May 2024 - Linux-stable-mirror

[PATCH 1/4] drm/exynos/vidi: fix memory leak in .get_modes()

by Jani Nikula

The duplicated EDID is never freed. Fix it. Cc: stable(a)vger.kernel.org Signed-off-by: Jani Nikula <jani.nikula(a)intel.com> --- drivers/gpu/drm/exynos/exynos_drm_vidi.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/exynos/exynos_drm_vidi.c b/drivers/gpu/drm/exynos/exynos_drm_vidi.c index fab135308b70..11a720fef32b 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_vidi.c +++ b/drivers/gpu/drm/exynos/exynos_drm_vidi.c @@ -309,6 +309,7 @@ static int vidi_get_modes(struct drm_connector *connector) struct vidi_context *ctx = ctx_from_connector(connector); struct edid *edid; int edid_len; + int count; /* * the edid data comes from user side and it would be set @@ -328,7 +329,11 @@ static int vidi_get_modes(struct drm_connector *connector) drm_connector_update_edid_property(connector, edid); - return drm_add_edid_modes(connector, edid); + count = drm_add_edid_modes(connector, edid); + + kfree(edid); + + return count; } static const struct drm_connector_helper_funcs vidi_connector_helper_funcs = { -- 2.39.2

11 months, 2 weeks

2
1
0 0

[PATCH v3 1/2] drm/rockchip: vop: clear DMA stop bit upon vblank on RK3066

by Val Packett

The RK3066 VOP sets a dma_stop bit when it's done scanning out a frame and needs the driver to acknowledge that by clearing the bit. So unless we clear it "between" frames, the RGB output only shows noise instead of the picture. vblank seems to be the most appropriate place to do it, since it indicates exactly that: that the hardware is done with the frame. This seems to be a redundant synchronization mechanism that was removed in later iterations of the VOP hardware block. Fixes: f4a6de8 ("drm: rockchip: vop: add rk3066 vop definitions") Cc: stable(a)vger.kernel.org Signed-off-by: Val Packett <val(a)packett.cool> --- drivers/gpu/drm/rockchip/rockchip_drm_vop.c | 6 ++++++ drivers/gpu/drm/rockchip/rockchip_drm_vop.h | 1 + drivers/gpu/drm/rockchip/rockchip_vop_reg.c | 1 + 3 files changed, 8 insertions(+) diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_vop.c b/drivers/gpu/drm/rockchip/rockchip_drm_vop.c index a13473b2d..2731fe2b2 100644 --- a/drivers/gpu/drm/rockchip/rockchip_drm_vop.c +++ b/drivers/gpu/drm/rockchip/rockchip_drm_vop.c @@ -1766,6 +1766,12 @@ static void vop_handle_vblank(struct vop *vop) } spin_unlock(&drm->event_lock); + if (VOP_HAS_REG(vop, common, dma_stop)) { + spin_lock(&vop->reg_lock); + VOP_REG_SET(vop, common, dma_stop, 0); + spin_unlock(&vop->reg_lock); + } + if (test_and_clear_bit(VOP_PENDING_FB_UNREF, &vop->pending)) drm_flip_work_commit(&vop->fb_unref_work, system_unbound_wq); } diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_vop.h b/drivers/gpu/drm/rockchip/rockchip_drm_vop.h index b33e5bdc2..0cf512cc1 100644 --- a/drivers/gpu/drm/rockchip/rockchip_drm_vop.h +++ b/drivers/gpu/drm/rockchip/rockchip_drm_vop.h @@ -122,6 +122,7 @@ struct vop_common { struct vop_reg lut_buffer_index; struct vop_reg gate_en; struct vop_reg mmu_en; + struct vop_reg dma_stop; struct vop_reg out_mode; struct vop_reg standby; }; diff --git a/drivers/gpu/drm/rockchip/rockchip_vop_reg.c b/drivers/gpu/drm/rockchip/rockchip_vop_reg.c index b9ee02061..9bcb40a64 100644 --- a/drivers/gpu/drm/rockchip/rockchip_vop_reg.c +++ b/drivers/gpu/drm/rockchip/rockchip_vop_reg.c @@ -466,6 +466,7 @@ static const struct vop_output rk3066_output = { }; static const struct vop_common rk3066_common = { + .dma_stop = VOP_REG(RK3066_SYS_CTRL0, 0x1, 0), .standby = VOP_REG(RK3066_SYS_CTRL0, 0x1, 1), .out_mode = VOP_REG(RK3066_DSP_CTRL0, 0xf, 0), .cfg_done = VOP_REG(RK3066_REG_CFG_DONE, 0x1, 0), -- 2.45.1

