August 2024 - Linux-stable-mirror

[PATCH v3] usb: dwc3: core: Prevent USB core invalid event buffer address access

by Selvarasu Ganesan

This commit addresses an issue where the USB core could access an invalid event buffer address during runtime suspend, potentially causing SMMU faults and other memory issues in Exynos platforms. The problem arises from the following sequence. 1. In dwc3_gadget_suspend, there is a chance of a timeout when moving the USB core to the halt state after clearing the run/stop bit by software. 2. In dwc3_core_exit, the event buffer is cleared regardless of the USB core's status, which may lead to an SMMU faults and other memory issues. if the USB core tries to access the event buffer address. To prevent this hardware quirk on Exynos platforms, this commit ensures that the event buffer address is not cleared by software when the USB core is active during runtime suspend by checking its status before clearing the buffer address. Cc: stable(a)vger.kernel.org # v6.1+ Signed-off-by: Selvarasu Ganesan <selvarasu.g(a)samsung.com> --- Changes in v3: - Added comment on why we need this fix. - Included platform name in commit message. - Removed Fixes tag as no issue on the previous commits, and updated Cc tag. - Link to v2: https://lore.kernel.org/lkml/20240808120507.1464-1-selvarasu.g@samsung.com/ Changes in v2: - Added separate check for USB controller status before cleaning the event buffer. - Link to v1: https://lore.kernel.org/lkml/20240722145617.537-1-selvarasu.g@samsung.com/ --- drivers/usb/dwc3/core.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/drivers/usb/dwc3/core.c b/drivers/usb/dwc3/core.c index 734de2a8bd21..ccc3895dbd7f 100644 --- a/drivers/usb/dwc3/core.c +++ b/drivers/usb/dwc3/core.c @@ -564,9 +564,17 @@ int dwc3_event_buffers_setup(struct dwc3 *dwc) void dwc3_event_buffers_cleanup(struct dwc3 *dwc) { struct dwc3_event_buffer *evt; + u32 reg; if (!dwc->ev_buf) return; + /* + * Exynos platforms may not be able to access event buffer if the + * controller failed to halt on dwc3_core_exit(). + */ + reg = dwc3_readl(dwc->regs, DWC3_DSTS); + if (!(reg & DWC3_DSTS_DEVCTRLHLT)) + return; evt = dwc->ev_buf; -- 2.17.1

1 year, 3 months

3
8
0 0

+ codetag-debug-mark-codetags-for-poisoned-page-as-empty.patch added to mm-hotfixes-unstable branch

