5.4.233-rc1 review

This is the start of the stable review cycle for the 5.4.233 release. There are 18 patches in this series, all will be posted as a response to this one. If anyone has any issues with these being applied, please let me know.

Responses should be made by Sat, 25 Feb 2023 13:04:16 +0000. Anything received after that time might be too late.

The whole patch series can be found in one patch at:

	https://www.kernel.org/pub/linux/kernel/v5.x/stable-review/patch-5.4.233-rc1.gz

or in the git tree and branch at:
git://git.kernel.org/pub/scm/linux/kernel/git/stable/linux-stable-rc.git linux-5.4.y
and the diffstat can be found below.

thanks,

greg k-h

-------------
Pseudo-Shortlog of commits:

Greg Kroah-Hartman <[email protected]>

    Linux 5.4.233-rc1

Vladimir Oltean <[email protected]>
Revert "net/sched: taprio: make qdisc_leaf() see the per-netdev-queue pfifo child qdiscs"

Kees Cook <[email protected]>
ext4: Fix function prototype mismatch for ext4_feat_ktype

Lukas Wunner <[email protected]>
wifi: mwifiex: Add missing compatible string for SD8787

Dave Hansen <[email protected]>
uaccess: Add speculation barrier to copy_from_user()

Pavel Skripkin <[email protected]>
mac80211: mesh: embedd mesh_paths and mpp_paths into ieee80211_if_mesh

Zheng Wang <[email protected]>
drm/i915/gvt: fix double free bug in split_2MB_gtt_entry

Thomas Gleixner <[email protected]>
alarmtimer: Prevent starvation by small intervals and SIG_IGN

Sean Anderson <[email protected]>
powerpc: dts: t208x: Disable 10G on MAC1 and MAC2

Marc Kleine-Budde <[email protected]>
can: kvaser_usb: hydra: help gcc-13 to figure out cmd_len

Jim Mattson <[email protected]>
KVM: VMX: Execute IBPB on emulated VM-exit when guest has IBRS

Sean Christopherson <[email protected]>
KVM: x86: Fail emulation during EMULTYPE_SKIP on any exception

Jason A. Donenfeld <[email protected]>
random: always mix cycle counter in add_latent_entropy()

Sean Anderson <[email protected]>
powerpc: dts: t208x: Mark MAC1 and MAC2 as 10G

Bitterblue Smith <[email protected]>
wifi: rtl8xxxu: gen2: Turn on the rate control

Lucas Stach <[email protected]>
drm/etnaviv: don't truncate physical page address

Marek Szyprowski <[email protected]>
drm: etnaviv: fix common struct sg_table related issues

Marek Szyprowski <[email protected]>
scatterlist: add generic wrappers for iterating over sgtable objects

Marek Szyprowski <[email protected]>
dma-mapping: add generic helpers for mapping sgtable objects

-------------

Diffstat:

 Makefile                                           |  4 +-
 arch/powerpc/boot/dts/fsl/qoriq-fman3-0-10g-2.dtsi | 44 +++++++++++
 arch/powerpc/boot/dts/fsl/qoriq-fman3-0-10g-3.dtsi | 44 +++++++++++
 arch/powerpc/boot/dts/fsl/t2081si-post.dtsi        | 20 ++++-
 arch/x86/kvm/vmx/nested.c                          | 11 +++
 arch/x86/kvm/vmx/vmx.c                             |  6 +-
 arch/x86/kvm/x86.c                                 |  4 +-
 drivers/gpu/drm/etnaviv/etnaviv_gem.c              | 12 ++-
 drivers/gpu/drm/etnaviv/etnaviv_mmu.c              | 19 ++---
 drivers/gpu/drm/i915/gvt/gtt.c                     | 17 ++++-
 drivers/net/can/usb/kvaser_usb/kvaser_usb_hydra.c  | 33 +++++---
 drivers/net/wireless/marvell/mwifiex/sdio.c        |  1 +
 .../net/wireless/realtek/rtl8xxxu/rtl8xxxu_core.c  |  8 +-
 fs/ext4/sysfs.c                                    |  7 +-
 include/linux/dma-mapping.h                        | 80 +++++++++++++++++++
 include/linux/nospec.h                             |  4 +
 include/linux/random.h                             |  6 +-
 include/linux/scatterlist.h                        | 50 +++++++++++-
 kernel/bpf/core.c                                  |  2 -
 kernel/time/alarmtimer.c                           | 33 +++++++-
 lib/usercopy.c                                     |  7 ++
 net/mac80211/ieee80211_i.h                         | 24 +++++-
 net/mac80211/mesh.h                                | 22 +-----
 net/mac80211/mesh_pathtbl.c                        | 89 ++++++++--------------
 net/sched/sch_taprio.c                             |  8 +-
 25 files changed, 410 insertions(+), 145 deletions(-)

