From: Yifan Zhang yifan1.zhang@amd.com

commit ee5468b9f1d3bf48082eed351dace14598e8ca39 upstream.

This reverts commit 4cbbe34807938e6e494e535a68d5ff64edac3f20.

Reason for revert: side effect of enlarging CP_MEC_DOORBELL_RANGE may cause some APUs fail to enter gfxoff in certain user cases.

Signed-off-by: Yifan Zhang yifan1.zhang@amd.com Acked-by: Alex Deucher alexander.deucher@amd.com Signed-off-by: Alex Deucher alexander.deucher@amd.com Cc: stable@vger.kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c | 6 +----- 1 file changed, 1 insertion(+), 5 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c index 1859d293ef71..fb15e8b5af32 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c @@ -3619,12 +3619,8 @@ static int gfx_v9_0_kiq_init_register(struct amdgpu_ring *ring) if (ring->use_doorbell) { WREG32_SOC15(GC, 0, mmCP_MEC_DOORBELL_RANGE_LOWER, (adev->doorbell_index.kiq * 2) << 2); - /* If GC has entered CGPG, ringing doorbell > first page doesn't - * wakeup GC. Enlarge CP_MEC_DOORBELL_RANGE_UPPER to workaround - * this issue. - */ WREG32_SOC15(GC, 0, mmCP_MEC_DOORBELL_RANGE_UPPER, - (adev->doorbell.size - 4)); + (adev->doorbell_index.userqueue_end * 2) << 2); }

WREG32_SOC15_RLC(GC, 0, mmCP_HQD_PQ_DOORBELL_CONTROL,

From: Desmond Cheong Zhi Xi desmondcheongzx@gmail.com

commit 1815d9c86e3090477fbde066ff314a7e9721ee0f upstream.

While checking the master status of the DRM file in drm_is_current_master(), the device's master mutex should be held. Without the mutex, the pointer fpriv->master may be freed concurrently by another process calling drm_setmaster_ioctl(). This could lead to use-after-free errors when the pointer is subsequently dereferenced in drm_lease_owner().

The callers of drm_is_current_master() from drm_auth.c hold the device's master mutex, but external callers do not. Hence, we implement drm_is_current_master_locked() to be used within drm_auth.c, and modify drm_is_current_master() to grab the device's master mutex before checking the master status.

Reported-by: Daniel Vetter daniel.vetter@ffwll.ch Signed-off-by: Desmond Cheong Zhi Xi desmondcheongzx@gmail.com Reviewed-by: Emil Velikov emil.l.velikov@gmail.com Cc: stable@vger.kernel.org Signed-off-by: Daniel Vetter daniel.vetter@ffwll.ch Link: https://patchwork.freedesktop.org/patch/msgid/20210620110327.4964-2-desmondc... Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/gpu/drm/drm_auth.c | 51 ++++++++++++++++++++++++-------------- 1 file changed, 32 insertions(+), 19 deletions(-)

diff --git a/drivers/gpu/drm/drm_auth.c b/drivers/gpu/drm/drm_auth.c index 232abbba3686..86d4b72e95cb 100644 --- a/drivers/gpu/drm/drm_auth.c +++ b/drivers/gpu/drm/drm_auth.c @@ -61,6 +61,35 @@ * trusted clients. */

+static bool drm_is_current_master_locked(struct drm_file *fpriv) +{ + lockdep_assert_held_once(&fpriv->master->dev->master_mutex); + + return fpriv->is_master && drm_lease_owner(fpriv->master) == fpriv->minor->dev->master; +} + +/** + * drm_is_current_master - checks whether @priv is the current master + * @fpriv: DRM file private + * + * Checks whether @fpriv is current master on its device. This decides whether a + * client is allowed to run DRM_MASTER IOCTLs. + * + * Most of the modern IOCTL which require DRM_MASTER are for kernel modesetting + * - the current master is assumed to own the non-shareable display hardware. + */ +bool drm_is_current_master(struct drm_file *fpriv) +{ + bool ret; + + mutex_lock(&fpriv->master->dev->master_mutex); + ret = drm_is_current_master_locked(fpriv); + mutex_unlock(&fpriv->master->dev->master_mutex); + + return ret; +} +EXPORT_SYMBOL(drm_is_current_master); + int drm_getmagic(struct drm_device *dev, void *data, struct drm_file *file_priv) { struct drm_auth *auth = data; @@ -223,7 +252,7 @@ int drm_setmaster_ioctl(struct drm_device *dev, void *data, if (ret) goto out_unlock;

- if (drm_is_current_master(file_priv)) + if (drm_is_current_master_locked(file_priv)) goto out_unlock;

if (dev->master) { @@ -272,7 +301,7 @@ int drm_dropmaster_ioctl(struct drm_device *dev, void *data, if (ret) goto out_unlock;

- if (!drm_is_current_master(file_priv)) { + if (!drm_is_current_master_locked(file_priv)) { ret = -EINVAL; goto out_unlock; } @@ -321,7 +350,7 @@ void drm_master_release(struct drm_file *file_priv) if (file_priv->magic) idr_remove(&file_priv->master->magic_map, file_priv->magic);

- if (!drm_is_current_master(file_priv)) + if (!drm_is_current_master_locked(file_priv)) goto out;

drm_legacy_lock_master_cleanup(dev, master); @@ -342,22 +371,6 @@ void drm_master_release(struct drm_file *file_priv) mutex_unlock(&dev->master_mutex); }

-/** - * drm_is_current_master - checks whether @priv is the current master - * @fpriv: DRM file private - * - * Checks whether @fpriv is current master on its device. This decides whether a - * client is allowed to run DRM_MASTER IOCTLs. - * - * Most of the modern IOCTL which require DRM_MASTER are for kernel modesetting - * - the current master is assumed to own the non-shareable display hardware. - */ -bool drm_is_current_master(struct drm_file *fpriv) -{ - return fpriv->is_master && drm_lease_owner(fpriv->master) == fpriv->minor->dev->master; -} -EXPORT_SYMBOL(drm_is_current_master); - /** * drm_master_get - reference a master pointer * @master: &struct drm_master

From: Christian König christian.koenig@amd.com

commit 4b41726aae563273bb4b4a9462ba51ce4d372f78 upstream.

We actually need to wait for the moving fence after pinning the BO to make sure that the pin is completed.

Signed-off-by: Christian König christian.koenig@amd.com Reviewed-by: Daniel Vetter daniel.vetter@ffwll.ch References: https://lore.kernel.org/dri-devel/20210621151758.2347474-1-daniel.vetter@ffw... CC: stable@kernel.org Link: https://patchwork.freedesktop.org/patch/msgid/20210622114506.106349-2-christ... Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/gpu/drm/radeon/radeon_prime.c | 16 +++++++++++++--- 1 file changed, 13 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/radeon/radeon_prime.c b/drivers/gpu/drm/radeon/radeon_prime.c index b9de0e51c0be..cbad81578190 100644 --- a/drivers/gpu/drm/radeon/radeon_prime.c +++ b/drivers/gpu/drm/radeon/radeon_prime.c @@ -94,9 +94,19 @@ int radeon_gem_prime_pin(struct drm_gem_object *obj)

/* pin buffer into GTT */ ret = radeon_bo_pin(bo, RADEON_GEM_DOMAIN_GTT, NULL); - if (likely(ret == 0)) - bo->prime_shared_count++; - + if (unlikely(ret)) + goto error; + + if (bo->tbo.moving) { + ret = dma_fence_wait(bo->tbo.moving, false); + if (unlikely(ret)) { + radeon_bo_unpin(bo); + goto error; + } + } + + bo->prime_shared_count++; +error: radeon_bo_unreserve(bo); return ret; }

From: Arnd Bergmann arnd@arndb.de

commit dad7b9896a5dbac5da8275d5a6147c65c81fb5f2 upstream.

When building the kernel wtih gcc-10 or higher using the CONFIG_CC_OPTIMIZE_FOR_PERFORMANCE=y flag, the compiler picks a slightly different set of registers for the inline assembly in cpu_init() that subsequently results in a corrupt kernel stack as well as remaining in FIQ mode. If a banked register is used for the last argument, the wrong version of that register gets loaded into CPSR_c. When building in Arm mode, the arguments are passed as immediate values and the bug cannot happen.

This got introduced when Daniel reworked the FIQ handling and was technically always broken, but happened to work with both clang and gcc before gcc-10 as long as they picked one of the lower registers. This is probably an indication that still very few people build the kernel in Thumb2 mode.

Marek pointed out the problem on IRC, Arnd narrowed it down to this inline assembly and Russell pinpointed the exact bug.

Change the constraints to force the final mode switch to use a non-banked register for the argument to ensure that the correct constant gets loaded. Another alternative would be to always use registers for the constant arguments to avoid the #ifdef that has now become more complex.

Cc: stable@vger.kernel.org # v3.18+ Cc: Daniel Thompson daniel.thompson@linaro.org Reported-by: Marek Vasut marek.vasut@gmail.com Acked-by: Ard Biesheuvel ardb@kernel.org Fixes: c0e7f7ee717e ("ARM: 8150/3: fiq: Replace default FIQ handler") Signed-off-by: Arnd Bergmann arnd@arndb.de Signed-off-by: Russell King rmk+kernel@armlinux.org.uk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- arch/arm/kernel/setup.c | 16 +++++++++------- 1 file changed, 9 insertions(+), 7 deletions(-)

diff --git a/arch/arm/kernel/setup.c b/arch/arm/kernel/setup.c index f90479d8b50c..b06602cea99c 100644 --- a/arch/arm/kernel/setup.c +++ b/arch/arm/kernel/setup.c @@ -544,9 +544,11 @@ void notrace cpu_init(void) * In Thumb-2, msr with an immediate value is not allowed. */ #ifdef CONFIG_THUMB2_KERNEL -#define PLC "r" +#define PLC_l "l" +#define PLC_r "r" #else -#define PLC "I" +#define PLC_l "I" +#define PLC_r "I" #endif

/* @@ -568,15 +570,15 @@ void notrace cpu_init(void) "msr cpsr_c, %9" : : "r" (stk), - PLC (PSR_F_BIT | PSR_I_BIT | IRQ_MODE), + PLC_r (PSR_F_BIT | PSR_I_BIT | IRQ_MODE), "I" (offsetof(struct stack, irq[0])), - PLC (PSR_F_BIT | PSR_I_BIT | ABT_MODE), + PLC_r (PSR_F_BIT | PSR_I_BIT | ABT_MODE), "I" (offsetof(struct stack, abt[0])), - PLC (PSR_F_BIT | PSR_I_BIT | UND_MODE), + PLC_r (PSR_F_BIT | PSR_I_BIT | UND_MODE), "I" (offsetof(struct stack, und[0])), - PLC (PSR_F_BIT | PSR_I_BIT | FIQ_MODE), + PLC_r (PSR_F_BIT | PSR_I_BIT | FIQ_MODE), "I" (offsetof(struct stack, fiq[0])), - PLC (PSR_F_BIT | PSR_I_BIT | SVC_MODE) + PLC_l (PSR_F_BIT | PSR_I_BIT | SVC_MODE) : "r14"); #endif }

From: Nathan Chancellor nathan@kernel.org

commit e607ff630c6053ecc67502677c0e50053d7892d4 upstream.

With the latest mkimage from U-Boot 2021.04, the generic defconfigs no longer build, failing with:

/usr/bin/mkimage: verify_header failed for FIT Image support with exit code 1

This is expected after the linked U-Boot commits because '@' is forbidden in the node names due to the way that libfdt treats nodes with the same prefix but different unit addresses.

Switch the '@' in the node name to '-'. Drop the unit addresses from the hash and kernel child nodes because there is only one node so they do not need to have a number to differentiate them.

Cc: stable@vger.kernel.org Link: https://source.denx.de/u-boot/u-boot/-/commit/79af75f7776fc20b0d7eb6afe1e27c... Link: https://source.denx.de/u-boot/u-boot/-/commit/3f04db891a353f4b127ed57279279f... Suggested-by: Simon Glass sjg@chromium.org Signed-off-by: Nathan Chancellor nathan@kernel.org Reviewed-by: Tom Rini trini@konsulko.com Signed-off-by: Thomas Bogendoerfer tsbogend@alpha.franken.de [nathan: Backport to 5.10, only apply to .its.S files that exist] Signed-off-by: Nathan Chancellor nathan@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- arch/mips/generic/board-boston.its.S | 10 +++++----- arch/mips/generic/board-ni169445.its.S | 10 +++++----- arch/mips/generic/board-ocelot.its.S | 20 ++++++++++---------- arch/mips/generic/board-xilfpga.its.S | 10 +++++----- arch/mips/generic/vmlinux.its.S | 10 +++++----- 5 files changed, 30 insertions(+), 30 deletions(-)

diff --git a/arch/mips/generic/board-boston.its.S b/arch/mips/generic/board-boston.its.S index a7f51f97b910..c45ad2759421 100644 --- a/arch/mips/generic/board-boston.its.S +++ b/arch/mips/generic/board-boston.its.S @@ -1,22 +1,22 @@ / { images { - fdt@boston { + fdt-boston { description = "img,boston Device Tree"; data = /incbin/("boot/dts/img/boston.dtb"); type = "flat_dt"; arch = "mips"; compression = "none"; - hash@0 { + hash { algo = "sha1"; }; }; };

configurations { - conf@boston { + conf-boston { description = "Boston Linux kernel"; - kernel = "kernel@0"; - fdt = "fdt@boston"; + kernel = "kernel"; + fdt = "fdt-boston"; }; }; }; diff --git a/arch/mips/generic/board-ni169445.its.S b/arch/mips/generic/board-ni169445.its.S index e4cb4f95a8cc..0a2e8f7a8526 100644 --- a/arch/mips/generic/board-ni169445.its.S +++ b/arch/mips/generic/board-ni169445.its.S @@ -1,22 +1,22 @@ / { images { - fdt@ni169445 { + fdt-ni169445 { description = "NI 169445 device tree"; data = /incbin/("boot/dts/ni/169445.dtb"); type = "flat_dt"; arch = "mips"; compression = "none"; - hash@0 { + hash { algo = "sha1"; }; }; };

configurations { - conf@ni169445 { + conf-ni169445 { description = "NI 169445 Linux Kernel"; - kernel = "kernel@0"; - fdt = "fdt@ni169445"; + kernel = "kernel"; + fdt = "fdt-ni169445"; }; }; }; diff --git a/arch/mips/generic/board-ocelot.its.S b/arch/mips/generic/board-ocelot.its.S index 3da23988149a..8c7e3a1b68d3 100644 --- a/arch/mips/generic/board-ocelot.its.S +++ b/arch/mips/generic/board-ocelot.its.S @@ -1,40 +1,40 @@ /* SPDX-License-Identifier: (GPL-2.0 OR MIT) */ / { images { - fdt@ocelot_pcb123 { + fdt-ocelot_pcb123 { description = "MSCC Ocelot PCB123 Device Tree"; data = /incbin/("boot/dts/mscc/ocelot_pcb123.dtb"); type = "flat_dt"; arch = "mips"; compression = "none"; - hash@0 { + hash { algo = "sha1"; }; };

- fdt@ocelot_pcb120 { + fdt-ocelot_pcb120 { description = "MSCC Ocelot PCB120 Device Tree"; data = /incbin/("boot/dts/mscc/ocelot_pcb120.dtb"); type = "flat_dt"; arch = "mips"; compression = "none"; - hash@0 { + hash { algo = "sha1"; }; }; };

configurations { - conf@ocelot_pcb123 { + conf-ocelot_pcb123 { description = "Ocelot Linux kernel"; - kernel = "kernel@0"; - fdt = "fdt@ocelot_pcb123"; + kernel = "kernel"; + fdt = "fdt-ocelot_pcb123"; };

- conf@ocelot_pcb120 { + conf-ocelot_pcb120 { description = "Ocelot Linux kernel"; - kernel = "kernel@0"; - fdt = "fdt@ocelot_pcb120"; + kernel = "kernel"; + fdt = "fdt-ocelot_pcb120"; }; }; }; diff --git a/arch/mips/generic/board-xilfpga.its.S b/arch/mips/generic/board-xilfpga.its.S index a2e773d3f14f..08c1e900eb4e 100644 --- a/arch/mips/generic/board-xilfpga.its.S +++ b/arch/mips/generic/board-xilfpga.its.S @@ -1,22 +1,22 @@ / { images { - fdt@xilfpga { + fdt-xilfpga { description = "MIPSfpga (xilfpga) Device Tree"; data = /incbin/("boot/dts/xilfpga/nexys4ddr.dtb"); type = "flat_dt"; arch = "mips"; compression = "none"; - hash@0 { + hash { algo = "sha1"; }; }; };

configurations { - conf@xilfpga { + conf-xilfpga { description = "MIPSfpga Linux kernel"; - kernel = "kernel@0"; - fdt = "fdt@xilfpga"; + kernel = "kernel"; + fdt = "fdt-xilfpga"; }; }; }; diff --git a/arch/mips/generic/vmlinux.its.S b/arch/mips/generic/vmlinux.its.S index 1a08438fd893..3e254676540f 100644 --- a/arch/mips/generic/vmlinux.its.S +++ b/arch/mips/generic/vmlinux.its.S @@ -6,7 +6,7 @@ #address-cells = <ADDR_CELLS>;

images { - kernel@0 { + kernel { description = KERNEL_NAME; data = /incbin/(VMLINUX_BINARY); type = "kernel"; @@ -15,18 +15,18 @@ compression = VMLINUX_COMPRESSION; load = /bits/ ADDR_BITS <VMLINUX_LOAD_ADDRESS>; entry = /bits/ ADDR_BITS <VMLINUX_ENTRY_ADDRESS>; - hash@0 { + hash { algo = "sha1"; }; }; };

configurations { - default = "conf@default"; + default = "conf-default";

- conf@default { + conf-default { description = "Generic Linux kernel"; - kernel = "kernel@0"; + kernel = "kernel"; }; }; };

From: Catalin Marinas catalin.marinas@arm.com

commit 2687275a5843d1089687f08fc64eb3f3b026a169 upstream.

mem_init() currently relies on knowing the boundaries of the crashkernel reservation to map such region with page granularity for later unmapping via set_memory_valid(..., 0). If the crashkernel reservation is deferred, such boundaries are not known when the linear mapping is created. Simply parse the command line for "crashkernel" and, if found, create the linear map with NO_BLOCK_MAPPINGS.

Signed-off-by: Catalin Marinas catalin.marinas@arm.com Tested-by: Nicolas Saenz Julienne nsaenzjulienne@suse.de Reviewed-by: Nicolas Saenz Julienne nsaenzjulienne@suse.de Acked-by: James Morse james.morse@arm.com Cc: James Morse james.morse@arm.com Cc: Nicolas Saenz Julienne nsaenzjulienne@suse.de Link: https://lore.kernel.org/r/20201119175556.18681-1-catalin.marinas@arm.com Signed-off-by: Catalin Marinas catalin.marinas@arm.com Cc: Kefeng Wang wangkefeng.wang@huawei.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- arch/arm64/mm/mmu.c | 37 ++++++++++++++++--------------------- 1 file changed, 16 insertions(+), 21 deletions(-)

diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c index afdad7607850..58dc93e56617 100644 --- a/arch/arm64/mm/mmu.c +++ b/arch/arm64/mm/mmu.c @@ -469,6 +469,21 @@ void __init mark_linear_text_alias_ro(void) PAGE_KERNEL_RO); }

+static bool crash_mem_map __initdata; + +static int __init enable_crash_mem_map(char *arg) +{ + /* + * Proper parameter parsing is done by reserve_crashkernel(). We only + * need to know if the linear map has to avoid block mappings so that + * the crashkernel reservations can be unmapped later. + */ + crash_mem_map = true; + + return 0; +} +early_param("crashkernel", enable_crash_mem_map); + static void __init map_mem(pgd_t *pgdp) { phys_addr_t kernel_start = __pa_symbol(_text); @@ -477,7 +492,7 @@ static void __init map_mem(pgd_t *pgdp) int flags = 0; u64 i;

- if (rodata_full || debug_pagealloc_enabled()) + if (rodata_full || crash_mem_map || debug_pagealloc_enabled()) flags = NO_BLOCK_MAPPINGS | NO_CONT_MAPPINGS;

/* @@ -487,11 +502,6 @@ static void __init map_mem(pgd_t *pgdp) * the following for-loop */ memblock_mark_nomap(kernel_start, kernel_end - kernel_start); -#ifdef CONFIG_KEXEC_CORE - if (crashk_res.end) - memblock_mark_nomap(crashk_res.start, - resource_size(&crashk_res)); -#endif

/* map all the memory banks */ for_each_mem_range(i, &start, &end) { @@ -519,21 +529,6 @@ static void __init map_mem(pgd_t *pgdp) __map_memblock(pgdp, kernel_start, kernel_end, PAGE_KERNEL, NO_CONT_MAPPINGS); memblock_clear_nomap(kernel_start, kernel_end - kernel_start); - -#ifdef CONFIG_KEXEC_CORE - /* - * Use page-level mappings here so that we can shrink the region - * in page granularity and put back unused memory to buddy system - * through /sys/kernel/kexec_crash_size interface. - */ - if (crashk_res.end) { - __map_memblock(pgdp, crashk_res.start, crashk_res.end + 1, - PAGE_KERNEL, - NO_BLOCK_MAPPINGS | NO_CONT_MAPPINGS); - memblock_clear_nomap(crashk_res.start, - resource_size(&crashk_res)); - } -#endif }

void mark_rodata_ro(void)

From: "Rafael J. Wysocki" rafael.j.wysocki@intel.com

[ Upstream commit 4d6035f9bf4ea12776322746a216e856dfe46698 ]

Revert commit 4514d991d992 ("PCI: PM: Do not read power state in pci_enable_device_flags()") that is reported to cause PCI device initialization issues on some systems.