11 months, 2 weeks

2
3
0 0

[PATCH v2 08/14] pinctrl: qcom: spmi-gpio: drop broken pm8008 support

by Johan Hovold

The SPMI GPIO driver assumes that the parent device is an SPMI device and accesses random data when backcasting the parent struct device pointer for non-SPMI devices. Fortunately this does not seem to cause any issues currently when the parent device is an I2C client like the PM8008, but this could change if the structures are reorganised (e.g. using structure randomisation). Notably the interrupt implementation is also broken for non-SPMI devices. Also note that the two GPIO pins on PM8008 are used for interrupts and reset so their practical use should be limited. Drop the broken GPIO support for PM8008 for now. Fixes: ea119e5a482a ("pinctrl: qcom-pmic-gpio: Add support for pm8008") Cc: stable(a)vger.kernel.org # 5.13 Reviewed-by: Bryan O'Donoghue <bryan.odonoghue(a)linaro.org> Reviewed-by: Stephen Boyd <swboyd(a)chromium.org> Signed-off-by: Johan Hovold <johan+linaro(a)kernel.org> --- drivers/pinctrl/qcom/pinctrl-spmi-gpio.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/pinctrl/qcom/pinctrl-spmi-gpio.c b/drivers/pinctrl/qcom/pinctrl-spmi-gpio.c index f4e2c88a7c82..e61be7d05494 100644 --- a/drivers/pinctrl/qcom/pinctrl-spmi-gpio.c +++ b/drivers/pinctrl/qcom/pinctrl-spmi-gpio.c @@ -1206,7 +1206,6 @@ static const struct of_device_id pmic_gpio_of_match[] = { { .compatible = "qcom,pm7325-gpio", .data = (void *) 10 }, { .compatible = "qcom,pm7550ba-gpio", .data = (void *) 8}, { .compatible = "qcom,pm8005-gpio", .data = (void *) 4 }, - { .compatible = "qcom,pm8008-gpio", .data = (void *) 2 }, { .compatible = "qcom,pm8019-gpio", .data = (void *) 6 }, /* pm8150 has 10 GPIOs with holes on 2, 5, 7 and 8 */ { .compatible = "qcom,pm8150-gpio", .data = (void *) 10 }, -- 2.44.1

11 months, 2 weeks

2
1
0 0

[PATCH] ACPI: x86: Force StorageD3Enable on more products

by Mario Limonciello

A Rembrandt-based HP thin client is reported to have problems where the NVME disk isn't present after resume from s2idle. This is because the NVME disk wasn't put into D3 at suspend, and that happened because the StorageD3Enable _DSD was missing in the BIOS. As AMD's architecture requires that the NVME is in D3 for s2idle, adjust the criteria for force_storage_d3 to match *all* Zen SoCs when the FADT advertises low power idle support. This will ensure that any future products with this BIOS deficiency don't need to be added to the allow list of overrides. Cc: stable(a)vger.kernel.org Signed-off-by: Mario Limonciello <mario.limonciello(a)amd.com> --- drivers/acpi/x86/utils.c | 24 ++++++++++-------------- 1 file changed, 10 insertions(+), 14 deletions(-) diff --git a/drivers/acpi/x86/utils.c b/drivers/acpi/x86/utils.c index 90c3d2eab9e9..7507a7706898 100644 --- a/drivers/acpi/x86/utils.c +++ b/drivers/acpi/x86/utils.c @@ -197,16 +197,16 @@ bool acpi_device_override_status(struct acpi_device *adev, unsigned long long *s } /* - * AMD systems from Renoir and Lucienne *require* that the NVME controller + * AMD systems from Renoir onwards *require* that the NVME controller * is put into D3 over a Modern Standby / suspend-to-idle cycle. * * This is "typically" accomplished using the `StorageD3Enable` * property in the _DSD that is checked via the `acpi_storage_d3` function - * but this property was introduced after many of these systems launched - * and most OEM systems don't have it in their BIOS. + * but some OEM systems still don't have it in their BIOS. * * The Microsoft documentation for StorageD3Enable mentioned that Windows has - * a hardcoded allowlist for D3 support, which was used for these platforms. + * a hardcoded allowlist for D3 support as well as a registry key to override + * the BIOS, which has been used for these cases. * * This allows quirking on Linux in a similar fashion. * @@ -219,19 +219,15 @@ bool acpi_device_override_status(struct acpi_device *adev, unsigned long long *s * https://bugzilla.kernel.org/show_bug.cgi?id=216773 * https://bugzilla.kernel.org/show_bug.cgi?id=217003 * 2) On at least one HP system StorageD3Enable is missing on the second NVME - disk in the system. + * disk in the system. + * 3) On at least one HP Rembrandt system StorageD3Enable is missing on the only + * NVME device. */ -static const struct x86_cpu_id storage_d3_cpu_ids[] = { - X86_MATCH_VENDOR_FAM_MODEL(AMD, 23, 24, NULL), /* Picasso */ - X86_MATCH_VENDOR_FAM_MODEL(AMD, 23, 96, NULL), /* Renoir */ - X86_MATCH_VENDOR_FAM_MODEL(AMD, 23, 104, NULL), /* Lucienne */ - X86_MATCH_VENDOR_FAM_MODEL(AMD, 25, 80, NULL), /* Cezanne */ - {} -}; - bool force_storage_d3(void) { - return x86_match_cpu(storage_d3_cpu_ids); + if (!cpu_feature_enabled(X86_FEATURE_ZEN)) + return false; + return acpi_gbl_FADT.flags & ACPI_FADT_LOW_POWER_S0; } /* -- 2.43.0