From: Marek Szyprowski <[email protected]>

[ Upstream commit d9d200bcebc1f6e56f0178cbb8db9953e8cc9a11 ]

struct sg_table is a common structure used for describing a memory buffer. It consists of a scatterlist with memory pages and DMA addresses (sgl entry), as well as the number of scatterlist entries: CPU pages (orig_nents entry) and DMA mapped pages (nents entry).

It turned out that it was a common mistake to misuse nents and orig_nents entries, calling DMA-mapping functions with a wrong number of entries or ignoring the number of mapped entries returned by the dma_map_sg function.

To avoid such issues, let's introduce a common wrappers operating directly on the struct sg_table objects, which take care of the proper use of the nents and orig_nents entries.

Stable-dep-of: d37c120b7312 ("drm/etnaviv: don't truncate physical page address")

---
 include/linux/dma-mapping.h | 80 +++++++++++++++++++++++++++++++++++++
 1 file changed, 80 insertions(+)

index 4d450672b7d66..87cbae4b051f1 100644
@@ -612,6 +612,86 @@ static inline void dma_sync_single_range_for_device(struct device *dev,
 	return dma_sync_single_for_device(dev, addr + offset, size, dir);
 }
 
+/**
+ * dma_map_sgtable - Map the given buffer for DMA
+ * @dev:	The device for which to perform the DMA operation
+ * @sgt:	The sg_table object describing the buffer
+ * @dir:	DMA direction
+ * @attrs:	Optional DMA attributes for the map operation
+ *
+ * Maps a buffer described by a scatterlist stored in the given sg_table
+ * object for the @dir DMA operation by the @dev device. After success the
+ * ownership for the buffer is transferred to the DMA domain.  One has to
+ * call dma_sync_sgtable_for_cpu() or dma_unmap_sgtable() to move the
+ * ownership of the buffer back to the CPU domain before touching the
+ * buffer by the CPU.
+ *
+ * Returns 0 on success or -EINVAL on error during mapping the buffer.
+ */
+static inline int dma_map_sgtable(struct device *dev, struct sg_table *sgt,
+		enum dma_data_direction dir, unsigned long attrs)
+{
+	int nents;
+
+	nents = dma_map_sg_attrs(dev, sgt->sgl, sgt->orig_nents, dir, attrs);
+	if (nents <= 0)
+		return -EINVAL;
+	sgt->nents = nents;
+	return 0;
+}
+
+/**
+ * dma_unmap_sgtable - Unmap the given buffer for DMA
+ * @dev:	The device for which to perform the DMA operation
+ * @sgt:	The sg_table object describing the buffer
+ * @dir:	DMA direction
+ * @attrs:	Optional DMA attributes for the unmap operation
+ *
+ * Unmaps a buffer described by a scatterlist stored in the given sg_table
+ * object for the @dir DMA operation by the @dev device. After this function
+ * the ownership of the buffer is transferred back to the CPU domain.
+ */
+static inline void dma_unmap_sgtable(struct device *dev, struct sg_table *sgt,
+		enum dma_data_direction dir, unsigned long attrs)
+{
+	dma_unmap_sg_attrs(dev, sgt->sgl, sgt->orig_nents, dir, attrs);
+}
+
+/**
+ * dma_sync_sgtable_for_cpu - Synchronize the given buffer for CPU access
+ * @dev:	The device for which to perform the DMA operation
+ * @sgt:	The sg_table object describing the buffer
+ * @dir:	DMA direction
+ *
+ * Performs the needed cache synchronization and moves the ownership of the
+ * buffer back to the CPU domain, so it is safe to perform any access to it
+ * by the CPU. Before doing any further DMA operations, one has to transfer
+ * the ownership of the buffer back to the DMA domain by calling the
+ * dma_sync_sgtable_for_device().
+ */
+static inline void dma_sync_sgtable_for_cpu(struct device *dev,
+		struct sg_table *sgt, enum dma_data_direction dir)
+{
+	dma_sync_sg_for_cpu(dev, sgt->sgl, sgt->orig_nents, dir);
+}
+
+/**
+ * dma_sync_sgtable_for_device - Synchronize the given buffer for DMA
+ * @dev:	The device for which to perform the DMA operation
+ * @sgt:	The sg_table object describing the buffer
+ * @dir:	DMA direction
+ *
+ * Performs the needed cache synchronization and moves the ownership of the
+ * buffer back to the DMA domain, so it is safe to perform the DMA operation.
+ * Once finished, one has to call dma_sync_sgtable_for_cpu() or
+ * dma_unmap_sgtable().
+ */
+static inline void dma_sync_sgtable_for_device(struct device *dev,
+		struct sg_table *sgt, enum dma_data_direction dir)
+{
+	dma_sync_sg_for_device(dev, sgt->sgl, sgt->orig_nents, dir);
+}
+
 #define dma_map_single(d, a, s, r) dma_map_single_attrs(d, a, s, r, 0)
 #define dma_unmap_single(d, a, s, r) dma_unmap_single_attrs(d, a, s, r, 0)
 #define dma_map_sg(d, s, n, r) dma_map_sg_attrs(d, s, n, r, 0)

