May 2023 - Linux-stable-mirror

[PATCH v6 0/5] mfd: tps6586x: register restart handler

by Benjamin Bara

Hi! The Tegra20 requires an enabled VDE power domain during startup. As the VDE is currently not used, it is disabled during runtime. Since 8f0c714ad9be, there is a workaround for the "normal restart path" which enables the VDE before doing PMC's warm reboot. This workaround is not executed in the "emergency restart path", leading to a hang-up during start. This series implements and registers a new pmic-based restart handler for boards with tps6586x. This cold reboot ensures that the VDE power domain is enabled during startup on tegra20-based boards. Since bae1d3a05a8b, i2c transfers are non-atomic while preemption is disabled (which is e.g. done during panic()). This could lead to warnings ("Voluntary context switch within RCU") in i2c-based restart handlers during emergency restart. The state of preemption should be detected by i2c_in_atomic_xfer_mode() to use atomic i2c xfer when required. Beside the new system_state check, the check is the same as the one pre v5.2. v5: https://lore.kernel.org/r/20230327-tegra-pmic-reboot-v5-0-ab090e03284d@skid… v6: - drop 4/6 to abort restart on unexpected failure (suggested by Dmitry) - 4,5: fix comments in handlers (suggested by Lee) - 4,5: same delay for both handlers (suggested by Lee) v5: - introduce new 3 & 4, therefore 3 -> 5, 4 -> 6 - 3: provide dev to sys_off handler, if it is known - 4: return NOTIFY_DONE from sys_off_notify, to avoid skipping - 5: drop Reviewed-by from Dmitry, add poweroff timeout - 5,6: return notifier value instead of direct errno from handler - 5,6: use new dev field instead of passing dev as cb_data - 5,6: increase timeout values based on error observations - 6: skip unsupported reboot modes in restart handler --- Benjamin Bara (5): kernel/reboot: emergency_restart: set correct system_state i2c: core: run atomic i2c xfer when !preemptible kernel/reboot: add device to sys_off_handler mfd: tps6586x: use devm-based power off handler mfd: tps6586x: register restart handler drivers/i2c/i2c-core.h | 2 +- drivers/mfd/tps6586x.c | 55 ++++++++++++++++++++++++++++++++++++++++++-------- include/linux/reboot.h | 3 +++ kernel/reboot.c | 4 ++++ 4 files changed, 55 insertions(+), 9 deletions(-) --- base-commit: 197b6b60ae7bc51dd0814953c562833143b292aa change-id: 20230327-tegra-pmic-reboot-4175ff814a4b Best regards, -- Benjamin Bara <benjamin.bara(a)skidata.com>

11 months, 1 week

4
8
0 0

[PATCH v3 4/6] Revert "PCI: hv: Fix a timing issue which causes kdump to fail occasionally"

by Dexuan Cui

This reverts commit d6af2ed29c7c1c311b96dac989dcb991e90ee195. The statement "the hv_pci_bus_exit() call releases structures of all its child devices" in commit d6af2ed29c7c is not true: in the path hv_pci_probe() -> hv_pci_enter_d0() -> hv_pci_bus_exit(hdev, true): the parameter "keep_devs" is true, so hv_pci_bus_exit() does *not* release the child "struct hv_pci_dev *hpdev" that is created earlier in pci_devices_present_work() -> new_pcichild_device(). The commit d6af2ed29c7c was originally made in July 2020 for RHEL 7.7, where the old version of hv_pci_bus_exit() was used; when the commit was rebased and merged into the upstream, people didn't notice that it's not really necessary. The commit itself doesn't cause any issue, but it makes hv_pci_probe() more complicated. Revert it to facilitate some upcoming changes to hv_pci_probe(). Signed-off-by: Dexuan Cui <decui(a)microsoft.com> Reviewed-by: Michael Kelley <mikelley(a)microsoft.com> Acked-by: Wei Hu <weh(a)microsoft.com> Cc: stable(a)vger.kernel.org --- v2: No change to the patch body. Added Wei Hu's Acked-by. Added Cc:stable v3: Added Michael's Reviewed-by. drivers/pci/controller/pci-hyperv.c | 71 ++++++++++++++--------------- 1 file changed, 34 insertions(+), 37 deletions(-) diff --git a/drivers/pci/controller/pci-hyperv.c b/drivers/pci/controller/pci-hyperv.c index 46df6d093d683..48feab095a144 100644 --- a/drivers/pci/controller/pci-hyperv.c +++ b/drivers/pci/controller/pci-hyperv.c @@ -3225,8 +3225,10 @@ static int hv_pci_enter_d0(struct hv_device *hdev) struct pci_bus_d0_entry *d0_entry; struct hv_pci_compl comp_pkt; struct pci_packet *pkt; + bool retry = true; int ret; +enter_d0_retry: /* * Tell the host that the bus is ready to use, and moved into the * powered-on state. This includes telling the host which region @@ -3253,6 +3255,38 @@ static int hv_pci_enter_d0(struct hv_device *hdev) if (ret) goto exit; + /* + * In certain case (Kdump) the pci device of interest was + * not cleanly shut down and resource is still held on host + * side, the host could return invalid device status. + * We need to explicitly request host to release the resource + * and try to enter D0 again. + */ + if (comp_pkt.completion_status < 0 && retry) { + retry = false; + + dev_err(&hdev->device, "Retrying D0 Entry\n"); + + /* + * Hv_pci_bus_exit() calls hv_send_resource_released() + * to free up resources of its child devices. + * In the kdump kernel we need to set the + * wslot_res_allocated to 255 so it scans all child + * devices to release resources allocated in the + * normal kernel before panic happened. + */ + hbus->wslot_res_allocated = 255; + + ret = hv_pci_bus_exit(hdev, true); + + if (ret == 0) { + kfree(pkt); + goto enter_d0_retry; + } + dev_err(&hdev->device, + "Retrying D0 failed with ret %d\n", ret); + } + if (comp_pkt.completion_status < 0) { dev_err(&hdev->device, "PCI Pass-through VSP failed D0 Entry with status %x\n", @@ -3493,7 +3527,6 @@ static int hv_pci_probe(struct hv_device *hdev, struct hv_pcibus_device *hbus; u16 dom_req, dom; char *name; - bool enter_d0_retry = true; int ret; /* @@ -3633,47 +3666,11 @@ static int hv_pci_probe(struct hv_device *hdev, if (ret) goto free_fwnode; -retry: ret = hv_pci_query_relations(hdev); if (ret) goto free_irq_domain; ret = hv_pci_enter_d0(hdev); - /* - * In certain case (Kdump) the pci device of interest was - * not cleanly shut down and resource is still held on host - * side, the host could return invalid device status. - * We need to explicitly request host to release the resource - * and try to enter D0 again. - * Since the hv_pci_bus_exit() call releases structures - * of all its child devices, we need to start the retry from - * hv_pci_query_relations() call, requesting host to send - * the synchronous child device relations message before this - * information is needed in hv_send_resources_allocated() - * call later. - */ - if (ret == -EPROTO && enter_d0_retry) { - enter_d0_retry = false; - - dev_err(&hdev->device, "Retrying D0 Entry\n"); - - /* - * Hv_pci_bus_exit() calls hv_send_resources_released() - * to free up resources of its child devices. - * In the kdump kernel we need to set the - * wslot_res_allocated to 255 so it scans all child - * devices to release resources allocated in the - * normal kernel before panic happened. - */ - hbus->wslot_res_allocated = 255; - ret = hv_pci_bus_exit(hdev, true); - - if (ret == 0) - goto retry; - - dev_err(&hdev->device, - "Retrying D0 failed with ret %d\n", ret); - } if (ret) goto free_irq_domain; -- 2.25.1