11 months, 2 weeks

3
2
0 0

[PATCH v3 2/2] 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 introducing a new flag SGX_ENCL_PAGE_BEING_REMOVED, which is unset by default and set only right-before the first mutex_unlock() in sgx_encl_remove_pages(). Upon loading the page, CPU2 checks whether this page is being removed, 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. Fixes: 9849bb27152c ("x86/sgx: Support complete page removal") Cc: stable(a)vger.kernel.org Signed-off-by: Dmitrii Kuvaiskii <dmitrii.kuvaiskii(a)intel.com> Reviewed-by: Haitao Huang <haitao.huang(a)linux.intel.com> Reviewed-by: Jarkko Sakkinen <jarkko(a)kernel.org> Acked-by: Reinette Chatre <reinette.chatre(a)intel.com> --- arch/x86/kernel/cpu/sgx/encl.c | 3 ++- arch/x86/kernel/cpu/sgx/encl.h | 3 +++ arch/x86/kernel/cpu/sgx/ioctl.c | 1 + 3 files changed, 6 insertions(+), 1 deletion(-) diff --git a/arch/x86/kernel/cpu/sgx/encl.c b/arch/x86/kernel/cpu/sgx/encl.c index 41f14b1a3025..7ccd8b2fce5f 100644 --- a/arch/x86/kernel/cpu/sgx/encl.c +++ b/arch/x86/kernel/cpu/sgx/encl.c @@ -257,7 +257,8 @@ static struct sgx_encl_page *__sgx_encl_load_page(struct sgx_encl *encl, /* Entry successfully located. */ if (entry->epc_page) { - if (entry->desc & SGX_ENCL_PAGE_BEING_RECLAIMED) + if (entry->desc & (SGX_ENCL_PAGE_BEING_RECLAIMED | + SGX_ENCL_PAGE_BEING_REMOVED)) return ERR_PTR(-EBUSY); return entry; diff --git a/arch/x86/kernel/cpu/sgx/encl.h b/arch/x86/kernel/cpu/sgx/encl.h index f94ff14c9486..fff5f2293ae7 100644 --- a/arch/x86/kernel/cpu/sgx/encl.h +++ b/arch/x86/kernel/cpu/sgx/encl.h @@ -25,6 +25,9 @@ /* 'desc' bit marking that the page is being reclaimed. */ #define SGX_ENCL_PAGE_BEING_RECLAIMED BIT(3) +/* 'desc' bit marking that the page is being removed. */ +#define SGX_ENCL_PAGE_BEING_REMOVED BIT(2) + struct sgx_encl_page { unsigned long desc; unsigned long vm_max_prot_bits:8; diff --git a/arch/x86/kernel/cpu/sgx/ioctl.c b/arch/x86/kernel/cpu/sgx/ioctl.c index 5d390df21440..de59219ae794 100644 --- a/arch/x86/kernel/cpu/sgx/ioctl.c +++ b/arch/x86/kernel/cpu/sgx/ioctl.c @@ -1142,6 +1142,7 @@ 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(). */ + entry->desc |= SGX_ENCL_PAGE_BEING_REMOVED; mutex_unlock(&encl->lock); sgx_zap_enclave_ptes(encl, addr); -- 2.34.1