by Andrew Morton

The patch titled Subject: codetag: debug: mark codetags for poisoned page as empty has been added to the -mm mm-hotfixes-unstable branch. Its filename is codetag-debug-mark-codetags-for-poisoned-page-as-empty.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: Hao Ge <gehao(a)kylinos.cn> Subject: codetag: debug: mark codetags for poisoned page as empty Date: Mon, 26 Aug 2024 00:36:49 +0800 When PG_hwpoison pages are freed they are treated differently in free_pages_prepare() and instead of being released they are isolated. Page allocation tag counters are decremented at this point since the page is considered not in use. Later on when such pages are released by unpoison_memory(), the allocation tag counters will be decremented again and the following warning gets reported: [ 113.930443][ T3282] ------------[ cut here ]------------ [ 113.931105][ T3282] alloc_tag was not set [ 113.931576][ T3282] WARNING: CPU: 2 PID: 3282 at ./include/linux/alloc_tag.h:130 pgalloc_tag_sub.part.66+0x154/0x164 [ 113.932866][ T3282] Modules linked in: hwpoison_inject fuse ip6t_rpfilter ip6t_REJECT nf_reject_ipv6 ipt_REJECT nf_reject_ipv4 xt_conntrack ebtable_nat ebtable_broute ip6table_nat ip6table_man4 [ 113.941638][ T3282] CPU: 2 UID: 0 PID: 3282 Comm: madvise11 Kdump: loaded Tainted: G W 6.11.0-rc4-dirty #18 [ 113.943003][ T3282] Tainted: [W]=WARN [ 113.943453][ T3282] Hardware name: QEMU KVM Virtual Machine, BIOS unknown 2/2/2022 [ 113.944378][ T3282] pstate: 40400005 (nZcv daif +PAN -UAO -TCO -DIT -SSBS BTYPE=--) [ 113.945319][ T3282] pc : pgalloc_tag_sub.part.66+0x154/0x164 [ 113.946016][ T3282] lr : pgalloc_tag_sub.part.66+0x154/0x164 [ 113.946706][ T3282] sp : ffff800087093a10 [ 113.947197][ T3282] x29: ffff800087093a10 x28: ffff0000d7a9d400 x27: ffff80008249f0a0 [ 113.948165][ T3282] x26: 0000000000000000 x25: ffff80008249f2b0 x24: 0000000000000000 [ 113.949134][ T3282] x23: 0000000000000001 x22: 0000000000000001 x21: 0000000000000000 [ 113.950597][ T3282] x20: ffff0000c08fcad8 x19: ffff80008251e000 x18: ffffffffffffffff [ 113.952207][ T3282] x17: 0000000000000000 x16: 0000000000000000 x15: ffff800081746210 [ 113.953161][ T3282] x14: 0000000000000000 x13: 205d323832335420 x12: 5b5d353031313339 [ 113.954120][ T3282] x11: ffff800087093500 x10: 000000000000005d x9 : 00000000ffffffd0 [ 113.955078][ T3282] x8 : 7f7f7f7f7f7f7f7f x7 : ffff80008236ba90 x6 : c0000000ffff7fff [ 113.956036][ T3282] x5 : ffff000b34bf4dc8 x4 : ffff8000820aba90 x3 : 0000000000000001 [ 113.956994][ T3282] x2 : ffff800ab320f000 x1 : 841d1e35ac932e00 x0 : 0000000000000000 [ 113.957962][ T3282] Call trace: [ 113.958350][ T3282] pgalloc_tag_sub.part.66+0x154/0x164 [ 113.959000][ T3282] pgalloc_tag_sub+0x14/0x1c [ 113.959539][ T3282] free_unref_page+0xf4/0x4b8 [ 113.960096][ T3282] __folio_put+0xd4/0x120 [ 113.960614][ T3282] folio_put+0x24/0x50 [ 113.961103][ T3282] unpoison_memory+0x4f0/0x5b0 [ 113.961678][ T3282] hwpoison_unpoison+0x30/0x48 [hwpoison_inject] [ 113.962436][ T3282] simple_attr_write_xsigned.isra.34+0xec/0x1cc [ 113.963183][ T3282] simple_attr_write+0x38/0x48 [ 113.963750][ T3282] debugfs_attr_write+0x54/0x80 [ 113.964330][ T3282] full_proxy_write+0x68/0x98 [ 113.964880][ T3282] vfs_write+0xdc/0x4d0 [ 113.965372][ T3282] ksys_write+0x78/0x100 [ 113.965875][ T3282] __arm64_sys_write+0x24/0x30 [ 113.966440][ T3282] invoke_syscall+0x7c/0x104 [ 113.966984][ T3282] el0_svc_common.constprop.1+0x88/0x104 [ 113.967652][ T3282] do_el0_svc+0x2c/0x38 [ 113.968893][ T3282] el0_svc+0x3c/0x1b8 [ 113.969379][ T3282] el0t_64_sync_handler+0x98/0xbc [ 113.969980][ T3282] el0t_64_sync+0x19c/0x1a0 [ 113.970511][ T3282] ---[ end trace 0000000000000000 ]--- To fix this, clear the page tag reference after the page got isolated and accounted for. Link: https://lkml.kernel.org/r/20240825163649.33294-1-hao.ge@linux.dev Fixes: d224eb0287fb ("codetag: debug: mark codetags for reserved pages as empty") Signed-off-by: Hao Ge <gehao(a)kylinos.cn> Reviewed-by: Miaohe Lin <linmiaohe(a)huawei.com> Acked-by: Suren Baghdasaryan <surenb(a)google.com> Cc: David Hildenbrand <david(a)redhat.com> Cc: Hao Ge <gehao(a)kylinos.cn> Cc: Kent Overstreet <kent.overstreet(a)linux.dev> Cc: Naoya Horiguchi <nao.horiguchi(a)gmail.com> Cc: Pasha Tatashin <pasha.tatashin(a)soleen.com> Cc: <stable(a)vger.kernel.org> [6.10+] Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- mm/page_alloc.c | 7 +++++++ 1 file changed, 7 insertions(+) --- a/mm/page_alloc.c~codetag-debug-mark-codetags-for-poisoned-page-as-empty +++ a/mm/page_alloc.c @@ -1054,6 +1054,13 @@ __always_inline bool free_pages_prepare( reset_page_owner(page, order); page_table_check_free(page, order); pgalloc_tag_sub(page, 1 << order); + + /* + * The page is isolated and accounted for. + * Mark the codetag as empty to avoid accounting error + * when the page is freed by unpoison_memory(). + */ + clear_page_tag_ref(page); return false; } _ Patches currently in -mm which might be from gehao(a)kylinos.cn are mm-slub-add-check-for-s-flags-in-the-alloc_tagging_slab_free_hook.patch codetag-debug-mark-codetags-for-poisoned-page-as-empty.patch mm-cma-change-the-addition-of-totalcma_pages-in-the-cma_init_reserved_mem.patch

