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 354da41f52de..06cdc22b5501 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c @@ -3593,12 +3593,8 @@ 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: Christian König christian.koenig@amd.com

commit 17b11f71795abdce46f62a808f906857e525cea8 upstream.

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

v2: grab the lock while waiting

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/20210622114506.106349-1-christ... Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/gpu/drm/nouveau/nouveau_prime.c | 17 ++++++++++++++++- 1 file changed, 16 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/nouveau/nouveau_prime.c b/drivers/gpu/drm/nouveau/nouveau_prime.c index bae6a3eccee0..f9ee562f72d3 100644 --- a/drivers/gpu/drm/nouveau/nouveau_prime.c +++ b/drivers/gpu/drm/nouveau/nouveau_prime.c @@ -112,7 +112,22 @@ int nouveau_gem_prime_pin(struct drm_gem_object *obj) if (ret) return -EINVAL;

- return 0; + ret = ttm_bo_reserve(&nvbo->bo, false, false, NULL); + if (ret) + goto error; + + if (nvbo->bo.moving) + ret = dma_fence_wait(nvbo->bo.moving, true); + + ttm_bo_unreserve(&nvbo->bo); + if (ret) + goto error; + + return ret; + +error: + nouveau_bo_unpin(nvbo); + return ret; }

void nouveau_gem_prime_unpin(struct drm_gem_object *obj)

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 924285d0bccd..43d6a6085d86 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: Sami Tolvanen samitolvanen@google.com

commit b744b43f79cc758127042e71f9ad7b1afda30f84 upstream.

Similarly to the CC_IS_CLANG config, add LD_IS_LLD to avoid GNU ld specific logic such as ld-version or ld-ifversion and gain the ability to select potential features that depend on the linker at configuration time such as LTO.

Signed-off-by: Sami Tolvanen samitolvanen@google.com Acked-by: Masahiro Yamada masahiroy@kernel.org [nc: Reword commit message] Signed-off-by: Nathan Chancellor natechancellor@gmail.com Tested-by: Sedat Dilek sedat.dilek@gmail.com Reviewed-by: Sedat Dilek sedat.dilek@gmail.com Signed-off-by: Thomas Bogendoerfer tsbogend@alpha.franken.de Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- init/Kconfig | 3 +++ 1 file changed, 3 insertions(+)

diff --git a/init/Kconfig b/init/Kconfig index 4f9fd78e2200..f23e90d9935f 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -20,6 +20,9 @@ config GCC_VERSION config CC_IS_CLANG def_bool $(success,$(CC) --version | head -n 1 | grep -q clang)

+config LD_IS_LLD + def_bool $(success,$(LD) -v | head -n 1 | grep -q LLD) + config CLANG_VERSION int default $(shell,$(srctree)/scripts/clang-version.sh $(CC))

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 5.4, 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: "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 34a06e89e176..3c3bc9f58498 100644 --- a/drivers/pci/pci.c +++ b/drivers/pci/pci.c @@ -1666,11 +1666,21 @@ 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: Johannes Berg johannes.berg@intel.com

[ Upstream commit 0ee4d55534f82a0624701d0bb9fc2304d4529086 ]

Syzbot reports that it's possible to hit this from userspace, by trying to add a station before any other connection setup has been done. Instead of trying to catch this in some other way simply remove the warning, that will appropriately reject the call from userspace.

Reported-by: syzbot+7716dbc401d9a437890d@syzkaller.appspotmail.com Link: https://lore.kernel.org/r/20210517164715.f537da276d17.Id05f40ec8761d6a8cc2df... Signed-off-by: Johannes Berg johannes.berg@intel.com Signed-off-by: Sasha Levin sashal@kernel.org --- net/mac80211/ieee80211_i.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h index a7933279a80b..e574fbf6745a 100644 --- a/net/mac80211/ieee80211_i.h +++ b/net/mac80211/ieee80211_i.h @@ -1420,7 +1420,7 @@ ieee80211_get_sband(struct ieee80211_sub_if_data *sdata) rcu_read_lock(); chanctx_conf = rcu_dereference(sdata->vif.chanctx_conf);

- if (WARN_ON_ONCE(!chanctx_conf)) { + if (!chanctx_conf) { rcu_read_unlock(); return NULL; }

From: Du Cheng ducheng2@gmail.com

[ Upstream commit a64b6a25dd9f984ed05fade603a00e2eae787d2f ]