BugLink: https://bugzilla.kernel.org/show_bug.cgi?id=213481 Link: https://lore.kernel.org/linux-acpi/YNDoGICcg0V8HhpQ@eldamar.lan Reported-by: Michael phyre@rogers.com Reported-by: Salvatore Bonaccorso carnil@debian.org Fixes: 4514d991d992 ("PCI: PM: Do not read power state in pci_enable_device_flags()") Signed-off-by: Rafael J. Wysocki rafael.j.wysocki@intel.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/pci/pci.c | 16 +++++++++++++--- 1 file changed, 13 insertions(+), 3 deletions(-)

diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c index d5d9ea864fe6..9e971fffeb6a 100644 --- a/drivers/pci/pci.c +++ b/drivers/pci/pci.c @@ -1874,11 +1874,21 @@ static int pci_enable_device_flags(struct pci_dev *dev, unsigned long flags) int err; int i, bars = 0;

- if (atomic_inc_return(&dev->enable_cnt) > 1) { - pci_update_current_state(dev, dev->current_state); - return 0; /* already enabled */ + /* + * Power state could be unknown at this point, either due to a fresh + * boot or a device removal call. So get the current power state + * so that things like MSI message writing will behave as expected + * (e.g. if the device really is in D0 at enable time). + */ + if (dev->pm_cap) { + u16 pmcsr; + pci_read_config_word(dev, dev->pm_cap + PCI_PM_CTRL, &pmcsr); + dev->current_state = (pmcsr & PCI_PM_CTRL_STATE_MASK); }

+ if (atomic_inc_return(&dev->enable_cnt) > 1) + return 0; /* already enabled */ + bridge = pci_upstream_bridge(dev); if (bridge) pci_enable_bridge(bridge);

From: Maxime Ripard maxime@cerno.tech

[ Upstream commit 9984d6664ce9dcbbc713962539eaf7636ea246c2 ]

If the HPD GPIO is not available and drm_probe_ddc fails, we end up reading the HDMI_HOTPLUG register, but the controller might be powered off resulting in a CPU hang. Make sure we have the power domain and the HSM clock powered during the detect cycle to prevent the hang from happening.

Fixes: 4f6e3d66ac52 ("drm/vc4: Add runtime PM support to the HDMI encoder driver") Signed-off-by: Maxime Ripard maxime@cerno.tech Reviewed-by: Dave Stevenson dave.stevenson@raspberrypi.com Link: https://patchwork.freedesktop.org/patch/msgid/20210525091059.234116-4-maxime... Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/gpu/drm/vc4/vc4_hdmi.c | 4 ++++ 1 file changed, 4 insertions(+)

diff --git a/drivers/gpu/drm/vc4/vc4_hdmi.c b/drivers/gpu/drm/vc4/vc4_hdmi.c index 5978e99a0e85..88a8cb840cd5 100644 --- a/drivers/gpu/drm/vc4/vc4_hdmi.c +++ b/drivers/gpu/drm/vc4/vc4_hdmi.c @@ -146,6 +146,8 @@ vc4_hdmi_connector_detect(struct drm_connector *connector, bool force) struct vc4_hdmi *vc4_hdmi = connector_to_vc4_hdmi(connector); bool connected = false;

+ WARN_ON(pm_runtime_resume_and_get(&vc4_hdmi->pdev->dev)); + if (vc4_hdmi->hpd_gpio) { if (gpio_get_value_cansleep(vc4_hdmi->hpd_gpio) ^ vc4_hdmi->hpd_active_low) @@ -167,10 +169,12 @@ vc4_hdmi_connector_detect(struct drm_connector *connector, bool force) } }

+ pm_runtime_put(&vc4_hdmi->pdev->dev); return connector_status_connected; }

cec_phys_addr_invalidate(vc4_hdmi->cec_adap); + pm_runtime_put(&vc4_hdmi->pdev->dev); return connector_status_disconnected; }

From: Peter Zijlstra peterz@infradead.org

[ Upstream commit 240001d4e3041832e8a2654adc3ccf1683132b92 ]

Fix:

vmlinux.o: warning: objtool: __do_fast_syscall_32()+0xf5: call to trace_hardirqs_off() leaves .noinstr.text section

Fixes: 5d5675df792f ("x86/entry: Fix entry/exit mismatch on failed fast 32-bit syscalls") Signed-off-by: Peter Zijlstra (Intel) peterz@infradead.org Signed-off-by: Ingo Molnar mingo@kernel.org Link: https://lore.kernel.org/r/20210621120120.467898710@infradead.org Signed-off-by: Sasha Levin sashal@kernel.org --- arch/x86/entry/common.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/x86/entry/common.c b/arch/x86/entry/common.c index 2e4d91f3feea..93a3122cd15f 100644 --- a/arch/x86/entry/common.c +++ b/arch/x86/entry/common.c @@ -127,8 +127,8 @@ static noinstr bool __do_fast_syscall_32(struct pt_regs *regs) /* User code screwed up. */ regs->ax = -EFAULT;

- instrumentation_end(); local_irq_disable(); + instrumentation_end(); irqentry_exit_to_user_mode(regs); return false; }

From: Peter Zijlstra peterz@infradead.org

[ Upstream commit 49faa77759b211fff344898edc23bb780707fff5 ]

Better handle the failure paths.

vmlinux.o: warning: objtool: debug_locks_off()+0x23: call to console_verbose() leaves .noinstr.text section vmlinux.o: warning: objtool: debug_locks_off()+0x19: call to __kasan_check_write() leaves .noinstr.text section

debug_locks_off+0x19/0x40: instrument_atomic_write at include/linux/instrumented.h:86 (inlined by) __debug_locks_off at include/linux/debug_locks.h:17 (inlined by) debug_locks_off at lib/debug_locks.c:41

Fixes: 6eebad1ad303 ("lockdep: __always_inline more for noinstr") Signed-off-by: Peter Zijlstra (Intel) peterz@infradead.org Signed-off-by: Ingo Molnar mingo@kernel.org Link: https://lore.kernel.org/r/20210621120120.784404944@infradead.org Signed-off-by: Sasha Levin sashal@kernel.org --- include/linux/debug_locks.h | 2 ++ kernel/locking/lockdep.c | 4 +++- lib/debug_locks.c | 2 +- 3 files changed, 6 insertions(+), 2 deletions(-)

diff --git a/include/linux/debug_locks.h b/include/linux/debug_locks.h index 2915f56ad421..edb5c186b0b7 100644 --- a/include/linux/debug_locks.h +++ b/include/linux/debug_locks.h @@ -27,8 +27,10 @@ extern int debug_locks_off(void); int __ret = 0; \ \ if (!oops_in_progress && unlikely(c)) { \ + instrumentation_begin(); \ if (debug_locks_off() && !debug_locks_silent) \ WARN(1, "DEBUG_LOCKS_WARN_ON(%s)", #c); \ + instrumentation_end(); \ __ret = 1; \ } \ __ret; \ diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c index 858b96b438ce..cdca007551e7 100644 --- a/kernel/locking/lockdep.c +++ b/kernel/locking/lockdep.c @@ -842,7 +842,7 @@ static int count_matching_names(struct lock_class *new_class) }

/* used from NMI context -- must be lockless */ -static __always_inline struct lock_class * +static noinstr struct lock_class * look_up_lock_class(const struct lockdep_map *lock, unsigned int subclass) { struct lockdep_subclass_key *key; @@ -850,12 +850,14 @@ look_up_lock_class(const struct lockdep_map *lock, unsigned int subclass) struct lock_class *class;

if (unlikely(subclass >= MAX_LOCKDEP_SUBCLASSES)) { + instrumentation_begin(); debug_locks_off(); printk(KERN_ERR "BUG: looking up invalid subclass: %u\n", subclass); printk(KERN_ERR "turning off the locking correctness validator.\n"); dump_stack(); + instrumentation_end(); return NULL; }

diff --git a/lib/debug_locks.c b/lib/debug_locks.c index 06d3135bd184..a75ee30b77cb 100644 --- a/lib/debug_locks.c +++ b/lib/debug_locks.c @@ -36,7 +36,7 @@ EXPORT_SYMBOL_GPL(debug_locks_silent); /* * Generic 'turn off all lock debugging' function: */ -noinstr int debug_locks_off(void) +int debug_locks_off(void) { if (debug_locks && __debug_locks_off()) { if (!debug_locks_silent) {

From: Thomas Gleixner tglx@linutronix.de

[ Upstream commit 7f049fbdd57f6ea71dc741d903c19c73b2f70950 ]

XRSTORS requires a valid xstate buffer to work correctly. XSAVES does not guarantee to write a fully valid buffer according to the SDM:

"XSAVES does not write to any parts of the XSAVE header other than the XSTATE_BV and XCOMP_BV fields."

XRSTORS triggers a #GP:

"If bytes 63:16 of the XSAVE header are not all zero."

It's dubious at best how this can work at all when the buffer is not zeroed before use.

Allocate the buffers with __GFP_ZERO to prevent XRSTORS failure.

Fixes: ce711ea3cab9 ("perf/x86/intel/lbr: Support XSAVES/XRSTORS for LBR context switch") Signed-off-by: Thomas Gleixner tglx@linutronix.de Signed-off-by: Ingo Molnar mingo@kernel.org Link: https://lore.kernel.org/r/87wnr0wo2z.ffs@nanos.tec.linutronix.de Signed-off-by: Sasha Levin sashal@kernel.org --- arch/x86/events/intel/lbr.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/arch/x86/events/intel/lbr.c b/arch/x86/events/intel/lbr.c index 6c1231837382..29ec4fe48507 100644 --- a/arch/x86/events/intel/lbr.c +++ b/arch/x86/events/intel/lbr.c @@ -730,7 +730,8 @@ void reserve_lbr_buffers(void) if (!kmem_cache || cpuc->lbr_xsave) continue;

- cpuc->lbr_xsave = kmem_cache_alloc_node(kmem_cache, GFP_KERNEL, + cpuc->lbr_xsave = kmem_cache_alloc_node(kmem_cache, + GFP_KERNEL | __GFP_ZERO, cpu_to_node(cpu)); } }

From: Yu Kuai yukuai3@huawei.com

[ Upstream commit 83eb4868d325b86e18509d0874e911497667cb54 ]

pm_runtime_get_sync will increment pm usage counter even it failed. Forgetting to putting operation will result in reference leak here. Fix it by replacing it with pm_runtime_resume_and_get to keep usage counter balanced.

Reported-by: Hulk Robot hulkci@huawei.com Signed-off-by: Yu Kuai yukuai3@huawei.com Link: https://lore.kernel.org/r/20210517081826.1564698-2-yukuai3@huawei.com Signed-off-by: Vinod Koul vkoul@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/dma/stm32-mdma.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/dma/stm32-mdma.c b/drivers/dma/stm32-mdma.c index 08cfbfab837b..9d473923712a 100644 --- a/drivers/dma/stm32-mdma.c +++ b/drivers/dma/stm32-mdma.c @@ -1448,7 +1448,7 @@ static int stm32_mdma_alloc_chan_resources(struct dma_chan *c) return -ENOMEM; }

- ret = pm_runtime_get_sync(dmadev->ddev.dev); + ret = pm_runtime_resume_and_get(dmadev->ddev.dev); if (ret < 0) return ret;

@@ -1714,7 +1714,7 @@ static int stm32_mdma_pm_suspend(struct device *dev) u32 ccr, id; int ret;

- ret = pm_runtime_get_sync(dev); + ret = pm_runtime_resume_and_get(dev); if (ret < 0) return ret;

From: Laurent Pinchart laurent.pinchart@ideasonboard.com

[ Upstream commit 9f007e7b6643799e2a6538a5fe04f51c371c6657 ]

While the descriptor ID is stored in a 32-bit field in the hardware descriptor, only 16 bits are used by the hardware and are reported through the XILINX_DPDMA_CH_DESC_ID register. Failure to handle the wrap-around results in a descriptor ID mismatch after 65536 frames. Fix it.

Signed-off-by: Laurent Pinchart laurent.pinchart@ideasonboard.com Tested-by: Jianqiang Chen jianqiang.chen@xilinx.com Reviewed-by: Jianqiang Chen jianqiang.chen@xilinx.com Link: https://lore.kernel.org/r/20210520152420.23986-5-laurent.pinchart@ideasonboa... Signed-off-by: Vinod Koul vkoul@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/dma/xilinx/xilinx_dpdma.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/drivers/dma/xilinx/xilinx_dpdma.c b/drivers/dma/xilinx/xilinx_dpdma.c index ff7dfb3fdeb4..6c709803203a 100644 --- a/drivers/dma/xilinx/xilinx_dpdma.c +++ b/drivers/dma/xilinx/xilinx_dpdma.c @@ -113,6 +113,7 @@ #define XILINX_DPDMA_CH_VDO 0x020 #define XILINX_DPDMA_CH_PYLD_SZ 0x024 #define XILINX_DPDMA_CH_DESC_ID 0x028 +#define XILINX_DPDMA_CH_DESC_ID_MASK GENMASK(15, 0)

/* DPDMA descriptor fields */ #define XILINX_DPDMA_DESC_CONTROL_PREEMBLE 0xa5 @@ -866,7 +867,8 @@ static void xilinx_dpdma_chan_queue_transfer(struct xilinx_dpdma_chan *chan) * will be used, but it should be enough. */ list_for_each_entry(sw_desc, &desc->descriptors, node) - sw_desc->hw.desc_id = desc->vdesc.tx.cookie; + sw_desc->hw.desc_id = desc->vdesc.tx.cookie + & XILINX_DPDMA_CH_DESC_ID_MASK;

sw_desc = list_first_entry(&desc->descriptors, struct xilinx_dpdma_sw_desc, node); @@ -1086,7 +1088,8 @@ static void xilinx_dpdma_chan_vsync_irq(struct xilinx_dpdma_chan *chan) if (!chan->running || !pending) goto out;

- desc_id = dpdma_read(chan->reg, XILINX_DPDMA_CH_DESC_ID); + desc_id = dpdma_read(chan->reg, XILINX_DPDMA_CH_DESC_ID) + & XILINX_DPDMA_CH_DESC_ID_MASK;

/* If the retrigger raced with vsync, retry at the next frame. */ sw_desc = list_first_entry(&pending->descriptors,

From: Johannes Berg johannes.berg@intel.com

[ Upstream commit bd18de517923903a177508fc8813f44e717b1c00 ]

Syzbot reports that we may be able to get into a situation where mac80211 has pending ACK frames on shutdown with hwsim. It appears that the reason for this is that syzbot uses the wmediumd hooks to intercept/injection frames, and may shut down hwsim, removing the radio(s), while frames are pending in the air simulation.

Clean out the pending queue when the interface is stopped, after this the frames can't be reported back to mac80211 properly anyway.

Reported-by: syzbot+a063bbf0b15737362592@syzkaller.appspotmail.com Link: https://lore.kernel.org/r/20210517170429.b0f85ab0eda1.Ie42a6ec6b940c971f3441... Signed-off-by: Johannes Berg johannes.berg@intel.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/wireless/mac80211_hwsim.c | 5 +++++ 1 file changed, 5 insertions(+)

diff --git a/drivers/net/wireless/mac80211_hwsim.c b/drivers/net/wireless/mac80211_hwsim.c index 3b3fc7c9c91d..f147d4feedb9 100644 --- a/drivers/net/wireless/mac80211_hwsim.c +++ b/drivers/net/wireless/mac80211_hwsim.c @@ -1623,8 +1623,13 @@ static int mac80211_hwsim_start(struct ieee80211_hw *hw) static void mac80211_hwsim_stop(struct ieee80211_hw *hw) { struct mac80211_hwsim_data *data = hw->priv; + data->started = false; hrtimer_cancel(&data->beacon_timer); + + while (!skb_queue_empty(&data->pending)) + ieee80211_free_txskb(hw, skb_dequeue(&data->pending)); + wiphy_dbg(hw->wiphy, "%s\n", __func__); }

From: Zou Wei zou_wei@huawei.com

[ Upstream commit dea8464ddf553803382efb753b6727dbf3931d06 ]

pm_runtime_get_sync will increment pm usage counter even it failed. Forgetting to putting operation will result in reference leak here. Fix it by replacing it with pm_runtime_resume_and_get to keep usage counter balanced.

Reported-by: Hulk Robot hulkci@huawei.com Signed-off-by: Zou Wei zou_wei@huawei.com Reviewed-by: Laurent Pinchart laurent.pinchart@ideasonboard.com Reviewed-by: Geert Uytterhoeven geert+renesas@glider.be Link: https://lore.kernel.org/r/1622442963-54095-1-git-send-email-zou_wei@huawei.c... Signed-off-by: Vinod Koul vkoul@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/dma/sh/rcar-dmac.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/dma/sh/rcar-dmac.c b/drivers/dma/sh/rcar-dmac.c index a57705356e8b..991a7b5da29f 100644 --- a/drivers/dma/sh/rcar-dmac.c +++ b/drivers/dma/sh/rcar-dmac.c @@ -1874,7 +1874,7 @@ static int rcar_dmac_probe(struct platform_device *pdev)

/* Enable runtime PM and initialize the device. */ pm_runtime_enable(&pdev->dev); - ret = pm_runtime_get_sync(&pdev->dev); + ret = pm_runtime_resume_and_get(&pdev->dev); if (ret < 0) { dev_err(&pdev->dev, "runtime PM get sync failed (%d)\n", ret); return ret;

From: Guillaume Ranquet granquet@baylibre.com

[ Upstream commit 2537b40b0a4f61d2c83900744fe89b09076be9c6 ]

Avoid issuing a new desc if one is still being processed as this can lead to some desc never being marked as completed.

Signed-off-by: Guillaume Ranquet granquet@baylibre.com

Link: https://lore.kernel.org/r/20210513192642.29446-3-granquet@baylibre.com Signed-off-by: Vinod Koul vkoul@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/dma/mediatek/mtk-uart-apdma.c | 20 ++++++++++++-------- 1 file changed, 12 insertions(+), 8 deletions(-)

diff --git a/drivers/dma/mediatek/mtk-uart-apdma.c b/drivers/dma/mediatek/mtk-uart-apdma.c index e38b67fc0c0c..a09ab2dd3b46 100644 --- a/drivers/dma/mediatek/mtk-uart-apdma.c +++ b/drivers/dma/mediatek/mtk-uart-apdma.c @@ -204,14 +204,9 @@ static void mtk_uart_apdma_start_rx(struct mtk_chan *c)

static void mtk_uart_apdma_tx_handler(struct mtk_chan *c) { - struct mtk_uart_apdma_desc *d = c->desc; - mtk_uart_apdma_write(c, VFF_INT_FLAG, VFF_TX_INT_CLR_B); mtk_uart_apdma_write(c, VFF_INT_EN, VFF_INT_EN_CLR_B); mtk_uart_apdma_write(c, VFF_EN, VFF_EN_CLR_B); - - list_del(&d->vd.node); - vchan_cookie_complete(&d->vd); }

static void mtk_uart_apdma_rx_handler(struct mtk_chan *c) @@ -242,9 +237,17 @@ static void mtk_uart_apdma_rx_handler(struct mtk_chan *c)

c->rx_status = d->avail_len - cnt; mtk_uart_apdma_write(c, VFF_RPT, wg); +}

- list_del(&d->vd.node); - vchan_cookie_complete(&d->vd); +static void mtk_uart_apdma_chan_complete_handler(struct mtk_chan *c) +{ + struct mtk_uart_apdma_desc *d = c->desc; + + if (d) { + list_del(&d->vd.node); + vchan_cookie_complete(&d->vd); + c->desc = NULL; + } }

static irqreturn_t mtk_uart_apdma_irq_handler(int irq, void *dev_id) @@ -258,6 +261,7 @@ static irqreturn_t mtk_uart_apdma_irq_handler(int irq, void *dev_id) mtk_uart_apdma_rx_handler(c); else if (c->dir == DMA_MEM_TO_DEV) mtk_uart_apdma_tx_handler(c); + mtk_uart_apdma_chan_complete_handler(c); spin_unlock_irqrestore(&c->vc.lock, flags);

return IRQ_HANDLED; @@ -363,7 +367,7 @@ static void mtk_uart_apdma_issue_pending(struct dma_chan *chan) unsigned long flags;

spin_lock_irqsave(&c->vc.lock, flags); - if (vchan_issue_pending(&c->vc)) { + if (vchan_issue_pending(&c->vc) && !c->desc) { vd = vchan_next_desc(&c->vc); c->desc = to_mtk_uart_apdma_desc(&vd->tx);

From: Zheng Yongjun zhengyongjun3@huawei.com

[ Upstream commit 5ac6b198d7e312bd10ebe7d58c64690dc59cc49a ]

When 'nla_parse_nested_deprecated' failed, it's no need to BUG() here, return -EINVAL is ok.