1 year, 3 months

1
0
0 0

[PATCH 1/1] PM / devfreq: Fix buffer overflow in trans_stat_show

by Koichiro Den

From: Christian Marangi <ansuelsmth(a)gmail.com> Fix buffer overflow in trans_stat_show(). Convert simple snprintf to the more secure scnprintf with size of PAGE_SIZE. Add condition checking if we are exceeding PAGE_SIZE and exit early from loop. Also add at the end a warning that we exceeded PAGE_SIZE and that stats is disabled. Return -EFBIG in the case where we don't have enough space to write the full transition table. Also document in the ABI that this function can return -EFBIG error. Link: https://lore.kernel.org/all/20231024183016.14648-2-ansuelsmth@gmail.com/ Cc: stable(a)vger.kernel.org Closes: https://bugzilla.kernel.org/show_bug.cgi?id=218041 Fixes: e552bbaf5b98 ("PM / devfreq: Add sysfs node for representing frequency transition information.") Signed-off-by: Christian Marangi <ansuelsmth(a)gmail.com> Signed-off-by: Chanwoo Choi <cw00.choi(a)samsung.com> (backported from commit 08e23d05fa6dc4fc13da0ccf09defdd4bbc92ff4) [koichiroden: Adjusted context due to missing commits: commit b5d281f6c16d ("PM / devfreq: Rework freq_table to be local to devfreq struct") commit a03dacb0316f ("PM / devfreq: Add cpu based scaling support to passive governor") commit 483d557ee9a3 ("PM / devfreq: Clean up the devfreq instance name in sysfs attr") commit 1ebd0bc0e8ad ("PM / devfreq: Move statistics to separate struct devfreq_stats") commit 14a343968199 ("PM / devfreq: Add clearing transitions stats") commit b76b3479dab9 ("PM / devfreq: Change time stats to 64-bit") commit 5c0f6c795957 ("PM / devfreq: Add new interrupt_driven flag for governors")] CVE-2023-52614 Signed-off-by: Koichiro Den <koichiro.den(a)canonical.com> --- Documentation/ABI/testing/sysfs-class-devfreq | 2 + drivers/devfreq/devfreq.c | 60 +++++++++++++------ 2 files changed, 43 insertions(+), 19 deletions(-) diff --git a/Documentation/ABI/testing/sysfs-class-devfreq b/Documentation/ABI/testing/sysfs-class-devfreq index 75897e2fde43..f95b69551b60 100644 --- a/Documentation/ABI/testing/sysfs-class-devfreq +++ b/Documentation/ABI/testing/sysfs-class-devfreq @@ -61,6 +61,8 @@ Description: In order to activate this ABI, the devfreq target device driver should provide the list of available frequencies with its profile. + If the transition table is bigger than PAGE_SIZE, reading + this will return an -EFBIG error. What: /sys/class/devfreq/.../userspace/set_freq Date: September 2011 diff --git a/drivers/devfreq/devfreq.c b/drivers/devfreq/devfreq.c index 31e6cb5211bc..7a6115c23ec8 100644 --- a/drivers/devfreq/devfreq.c +++ b/drivers/devfreq/devfreq.c @@ -1403,12 +1403,12 @@ static ssize_t trans_stat_show(struct device *dev, struct device_attribute *attr, char *buf) { struct devfreq *devfreq = to_devfreq(dev); - ssize_t len; + ssize_t len = 0; int i, j; unsigned int max_state = devfreq->profile->max_state; if (max_state == 0) - return sprintf(buf, "Not Supported.\n"); + return scnprintf(buf, PAGE_SIZE, "Not Supported.\n"); mutex_lock(&devfreq->lock); if (!devfreq->stop_polling && @@ -1418,32 +1418,54 @@ static ssize_t trans_stat_show(struct device *dev, } mutex_unlock(&devfreq->lock); - len = sprintf(buf, " From : To\n"); - len += sprintf(buf + len, " :"); - for (i = 0; i < max_state; i++) - len += sprintf(buf + len, "%10lu", - devfreq->profile->freq_table[i]); + len += scnprintf(buf + len, PAGE_SIZE - len, " From : To\n"); + len += scnprintf(buf + len, PAGE_SIZE - len, " :"); + for (i = 0; i < max_state; i++) { + if (len >= PAGE_SIZE - 1) + break; + len += scnprintf(buf + len, PAGE_SIZE - len, "%10lu", + devfreq->profile->freq_table[i]); + } + if (len >= PAGE_SIZE - 1) + return PAGE_SIZE - 1; - len += sprintf(buf + len, " time(ms)\n"); + len += scnprintf(buf + len, PAGE_SIZE - len, " time(ms)\n"); for (i = 0; i < max_state; i++) { + if (len >= PAGE_SIZE - 1) + break; if (devfreq->profile->freq_table[i] == devfreq->previous_freq) { - len += sprintf(buf + len, "*"); + len += scnprintf(buf + len, PAGE_SIZE - len, "*"); } else { - len += sprintf(buf + len, " "); + len += scnprintf(buf + len, PAGE_SIZE - len, " "); + } + if (len >= PAGE_SIZE - 1) + break; + + len += scnprintf(buf + len, PAGE_SIZE - len, "%10lu:", + devfreq->profile->freq_table[i]); + for (j = 0; j < max_state; j++) { + if (len >= PAGE_SIZE - 1) + break; + len += scnprintf(buf + len, PAGE_SIZE - len, "%10u", + devfreq->trans_table[(i * max_state) + j]); } - len += sprintf(buf + len, "%10lu:", - devfreq->profile->freq_table[i]); - for (j = 0; j < max_state; j++) - len += sprintf(buf + len, "%10u", - devfreq->trans_table[(i * max_state) + j]); - len += sprintf(buf + len, "%10u\n", - jiffies_to_msecs(devfreq->time_in_state[i])); + if (len >= PAGE_SIZE - 1) + break; + len += scnprintf(buf + len, PAGE_SIZE - len, "%10u\n", + jiffies_to_msecs(devfreq->time_in_state[i])); + } + + if (len < PAGE_SIZE - 1) + len += scnprintf(buf + len, PAGE_SIZE - len, "Total transition : %u\n", + devfreq->total_trans); + + if (len >= PAGE_SIZE - 1) { + pr_warn_once("devfreq transition table exceeds PAGE_SIZE. Disabling\n"); + return -EFBIG; } - len += sprintf(buf + len, "Total transition : %u\n", - devfreq->total_trans); return len; } static DEVICE_ATTR_RO(trans_stat); -- 2.43.0