If the userland switches back-and-forth between NL80211_IFTYPE_OCB and NL80211_IFTYPE_ADHOC via send_msg(NL80211_CMD_SET_INTERFACE), there is a chance where the cleanup cfg80211_leave_ocb() is not called. This leads to initialization of in-use memory (e.g. init u.ibss while in-use by u.ocb) due to a shared struct/union within ieee80211_sub_if_data:

struct ieee80211_sub_if_data { ... union { struct ieee80211_if_ap ap; struct ieee80211_if_vlan vlan; struct ieee80211_if_managed mgd; struct ieee80211_if_ibss ibss; // <- shares address struct ieee80211_if_mesh mesh; struct ieee80211_if_ocb ocb; // <- shares address struct ieee80211_if_mntr mntr; struct ieee80211_if_nan nan; } u; ... }

Therefore add handling of otype == NL80211_IFTYPE_OCB, during cfg80211_change_iface() to perform cleanup when leaving OCB mode.

link to syzkaller bug: https://syzkaller.appspot.com/bug?id=0612dbfa595bf4b9b680ff7b4948257b8e3732d...

Reported-by: syzbot+105896fac213f26056f9@syzkaller.appspotmail.com Signed-off-by: Du Cheng ducheng2@gmail.com Link: https://lore.kernel.org/r/20210428063941.105161-1-ducheng2@gmail.com Signed-off-by: Johannes Berg johannes.berg@intel.com Signed-off-by: Sasha Levin sashal@kernel.org --- net/wireless/util.c | 3 +++ 1 file changed, 3 insertions(+)

diff --git a/net/wireless/util.c b/net/wireless/util.c index 4eae6ad32851..f0247eab5bc9 100644 --- a/net/wireless/util.c +++ b/net/wireless/util.c @@ -1006,6 +1006,9 @@ int cfg80211_change_iface(struct cfg80211_registered_device *rdev, case NL80211_IFTYPE_MESH_POINT: /* mesh should be handled? */ break; + case NL80211_IFTYPE_OCB: + cfg80211_leave_ocb(rdev, dev); + break; default: break; }

From: Guillaume Ranquet granquet@baylibre.com

[ Upstream commit 0a2ff58f9f8f95526ecb0ccd7517fefceb96f661 ]

The desc_free handler assumed that the desc we want to free was always the current one associated with the channel.

This is seldom the case and this is causing use after free crashes in multiple places (tx/rx/terminate...).

BUG: KASAN: use-after-free in mtk_uart_apdma_rx_handler+0x120/0x304

Call trace: dump_backtrace+0x0/0x1b0 show_stack+0x24/0x34 dump_stack+0xe0/0x150 print_address_description+0x8c/0x55c __kasan_report+0x1b8/0x218 kasan_report+0x14/0x20 __asan_load4+0x98/0x9c mtk_uart_apdma_rx_handler+0x120/0x304 mtk_uart_apdma_irq_handler+0x50/0x80 __handle_irq_event_percpu+0xe0/0x210 handle_irq_event+0x8c/0x184 handle_fasteoi_irq+0x1d8/0x3ac __handle_domain_irq+0xb0/0x110 gic_handle_irq+0x50/0xb8 el0_irq_naked+0x60/0x6c

Allocated by task 3541: __kasan_kmalloc+0xf0/0x1b0 kasan_kmalloc+0x10/0x1c kmem_cache_alloc_trace+0x90/0x2dc mtk_uart_apdma_prep_slave_sg+0x6c/0x1a0 mtk8250_dma_rx_complete+0x220/0x2e4 vchan_complete+0x290/0x340 tasklet_action_common+0x220/0x298 tasklet_action+0x28/0x34 __do_softirq+0x158/0x35c

Freed by task 3541: __kasan_slab_free+0x154/0x224 kasan_slab_free+0x14/0x24 slab_free_freelist_hook+0xf8/0x15c kfree+0xb4/0x278 mtk_uart_apdma_desc_free+0x34/0x44 vchan_complete+0x1bc/0x340 tasklet_action_common+0x220/0x298 tasklet_action+0x28/0x34 __do_softirq+0x158/0x35c

The buggy address belongs to the object at ffff000063606800 which belongs to the cache kmalloc-256 of size 256 The buggy address is located 176 bytes inside of 256-byte region [ffff000063606800, ffff000063606900) The buggy address belongs to the page: page:fffffe00016d8180 refcount:1 mapcount:0 mapping:ffff00000302f600 index:0x0 compound_mapcount: 0 flags: 0xffff00000010200(slab|head) raw: 0ffff00000010200 dead000000000100 dead000000000122 ffff00000302f600 raw: 0000000000000000 0000000080100010 00000001ffffffff 0000000000000000 page dumped because: kasan: bad access detected

