August 2024 - Linux-stable-mirror

[PATCH] selftests: mm: Fix build errors on armhf

by Muhammad Usama Anjum

The __NR_mmap isn't found on armhf. The mmap() is commonly available system call and its wrapper is presnet on all architectures. So it should be used directly. It solves problem for armhf and doesn't create problem for architectures as well. Remove sys_mmap() functions as they aren't doing anything else other than calling mmap(). There is no need to set errno = 0 manually as glibc always resets it. For reference errors are as following: CC seal_elf seal_elf.c: In function 'sys_mmap': seal_elf.c:39:33: error: '__NR_mmap' undeclared (first use in this function) 39 | sret = (void *) syscall(__NR_mmap, addr, len, prot, | ^~~~~~~~~ mseal_test.c: In function 'sys_mmap': mseal_test.c:90:33: error: '__NR_mmap' undeclared (first use in this function) 90 | sret = (void *) syscall(__NR_mmap, addr, len, prot, | ^~~~~~~~~ Cc: stable(a)vger.kernel.org Fixes: 4926c7a52de7 ("selftest mm/mseal memory sealing") Signed-off-by: Muhammad Usama Anjum <usama.anjum(a)collabora.com> --- tools/testing/selftests/mm/mseal_test.c | 37 +++++++++---------------- tools/testing/selftests/mm/seal_elf.c | 13 +-------- 2 files changed, 14 insertions(+), 36 deletions(-) diff --git a/tools/testing/selftests/mm/mseal_test.c b/tools/testing/selftests/mm/mseal_test.c index a818f010de479..bfcea5cf9a484 100644 --- a/tools/testing/selftests/mm/mseal_test.c +++ b/tools/testing/selftests/mm/mseal_test.c @@ -81,17 +81,6 @@ static int sys_mprotect_pkey(void *ptr, size_t size, unsigned long orig_prot, return sret; } -static void *sys_mmap(void *addr, unsigned long len, unsigned long prot, - unsigned long flags, unsigned long fd, unsigned long offset) -{ - void *sret; - - errno = 0; - sret = (void *) syscall(__NR_mmap, addr, len, prot, - flags, fd, offset); - return sret; -} - static int sys_munmap(void *ptr, size_t size) { int sret; @@ -172,7 +161,7 @@ static void setup_single_address(int size, void **ptrOut) { void *ptr; - ptr = sys_mmap(NULL, size, PROT_READ, MAP_ANONYMOUS | MAP_PRIVATE, -1, 0); + ptr = mmap(NULL, size, PROT_READ, MAP_ANONYMOUS | MAP_PRIVATE, -1, 0); *ptrOut = ptr; } @@ -181,7 +170,7 @@ static void setup_single_address_rw(int size, void **ptrOut) void *ptr; unsigned long mapflags = MAP_ANONYMOUS | MAP_PRIVATE; - ptr = sys_mmap(NULL, size, PROT_READ | PROT_WRITE, mapflags, -1, 0); + ptr = mmap(NULL, size, PROT_READ | PROT_WRITE, mapflags, -1, 0); *ptrOut = ptr; } @@ -205,7 +194,7 @@ bool seal_support(void) void *ptr; unsigned long page_size = getpagesize(); - ptr = sys_mmap(NULL, page_size, PROT_READ, MAP_ANONYMOUS | MAP_PRIVATE, -1, 0); + ptr = mmap(NULL, page_size, PROT_READ, MAP_ANONYMOUS | MAP_PRIVATE, -1, 0); if (ptr == (void *) -1) return false; @@ -481,8 +470,8 @@ static void test_seal_zero_address(void) int prot; /* use mmap to change protection. */ - ptr = sys_mmap(0, size, PROT_NONE, - MAP_ANONYMOUS | MAP_PRIVATE | MAP_FIXED, -1, 0); + ptr = mmap(0, size, PROT_NONE, + MAP_ANONYMOUS | MAP_PRIVATE | MAP_FIXED, -1, 0); FAIL_TEST_IF_FALSE(ptr == 0); size = get_vma_size(ptr, &prot); @@ -1209,8 +1198,8 @@ static void test_seal_mmap_overwrite_prot(bool seal) } /* use mmap to change protection. */ - ret2 = sys_mmap(ptr, size, PROT_NONE, - MAP_ANONYMOUS | MAP_PRIVATE | MAP_FIXED, -1, 0); + ret2 = mmap(ptr, size, PROT_NONE, + MAP_ANONYMOUS | MAP_PRIVATE | MAP_FIXED, -1, 0); if (seal) { FAIL_TEST_IF_FALSE(ret2 == MAP_FAILED); FAIL_TEST_IF_FALSE(errno == EPERM); @@ -1240,8 +1229,8 @@ static void test_seal_mmap_expand(bool seal) } /* use mmap to expand. */ - ret2 = sys_mmap(ptr, size, PROT_READ, - MAP_ANONYMOUS | MAP_PRIVATE | MAP_FIXED, -1, 0); + ret2 = mmap(ptr, size, PROT_READ, + MAP_ANONYMOUS | MAP_PRIVATE | MAP_FIXED, -1, 0); if (seal) { FAIL_TEST_IF_FALSE(ret2 == MAP_FAILED); FAIL_TEST_IF_FALSE(errno == EPERM); @@ -1268,8 +1257,8 @@ static void test_seal_mmap_shrink(bool seal) } /* use mmap to shrink. */ - ret2 = sys_mmap(ptr, 8 * page_size, PROT_READ, - MAP_ANONYMOUS | MAP_PRIVATE | MAP_FIXED, -1, 0); + ret2 = mmap(ptr, 8 * page_size, PROT_READ, + MAP_ANONYMOUS | MAP_PRIVATE | MAP_FIXED, -1, 0); if (seal) { FAIL_TEST_IF_FALSE(ret2 == MAP_FAILED); FAIL_TEST_IF_FALSE(errno == EPERM); @@ -1650,7 +1639,7 @@ static void test_seal_discard_ro_anon_on_filebacked(bool seal) ret = fallocate(fd, 0, 0, size); FAIL_TEST_IF_FALSE(!ret); - ptr = sys_mmap(NULL, size, PROT_READ, mapflags, fd, 0); + ptr = mmap(NULL, size, PROT_READ, mapflags, fd, 0); FAIL_TEST_IF_FALSE(ptr != MAP_FAILED); if (seal) { @@ -1680,7 +1669,7 @@ static void test_seal_discard_ro_anon_on_shared(bool seal) int ret; unsigned long mapflags = MAP_ANONYMOUS | MAP_SHARED; - ptr = sys_mmap(NULL, size, PROT_READ, mapflags, -1, 0); + ptr = mmap(NULL, size, PROT_READ, mapflags, -1, 0); FAIL_TEST_IF_FALSE(ptr != (void *)-1); if (seal) { diff --git a/tools/testing/selftests/mm/seal_elf.c b/tools/testing/selftests/mm/seal_elf.c index 7aa1366063e4e..d9f8ba8d5050b 100644 --- a/tools/testing/selftests/mm/seal_elf.c +++ b/tools/testing/selftests/mm/seal_elf.c @@ -30,17 +30,6 @@ static int sys_mseal(void *start, size_t len) return sret; } -static void *sys_mmap(void *addr, unsigned long len, unsigned long prot, - unsigned long flags, unsigned long fd, unsigned long offset) -{ - void *sret; - - errno = 0; - sret = (void *) syscall(__NR_mmap, addr, len, prot, - flags, fd, offset); - return sret; -} - static inline int sys_mprotect(void *ptr, size_t size, unsigned long prot) { int sret; @@ -56,7 +45,7 @@ static bool seal_support(void) void *ptr; unsigned long page_size = getpagesize(); - ptr = sys_mmap(NULL, page_size, PROT_READ, MAP_ANONYMOUS | MAP_PRIVATE, -1, 0); + ptr = mmap(NULL, page_size, PROT_READ, MAP_ANONYMOUS | MAP_PRIVATE, -1, 0); if (ptr == (void *) -1) return false; -- 2.39.2