11 months, 2 weeks

3
4
0 0

[PATCH v2 1/2] memfd: fix MFD_NOEXEC_SEAL to be non-sealable by default

by jeffxu＠chromium.org

From: Jeff Xu <jeffxu(a)google.com> By default, memfd_create() creates a non-sealable MFD, unless the MFD_ALLOW_SEALING flag is set. When the MFD_NOEXEC_SEAL flag is initially introduced, the MFD created with that flag is sealable, even though MFD_ALLOW_SEALING is not set. This patch changes MFD_NOEXEC_SEAL to be non-sealable by default, unless MFD_ALLOW_SEALING is explicitly set. This is a non-backward compatible change. However, as MFD_NOEXEC_SEAL is new, we expect not many applications will rely on the nature of MFD_NOEXEC_SEAL being sealable. In most cases, the application already sets MFD_ALLOW_SEALING if they need a sealable MFD. Additionally, this enhances the useability of pid namespace sysctl vm.memfd_noexec. When vm.memfd_noexec equals 1 or 2, the kernel will add MFD_NOEXEC_SEAL if mfd_create does not specify MFD_EXEC or MFD_NOEXEC_SEAL, and the addition of MFD_NOEXEC_SEAL enables the MFD to be sealable. This means, any application that does not desire this behavior will be unable to utilize vm.memfd_noexec = 1 or 2 to migrate/enforce non-executable MFD. This adjustment ensures that applications can anticipate that the sealable characteristic will remain unmodified by vm.memfd_noexec. This patch was initially developed by Barnabás Pőcze, and Barnabás used Debian Code Search and GitHub to try to find potential breakages and could only find a single one. Dbus-broker's memfd_create() wrapper is aware of this implicit `MFD_ALLOW_SEALING` behavior, and tries to work around it [1]. This workaround will break. Luckily, this only affects the test suite, it does not affect the normal operations of dbus-broker. There is a PR with a fix[2]. In addition, David Rheinsberg also raised similar fix in [3] [1]: https://github.com/bus1/dbus-broker/blob/9eb0b7e5826fc76cad7b025bc46f267d4a… [2]: https://github.com/bus1/dbus-broker/pull/366 [3]: https://lore.kernel.org/lkml/20230714114753.170814-1-david@readahead.eu/ Cc: stable(a)vger.kernel.org Fixes: 105ff5339f498a ("mm/memfd: add MFD_NOEXEC_SEAL and MFD_EXEC") Signed-off-by: Barnabás Pőcze <pobrn(a)protonmail.com> Signed-off-by: Jeff Xu <jeffxu(a)google.com> Reviewed-by: David Rheinsberg <david(a)readahead.eu> --- mm/memfd.c | 9 ++++---- tools/testing/selftests/memfd/memfd_test.c | 26 +++++++++++++++++++++- 2 files changed, 29 insertions(+), 6 deletions(-) diff --git a/mm/memfd.c b/mm/memfd.c index 7d8d3ab3fa37..8b7f6afee21d 100644 --- a/mm/memfd.c +++ b/mm/memfd.c @@ -356,12 +356,11 @@ SYSCALL_DEFINE2(memfd_create, inode->i_mode &= ~0111; file_seals = memfd_file_seals_ptr(file); - if (file_seals) { - *file_seals &= ~F_SEAL_SEAL; + if (file_seals) *file_seals |= F_SEAL_EXEC; - } - } else if (flags & MFD_ALLOW_SEALING) { - /* MFD_EXEC and MFD_ALLOW_SEALING are set */ + } + + if (flags & MFD_ALLOW_SEALING) { file_seals = memfd_file_seals_ptr(file); if (file_seals) *file_seals &= ~F_SEAL_SEAL; diff --git a/tools/testing/selftests/memfd/memfd_test.c b/tools/testing/selftests/memfd/memfd_test.c index 95af2d78fd31..8579a93d006b 100644 --- a/tools/testing/selftests/memfd/memfd_test.c +++ b/tools/testing/selftests/memfd/memfd_test.c @@ -1151,7 +1151,7 @@ static void test_noexec_seal(void) mfd_def_size, MFD_CLOEXEC | MFD_NOEXEC_SEAL); mfd_assert_mode(fd, 0666); - mfd_assert_has_seals(fd, F_SEAL_EXEC); + mfd_assert_has_seals(fd, F_SEAL_SEAL | F_SEAL_EXEC); mfd_fail_chmod(fd, 0777); close(fd); } @@ -1169,6 +1169,14 @@ static void test_sysctl_sysctl0(void) mfd_assert_has_seals(fd, 0); mfd_assert_chmod(fd, 0644); close(fd); + + fd = mfd_assert_new("kern_memfd_sysctl_0_dfl", + mfd_def_size, + MFD_CLOEXEC); + mfd_assert_mode(fd, 0777); + mfd_assert_has_seals(fd, F_SEAL_SEAL); + mfd_assert_chmod(fd, 0644); + close(fd); } static void test_sysctl_set_sysctl0(void) @@ -1206,6 +1214,14 @@ static void test_sysctl_sysctl1(void) mfd_assert_has_seals(fd, F_SEAL_EXEC); mfd_fail_chmod(fd, 0777); close(fd); + + fd = mfd_assert_new("kern_memfd_sysctl_1_noexec_nosealable", + mfd_def_size, + MFD_CLOEXEC | MFD_NOEXEC_SEAL); + mfd_assert_mode(fd, 0666); + mfd_assert_has_seals(fd, F_SEAL_EXEC | F_SEAL_SEAL); + mfd_fail_chmod(fd, 0777); + close(fd); } static void test_sysctl_set_sysctl1(void) @@ -1238,6 +1254,14 @@ static void test_sysctl_sysctl2(void) mfd_assert_has_seals(fd, F_SEAL_EXEC); mfd_fail_chmod(fd, 0777); close(fd); + + fd = mfd_assert_new("kern_memfd_sysctl_2_noexec_notsealable", + mfd_def_size, + MFD_CLOEXEC | MFD_NOEXEC_SEAL); + mfd_assert_mode(fd, 0666); + mfd_assert_has_seals(fd, F_SEAL_EXEC | F_SEAL_SEAL); + mfd_fail_chmod(fd, 0777); + close(fd); } static void test_sysctl_set_sysctl2(void) -- 2.45.1.288.g0e0cd299f1-goog