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

Link: https://lore.kernel.org/r/20210513192642.29446-2-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 | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-)

diff --git a/drivers/dma/mediatek/mtk-uart-apdma.c b/drivers/dma/mediatek/mtk-uart-apdma.c index f40051d6aecb..311d7c236d27 100644 --- a/drivers/dma/mediatek/mtk-uart-apdma.c +++ b/drivers/dma/mediatek/mtk-uart-apdma.c @@ -131,10 +131,7 @@ static unsigned int mtk_uart_apdma_read(struct mtk_chan *c, unsigned int reg)

static void mtk_uart_apdma_desc_free(struct virt_dma_desc *vd) { - struct dma_chan *chan = vd->tx.chan; - struct mtk_chan *c = to_mtk_uart_apdma_chan(chan); - - kfree(c->desc); + kfree(container_of(vd, struct mtk_uart_apdma_desc, vd)); }

static void mtk_uart_apdma_start_tx(struct mtk_chan *c)

From: Guillaume Ranquet granquet@baylibre.com

[ Upstream commit 9041575348b21ade1fb74d790f1aac85d68198c7 ]

As recommended by the doc in: Documentation/drivers-api/dmaengine/provider.rst

Use GFP_NOWAIT to not deplete the emergency pool.

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

Link: https://lore.kernel.org/r/20210513192642.29446-4-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 | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/dma/mediatek/mtk-uart-apdma.c b/drivers/dma/mediatek/mtk-uart-apdma.c index e420e9f72b3d..9c0ea13ca788 100644 --- a/drivers/dma/mediatek/mtk-uart-apdma.c +++ b/drivers/dma/mediatek/mtk-uart-apdma.c @@ -349,7 +349,7 @@ static struct dma_async_tx_descriptor *mtk_uart_apdma_prep_slave_sg return NULL;

/* Now allocate and setup the descriptor */ - d = kzalloc(sizeof(*d), GFP_ATOMIC); + d = kzalloc(sizeof(*d), GFP_NOWAIT); if (!d) return NULL;

From: Johannes Berg johannes.berg@intel.com

[ Upstream commit a9799541ca34652d9996e45f80e8e03144c12949 ]

These are not permitted by the spec, just drop them.

Link: https://lore.kernel.org/r/20210609161305.23def022b750.Ibd6dd3cdce573dae262fc... Signed-off-by: Johannes Berg johannes.berg@intel.com Signed-off-by: Sasha Levin sashal@kernel.org --- net/mac80211/rx.c | 9 +++------ 1 file changed, 3 insertions(+), 6 deletions(-)

diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index 3d7a5c5e586a..670d84e54db7 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -2200,17 +2200,15 @@ ieee80211_rx_h_defragment(struct ieee80211_rx_data *rx) sc = le16_to_cpu(hdr->seq_ctrl); frag = sc & IEEE80211_SCTL_FRAG;

- if (is_multicast_ether_addr(hdr->addr1)) { - I802_DEBUG_INC(rx->local->dot11MulticastReceivedFrameCount); - goto out_no_led; - } - if (rx->sta) cache = &rx->sta->frags;

if (likely(!ieee80211_has_morefrags(fc) && frag == 0)) goto out;

+ if (is_multicast_ether_addr(hdr->addr1)) + return RX_DROP_MONITOR; + I802_DEBUG_INC(rx->local->rx_handlers_fragments);

if (skb_linearize(rx->skb)) @@ -2336,7 +2334,6 @@ ieee80211_rx_h_defragment(struct ieee80211_rx_data *rx)

out: ieee80211_led_rx(rx->local); - out_no_led: if (rx->sta) rx->sta->rx_stats.packets++; return RX_CONTINUE;

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 df6fbefe44d4..1c3d5d3702a1 100644 --- a/net/ipv4/ping.c +++ b/net/ipv4/ping.c @@ -963,6 +963,7 @@ 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 */

@@ -977,14 +978,15 @@ 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: 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 31a559513362..87c0cdbf262a 100644 --- a/drivers/net/phy/dp83867.c +++ b/drivers/net/phy/dp83867.c @@ -468,16 +468,12 @@ 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: Eric Dumazet edumazet@google.com

[ Upstream commit c7d2ef5dd4b03ed0ee1d13bc0c55f9cf62d49bd6 ]

tpacket_snd(), packet_snd(), packet_getname() and packet_seq_show() can read po->num without holding a lock. This means other threads can change po->num at the same time.