1 year, 3 months

1
1
0 0

[PATCH v4] usb: dwc3: Avoid waking up gadget during startxfer

by Prashanth K

When operating in High-Speed, it is observed that DSTS[USBLNKST] doesn't update link state immediately after receiving the wakeup interrupt. Since wakeup event handler calls the resume callbacks, there is a chance that function drivers can perform an ep queue, which in turn tries to perform remote wakeup from send_gadget_ep_cmd(STARTXFER). This happens because DSTS[[21:18] wasn't updated to U0 yet, it's observed that the latency of DSTS can be in order of milli-seconds. Hence avoid calling gadget_wakeup during startxfer to prevent unnecessarily issuing remote wakeup to host. Fixes: c36d8e947a56 ("usb: dwc3: gadget: put link to U0 before Start Transfer") Cc: <stable(a)vger.kernel.org> Suggested-by: Thinh Nguyen <Thinh.Nguyen(a)synopsys.com> Signed-off-by: Prashanth K <quic_prashk(a)quicinc.com> --- v4: Rewording the comment in function definition. v3: Added notes on top the function definition. v2: Refactored the patch as suggested in v1 discussion. drivers/usb/dwc3/gadget.c | 38 ++++++++++++++------------------------ 1 file changed, 14 insertions(+), 24 deletions(-) diff --git a/drivers/usb/dwc3/gadget.c b/drivers/usb/dwc3/gadget.c index 89fc690fdf34..ea583d24aa37 100644 --- a/drivers/usb/dwc3/gadget.c +++ b/drivers/usb/dwc3/gadget.c @@ -287,6 +287,20 @@ static int __dwc3_gadget_wakeup(struct dwc3 *dwc, bool async); * * Caller should handle locking. This function will issue @cmd with given * @params to @dep and wait for its completion. + * + * According to databook, while issuing StartXfer command if the link is in L1/L2/U3, + * then the command may not complete and timeout, hence software must bring the link + * back to ON state by performing remote wakeup. However, since issuing a command in + * USB2 speeds requires the clearing of GUSB2PHYCFG.SUSPENDUSB2, which turns on the + * signal required to complete the given command (usually within 50us). This should + * happen within the command timeout set by driver. Hence we don't expect to trigger + * a remote wakeup from here; instead it should be done by wakeup ops. + * + * Special note: If wakeup ops is triggered for remote wakeup, care should be taken + * if StartXfer command needs to be sent soon after. The wakeup ops is asynchronous + * and the link state may not transition to ON state yet. And after receiving wakeup + * event, device would no longer be in U3, and any link transition afterwards needs + * to be adressed with wakeup ops. */ int dwc3_send_gadget_ep_cmd(struct dwc3_ep *dep, unsigned int cmd, struct dwc3_gadget_ep_cmd_params *params) @@ -327,30 +341,6 @@ int dwc3_send_gadget_ep_cmd(struct dwc3_ep *dep, unsigned int cmd, dwc3_writel(dwc->regs, DWC3_GUSB2PHYCFG(0), reg); } - if (DWC3_DEPCMD_CMD(cmd) == DWC3_DEPCMD_STARTTRANSFER) { - int link_state; - - /* - * Initiate remote wakeup if the link state is in U3 when - * operating in SS/SSP or L1/L2 when operating in HS/FS. If the - * link state is in U1/U2, no remote wakeup is needed. The Start - * Transfer command will initiate the link recovery. - */ - link_state = dwc3_gadget_get_link_state(dwc); - switch (link_state) { - case DWC3_LINK_STATE_U2: - if (dwc->gadget->speed >= USB_SPEED_SUPER) - break; - - fallthrough; - case DWC3_LINK_STATE_U3: - ret = __dwc3_gadget_wakeup(dwc, false); - dev_WARN_ONCE(dwc->dev, ret, "wakeup failed --> %d\n", - ret); - break; - } - } - /* * For some commands such as Update Transfer command, DEPCMDPARn * registers are reserved. Since the driver often sends Update Transfer -- 2.25.1

1 year, 3 months

2
1
0 0

[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

1 year, 3 months

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>

1 year, 3 months

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

1 year, 3 months

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

1 year, 3 months

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

1 year, 3 months

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

1 year, 3 months

3
2
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-stable-mirror August 2024