8 months, 1 week

4
6
0 0

[PATCH] sysctl: avoid spurious permanent empty tables

by Thomas Weißschuh

The test if a table is a permanently empty one, inspects the address of the registered ctl_table argument. However as sysctl_mount_point is an empty array and does not occupy and space it can end up sharing an address with another object in memory. If that other object itself is a "struct ctl_table" then registering that table will fail as it's incorrectly recognized as permanently empty. Avoid this issue by adding a dummy element to the array so that the array is not empty anymore and the potential address sharing is avoided. Explicitly register the table with zero elements as otherwise the dummy element would be recognized as a sentinel element which would lead to a runtime warning from the sysctl core. While the issue seems unlikely to be encountered at this time, this seems mostly be due to luck. Also a future change, constifying sysctl_mount_point and root_table, can reliably trigger this issue on clang 18. Given that empty arrays are non-standard in the first place, avoid them if possible. Reported-by: kernel test robot <oliver.sang(a)intel.com> Closes: https://lore.kernel.org/oe-lkp/202408051453.f638857e-lkp@intel.com Fixes: 4a7b29f65094 ("sysctl: move sysctl type to ctl_table_header") Fixes: a35dd3a786f5 ("sysctl: drop now unnecessary out-of-bounds check") Cc: stable(a)vger.kernel.org Signed-off-by: Thomas Weißschuh <linux(a)weissschuh.net> --- This was originally part of a feature series [0], but is resubmitted on its own to make it into v6.11To. [0] https://lore.kernel.org/lkml/20240805-sysctl-const-api-v2-0-52c85f02ee5e@we… --- fs/proc/proc_sysctl.c | 11 ++++++++--- 1 file changed, 8 insertions(+), 3 deletions(-) diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c index 9553e77c9d31..d11ebc055ce0 100644 --- a/fs/proc/proc_sysctl.c +++ b/fs/proc/proc_sysctl.c @@ -29,8 +29,13 @@ static const struct inode_operations proc_sys_inode_operations; static const struct file_operations proc_sys_dir_file_operations; static const struct inode_operations proc_sys_dir_operations; -/* Support for permanently empty directories */ -static struct ctl_table sysctl_mount_point[] = { }; +/* + * Support for permanently empty directories. + * Must be non-empty to avoid sharing an address with other tables. + */ +static struct ctl_table sysctl_mount_point[] = { + { } +}; /** * register_sysctl_mount_point() - registers a sysctl mount point @@ -42,7 +47,7 @@ static struct ctl_table sysctl_mount_point[] = { }; */ struct ctl_table_header *register_sysctl_mount_point(const char *path) { - return register_sysctl(path, sysctl_mount_point); + return register_sysctl_sz(path, sysctl_mount_point, 0); } EXPORT_SYMBOL(register_sysctl_mount_point); --- base-commit: 3e9bff3bbe1355805de919f688bef4baefbfd436 change-id: 20240827-sysctl-const-shared-identity-9ab816e5fdfb Best regards, -- Thomas Weißschuh <linux(a)weissschuh.net>

8 months, 1 week

2
1
0 0

[PATCH 0/2] Fixes for the PCI dra7xx driver

by Siddharth Vadapalli

Hello, This series is based on commit 3e9bff3bbe13 Merge tag 'vfs-6.11-rc6.fixes' of gitolite.kernel.org:pub/scm/linux/kernel/git/vfs/vfs of Mainline Linux. The first patch fixes conversion to "devm_request_threaded_irq()" where the IRQF_ONESHOT flag should have been added since the handler is NULL. The second patch fixes the error handling when IRQ request fails in the probe function. The existing error handling doesn't cleanup the changes performed prior to the IRQ request invocation. Regards, Siddharth. Siddharth Vadapalli (2): PCI: dra7xx: Fix threaded IRQ request for "dra7xx-pcie-main" IRQ PCI: dra7xx: Fix error handling when IRQ request fails in probe drivers/pci/controller/dwc/pci-dra7xx.c | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) -- 2.40.1