KCSAN complained about this known fact [1] Add READ_ONCE()/WRITE_ONCE() to address the issue.

[1] BUG: KCSAN: data-race in packet_do_bind / packet_sendmsg

write to 0xffff888131a0dcc0 of 2 bytes by task 24714 on cpu 0: packet_do_bind+0x3ab/0x7e0 net/packet/af_packet.c:3181 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 0xffff888131a0dcc0 of 2 bytes by task 24719 on cpu 1: packet_snd net/packet/af_packet.c:2899 [inline] packet_sendmsg+0x317/0x3570 net/packet/af_packet.c:3040 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_sendmsg+0x1ed/0x270 net/socket.c:2433 __do_sys_sendmsg net/socket.c:2442 [inline] __se_sys_sendmsg net/socket.c:2440 [inline] __x64_sys_sendmsg+0x42/0x50 net/socket.c:2440 do_syscall_64+0x4a/0x90 arch/x86/entry/common.c:47 entry_SYSCALL_64_after_hwframe+0x44/0xae

value changed: 0x0000 -> 0x1200

Reported by Kernel Concurrency Sanitizer on: CPU: 1 PID: 24719 Comm: syz-executor.5 Not tainted 5.13.0-rc4-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, 8 insertions(+), 8 deletions(-)

diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index fbc2d4dfddf0..e582799d4e85 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -2656,7 +2656,7 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg) } if (likely(saddr == NULL)) { dev = packet_cached_dev_get(po); - proto = po->num; + proto = READ_ONCE(po->num); } else { err = -EINVAL; if (msg->msg_namelen < sizeof(struct sockaddr_ll)) @@ -2869,7 +2869,7 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len)

if (likely(saddr == NULL)) { dev = packet_cached_dev_get(po); - proto = po->num; + proto = READ_ONCE(po->num); } else { err = -EINVAL; if (msg->msg_namelen < sizeof(struct sockaddr_ll)) @@ -3141,7 +3141,7 @@ static int packet_do_bind(struct sock *sk, const char *name, int ifindex, /* prevents packet_notifier() from calling * register_prot_hook() */ - po->num = 0; + WRITE_ONCE(po->num, 0); __unregister_prot_hook(sk, true); rcu_read_lock(); dev_curr = po->prot_hook.dev; @@ -3151,7 +3151,7 @@ static int packet_do_bind(struct sock *sk, const char *name, int ifindex, }

BUG_ON(po->running); - po->num = proto; + WRITE_ONCE(po->num, proto); po->prot_hook.type = proto;

if (unlikely(unlisted)) { @@ -3496,7 +3496,7 @@ static int packet_getname(struct socket *sock, struct sockaddr *uaddr,

sll->sll_family = AF_PACKET; sll->sll_ifindex = po->ifindex; - sll->sll_protocol = po->num; + 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); @@ -4405,7 +4405,7 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u, was_running = po->running; num = po->num; if (was_running) { - po->num = 0; + WRITE_ONCE(po->num, 0); __unregister_prot_hook(sk, false); } spin_unlock(&po->bind_lock); @@ -4440,7 +4440,7 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u,

spin_lock(&po->bind_lock); if (was_running) { - po->num = num; + WRITE_ONCE(po->num, num); register_prot_hook(sk); } spin_unlock(&po->bind_lock); @@ -4613,7 +4613,7 @@ static int packet_seq_show(struct seq_file *seq, void *v) s, refcount_read(&s->sk_refcnt), s->sk_type, - ntohs(po->num), + ntohs(READ_ONCE(po->num)), po->ifindex, po->running, atomic_read(&s->sk_rmem_alloc),

From: Kees Cook keescook@chromium.org

[ Upstream commit 99718abdc00e86e4f286dd836408e2834886c16e ]

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/usb/r8152.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c index f6d643ecaf39..24d124633037 100644 --- a/drivers/net/usb/r8152.c +++ b/drivers/net/usb/r8152.c @@ -5065,7 +5065,7 @@ static void rtl8152_get_strings(struct net_device *dev, u32 stringset, u8 *data) { switch (stringset) { case ETH_SS_STATS: - memcpy(data, *rtl8152_gstrings, sizeof(rtl8152_gstrings)); + memcpy(data, rtl8152_gstrings, sizeof(rtl8152_gstrings)); break; } }

From: Kees Cook keescook@chromium.org

[ Upstream commit da5ac772cfe2a03058b0accfac03fad60c46c24d ]

