vm_area_struct *vma, if (!test_bit(SGX_ENCL_INITIALIZED, &encl->flags)) return VM_FAULT_SIGBUS; + mutex_lock(&encl->lock); + + /* + * Multiple threads may try to fault on the same page concurrently. + * Re-check if another thread has already done that. + */ + encl_page = xa_load(&encl->page_array, PFN_DOWN(addr)); + if (encl_page) + goto done; + /* * Ignore internal permission checking for dynamically added pages. * They matter only for data added during the pre-initialization @@ -345,23 +355,23 @@ static vm_fault_t sgx_encl_eaug_page(struct vm_area_struct *vma, */ secinfo_flags = SGX_SECINFO_R | SGX_SECINFO_W | SGX_SECINFO_X; encl_page = sgx_encl_page_alloc(encl, addr - encl->base, secinfo_flags); - if (IS_ERR(encl_page)) - return VM_FAULT_OOM; - - mutex_lock(&encl->lock); + if (IS_ERR(encl_page)) { + vmret = VM_FAULT_OOM; + goto err_out_unlock; + } epc_page = sgx_encl_load_secs(encl); if (IS_ERR(epc_page)) { if (PTR_ERR(epc_page) == -EBUSY) vmret = VM_FAULT_NOPAGE; - goto err_out_unlock; + goto err_out_encl; } epc_page = sgx_alloc_epc_page(encl_page, false); if (IS_ERR(epc_page)) { if (PTR_ERR(epc_page) == -EBUSY) vmret = VM_FAULT_NOPAGE; - goto err_out_unlock; + goto err_out_encl; } va_page = sgx_encl_grow(encl, false); @@ -376,10 +386,6 @@ static vm_fault_t sgx_encl_eaug_page(struct vm_area_struct *vma, ret = xa_insert(&encl->page_array, PFN_DOWN(encl_page->desc), encl_page, GFP_KERNEL); - /* - * If ret == -EBUSY then page was created in another flow while - * running without encl->lock - */ if (ret) goto err_out_shrink; @@ -389,7 +395,7 @@ static vm_fault_t sgx_encl_eaug_page(struct vm_area_struct *vma, ret = __eaug(&pginfo, sgx_get_epc_virt_addr(epc_page)); if (ret) - goto err_out; + goto err_out_eaug; encl_page->encl = encl; encl_page->epc_page = epc_page; @@ -408,20 +414,20 @@ static vm_fault_t sgx_encl_eaug_page(struct vm_area_struct *vma, mutex_unlock(&encl->lock); return VM_FAULT_SIGBUS; } +done: mutex_unlock(&encl->lock); return VM_FAULT_NOPAGE; -err_out: +err_out_eaug: xa_erase(&encl->page_array, PFN_DOWN(encl_page->desc)); - err_out_shrink: sgx_encl_shrink(encl, va_page); err_out_epc: sgx_encl_free_epc_page(epc_page); +err_out_encl: + kfree(encl_page); err_out_unlock: mutex_unlock(&encl->lock); - kfree(encl_page); - return vmret; } -- 2.43.0