11 months, 1 week

2
2
0 0

[PATCH v3 3/6] PCI: hv: Remove the useless hv_pcichild_state from struct hv_pci_dev

by Dexuan Cui

The hpdev->state is never really useful. The only use in hv_pci_eject_device() and hv_eject_device_work() is not really necessary. Signed-off-by: Dexuan Cui <decui(a)microsoft.com> Reviewed-by: Michael Kelley <mikelley(a)microsoft.com> Cc: stable(a)vger.kernel.org --- v2: No change to the patch body. Added Cc:stable v3: Added Michael's Reviewed-by. drivers/pci/controller/pci-hyperv.c | 12 ------------ 1 file changed, 12 deletions(-) diff --git a/drivers/pci/controller/pci-hyperv.c b/drivers/pci/controller/pci-hyperv.c index 1b11cf7391933..46df6d093d683 100644 --- a/drivers/pci/controller/pci-hyperv.c +++ b/drivers/pci/controller/pci-hyperv.c @@ -553,19 +553,10 @@ struct hv_dr_state { struct hv_pcidev_description func[]; }; -enum hv_pcichild_state { - hv_pcichild_init = 0, - hv_pcichild_requirements, - hv_pcichild_resourced, - hv_pcichild_ejecting, - hv_pcichild_maximum -}; - struct hv_pci_dev { /* List protected by pci_rescan_remove_lock */ struct list_head list_entry; refcount_t refs; - enum hv_pcichild_state state; struct pci_slot *pci_slot; struct hv_pcidev_description desc; bool reported_missing; @@ -2750,8 +2741,6 @@ static void hv_eject_device_work(struct work_struct *work) hpdev = container_of(work, struct hv_pci_dev, wrk); hbus = hpdev->hbus; - WARN_ON(hpdev->state != hv_pcichild_ejecting); - /* * Ejection can come before or after the PCI bus has been set up, so * attempt to find it and tear down the bus state, if it exists. This @@ -2808,7 +2797,6 @@ static void hv_pci_eject_device(struct hv_pci_dev *hpdev) return; } - hpdev->state = hv_pcichild_ejecting; get_pcichild(hpdev); INIT_WORK(&hpdev->wrk, hv_eject_device_work); queue_work(hbus->wq, &hpdev->wrk); -- 2.25.1

11 months, 1 week

2
2
0 0

[PATCH v3 2/6] PCI: hv: Fix a race condition in hv_irq_unmask() that can cause panic