8 months, 1 week

5
7
0 0

[PATCH RESEND] drm/sti: avoid potential dereference of error pointers

by Ma Ke

The return value of drm_atomic_get_crtc_state() needs to be checked. To avoid use of error pointer 'crtc_state' in case of the failure. Cc: stable(a)vger.kernel.org Fixes: dec92020671c ("drm: Use the state pointer directly in planes atomic_check") Signed-off-by: Ma Ke <make24(a)iscas.ac.cn> --- drivers/gpu/drm/sti/sti_cursor.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/gpu/drm/sti/sti_cursor.c b/drivers/gpu/drm/sti/sti_cursor.c index db0a1eb53532..e460f5ba2d87 100644 --- a/drivers/gpu/drm/sti/sti_cursor.c +++ b/drivers/gpu/drm/sti/sti_cursor.c @@ -200,6 +200,8 @@ static int sti_cursor_atomic_check(struct drm_plane *drm_plane, return 0; crtc_state = drm_atomic_get_crtc_state(state, crtc); + if (IS_ERR(crtc_state)) + return PTR_ERR(crtc_state); mode = &crtc_state->mode; dst_x = new_plane_state->crtc_x; dst_y = new_plane_state->crtc_y; -- 2.25.1

8 months, 1 week

3
4
0 0

[PATCH v3] PCI: pci_call_probe: call local_pci_probe() when selected cpu is offline

by Hongchen Zhang

Call work_on_cpu(cpu, fn, arg) in pci_call_probe() while the argument @cpu is a offline cpu would cause system stuck forever. This can be happen if a node is online while all its CPUs are offline (We can use "maxcpus=1" without "nr_cpus=1" to reproduce it). So, in the above case, let pci_call_probe() call local_pci_probe() instead of work_on_cpu() when the best selected cpu is offline. Fixes: 69a18b18699b ("PCI: Restrict probe functions to housekeeping CPUs") Cc: <stable(a)vger.kernel.org> Signed-off-by: Huacai Chen <chenhuacai(a)loongson.cn> Signed-off-by: Hongchen Zhang <zhanghongchen(a)loongson.cn> --- v2 -> v3: Modify commit message according to Markus's suggestion v1 -> v2: Add a method to reproduce the problem --- drivers/pci/pci-driver.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/pci/pci-driver.c b/drivers/pci/pci-driver.c index af2996d0d17f..32a99828e6a3 100644 --- a/drivers/pci/pci-driver.c +++ b/drivers/pci/pci-driver.c @@ -386,7 +386,7 @@ static int pci_call_probe(struct pci_driver *drv, struct pci_dev *dev, free_cpumask_var(wq_domain_mask); } - if (cpu < nr_cpu_ids) + if ((cpu < nr_cpu_ids) && cpu_online(cpu)) error = work_on_cpu(cpu, local_pci_probe, &ddi); else error = local_pci_probe(&ddi); -- 2.33.0