8 months, 3 weeks

3
2
0 0

[PATCH v5 1/3] x86/sgx: Split SGX_ENCL_PAGE_BEING_RECLAIMED into two flags

by Dmitrii Kuvaiskii

The page reclaimer thread sets SGX_ENC_PAGE_BEING_RECLAIMED flag when the enclave page is being reclaimed (moved to the backing store). This flag however has two logical meanings: 1. Don't attempt to load the enclave page (the page is busy), see __sgx_encl_load_page(). 2. Don't attempt to remove the PCMD page corresponding to this enclave page (the PCMD page is busy), see reclaimer_writing_to_pcmd(). To reflect these two meanings, split SGX_ENCL_PAGE_BEING_RECLAIMED into two flags: SGX_ENCL_PAGE_BUSY and SGX_ENCL_PAGE_PCMD_BUSY. Currently, both flags are set only when the enclave page is being reclaimed (by the page reclaimer thread). A future commit will introduce new cases when the enclave page is being operated on; these new cases will set only the SGX_ENCL_PAGE_BUSY flag. Cc: stable(a)vger.kernel.org Signed-off-by: Dmitrii Kuvaiskii <dmitrii.kuvaiskii(a)intel.com> Reviewed-by: Haitao Huang <haitao.huang(a)linux.intel.com> Acked-by: Kai Huang <kai.huang(a)intel.com> --- arch/x86/kernel/cpu/sgx/encl.c | 16 +++++++--------- arch/x86/kernel/cpu/sgx/encl.h | 10 ++++++++-- arch/x86/kernel/cpu/sgx/main.c | 4 ++-- 3 files changed, 17 insertions(+), 13 deletions(-) diff --git a/arch/x86/kernel/cpu/sgx/encl.c b/arch/x86/kernel/cpu/sgx/encl.c index 279148e72459..c0a3c00284c8 100644 --- a/arch/x86/kernel/cpu/sgx/encl.c +++ b/arch/x86/kernel/cpu/sgx/encl.c @@ -46,10 +46,10 @@ static int sgx_encl_lookup_backing(struct sgx_encl *encl, unsigned long page_ind * a check if an enclave page sharing the PCMD page is in the process of being * reclaimed. * - * The reclaimer sets the SGX_ENCL_PAGE_BEING_RECLAIMED flag when it - * intends to reclaim that enclave page - it means that the PCMD page - * associated with that enclave page is about to get some data and thus - * even if the PCMD page is empty, it should not be truncated. + * The reclaimer sets the SGX_ENCL_PAGE_PCMD_BUSY flag when it intends to + * reclaim that enclave page - it means that the PCMD page associated with that + * enclave page is about to get some data and thus even if the PCMD page is + * empty, it should not be truncated. * * Context: Enclave mutex (&sgx_encl->lock) must be held. * Return: 1 if the reclaimer is about to write to the PCMD page @@ -77,8 +77,7 @@ static int reclaimer_writing_to_pcmd(struct sgx_encl *encl, * Stop when reaching the SECS page - it does not * have a page_array entry and its reclaim is * started and completed with enclave mutex held so - * it does not use the SGX_ENCL_PAGE_BEING_RECLAIMED - * flag. + * it does not use the SGX_ENCL_PAGE_PCMD_BUSY flag. */ if (addr == encl->base + encl->size) break; @@ -91,8 +90,7 @@ static int reclaimer_writing_to_pcmd(struct sgx_encl *encl, * VA page slot ID uses same bit as the flag so it is important * to ensure that the page is not already in backing store. */ - if (entry->epc_page && - (entry->desc & SGX_ENCL_PAGE_BEING_RECLAIMED)) { + if (entry->epc_page && (entry->desc & SGX_ENCL_PAGE_PCMD_BUSY)) { reclaimed = 1; break; } @@ -257,7 +255,7 @@ static struct sgx_encl_page *__sgx_encl_load_page(struct sgx_encl *encl, /* Entry successfully located. */ if (entry->epc_page) { - if (entry->desc & SGX_ENCL_PAGE_BEING_RECLAIMED) + if (entry->desc & SGX_ENCL_PAGE_BUSY) return ERR_PTR(-EBUSY); return entry; diff --git a/arch/x86/kernel/cpu/sgx/encl.h b/arch/x86/kernel/cpu/sgx/encl.h index f94ff14c9486..b566b8ad5f33 100644 --- a/arch/x86/kernel/cpu/sgx/encl.h +++ b/arch/x86/kernel/cpu/sgx/encl.h @@ -22,8 +22,14 @@ /* 'desc' bits holding the offset in the VA (version array) page. */ #define SGX_ENCL_PAGE_VA_OFFSET_MASK GENMASK_ULL(11, 3) -/* 'desc' bit marking that the page is being reclaimed. */ -#define SGX_ENCL_PAGE_BEING_RECLAIMED BIT(3) +/* 'desc' bit indicating that the page is busy (being reclaimed). */ +#define SGX_ENCL_PAGE_BUSY BIT(2) + +/* + * 'desc' bit indicating that PCMD page associated with the enclave page is + * busy (because the enclave page is being reclaimed). + */ +#define SGX_ENCL_PAGE_PCMD_BUSY BIT(3) struct sgx_encl_page { unsigned long desc; diff --git a/arch/x86/kernel/cpu/sgx/main.c b/arch/x86/kernel/cpu/sgx/main.c index 166692f2d501..e94b09c43673 100644 --- a/arch/x86/kernel/cpu/sgx/main.c +++ b/arch/x86/kernel/cpu/sgx/main.c @@ -204,7 +204,7 @@ static void sgx_encl_ewb(struct sgx_epc_page *epc_page, void *va_slot; int ret; - encl_page->desc &= ~SGX_ENCL_PAGE_BEING_RECLAIMED; + encl_page->desc &= ~(SGX_ENCL_PAGE_BUSY | SGX_ENCL_PAGE_PCMD_BUSY); va_page = list_first_entry(&encl->va_pages, struct sgx_va_page, list); @@ -340,7 +340,7 @@ static void sgx_reclaim_pages(void) goto skip; } - encl_page->desc |= SGX_ENCL_PAGE_BEING_RECLAIMED; + encl_page->desc |= SGX_ENCL_PAGE_BUSY | SGX_ENCL_PAGE_PCMD_BUSY; mutex_unlock(&encl_page->encl->lock); continue; -- 2.43.0