11 months, 2 weeks

5
6
0 0

[PATCH 1/1] hwrng: amd - Convert PCIBIOS_* return codes to errnos

by Ilpo Järvinen

amd_rng_mod_init() uses pci_read_config_dword() that returns PCIBIOS_* codes. The return code is then returned as is but amd_rng_mod_init() is a module_init() function that should return normal errnos. Convert PCIBIOS_* returns code using pcibios_err_to_errno() into normal errno before returning it. Fixes: 96d63c0297cc ("[PATCH] Add AMD HW RNG driver") Cc: stable(a)vger.kernel.org Signed-off-by: Ilpo Järvinen <ilpo.jarvinen(a)linux.intel.com> --- drivers/char/hw_random/amd-rng.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/char/hw_random/amd-rng.c b/drivers/char/hw_random/amd-rng.c index 86162a13681e..9a24d19236dc 100644 --- a/drivers/char/hw_random/amd-rng.c +++ b/drivers/char/hw_random/amd-rng.c @@ -143,8 +143,10 @@ static int __init amd_rng_mod_init(void) found: err = pci_read_config_dword(pdev, 0x58, &pmbase); - if (err) + if (err) { + err = pcibios_err_to_errno(err); goto put_dev; + } pmbase &= 0x0000FF00; if (pmbase == 0) { -- 2.39.2

11 months, 2 weeks

2
1
0 0

backport request

by Ard Biesheuvel

Please consider commit 15aa8fb852f995dd x86/efistub: Omit physical KASLR when memory reservations exist for backporting to v6.1 and later. Thanks, Ard.