Signed-off-by: Zheng Yongjun zhengyongjun3@huawei.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- net/ipv4/devinet.c | 2 +- net/ipv6/addrconf.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index 123a6d39438f..7c1859777429 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -1989,7 +1989,7 @@ static int inet_set_link_af(struct net_device *dev, const struct nlattr *nla) return -EAFNOSUPPORT;

if (nla_parse_nested_deprecated(tb, IFLA_INET_MAX, nla, NULL, NULL) < 0) - BUG(); + return -EINVAL;

if (tb[IFLA_INET_CONF]) { nla_for_each_nested(a, tb[IFLA_INET_CONF], rem) diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 4c881f5d9080..884d430e23cb 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -5799,7 +5799,7 @@ static int inet6_set_link_af(struct net_device *dev, const struct nlattr *nla) return -EAFNOSUPPORT;

if (nla_parse_nested_deprecated(tb, IFLA_INET6_MAX, nla, NULL, NULL) < 0) - BUG(); + return -EINVAL;

if (tb[IFLA_INET6_TOKEN]) { err = inet6_set_iftoken(idev, nla_data(tb[IFLA_INET6_TOKEN]));

From: Austin Kim austindh.kim@gmail.com

[ Upstream commit 80ec82e3d2c1fab42eeb730aaa7985494a963d3f ]

Several ethtool functions leave heap uncleared (potentially) by drivers. This will leave the unused portion of heap unchanged and might copy the full contents back to userspace.

Signed-off-by: Austin Kim austindh.kim@gmail.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- net/ethtool/ioctl.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/net/ethtool/ioctl.c b/net/ethtool/ioctl.c index 2917af3f5ac1..68ff19af195c 100644 --- a/net/ethtool/ioctl.c +++ b/net/ethtool/ioctl.c @@ -1421,7 +1421,7 @@ static int ethtool_get_any_eeprom(struct net_device *dev, void __user *useraddr, if (eeprom.offset + eeprom.len > total_len) return -EINVAL;

- data = kmalloc(PAGE_SIZE, GFP_USER); + data = kzalloc(PAGE_SIZE, GFP_USER); if (!data) return -ENOMEM;

@@ -1486,7 +1486,7 @@ static int ethtool_set_eeprom(struct net_device *dev, void __user *useraddr) if (eeprom.offset + eeprom.len > ops->get_eeprom_len(dev)) return -EINVAL;

- data = kmalloc(PAGE_SIZE, GFP_USER); + data = kzalloc(PAGE_SIZE, GFP_USER); if (!data) return -ENOMEM;

@@ -1765,7 +1765,7 @@ static int ethtool_self_test(struct net_device *dev, char __user *useraddr) return -EFAULT;

test.len = test_len; - data = kmalloc_array(test_len, sizeof(u64), GFP_USER); + data = kcalloc(test_len, sizeof(u64), GFP_USER); if (!data) return -ENOMEM;

@@ -2281,7 +2281,7 @@ static int ethtool_get_tunable(struct net_device *dev, void __user *useraddr) ret = ethtool_tunable_valid(&tuna); if (ret) return ret; - data = kmalloc(tuna.len, GFP_USER); + data = kzalloc(tuna.len, GFP_USER); if (!data) return -ENOMEM; ret = ops->get_tunable(dev, &tuna, data); @@ -2473,7 +2473,7 @@ static int get_phy_tunable(struct net_device *dev, void __user *useraddr) ret = ethtool_phy_tunable_valid(&tuna); if (ret) return ret; - data = kmalloc(tuna.len, GFP_USER); + data = kzalloc(tuna.len, GFP_USER); if (!data) return -ENOMEM; if (phy_drv_tunable) {

From: Zheng Yongjun zhengyongjun3@huawei.com

[ Upstream commit 9d44fa3e50cc91691896934d106c86e4027e61ca ]

Function 'ping_queue_rcv_skb' not always return success, which will also return fail. If not check the wrong return value of it, lead to function `ping_rcv` return success.

Signed-off-by: Zheng Yongjun zhengyongjun3@huawei.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- net/ipv4/ping.c | 12 +++++++----- 1 file changed, 7 insertions(+), 5 deletions(-)

diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c index 248856b301c4..8ce8b7300b9d 100644 --- a/net/ipv4/ping.c +++ b/net/ipv4/ping.c @@ -952,6 +952,7 @@ bool ping_rcv(struct sk_buff *skb) struct sock *sk; struct net *net = dev_net(skb->dev); struct icmphdr *icmph = icmp_hdr(skb); + bool rc = false;

/* We assume the packet has already been checked by icmp_rcv */

@@ -966,14 +967,15 @@ bool ping_rcv(struct sk_buff *skb) struct sk_buff *skb2 = skb_clone(skb, GFP_ATOMIC);

pr_debug("rcv on socket %p\n", sk); - if (skb2) - ping_queue_rcv_skb(sk, skb2); + if (skb2 && !ping_queue_rcv_skb(sk, skb2)) + rc = true; sock_put(sk); - return true; } - pr_debug("no socket, dropping\n");

- return false; + if (!rc) + pr_debug("no socket, dropping\n"); + + return rc; } EXPORT_SYMBOL_GPL(ping_rcv);

From: Eric Dumazet edumazet@google.com

[ Upstream commit b71eaed8c04f72a919a9c44e83e4ee254e69e7f3 ]

UDP sendmsg() path can be lockless, it is possible for another thread to re-connect an change sk->sk_txhash under us.

There is no serious impact, but we can use READ_ONCE()/WRITE_ONCE() pair to document the race.

BUG: KCSAN: data-race in __ip4_datagram_connect / skb_set_owner_w

write to 0xffff88813397920c of 4 bytes by task 30997 on cpu 1: sk_set_txhash include/net/sock.h:1937 [inline] __ip4_datagram_connect+0x69e/0x710 net/ipv4/datagram.c:75 __ip6_datagram_connect+0x551/0x840 net/ipv6/datagram.c:189 ip6_datagram_connect+0x2a/0x40 net/ipv6/datagram.c:272 inet_dgram_connect+0xfd/0x180 net/ipv4/af_inet.c:580 __sys_connect_file net/socket.c:1837 [inline] __sys_connect+0x245/0x280 net/socket.c:1854 __do_sys_connect net/socket.c:1864 [inline] __se_sys_connect net/socket.c:1861 [inline] __x64_sys_connect+0x3d/0x50 net/socket.c:1861 do_syscall_64+0x4a/0x90 arch/x86/entry/common.c:47 entry_SYSCALL_64_after_hwframe+0x44/0xae

read to 0xffff88813397920c of 4 bytes by task 31039 on cpu 0: skb_set_hash_from_sk include/net/sock.h:2211 [inline] skb_set_owner_w+0x118/0x220 net/core/sock.c:2101 sock_alloc_send_pskb+0x452/0x4e0 net/core/sock.c:2359 sock_alloc_send_skb+0x2d/0x40 net/core/sock.c:2373 __ip6_append_data+0x1743/0x21a0 net/ipv6/ip6_output.c:1621 ip6_make_skb+0x258/0x420 net/ipv6/ip6_output.c:1983 udpv6_sendmsg+0x160a/0x16b0 net/ipv6/udp.c:1527 inet6_sendmsg+0x5f/0x80 net/ipv6/af_inet6.c:642 sock_sendmsg_nosec net/socket.c:654 [inline] sock_sendmsg net/socket.c:674 [inline] ____sys_sendmsg+0x360/0x4d0 net/socket.c:2350 ___sys_sendmsg net/socket.c:2404 [inline] __sys_sendmmsg+0x315/0x4b0 net/socket.c:2490 __do_sys_sendmmsg net/socket.c:2519 [inline] __se_sys_sendmmsg net/socket.c:2516 [inline] __x64_sys_sendmmsg+0x53/0x60 net/socket.c:2516 do_syscall_64+0x4a/0x90 arch/x86/entry/common.c:47 entry_SYSCALL_64_after_hwframe+0x44/0xae

value changed: 0xbca3c43d -> 0xfdb309e0

Reported by Kernel Concurrency Sanitizer on: CPU: 0 PID: 31039 Comm: syz-executor.2 Not tainted 5.13.0-rc3-syzkaller #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011

Signed-off-by: Eric Dumazet edumazet@google.com Reported-by: syzbot syzkaller@googlegroups.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- include/net/sock.h | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-)

diff --git a/include/net/sock.h b/include/net/sock.h index 9199ab7ab2da..3c7addf95150 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -1900,7 +1900,8 @@ static inline u32 net_tx_rndhash(void)

static inline void sk_set_txhash(struct sock *sk) { - sk->sk_txhash = net_tx_rndhash(); + /* This pairs with READ_ONCE() in skb_set_hash_from_sk() */ + WRITE_ONCE(sk->sk_txhash, net_tx_rndhash()); }

static inline bool sk_rethink_txhash(struct sock *sk) @@ -2172,9 +2173,12 @@ static inline void sock_poll_wait(struct file *filp, struct socket *sock,

static inline void skb_set_hash_from_sk(struct sk_buff *skb, struct sock *sk) { - if (sk->sk_txhash) { + /* This pairs with WRITE_ONCE() in sk_set_txhash() */ + u32 txhash = READ_ONCE(sk->sk_txhash); + + if (txhash) { skb->l4_hash = 1; - skb->hash = sk->sk_txhash; + skb->hash = txhash; } }

From: Praneeth Bajjuri praneeth@ti.com

[ Upstream commit da9ef50f545f86ffe6ff786174d26500c4db737a ]

Current logic is performing hard reset and causing the programmed registers to be wiped out.

as per datasheet: https://www.ti.com/lit/ds/symlink/dp83867cr.pdf 8.6.26 Control Register (CTRL)

do SW_RESTART to perform a reset not including the registers, If performed when link is already present, it will drop the link and trigger re-auto negotiation.

Signed-off-by: Praneeth Bajjuri praneeth@ti.com Signed-off-by: Geet Modi geet.modi@ti.com Reviewed-by: Andrew Lunn andrew@lunn.ch Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/phy/dp83867.c | 6 +----- 1 file changed, 1 insertion(+), 5 deletions(-)

diff --git a/drivers/net/phy/dp83867.c b/drivers/net/phy/dp83867.c index 69d3eacc2b96..c716074fdef0 100644 --- a/drivers/net/phy/dp83867.c +++ b/drivers/net/phy/dp83867.c @@ -792,16 +792,12 @@ static int dp83867_phy_reset(struct phy_device *phydev) { int err;

- err = phy_write(phydev, DP83867_CTRL, DP83867_SW_RESET); + err = phy_write(phydev, DP83867_CTRL, DP83867_SW_RESTART); if (err < 0) return err;

usleep_range(10, 20);

- /* After reset FORCE_LINK_GOOD bit is set. Although the - * default value should be unset. Disable FORCE_LINK_GOOD - * for the phy to work properly. - */ return phy_modify(phydev, MII_DP83867_PHYCTRL, DP83867_PHYCR_FORCE_LINK_GOOD, 0); }

From: Pavel Skripkin paskripkin@gmail.com

[ Upstream commit 58af3d3d54e87bfc1f936e16c04ade3369d34011 ]

Syzbot reported memory leak in tty_init_dev(). The problem was in unputted tty in ldisc_open()

static int ldisc_open(struct tty_struct *tty) { ... ser->tty = tty_kref_get(tty); ... result = register_netdevice(dev); if (result) { rtnl_unlock(); free_netdev(dev); return -ENODEV; } ... }

Ser pointer is netdev private_data, so after free_netdev() this pointer goes away with unputted tty reference. So, fix it by adding tty_kref_put() before freeing netdev.

Reported-and-tested-by: syzbot+f303e045423e617d2cad@syzkaller.appspotmail.com Signed-off-by: Pavel Skripkin paskripkin@gmail.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/caif/caif_serial.c | 1 + 1 file changed, 1 insertion(+)

diff --git a/drivers/net/caif/caif_serial.c b/drivers/net/caif/caif_serial.c index d025ea434933..39fbd0be179c 100644 --- a/drivers/net/caif/caif_serial.c +++ b/drivers/net/caif/caif_serial.c @@ -351,6 +351,7 @@ static int ldisc_open(struct tty_struct *tty) rtnl_lock(); result = register_netdevice(dev); if (result) { + tty_kref_put(tty); rtnl_unlock(); free_netdev(dev); return -ENODEV;

From: Eric Dumazet edumazet@google.com

[ Upstream commit e032f7c9c7cefffcfb79b9fc16c53011d2d9d11f ]

Like prior patch, we need to annotate lockless accesses to po->ifindex For instance, packet_getname() is reading po->ifindex (twice) while another thread is able to change po->ifindex.

KCSAN reported:

BUG: KCSAN: data-race in packet_do_bind / packet_getname

write to 0xffff888143ce3cbc of 4 bytes by task 25573 on cpu 1: packet_do_bind+0x420/0x7e0 net/packet/af_packet.c:3191 packet_bind+0xc3/0xd0 net/packet/af_packet.c:3255 __sys_bind+0x200/0x290 net/socket.c:1637 __do_sys_bind net/socket.c:1648 [inline] __se_sys_bind net/socket.c:1646 [inline] __x64_sys_bind+0x3d/0x50 net/socket.c:1646 do_syscall_64+0x4a/0x90 arch/x86/entry/common.c:47 entry_SYSCALL_64_after_hwframe+0x44/0xae

read to 0xffff888143ce3cbc of 4 bytes by task 25578 on cpu 0: packet_getname+0x5b/0x1a0 net/packet/af_packet.c:3525 __sys_getsockname+0x10e/0x1a0 net/socket.c:1887 __do_sys_getsockname net/socket.c:1902 [inline] __se_sys_getsockname net/socket.c:1899 [inline] __x64_sys_getsockname+0x3e/0x50 net/socket.c:1899 do_syscall_64+0x4a/0x90 arch/x86/entry/common.c:47 entry_SYSCALL_64_after_hwframe+0x44/0xae

value changed: 0x00000000 -> 0x00000001

Reported by Kernel Concurrency Sanitizer on: CPU: 0 PID: 25578 Comm: syz-executor.5 Not tainted 5.13.0-rc6-syzkaller #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011

Signed-off-by: Eric Dumazet edumazet@google.com Reported-by: syzbot syzkaller@googlegroups.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- net/packet/af_packet.c | 16 +++++++++------- 1 file changed, 9 insertions(+), 7 deletions(-)

diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index c4eb26f0f1a7..08144559eed5 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -3186,11 +3186,11 @@ static int packet_do_bind(struct sock *sk, const char *name, int ifindex, if (unlikely(unlisted)) { dev_put(dev); po->prot_hook.dev = NULL; - po->ifindex = -1; + WRITE_ONCE(po->ifindex, -1); packet_cached_dev_reset(po); } else { po->prot_hook.dev = dev; - po->ifindex = dev ? dev->ifindex : 0; + WRITE_ONCE(po->ifindex, dev ? dev->ifindex : 0); packet_cached_dev_assign(po, dev); } } @@ -3504,7 +3504,7 @@ static int packet_getname_spkt(struct socket *sock, struct sockaddr *uaddr, uaddr->sa_family = AF_PACKET; memset(uaddr->sa_data, 0, sizeof(uaddr->sa_data)); rcu_read_lock(); - dev = dev_get_by_index_rcu(sock_net(sk), pkt_sk(sk)->ifindex); + dev = dev_get_by_index_rcu(sock_net(sk), READ_ONCE(pkt_sk(sk)->ifindex)); if (dev) strlcpy(uaddr->sa_data, dev->name, sizeof(uaddr->sa_data)); rcu_read_unlock(); @@ -3519,16 +3519,18 @@ static int packet_getname(struct socket *sock, struct sockaddr *uaddr, struct sock *sk = sock->sk; struct packet_sock *po = pkt_sk(sk); DECLARE_SOCKADDR(struct sockaddr_ll *, sll, uaddr); + int ifindex;

if (peer) return -EOPNOTSUPP;

+ ifindex = READ_ONCE(po->ifindex); sll->sll_family = AF_PACKET; - sll->sll_ifindex = po->ifindex; + sll->sll_ifindex = ifindex; sll->sll_protocol = READ_ONCE(po->num); sll->sll_pkttype = 0; rcu_read_lock(); - dev = dev_get_by_index_rcu(sock_net(sk), po->ifindex); + dev = dev_get_by_index_rcu(sock_net(sk), ifindex); if (dev) { sll->sll_hatype = dev->type; sll->sll_halen = dev->addr_len; @@ -4107,7 +4109,7 @@ static int packet_notifier(struct notifier_block *this, } if (msg == NETDEV_UNREGISTER) { packet_cached_dev_reset(po); - po->ifindex = -1; + WRITE_ONCE(po->ifindex, -1); if (po->prot_hook.dev) dev_put(po->prot_hook.dev); po->prot_hook.dev = NULL; @@ -4617,7 +4619,7 @@ static int packet_seq_show(struct seq_file *seq, void *v) refcount_read(&s->sk_refcnt), s->sk_type, ntohs(READ_ONCE(po->num)), - po->ifindex, + READ_ONCE(po->ifindex), po->running, atomic_read(&s->sk_rmem_alloc), from_kuid_munged(seq_user_ns(seq), sock_i_uid(s)),

From: Kees Cook keescook@chromium.org

[ Upstream commit 224004fbb033600715dbd626bceec10bfd9c58bc ]

In preparation for FORTIFY_SOURCE performing compile-time and run-time field bounds checking for memcpy(), memmove(), and memset(), avoid intentionally reading across neighboring array fields.

The memcpy() is copying the entire structure, not just the first array. Adjust the source argument so the compiler can do appropriate bounds checking.

Signed-off-by: Kees Cook keescook@chromium.org Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/renesas/sh_eth.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/renesas/sh_eth.c b/drivers/net/ethernet/renesas/sh_eth.c index 6d84266c03ca..5cab2d3c0023 100644 --- a/drivers/net/ethernet/renesas/sh_eth.c +++ b/drivers/net/ethernet/renesas/sh_eth.c @@ -2287,7 +2287,7 @@ static void sh_eth_get_strings(struct net_device *ndev, u32 stringset, u8 *data) { switch (stringset) { case ETH_SS_STATS: - memcpy(data, *sh_eth_gstrings_stats, + memcpy(data, sh_eth_gstrings_stats, sizeof(sh_eth_gstrings_stats)); break; }

From: Fuad Tabba tabba@google.com

[ Upstream commit d8ac05ea13d789d5491a5920d70a05659015441d ]

KVM_CHECK_EXTENSION ioctl can return any negative value on error, and not necessarily -1. Change the assertion to reflect that.

Signed-off-by: Fuad Tabba tabba@google.com Message-Id: 20210615150443.1183365-1-tabba@google.com Signed-off-by: Paolo Bonzini pbonzini@redhat.com Signed-off-by: Sasha Levin sashal@kernel.org --- tools/testing/selftests/kvm/lib/kvm_util.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c index 126c6727a6b0..49805fd16fdf 100644 --- a/tools/testing/selftests/kvm/lib/kvm_util.c +++ b/tools/testing/selftests/kvm/lib/kvm_util.c @@ -55,7 +55,7 @@ int kvm_check_cap(long cap) exit(KSFT_SKIP);

ret = ioctl(kvm_fd, KVM_CHECK_EXTENSION, cap); - TEST_ASSERT(ret != -1, "KVM_CHECK_EXTENSION IOCTL failed,\n" + TEST_ASSERT(ret >= 0, "KVM_CHECK_EXTENSION IOCTL failed,\n" " rc: %i errno: %i", ret, errno);

close(kvm_fd);

From: Kees Cook keescook@chromium.org

[ Upstream commit 1c200f832e14420fa770193f9871f4ce2df00d07 ]

The source (&dcbx_info->operational.params) and dest (&p_hwfn->p_dcbx_info->set.config.params) are both struct qed_dcbx_params (560 bytes), not struct qed_dcbx_admin_params (564 bytes), which is used as the memcpy() size.

However it seems that struct qed_dcbx_operational_params (dcbx_info->operational)'s layout matches struct qed_dcbx_admin_params (p_hwfn->p_dcbx_info->set.config)'s 4 byte difference (3 padding, 1 byte for "valid").

On the assumption that the size is wrong (rather than the source structure type), adjust the memcpy() size argument to be 4 bytes smaller and add a BUILD_BUG_ON() to validate any changes to the structure sizes.