8 months, 3 weeks

2
1
0 0

[PATCH net] net: drop bad gso csum_start and offset in virtio_net_hdr

by Willem de Bruijn

From: Willem de Bruijn <willemb(a)google.com> Tighten csum_start and csum_offset checks in virtio_net_hdr_to_skb for GSO packets. The function already checks that a checksum requested with VIRTIO_NET_HDR_F_NEEDS_CSUM is in skb linear. But for GSO packets this might not hold for segs after segmentation. Syzkaller demonstrated to reach this warning in skb_checksum_help offset = skb_checksum_start_offset(skb); ret = -EINVAL; if (WARN_ON_ONCE(offset >= skb_headlen(skb))) By injecting a TSO packet: WARNING: CPU: 1 PID: 3539 at net/core/dev.c:3284 skb_checksum_help+0x3d0/0x5b0 ip_do_fragment+0x209/0x1b20 net/ipv4/ip_output.c:774 ip_finish_output_gso net/ipv4/ip_output.c:279 [inline] __ip_finish_output+0x2bd/0x4b0 net/ipv4/ip_output.c:301 iptunnel_xmit+0x50c/0x930 net/ipv4/ip_tunnel_core.c:82 ip_tunnel_xmit+0x2296/0x2c70 net/ipv4/ip_tunnel.c:813 __gre_xmit net/ipv4/ip_gre.c:469 [inline] ipgre_xmit+0x759/0xa60 net/ipv4/ip_gre.c:661 __netdev_start_xmit include/linux/netdevice.h:4850 [inline] netdev_start_xmit include/linux/netdevice.h:4864 [inline] xmit_one net/core/dev.c:3595 [inline] dev_hard_start_xmit+0x261/0x8c0 net/core/dev.c:3611 __dev_queue_xmit+0x1b97/0x3c90 net/core/dev.c:4261 packet_snd net/packet/af_packet.c:3073 [inline] The geometry of the bad input packet at tcp_gso_segment: [ 52.003050][ T8403] skb len=12202 headroom=244 headlen=12093 tailroom=0 [ 52.003050][ T8403] mac=(168,24) mac_len=24 net=(192,52) trans=244 [ 52.003050][ T8403] shinfo(txflags=0 nr_frags=1 gso(size=1552 type=3 segs=0)) [ 52.003050][ T8403] csum(0x60000c7 start=199 offset=1536 ip_summed=3 complete_sw=0 valid=0 level=0) Migitage with stricter input validation. csum_offset: for GSO packets, deduce the correct value from gso_type. This is already done for USO. Extend it to TSO. Let UFO be: udp[46]_ufo_fragment ignores these fields and always computes the checksum in software. csum_start: finding the real offset requires parsing to the transport header. Do not add a parser, use existing segmentation parsing. Thanks to SKB_GSO_DODGY, that also catches bad packets that are hw offloaded. Again test both TSO and USO. Do not test UFO for the above reason, and do not test UDP tunnel offload. GSO packet are almost always CHECKSUM_PARTIAL. USO packets may be CHECKSUM_NONE since commit 10154dbded6d6 ("udp: Allow GSO transmit from devices with no checksum offload"), but then still these fields are initialized correctly in udp4_hwcsum/udp6_hwcsum_outgoing. So no need to test for ip_summed == CHECKSUM_PARTIAL first. This revises an existing fix mentioned in the Fixes tag, which broke small packets with GSO offload, as detected by kselftests. Link: https://syzkaller.appspot.com/bug?extid=e1db31216c789f552871 Link: https://lore.kernel.org/netdev/20240723223109.2196886-1-kuba@kernel.org Fixes: e269d79c7d35 ("net: missing check virtio") Cc: stable(a)vger.kernel.org Signed-off-by: Willem de Bruijn <willemb(a)google.com> --- include/linux/virtio_net.h | 16 +++++----------- net/ipv4/tcp_offload.c | 3 +++ net/ipv4/udp_offload.c | 3 +++ 3 files changed, 11 insertions(+), 11 deletions(-) diff --git a/include/linux/virtio_net.h b/include/linux/virtio_net.h index d1d7825318c32..6c395a2600e8d 100644 --- a/include/linux/virtio_net.h +++ b/include/linux/virtio_net.h @@ -56,7 +56,6 @@ static inline int virtio_net_hdr_to_skb(struct sk_buff *skb, unsigned int thlen = 0; unsigned int p_off = 0; unsigned int ip_proto; - u64 ret, remainder, gso_size; if (hdr->gso_type != VIRTIO_NET_HDR_GSO_NONE) { switch (hdr->gso_type & ~VIRTIO_NET_HDR_GSO_ECN) { @@ -99,16 +98,6 @@ static inline int virtio_net_hdr_to_skb(struct sk_buff *skb, u32 off = __virtio16_to_cpu(little_endian, hdr->csum_offset); u32 needed = start + max_t(u32, thlen, off + sizeof(__sum16)); - if (hdr->gso_size) { - gso_size = __virtio16_to_cpu(little_endian, hdr->gso_size); - ret = div64_u64_rem(skb->len, gso_size, &remainder); - if (!(ret && (hdr->gso_size > needed) && - ((remainder > needed) || (remainder == 0)))) { - return -EINVAL; - } - skb_shinfo(skb)->tx_flags |= SKBFL_SHARED_FRAG; - } - if (!pskb_may_pull(skb, needed)) return -EINVAL; @@ -182,6 +171,11 @@ static inline int virtio_net_hdr_to_skb(struct sk_buff *skb, if (gso_type != SKB_GSO_UDP_L4) return -EINVAL; break; + case SKB_GSO_TCPV4: + case SKB_GSO_TCPV6: + if (skb->csum_offset != offsetof(struct tcphdr, check)) + return -EINVAL; + break; } /* Kernel has a special handling for GSO_BY_FRAGS. */ diff --git a/net/ipv4/tcp_offload.c b/net/ipv4/tcp_offload.c index 4b791e74529e1..9e49ffcc77071 100644 --- a/net/ipv4/tcp_offload.c +++ b/net/ipv4/tcp_offload.c @@ -140,6 +140,9 @@ struct sk_buff *tcp_gso_segment(struct sk_buff *skb, if (thlen < sizeof(*th)) goto out; + if (unlikely(skb->csum_start != skb->transport_header)) + goto out; + if (!pskb_may_pull(skb, thlen)) goto out; diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c index aa2e0a28ca613..f521152c40871 100644 --- a/net/ipv4/udp_offload.c +++ b/net/ipv4/udp_offload.c @@ -278,6 +278,9 @@ struct sk_buff *__udp_gso_segment(struct sk_buff *gso_skb, if (gso_skb->len <= sizeof(*uh) + mss) return ERR_PTR(-EINVAL); + if (unlikely(gso_skb->csum_start != gso_skb->transport_header)) + return ERR_PTR(-EINVAL); + if (skb_gso_ok(gso_skb, features | NETIF_F_GSO_ROBUST)) { /* Packet is from an untrusted source, reset gso_segs. */ skb_shinfo(gso_skb)->gso_segs = DIV_ROUND_UP(gso_skb->len - sizeof(*uh), -- 2.46.0.rc1.232.g9752f9e123-goog