by Dexuan Cui

When the host tries to remove a PCI device, the host first sends a PCI_EJECT message to the guest, and the guest is supposed to gracefully remove the PCI device and send a PCI_EJECTION_COMPLETE message to the host; the host then sends a VMBus message CHANNELMSG_RESCIND_CHANNELOFFER to the guest (when the guest receives this message, the device is already unassigned from the guest) and the guest can do some final cleanup work; if the guest fails to respond to the PCI_EJECT message within one minute, the host sends the VMBus message CHANNELMSG_RESCIND_CHANNELOFFER and removes the PCI device forcibly. In the case of fast device addition/removal, it's possible that the PCI device driver is still configuring MSI-X interrupts when the guest receives the PCI_EJECT message; the channel callback calls hv_pci_eject_device(), which sets hpdev->state to hv_pcichild_ejecting, and schedules a work hv_eject_device_work(); if the PCI device driver is calling pci_alloc_irq_vectors() -> ... -> hv_compose_msi_msg(), we can break the while loop in hv_compose_msi_msg() due to the updated hpdev->state, and leave data->chip_data with its default value of NULL; later, when the PCI device driver calls request_irq() -> ... -> hv_irq_unmask(), the guest crashes in hv_arch_irq_unmask() due to data->chip_data being NULL. Fix the issue by not testing hpdev->state in the while loop: when the guest receives PCI_EJECT, the device is still assigned to the guest, and the guest has one minute to finish the device removal gracefully. We don't really need to (and we should not) test hpdev->state in the loop. Fixes: de0aa7b2f97d ("PCI: hv: Fix 2 hang issues in hv_compose_msi_msg()") Signed-off-by: Dexuan Cui <decui(a)microsoft.com> Reviewed-by: Michael Kelley <mikelley(a)microsoft.com> Cc: stable(a)vger.kernel.org --- v2: Removed the "debug code". No change to the patch body. Added Cc:stable v3: Added Michael's Reviewed-by. drivers/pci/controller/pci-hyperv.c | 11 +++++------ 1 file changed, 5 insertions(+), 6 deletions(-) diff --git a/drivers/pci/controller/pci-hyperv.c b/drivers/pci/controller/pci-hyperv.c index b82c7cde19e66..1b11cf7391933 100644 --- a/drivers/pci/controller/pci-hyperv.c +++ b/drivers/pci/controller/pci-hyperv.c @@ -643,6 +643,11 @@ static void hv_arch_irq_unmask(struct irq_data *data) pbus = pdev->bus; hbus = container_of(pbus->sysdata, struct hv_pcibus_device, sysdata); int_desc = data->chip_data; + if (!int_desc) { + dev_warn(&hbus->hdev->device, "%s() can not unmask irq %u\n", + __func__, data->irq); + return; + } spin_lock_irqsave(&hbus->retarget_msi_interrupt_lock, flags); @@ -1911,12 +1916,6 @@ static void hv_compose_msi_msg(struct irq_data *data, struct msi_msg *msg) hv_pci_onchannelcallback(hbus); spin_unlock_irqrestore(&channel->sched_lock, flags); - if (hpdev->state == hv_pcichild_ejecting) { - dev_err_once(&hbus->hdev->device, - "the device is being ejected\n"); - goto enable_tasklet; - } - udelay(100); } -- 2.25.1

11 months, 1 week

2
2
0 0

[PATCH v3 1/6] PCI: hv: Fix a race condition bug in hv_pci_query_relations()

by Dexuan Cui

Fix the longstanding race between hv_pci_query_relations() and survey_child_resources() by flushing the workqueue before we exit from hv_pci_query_relations(). Fixes: 4daace0d8ce8 ("PCI: hv: Add paravirtual PCI front-end for Microsoft Hyper-V VMs") Signed-off-by: Dexuan Cui <decui(a)microsoft.com> Reviewed-by: Michael Kelley <mikelley(a)microsoft.com> Cc: stable(a)vger.kernel.org --- v2: Removed the "debug code". No change to the patch body. Added Cc:stable v3: Added Michael's Reviewed-by. drivers/pci/controller/pci-hyperv.c | 13 +++++++++++++ 1 file changed, 13 insertions(+) diff --git a/drivers/pci/controller/pci-hyperv.c b/drivers/pci/controller/pci-hyperv.c index f33370b756283..b82c7cde19e66 100644 --- a/drivers/pci/controller/pci-hyperv.c +++ b/drivers/pci/controller/pci-hyperv.c @@ -3308,6 +3308,19 @@ static int hv_pci_query_relations(struct hv_device *hdev) if (!ret) ret = wait_for_response(hdev, &comp); + /* + * In the case of fast device addition/removal, it's possible that + * vmbus_sendpacket() or wait_for_response() returns -ENODEV but we + * already got a PCI_BUS_RELATIONS* message from the host and the + * channel callback already scheduled a work to hbus->wq, which can be + * running survey_child_resources() -> complete(&hbus->survey_event), + * even after hv_pci_query_relations() exits and the stack variable + * 'comp' is no longer valid. This can cause a strange hang issue + * or sometimes a page fault. Flush hbus->wq before we exit from + * hv_pci_query_relations() to avoid the issues. + */ + flush_workqueue(hbus->wq); + return ret; } -- 2.25.1

11 months, 1 week

2
2
0 0

[PATCH] clk: pxa: fix NULL pointer dereference in pxa3xx_clk_update_accr

by Arnd Bergmann

From: Arnd Bergmann <arnd(a)arndb.de> sparse points out an embarrasing bug in an older patch of mine, which uses the register offset instead of an __iomem pointer: drivers/clk/pxa/clk-pxa3xx.c:167:9: sparse: sparse: Using plain integer as NULL pointer Unlike sparse, gcc and clang ignore this bug and fail to warn because a literal '0' is considered a valid representation of a NULL pointer. Fixes: 3c816d950a49 ("ARM: pxa: move clk register definitions to driver") Cc: stable(a)vger.kernel.org Reported-by: kernel test robot <lkp(a)intel.com> Link: https://lore.kernel.org/oe-kbuild-all/202305111301.RAHohdob-lkp@intel.com/ Signed-off-by: Arnd Bergmann <arnd(a)arndb.de> --- drivers/clk/pxa/clk-pxa3xx.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/clk/pxa/clk-pxa3xx.c b/drivers/clk/pxa/clk-pxa3xx.c index 42958a542662..621e298f101a 100644 --- a/drivers/clk/pxa/clk-pxa3xx.c +++ b/drivers/clk/pxa/clk-pxa3xx.c @@ -164,7 +164,7 @@ void pxa3xx_clk_update_accr(u32 disable, u32 enable, u32 xclkcfg, u32 mask) accr &= ~disable; accr |= enable; - writel(accr, ACCR); + writel(accr, clk_regs + ACCR); if (xclkcfg) __asm__("mcr p14, 0, %0, c6, c0, 0\n" : : "r"(xclkcfg)); -- 2.39.2