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/realtek/r8169_main.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c index 8ff178fc2670..661202e85412 100644 --- a/drivers/net/ethernet/realtek/r8169_main.c +++ b/drivers/net/ethernet/realtek/r8169_main.c @@ -1801,7 +1801,7 @@ static void rtl8169_get_strings(struct net_device *dev, u32 stringset, u8 *data) { switch(stringset) { case ETH_SS_STATS: - memcpy(data, *rtl8169_gstrings, sizeof(rtl8169_gstrings)); + memcpy(data, rtl8169_gstrings, sizeof(rtl8169_gstrings)); break; } }

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 5c6a276f69ac..426b8098c50e 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_dcbx.c +++ b/drivers/net/ethernet/qlogic/qed/qed_dcbx.c @@ -1293,9 +1293,11 @@ 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: 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 0c67a5a94de3..76959a7d88c8 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 d3d9f7046913..9a7af7dda70d 100644 --- a/drivers/net/ethernet/xilinx/ll_temac_main.c +++ b/drivers/net/ethernet/xilinx/ll_temac_main.c @@ -939,6 +939,11 @@ 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: 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 e60be7bb55b0..c6c8a33c81d5 100644 --- a/fs/nilfs2/sysfs.c +++ b/fs/nilfs2/sysfs.c @@ -1054,6 +1054,7 @@ 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: Johan Hovold johan@kernel.org

commit 4ca070ef0dd885616ef294d269a9bf8e3b258e1a upstream.

The direction of the pipe argument must match the request-type direction bit or control requests may fail depending on the host-controller-driver implementation.

Control transfers without a data stage are treated as OUT requests by the USB stack and should be using usb_sndctrlpipe(). Failing to do so will now trigger a warning.

Fix the OSIFI2C_SET_BIT_RATE and OSIFI2C_STOP requests which erroneously used the osif_usb_read() helper and set the IN direction bit.

Reported-by: syzbot+9d7dadd15b8819d73f41@syzkaller.appspotmail.com Fixes: 83e53a8f120f ("i2c: Add bus driver for for OSIF USB i2c device.") Cc: stable@vger.kernel.org # 3.14 Signed-off-by: Johan Hovold johan@kernel.org Signed-off-by: Wolfram Sang wsa@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/i2c/busses/i2c-robotfuzz-osif.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/i2c/busses/i2c-robotfuzz-osif.c b/drivers/i2c/busses/i2c-robotfuzz-osif.c index a39f7d092797..66dfa211e736 100644 --- a/drivers/i2c/busses/i2c-robotfuzz-osif.c +++ b/drivers/i2c/busses/i2c-robotfuzz-osif.c @@ -83,7 +83,7 @@ static int osif_xfer(struct i2c_adapter *adapter, struct i2c_msg *msgs, } }

- ret = osif_usb_read(adapter, OSIFI2C_STOP, 0, 0, NULL, 0); + ret = osif_usb_write(adapter, OSIFI2C_STOP, 0, 0, NULL, 0); if (ret) { dev_err(&adapter->dev, "failure sending STOP\n"); return -EREMOTEIO; @@ -153,7 +153,7 @@ static int osif_probe(struct usb_interface *interface, * Set bus frequency. The frequency is: * 120,000,000 / ( 16 + 2 * div * 4^prescale). * Using dev = 52, prescale = 0 give 100KHz */ - ret = osif_usb_read(&priv->adapter, OSIFI2C_SET_BIT_RATE, 52, 0, + ret = osif_usb_write(&priv->adapter, OSIFI2C_SET_BIT_RATE, 52, 0, NULL, 0); if (ret) { dev_err(&interface->dev, "failure sending bit rate");

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 1086f21c641b..2eb8d7550324 100644 --- a/kernel/kthread.c +++ b/kernel/kthread.c @@ -1047,8 +1047,11 @@ 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. @@ -1056,13 +1059,8 @@ 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. @@ -1115,11 +1113,23 @@ 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: @@ -1141,7 +1151,10 @@ 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: 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 0c7b2a9400d4..ccc8a780e348 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -1737,7 +1737,7 @@ 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 00bbe57c1ce2..5092ef2aa8a1 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -321,6 +321,7 @@ 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 d8b86fd39113..d2dbe462efee 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -259,6 +259,7 @@ 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) { @@ -267,7 +268,7 @@ 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) @@ -398,6 +399,11 @@ 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 e74c5a505e2b..47d95048f31e 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; } @@ -2182,7 +2185,7 @@ 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

[ Upstream commit 494334e43c16d63b878536a26505397fce6ff3a2 ]

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

Note on stable backport: fixed up conflicts on intervening thp_size().