8 months, 1 week

3
8
0 0

[PATCH] rtc: at91sam9: fix OF node leak in probe() error path

by Krzysztof Kozlowski

Driver is leaking an OF node reference obtained from of_parse_phandle_with_fixed_args(). Fixes: 43e112bb3dea ("rtc: at91sam9: make use of syscon/regmap to access GPBR registers") Cc: <stable(a)vger.kernel.org> Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski(a)linaro.org> --- drivers/rtc/rtc-at91sam9.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/rtc/rtc-at91sam9.c b/drivers/rtc/rtc-at91sam9.c index f93bee96e362..993c0878fb66 100644 --- a/drivers/rtc/rtc-at91sam9.c +++ b/drivers/rtc/rtc-at91sam9.c @@ -368,6 +368,7 @@ static int at91_rtc_probe(struct platform_device *pdev) return ret; rtc->gpbr = syscon_node_to_regmap(args.np); + of_node_put(args.np); rtc->gpbr_offset = args.args[0]; if (IS_ERR(rtc->gpbr)) { dev_err(&pdev->dev, "failed to retrieve gpbr regmap, aborting.\n"); -- 2.43.0

8 months, 1 week

4
5
0 0

[PATCH] usb: dwc3: Runtime get and put usb power_supply handle

by Kyle Tso

It is possible that the usb power_supply is registered after the probe of dwc3. In this case, trying to get the usb power_supply during the probe will fail and there is no chance to try again. Also the usb power_supply might be unregistered at anytime so that the handle of it in dwc3 would become invalid. To fix this, get the handle right before calling to power_supply functions and put it afterward. Fixes: 6f0764b5adea ("usb: dwc3: add a power supply for current control") Cc: stable(a)vger.kernel.org Signed-off-by: Kyle Tso <kyletso(a)google.com> --- drivers/usb/dwc3/core.c | 25 +++++-------------------- drivers/usb/dwc3/core.h | 4 ++-- drivers/usb/dwc3/gadget.c | 19 ++++++++++++++----- 3 files changed, 21 insertions(+), 27 deletions(-) diff --git a/drivers/usb/dwc3/core.c b/drivers/usb/dwc3/core.c index 734de2a8bd21..ab563edd9b4c 100644 --- a/drivers/usb/dwc3/core.c +++ b/drivers/usb/dwc3/core.c @@ -1631,8 +1631,6 @@ static void dwc3_get_properties(struct dwc3 *dwc) u8 tx_thr_num_pkt_prd = 0; u8 tx_max_burst_prd = 0; u8 tx_fifo_resize_max_num; - const char *usb_psy_name; - int ret; /* default to highest possible threshold */ lpm_nyet_threshold = 0xf; @@ -1667,12 +1665,7 @@ static void dwc3_get_properties(struct dwc3 *dwc) dwc->sys_wakeup = device_may_wakeup(dwc->sysdev); - ret = device_property_read_string(dev, "usb-psy-name", &usb_psy_name); - if (ret >= 0) { - dwc->usb_psy = power_supply_get_by_name(usb_psy_name); - if (!dwc->usb_psy) - dev_err(dev, "couldn't get usb power supply\n"); - } + device_property_read_string(dev, "usb-psy-name", &dwc->usb_psy_name); dwc->has_lpm_erratum = device_property_read_bool(dev, "snps,has-lpm-erratum"); @@ -2133,18 +2126,16 @@ static int dwc3_probe(struct platform_device *pdev) dwc3_get_software_properties(dwc); dwc->reset = devm_reset_control_array_get_optional_shared(dev); - if (IS_ERR(dwc->reset)) { - ret = PTR_ERR(dwc->reset); - goto err_put_psy; - } + if (IS_ERR(dwc->reset)) + return PTR_ERR(dwc->reset); ret = dwc3_get_clocks(dwc); if (ret) - goto err_put_psy; + return ret; ret = reset_control_deassert(dwc->reset); if (ret) - goto err_put_psy; + return ret; ret = dwc3_clk_enable(dwc); if (ret) @@ -2245,9 +2236,6 @@ static int dwc3_probe(struct platform_device *pdev) dwc3_clk_disable(dwc); err_assert_reset: reset_control_assert(dwc->reset); -err_put_psy: - if (dwc->usb_psy) - power_supply_put(dwc->usb_psy); return ret; } @@ -2276,9 +2264,6 @@ static void dwc3_remove(struct platform_device *pdev) pm_runtime_set_suspended(&pdev->dev); dwc3_free_event_buffers(dwc); - - if (dwc->usb_psy) - power_supply_put(dwc->usb_psy); } #ifdef CONFIG_PM diff --git a/drivers/usb/dwc3/core.h b/drivers/usb/dwc3/core.h index 1e561fd8b86e..ecfe2cc224f7 100644 --- a/drivers/usb/dwc3/core.h +++ b/drivers/usb/dwc3/core.h @@ -1045,7 +1045,7 @@ struct dwc3_scratchpad_array { * @role_sw: usb_role_switch handle * @role_switch_default_mode: default operation mode of controller while * usb role is USB_ROLE_NONE. - * @usb_psy: pointer to power supply interface. + * @usb_psy_name: name of the usb power supply interface. * @usb2_phy: pointer to USB2 PHY * @usb3_phy: pointer to USB3 PHY * @usb2_generic_phy: pointer to array of USB2 PHYs @@ -1223,7 +1223,7 @@ struct dwc3 { struct usb_role_switch *role_sw; enum usb_dr_mode role_switch_default_mode; - struct power_supply *usb_psy; + const char *usb_psy_name; u32 fladj; u32 ref_clk_per; diff --git a/drivers/usb/dwc3/gadget.c b/drivers/usb/dwc3/gadget.c index 89fc690fdf34..c89b5b5a64cf 100644 --- a/drivers/usb/dwc3/gadget.c +++ b/drivers/usb/dwc3/gadget.c @@ -3049,20 +3049,29 @@ static void dwc3_gadget_set_ssp_rate(struct usb_gadget *g, static int dwc3_gadget_vbus_draw(struct usb_gadget *g, unsigned int mA) { - struct dwc3 *dwc = gadget_to_dwc(g); + struct dwc3 *dwc = gadget_to_dwc(g); + struct power_supply *usb_psy; union power_supply_propval val = {0}; int ret; if (dwc->usb2_phy) return usb_phy_set_power(dwc->usb2_phy, mA); - if (!dwc->usb_psy) + if (!dwc->usb_psy_name) return -EOPNOTSUPP; - val.intval = 1000 * mA; - ret = power_supply_set_property(dwc->usb_psy, POWER_SUPPLY_PROP_INPUT_CURRENT_LIMIT, &val); + usb_psy = power_supply_get_by_name(dwc->usb_psy_name); + if (usb_psy) { + val.intval = 1000 * mA; + ret = power_supply_set_property(usb_psy, POWER_SUPPLY_PROP_INPUT_CURRENT_LIMIT, + &val); + power_supply_put(usb_psy); + return ret; + } - return ret; + dev_err(dwc->dev, "couldn't get usb power supply\n"); + + return -EOPNOTSUPP; } /** -- 2.45.2.993.g49e7a77208-goog