2.39.0

From: Marek Szyprowski <[email protected]>

[ Upstream commit 709d6d73c756107fb8a292a9f957d630097425fa ]

struct sg_table is a common structure used for describing a memory buffer. It consists of a scatterlist with memory pages and DMA addresses (sgl entry), as well as the number of scatterlist entries: CPU pages (orig_nents entry) and DMA mapped pages (nents entry).

It turned out that it was a common mistake to misuse nents and orig_nents entries, calling the scatterlist iterating functions with a wrong number of the entries.

To avoid such issues, lets introduce a common wrappers operating directly on the struct sg_table objects, which take care of the proper use of the nents and orig_nents entries.

While touching this, lets clarify some ambiguities in the comments for the existing for_each helpers.

Stable-dep-of: d37c120b7312 ("drm/etnaviv: don't truncate physical page address")

---
 include/linux/scatterlist.h | 50 ++++++++++++++++++++++++++++++++++---
 1 file changed, 47 insertions(+), 3 deletions(-)

index 6eec50fb36c80..4f922afb607ac 100644
@@ -151,6 +151,20 @@ static inline void sg_set_buf(struct scatterlist *sg, const void *buf,
 #define for_each_sg(sglist, sg, nr, __i)	\
 	for (__i = 0, sg = (sglist); __i < (nr); __i++, sg = sg_next(sg))
 
+/*
+ * Loop over each sg element in the given sg_table object.
+ */
+#define for_each_sgtable_sg(sgt, sg, i)		\
+	for_each_sg(sgt->sgl, sg, sgt->orig_nents, i)
+
+/*
+ * Loop over each sg element in the given *DMA mapped* sg_table object.
+ * Please use sg_dma_address(sg) and sg_dma_len(sg) to extract DMA addresses
+ * of the each element.
+ */
+#define for_each_sgtable_dma_sg(sgt, sg, i)	\
+	for_each_sg(sgt->sgl, sg, sgt->nents, i)
+
 /**
  * sg_chain - Chain two sglists together
  * @prv:	First scatterlist

@@ -401,9 +415,10 @@ sg_page_iter_dma_address(struct sg_dma_page_iter *dma_iter)
  * @sglist:	sglist to iterate over
  * @piter:	page iterator to hold current page, sg, sg_pgoffset
  * @nents:	maximum number of sg entries to iterate over
- * @pgoffset:	starting page offset
+ * @pgoffset:	starting page offset (in pages)
  *
  * Callers may use sg_page_iter_page() to get each page pointer.
+ * In each loop it operates on PAGE_SIZE unit.
  */
 #define for_each_sg_page(sglist, piter, nents, pgoffset)		   \
 	for (__sg_page_iter_start((piter), (sglist), (nents), (pgoffset)); \