Signed-off-by: Kees Cook keescook@chromium.org Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/qlogic/qed/qed_dcbx.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/qlogic/qed/qed_dcbx.c b/drivers/net/ethernet/qlogic/qed/qed_dcbx.c index 17d5b649eb36..e81dd34a3cac 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_dcbx.c +++ b/drivers/net/ethernet/qlogic/qed/qed_dcbx.c @@ -1266,9 +1266,11 @@ int qed_dcbx_get_config_params(struct qed_hwfn *p_hwfn, p_hwfn->p_dcbx_info->set.ver_num |= DCBX_CONFIG_VERSION_STATIC;

p_hwfn->p_dcbx_info->set.enabled = dcbx_info->operational.enabled; + BUILD_BUG_ON(sizeof(dcbx_info->operational.params) != + sizeof(p_hwfn->p_dcbx_info->set.config.params)); memcpy(&p_hwfn->p_dcbx_info->set.config.params, &dcbx_info->operational.params, - sizeof(struct qed_dcbx_admin_params)); + sizeof(p_hwfn->p_dcbx_info->set.config.params)); p_hwfn->p_dcbx_info->set.config.valid = true;

memcpy(params, &p_hwfn->p_dcbx_info->set, sizeof(struct qed_dcbx_set));

From: Johannes Berg johannes.berg@intel.com

[ Upstream commit 652e8363bbc7d149fa194a5cbf30b1001c0274b0 ]

Various elements are parsed with a requirement to have an exact size, when really we should only check that they have the minimum size that we need. Check only that and therefore ignore any additional data that they might carry.

Signed-off-by: Johannes Berg johannes.berg@intel.com Signed-off-by: Luca Coelho luciano.coelho@intel.com Link: https://lore.kernel.org/r/iwlwifi.20210618133832.cd101f8040a4.Iadf0e9b37b100... Signed-off-by: Johannes Berg johannes.berg@intel.com Signed-off-by: Sasha Levin sashal@kernel.org --- net/mac80211/util.c | 22 +++++++++++----------- 1 file changed, 11 insertions(+), 11 deletions(-)

diff --git a/net/mac80211/util.c b/net/mac80211/util.c index d8f9fb0646a4..fbf56a203c0e 100644 --- a/net/mac80211/util.c +++ b/net/mac80211/util.c @@ -954,7 +954,7 @@ static void ieee80211_parse_extension_element(u32 *crc,

switch (elem->data[0]) { case WLAN_EID_EXT_HE_MU_EDCA: - if (len == sizeof(*elems->mu_edca_param_set)) { + if (len >= sizeof(*elems->mu_edca_param_set)) { elems->mu_edca_param_set = data; if (crc) *crc = crc32_be(*crc, (void *)elem, @@ -975,7 +975,7 @@ static void ieee80211_parse_extension_element(u32 *crc, } break; case WLAN_EID_EXT_UORA: - if (len == 1) + if (len >= 1) elems->uora_element = data; break; case WLAN_EID_EXT_MAX_CHANNEL_SWITCH_TIME: @@ -983,7 +983,7 @@ static void ieee80211_parse_extension_element(u32 *crc, elems->max_channel_switch_time = data; break; case WLAN_EID_EXT_MULTIPLE_BSSID_CONFIGURATION: - if (len == sizeof(*elems->mbssid_config_ie)) + if (len >= sizeof(*elems->mbssid_config_ie)) elems->mbssid_config_ie = data; break; case WLAN_EID_EXT_HE_SPR: @@ -992,7 +992,7 @@ static void ieee80211_parse_extension_element(u32 *crc, elems->he_spr = data; break; case WLAN_EID_EXT_HE_6GHZ_CAPA: - if (len == sizeof(*elems->he_6ghz_capa)) + if (len >= sizeof(*elems->he_6ghz_capa)) elems->he_6ghz_capa = data; break; } @@ -1081,14 +1081,14 @@ _ieee802_11_parse_elems_crc(const u8 *start, size_t len, bool action,

switch (id) { case WLAN_EID_LINK_ID: - if (elen + 2 != sizeof(struct ieee80211_tdls_lnkie)) { + if (elen + 2 < sizeof(struct ieee80211_tdls_lnkie)) { elem_parse_failed = true; break; } elems->lnk_id = (void *)(pos - 2); break; case WLAN_EID_CHAN_SWITCH_TIMING: - if (elen != sizeof(struct ieee80211_ch_switch_timing)) { + if (elen < sizeof(struct ieee80211_ch_switch_timing)) { elem_parse_failed = true; break; } @@ -1251,7 +1251,7 @@ _ieee802_11_parse_elems_crc(const u8 *start, size_t len, bool action, elems->sec_chan_offs = (void *)pos; break; case WLAN_EID_CHAN_SWITCH_PARAM: - if (elen != + if (elen < sizeof(*elems->mesh_chansw_params_ie)) { elem_parse_failed = true; break; @@ -1260,7 +1260,7 @@ _ieee802_11_parse_elems_crc(const u8 *start, size_t len, bool action, break; case WLAN_EID_WIDE_BW_CHANNEL_SWITCH: if (!action || - elen != sizeof(*elems->wide_bw_chansw_ie)) { + elen < sizeof(*elems->wide_bw_chansw_ie)) { elem_parse_failed = true; break; } @@ -1279,7 +1279,7 @@ _ieee802_11_parse_elems_crc(const u8 *start, size_t len, bool action, ie = cfg80211_find_ie(WLAN_EID_WIDE_BW_CHANNEL_SWITCH, pos, elen); if (ie) { - if (ie[1] == sizeof(*elems->wide_bw_chansw_ie)) + if (ie[1] >= sizeof(*elems->wide_bw_chansw_ie)) elems->wide_bw_chansw_ie = (void *)(ie + 2); else @@ -1323,7 +1323,7 @@ _ieee802_11_parse_elems_crc(const u8 *start, size_t len, bool action, elems->cisco_dtpc_elem = pos; break; case WLAN_EID_ADDBA_EXT: - if (elen != sizeof(struct ieee80211_addba_ext_ie)) { + if (elen < sizeof(struct ieee80211_addba_ext_ie)) { elem_parse_failed = true; break; } @@ -1349,7 +1349,7 @@ _ieee802_11_parse_elems_crc(const u8 *start, size_t len, bool action, elem, elems); break; case WLAN_EID_S1G_CAPABILITIES: - if (elen == sizeof(*elems->s1g_capab)) + if (elen >= sizeof(*elems->s1g_capab)) elems->s1g_capab = (void *)pos; else elem_parse_failed = true;

From: Mikel Rychliski mikel@mikelr.com

[ Upstream commit cacf994a91d3a55c0c2f853d6429cd7b86113915 ]

Although the AMD RS690 chipset has 64-bit DMA support, BIOS implementations sometimes fail to configure the memory limit registers correctly.

The Acer F690GVM mainboard uses this chipset and a Marvell 88E8056 NIC. The sky2 driver programs the NIC to use 64-bit DMA, which will not work:

sky2 0000:02:00.0: error interrupt status=0x8 sky2 0000:02:00.0 eth0: tx timeout sky2 0000:02:00.0 eth0: transmit ring 0 .. 22 report=0 done=0

Other drivers required by this mainboard either don't support 64-bit DMA, or have it disabled using driver specific quirks. For example, the ahci driver has quirks to enable or disable 64-bit DMA depending on the BIOS version (see ahci_sb600_enable_64bit() in ahci.c). This ahci quirk matches against the SB600 SATA controller, but the real issue is almost certainly with the RS690 PCI host that it was commonly attached to.

To avoid this issue in all drivers with 64-bit DMA support, fix the configuration of the PCI host. If the kernel is aware of physical memory above 4GB, but the BIOS never configured the PCI host with this information, update the registers with our values.

[bhelgaas: drop PCI_DEVICE_ID_ATI_RS690 definition] Link: https://lore.kernel.org/r/20210611214823.4898-1-mikel@mikelr.com Signed-off-by: Mikel Rychliski mikel@mikelr.com Signed-off-by: Bjorn Helgaas bhelgaas@google.com Signed-off-by: Sasha Levin sashal@kernel.org --- arch/x86/pci/fixup.c | 44 ++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 44 insertions(+)

diff --git a/arch/x86/pci/fixup.c b/arch/x86/pci/fixup.c index 0a0e168be1cb..9b0e771302ce 100644 --- a/arch/x86/pci/fixup.c +++ b/arch/x86/pci/fixup.c @@ -779,4 +779,48 @@ DECLARE_PCI_FIXUP_RESUME(PCI_VENDOR_ID_AMD, 0x1571, pci_amd_enable_64bit_bar); DECLARE_PCI_FIXUP_RESUME(PCI_VENDOR_ID_AMD, 0x15b1, pci_amd_enable_64bit_bar); DECLARE_PCI_FIXUP_RESUME(PCI_VENDOR_ID_AMD, 0x1601, pci_amd_enable_64bit_bar);

+#define RS690_LOWER_TOP_OF_DRAM2 0x30 +#define RS690_LOWER_TOP_OF_DRAM2_VALID 0x1 +#define RS690_UPPER_TOP_OF_DRAM2 0x31 +#define RS690_HTIU_NB_INDEX 0xA8 +#define RS690_HTIU_NB_INDEX_WR_ENABLE 0x100 +#define RS690_HTIU_NB_DATA 0xAC + +/* + * Some BIOS implementations support RAM above 4GB, but do not configure the + * PCI host to respond to bus master accesses for these addresses. These + * implementations set the TOP_OF_DRAM_SLOT1 register correctly, so PCI DMA + * works as expected for addresses below 4GB. + * + * Reference: "AMD RS690 ASIC Family Register Reference Guide" (pg. 2-57) + * https://www.amd.com/system/files/TechDocs/43372_rs690_rrg_3.00o.pdf + */ +static void rs690_fix_64bit_dma(struct pci_dev *pdev) +{ + u32 val = 0; + phys_addr_t top_of_dram = __pa(high_memory - 1) + 1; + + if (top_of_dram <= (1ULL << 32)) + return; + + pci_write_config_dword(pdev, RS690_HTIU_NB_INDEX, + RS690_LOWER_TOP_OF_DRAM2); + pci_read_config_dword(pdev, RS690_HTIU_NB_DATA, &val); + + if (val) + return; + + pci_info(pdev, "Adjusting top of DRAM to %pa for 64-bit DMA support\n", &top_of_dram); + + pci_write_config_dword(pdev, RS690_HTIU_NB_INDEX, + RS690_UPPER_TOP_OF_DRAM2 | RS690_HTIU_NB_INDEX_WR_ENABLE); + pci_write_config_dword(pdev, RS690_HTIU_NB_DATA, top_of_dram >> 32); + + pci_write_config_dword(pdev, RS690_HTIU_NB_INDEX, + RS690_LOWER_TOP_OF_DRAM2 | RS690_HTIU_NB_INDEX_WR_ENABLE); + pci_write_config_dword(pdev, RS690_HTIU_NB_DATA, + top_of_dram | RS690_LOWER_TOP_OF_DRAM2_VALID); +} +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ATI, 0x7910, rs690_fix_64bit_dma); + #endif

From: Esben Haabendal esben@geanix.com

[ Upstream commit f6396341194234e9b01cd7538bc2c6ac4501ab14 ]

As documented in Documentation/networking/driver.rst, the ndo_start_xmit method must not return NETDEV_TX_BUSY under any normal circumstances, and as recommended, we simply stop the tx queue in advance, when there is a risk that the next xmit would cause a NETDEV_TX_BUSY return.

Signed-off-by: Esben Haabendal esben@geanix.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/xilinx/ll_temac_main.c | 5 +++++ 1 file changed, 5 insertions(+)

diff --git a/drivers/net/ethernet/xilinx/ll_temac_main.c b/drivers/net/ethernet/xilinx/ll_temac_main.c index b105e1d35d15..6bd3a389d389 100644 --- a/drivers/net/ethernet/xilinx/ll_temac_main.c +++ b/drivers/net/ethernet/xilinx/ll_temac_main.c @@ -942,6 +942,11 @@ temac_start_xmit(struct sk_buff *skb, struct net_device *ndev) wmb(); lp->dma_out(lp, TX_TAILDESC_PTR, tail_p); /* DMA start */

+ if (temac_check_tx_bd_space(lp, MAX_SKB_FRAGS + 1)) { + netdev_info(ndev, "%s -> netif_stop_queue\n", __func__); + netif_stop_queue(ndev); + } + return NETDEV_TX_OK; }

From: Fabien Dessenne fabien.dessenne@foss.st.com

[ Upstream commit 67e2996f72c71ebe4ac2fcbcf77e54479bb7aa11 ]

Each GPIO bank supports a variable number of lines which is usually 16, but is less in some cases : this is specified by the last argument of the "gpio-ranges" bank node property. Report to the framework, the actual number of lines, so the libgpiod gpioinfo command lists the actually existing GPIO lines.

Fixes: 1dc9d289154b ("pinctrl: stm32: add possibility to use gpio-ranges to declare bank range") Signed-off-by: Fabien Dessenne fabien.dessenne@foss.st.com Link: https://lore.kernel.org/r/20210617144629.2557693-1-fabien.dessenne@foss.st.c... Signed-off-by: Linus Walleij linus.walleij@linaro.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/pinctrl/stm32/pinctrl-stm32.c | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-)

diff --git a/drivers/pinctrl/stm32/pinctrl-stm32.c b/drivers/pinctrl/stm32/pinctrl-stm32.c index 7d9bdedcd71b..3af4430543dc 100644 --- a/drivers/pinctrl/stm32/pinctrl-stm32.c +++ b/drivers/pinctrl/stm32/pinctrl-stm32.c @@ -1229,7 +1229,7 @@ static int stm32_gpiolib_register_bank(struct stm32_pinctrl *pctl, struct device *dev = pctl->dev; struct resource res; int npins = STM32_GPIO_PINS_PER_BANK; - int bank_nr, err; + int bank_nr, err, i = 0;

if (!IS_ERR(bank->rstc)) reset_control_deassert(bank->rstc); @@ -1251,9 +1251,14 @@ static int stm32_gpiolib_register_bank(struct stm32_pinctrl *pctl,

of_property_read_string(np, "st,bank-name", &bank->gpio_chip.label);

- if (!of_parse_phandle_with_fixed_args(np, "gpio-ranges", 3, 0, &args)) { + if (!of_parse_phandle_with_fixed_args(np, "gpio-ranges", 3, i, &args)) { bank_nr = args.args[1] / STM32_GPIO_PINS_PER_BANK; bank->gpio_chip.base = args.args[1]; + + npins = args.args[2]; + while (!of_parse_phandle_with_fixed_args(np, "gpio-ranges", 3, + ++i, &args)) + npins += args.args[2]; } else { bank_nr = pctl->nbanks; bank->gpio_chip.base = bank_nr * STM32_GPIO_PINS_PER_BANK;

From: Gabriel Knezek gabeknez@linux.microsoft.com

[ Upstream commit cb8f63b8cbf39845244f3ccae43bb7e63bd70543 ]

When userspace requests a GPIO v1 line info changed event, lineinfo_watch_read() populates and returns the gpioline_info_changed structure. It contains 5 words of padding at the end which are not initialized before being returned to userspace.

Zero the structure in gpio_v2_line_info_change_to_v1() before populating its contents.

Fixes: aad955842d1c ("gpiolib: cdev: support GPIO_V2_GET_LINEINFO_IOCTL and GPIO_V2_GET_LINEINFO_WATCH_IOCTL") Signed-off-by: Gabriel Knezek gabeknez@linux.microsoft.com Reviewed-by: Kent Gibson warthog618@gmail.com Signed-off-by: Bartosz Golaszewski bgolaszewski@baylibre.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/gpio/gpiolib-cdev.c | 1 + 1 file changed, 1 insertion(+)

diff --git a/drivers/gpio/gpiolib-cdev.c b/drivers/gpio/gpiolib-cdev.c index ade3ecf2ee49..2613881a66e6 100644 --- a/drivers/gpio/gpiolib-cdev.c +++ b/drivers/gpio/gpiolib-cdev.c @@ -1865,6 +1865,7 @@ static void gpio_v2_line_info_changed_to_v1( struct gpio_v2_line_info_changed *lic_v2, struct gpioline_info_changed *lic_v1) { + memset(lic_v1, 0, sizeof(*lic_v1)); gpio_v2_line_info_to_v1(&lic_v2->info, &lic_v1->info); lic_v1->timestamp = lic_v2->timestamp_ns; lic_v1->event_type = lic_v2->event_type;

From: Pavel Skripkin paskripkin@gmail.com

[ Upstream commit 8fd0c1b0647a6bda4067ee0cd61e8395954b6f28 ]

My local syzbot instance hit memory leak in nilfs2. The problem was in missing kobject_put() in nilfs_sysfs_delete_device_group().

kobject_del() does not call kobject_cleanup() for passed kobject and it leads to leaking duped kobject name if kobject_put() was not called.

Fail log:

BUG: memory leak unreferenced object 0xffff8880596171e0 (size 8): comm "syz-executor379", pid 8381, jiffies 4294980258 (age 21.100s) hex dump (first 8 bytes): 6c 6f 6f 70 30 00 00 00 loop0... backtrace: kstrdup+0x36/0x70 mm/util.c:60 kstrdup_const+0x53/0x80 mm/util.c:83 kvasprintf_const+0x108/0x190 lib/kasprintf.c:48 kobject_set_name_vargs+0x56/0x150 lib/kobject.c:289 kobject_add_varg lib/kobject.c:384 [inline] kobject_init_and_add+0xc9/0x160 lib/kobject.c:473 nilfs_sysfs_create_device_group+0x150/0x800 fs/nilfs2/sysfs.c:999 init_nilfs+0xe26/0x12b0 fs/nilfs2/the_nilfs.c:637

Link: https://lkml.kernel.org/r/20210612140559.20022-1-paskripkin@gmail.com Fixes: da7141fb78db ("nilfs2: add /sys/fs/nilfs2/<device> group") Signed-off-by: Pavel Skripkin paskripkin@gmail.com Acked-by: Ryusuke Konishi konishi.ryusuke@gmail.com Cc: Michael L. Semon mlsemon35@gmail.com Signed-off-by: Andrew Morton akpm@linux-foundation.org Signed-off-by: Linus Torvalds torvalds@linux-foundation.org Signed-off-by: Sasha Levin sashal@kernel.org --- fs/nilfs2/sysfs.c | 1 + 1 file changed, 1 insertion(+)

diff --git a/fs/nilfs2/sysfs.c b/fs/nilfs2/sysfs.c index 303d71430bdd..9c6c0e2e5880 100644 --- a/fs/nilfs2/sysfs.c +++ b/fs/nilfs2/sysfs.c @@ -1053,6 +1053,7 @@ void nilfs_sysfs_delete_device_group(struct the_nilfs *nilfs) nilfs_sysfs_delete_superblock_group(nilfs); nilfs_sysfs_delete_segctor_group(nilfs); kobject_del(&nilfs->ns_dev_kobj); + kobject_put(&nilfs->ns_dev_kobj); kfree(nilfs->ns_dev_subgroups); }

From: Nicholas Piggin npiggin@gmail.com

commit f8be156be163a052a067306417cd0ff679068c97 upstream.

It's possible to create a region which maps valid but non-refcounted pages (e.g., tail pages of non-compound higher order allocations). These host pages can then be returned by gfn_to_page, gfn_to_pfn, etc., family of APIs, which take a reference to the page, which takes it from 0 to 1. When the reference is dropped, this will free the page incorrectly.

Fix this by only taking a reference on valid pages if it was non-zero, which indicates it is participating in normal refcounting (and can be released with put_page).

This addresses CVE-2021-22543.

Signed-off-by: Nicholas Piggin npiggin@gmail.com Tested-by: Paolo Bonzini pbonzini@redhat.com Cc: stable@vger.kernel.org Signed-off-by: Paolo Bonzini pbonzini@redhat.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- virt/kvm/kvm_main.c | 19 +++++++++++++++++-- 1 file changed, 17 insertions(+), 2 deletions(-)

diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index f446c36f5800..1353439691cf 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -1883,6 +1883,13 @@ static bool vma_is_valid(struct vm_area_struct *vma, bool write_fault) return true; }

+static int kvm_try_get_pfn(kvm_pfn_t pfn) +{ + if (kvm_is_reserved_pfn(pfn)) + return 1; + return get_page_unless_zero(pfn_to_page(pfn)); +} + static int hva_to_pfn_remapped(struct vm_area_struct *vma, unsigned long addr, bool *async, bool write_fault, bool *writable, @@ -1932,13 +1939,21 @@ static int hva_to_pfn_remapped(struct vm_area_struct *vma, * Whoever called remap_pfn_range is also going to call e.g. * unmap_mapping_range before the underlying pages are freed, * causing a call to our MMU notifier. + * + * Certain IO or PFNMAP mappings can be backed with valid + * struct pages, but be allocated without refcounting e.g., + * tail pages of non-compound higher order allocations, which + * would then underflow the refcount when the caller does the + * required put_page. Don't allow those pages here. */ - kvm_get_pfn(pfn); + if (!kvm_try_get_pfn(pfn)) + r = -EFAULT;

out: pte_unmap_unlock(ptep, ptl); *p_pfn = pfn; - return 0; + + return r; }

/*

From: Jeff Layton jlayton@kernel.org

commit 27171ae6a0fdc75571e5bf3d0961631a1e4fb765 upstream.

...and add a lockdep assertion for it to ceph_fill_inode().