8 months, 1 week

3
2
0 0

[PATCH] Revert "f2fs: stop allocating pinned sections if EAGAIN happens"

by Wu Bo

This reverts commit 2e42b7f817acd6e8d78226445eb6fe44fe79c12a. If the GC victim section has a pinned block when fallocate() trigger FG_GC, the section is not able to be recycled. And this will return -EAGAIN cause fallocate() failed, even though there are much spare space as user see. As the GC policy prone to chose the same victim, fallocate() may not successed at a long period. This scenario has been found during Android OTA. Link: https://lore.kernel.org/linux-f2fs-devel/20231030094024.263707-1-bo.wu@vivo… CC: stable(a)vger.kernel.org Signed-off-by: Wu Bo <bo.wu(a)vivo.com> --- fs/f2fs/file.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c index b58ab1157b7e..19915faccee9 100644 --- a/fs/f2fs/file.c +++ b/fs/f2fs/file.c @@ -1725,7 +1725,7 @@ static int f2fs_expand_inode_data(struct inode *inode, loff_t offset, f2fs_down_write(&sbi->gc_lock); stat_inc_gc_call_count(sbi, FOREGROUND); err = f2fs_gc(sbi, &gc_control); - if (err && err != -ENODATA) + if (err && err != -ENODATA && err != -EAGAIN) goto out_err; } -- 2.25.1