@@ -412,18 +427,47 @@ sg_page_iter_dma_address(struct sg_dma_page_iter *dma_iter)
 /**
  * for_each_sg_dma_page - iterate over the pages of the given sg list
  * @sglist:	sglist to iterate over
- * @dma_iter:	page iterator to hold current page
+ * @dma_iter:	DMA page iterator to hold current page
  * @dma_nents:	maximum number of sg entries to iterate over, this is the value
  *              returned from dma_map_sg
- * @pgoffset:	starting page offset
+ * @pgoffset:	starting page offset (in pages)
  *
  * Callers may use sg_page_iter_dma_address() to get each page's DMA address.
+ * In each loop it operates on PAGE_SIZE unit.
  */
 #define for_each_sg_dma_page(sglist, dma_iter, dma_nents, pgoffset)            \
 	for (__sg_page_iter_start(&(dma_iter)->base, sglist, dma_nents,        \
 				  pgoffset);                                   \
 	     __sg_page_iter_dma_next(dma_iter);)
 
+/**
+ * for_each_sgtable_page - iterate over all pages in the sg_table object
+ * @sgt:	sg_table object to iterate over
+ * @piter:	page iterator to hold current page
+ * @pgoffset:	starting page offset (in pages)
+ *
+ * Iterates over the all memory pages in the buffer described by
+ * a scatterlist stored in the given sg_table object.
+ * See also for_each_sg_page(). In each loop it operates on PAGE_SIZE unit.
+ */
+#define for_each_sgtable_page(sgt, piter, pgoffset)	\
+	for_each_sg_page(sgt->sgl, piter, sgt->orig_nents, pgoffset)
+
+/**
+ * for_each_sgtable_dma_page - iterate over the DMA mapped sg_table object
+ * @sgt:	sg_table object to iterate over
+ * @dma_iter:	DMA page iterator to hold current page
+ * @pgoffset:	starting page offset (in pages)
+ *
+ * Iterates over the all DMA mapped pages in the buffer described by
+ * a scatterlist stored in the given sg_table object.
+ * See also for_each_sg_dma_page(). In each loop it operates on PAGE_SIZE
+ * unit.
+ */
+#define for_each_sgtable_dma_page(sgt, dma_iter, pgoffset)	\
+	for_each_sg_dma_page(sgt->sgl, dma_iter, sgt->nents, pgoffset)
+
+
 /*
  * Mapping sg iterator
  *

2.39.0

From: Marek Szyprowski <[email protected]>

[ Upstream commit 182354a526a0540c9197e03d9fce8a949ffd36ca ]

The Documentation/DMA-API-HOWTO.txt states that the dma_map_sg() function returns the number of the created entries in the DMA address space. However the subsequent calls to the dma_sync_sg_for_{device,cpu}() and dma_unmap_sg must be called with the original number of the entries passed to the dma_map_sg().

struct sg_table is a common structure used for describing a non-contiguous memory buffer, used commonly in the DRM and graphics subsystems. It consists of a scatterlist with memory pages and DMA addresses (sgl entry), as well as the number of scatterlist entries: CPU pages (orig_nents entry) and DMA mapped pages (nents entry).

It turned out that it was a common mistake to misuse nents and orig_nents entries, calling DMA-mapping functions with a wrong number of entries or ignoring the number of mapped entries returned by the dma_map_sg() function.

To avoid such issues, lets use a common dma-mapping wrappers operating directly on the struct sg_table objects and use scatterlist page iterators where possible. This, almost always, hides references to the nents and orig_nents entries, making the code robust, easier to follow and copy/paste safe.

Stable-dep-of: d37c120b7312 ("drm/etnaviv: don't truncate physical page address")

---
 drivers/gpu/drm/etnaviv/etnaviv_gem.c | 12 +++++-------
 drivers/gpu/drm/etnaviv/etnaviv_mmu.c | 15 ++++-----------
 2 files changed, 9 insertions(+), 18 deletions(-)

index 519948637186e..5107a0f5bc7fe 100644
@@ -27,7 +27,7 @@ static void etnaviv_gem_scatter_map(struct etnaviv_gem_object *etnaviv_obj)
 	 * because display controller, GPU, etc. are not coherent.
 	 */
 	if (etnaviv_obj->flags & ETNA_BO_CACHE_MASK)
-		dma_map_sg(dev->dev, sgt->sgl, sgt->nents, DMA_BIDIRECTIONAL);
+		dma_map_sgtable(dev->dev, sgt, DMA_BIDIRECTIONAL, 0);
 }
 
 static void etnaviv_gem_scatterlist_unmap(struct etnaviv_gem_object *etnaviv_obj)