Cc: stable@vger.kernel.org # v5.7+ Fixes: 9a8d03ca2e2c3 ("ceph: attempt to do async create when possible") Signed-off-by: Jeff Layton jlayton@kernel.org Reviewed-by: Ilya Dryomov idryomov@gmail.com Signed-off-by: Ilya Dryomov idryomov@gmail.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- fs/ceph/file.c | 3 +++ fs/ceph/inode.c | 2 ++ 2 files changed, 5 insertions(+)

diff --git a/fs/ceph/file.c b/fs/ceph/file.c index 209535d5b8d3..3d2e3dd4ee01 100644 --- a/fs/ceph/file.c +++ b/fs/ceph/file.c @@ -578,6 +578,7 @@ static int ceph_finish_async_create(struct inode *dir, struct dentry *dentry, struct ceph_inode_info *ci = ceph_inode(dir); struct inode *inode; struct timespec64 now; + struct ceph_mds_client *mdsc = ceph_sb_to_mdsc(dir->i_sb); struct ceph_vino vino = { .ino = req->r_deleg_ino, .snap = CEPH_NOSNAP };

@@ -615,8 +616,10 @@ static int ceph_finish_async_create(struct inode *dir, struct dentry *dentry,

ceph_file_layout_to_legacy(lo, &in.layout);

+ down_read(&mdsc->snap_rwsem); ret = ceph_fill_inode(inode, NULL, &iinfo, NULL, req->r_session, req->r_fmode, NULL); + up_read(&mdsc->snap_rwsem); if (ret) { dout("%s failed to fill inode: %d\n", __func__, ret); ceph_dir_clear_complete(dir); diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c index 346fcdfcd3e9..57cd78e942c0 100644 --- a/fs/ceph/inode.c +++ b/fs/ceph/inode.c @@ -762,6 +762,8 @@ int ceph_fill_inode(struct inode *inode, struct page *locked_page, bool new_version = false; bool fill_inline = false;

+ lockdep_assert_held(&mdsc->snap_rwsem); + dout("%s %p ino %llx.%llx v %llu had %llu\n", __func__, inode, ceph_vinop(inode), le64_to_cpu(info->version), ci->i_version);

From: Petr Mladek pmladek@suse.com

commit 5fa54346caf67b4b1b10b1f390316ae466da4d53 upstream.

The system might hang with the following backtrace:

schedule+0x80/0x100 schedule_timeout+0x48/0x138 wait_for_common+0xa4/0x134 wait_for_completion+0x1c/0x2c kthread_flush_work+0x114/0x1cc kthread_cancel_work_sync.llvm.16514401384283632983+0xe8/0x144 kthread_cancel_delayed_work_sync+0x18/0x2c xxxx_pm_notify+0xb0/0xd8 blocking_notifier_call_chain_robust+0x80/0x194 pm_notifier_call_chain_robust+0x28/0x4c suspend_prepare+0x40/0x260 enter_state+0x80/0x3f4 pm_suspend+0x60/0xdc state_store+0x108/0x144 kobj_attr_store+0x38/0x88 sysfs_kf_write+0x64/0xc0 kernfs_fop_write_iter+0x108/0x1d0 vfs_write+0x2f4/0x368 ksys_write+0x7c/0xec

It is caused by the following race between kthread_mod_delayed_work() and kthread_cancel_delayed_work_sync():

CPU0 CPU1

Context: Thread A Context: Thread B

kthread_mod_delayed_work() spin_lock() __kthread_cancel_work() spin_unlock() del_timer_sync() kthread_cancel_delayed_work_sync() spin_lock() __kthread_cancel_work() spin_unlock() del_timer_sync() spin_lock()

work->canceling++ spin_unlock spin_lock() queue_delayed_work() // dwork is put into the worker->delayed_work_list

spin_unlock()

kthread_flush_work() // flush_work is put at the tail of the dwork

wait_for_completion()

Context: IRQ

kthread_delayed_work_timer_fn() spin_lock() list_del_init(&work->node); spin_unlock()

BANG: flush_work is not longer linked and will never get proceed.

The problem is that kthread_mod_delayed_work() checks work->canceling flag before canceling the timer.

A simple solution is to (re)check work->canceling after __kthread_cancel_work(). But then it is not clear what should be returned when __kthread_cancel_work() removed the work from the queue (list) and it can't queue it again with the new @delay.

The return value might be used for reference counting. The caller has to know whether a new work has been queued or an existing one was replaced.

The proper solution is that kthread_mod_delayed_work() will remove the work from the queue (list) _only_ when work->canceling is not set. The flag must be checked after the timer is stopped and the remaining operations can be done under worker->lock.

Note that kthread_mod_delayed_work() could remove the timer and then bail out. It is fine. The other canceling caller needs to cancel the timer as well. The important thing is that the queue (list) manipulation is done atomically under worker->lock.

Link: https://lkml.kernel.org/r/20210610133051.15337-3-pmladek@suse.com Fixes: 9a6b06c8d9a220860468a ("kthread: allow to modify delayed kthread work") Signed-off-by: Petr Mladek pmladek@suse.com Reported-by: Martin Liu liumartin@google.com Cc: jenhaochen@google.com Cc: Minchan Kim minchan@google.com Cc: Nathan Chancellor nathan@kernel.org Cc: Nick Desaulniers ndesaulniers@google.com Cc: Oleg Nesterov oleg@redhat.com Cc: Tejun Heo tj@kernel.org Cc: stable@vger.kernel.org Signed-off-by: Andrew Morton akpm@linux-foundation.org Signed-off-by: Linus Torvalds torvalds@linux-foundation.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- kernel/kthread.c | 35 ++++++++++++++++++++++++----------- 1 file changed, 24 insertions(+), 11 deletions(-)

diff --git a/kernel/kthread.c b/kernel/kthread.c index 415417b76bfb..36be4364b313 100644 --- a/kernel/kthread.c +++ b/kernel/kthread.c @@ -1071,8 +1071,11 @@ static void kthread_cancel_delayed_work_timer(struct kthread_work *work, }

/* - * This function removes the work from the worker queue. Also it makes sure - * that it won't get queued later via the delayed work's timer. + * This function removes the work from the worker queue. + * + * It is called under worker->lock. The caller must make sure that + * the timer used by delayed work is not running, e.g. by calling + * kthread_cancel_delayed_work_timer(). * * The work might still be in use when this function finishes. See the * current_work proceed by the worker. @@ -1080,13 +1083,8 @@ static void kthread_cancel_delayed_work_timer(struct kthread_work *work, * Return: %true if @work was pending and successfully canceled, * %false if @work was not pending */ -static bool __kthread_cancel_work(struct kthread_work *work, bool is_dwork, - unsigned long *flags) +static bool __kthread_cancel_work(struct kthread_work *work) { - /* Try to cancel the timer if exists. */ - if (is_dwork) - kthread_cancel_delayed_work_timer(work, flags); - /* * Try to remove the work from a worker list. It might either * be from worker->work_list or from worker->delayed_work_list. @@ -1139,11 +1137,23 @@ bool kthread_mod_delayed_work(struct kthread_worker *worker, /* Work must not be used with >1 worker, see kthread_queue_work() */ WARN_ON_ONCE(work->worker != worker);

- /* Do not fight with another command that is canceling this work. */ + /* + * Temporary cancel the work but do not fight with another command + * that is canceling the work as well. + * + * It is a bit tricky because of possible races with another + * mod_delayed_work() and cancel_delayed_work() callers. + * + * The timer must be canceled first because worker->lock is released + * when doing so. But the work can be removed from the queue (list) + * only when it can be queued again so that the return value can + * be used for reference counting. + */ + kthread_cancel_delayed_work_timer(work, &flags); if (work->canceling) goto out; + ret = __kthread_cancel_work(work);

- ret = __kthread_cancel_work(work, true, &flags); fast_queue: __kthread_queue_delayed_work(worker, dwork, delay); out: @@ -1165,7 +1175,10 @@ static bool __kthread_cancel_work_sync(struct kthread_work *work, bool is_dwork) /* Work must not be used with >1 worker, see kthread_queue_work(). */ WARN_ON_ONCE(work->worker != worker);

- ret = __kthread_cancel_work(work, is_dwork, &flags); + if (is_dwork) + kthread_cancel_delayed_work_timer(work, &flags); + + ret = __kthread_cancel_work(work);

if (worker->current_work != work) goto out_fast;

From: Thomas Gleixner tglx@linutronix.de

commit f9dfb5e390fab2df9f7944bb91e7705aba14cd26 upstream.

The XSAVE init code initializes all enabled and supported components with XRSTOR(S) to init state. Then it XSAVEs the state of the components back into init_fpstate which is used in several places to fill in the init state of components.

This works correctly with XSAVE, but not with XSAVEOPT and XSAVES because those use the init optimization and skip writing state of components which are in init state. So init_fpstate.xsave still contains all zeroes after this operation.

There are two ways to solve that:

1) Use XSAVE unconditionally, but that requires to reshuffle the buffer when XSAVES is enabled because XSAVES uses compacted format.

2) Save the components which are known to have a non-zero init state by other means.

Looking deeper, #2 is the right thing to do because all components the kernel supports have all-zeroes init state except the legacy features (FP, SSE). Those cannot be hard coded because the states are not identical on all CPUs, but they can be saved with FXSAVE which avoids all conditionals.

Use FXSAVE to save the legacy FP/SSE components in init_fpstate along with a BUILD_BUG_ON() which reminds developers to validate that a newly added component has all zeroes init state. As a bonus remove the now unused copy_xregs_to_kernel_booting() crutch.

The XSAVE and reshuffle method can still be implemented in the unlikely case that components are added which have a non-zero init state and no other means to save them. For now, FXSAVE is just simple and good enough.

[ bp: Fix a typo or two in the text. ]

Fixes: 6bad06b76892 ("x86, xsave: Use xsaveopt in context-switch path when supported") Signed-off-by: Thomas Gleixner tglx@linutronix.de Signed-off-by: Borislav Petkov bp@suse.de Reviewed-by: Borislav Petkov bp@suse.de Cc: stable@vger.kernel.org Link: https://lkml.kernel.org/r/20210618143444.587311343@linutronix.de Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- arch/x86/include/asm/fpu/internal.h | 30 ++++++--------------- arch/x86/kernel/fpu/xstate.c | 41 ++++++++++++++++++++++++++--- 2 files changed, 46 insertions(+), 25 deletions(-)

diff --git a/arch/x86/include/asm/fpu/internal.h b/arch/x86/include/asm/fpu/internal.h index fdee23ea4e17..16bf4d4a8159 100644 --- a/arch/x86/include/asm/fpu/internal.h +++ b/arch/x86/include/asm/fpu/internal.h @@ -204,6 +204,14 @@ static inline void copy_fxregs_to_kernel(struct fpu *fpu) asm volatile("fxsaveq %[fx]" : [fx] "=m" (fpu->state.fxsave)); }

+static inline void fxsave(struct fxregs_state *fx) +{ + if (IS_ENABLED(CONFIG_X86_32)) + asm volatile( "fxsave %[fx]" : [fx] "=m" (*fx)); + else + asm volatile("fxsaveq %[fx]" : [fx] "=m" (*fx)); +} + /* These macros all use (%edi)/(%rdi) as the single memory argument. */ #define XSAVE ".byte " REX_PREFIX "0x0f,0xae,0x27" #define XSAVEOPT ".byte " REX_PREFIX "0x0f,0xae,0x37" @@ -268,28 +276,6 @@ static inline void copy_fxregs_to_kernel(struct fpu *fpu) : "D" (st), "m" (*st), "a" (lmask), "d" (hmask) \ : "memory")

-/* - * This function is called only during boot time when x86 caps are not set - * up and alternative can not be used yet. - */ -static inline void copy_xregs_to_kernel_booting(struct xregs_state *xstate) -{ - u64 mask = xfeatures_mask_all; - u32 lmask = mask; - u32 hmask = mask >> 32; - int err; - - WARN_ON(system_state != SYSTEM_BOOTING); - - if (boot_cpu_has(X86_FEATURE_XSAVES)) - XSTATE_OP(XSAVES, xstate, lmask, hmask, err); - else - XSTATE_OP(XSAVE, xstate, lmask, hmask, err); - - /* We should never fault when copying to a kernel buffer: */ - WARN_ON_FPU(err); -} - /* * This function is called only during boot time when x86 caps are not set * up and alternative can not be used yet. diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c index 67f1a03b9b23..80dcf0417f30 100644 --- a/arch/x86/kernel/fpu/xstate.c +++ b/arch/x86/kernel/fpu/xstate.c @@ -440,6 +440,25 @@ static void __init print_xstate_offset_size(void) } }

+/* + * All supported features have either init state all zeros or are + * handled in setup_init_fpu() individually. This is an explicit + * feature list and does not use XFEATURE_MASK*SUPPORTED to catch + * newly added supported features at build time and make people + * actually look at the init state for the new feature. + */ +#define XFEATURES_INIT_FPSTATE_HANDLED \ + (XFEATURE_MASK_FP | \ + XFEATURE_MASK_SSE | \ + XFEATURE_MASK_YMM | \ + XFEATURE_MASK_OPMASK | \ + XFEATURE_MASK_ZMM_Hi256 | \ + XFEATURE_MASK_Hi16_ZMM | \ + XFEATURE_MASK_PKRU | \ + XFEATURE_MASK_BNDREGS | \ + XFEATURE_MASK_BNDCSR | \ + XFEATURE_MASK_PASID) + /* * setup the xstate image representing the init state */ @@ -447,6 +466,10 @@ static void __init setup_init_fpu_buf(void) { static int on_boot_cpu __initdata = 1;

+ BUILD_BUG_ON((XFEATURE_MASK_USER_SUPPORTED | + XFEATURE_MASK_SUPERVISOR_SUPPORTED) != + XFEATURES_INIT_FPSTATE_HANDLED); + WARN_ON_FPU(!on_boot_cpu); on_boot_cpu = 0;

@@ -466,10 +489,22 @@ static void __init setup_init_fpu_buf(void) copy_kernel_to_xregs_booting(&init_fpstate.xsave);

/* - * Dump the init state again. This is to identify the init state - * of any feature which is not represented by all zero's. + * All components are now in init state. Read the state back so + * that init_fpstate contains all non-zero init state. This only + * works with XSAVE, but not with XSAVEOPT and XSAVES because + * those use the init optimization which skips writing data for + * components in init state. + * + * XSAVE could be used, but that would require to reshuffle the + * data when XSAVES is available because XSAVES uses xstate + * compaction. But doing so is a pointless exercise because most + * components have an all zeros init state except for the legacy + * ones (FP and SSE). Those can be saved with FXSAVE into the + * legacy area. Adding new features requires to ensure that init + * state is all zeroes or if not to add the necessary handling + * here. */ - copy_xregs_to_kernel_booting(&init_fpstate.xsave); + fxsave(&init_fpstate.fxsave); }

static int xfeature_uncompacted_offset(int xfeature_nr)

From: Miaohe Lin linmiaohe@huawei.com

[ Upstream commit e0af87ff7afcde2660be44302836d2d5618185af ]

Remove extra semicolon without any functional change intended.

Link: https://lkml.kernel.org/r/20210127093425.39640-1-linmiaohe@huawei.com Signed-off-by: Miaohe Lin linmiaohe@huawei.com Signed-off-by: Andrew Morton akpm@linux-foundation.org Signed-off-by: Linus Torvalds torvalds@linux-foundation.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- mm/rmap.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/mm/rmap.c b/mm/rmap.c index 6657000b18d4..5858639443b4 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -1763,7 +1763,7 @@ bool try_to_unmap(struct page *page, enum ttu_flags flags) static int page_not_mapped(struct page *page) { return !page_mapped(page); -}; +}

/** * try_to_munlock - try to munlock a page

From: Xu Yu xuyu@linux.alibaba.com

commit ffc90cbb2970ab88b66ea51dd580469eede57b67 upstream.

We notice that hung task happens in a corner but practical scenario when CONFIG_PREEMPT_NONE is enabled, as follows.

Process 0 Process 1 Process 2..Inf split_huge_page_to_list unmap_page split_huge_pmd_address __migration_entry_wait(head) __migration_entry_wait(tail) remap_page (roll back) remove_migration_ptes rmap_walk_anon cond_resched

Where __migration_entry_wait(tail) is occurred in kernel space, e.g., copy_to_user in fstat, which will immediately fault again without rescheduling, and thus occupy the cpu fully.

When there are too many processes performing __migration_entry_wait on tail page, remap_page will never be done after cond_resched.

This makes __migration_entry_wait operate on the compound head page, thus waits for remap_page to complete, whether the THP is split successfully or roll back.

Note that put_and_wait_on_page_locked helps to drop the page reference acquired with get_page_unless_zero, as soon as the page is on the wait queue, before actually waiting. So splitting the THP is only prevented for a brief interval.

Link: https://lkml.kernel.org/r/b9836c1dd522e903891760af9f0c86a2cce987eb.162314400... Fixes: ba98828088ad ("thp: add option to setup migration entries during PMD split") Suggested-by: Hugh Dickins hughd@google.com Signed-off-by: Gang Deng gavin.dg@linux.alibaba.com Signed-off-by: Xu Yu xuyu@linux.alibaba.com Acked-by: Kirill A. Shutemov kirill.shutemov@linux.intel.com Acked-by: Hugh Dickins hughd@google.com Cc: Matthew Wilcox willy@infradead.org Cc: stable@vger.kernel.org Signed-off-by: Andrew Morton akpm@linux-foundation.org Signed-off-by: Linus Torvalds torvalds@linux-foundation.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- mm/migrate.c | 1 + 1 file changed, 1 insertion(+)

diff --git a/mm/migrate.c b/mm/migrate.c index 7982256a5125..278e6f3fa62c 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -326,6 +326,7 @@ void __migration_entry_wait(struct mm_struct *mm, pte_t *ptep, goto out;

page = migration_entry_to_page(entry); + page = compound_head(page);

/* * Once page cache replacement of page migration started, page_count

From: Hugh Dickins hughd@google.com

commit 3b77e8c8cde581dadab9a0f1543a347e24315f11 upstream.

Most callers of is_huge_zero_pmd() supply a pmd already verified present; but a few (notably zap_huge_pmd()) do not - it might be a pmd migration entry, in which the pfn is encoded differently from a present pmd: which might pass the is_huge_zero_pmd() test (though not on x86, since L1TF forced us to protect against that); or perhaps even crash in pmd_page() applied to a swap-like entry.

Make it safe by adding pmd_present() check into is_huge_zero_pmd() itself; and make it quicker by saving huge_zero_pfn, so that is_huge_zero_pmd() will not need to do that pmd_page() lookup each time.

__split_huge_pmd_locked() checked pmd_trans_huge() before: that worked, but is unnecessary now that is_huge_zero_pmd() checks present.

Link: https://lkml.kernel.org/r/21ea9ca-a1f5-8b90-5e88-95fb1c49bbfa@google.com Fixes: e71769ae5260 ("mm: enable thp migration for shmem thp") Signed-off-by: Hugh Dickins hughd@google.com Acked-by: Kirill A. Shutemov kirill.shutemov@linux.intel.com Reviewed-by: Yang Shi shy828301@gmail.com Cc: Alistair Popple apopple@nvidia.com Cc: Jan Kara jack@suse.cz Cc: Jue Wang juew@google.com Cc: "Matthew Wilcox (Oracle)" willy@infradead.org Cc: Miaohe Lin linmiaohe@huawei.com Cc: Minchan Kim minchan@kernel.org Cc: Naoya Horiguchi naoya.horiguchi@nec.com Cc: Oscar Salvador osalvador@suse.de Cc: Peter Xu peterx@redhat.com Cc: Ralph Campbell rcampbell@nvidia.com Cc: Shakeel Butt shakeelb@google.com Cc: Wang Yugui wangyugui@e16-tech.com Cc: Zi Yan ziy@nvidia.com Cc: stable@vger.kernel.org Signed-off-by: Andrew Morton akpm@linux-foundation.org Signed-off-by: Linus Torvalds torvalds@linux-foundation.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- include/linux/huge_mm.h | 8 +++++++- mm/huge_memory.c | 5 ++++- 2 files changed, 11 insertions(+), 2 deletions(-)

diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index 0365aa97f8e7..ff55be011739 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -297,6 +297,7 @@ struct page *follow_devmap_pud(struct vm_area_struct *vma, unsigned long addr, extern vm_fault_t do_huge_pmd_numa_page(struct vm_fault *vmf, pmd_t orig_pmd);

extern struct page *huge_zero_page; +extern unsigned long huge_zero_pfn;

static inline bool is_huge_zero_page(struct page *page) { @@ -305,7 +306,7 @@ static inline bool is_huge_zero_page(struct page *page)

static inline bool is_huge_zero_pmd(pmd_t pmd) { - return is_huge_zero_page(pmd_page(pmd)); + return READ_ONCE(huge_zero_pfn) == pmd_pfn(pmd) && pmd_present(pmd); }

static inline bool is_huge_zero_pud(pud_t pud) @@ -451,6 +452,11 @@ static inline bool is_huge_zero_page(struct page *page) return false; }

+static inline bool is_huge_zero_pmd(pmd_t pmd) +{ + return false; +} + static inline bool is_huge_zero_pud(pud_t pud) { return false; diff --git a/mm/huge_memory.c b/mm/huge_memory.c index be0ad6f7981e..7d8159be4736 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -61,6 +61,7 @@ static struct shrinker deferred_split_shrinker;

static atomic_t huge_zero_refcount; struct page *huge_zero_page __read_mostly; +unsigned long huge_zero_pfn __read_mostly = ~0UL;

bool transparent_hugepage_enabled(struct vm_area_struct *vma) { @@ -97,6 +98,7 @@ static struct page *get_huge_zero_page(void) __free_pages(zero_page, compound_order(zero_page)); goto retry; } + WRITE_ONCE(huge_zero_pfn, page_to_pfn(zero_page));

/* We take additional reference here. It will be put back by shrinker */ atomic_set(&huge_zero_refcount, 2); @@ -146,6 +148,7 @@ static unsigned long shrink_huge_zero_page_scan(struct shrinker *shrink, if (atomic_cmpxchg(&huge_zero_refcount, 1, 0) == 1) { struct page *zero_page = xchg(&huge_zero_page, NULL); BUG_ON(zero_page == NULL); + WRITE_ONCE(huge_zero_pfn, ~0UL); __free_pages(zero_page, compound_order(zero_page)); return HPAGE_PMD_NR; } @@ -2058,7 +2061,7 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd, return; }

- if (pmd_trans_huge(*pmd) && is_huge_zero_pmd(*pmd)) { + if (is_huge_zero_pmd(*pmd)) { /* * FIXME: Do we want to invalidate secondary mmu by calling * mmu_notifier_invalidate_range() see comments below inside

From: Hugh Dickins hughd@google.com

commit 494334e43c16d63b878536a26505397fce6ff3a2 upstream.