8 months, 1 week

4
7
0 0

FAILED: patch "[PATCH] memcg: protect concurrent access to mem_cgroup_idr" failed to apply to 5.10-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 5.10-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-5.10.y git checkout FETCH_HEAD git cherry-pick -x 9972605a238339b85bd16b084eed5f18414d22db # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2024081218-demote-shakily-f31c@gregkh' --subject-prefix 'PATCH 5.10.y' HEAD^.. Possible dependencies: 9972605a2383 ("memcg: protect concurrent access to mem_cgroup_idr") 6f0df8e16eb5 ("memcontrol: ensure memcg acquired by id is properly set up") e4dde56cd208 ("mm: multi-gen LRU: per-node lru_gen_folio lists") 7348cc91821b ("mm: multi-gen LRU: remove aging fairness safeguard") a579086c99ed ("mm: multi-gen LRU: remove eviction fairness safeguard") adb8213014b2 ("mm: memcg: fix stale protection of reclaim target memcg") 57e9cc50f4dd ("mm: vmscan: split khugepaged stats from direct reclaim stats") e4fea72b1438 ("mglru: mm/vmscan.c: fix imprecise comments") d396def5d86d ("memcg: rearrange code") 410f8e82689e ("memcg: extract memcg_vmstats from struct mem_cgroup") d6c3af7d8a2b ("mm: multi-gen LRU: debugfs interface") 1332a809d95a ("mm: multi-gen LRU: thrashing prevention") 354ed5974429 ("mm: multi-gen LRU: kill switch") f76c83378851 ("mm: multi-gen LRU: optimize multiple memcgs") bd74fdaea146 ("mm: multi-gen LRU: support page table walks") 018ee47f1489 ("mm: multi-gen LRU: exploit locality in rmap") ac35a4902374 ("mm: multi-gen LRU: minimal implementation") ec1c86b25f4b ("mm: multi-gen LRU: groundwork") f1e1a7be4718 ("mm/vmscan.c: refactor shrink_node()") d3629af59f41 ("mm/vmscan: make the annotations of refaults code at the right place") thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 9972605a238339b85bd16b084eed5f18414d22db Mon Sep 17 00:00:00 2001 From: Shakeel Butt <shakeel.butt(a)linux.dev> Date: Fri, 2 Aug 2024 16:58:22 -0700 Subject: [PATCH] memcg: protect concurrent access to mem_cgroup_idr Commit 73f576c04b94 ("mm: memcontrol: fix cgroup creation failure after many small jobs") decoupled the memcg IDs from the CSS ID space to fix the cgroup creation failures. It introduced IDR to maintain the memcg ID space. The IDR depends on external synchronization mechanisms for modifications. For the mem_cgroup_idr, the idr_alloc() and idr_replace() happen within css callback and thus are protected through cgroup_mutex from concurrent modifications. However idr_remove() for mem_cgroup_idr was not protected against concurrency and can be run concurrently for different memcgs when they hit their refcnt to zero. Fix that. We have been seeing list_lru based kernel crashes at a low frequency in our fleet for a long time. These crashes were in different part of list_lru code including list_lru_add(), list_lru_del() and reparenting code. Upon further inspection, it looked like for a given object (dentry and inode), the super_block's list_lru didn't have list_lru_one for the memcg of that object. The initial suspicions were either the object is not allocated through kmem_cache_alloc_lru() or somehow memcg_list_lru_alloc() failed to allocate list_lru_one() for a memcg but returned success. No evidence were found for these cases. Looking more deeply, we started seeing situations where valid memcg's id is not present in mem_cgroup_idr and in some cases multiple valid memcgs have same id and mem_cgroup_idr is