11 months, 1 week

2
1
0 0

[PATCH v2 1/2] clk: composite: Fix handling of high clock rates

by Sebastian Reichel

ULONG_MAX is used by a few drivers to figure out the highest available clock rate via clk_round_rate(clk, ULONG_MAX). Since abs() takes a signed value as input, the current logic effectively calculates with ULONG_MAX = -1, which results in the worst parent clock being chosen instead of the best one. For example on Rockchip RK3588 the eMMC driver tries to figure out the highest available clock rate. There are three parent clocks available resulting in the following rate diffs with the existing logic: GPLL: abs(18446744073709551615 - 1188000000) = 1188000001 CPLL: abs(18446744073709551615 - 1500000000) = 1500000001 XIN24M: abs(18446744073709551615 - 24000000) = 24000001 As a result the clock framework will promote a maximum supported clock rate of 24 MHz, even though 1.5GHz are possible. With the updated logic any casting between signed and unsigned is avoided and the numbers look like this instead: GPLL: 18446744073709551615 - 1188000000 = 18446744072521551615 CPLL: 18446744073709551615 - 1500000000 = 18446744072209551615 XIN24M: 18446744073709551615 - 24000000 = 18446744073685551615 As a result the parent with the highest acceptable rate is chosen instead of the parent clock with the lowest one. Cc: stable(a)vger.kernel.org Fixes: 49502408007b ("mmc: sdhci-of-dwcmshc: properly determine max clock on Rockchip") Tested-by: Christopher Obbard <chris.obbard(a)collabora.com> Signed-off-by: Sebastian Reichel <sebastian.reichel(a)collabora.com> --- drivers/clk/clk-composite.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/drivers/clk/clk-composite.c b/drivers/clk/clk-composite.c index edfa94641bbf..66759fe28fad 100644 --- a/drivers/clk/clk-composite.c +++ b/drivers/clk/clk-composite.c @@ -119,7 +119,10 @@ static int clk_composite_determine_rate(struct clk_hw *hw, if (ret) continue; - rate_diff = abs(req->rate - tmp_req.rate); + if (req->rate >= tmp_req.rate) + rate_diff = req->rate - tmp_req.rate; + else + rate_diff = tmp_req.rate - req->rate; if (!rate_diff || !req->best_parent_hw || best_rate_diff > rate_diff) { -- 2.39.2

11 months, 1 week

4
5
0 0

[REGRESSION] Asus X541UAK hangs on suspend and poweroff (v6.1.6 onward)

by Acid Bong

Hi there, hello, Sometimes when I suspend (by closing the lid, less often - by pressing Fn+F1 (sleep key combo)) or poweroff my laptop (both by pressing powerit button and running "loginctl poweroff"), it goes in such a state when it doesn't respond to opening/closing the lid, power button nor Ctrl+Alt+Del, but, unlike in sleep mode, the fan is rotating and the "awake status" LED is on. I checked /var/log/kern.log, but it didn't report suspend at that moment at all: went straight from [UFW BLOCK] to "Microcode updated" on force reboot (marked with an arrow): Apr 13 10:40:32 bong kernel: asus_wmi: Unknown key code 0xcf Apr 13 10:44:05 bong kernel: [UFW BLOCK] IN=wlan0 OUT= MAC=/*confidential*/ Apr 13 10:47:45 bong kernel: [UFW BLOCK] IN=wlan0 OUT= MAC=/*confidential*/ Apr 13 10:47:46 bong kernel: ICMPv6: NA: /*router*/ advertised our address /*ipv6*/ on wlan0! Apr 13 10:47:48 bong last message buffered 2 times -> Apr 13 10:49:11 bong kernel: [UFW BLOCK] IN=wlan0 OUT= MAC=/*confidential*/ Apr 13 10:52:34 bong kernel: microcode: microcode updated early to revision 0xf0, date = 2021-11-12 Apr 13 10:52:34 bong kernel: Linux version 6.1.23-bong+ (acid@bong) (gcc (Gentoo Hardened 12.2.1_p20230121-r1 p10) 12.2.1 20230121, GNU ld (Gentoo 2.39 p5) 2.39.0) #1 SMP PREEMPT_DYNAMIC Tue Apr 11 15:21:57 EEST 2023 Apr 13 10:52:34 bong kernel: Command line: root=/dev/genston/root ro loglevel=4 rd.lvm.vg=genston rd.luks.uuid=97d10669-2da1-452d-a372-887e420b2ad4 rd.luks.allow-discards pci=nomsi initrd=\x5cinitramfs-6.1.23-bong+.img Apr 13 10:52:34 bong kernel: x86/fpu: Supporting XSAVE feature 0x001: 'x87 floating point registers' Apr 13 10:52:34 bong kernel: x86/fpu: Supporting XSAVE feature 0x002: 'SSE registers' Apr 13 10:52:34 bong kernel: x86/fpu: Supporting XSAVE feature 0x004: 'AVX registers' Normally it starts like this (taken from dmesg to sync with elogind messages) [ 7835.869228] elogind-daemon[2033]: Lid closed. [ 7835.872875] elogind-daemon[2033]: Suspending... [ 7835.873955] elogind-daemon[2033]: Suspending system... [ 7835.873970] PM: suspend entry (deep) [ 7835.902814] Filesystems sync: 0.028 seconds [ 7835.920362] Freezing user space processes [ 7835.923030] Freezing user space processes completed (elapsed 0.002 seconds) [ 7835.923046] OOM killer disabled. [ 7835.923049] Freezing remaining freezable tasks [ 7835.924445] Freezing remaining freezable tasks completed (elapsed 0.001 seconds) [ 7835.924624] printk: Suspending console(s) (use no_console_suspend to debug) The issue appeared when I was using pf-kernel with genpatches and updated from 6.1-pf2 to 6.1-pf3 (corresponding to vanilla versions 6.1.3 -> 6.1.6). I used that fork until 6.2-pf2, but since then (early March) moved to vanilla sources and started following the 6.1.y branch when it was declared LTS. And the issue was present on all of them. The hang was last detected 3 days ago on 6.1.22 and today on 6.1.23. I'd like to bisect it, but it could take ages for a couple of reasons: 1) I don't know exact patterns it follows. One of the scenarios I've noticed was this one (sorry if too ridiculous): - put the laptop on the nearby couch and simultaneously close the lid; the loose charger jack might disconnect; - lay the mouse upside down (so it doesn't wake up when I reconnect the charger), but it's not a 100% guarantee of the bug and, as I said earlier, the laptop also misbehaves on shutdown. 2) The issue happens rarely, once in a few days (sometimes up to a week; I haven't measured it precisely back then). Hardware: https://tilde.cafe/u/acidbong/kernel/lspci (`lspci -vvnn`) Config (latest vanilla): https://git.sr.ht/~acid-bong/kernel/tree/806e6639da610952798e1b5d8c0d700062… Built with KCFLAGS="-march=native" Isolated cmdline: root=/dev/genston/root ro loglevel=4 rd.lvm.vg=genston rd.luks.uuid=97d10669-2da1-452d-a372-887e420b2ad4 rd.luks.allow-discards pci=nomsi initrd=\initramfs-6.1.23-bong+.img # regzbot introduced v6.1.3..v6.1.6 --- Regards, ~acidbong