@@ -51,7 +51,7 @@ static void etnaviv_gem_scatterlist_unmap(struct etnaviv_gem_object *etnaviv_obj
 	 * discard those writes.
 	 */
 	if (etnaviv_obj->flags & ETNA_BO_CACHE_MASK)
-		dma_unmap_sg(dev->dev, sgt->sgl, sgt->nents, DMA_BIDIRECTIONAL);
+		dma_unmap_sgtable(dev->dev, sgt, DMA_BIDIRECTIONAL, 0);
 }
 
 /* called with etnaviv_obj->lock held */

@@ -403,9 +403,8 @@ int etnaviv_gem_cpu_prep(struct drm_gem_object *obj, u32 op,
 	}
 
 	if (etnaviv_obj->flags & ETNA_BO_CACHED) {
-		dma_sync_sg_for_cpu(dev->dev, etnaviv_obj->sgt->sgl,
-				    etnaviv_obj->sgt->nents,
-				    etnaviv_op_to_dma_dir(op));
+		dma_sync_sgtable_for_cpu(dev->dev, etnaviv_obj->sgt,
+					 etnaviv_op_to_dma_dir(op));
 		etnaviv_obj->last_cpu_prep_op = op;
 	}
 

@@ -420,8 +419,7 @@ int etnaviv_gem_cpu_fini(struct drm_gem_object *obj)
 	if (etnaviv_obj->flags & ETNA_BO_CACHED) {
 		/* fini without a prep is almost certainly a userspace error */
 		WARN_ON(etnaviv_obj->last_cpu_prep_op == 0);
-		dma_sync_sg_for_device(dev->dev, etnaviv_obj->sgt->sgl,
-			etnaviv_obj->sgt->nents,
+		dma_sync_sgtable_for_device(dev->dev, etnaviv_obj->sgt,
 			etnaviv_op_to_dma_dir(etnaviv_obj->last_cpu_prep_op));
 		etnaviv_obj->last_cpu_prep_op = 0;
 	}

index 790cbb20aaeba..9ba2fe48228f1 100644
@@ -73,13 +73,13 @@ static int etnaviv_iommu_map(struct etnaviv_iommu_context *context, u32 iova,
 			     struct sg_table *sgt, unsigned len, int prot)
 {	struct scatterlist *sg;
 	unsigned int da = iova;
-	unsigned int i, j;
+	unsigned int i;
 	int ret;
 
 	if (!context || !sgt)
 		return -EINVAL;
 
-	for_each_sg(sgt->sgl, sg, sgt->nents, i) {
+	for_each_sgtable_dma_sg(sgt, sg, i) {
 		u32 pa = sg_dma_address(sg) - sg->offset;
 		size_t bytes = sg_dma_len(sg) + sg->offset;
 

@@ -95,14 +95,7 @@ static int etnaviv_iommu_map(struct etnaviv_iommu_context *context, u32 iova,
 	return 0;
 
 fail:
-	da = iova;
-
-	for_each_sg(sgt->sgl, sg, i, j) {
-		size_t bytes = sg_dma_len(sg) + sg->offset;
-
-		etnaviv_context_unmap(context, da, bytes);
-		da += bytes;
-	}
+	etnaviv_context_unmap(context, iova, da - iova);
 	return ret;
 }
 

@@ -113,7 +106,7 @@ static void etnaviv_iommu_unmap(struct etnaviv_iommu_context *context, u32 iova,
 	unsigned int da = iova;
 	int i;
 
-	for_each_sg(sgt->sgl, sg, sgt->nents, i) {
+	for_each_sgtable_dma_sg(sgt, sg, i) {
 		size_t bytes = sg_dma_len(sg) + sg->offset;
 
 		etnaviv_context_unmap(context, da, bytes);

2.39.0

From: Lucas Stach <[email protected]>

[ Upstream commit d37c120b73128690434cc093952439eef9d56af1 ]

While the interface for the MMU mapping takes phys_addr_t to hold a full 64bit address when necessary and MMUv2 is able to map physical addresses with up to 40bit, etnaviv_iommu_map() truncates the address to 32bits. Fix this by using the correct type.

---
 drivers/gpu/drm/etnaviv/etnaviv_mmu.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

index 9ba2fe48228f1..44fbc0a123bf3 100644
@@ -80,10 +80,10 @@ static int etnaviv_iommu_map(struct etnaviv_iommu_context *context, u32 iova,
 		return -EINVAL;
 
 	for_each_sgtable_dma_sg(sgt, sg, i) {
-		u32 pa = sg_dma_address(sg) - sg->offset;
+		phys_addr_t pa = sg_dma_address(sg) - sg->offset;
 		size_t bytes = sg_dma_len(sg) + sg->offset;
 
-		VERB("map[%d]: %08x %08x(%zx)", i, iova, pa, bytes);
+		VERB("map[%d]: %08x %pap(%zx)", i, iova, &pa, bytes);
 
 		ret = etnaviv_context_map(context, da, pa, bytes, prot);
 		if (ret)

2.39.0

From: Bitterblue Smith <[email protected]>

[ Upstream commit 791082ec0ab843e0be07c8ce3678e4c2afd2e33d ]

Re-enable the function rtl8xxxu_gen2_report_connect.

It informs the firmware when connecting to a network. This makes the firmware enable the rate control, which makes the upload faster.

It also informs the firmware when disconnecting from a network. In the past this made reconnecting impossible because it was sending the auth on queue 0x7 (TXDESC_QUEUE_VO) instead of queue 0x12 (TXDESC_QUEUE_MGNT):

wlp0s20f0u3: send auth to 90:55:de:__:__:__ (try 1/3)
wlp0s20f0u3: send auth to 90:55:de:__:__:__ (try 2/3)
wlp0s20f0u3: send auth to 90:55:de:__:__:__ (try 3/3)
wlp0s20f0u3: authentication with 90:55:de:__:__:__ timed out

Probably the firmware disables the unnecessary TX queues when it knows it's disconnected.

However, this was fixed in commit edd5747aa12e ("wifi: rtl8xxxu: Fix skb misuse in TX queue selection").

---
 drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_core.c | 8 ++------
 1 file changed, 2 insertions(+), 6 deletions(-)

index 4a81e810a0ce3..0bc747489c55a 100644
@@ -4372,12 +4372,9 @@ void rtl8xxxu_gen1_report_connect(struct rtl8xxxu_priv *priv,
 void rtl8xxxu_gen2_report_connect(struct rtl8xxxu_priv *priv,
 				  u8 macid, bool connect)
 {
-#ifdef RTL8XXXU_GEN2_REPORT_CONNECT
 	/*
-	 * Barry Day reports this causes issues with 8192eu and 8723bu
-	 * devices reconnecting. The reason for this is unclear, but
-	 * until it is better understood, leave the code in place but
-	 * disabled, so it is not lost.
+	 * The firmware turns on the rate control when it knows it's
+	 * connected to a network.
 	 */
 	struct h2c_cmd h2c;
 

@@ -4390,7 +4387,6 @@ void rtl8xxxu_gen2_report_connect(struct rtl8xxxu_priv *priv,
 		h2c.media_status_rpt.parm &= ~BIT(0);
 
 	rtl8xxxu_gen2_h2c_cmd(priv, &h2c, sizeof(h2c.media_status_rpt));
-#endif
 }
 
 void rtl8xxxu_gen1_init_aggregation(struct rtl8xxxu_priv *priv)

2.39.0

From: Sean Anderson <[email protected]>

[ Upstream commit 36926a7d70c2d462fca1ed85bfee000d17fd8662 ]

On the T208X SoCs, MAC1 and MAC2 support XGMII. Add some new MAC dtsi fragments, and mark the QMAN ports as 10G.