pointing to one of them. So, the most reasonable explanation is that these situations can happen due to race between multiple idr_remove() calls or race between idr_alloc()/idr_replace() and idr_remove(). These races are causing multiple memcgs to acquire the same ID and then offlining of one of them would cleanup list_lrus on the system for all of them. Later access from other memcgs to the list_lru cause crashes due to missing list_lru_one. Link: https://lkml.kernel.org/r/20240802235822.1830976-1-shakeel.butt@linux.dev Fixes: 73f576c04b94 ("mm: memcontrol: fix cgroup creation failure after many small jobs") Signed-off-by: Shakeel Butt <shakeel.butt(a)linux.dev> Acked-by: Muchun Song <muchun.song(a)linux.dev> Reviewed-by: Roman Gushchin <roman.gushchin(a)linux.dev> Acked-by: Johannes Weiner <hannes(a)cmpxchg.org> Cc: Michal Hocko <mhocko(a)suse.com> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 960371788687..f29157288b7d 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -3386,11 +3386,28 @@ static void memcg_wb_domain_size_changed(struct mem_cgroup *memcg) #define MEM_CGROUP_ID_MAX ((1UL << MEM_CGROUP_ID_SHIFT) - 1) static DEFINE_IDR(mem_cgroup_idr); +static DEFINE_SPINLOCK(memcg_idr_lock); + +static int mem_cgroup_alloc_id(void) +{ + int ret; + + idr_preload(GFP_KERNEL); + spin_lock(&memcg_idr_lock); + ret = idr_alloc(&mem_cgroup_idr, NULL, 1, MEM_CGROUP_ID_MAX + 1, + GFP_NOWAIT); + spin_unlock(&memcg_idr_lock); + idr_preload_end(); + return ret; +} static void mem_cgroup_id_remove(struct mem_cgroup *memcg) { if (memcg->id.id > 0) { + spin_lock(&memcg_idr_lock); idr_remove(&mem_cgroup_idr, memcg->id.id); + spin_unlock(&memcg_idr_lock); + memcg->id.id = 0; } } @@ -3524,8 +3541,7 @@ static struct mem_cgroup *mem_cgroup_alloc(struct mem_cgroup *parent) if (!memcg) return ERR_PTR(error); - memcg->id.id = idr_alloc(&mem_cgroup_idr, NULL, - 1, MEM_CGROUP_ID_MAX + 1, GFP_KERNEL); + memcg->id.id = mem_cgroup_alloc_id(); if (memcg->id.id < 0) { error = memcg->id.id; goto fail; @@ -3667,7 +3683,9 @@ static int mem_cgroup_css_online(struct cgroup_subsys_state *css) * publish it here at the end of onlining. This matches the * regular ID destruction during offlining. */ + spin_lock(&memcg_idr_lock); idr_replace(&mem_cgroup_idr, memcg, memcg->id.id); + spin_unlock(&memcg_idr_lock); return 0; offline_kmem:

8 months, 1 week

4
8
0 0

[PATCH net v2] 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) Mitigate 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> --- v1->v2 - skb_transport_header instead of skb->transport_header (edumazet@) - typo: migitate -> mitigate --- include/linux/virtio_net.h | 16 +++++----------- net/ipv4/tcp_offload.c | 3 +++ net/ipv4/udp_offload.c | 4 ++++ 3 files changed, 12 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..e4ad3311e1489 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_checksum_start(skb) != skb_transport_header(skb))) + 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..bc8a9da750fed 100644 --- a/net/ipv4/udp_offload.c +++ b/net/ipv4/udp_offload.c @@ -278,6 +278,10 @@ struct sk_buff *__udp_gso_segment(struct sk_buff *gso_skb, if (gso_skb->len <= sizeof(*uh) + mss) return ERR_PTR(-EINVAL); + if (unlikely(skb_checksum_start(gso_skb) != + skb_transport_header(gso_skb))) + 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, 1 week

9
18
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-stable-mirror August 2024