Signed-off-by: Hugh Dickins hughd@google.com 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 7dd7fbb577a9..cf382549dd70 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -339,27 +339,52 @@ 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 + PAGE_SIZE * (hpage_nr_pages(page) - 1); - - /* 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 5a2a371a2c98..d4e0440fef2a 100644 --- a/mm/page_vma_mapped.c +++ b/mm/page_vma_mapped.c @@ -223,18 +223,18 @@ 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) + - hpage_nr_pages(pvmw->page) * PAGE_SIZE) + if (pvmw->address >= end) return not_found(pvmw); /* Did we cross page table boundary? */ if (pvmw->address % PMD_SIZE == 0) { @@ -272,14 +272,10 @@ 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 + PAGE_SIZE * (hpage_nr_pages(page) - 1);

- 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 c61a6384d950..dfadc8364aa9 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -687,7 +687,6 @@ 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); /* @@ -702,10 +701,8 @@ 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) @@ -899,7 +896,7 @@ 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)) { @@ -1383,9 +1380,10 @@ 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 @@ -1843,6 +1841,7 @@ 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)) @@ -1897,6 +1896,7 @@ 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(). Use hpage_nr_pages() in unmap_mapping_page().

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 5565d11f9542..a7d626b4cad1 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1459,6 +1459,7 @@ 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, @@ -1505,6 +1506,7 @@ extern vm_fault_t handle_mm_fault(struct vm_area_struct *vma, extern int fixup_user_fault(struct task_struct *tsk, 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, @@ -1525,6 +1527,7 @@ static inline int fixup_user_fault(struct task_struct *tsk, 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 13a575ce2ec8..4bb7c6a364c8 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -1165,7 +1165,18 @@ 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 @@ -2769,6 +2780,36 @@ 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 + hpage_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 dd9ebc1da356..4d5add7d8ab6 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)) { - pgoff_t nr = PageTransHuge(page) ? HPAGE_PMD_NR : 1; - 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, PAGE_SIZE); @@ -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]); @@ -715,6 +712,16 @@ 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) { @@ -722,23 +729,11 @@ 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

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 d4e0440fef2a..2e448636b752 100644 --- a/mm/page_vma_mapped.c +++ b/mm/page_vma_mapped.c @@ -151,7 +151,7 @@ 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) @@ -212,8 +212,7 @@ 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); @@ -229,9 +228,9 @@ 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

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 ebf021d4e68b..76503169c1e2 100644 --- a/mm/page_vma_mapped.c +++ b/mm/page_vma_mapped.c @@ -186,18 +186,19 @@ 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

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 f9833b1e586a..bf17f93f162c 100644 --- a/mm/page_vma_mapped.c +++ b/mm/page_vma_mapped.c @@ -239,16 +239,16 @@ 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

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 b71058fcfde9..fc68ab2d3ea1 100644 --- a/mm/page_vma_mapped.c +++ b/mm/page_vma_mapped.c @@ -139,6 +139,7 @@ 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; @@ -228,10 +229,7 @@ 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: @@ -260,6 +258,7 @@ 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

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 93dd79ba9969..0e8f54683709 100644 --- a/mm/page_vma_mapped.c +++ b/mm/page_vma_mapped.c @@ -111,6 +111,13 @@ static bool check_pte(struct page_vma_mapped_walk *pvmw) return pfn_in_hpage(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 @@ -178,16 +185,22 @@ 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); /* @@ -234,7 +247,8 @@ 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; @@ -264,7 +278,9 @@ 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

[ Upstream commit fe19bd3dae3d15d2fbfdb3de8839a6ea0fe94264 ]

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

Note on stable backport: leave redundant #include <linux/hugetlb.h> in kernel/futex.c, to avoid conflict over the header files included.

Signed-off-by: Hugh Dickins hughd@google.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- include/linux/hugetlb.h | 16 ---------------- include/linux/pagemap.h | 13 +++++++------ kernel/futex.c | 2 +- mm/hugetlb.c | 5 +---- 4 files changed, 9 insertions(+), 27 deletions(-)

diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index fc717aeb2b3d..a0513c444446 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -469,17 +469,6 @@ 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); @@ -695,11 +684,6 @@ 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 37a4d9e32cd3..8543b1aaa529 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -397,7 +397,7 @@ 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) @@ -416,15 +416,16 @@ 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 375e7e98e301..f82879ae6577 100644 --- a/kernel/futex.c +++ b/kernel/futex.c @@ -737,7 +737,7 @@ get_futex_key(u32 __user *uaddr, int fshared, union futex_key *key, enum futex_a

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 fe15e7d8220a..95a32749af4d 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -1461,15 +1461,12 @@ int PageHeadHuge(struct page *page_head) return get_compound_page_dtor(page_head) == free_huge_page; }

-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: Nayna Jain nayna@linux.ibm.com

[ Upstream commit ad723674d6758478829ee766e3f1a2a24d56236f ]

The handlers to add the keys to the .platform keyring and blacklisted hashes to the .blacklist keyring is common for both the uefi and powerpc mechanisms of loading the keys/hashes from the firmware.