Running certain tests with a DEBUG_VM kernel would crash within hours, on the total_mapcount BUG() in split_huge_page_to_list(), while trying to free up some memory by punching a hole in a shmem huge page: split's try_to_unmap() was unable to find all the mappings of the page (which, on a !DEBUG_VM kernel, would then keep the huge page pinned in memory).

When that BUG() was changed to a WARN(), it would later crash on the VM_BUG_ON_VMA(end < vma->vm_start || start >= vma->vm_end, vma) in mm/internal.h:vma_address(), used by rmap_walk_file() for try_to_unmap().

vma_address() is usually correct, but there's a wraparound case when the vm_start address is unusually low, but vm_pgoff not so low: vma_address() chooses max(start, vma->vm_start), but that decides on the wrong address, because start has become almost ULONG_MAX.

Rewrite vma_address() to be more careful about vm_pgoff; move the VM_BUG_ON_VMA() out of it, returning -EFAULT for errors, so that it can be safely used from page_mapped_in_vma() and page_address_in_vma() too.

Add vma_address_end() to apply similar care to end address calculation, in page_vma_mapped_walk() and page_mkclean_one() and try_to_unmap_one(); though it raises a question of whether callers would do better to supply pvmw->end to page_vma_mapped_walk() - I chose not, for a smaller patch.

An irritation is that their apparent generality breaks down on KSM pages, which cannot be located by the page->index that page_to_pgoff() uses: as commit 4b0ece6fa016 ("mm: migrate: fix remove_migration_pte() for ksm pages") once discovered. I dithered over the best thing to do about that, and have ended up with a VM_BUG_ON_PAGE(PageKsm) in both vma_address() and vma_address_end(); though the only place in danger of using it on them was try_to_unmap_one().

Sidenote: vma_address() and vma_address_end() now use compound_nr() on a head page, instead of thp_size(): to make the right calculation on a hugetlbfs page, whether or not THPs are configured. try_to_unmap() is used on hugetlbfs pages, but perhaps the wrong calculation never mattered.

Link: https://lkml.kernel.org/r/caf1c1a3-7cfb-7f8f-1beb-ba816e932825@google.com Fixes: a8fa41ad2f6f ("mm, rmap: check all VMAs that PTE-mapped THP can be part of") Signed-off-by: Hugh Dickins hughd@google.com Acked-by: Kirill A. Shutemov kirill.shutemov@linux.intel.com Cc: Alistair Popple apopple@nvidia.com Cc: Jan Kara jack@suse.cz Cc: Jue Wang juew@google.com Cc: "Matthew Wilcox (Oracle)" willy@infradead.org Cc: Miaohe Lin linmiaohe@huawei.com Cc: Minchan Kim minchan@kernel.org Cc: Naoya Horiguchi naoya.horiguchi@nec.com Cc: Oscar Salvador osalvador@suse.de Cc: Peter Xu peterx@redhat.com Cc: Ralph Campbell rcampbell@nvidia.com Cc: Shakeel Butt shakeelb@google.com Cc: Wang Yugui wangyugui@e16-tech.com Cc: Yang Shi shy828301@gmail.com Cc: Zi Yan ziy@nvidia.com Cc: stable@vger.kernel.org Signed-off-by: Andrew Morton akpm@linux-foundation.org Signed-off-by: Linus Torvalds torvalds@linux-foundation.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- mm/internal.h | 53 ++++++++++++++++++++++++++++++++------------ mm/page_vma_mapped.c | 16 +++++-------- mm/rmap.c | 16 ++++++------- 3 files changed, 53 insertions(+), 32 deletions(-)

diff --git a/mm/internal.h b/mm/internal.h index c43ccdddb0f6..840b8a330b9a 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -379,27 +379,52 @@ static inline void mlock_migrate_page(struct page *newpage, struct page *page) extern pmd_t maybe_pmd_mkwrite(pmd_t pmd, struct vm_area_struct *vma);

/* - * At what user virtual address is page expected in @vma? + * At what user virtual address is page expected in vma? + * Returns -EFAULT if all of the page is outside the range of vma. + * If page is a compound head, the entire compound page is considered. */ static inline unsigned long -__vma_address(struct page *page, struct vm_area_struct *vma) +vma_address(struct page *page, struct vm_area_struct *vma) { - pgoff_t pgoff = page_to_pgoff(page); - return vma->vm_start + ((pgoff - vma->vm_pgoff) << PAGE_SHIFT); + pgoff_t pgoff; + unsigned long address; + + VM_BUG_ON_PAGE(PageKsm(page), page); /* KSM page->index unusable */ + pgoff = page_to_pgoff(page); + if (pgoff >= vma->vm_pgoff) { + address = vma->vm_start + + ((pgoff - vma->vm_pgoff) << PAGE_SHIFT); + /* Check for address beyond vma (or wrapped through 0?) */ + if (address < vma->vm_start || address >= vma->vm_end) + address = -EFAULT; + } else if (PageHead(page) && + pgoff + compound_nr(page) - 1 >= vma->vm_pgoff) { + /* Test above avoids possibility of wrap to 0 on 32-bit */ + address = vma->vm_start; + } else { + address = -EFAULT; + } + return address; }

+/* + * Then at what user virtual address will none of the page be found in vma? + * Assumes that vma_address() already returned a good starting address. + * If page is a compound head, the entire compound page is considered. + */ static inline unsigned long -vma_address(struct page *page, struct vm_area_struct *vma) +vma_address_end(struct page *page, struct vm_area_struct *vma) { - unsigned long start, end; - - start = __vma_address(page, vma); - end = start + thp_size(page) - PAGE_SIZE; - - /* page should be within @vma mapping range */ - VM_BUG_ON_VMA(end < vma->vm_start || start >= vma->vm_end, vma); - - return max(start, vma->vm_start); + pgoff_t pgoff; + unsigned long address; + + VM_BUG_ON_PAGE(PageKsm(page), page); /* KSM page->index unusable */ + pgoff = page_to_pgoff(page) + compound_nr(page); + address = vma->vm_start + ((pgoff - vma->vm_pgoff) << PAGE_SHIFT); + /* Check for address beyond vma (or wrapped through 0?) */ + if (address < vma->vm_start || address > vma->vm_end) + address = vma->vm_end; + return address; }

static inline struct file *maybe_unlock_mmap_for_io(struct vm_fault *vmf, diff --git a/mm/page_vma_mapped.c b/mm/page_vma_mapped.c index 3ba2bedc5794..a540af346f88 100644 --- a/mm/page_vma_mapped.c +++ b/mm/page_vma_mapped.c @@ -227,18 +227,18 @@ bool page_vma_mapped_walk(struct page_vma_mapped_walk *pvmw) if (!map_pte(pvmw)) goto next_pte; while (1) { + unsigned long end; + if (check_pte(pvmw)) return true; next_pte: /* Seek to next pte only makes sense for THP */ if (!PageTransHuge(pvmw->page) || PageHuge(pvmw->page)) return not_found(pvmw); + end = vma_address_end(pvmw->page, pvmw->vma); do { pvmw->address += PAGE_SIZE; - if (pvmw->address >= pvmw->vma->vm_end || - pvmw->address >= - __vma_address(pvmw->page, pvmw->vma) + - thp_size(pvmw->page)) + if (pvmw->address >= end) return not_found(pvmw); /* Did we cross page table boundary? */ if (pvmw->address % PMD_SIZE == 0) { @@ -276,14 +276,10 @@ int page_mapped_in_vma(struct page *page, struct vm_area_struct *vma) .vma = vma, .flags = PVMW_SYNC, }; - unsigned long start, end; - - start = __vma_address(page, vma); - end = start + thp_size(page) - PAGE_SIZE;

- if (unlikely(end < vma->vm_start || start >= vma->vm_end)) + pvmw.address = vma_address(page, vma); + if (pvmw.address == -EFAULT) return 0; - pvmw.address = max(start, vma->vm_start); if (!page_vma_mapped_walk(&pvmw)) return 0; page_vma_mapped_walk_done(&pvmw); diff --git a/mm/rmap.c b/mm/rmap.c index 2b721412bd7f..62cd108bb2bd 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -700,7 +700,6 @@ static bool should_defer_flush(struct mm_struct *mm, enum ttu_flags flags) */ unsigned long page_address_in_vma(struct page *page, struct vm_area_struct *vma) { - unsigned long address; if (PageAnon(page)) { struct anon_vma *page__anon_vma = page_anon_vma(page); /* @@ -715,10 +714,8 @@ unsigned long page_address_in_vma(struct page *page, struct vm_area_struct *vma) return -EFAULT; } else return -EFAULT; - address = __vma_address(page, vma); - if (unlikely(address < vma->vm_start || address >= vma->vm_end)) - return -EFAULT; - return address; + + return vma_address(page, vma); }

pmd_t *mm_find_pmd(struct mm_struct *mm, unsigned long address) @@ -912,7 +909,7 @@ static bool page_mkclean_one(struct page *page, struct vm_area_struct *vma, */ mmu_notifier_range_init(&range, MMU_NOTIFY_PROTECTION_PAGE, 0, vma, vma->vm_mm, address, - min(vma->vm_end, address + page_size(page))); + vma_address_end(page, vma)); mmu_notifier_invalidate_range_start(&range);

while (page_vma_mapped_walk(&pvmw)) { @@ -1415,9 +1412,10 @@ static bool try_to_unmap_one(struct page *page, struct vm_area_struct *vma, * Note that the page can not be free in this function as call of * try_to_unmap() must hold a reference on the page. */ + range.end = PageKsm(page) ? + address + PAGE_SIZE : vma_address_end(page, vma); mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma, vma->vm_mm, - address, - min(vma->vm_end, address + page_size(page))); + address, range.end); if (PageHuge(page)) { /* * If sharing is possible, start and end will be adjusted @@ -1869,6 +1867,7 @@ static void rmap_walk_anon(struct page *page, struct rmap_walk_control *rwc, struct vm_area_struct *vma = avc->vma; unsigned long address = vma_address(page, vma);

+ VM_BUG_ON_VMA(address == -EFAULT, vma); cond_resched();

if (rwc->invalid_vma && rwc->invalid_vma(vma, rwc->arg)) @@ -1923,6 +1922,7 @@ static void rmap_walk_file(struct page *page, struct rmap_walk_control *rwc, pgoff_start, pgoff_end) { unsigned long address = vma_address(page, vma);

+ VM_BUG_ON_VMA(address == -EFAULT, vma); cond_resched();

if (rwc->invalid_vma && rwc->invalid_vma(vma, rwc->arg))

From: Hugh Dickins hughd@google.com

[ Upstream commit 22061a1ffabdb9c3385de159c5db7aac3a4df1cc ]

There is a race between THP unmapping and truncation, when truncate sees pmd_none() and skips the entry, after munmap's zap_huge_pmd() cleared it, but before its page_remove_rmap() gets to decrement compound_mapcount: generating false "BUG: Bad page cache" reports that the page is still mapped when deleted. This commit fixes that, but not in the way I hoped.

The first attempt used try_to_unmap(page, TTU_SYNC|TTU_IGNORE_MLOCK) instead of unmap_mapping_range() in truncate_cleanup_page(): it has often been an annoyance that we usually call unmap_mapping_range() with no pages locked, but there apply it to a single locked page. try_to_unmap() looks more suitable for a single locked page.

However, try_to_unmap_one() contains a VM_BUG_ON_PAGE(!pvmw.pte,page): it is used to insert THP migration entries, but not used to unmap THPs. Copy zap_huge_pmd() and add THP handling now? Perhaps, but their TLB needs are different, I'm too ignorant of the DAX cases, and couldn't decide how far to go for anon+swap. Set that aside.

The second attempt took a different tack: make no change in truncate.c, but modify zap_huge_pmd() to insert an invalidated huge pmd instead of clearing it initially, then pmd_clear() between page_remove_rmap() and unlocking at the end. Nice. But powerpc blows that approach out of the water, with its serialize_against_pte_lookup(), and interesting pgtable usage. It would need serious help to get working on powerpc (with a minor optimization issue on s390 too). Set that aside.

Just add an "if (page_mapped(page)) synchronize_rcu();" or other such delay, after unmapping in truncate_cleanup_page()? Perhaps, but though that's likely to reduce or eliminate the number of incidents, it would give less assurance of whether we had identified the problem correctly.

This successful iteration introduces "unmap_mapping_page(page)" instead of try_to_unmap(), and goes the usual unmap_mapping_range_tree() route, with an addition to details. Then zap_pmd_range() watches for this case, and does spin_unlock(pmd_lock) if so - just like page_vma_mapped_walk() now does in the PVMW_SYNC case. Not pretty, but safe.

Note that unmap_mapping_page() is doing a VM_BUG_ON(!PageLocked) to assert its interface; but currently that's only used to make sure that page->mapping is stable, and zap_pmd_range() doesn't care if the page is locked or not. Along these lines, in invalidate_inode_pages2_range() move the initial unmap_mapping_range() out from under page lock, before then calling unmap_mapping_page() under page lock if still mapped.

Link: https://lkml.kernel.org/r/a2a4a148-cdd8-942c-4ef8-51b77f643dbe@google.com Fixes: fc127da085c2 ("truncate: handle file thp") Signed-off-by: Hugh Dickins hughd@google.com Acked-by: Kirill A. Shutemov kirill.shutemov@linux.intel.com Reviewed-by: Yang Shi shy828301@gmail.com Cc: Alistair Popple apopple@nvidia.com Cc: Jan Kara jack@suse.cz Cc: Jue Wang juew@google.com Cc: "Matthew Wilcox (Oracle)" willy@infradead.org Cc: Miaohe Lin linmiaohe@huawei.com Cc: Minchan Kim minchan@kernel.org Cc: Naoya Horiguchi naoya.horiguchi@nec.com Cc: Oscar Salvador osalvador@suse.de Cc: Peter Xu peterx@redhat.com Cc: Ralph Campbell rcampbell@nvidia.com Cc: Shakeel Butt shakeelb@google.com Cc: Wang Yugui wangyugui@e16-tech.com Cc: Zi Yan ziy@nvidia.com Cc: stable@vger.kernel.org Signed-off-by: Andrew Morton akpm@linux-foundation.org Signed-off-by: Linus Torvalds torvalds@linux-foundation.org

Note on stable backport: fixed up call to truncate_cleanup_page() in truncate_inode_pages_range().

Signed-off-by: Hugh Dickins hughd@google.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- include/linux/mm.h | 3 +++ mm/memory.c | 41 +++++++++++++++++++++++++++++++++++++++++ mm/truncate.c | 43 +++++++++++++++++++------------------------ 3 files changed, 63 insertions(+), 24 deletions(-)

diff --git a/include/linux/mm.h b/include/linux/mm.h index 5106db3ad1ce..289c26f055cd 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1648,6 +1648,7 @@ struct zap_details { struct address_space *check_mapping; /* Check page->mapping if set */ pgoff_t first_index; /* Lowest page->index to unmap */ pgoff_t last_index; /* Highest page->index to unmap */ + struct page *single_page; /* Locked page to be unmapped */ };

struct page *vm_normal_page(struct vm_area_struct *vma, unsigned long addr, @@ -1695,6 +1696,7 @@ extern vm_fault_t handle_mm_fault(struct vm_area_struct *vma, extern int fixup_user_fault(struct mm_struct *mm, unsigned long address, unsigned int fault_flags, bool *unlocked); +void unmap_mapping_page(struct page *page); void unmap_mapping_pages(struct address_space *mapping, pgoff_t start, pgoff_t nr, bool even_cows); void unmap_mapping_range(struct address_space *mapping, @@ -1715,6 +1717,7 @@ static inline int fixup_user_fault(struct mm_struct *mm, unsigned long address, BUG(); return -EFAULT; } +static inline void unmap_mapping_page(struct page *page) { } static inline void unmap_mapping_pages(struct address_space *mapping, pgoff_t start, pgoff_t nr, bool even_cows) { } static inline void unmap_mapping_range(struct address_space *mapping, diff --git a/mm/memory.c b/mm/memory.c index b70bd3ba3388..eb31b3e4ef93 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -1355,7 +1355,18 @@ static inline unsigned long zap_pmd_range(struct mmu_gather *tlb, else if (zap_huge_pmd(tlb, vma, pmd, addr)) goto next; /* fall through */ + } else if (details && details->single_page && + PageTransCompound(details->single_page) && + next - addr == HPAGE_PMD_SIZE && pmd_none(*pmd)) { + spinlock_t *ptl = pmd_lock(tlb->mm, pmd); + /* + * Take and drop THP pmd lock so that we cannot return + * prematurely, while zap_huge_pmd() has cleared *pmd, + * but not yet decremented compound_mapcount(). + */ + spin_unlock(ptl); } + /* * Here there can be other concurrent MADV_DONTNEED or * trans huge page faults running, and if the pmd is @@ -3185,6 +3196,36 @@ static inline void unmap_mapping_range_tree(struct rb_root_cached *root, } }

+/** + * unmap_mapping_page() - Unmap single page from processes. + * @page: The locked page to be unmapped. + * + * Unmap this page from any userspace process which still has it mmaped. + * Typically, for efficiency, the range of nearby pages has already been + * unmapped by unmap_mapping_pages() or unmap_mapping_range(). But once + * truncation or invalidation holds the lock on a page, it may find that + * the page has been remapped again: and then uses unmap_mapping_page() + * to unmap it finally. + */ +void unmap_mapping_page(struct page *page) +{ + struct address_space *mapping = page->mapping; + struct zap_details details = { }; + + VM_BUG_ON(!PageLocked(page)); + VM_BUG_ON(PageTail(page)); + + details.check_mapping = mapping; + details.first_index = page->index; + details.last_index = page->index + thp_nr_pages(page) - 1; + details.single_page = page; + + i_mmap_lock_write(mapping); + if (unlikely(!RB_EMPTY_ROOT(&mapping->i_mmap.rb_root))) + unmap_mapping_range_tree(&mapping->i_mmap, &details); + i_mmap_unlock_write(mapping); +} + /** * unmap_mapping_pages() - Unmap pages from processes. * @mapping: The address space containing pages to be unmapped. diff --git a/mm/truncate.c b/mm/truncate.c index 960edf5803ca..8914ca4ce4b1 100644 --- a/mm/truncate.c +++ b/mm/truncate.c @@ -173,13 +173,10 @@ void do_invalidatepage(struct page *page, unsigned int offset, * its lock, b) when a concurrent invalidate_mapping_pages got there first and * c) when tmpfs swizzles a page between a tmpfs inode and swapper_space. */ -static void -truncate_cleanup_page(struct address_space *mapping, struct page *page) +static void truncate_cleanup_page(struct page *page) { - if (page_mapped(page)) { - unsigned int nr = thp_nr_pages(page); - unmap_mapping_pages(mapping, page->index, nr, false); - } + if (page_mapped(page)) + unmap_mapping_page(page);

if (page_has_private(page)) do_invalidatepage(page, 0, thp_size(page)); @@ -224,7 +221,7 @@ int truncate_inode_page(struct address_space *mapping, struct page *page) if (page->mapping != mapping) return -EIO;

- truncate_cleanup_page(mapping, page); + truncate_cleanup_page(page); delete_from_page_cache(page); return 0; } @@ -362,7 +359,7 @@ void truncate_inode_pages_range(struct address_space *mapping, pagevec_add(&locked_pvec, page); } for (i = 0; i < pagevec_count(&locked_pvec); i++) - truncate_cleanup_page(mapping, locked_pvec.pages[i]); + truncate_cleanup_page(locked_pvec.pages[i]); delete_from_page_cache_batch(mapping, &locked_pvec); for (i = 0; i < pagevec_count(&locked_pvec); i++) unlock_page(locked_pvec.pages[i]); @@ -737,6 +734,16 @@ int invalidate_inode_pages2_range(struct address_space *mapping, continue; }

+ if (!did_range_unmap && page_mapped(page)) { + /* + * If page is mapped, before taking its lock, + * zap the rest of the file in one hit. + */ + unmap_mapping_pages(mapping, index, + (1 + end - index), false); + did_range_unmap = 1; + } + lock_page(page); WARN_ON(page_to_index(page) != index); if (page->mapping != mapping) { @@ -744,23 +751,11 @@ int invalidate_inode_pages2_range(struct address_space *mapping, continue; } wait_on_page_writeback(page); - if (page_mapped(page)) { - if (!did_range_unmap) { - /* - * Zap the rest of the file in one hit. - */ - unmap_mapping_pages(mapping, index, - (1 + end - index), false); - did_range_unmap = 1; - } else { - /* - * Just zap this page - */ - unmap_mapping_pages(mapping, index, - 1, false); - } - } + + if (page_mapped(page)) + unmap_mapping_page(page); BUG_ON(page_mapped(page)); + ret2 = do_launder_page(mapping, page); if (ret2 == 0) { if (!invalidate_complete_page2(mapping, page))

From: Hugh Dickins hughd@google.com

commit f003c03bd29e6f46fef1b9a8e8d636ac732286d5 upstream.