11 months, 2 weeks

2
7
0 0

[PATCH 5.15 00/23] 5.15.160-rc1 review

by Greg Kroah-Hartman

This is the start of the stable review cycle for the 5.15.160 release. There are 23 patches in this series, all will be posted as a response to this one. If anyone has any issues with these being applied, please let me know. Responses should be made by Sat, 25 May 2024 13:03:15 +0000. Anything received after that time might be too late. The whole patch series can be found in one patch at: https://www.kernel.org/pub/linux/kernel/v5.x/stable-review/patch-5.15.160-r… or in the git tree and branch at: git://git.kernel.org/pub/scm/linux/kernel/git/stable/linux-stable-rc.git linux-5.15.y and the diffstat can be found below. thanks, greg k-h ------------- Pseudo-Shortlog of commits: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Linux 5.15.160-rc1 Akira Yokosawa <akiyks(a)gmail.com> docs: kernel_include.py: Cope with docutils 0.21 Thomas Weißschuh <linux(a)weissschuh.net> admin-guide/hw-vuln/core-scheduling: fix return type of PR_SCHED_CORE_GET Jarkko Sakkinen <jarkko(a)kernel.org> KEYS: trusted: Do not use WARN when encode fails AngeloGioacchino Del Regno <angelogioacchino.delregno(a)collabora.com> remoteproc: mediatek: Make sure IPI buffer fits in L2TCM Daniel Thompson <daniel.thompson(a)linaro.org> serial: kgdboc: Fix NMI-safety problems from keyboard reset code Heikki Krogerus <heikki.krogerus(a)linux.intel.com> usb: typec: ucsi: displayport: Fix potential deadlock Carlos Llamas <cmllamas(a)google.com> binder: fix max_thread type inconsistency Srinivasan Shanmugam <srinivasan.shanmugam(a)amd.com> drm/amdgpu: Fix possible NULL dereference in amdgpu_ras_query_error_status_helper() Sean Christopherson <seanjc(a)google.com> KVM: x86: Clear "has_error_code", not "error_code", for RM exception injection Eric Dumazet <edumazet(a)google.com> netlink: annotate data-races around sk->sk_err Eric Dumazet <edumazet(a)google.com> netlink: annotate lockless accesses to nlk->max_recvmsg_len Jakub Kicinski <kuba(a)kernel.org> net: tls: handle backlogging of crypto requests Jakub Kicinski <kuba(a)kernel.org> tls: fix race between async notify and socket close Jakub Kicinski <kuba(a)kernel.org> net: tls: factor out tls_*crypt_async_wait() Sabrina Dubroca <sd(a)queasysnail.net> tls: extract context alloc/initialization out of tls_set_sw_offload Jakub Kicinski <kuba(a)kernel.org> tls: rx: simplify async wait Doug Berger <opendmb(a)gmail.com> net: bcmgenet: synchronize UMAC_CMD access Doug Berger <opendmb(a)gmail.com> net: bcmgenet: synchronize EXT_RGMII_OOB_CTRL access Harshit Mogalapalli <harshit.m.mogalapalli(a)oracle.com> Revert "selftests: mm: fix map_hugetlb failure on 64K page size systems" Jarkko Sakkinen <jarkko(a)kernel.org> KEYS: trusted: Fix memory leak in tpm2_key_encode() NeilBrown <neilb(a)suse.de> nfsd: don't allow nfsd threads to be signalled. Sergey Shtylyov <s.shtylyov(a)omp.ru> pinctrl: core: handle radix_tree_insert() errors in pinctrl_register_one_pin() Jose Fernandez <josef(a)netflix.com> drm/amd/display: Fix division by zero in setup_dsc_config ------------- Diffstat: .../admin-guide/hw-vuln/core-scheduling.rst | 4 +- Documentation/sphinx/kernel_include.py | 1 - Makefile | 4 +- arch/x86/kvm/x86.c | 11 +- drivers/android/binder.c | 2 +- drivers/android/binder_internal.h | 2 +- drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c | 3 + drivers/gpu/drm/amd/display/dc/dsc/dc_dsc.c | 7 +- drivers/net/ethernet/broadcom/genet/bcmgenet.c | 12 +- drivers/net/ethernet/broadcom/genet/bcmgenet.h | 2 + drivers/net/ethernet/broadcom/genet/bcmgenet_wol.c | 6 + drivers/net/ethernet/broadcom/genet/bcmmii.c | 4 + drivers/pinctrl/core.c | 14 +- drivers/remoteproc/mtk_scp.c | 10 +- drivers/tty/serial/kgdboc.c | 30 +++- drivers/usb/typec/ucsi/displayport.c | 4 - fs/nfs/callback.c | 9 +- fs/nfsd/nfs4proc.c | 5 +- fs/nfsd/nfssvc.c | 12 -- include/net/tls.h | 6 - net/netlink/af_netlink.c | 23 +-- net/sunrpc/svc_xprt.c | 16 +- net/tls/tls_sw.c | 199 +++++++++++---------- security/keys/trusted-keys/trusted_tpm2.c | 25 ++- tools/testing/selftests/vm/map_hugetlb.c | 7 - 25 files changed, 243 insertions(+), 175 deletions(-)

11 months, 2 weeks

14
48
0 0

Re: Patch "arm64: fpsimd: Drop unneeded 'busy' flag" has been added to the 6.6-stable tree