This patch moves the common code from load_uefi.c to keyring_handler.c

Signed-off-by: Nayna Jain nayna@linux.ibm.com Acked-by: Mimi Zohar zohar@linux.ibm.com Signed-off-by: Eric Richter erichte@linux.ibm.com Signed-off-by: Michael Ellerman mpe@ellerman.id.au Link: https://lore.kernel.org/r/1573441836-3632-4-git-send-email-nayna@linux.ibm.c... Signed-off-by: Sasha Levin sashal@kernel.org --- security/integrity/Makefile | 3 +- .../platform_certs/keyring_handler.c | 80 +++++++++++++++++++ .../platform_certs/keyring_handler.h | 32 ++++++++ security/integrity/platform_certs/load_uefi.c | 67 +--------------- 4 files changed, 115 insertions(+), 67 deletions(-) create mode 100644 security/integrity/platform_certs/keyring_handler.c create mode 100644 security/integrity/platform_certs/keyring_handler.h

diff --git a/security/integrity/Makefile b/security/integrity/Makefile index 35e6ca773734..351c9662994b 100644 --- a/security/integrity/Makefile +++ b/security/integrity/Makefile @@ -11,7 +11,8 @@ integrity-$(CONFIG_INTEGRITY_SIGNATURE) += digsig.o integrity-$(CONFIG_INTEGRITY_ASYMMETRIC_KEYS) += digsig_asymmetric.o integrity-$(CONFIG_INTEGRITY_PLATFORM_KEYRING) += platform_certs/platform_keyring.o integrity-$(CONFIG_LOAD_UEFI_KEYS) += platform_certs/efi_parser.o \ - platform_certs/load_uefi.o + platform_certs/load_uefi.o \ + platform_certs/keyring_handler.o integrity-$(CONFIG_LOAD_IPL_KEYS) += platform_certs/load_ipl_s390.o