Patch series "mm: page_vma_mapped_walk() cleanup and THP fixes".

I've marked all of these for stable: many are merely cleanups, but I think they are much better before the main fix than after.

This patch (of 11):

page_vma_mapped_walk() cleanup: sometimes the local copy of pvwm->page was used, sometimes pvmw->page itself: use the local copy "page" throughout.

Link: https://lkml.kernel.org/r/589b358c-febc-c88e-d4c2-7834b37fa7bf@google.com Link: https://lkml.kernel.org/r/88e67645-f467-c279-bf5e-af4b5c6b13eb@google.com Signed-off-by: Hugh Dickins hughd@google.com Reviewed-by: Alistair Popple apopple@nvidia.com Acked-by: Kirill A. Shutemov kirill.shutemov@linux.intel.com Reviewed-by: Peter Xu peterx@redhat.com Cc: Yang Shi shy828301@gmail.com Cc: Wang Yugui wangyugui@e16-tech.com Cc: Matthew Wilcox willy@infradead.org Cc: Ralph Campbell rcampbell@nvidia.com Cc: Zi Yan ziy@nvidia.com Cc: Will Deacon will@kernel.org Cc: stable@vger.kernel.org Signed-off-by: Andrew Morton akpm@linux-foundation.org Signed-off-by: Linus Torvalds torvalds@linux-foundation.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- mm/page_vma_mapped.c | 9 ++++----- 1 file changed, 4 insertions(+), 5 deletions(-)

diff --git a/mm/page_vma_mapped.c b/mm/page_vma_mapped.c index a540af346f88..3cd41168e802 100644 --- a/mm/page_vma_mapped.c +++ b/mm/page_vma_mapped.c @@ -155,7 +155,7 @@ bool page_vma_mapped_walk(struct page_vma_mapped_walk *pvmw) if (pvmw->pte) goto next_pte;

- if (unlikely(PageHuge(pvmw->page))) { + if (unlikely(PageHuge(page))) { /* when pud is not present, pte will be NULL */ pvmw->pte = huge_pte_offset(mm, pvmw->address, page_size(page)); if (!pvmw->pte) @@ -216,8 +216,7 @@ bool page_vma_mapped_walk(struct page_vma_mapped_walk *pvmw) * cannot return prematurely, while zap_huge_pmd() has * cleared *pmd but not decremented compound_mapcount(). */ - if ((pvmw->flags & PVMW_SYNC) && - PageTransCompound(pvmw->page)) { + if ((pvmw->flags & PVMW_SYNC) && PageTransCompound(page)) { spinlock_t *ptl = pmd_lock(mm, pvmw->pmd);

spin_unlock(ptl); @@ -233,9 +232,9 @@ bool page_vma_mapped_walk(struct page_vma_mapped_walk *pvmw) return true; next_pte: /* Seek to next pte only makes sense for THP */ - if (!PageTransHuge(pvmw->page) || PageHuge(pvmw->page)) + if (!PageTransHuge(page) || PageHuge(page)) return not_found(pvmw); - end = vma_address_end(pvmw->page, pvmw->vma); + end = vma_address_end(page, pvmw->vma); do { pvmw->address += PAGE_SIZE; if (pvmw->address >= end)

From: Hugh Dickins hughd@google.com

commit 3306d3119ceacc43ea8b141a73e21fea68eec30c upstream.

page_vma_mapped_walk() cleanup: re-evaluate pmde after taking lock, then use it in subsequent tests, instead of repeatedly dereferencing pointer.

Link: https://lkml.kernel.org/r/53fbc9d-891e-46b2-cb4b-468c3b19238e@google.com Signed-off-by: Hugh Dickins hughd@google.com Acked-by: Kirill A. Shutemov kirill.shutemov@linux.intel.com Reviewed-by: Peter Xu peterx@redhat.com Cc: Alistair Popple apopple@nvidia.com Cc: Matthew Wilcox willy@infradead.org Cc: Ralph Campbell rcampbell@nvidia.com Cc: Wang Yugui wangyugui@e16-tech.com Cc: Will Deacon will@kernel.org Cc: Yang Shi shy828301@gmail.com Cc: Zi Yan ziy@nvidia.com Cc: stable@vger.kernel.org Signed-off-by: Andrew Morton akpm@linux-foundation.org Signed-off-by: Linus Torvalds torvalds@linux-foundation.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- mm/page_vma_mapped.c | 11 ++++++----- 1 file changed, 6 insertions(+), 5 deletions(-)

diff --git a/mm/page_vma_mapped.c b/mm/page_vma_mapped.c index 4f04472effb7..821147eca0e1 100644 --- a/mm/page_vma_mapped.c +++ b/mm/page_vma_mapped.c @@ -190,18 +190,19 @@ bool page_vma_mapped_walk(struct page_vma_mapped_walk *pvmw) pmde = READ_ONCE(*pvmw->pmd); if (pmd_trans_huge(pmde) || is_pmd_migration_entry(pmde)) { pvmw->ptl = pmd_lock(mm, pvmw->pmd); - if (likely(pmd_trans_huge(*pvmw->pmd))) { + pmde = *pvmw->pmd; + if (likely(pmd_trans_huge(pmde))) { if (pvmw->flags & PVMW_MIGRATION) return not_found(pvmw); - if (pmd_page(*pvmw->pmd) != page) + if (pmd_page(pmde) != page) return not_found(pvmw); return true; - } else if (!pmd_present(*pvmw->pmd)) { + } else if (!pmd_present(pmde)) { if (thp_migration_supported()) { if (!(pvmw->flags & PVMW_MIGRATION)) return not_found(pvmw); - if (is_migration_entry(pmd_to_swp_entry(*pvmw->pmd))) { - swp_entry_t entry = pmd_to_swp_entry(*pvmw->pmd); + if (is_migration_entry(pmd_to_swp_entry(pmde))) { + swp_entry_t entry = pmd_to_swp_entry(pmde);

if (migration_entry_to_page(entry) != page) return not_found(pvmw);

From: Hugh Dickins hughd@google.com

commit 448282487483d6fa5b2eeeafaa0acc681e544a9c upstream.

page_vma_mapped_walk() cleanup: adjust the test for crossing page table boundary - I believe pvmw->address is always page-aligned, but nothing else here assumed that; and remember to reset pvmw->pte to NULL after unmapping the page table, though I never saw any bug from that.

Link: https://lkml.kernel.org/r/799b3f9c-2a9e-dfef-5d89-26e9f76fd97@google.com Signed-off-by: Hugh Dickins hughd@google.com Acked-by: Kirill A. Shutemov kirill.shutemov@linux.intel.com Cc: Alistair Popple apopple@nvidia.com Cc: Matthew Wilcox willy@infradead.org Cc: Peter Xu peterx@redhat.com Cc: Ralph Campbell rcampbell@nvidia.com Cc: Wang Yugui wangyugui@e16-tech.com Cc: Will Deacon will@kernel.org Cc: Yang Shi shy828301@gmail.com Cc: Zi Yan ziy@nvidia.com Cc: stable@vger.kernel.org Signed-off-by: Andrew Morton akpm@linux-foundation.org Signed-off-by: Linus Torvalds torvalds@linux-foundation.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- mm/page_vma_mapped.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/mm/page_vma_mapped.c b/mm/page_vma_mapped.c index a9cd4e4b8d95..36b40fd23f94 100644 --- a/mm/page_vma_mapped.c +++ b/mm/page_vma_mapped.c @@ -243,16 +243,16 @@ bool page_vma_mapped_walk(struct page_vma_mapped_walk *pvmw) if (pvmw->address >= end) return not_found(pvmw); /* Did we cross page table boundary? */ - if (pvmw->address % PMD_SIZE == 0) { - pte_unmap(pvmw->pte); + if ((pvmw->address & (PMD_SIZE - PAGE_SIZE)) == 0) { if (pvmw->ptl) { spin_unlock(pvmw->ptl); pvmw->ptl = NULL; } + pte_unmap(pvmw->pte); + pvmw->pte = NULL; goto restart; - } else { - pvmw->pte++; } + pvmw->pte++; } while (pte_none(*pvmw->pte));

if (!pvmw->ptl) {

From: Hugh Dickins hughd@google.com

commit 474466301dfd8b39a10c01db740645f3f7ae9a28 upstream.

page_vma_mapped_walk() cleanup: add a label this_pte, matching next_pte, and use "goto this_pte", in place of the "while (1)" loop at the end.

Link: https://lkml.kernel.org/r/a52b234a-851-3616-2525-f42736e8934@google.com Signed-off-by: Hugh Dickins hughd@google.com Acked-by: Kirill A. Shutemov kirill.shutemov@linux.intel.com Cc: Alistair Popple apopple@nvidia.com Cc: Matthew Wilcox willy@infradead.org Cc: Peter Xu peterx@redhat.com Cc: Ralph Campbell rcampbell@nvidia.com Cc: Wang Yugui wangyugui@e16-tech.com Cc: Will Deacon will@kernel.org Cc: Yang Shi shy828301@gmail.com Cc: Zi Yan ziy@nvidia.com Cc: stable@vger.kernel.org Signed-off-by: Andrew Morton akpm@linux-foundation.org Signed-off-by: Linus Torvalds torvalds@linux-foundation.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- mm/page_vma_mapped.c | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-)

diff --git a/mm/page_vma_mapped.c b/mm/page_vma_mapped.c index 3c3a7cb2de85..cb43affe6c76 100644 --- a/mm/page_vma_mapped.c +++ b/mm/page_vma_mapped.c @@ -143,6 +143,7 @@ bool page_vma_mapped_walk(struct page_vma_mapped_walk *pvmw) { struct mm_struct *mm = pvmw->vma->vm_mm; struct page *page = pvmw->page; + unsigned long end; pgd_t *pgd; p4d_t *p4d; pud_t *pud; @@ -232,10 +233,7 @@ bool page_vma_mapped_walk(struct page_vma_mapped_walk *pvmw) } if (!map_pte(pvmw)) goto next_pte; - } - while (1) { - unsigned long end; - +this_pte: if (check_pte(pvmw)) return true; next_pte: @@ -264,6 +262,7 @@ bool page_vma_mapped_walk(struct page_vma_mapped_walk *pvmw) pvmw->ptl = pte_lockptr(mm, pvmw->pmd); spin_lock(pvmw->ptl); } + goto this_pte; } }

From: Hugh Dickins hughd@google.com

commit a9a7504d9beaf395481faa91e70e2fd08f7a3dde upstream.

Running certain tests with a DEBUG_VM kernel would crash within hours, on the total_mapcount BUG() in split_huge_page_to_list(), while trying to free up some memory by punching a hole in a shmem huge page: split's try_to_unmap() was unable to find all the mappings of the page (which, on a !DEBUG_VM kernel, would then keep the huge page pinned in memory).

Crash dumps showed two tail pages of a shmem huge page remained mapped by pte: ptes in a non-huge-aligned vma of a gVisor process, at the end of a long unmapped range; and no page table had yet been allocated for the head of the huge page to be mapped into.

Although designed to handle these odd misaligned huge-page-mapped-by-pte cases, page_vma_mapped_walk() falls short by returning false prematurely when !pmd_present or !pud_present or !p4d_present or !pgd_present: there are cases when a huge page may span the boundary, with ptes present in the next.

Restructure page_vma_mapped_walk() as a loop to continue in these cases, while keeping its layout much as before. Add a step_forward() helper to advance pvmw->address across those boundaries: originally I tried to use mm's standard p?d_addr_end() macros, but hit the same crash 512 times less often: because of the way redundant levels are folded together, but folded differently in different configurations, it was just too difficult to use them correctly; and step_forward() is simpler anyway.

Link: https://lkml.kernel.org/r/fedb8632-1798-de42-f39e-873551d5bc81@google.com Fixes: ace71a19cec5 ("mm: introduce page_vma_mapped_walk()") Signed-off-by: Hugh Dickins hughd@google.com Acked-by: Kirill A. Shutemov kirill.shutemov@linux.intel.com Cc: Alistair Popple apopple@nvidia.com Cc: Matthew Wilcox willy@infradead.org Cc: Peter Xu peterx@redhat.com Cc: Ralph Campbell rcampbell@nvidia.com Cc: Wang Yugui wangyugui@e16-tech.com Cc: Will Deacon will@kernel.org Cc: Yang Shi shy828301@gmail.com Cc: Zi Yan ziy@nvidia.com Cc: stable@vger.kernel.org Signed-off-by: Andrew Morton akpm@linux-foundation.org Signed-off-by: Linus Torvalds torvalds@linux-foundation.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- mm/page_vma_mapped.c | 34 +++++++++++++++++++++++++--------- 1 file changed, 25 insertions(+), 9 deletions(-)

diff --git a/mm/page_vma_mapped.c b/mm/page_vma_mapped.c index 5df88f3b454c..2ad76a3d871d 100644 --- a/mm/page_vma_mapped.c +++ b/mm/page_vma_mapped.c @@ -115,6 +115,13 @@ static bool check_pte(struct page_vma_mapped_walk *pvmw) return pfn_is_match(pvmw->page, pfn); }

+static void step_forward(struct page_vma_mapped_walk *pvmw, unsigned long size) +{ + pvmw->address = (pvmw->address + size) & ~(size - 1); + if (!pvmw->address) + pvmw->address = ULONG_MAX; +} + /** * page_vma_mapped_walk - check if @pvmw->page is mapped in @pvmw->vma at * @pvmw->address @@ -182,16 +189,22 @@ bool page_vma_mapped_walk(struct page_vma_mapped_walk *pvmw) if (pvmw->pte) goto next_pte; restart: - { + do { pgd = pgd_offset(mm, pvmw->address); - if (!pgd_present(*pgd)) - return false; + if (!pgd_present(*pgd)) { + step_forward(pvmw, PGDIR_SIZE); + continue; + } p4d = p4d_offset(pgd, pvmw->address); - if (!p4d_present(*p4d)) - return false; + if (!p4d_present(*p4d)) { + step_forward(pvmw, P4D_SIZE); + continue; + } pud = pud_offset(p4d, pvmw->address); - if (!pud_present(*pud)) - return false; + if (!pud_present(*pud)) { + step_forward(pvmw, PUD_SIZE); + continue; + }

pvmw->pmd = pmd_offset(pud, pvmw->address); /* @@ -238,7 +251,8 @@ bool page_vma_mapped_walk(struct page_vma_mapped_walk *pvmw)

spin_unlock(ptl); } - return false; + step_forward(pvmw, PMD_SIZE); + continue; } if (!map_pte(pvmw)) goto next_pte; @@ -268,7 +282,9 @@ bool page_vma_mapped_walk(struct page_vma_mapped_walk *pvmw) spin_lock(pvmw->ptl); } goto this_pte; - } + } while (pvmw->address < end); + + return false; }

/**

From: Hugh Dickins hughd@google.com

commit fe19bd3dae3d15d2fbfdb3de8839a6ea0fe94264 upstream.

If more than one futex is placed on a shmem huge page, it can happen that waking the second wakes the first instead, and leaves the second waiting: the key's shared.pgoff is wrong.

When 3.11 commit 13d60f4b6ab5 ("futex: Take hugepages into account when generating futex_key"), the only shared huge pages came from hugetlbfs, and the code added to deal with its exceptional page->index was put into hugetlb source. Then that was missed when 4.8 added shmem huge pages.

page_to_pgoff() is what others use for this nowadays: except that, as currently written, it gives the right answer on hugetlbfs head, but nonsense on hugetlbfs tails. Fix that by calling hugetlbfs-specific hugetlb_basepage_index() on PageHuge tails as well as on head.

Yes, it's unconventional to declare hugetlb_basepage_index() there in pagemap.h, rather than in hugetlb.h; but I do not expect anything but page_to_pgoff() ever to need it.

[akpm@linux-foundation.org: give hugetlb_basepage_index() prototype the correct scope]

Link: https://lkml.kernel.org/r/b17d946b-d09-326e-b42a-52884c36df32@google.com Fixes: 800d8c63b2e9 ("shmem: add huge pages support") Reported-by: Neel Natu neelnatu@google.com Signed-off-by: Hugh Dickins hughd@google.com Reviewed-by: Matthew Wilcox (Oracle) willy@infradead.org Acked-by: Thomas Gleixner tglx@linutronix.de Cc: "Kirill A. Shutemov" kirill.shutemov@linux.intel.com Cc: Zhang Yi wetpzy@gmail.com Cc: Mel Gorman mgorman@techsingularity.net Cc: Mike Kravetz mike.kravetz@oracle.com Cc: Ingo Molnar mingo@redhat.com Cc: Peter Zijlstra peterz@infradead.org Cc: Darren Hart dvhart@infradead.org Cc: Davidlohr Bueso dave@stgolabs.net Cc: stable@vger.kernel.org Signed-off-by: Andrew Morton akpm@linux-foundation.org Signed-off-by: Linus Torvalds torvalds@linux-foundation.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- include/linux/hugetlb.h | 16 ---------------- include/linux/pagemap.h | 13 +++++++------ kernel/futex.c | 3 +-- mm/hugetlb.c | 5 +---- 4 files changed, 9 insertions(+), 28 deletions(-)

diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index b5807f23caf8..5b68c9787f7c 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -628,17 +628,6 @@ static inline int hstate_index(struct hstate *h) return h - hstates; }

-pgoff_t __basepage_index(struct page *page); - -/* Return page->index in PAGE_SIZE units */ -static inline pgoff_t basepage_index(struct page *page) -{ - if (!PageCompound(page)) - return page->index; - - return __basepage_index(page); -} - extern int dissolve_free_huge_page(struct page *page); extern int dissolve_free_huge_pages(unsigned long start_pfn, unsigned long end_pfn); @@ -871,11 +860,6 @@ static inline int hstate_index(struct hstate *h) return 0; }

-static inline pgoff_t basepage_index(struct page *page) -{ - return page->index; -} - static inline int dissolve_free_huge_page(struct page *page) { return 0; diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index b032f094a782..fcb3f040102a 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -501,7 +501,7 @@ static inline struct page *read_mapping_page(struct address_space *mapping, }

/* - * Get index of the page with in radix-tree + * Get index of the page within radix-tree (but not for hugetlb pages). * (TODO: remove once hugetlb pages will have ->index in PAGE_SIZE) */ static inline pgoff_t page_to_index(struct page *page) @@ -520,15 +520,16 @@ static inline pgoff_t page_to_index(struct page *page) return pgoff; }

+extern pgoff_t hugetlb_basepage_index(struct page *page); + /* - * Get the offset in PAGE_SIZE. - * (TODO: hugepage should have ->index in PAGE_SIZE) + * Get the offset in PAGE_SIZE (even for hugetlb pages). + * (TODO: hugetlb pages should have ->index in PAGE_SIZE) */ static inline pgoff_t page_to_pgoff(struct page *page) { - if (unlikely(PageHeadHuge(page))) - return page->index << compound_order(page); - + if (unlikely(PageHuge(page))) + return hugetlb_basepage_index(page); return page_to_index(page); }

diff --git a/kernel/futex.c b/kernel/futex.c index 3136aba17772..98a6e1b80bfe 100644 --- a/kernel/futex.c +++ b/kernel/futex.c @@ -35,7 +35,6 @@ #include <linux/jhash.h> #include <linux/pagemap.h> #include <linux/syscalls.h> -#include <linux/hugetlb.h> #include <linux/freezer.h> #include <linux/memblock.h> #include <linux/fault-inject.h> @@ -652,7 +651,7 @@ static int get_futex_key(u32 __user *uaddr, bool fshared, union futex_key *key,

key->both.offset |= FUT_OFF_INODE; /* inode-based key */ key->shared.i_seq = get_inode_sequence_number(inode); - key->shared.pgoff = basepage_index(tail); + key->shared.pgoff = page_to_pgoff(tail); rcu_read_unlock(); }

diff --git a/mm/hugetlb.c b/mm/hugetlb.c index bc1006a32733..d4f89c2f9544 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -1635,15 +1635,12 @@ struct address_space *hugetlb_page_mapping_lock_write(struct page *hpage) return NULL; }

-pgoff_t __basepage_index(struct page *page) +pgoff_t hugetlb_basepage_index(struct page *page) { struct page *page_head = compound_head(page); pgoff_t index = page_index(page_head); unsigned long compound_idx;

- if (!PageHuge(page_head)) - return page_index(page); - if (compound_order(page_head) >= MAX_ORDER) compound_idx = page_to_pfn(page) - page_to_pfn(page_head); else

From: Bumyong Lee bumyong.lee@samsung.com

commit 5f89468e2f060031cd89fd4287298e0eaf246bf6 upstream.

in case of driver wants to sync part of ranges with offset, swiotlb_tbl_sync_single() copies from orig_addr base to tlb_addr with offset and ends up with data mismatch.