8 months, 3 weeks

10
25
0 0

[PATCH v2] spi: rockchip: Resolve unbalanced runtime PM / system PM handling

by Brian Norris

Commit e882575efc77 ("spi: rockchip: Suspend and resume the bus during NOIRQ_SYSTEM_SLEEP_PM ops") stopped respecting runtime PM status and simply disabled clocks unconditionally when suspending the system. This causes problems when the device is already runtime suspended when we go to sleep -- in which case we double-disable clocks and produce a WARNing. Switch back to pm_runtime_force_{suspend,resume}(), because that still seems like the right thing to do, and the aforementioned commit makes no explanation why it stopped using it. Also, refactor some of the resume() error handling, because it's not actually a good idea to re-disable clocks on failure. Fixes: e882575efc77 ("spi: rockchip: Suspend and resume the bus during NOIRQ_SYSTEM_SLEEP_PM ops") Cc: <stable(a)vger.kernel.org> Reported-by: "Ondřej Jirman" <megi(a)xff.cz> Closes: https://lore.kernel.org/lkml/20220621154218.sau54jeij4bunf56@core/ Signed-off-by: Brian Norris <briannorris(a)chromium.org> --- Changes in v2: - fix unused 'rs' warning drivers/spi/spi-rockchip.c | 23 +++++++---------------- 1 file changed, 7 insertions(+), 16 deletions(-) diff --git a/drivers/spi/spi-rockchip.c b/drivers/spi/spi-rockchip.c index e1ecd96c7858..0bb33c43b1b4 100644 --- a/drivers/spi/spi-rockchip.c +++ b/drivers/spi/spi-rockchip.c @@ -945,14 +945,16 @@ static int rockchip_spi_suspend(struct device *dev) { int ret; struct spi_controller *ctlr = dev_get_drvdata(dev); - struct rockchip_spi *rs = spi_controller_get_devdata(ctlr); ret = spi_controller_suspend(ctlr); if (ret < 0) return ret; - clk_disable_unprepare(rs->spiclk); - clk_disable_unprepare(rs->apb_pclk); + ret = pm_runtime_force_suspend(dev); + if (ret < 0) { + spi_controller_resume(ctlr); + return ret; + } pinctrl_pm_select_sleep_state(dev); @@ -963,25 +965,14 @@ static int rockchip_spi_resume(struct device *dev) { int ret; struct spi_controller *ctlr = dev_get_drvdata(dev); - struct rockchip_spi *rs = spi_controller_get_devdata(ctlr); pinctrl_pm_select_default_state(dev); - ret = clk_prepare_enable(rs->apb_pclk); + ret = pm_runtime_force_resume(dev); if (ret < 0) return ret; - ret = clk_prepare_enable(rs->spiclk); - if (ret < 0) - clk_disable_unprepare(rs->apb_pclk); - - ret = spi_controller_resume(ctlr); - if (ret < 0) { - clk_disable_unprepare(rs->spiclk); - clk_disable_unprepare(rs->apb_pclk); - } - - return 0; + return spi_controller_resume(ctlr); } #endif /* CONFIG_PM_SLEEP */ -- 2.46.0.295.g3b9ea8a38a-goog

8 months, 3 weeks

1
0
0 0

Re: [PATCH 6.10 000/273] 6.10.7-rc1 review

by Ronald Warsow

Hi Greg no regressions here on x86_64 (RKL, Intel 11th Gen. CPU) Thanks Tested-by: Ronald Warsow <rwarsow(a)gmx.de>

8 months, 3 weeks

1
0
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-stable-mirror August 2024