obj-$(CONFIG_IMA) += ima/ diff --git a/security/integrity/platform_certs/keyring_handler.c b/security/integrity/platform_certs/keyring_handler.c new file mode 100644 index 000000000000..c5ba695c10e3 --- /dev/null +++ b/security/integrity/platform_certs/keyring_handler.c @@ -0,0 +1,80 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <linux/kernel.h> +#include <linux/sched.h> +#include <linux/cred.h> +#include <linux/err.h> +#include <linux/efi.h> +#include <linux/slab.h> +#include <keys/asymmetric-type.h> +#include <keys/system_keyring.h> +#include "../integrity.h" + +static efi_guid_t efi_cert_x509_guid __initdata = EFI_CERT_X509_GUID; +static efi_guid_t efi_cert_x509_sha256_guid __initdata = + EFI_CERT_X509_SHA256_GUID; +static efi_guid_t efi_cert_sha256_guid __initdata = EFI_CERT_SHA256_GUID; + +/* + * Blacklist a hash. + */ +static __init void uefi_blacklist_hash(const char *source, const void *data, + size_t len, const char *type, + size_t type_len) +{ + char *hash, *p; + + hash = kmalloc(type_len + len * 2 + 1, GFP_KERNEL); + if (!hash) + return; + p = memcpy(hash, type, type_len); + p += type_len; + bin2hex(p, data, len); + p += len * 2; + *p = 0; + + mark_hash_blacklisted(hash); + kfree(hash); +} + +/* + * Blacklist an X509 TBS hash. + */ +static __init void uefi_blacklist_x509_tbs(const char *source, + const void *data, size_t len) +{ + uefi_blacklist_hash(source, data, len, "tbs:", 4); +} + +/* + * Blacklist the hash of an executable. + */ +static __init void uefi_blacklist_binary(const char *source, + const void *data, size_t len) +{ + uefi_blacklist_hash(source, data, len, "bin:", 4); +} + +/* + * Return the appropriate handler for particular signature list types found in + * the UEFI db and MokListRT tables. + */ +__init efi_element_handler_t get_handler_for_db(const efi_guid_t *sig_type) +{ + if (efi_guidcmp(*sig_type, efi_cert_x509_guid) == 0) + return add_to_platform_keyring; + return 0; +} + +/* + * Return the appropriate handler for particular signature list types found in + * the UEFI dbx and MokListXRT tables. + */ +__init efi_element_handler_t get_handler_for_dbx(const efi_guid_t *sig_type) +{ + if (efi_guidcmp(*sig_type, efi_cert_x509_sha256_guid) == 0) + return uefi_blacklist_x509_tbs; + if (efi_guidcmp(*sig_type, efi_cert_sha256_guid) == 0) + return uefi_blacklist_binary; + return 0; +} diff --git a/security/integrity/platform_certs/keyring_handler.h b/security/integrity/platform_certs/keyring_handler.h new file mode 100644 index 000000000000..2462bfa08fe3 --- /dev/null +++ b/security/integrity/platform_certs/keyring_handler.h @@ -0,0 +1,32 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#ifndef PLATFORM_CERTS_INTERNAL_H +#define PLATFORM_CERTS_INTERNAL_H + +#include <linux/efi.h> + +void blacklist_hash(const char *source, const void *data, + size_t len, const char *type, + size_t type_len); + +/* + * Blacklist an X509 TBS hash. + */ +void blacklist_x509_tbs(const char *source, const void *data, size_t len); + +/* + * Blacklist the hash of an executable. + */ +void blacklist_binary(const char *source, const void *data, size_t len); + +/* + * Return the handler for particular signature list types found in the db. + */ +efi_element_handler_t get_handler_for_db(const efi_guid_t *sig_type); + +/* + * Return the handler for particular signature list types found in the dbx. + */ +efi_element_handler_t get_handler_for_dbx(const efi_guid_t *sig_type); + +#endif diff --git a/security/integrity/platform_certs/load_uefi.c b/security/integrity/platform_certs/load_uefi.c index 020fc7a11ef0..aa874d84e413 100644 --- a/security/integrity/platform_certs/load_uefi.c +++ b/security/integrity/platform_certs/load_uefi.c @@ -9,6 +9,7 @@ #include <keys/asymmetric-type.h> #include <keys/system_keyring.h> #include "../integrity.h" +#include "keyring_handler.h"

static efi_guid_t efi_cert_x509_guid __initdata = EFI_CERT_X509_GUID; static efi_guid_t efi_cert_x509_sha256_guid __initdata = @@ -69,72 +70,6 @@ static __init void *get_cert_list(efi_char16_t *name, efi_guid_t *guid, return db; }

-/* - * Blacklist a hash. - */ -static __init void uefi_blacklist_hash(const char *source, const void *data, - size_t len, const char *type, - size_t type_len) -{ - char *hash, *p; - - hash = kmalloc(type_len + len * 2 + 1, GFP_KERNEL); - if (!hash) - return; - p = memcpy(hash, type, type_len); - p += type_len; - bin2hex(p, data, len); - p += len * 2; - *p = 0; - - mark_hash_blacklisted(hash); - kfree(hash); -} - -/* - * Blacklist an X509 TBS hash. - */ -static __init void uefi_blacklist_x509_tbs(const char *source, - const void *data, size_t len) -{ - uefi_blacklist_hash(source, data, len, "tbs:", 4); -} - -/* - * Blacklist the hash of an executable. - */ -static __init void uefi_blacklist_binary(const char *source, - const void *data, size_t len) -{ - uefi_blacklist_hash(source, data, len, "bin:", 4); -} - -/* - * Return the appropriate handler for particular signature list types found in - * the UEFI db and MokListRT tables. - */ -static __init efi_element_handler_t get_handler_for_db(const efi_guid_t * - sig_type) -{ - if (efi_guidcmp(*sig_type, efi_cert_x509_guid) == 0) - return add_to_platform_keyring; - return 0; -} - -/* - * Return the appropriate handler for particular signature list types found in - * the UEFI dbx and MokListXRT tables. - */ -static __init efi_element_handler_t get_handler_for_dbx(const efi_guid_t * - sig_type) -{ - if (efi_guidcmp(*sig_type, efi_cert_x509_sha256_guid) == 0) - return uefi_blacklist_x509_tbs; - if (efi_guidcmp(*sig_type, efi_cert_sha256_guid) == 0) - return uefi_blacklist_binary; - return 0; -} - /* * Load the certs contained in the UEFI databases into the platform trusted * keyring and the UEFI blacklisted X.509 cert SHA256 hashes into the blacklist

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);