by Ard Biesheuvel

On Thu, 30 May 2024 at 21:11, Sasha Levin <sashal(a)kernel.org> wrote: > > This is a note to let you know that I've just added the patch titled > > arm64: fpsimd: Drop unneeded 'busy' flag > > to the 6.6-stable tree Why? > which can be found at: > http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum… > > The filename of the patch is: > arm64-fpsimd-drop-unneeded-busy-flag.patch > and it can be found in the queue-6.6 subdirectory. > > If you, or anyone else, feels it should not be added to the stable tree, > please let <stable(a)vger.kernel.org> know about it. > > > > commit 37f2773a1ef05374538d5e4ed26cbacebe363241 > Author: Ard Biesheuvel <ardb(a)kernel.org> > Date: Fri Dec 8 12:32:20 2023 +0100 > > arm64: fpsimd: Drop unneeded 'busy' flag > > [ Upstream commit 9b19700e623f96222c69ecb2adecb1a3e3664cc0 ] > > Kernel mode NEON will preserve the user mode FPSIMD state by saving it > into the task struct before clobbering the registers. In order to avoid > the need for preserving kernel mode state too, we disallow nested use of > kernel mode NEON, i..e, use in softirq context while the interrupted > task context was using kernel mode NEON too. > > Originally, this policy was implemented using a per-CPU flag which was > exposed via may_use_simd(), requiring the users of the kernel mode NEON > to deal with the possibility that it might return false, and having NEON > and non-NEON code paths. This policy was changed by commit > 13150149aa6ded1 ("arm64: fpsimd: run kernel mode NEON with softirqs > disabled"), and now, softirq processing is disabled entirely instead, > and so may_use_simd() can never fail when called from task or softirq > context. > > This means we can drop the fpsimd_context_busy flag entirely, and > instead, ensure that we disable softirq processing in places where we > formerly relied on the flag for preventing races in the FPSIMD preserve > routines. > > Signed-off-by: Ard Biesheuvel <ardb(a)kernel.org> > Reviewed-by: Mark Brown <broonie(a)kernel.org> > Tested-by: Geert Uytterhoeven <geert+renesas(a)glider.be> > Link: https://lore.kernel.org/r/20231208113218.3001940-7-ardb@google.com > [will: Folded in fix from CAMj1kXFhzbJRyWHELCivQW1yJaF=p07LLtbuyXYX3G1WtsdyQg(a)mail.gmail.com] > Signed-off-by: Will Deacon <will(a)kernel.org> > Stable-dep-of: b8995a184170 ("Revert "arm64: fpsimd: Implement lazy restore for kernel mode FPSIMD"") > Signed-off-by: Sasha Levin <sashal(a)kernel.org> > > diff --git a/arch/arm64/include/asm/simd.h b/arch/arm64/include/asm/simd.h > index 6a75d7ecdcaa2..8e86c9e70e483 100644 > --- a/arch/arm64/include/asm/simd.h > +++ b/arch/arm64/include/asm/simd.h > @@ -12,8 +12,6 @@ > #include <linux/preempt.h> > #include <linux/types.h> > > -DECLARE_PER_CPU(bool, fpsimd_context_busy); > - > #ifdef CONFIG_KERNEL_MODE_NEON > > /* > @@ -28,17 +26,10 @@ static __must_check inline bool may_use_simd(void) > /* > * We must make sure that the SVE has been initialized properly > * before using the SIMD in kernel. > - * fpsimd_context_busy is only set while preemption is disabled, > - * and is clear whenever preemption is enabled. Since > - * this_cpu_read() is atomic w.r.t. preemption, fpsimd_context_busy > - * cannot change under our feet -- if it's set we cannot be > - * migrated, and if it's clear we cannot be migrated to a CPU > - * where it is set. > */ > return !WARN_ON(!system_capabilities_finalized()) && > system_supports_fpsimd() && > - !in_hardirq() && !irqs_disabled() && !in_nmi() && > - !this_cpu_read(fpsimd_context_busy); > + !in_hardirq() && !irqs_disabled() && !in_nmi(); > } > > #else /* ! CONFIG_KERNEL_MODE_NEON */ > diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c > index 5cdfcc9e3e54b..b805bdab284c4 100644 > --- a/arch/arm64/kernel/fpsimd.c > +++ b/arch/arm64/kernel/fpsimd.c > @@ -85,13 +85,13 @@ > * softirq kicks in. Upon vcpu_put(), KVM will save the vcpu FP state and > * flag the register state as invalid. > * > - * In order to allow softirq handlers to use FPSIMD, kernel_neon_begin() may > - * save the task's FPSIMD context back to task_struct from softirq context. > - * To prevent this from racing with the manipulation of the task's FPSIMD state > - * from task context and thereby