11 months, 1 week

5
18
0 0

[PATCH] clk: clk-loongson2: Zero init clk_init_data

by Binbin Zhou

As clk_core_populate_parent_map() checks clk_init_data.num_parents first, and checks clk_init_data.parent_names[] before clk_init_data.parent_data[] and clk_init_data.parent_hws[]. Therefore the clk_init_data structure needs to be explicitly initialised to prevent an unexpected crash if clk_init_data.parent_names[] is a random value. [ 1.374074] CPU 0 Unable to handle kernel paging request at virtual address 0000000000000dc0, era == 9000000002986290, ra == 900000000298624c [ 1.386856] Oops[#1]: [ 1.389151] CPU: 0 PID: 1 Comm: swapper/0 Not tainted 6.4.0-rc2+ #4582 [ 1.395717] pc 9000000002986290 ra 900000000298624c tp 9000000100094000 sp 9000000100097a60 [ 1.404126] a0 9000000104541e00 a1 0000000000000000 a2 0000000000000dc0 a3 0000000000000001 [ 1.412533] a4 90000001000979f0 a5 90000001800977d7 a6 0000000000000000 a7 900000000362a000 [ 1.420939] t0 90000000034f3548 t1 6f8c2a9cb5ab5f64 t2 0000000000011340 t3 90000000031cf5b0 [ 1.429346] t4 0000000000000dc0 t5 0000000000000004 t6 0000000000011300 t7 9000000104541e40 [ 1.437753] t8 000000000005a4f8 u0 9000000104541e00 s9 9000000104541e00 s0 9000000104bc4700 [ 1.446159] s1 9000000104541da8 s2 0000000000000001 s3 900000000356f9d8 s4 ffffffffffffffff [ 1.454565] s5 0000000000000000 s6 0000000000000dc0 s7 90000000030d0a88 s8 0000000000000000 [ 1.462972] ra: 900000000298624c __clk_register+0x228/0x84c [ 1.468854] ERA: 9000000002986290 __clk_register+0x26c/0x84c [ 1.474724] CRMD: 000000b0 (PLV0 -IE -DA +PG DACF=CC DACM=CC -WE) [ 1.480975] PRMD: 00000004 (PPLV0 +PIE -PWE) [ 1.485373] EUEN: 00000000 (-FPE -SXE -ASXE -BTE) [ 1.490209] ECFG: 00071c1c (LIE=2-4,10-12 VS=7) [ 1.494865] ESTAT: 00010000 [PIL] (IS= ECode=1 EsubCode=0) [ 1.500390] BADV: 0000000000000dc0 [ 1.503899] PRID: 0014a000 (Loongson-64bit, ) [ 1.508369] Modules linked in: [ 1.511447] Process swapper/0 (pid: 1, threadinfo=(____ptrval____), task=(____ptrval____)) [ 1.519768] Stack : 90000000031c1810 90000000030d0a88 900000000325bac0 90000000034f3548 [ 1.527848] 90000001002ab410 9000000104541e00 0000000000000dc0 9000000003150098 [ 1.535923] 90000000031c1810 90000000031a0460 900000000362a000 90000001002ab410 [ 1.543998] 900000000362a000 9000000104541da8 9000000104541de8 90000001002ab410 [ 1.552073] 900000000362a000 9000000002986a68 90000000034f3ed8 90000000030d0aa8 [ 1.560148] 9000000104541da8 900000000298d3b8 90000000031c1810 0000000000000000 [ 1.568223] 90000000034f3ed8 90000000030d0aa8 0000000000000dc0 90000000030d0a88 [ 1.576298] 90000001002ab410 900000000298d401 0000000000000000 6f8c2a9cb5ab5f64 [ 1.584373] 90000000034f4000 90000000030d0a88 9000000003a48a58 90000001002ab410 [ 1.592448] 9000000104bd81a8 900000000298d484 9000000100020260 0000000000000000 [ 1.600523] ... [ 1.602993] Call Trace: [ 1.603000] [<9000000002986290>] __clk_register+0x26c/0x84c [ 1.611072] [<9000000002986a68>] devm_clk_hw_register+0x5c/0xe0 [ 1.617031] [<900000000298d3b8>] loongson2_clk_register.constprop.0+0xdc/0x10c [ 1.624314] [<900000000298d484>] loongson2_clk_probe+0x9c/0x4ac [ 1.630270] [<9000000002a4eba4>] platform_probe+0x68/0xc8 [ 1.635703] [<9000000002a4bf80>] really_probe+0xbc/0x2f0 [ 1.641054] [<9000000002a4c23c>] __driver_probe_device+0x88/0x128 [ 1.647185] [<9000000002a4c318>] driver_probe_device+0x3c/0x11c [ 1.653142] [<9000000002a4c5dc>] __driver_attach+0x98/0x18c [ 1.658749] [<9000000002a49ca0>] bus_for_each_dev+0x80/0xe0 [ 1.664357] [<9000000002a4b0dc>] bus_add_driver+0xfc/0x1ec [ 1.669878] [<9000000002a4d4a8>] driver_register+0x68/0x134 [ 1.675486] [<90000000020f0110>] do_one_initcall+0x50/0x188 [ 1.681094] [<9000000003150f00>] kernel_init_freeable+0x224/0x294 [ 1.687226] [<90000000030240fc>] kernel_init+0x20/0x110 [ 1.692493] [<90000000020f1568>] ret_from_kernel_thread+0xc/0xa4 Fixes: acc0ccffec50 ("clk: clk-loongson2: add clock controller driver support") Cc: stable(a)vger.kernel.org Cc: Yinbo Zhu <zhuyinbo(a)loongson.cn> Signed-off-by: Binbin Zhou <zhoubinbin(a)loongson.cn> --- drivers/clk/clk-loongson2.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/clk/clk-loongson2.c b/drivers/clk/clk-loongson2.c index 70ae1dd2e474..b839edd7271b 100644 --- a/drivers/clk/clk-loongson2.c +++ b/drivers/clk/clk-loongson2.c @@ -40,7 +40,7 @@ static struct clk_hw *loongson2_clk_register(struct device *dev, { int ret; struct clk_hw *hw; - struct clk_init_data init; + struct clk_init_data init = { NULL }; hw = devm_kzalloc(dev, sizeof(*hw), GFP_KERNEL); if (!hw) -- 2.39.1