---
 .../boot/dts/fsl/qoriq-fman3-0-10g-2.dtsi     | 44 +++++++++++++++++++
 .../boot/dts/fsl/qoriq-fman3-0-10g-3.dtsi     | 44 +++++++++++++++++++
 arch/powerpc/boot/dts/fsl/t2081si-post.dtsi   |  4 +-
 3 files changed, 90 insertions(+), 2 deletions(-)
 create mode 100644 arch/powerpc/boot/dts/fsl/qoriq-fman3-0-10g-2.dtsi
 create mode 100644 arch/powerpc/boot/dts/fsl/qoriq-fman3-0-10g-3.dtsi

new file mode 100644
index 0000000000000..437dab3fc0176
@@ -0,0 +1,44 @@
+// SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0-or-later
+/*
+ * QorIQ FMan v3 10g port #2 device tree stub [ controller @ offset 0x400000 ]
+ *
+ * Copyright 2022 Sean Anderson <[email protected]>
+ * Copyright 2012 - 2015 Freescale Semiconductor Inc.
+ */
+
+fman@400000 {
+	fman0_rx_0x08: port@88000 {
+		cell-index = <0x8>;
+		compatible = "fsl,fman-v3-port-rx";
+		reg = <0x88000 0x1000>;
+		fsl,fman-10g-port;
+	};
+
+	fman0_tx_0x28: port@a8000 {
+		cell-index = <0x28>;
+		compatible = "fsl,fman-v3-port-tx";
+		reg = <0xa8000 0x1000>;
+		fsl,fman-10g-port;
+	};
+
+	ethernet@e0000 {
+		cell-index = <0>;
+		compatible = "fsl,fman-memac";
+		reg = <0xe0000 0x1000>;
+		fsl,fman-ports = <&fman0_rx_0x08 &fman0_tx_0x28>;
+		ptp-timer = <&ptp_timer0>;
+		pcsphy-handle = <&pcsphy0>;
+	};
+
+	mdio@e1000 {
+		#address-cells = <1>;
+		#size-cells = <0>;
+		compatible = "fsl,fman-memac-mdio", "fsl,fman-xmdio";
+		reg = <0xe1000 0x1000>;
+		fsl,erratum-a011043; /* must ignore read errors */
+
+		pcsphy0: ethernet-phy@0 {
+			reg = <0x0>;
+		};
+	};
+};

index ecbb447920bc6..74e17e134387d 100644
@@ -609,8 +609,8 @@
 /include/ "qoriq-bman1.dtsi"
 
 /include/ "qoriq-fman3-0.dtsi"
-/include/ "qoriq-fman3-0-1g-0.dtsi"
-/include/ "qoriq-fman3-0-1g-1.dtsi"
+/include/ "qoriq-fman3-0-10g-2.dtsi"
+/include/ "qoriq-fman3-0-10g-3.dtsi"
 /include/ "qoriq-fman3-0-1g-2.dtsi"
 /include/ "qoriq-fman3-0-1g-3.dtsi"
 /include/ "qoriq-fman3-0-1g-4.dtsi"

2.39.0

From: Jason A. Donenfeld <[email protected]>

[ Upstream commit d7bf7f3b813e3755226bcb5114ad2ac477514ebf ]

add_latent_entropy() is called every time a process forks, in kernel_clone(). This in turn calls add_device_randomness() using the latent entropy global state. add_device_randomness() does two things:

2) Mixes into the input pool the latent entropy argument passed; and
1) Mixes in a cycle counter, a sort of measurement of when the event took place, the high precision bits of which are presumably difficult to predict.

(2) is impossible without CONFIG_GCC_PLUGIN_LATENT_ENTROPY=y. But (1) is always possible. However, currently CONFIG_GCC_PLUGIN_LATENT_ENTROPY=n disables both (1) and (2), instead of just (2).

This commit causes the CONFIG_GCC_PLUGIN_LATENT_ENTROPY=n case to still do (1) by passing NULL (len 0) to add_device_randomness() when add_latent_ entropy() is called.

---
 include/linux/random.h | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

index 3feafab498ad9..ed75fb2b0ca94 100644
@@ -19,14 +19,14 @@ void add_input_randomness(unsigned int type, unsigned int code,
 void add_interrupt_randomness(int irq) __latent_entropy;
 void add_hwgenerator_randomness(const void *buf, size_t len, size_t entropy);
 
-#if defined(LATENT_ENTROPY_PLUGIN) && !defined(__CHECKER__)
 static inline void add_latent_entropy(void)
 {
+#if defined(LATENT_ENTROPY_PLUGIN) && !defined(__CHECKER__)
 	add_device_randomness((const void *)&latent_entropy, sizeof(latent_entropy));
-}
 #else
-static inline void add_latent_entropy(void) { }
+	add_device_randomness(NULL, 0);
 #endif
+}
 
 void get_random_bytes(void *buf, size_t len);
 size_t __must_check get_random_bytes_arch(void *buf, size_t len);