corrupting the state, it is necessary to > - * protect any manipulation of a task's fpsimd_state or TIF_FOREIGN_FPSTATE > - * flag with {, __}get_cpu_fpsimd_context(). This will still allow softirqs to > - * run but prevent them to use FPSIMD. > + * In order to allow softirq handlers to use FPSIMD, kernel_neon_begin() may be > + * called from softirq context, which will save the task's FPSIMD context back > + * to task_struct. To prevent this from racing with the manipulation of the > + * task's FPSIMD state from task context and thereby corrupting the state, it > + * is necessary to protect any manipulation of a task's fpsimd_state or > + * TIF_FOREIGN_FPSTATE flag with get_cpu_fpsimd_context(), which will suspend > + * softirq servicing entirely until put_cpu_fpsimd_context() is called. > * > * For a certain task, the sequence may look something like this: > * - the task gets scheduled in; if both the task's fpsimd_cpu field > @@ -209,27 +209,14 @@ static inline void sme_free(struct task_struct *t) { } > > #endif > > -DEFINE_PER_CPU(bool, fpsimd_context_busy); > -EXPORT_PER_CPU_SYMBOL(fpsimd_context_busy); > - > static void fpsimd_bind_task_to_cpu(void); > > -static void __get_cpu_fpsimd_context(void) > -{ > - bool busy = __this_cpu_xchg(fpsimd_context_busy, true); > - > - WARN_ON(busy); > -} > - > /* > * Claim ownership of the CPU FPSIMD context for use by the calling context. > * > * The caller may freely manipulate the FPSIMD context metadata until > * put_cpu_fpsimd_context() is called. > * > - * The double-underscore version must only be called if you know the task > - * can't be preempted. > - * > * On RT kernels local_bh_disable() is not sufficient because it only > * serializes soft interrupt related sections via a local lock, but stays > * preemptible. Disabling preemption is the right choice here as bottom > @@ -242,14 +229,6 @@ static void get_cpu_fpsimd_context(void) > local_bh_disable(); > else > preempt_disable(); > - __get_cpu_fpsimd_context(); > -} > - > -static void __put_cpu_fpsimd_context(void) > -{ > - bool busy = __this_cpu_xchg(fpsimd_context_busy, false); > - > - WARN_ON(!busy); /* No matching get_cpu_fpsimd_context()? */ > } > > /* > @@ -261,18 +240,12 @@ static void __put_cpu_fpsimd_context(void) > */ > static void put_cpu_fpsimd_context(void) > { > - __put_cpu_fpsimd_context(); > if (!IS_ENABLED(CONFIG_PREEMPT_RT)) > local_bh_enable(); > else > preempt_enable(); > } > > -static bool have_cpu_fpsimd_context(void) > -{ > - return !preemptible() && __this_cpu_read(fpsimd_context_busy); > -} > - > unsigned int task_get_vl(const struct task_struct *task, enum vec_type type) > { > return task->thread.vl[type]; > @@ -383,7 +356,7 @@ static void task_fpsimd_load(void) > bool restore_ffr; > > WARN_ON(!system_supports_fpsimd()); > - WARN_ON(!have_cpu_fpsimd_context()); > + WARN_ON(preemptible()); > > if (system_supports_sve() || system_supports_sme()) { > switch (current->thread.fp_type) { > @@ -467,7 +440,7 @@ static void fpsimd_save(void) > unsigned int vl; > > WARN_ON(!system_supports_fpsimd()); > - WARN_ON(!have_cpu_fpsimd_context()); > + WARN_ON(preemptible()); > > if (test_thread_flag(TIF_FOREIGN_FPSTATE)) > return; > @@ -1583,7 +1556,7 @@ void fpsimd_thread_switch(struct task_struct *next) > if (!system_supports_fpsimd()) > return; > > - __get_cpu_fpsimd_context(); > + WARN_ON_ONCE(!irqs_disabled()); > > /* Save unsaved fpsimd state, if any: */ > fpsimd_save(); > @@ -1599,8 +1572,6 @@ void fpsimd_thread_switch(struct task_struct *next) > > update_tsk_thread_flag(next, TIF_FOREIGN_FPSTATE, > wrong_task || wrong_cpu); > - > - __put_cpu_fpsimd_context(); > } > > static void fpsimd_flush_thread_vl(enum vec_type type) > @@ -1892,13 +1863,15 @@ static void fpsimd_flush_cpu_state(void) > */ > void fpsimd_save_and_flush_cpu_state(void) > { > + unsigned long flags; > + > if (!system_supports_fpsimd()) > return; > WARN_ON(preemptible()); > - __get_cpu_fpsimd_context(); > + local_irq_save(flags); > fpsimd_save(); > fpsimd_flush_cpu_state(); > - __put_cpu_fpsimd_context(); > + local_irq_restore(flags); > } > > #ifdef CONFIG_KERNEL_MODE_NEON

11 months, 2 weeks

2
3
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-stable-mirror May 2024