11 months, 1 week

2
1
0 0

[PATCH v1 1/5] hostfs: Fix ephemeral inodes

by Mickaël Salaün

hostfs creates a new inode for each opened or created file, which created useless inode allocations and forbade identifying a host file with a kernel inode. Fix this uncommon filesystem behavior by tying kernel inodes to host file's inode and device IDs. Even if the host filesystem inodes may be recycled, this cannot happen while a file referencing it is open, which is the case with hostfs. It should be noted that hostfs inode IDs may not be unique for the same hostfs superblock because multiple host's (backed) superblocks may be used. Delete inodes when dropping them to force backed host's file descriptors closing. This enables to entirely remove ARCH_EPHEMERAL_INODES, and then makes Landlock fully supported by UML. This is very useful for testing (ongoing and backported) changes. These changes also factor out and simplify some helpers thanks to the new hostfs_inode_update() and the hostfs_iget() revamp: read_name(), hostfs_create(), hostfs_lookup(), hostfs_mknod(), and hostfs_fill_sb_common(). A following commit with new Landlock tests check this new hostfs inode consistency. Cc: Anton Ivanov <anton.ivanov(a)cambridgegreys.com> Cc: Johannes Berg <johannes(a)sipsolutions.net> Cc: Richard Weinberger <richard(a)nod.at> Cc: <stable(a)vger.kernel.org> # 5.15.x: ce72750f04d6: hostfs: Fix writeback of dirty pages Cc: <stable(a)vger.kernel.org> # 5.15+ Signed-off-by: Mickaël Salaün <mic(a)digikod.net> Link: https://lore.kernel.org/r/20230309165455.175131-2-mic@digikod.net --- arch/Kconfig | 7 -- arch/um/Kconfig | 1 - fs/hostfs/hostfs.h | 1 + fs/hostfs/hostfs_kern.c | 213 +++++++++++++++++++------------------- fs/hostfs/hostfs_user.c | 1 + security/landlock/Kconfig | 2 +- 6 files changed, 109 insertions(+), 116 deletions(-) diff --git a/arch/Kconfig b/arch/Kconfig index e3511afbb7f2..d5f0841ac3c1 100644 --- a/arch/Kconfig +++ b/arch/Kconfig @@ -1156,13 +1156,6 @@ config COMPAT_32BIT_TIME config ARCH_NO_PREEMPT bool -config ARCH_EPHEMERAL_INODES - def_bool n - help - An arch should select this symbol if it doesn't keep track of inode - instances on its own, but instead relies on something else (e.g. the - host kernel for an UML kernel). - config ARCH_SUPPORTS_RT bool diff --git a/arch/um/Kconfig b/arch/um/Kconfig index 541a9b18e343..4057d5267c6a 100644 --- a/arch/um/Kconfig +++ b/arch/um/Kconfig @@ -5,7 +5,6 @@ menu "UML-specific options" config UML bool default y - select ARCH_EPHEMERAL_INODES select ARCH_HAS_FORTIFY_SOURCE select ARCH_HAS_GCOV_PROFILE_ALL select ARCH_HAS_KCOV diff --git a/fs/hostfs/hostfs.h b/fs/hostfs/hostfs.h index 69cb796f6270..0239e3af3945 100644 --- a/fs/hostfs/hostfs.h +++ b/fs/hostfs/hostfs.h @@ -65,6 +65,7 @@ struct hostfs_stat { unsigned long long blocks; unsigned int maj; unsigned int min; + dev_t dev; }; extern int stat_file(const char *path, struct hostfs_stat *p, int fd); diff --git a/fs/hostfs/hostfs_kern.c b/fs/hostfs/hostfs_kern.c index 28b4f15c19eb..19496f732016 100644 --- a/fs/hostfs/hostfs_kern.c +++ b/fs/hostfs/hostfs_kern.c @@ -26,6 +26,7 @@ struct hostfs_inode_info { fmode_t mode; struct inode vfs_inode; struct mutex open_mutex; + dev_t dev; }; static inline struct hostfs_inode_info *HOSTFS_I(struct inode *inode) @@ -182,14 +183,6 @@ static char *follow_link(char *link) return ERR_PTR(n); } -static struct inode *hostfs_iget(struct super_block *sb) -{ - struct inode *inode = new_inode(sb); - if (!inode) - return ERR_PTR(-ENOMEM); - return inode; -} - static int hostfs_statfs(struct dentry *dentry, struct kstatfs *sf) { /* @@ -228,6 +221,7 @@ static struct inode *hostfs_alloc_inode(struct super_block *sb) return NULL; hi->fd = -1; hi->mode = 0; + hi->dev = 0; inode_init_once(&hi->vfs_inode); mutex_init(&hi->open_mutex); return &hi->vfs_inode; @@ -240,6 +234,7 @@ static void hostfs_evict_inode(struct inode *inode) if (HOSTFS_I(inode)->fd != -1) { close_file(&HOSTFS_I(inode)->fd); HOSTFS_I(inode)->fd = -1; + HOSTFS_I(inode)->dev = 0; } } @@ -265,6 +260,7 @@ static int hostfs_show_options(struct seq_file *seq, struct dentry *root) static const struct super_operations hostfs_sbops = { .alloc_inode = hostfs_alloc_inode, .free_inode = hostfs_free_inode, + .drop_inode = generic_delete_inode, .evict_inode = hostfs_evict_inode, .statfs = hostfs_statfs, .show_options = hostfs_show_options, @@ -512,18 +508,31 @@ static const struct address_space_operations hostfs_aops = { .write_end = hostfs_write_end, }; -static int read_name(struct inode *ino, char *name) +static int hostfs_inode_update(struct inode *ino, const struct hostfs_stat *st) +{ + set_nlink(ino, st->nlink); + i_uid_write(ino, st->uid); + i_gid_write(ino, st->gid); + ino->i_atime = + (struct timespec64){ st->atime.tv_sec, st->atime.tv_nsec }; + ino->i_mtime = + (struct timespec64){ st->mtime.tv_sec, st->mtime.tv_nsec }; + ino->i_ctime = + (struct timespec64){ st->ctime.tv_sec, st->ctime.tv_nsec }; + ino->i_size = st->size; + ino->i_blocks = st->blocks; + return 0; +} + +static int hostfs_inode_set(struct inode *ino, void *data) { + struct hostfs_stat *st = data; dev_t rdev; - struct hostfs_stat st; - int err = stat_file(name, &st, -1); - if (err) - return err; /* Reencode maj and min with the kernel encoding.*/ - rdev = MKDEV(st.maj, st.min); + rdev = MKDEV(st->maj, st->min); - switch (st.mode & S_IFMT) { + switch (st->mode & S_IFMT) { case S_IFLNK: ino->i_op = &hostfs_link_iops; break; @@ -535,7 +544,7 @@ static int read_name(struct inode *ino, char *name) case S_IFBLK: case S_IFIFO: case S_IFSOCK: - init_special_inode(ino, st.mode & S_IFMT, rdev); + init_special_inode(ino, st->mode & S_IFMT, rdev); ino->i_op = &hostfs_iops; break; case S_IFREG: @@ -547,17 +556,42 @@ static int read_name(struct inode *ino, char *name) return -EIO; } - ino->i_ino = st.ino; - ino->i_mode = st.mode; - set_nlink(ino, st.nlink); - i_uid_write(ino, st.uid); - i_gid_write(ino, st.gid); - ino->i_atime = (struct timespec64){ st.atime.tv_sec, st.atime.tv_nsec }; - ino->i_mtime = (struct timespec64){ st.mtime.tv_sec, st.mtime.tv_nsec }; - ino->i_ctime = (struct timespec64){ st.ctime.tv_sec, st.ctime.tv_nsec }; - ino->i_size = st.size; - ino->i_blocks = st.blocks; - return 0; + HOSTFS_I(ino)->dev = st->dev; + ino->i_ino = st->ino; + ino->i_mode = st->mode; + return hostfs_inode_update(ino, st); +} + +static int hostfs_inode_test(struct inode *inode, void *data) +{ + const struct hostfs_stat *st = data; + + return inode->i_ino == st->ino && HOSTFS_I(inode)->dev == st->dev; +} + +static struct inode *hostfs_iget(struct super_block *sb, char *name) +{ + struct inode *inode; + struct hostfs_stat st; + int err = stat_file(name, &st, -1); + + if (err) + return ERR_PTR(err); + + inode = iget5_locked(sb, st.ino, hostfs_inode_test, hostfs_inode_set, + &st); + if (!inode) + return ERR_PTR(-ENOMEM); + + if (inode->i_state & I_NEW) { + unlock_new_inode(inode); + } else { + spin_lock(&inode->i_lock); + hostfs_inode_update(inode, &st); + spin_unlock(&inode->i_lock); + } + + return inode; } static int hostfs_create(struct mnt_idmap *idmap, struct inode *dir, @@ -565,62 +599,48 @@ static int hostfs_create(struct mnt_idmap *idmap, struct inode *dir, { struct inode *inode; char *name; - int error, fd; - - inode = hostfs_iget(dir->i_sb); - if (IS_ERR(inode)) { - error = PTR_ERR(inode); - goto out; - } + int fd; - error = -ENOMEM; name = dentry_name(dentry); if (name == NULL) - goto out_put; + return -ENOMEM; fd = file_create(name, mode & 0777); - if (fd < 0) - error = fd; - else - error = read_name(inode, name); + if (fd < 0) { + __putname(name); + return fd; + } + inode = hostfs_iget(dir->i_sb, name); __putname(name); - if (error) - goto out_put; + if (IS_ERR(inode)) + return PTR_ERR(inode); HOSTFS_I(inode)->fd = fd; HOSTFS_I(inode)->mode = FMODE_READ | FMODE_WRITE; d_instantiate(dentry, inode); return 0; - - out_put: - iput(inode); - out: - return error; } static struct dentry *hostfs_lookup(struct inode *ino, struct dentry *dentry, unsigned int flags) { - struct inode *inode; + struct inode *inode = NULL; char *name; - int err; - - inode = hostfs_iget(ino->i_sb); - if (IS_ERR(inode)) - goto out; - err = -ENOMEM; name = dentry_name(dentry); - if (name) { - err = read_name(inode, name); - __putname(name); - } - if (err) { - iput(inode); - inode = (err == -ENOENT) ? NULL : ERR_PTR(err); + if (name == NULL) + return ERR_PTR(-ENOMEM); + + inode = hostfs_iget(ino->i_sb, name); + __putname(name); + if (IS_ERR(inode)) { + if (PTR_ERR(inode) == -ENOENT) + inode = NULL; + else + return ERR_CAST(inode); } - out: + return d_splice_alias(inode, dentry); } @@ -704,35 +724,23 @@ static int hostfs_mknod(struct mnt_idmap *idmap, struct inode *dir, char *name; int err; - inode = hostfs_iget(dir->i_sb); - if (IS_ERR(inode)) { - err = PTR_ERR(inode); - goto out; - } - - err = -ENOMEM; name = dentry_name(dentry); if (name == NULL) - goto out_put; + return -ENOMEM; err = do_mknod(name, mode, MAJOR(dev), MINOR(dev)); - if (err) - goto out_free; + if (err) { + __putname(name); + return err; + } - err = read_name(inode, name); + inode = hostfs_iget(dir->i_sb, name); __putname(name); - if (err) - goto out_put; + if (IS_ERR(inode)) + return PTR_ERR(inode); d_instantiate(dentry, inode); return 0; - - out_free: - __putname(name); - out_put: - iput(inode); - out: - return err; } static int hostfs_rename2(struct mnt_idmap *idmap, @@ -929,49 +937,40 @@ static int hostfs_fill_sb_common(struct super_block *sb, void *d, int silent) sb->s_maxbytes = MAX_LFS_FILESIZE; err = super_setup_bdi(sb); if (err) - goto out; + return err; /* NULL is printed as '(null)' by printf(): avoid that. */ if (req_root == NULL) req_root = ""; - err = -ENOMEM; sb->s_fs_info = host_root_path = kasprintf(GFP_KERNEL, "%s/%s", root_ino, req_root); if (host_root_path == NULL) - goto out; - - root_inode = new_inode(sb); - if (!root_inode) - goto out; + return -ENOMEM; - err = read_name(root_inode, host_root_path); - if (err) - goto out_put; + root_inode = hostfs_iget(sb, host_root_path); + if (IS_ERR(root_inode)) + return PTR_ERR(root_inode); if (S_ISLNK(root_inode->i_mode)) { - char *name = follow_link(host_root_path); - if (IS_ERR(name)) { - err = PTR_ERR(name); - goto out_put; - } - err = read_name(root_inode, name); + char *name; + + iput(root_inode); + name = follow_link(host_root_path); + if (IS_ERR(name)) + return PTR_ERR(name); + + root_inode = hostfs_iget(sb, name); kfree(name); - if (err) - goto out_put; + if (IS_ERR(root_inode)) + return PTR_ERR(root_inode); } - err = -ENOMEM; sb->s_root = d_make_root(root_inode); if (sb->s_root == NULL) - goto out; + return -ENOMEM; return 0; - -out_put: - iput(root_inode); -out: - return err; } static struct dentry *hostfs_read_sb(struct file_system_type *type, diff --git a/fs/hostfs/hostfs_user.c b/fs/hostfs/hostfs_user.c index 5ecc4706172b..840619e39a1a 100644 --- a/fs/hostfs/hostfs_user.c +++ b/fs/hostfs/hostfs_user.c @@ -36,6 +36,7 @@ static void stat64_to_hostfs(const struct stat64 *buf, struct hostfs_stat *p) p->blocks = buf->st_blocks; p->maj = os_major(buf->st_rdev); p->min = os_minor(buf->st_rdev); + p->dev = buf->st_dev; } int stat_file(const char *path, struct hostfs_stat *p, int fd) diff --git a/security/landlock/Kconfig b/security/landlock/Kconfig index 8e33c4e8ffb8..c1e862a38410 100644 --- a/security/landlock/Kconfig +++ b/security/landlock/Kconfig @@ -2,7 +2,7 @@ config SECURITY_LANDLOCK bool "Landlock support" - depends on SECURITY && !ARCH_EPHEMERAL_INODES + depends on SECURITY select SECURITY_PATH help Landlock is a sandboxing mechanism that enables processes to restrict -- 2.39.2

11 months, 1 week

3
6
0 0

2024

2023

2022

2021

2020

2019

2018

2017

Linux-stable-mirror May 2023