It was removed from "swiotlb: don't modify orig_addr in swiotlb_tbl_sync_single", but said logic has to be added back in.

From Linus's email:

"That commit which the removed the offset calculation entirely, because the old

(unsigned long)tlb_addr & (IO_TLB_SIZE - 1)

was wrong, but instead of removing it, I think it should have just fixed it to be

(tlb_addr - mem->start) & (IO_TLB_SIZE - 1);

instead. That way the slot offset always matches the slot index calculation."

(Unfortunatly that broke NVMe).

The use-case that drivers are hitting is as follow:

1. Get dma_addr_t from dma_map_single()

dma_addr_t tlb_addr = dma_map_single(dev, vaddr, vsize, DMA_TO_DEVICE);

|<---------------vsize------------->| +-----------------------------------+ | | original buffer +-----------------------------------+ vaddr

swiotlb_align_offset |<----->|<---------------vsize------------->| +-------+-----------------------------------+ | | | swiotlb buffer +-------+-----------------------------------+ tlb_addr

2. Do something 3. Sync dma_addr_t through dma_sync_single_for_device(..)

dma_sync_single_for_device(dev, tlb_addr + offset, size, DMA_TO_DEVICE);

Error case. Copy data to original buffer but it is from base addr (instead of base addr + offset) in original buffer:

swiotlb_align_offset |<----->|<- offset ->|<- size ->| +-------+-----------------------------------+ | | |##########| | swiotlb buffer +-------+-----------------------------------+ tlb_addr

|<- size ->| +-----------------------------------+ |##########| | original buffer +-----------------------------------+ vaddr

The fix is to copy the data to the original buffer and take into account the offset, like so:

swiotlb_align_offset |<----->|<- offset ->|<- size ->| +-------+-----------------------------------+ | | |##########| | swiotlb buffer +-------+-----------------------------------+ tlb_addr

|<- offset ->|<- size ->| +-----------------------------------+ | |##########| | original buffer +-----------------------------------+ vaddr

[One fix which was Linus's that made more sense to as it created a symmetry would break NVMe. The reason for that is the: unsigned int offset = (tlb_addr - mem->start) & (IO_TLB_SIZE - 1);

would come up with the proper offset, but it would lose the alignment (which this patch contains).]

Fixes: 16fc3cef33a0 ("swiotlb: don't modify orig_addr in swiotlb_tbl_sync_single") Signed-off-by: Bumyong Lee bumyong.lee@samsung.com Signed-off-by: Chanho Park chanho61.park@samsung.com Reviewed-by: Christoph Hellwig hch@lst.de Reported-by: Dominique MARTINET dominique.martinet@atmark-techno.com Reported-by: Horia Geantă horia.geanta@nxp.com Tested-by: Horia Geantă horia.geanta@nxp.com CC: stable@vger.kernel.org Signed-off-by: Konrad Rzeszutek Wilk konrad.wilk@oracle.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- kernel/dma/swiotlb.c | 3 +++ 1 file changed, 3 insertions(+)

diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c index 0f61b14b0099..0ed0e1f215c7 100644 --- a/kernel/dma/swiotlb.c +++ b/kernel/dma/swiotlb.c @@ -667,6 +667,9 @@ void swiotlb_tbl_sync_single(struct device *hwdev, phys_addr_t tlb_addr, if (orig_addr == INVALID_PHYS_ADDR) return;

+ orig_addr += (tlb_addr & (IO_TLB_SIZE - 1)) - + swiotlb_align_offset(hwdev, orig_addr); + switch (target) { case SYNC_FOR_CPU: if (likely(dir == DMA_FROM_DEVICE || dir == DMA_BIDIRECTIONAL))

From: Daniel Vetter daniel.vetter@ffwll.ch

commit f54b3ca7ea1e5e02f481cf4ca54568e57bd66086 upstream.

This reverts commit 1815d9c86e3090477fbde066ff314a7e9721ee0f.

Unfortunately this inverts the locking hierarchy, so back to the drawing board. Full lockdep splat below:

====================================================== WARNING: possible circular locking dependency detected 5.13.0-rc7-CI-CI_DRM_10254+ #1 Not tainted ------------------------------------------------------ kms_frontbuffer/1087 is trying to acquire lock: ffff88810dcd01a8 (&dev->master_mutex){+.+.}-{3:3}, at: drm_is_current_master+0x1b/0x40 but task is already holding lock: ffff88810dcd0488 (&dev->mode_config.mutex){+.+.}-{3:3}, at: drm_mode_getconnector+0x1c6/0x4a0 which lock already depends on the new lock. the existing dependency chain (in reverse order) is: -> #2 (&dev->mode_config.mutex){+.+.}-{3:3}: __mutex_lock+0xab/0x970 drm_client_modeset_probe+0x22e/0xca0 __drm_fb_helper_initial_config_and_unlock+0x42/0x540 intel_fbdev_initial_config+0xf/0x20 [i915] async_run_entry_fn+0x28/0x130 process_one_work+0x26d/0x5c0 worker_thread+0x37/0x380 kthread+0x144/0x170 ret_from_fork+0x1f/0x30 -> #1 (&client->modeset_mutex){+.+.}-{3:3}: __mutex_lock+0xab/0x970 drm_client_modeset_commit_locked+0x1c/0x180 drm_client_modeset_commit+0x1c/0x40 __drm_fb_helper_restore_fbdev_mode_unlocked+0x88/0xb0 drm_fb_helper_set_par+0x34/0x40 intel_fbdev_set_par+0x11/0x40 [i915] fbcon_init+0x270/0x4f0 visual_init+0xc6/0x130 do_bind_con_driver+0x1e5/0x2d0 do_take_over_console+0x10e/0x180 do_fbcon_takeover+0x53/0xb0 register_framebuffer+0x22d/0x310 __drm_fb_helper_initial_config_and_unlock+0x36c/0x540 intel_fbdev_initial_config+0xf/0x20 [i915] async_run_entry_fn+0x28/0x130 process_one_work+0x26d/0x5c0 worker_thread+0x37/0x380 kthread+0x144/0x170 ret_from_fork+0x1f/0x30 -> #0 (&dev->master_mutex){+.+.}-{3:3}: __lock_acquire+0x151e/0x2590 lock_acquire+0xd1/0x3d0 __mutex_lock+0xab/0x970 drm_is_current_master+0x1b/0x40 drm_mode_getconnector+0x37e/0x4a0 drm_ioctl_kernel+0xa8/0xf0 drm_ioctl+0x1e8/0x390 __x64_sys_ioctl+0x6a/0xa0 do_syscall_64+0x39/0xb0 entry_SYSCALL_64_after_hwframe+0x44/0xae other info that might help us debug this: Chain exists of: &dev->master_mutex --> &client->modeset_mutex --> &dev->mode_config.mutex Possible unsafe locking scenario: CPU0 CPU1 ---- ---- lock(&dev->mode_config.mutex); lock(&client->modeset_mutex); lock(&dev->mode_config.mutex); lock(&dev->master_mutex); --- drivers/gpu/drm/drm_auth.c | 51 ++++++++++++++------------------------ 1 file changed, 19 insertions(+), 32 deletions(-)

diff --git a/drivers/gpu/drm/drm_auth.c b/drivers/gpu/drm/drm_auth.c index 86d4b72e95cb..232abbba3686 100644 --- a/drivers/gpu/drm/drm_auth.c +++ b/drivers/gpu/drm/drm_auth.c @@ -61,35 +61,6 @@ * trusted clients. */

-static bool drm_is_current_master_locked(struct drm_file *fpriv) -{ - lockdep_assert_held_once(&fpriv->master->dev->master_mutex); - - return fpriv->is_master && drm_lease_owner(fpriv->master) == fpriv->minor->dev->master; -} - -/** - * drm_is_current_master - checks whether @priv is the current master - * @fpriv: DRM file private - * - * Checks whether @fpriv is current master on its device. This decides whether a - * client is allowed to run DRM_MASTER IOCTLs. - * - * Most of the modern IOCTL which require DRM_MASTER are for kernel modesetting - * - the current master is assumed to own the non-shareable display hardware. - */ -bool drm_is_current_master(struct drm_file *fpriv) -{ - bool ret; - - mutex_lock(&fpriv->master->dev->master_mutex); - ret = drm_is_current_master_locked(fpriv); - mutex_unlock(&fpriv->master->dev->master_mutex); - - return ret; -} -EXPORT_SYMBOL(drm_is_current_master); - int drm_getmagic(struct drm_device *dev, void *data, struct drm_file *file_priv) { struct drm_auth *auth = data; @@ -252,7 +223,7 @@ int drm_setmaster_ioctl(struct drm_device *dev, void *data, if (ret) goto out_unlock;

- if (drm_is_current_master_locked(file_priv)) + if (drm_is_current_master(file_priv)) goto out_unlock;

if (dev->master) { @@ -301,7 +272,7 @@ int drm_dropmaster_ioctl(struct drm_device *dev, void *data, if (ret) goto out_unlock;

- if (!drm_is_current_master_locked(file_priv)) { + if (!drm_is_current_master(file_priv)) { ret = -EINVAL; goto out_unlock; } @@ -350,7 +321,7 @@ void drm_master_release(struct drm_file *file_priv) if (file_priv->magic) idr_remove(&file_priv->master->magic_map, file_priv->magic);

- if (!drm_is_current_master_locked(file_priv)) + if (!drm_is_current_master(file_priv)) goto out;

drm_legacy_lock_master_cleanup(dev, master); @@ -371,6 +342,22 @@ void drm_master_release(struct drm_file *file_priv) mutex_unlock(&dev->master_mutex); }

+/** + * drm_is_current_master - checks whether @priv is the current master + * @fpriv: DRM file private + * + * Checks whether @fpriv is current master on its device. This decides whether a + * client is allowed to run DRM_MASTER IOCTLs. + * + * Most of the modern IOCTL which require DRM_MASTER are for kernel modesetting + * - the current master is assumed to own the non-shareable display hardware. + */ +bool drm_is_current_master(struct drm_file *fpriv) +{ + return fpriv->is_master && drm_lease_owner(fpriv->master) == fpriv->minor->dev->master; +} +EXPORT_SYMBOL(drm_is_current_master); + /** * drm_master_get - reference a master pointer * @master: &struct drm_master

From: Eric Snowberg eric.snowberg@oracle.com

[ Upstream commit 2565ca7f5ec1a98d51eea8860c4ab923f1ca2c85 ]

Move functionality within load_system_certificate_list to a common function, so it can be reused in the future.

DH Changes: - Added inclusion of common.h to common.c (Eric [1]).

Signed-off-by: Eric Snowberg eric.snowberg@oracle.com Acked-by: Jarkko Sakkinen jarkko@kernel.org Signed-off-by: David Howells dhowells@redhat.com cc: keyrings@vger.kernel.org Link: https://lore.kernel.org/r/EDA280F9-F72D-4181-93C7-CDBE95976FF7@oracle.com/ [1] Link: https://lore.kernel.org/r/20200930201508.35113-2-eric.snowberg@oracle.com/ Link: https://lore.kernel.org/r/20210122181054.32635-3-eric.snowberg@oracle.com/ # v5 Link: https://lore.kernel.org/r/161428672825.677100.7545516389752262918.stgit@wart... Link: https://lore.kernel.org/r/161433311696.902181.3599366124784670368.stgit@wart... # v2 Link: https://lore.kernel.org/r/161529605850.163428.7786675680201528556.stgit@wart... # v3 Signed-off-by: Sasha Levin sashal@kernel.org --- certs/Makefile | 2 +- certs/common.c | 57 ++++++++++++++++++++++++++++++++++++++++++ certs/common.h | 9 +++++++ certs/system_keyring.c | 49 +++--------------------------------- 4 files changed, 70 insertions(+), 47 deletions(-) create mode 100644 certs/common.c create mode 100644 certs/common.h

diff --git a/certs/Makefile b/certs/Makefile index f4c25b67aad9..f4b90bad8690 100644 --- a/certs/Makefile +++ b/certs/Makefile @@ -3,7 +3,7 @@ # Makefile for the linux kernel signature checking certificates. #

-obj-$(CONFIG_SYSTEM_TRUSTED_KEYRING) += system_keyring.o system_certificates.o +obj-$(CONFIG_SYSTEM_TRUSTED_KEYRING) += system_keyring.o system_certificates.o common.o obj-$(CONFIG_SYSTEM_BLACKLIST_KEYRING) += blacklist.o ifneq ($(CONFIG_SYSTEM_BLACKLIST_HASH_LIST),"") obj-$(CONFIG_SYSTEM_BLACKLIST_KEYRING) += blacklist_hashes.o diff --git a/certs/common.c b/certs/common.c new file mode 100644 index 000000000000..16a220887a53 --- /dev/null +++ b/certs/common.c @@ -0,0 +1,57 @@ +// SPDX-License-Identifier: GPL-2.0-or-later + +#include <linux/kernel.h> +#include <linux/key.h> +#include "common.h" + +int load_certificate_list(const u8 cert_list[], + const unsigned long list_size, + const struct key *keyring) +{ + key_ref_t key; + const u8 *p, *end; + size_t plen; + + p = cert_list; + end = p + list_size; + while (p < end) { + /* Each cert begins with an ASN.1 SEQUENCE tag and must be more + * than 256 bytes in size. + */ + if (end - p < 4) + goto dodgy_cert; + if (p[0] != 0x30 && + p[1] != 0x82) + goto dodgy_cert; + plen = (p[2] << 8) | p[3]; + plen += 4; + if (plen > end - p) + goto dodgy_cert; + + key = key_create_or_update(make_key_ref(keyring, 1), + "asymmetric", + NULL, + p, + plen, + ((KEY_POS_ALL & ~KEY_POS_SETATTR) | + KEY_USR_VIEW | KEY_USR_READ), + KEY_ALLOC_NOT_IN_QUOTA | + KEY_ALLOC_BUILT_IN | + KEY_ALLOC_BYPASS_RESTRICTION); + if (IS_ERR(key)) { + pr_err("Problem loading in-kernel X.509 certificate (%ld)\n", + PTR_ERR(key)); + } else { + pr_notice("Loaded X.509 cert '%s'\n", + key_ref_to_ptr(key)->description); + key_ref_put(key); + } + p += plen; + } + + return 0; + +dodgy_cert: + pr_err("Problem parsing in-kernel X.509 certificate list\n"); + return 0; +} diff --git a/certs/common.h b/certs/common.h new file mode 100644 index 000000000000..abdb5795936b --- /dev/null +++ b/certs/common.h @@ -0,0 +1,9 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ + +#ifndef _CERT_COMMON_H +#define _CERT_COMMON_H + +int load_certificate_list(const u8 cert_list[], const unsigned long list_size, + const struct key *keyring); + +#endif diff --git a/certs/system_keyring.c b/certs/system_keyring.c index cc165b359ea3..a44a8915c94c 100644 --- a/certs/system_keyring.c +++ b/certs/system_keyring.c @@ -15,6 +15,7 @@ #include <keys/asymmetric-type.h> #include <keys/system_keyring.h> #include <crypto/pkcs7.h> +#include "common.h"

static struct key *builtin_trusted_keys; #ifdef CONFIG_SECONDARY_TRUSTED_KEYRING @@ -136,54 +137,10 @@ device_initcall(system_trusted_keyring_init); */ static __init int load_system_certificate_list(void) { - key_ref_t key; - const u8 *p, *end; - size_t plen; - pr_notice("Loading compiled-in X.509 certificates\n");

- p = system_certificate_list; - end = p + system_certificate_list_size; - while (p < end) { - /* Each cert begins with an ASN.1 SEQUENCE tag and must be more - * than 256 bytes in size. - */ - if (end - p < 4) - goto dodgy_cert; - if (p[0] != 0x30 && - p[1] != 0x82) - goto dodgy_cert; - plen = (p[2] << 8) | p[3]; - plen += 4; - if (plen > end - p) - goto dodgy_cert; - - key = key_create_or_update(make_key_ref(builtin_trusted_keys, 1), - "asymmetric", - NULL, - p, - plen, - ((KEY_POS_ALL & ~KEY_POS_SETATTR) | - KEY_USR_VIEW | KEY_USR_READ), - KEY_ALLOC_NOT_IN_QUOTA | - KEY_ALLOC_BUILT_IN | - KEY_ALLOC_BYPASS_RESTRICTION); - if (IS_ERR(key)) { - pr_err("Problem loading in-kernel X.509 certificate (%ld)\n", - PTR_ERR(key)); - } else { - pr_notice("Loaded X.509 cert '%s'\n", - key_ref_to_ptr(key)->description); - key_ref_put(key); - } - p += plen; - } - - return 0; - -dodgy_cert: - pr_err("Problem parsing in-kernel X.509 certificate list\n"); - return 0; + return load_certificate_list(system_certificate_list, system_certificate_list_size, + builtin_trusted_keys); } late_initcall(load_system_certificate_list);

From: Eric Snowberg eric.snowberg@oracle.com

[ Upstream commit ebd9c2ae369a45bdd9f8615484db09be58fc242b ]

During boot the Secure Boot Forbidden Signature Database, dbx, is loaded into the blacklist keyring. Systems booted with shim have an equivalent Forbidden Signature Database called mokx. Currently mokx is only used by shim and grub, the contents are ignored by the kernel.

Add the ability to load mokx into the blacklist keyring during boot.

Signed-off-by: Eric Snowberg eric.snowberg@oracle.com Suggested-by: James Bottomley James.Bottomley@HansenPartnership.com Signed-off-by: David Howells dhowells@redhat.com Reviewed-by: Jarkko Sakkinen jarkko@kernel.org cc: keyrings@vger.kernel.org Link: https://lore.kernel.org/r/c33c8e3839a41e9654f41cc92c7231104931b1d7.camel@Han... Link: https://lore.kernel.org/r/20210122181054.32635-5-eric.snowberg@oracle.com/ # v5 Link: https://lore.kernel.org/r/161428674320.677100.12637282414018170743.stgit@war... Link: https://lore.kernel.org/r/161433313205.902181.2502803393898221637.stgit@wart... # v2 Link: https://lore.kernel.org/r/161529607422.163428.13530426573612578854.stgit@war... # v3 Signed-off-by: Sasha Levin sashal@kernel.org --- security/integrity/platform_certs/load_uefi.c | 20 +++++++++++++++++-- 1 file changed, 18 insertions(+), 2 deletions(-)

diff --git a/security/integrity/platform_certs/load_uefi.c b/security/integrity/platform_certs/load_uefi.c index ee4b4c666854..f290f78c3f30 100644 --- a/security/integrity/platform_certs/load_uefi.c +++ b/security/integrity/platform_certs/load_uefi.c @@ -132,8 +132,9 @@ static int __init load_moklist_certs(void) static int __init load_uefi_certs(void) { efi_guid_t secure_var = EFI_IMAGE_SECURITY_DATABASE_GUID; - void *db = NULL, *dbx = NULL; - unsigned long dbsize = 0, dbxsize = 0; + efi_guid_t mok_var = EFI_SHIM_LOCK_GUID; + void *db = NULL, *dbx = NULL, *mokx = NULL; + unsigned long dbsize = 0, dbxsize = 0, mokxsize = 0; efi_status_t status; int rc = 0;

@@ -175,6 +176,21 @@ static int __init load_uefi_certs(void) kfree(dbx); }

+ mokx = get_cert_list(L"MokListXRT", &mok_var, &mokxsize, &status); + if (!mokx) { + if (status == EFI_NOT_FOUND) + pr_debug("mokx variable wasn't found\n"); + else + pr_info("Couldn't get mokx list\n"); + } else { + rc = parse_efi_signature_list("UEFI:MokListXRT", + mokx, mokxsize, + get_handler_for_dbx); + if (rc) + pr_err("Couldn't parse mokx signatures %d\n", rc); + kfree(mokx); + } + /* Load the MokListRT certs */ rc = load_moklist_certs();