2.39.0

From: Sean Christopherson <[email protected]>

[ Upstream commit 17122c06b86c9f77f45b86b8e62c3ed440847a59 ]

Treat any exception during instruction decode for EMULTYPE_SKIP as a "full" emulation failure, i.e. signal failure instead of queuing the exception. When decoding purely to skip an instruction, KVM and/or the CPU has already done some amount of emulation that cannot be unwound, e.g. on an EPT misconfig VM-Exit KVM has already processeed the emulated MMIO. KVM already does this if a #UD is encountered, but not for other exceptions, e.g. if a #PF is encountered during fetch.

In SVM's soft-injection use case, queueing the exception is particularly problematic as queueing exceptions while injecting events can put KVM into an infinite loop due to bailing from VM-Enter to service the newly pending exception. E.g. multiple warnings to detect such behavior fire:

  ------------[ cut here ]------------
  WARNING: CPU: 3 PID: 1017 at arch/x86/kvm/x86.c:9873 kvm_arch_vcpu_ioctl_run+0x1de5/0x20a0 [kvm]
  Modules linked in: kvm_amd ccp kvm irqbypass
  CPU: 3 PID: 1017 Comm: svm_nested_soft Not tainted 6.0.0-rc1+ #220
  Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 0.0.0 02/06/2015
  RIP: 0010:kvm_arch_vcpu_ioctl_run+0x1de5/0x20a0 [kvm]
  Call Trace:
   kvm_vcpu_ioctl+0x223/0x6d0 [kvm]
   __x64_sys_ioctl+0x85/0xc0
   do_syscall_64+0x2b/0x50
   entry_SYSCALL_64_after_hwframe+0x46/0xb0
  ---[ end trace 0000000000000000 ]---
  ------------[ cut here ]------------
  WARNING: CPU: 3 PID: 1017 at arch/x86/kvm/x86.c:9987 kvm_arch_vcpu_ioctl_run+0x12a3/0x20a0 [kvm]
  Modules linked in: kvm_amd ccp kvm irqbypass
  CPU: 3 PID: 1017 Comm: svm_nested_soft Tainted: G        W          6.0.0-rc1+ #220
  Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 0.0.0 02/06/2015
  RIP: 0010:kvm_arch_vcpu_ioctl_run+0x12a3/0x20a0 [kvm]
  Call Trace:
   kvm_vcpu_ioctl+0x223/0x6d0 [kvm]
   __x64_sys_ioctl+0x85/0xc0
   do_syscall_64+0x2b/0x50
   entry_SYSCALL_64_after_hwframe+0x46/0xb0
  ---[ end trace 0000000000000000 ]---

---
 arch/x86/kvm/x86.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

index cf37a61729972..f5e9590a8f311 100644
@@ -6787,7 +6787,9 @@ int x86_emulate_instruction(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa,
 						  write_fault_to_spt,
 						  emulation_type))
 				return 1;
-			if (ctxt->have_exception) {
+
+			if (ctxt->have_exception &&
+			    !(emulation_type & EMULTYPE_SKIP)) {
 				/*
 				 * #UD should result in just EMULATION_FAILED, and trap-like
 				 * exception should not be encountered during decode.

2.39.0

From: Jim Mattson <[email protected]>

[ Upstream commit 2e7eab81425ad6c875f2ed47c0ce01e78afc38a5 ]

According to Intel's document on Indirect Branch Restricted Speculation, "Enabling IBRS does not prevent software from controlling the predicted targets of indirect branches of unrelated software executed later at the same predictor mode (for example, between two different user applications, or two different virtual machines). Such isolation can be ensured through use of the Indirect Branch Predictor Barrier (IBPB) command." This applies to both basic and enhanced IBRS.

Since L1 and L2 VMs share hardware predictor modes (guest-user and guest-kernel), hardware IBRS is not sufficient to virtualize IBRS. (The way that basic IBRS is implemented on pre-eIBRS parts, hardware IBRS is actually sufficient in practice, even though it isn't sufficient architecturally.)

For virtual CPUs that support IBRS, add an indirect branch prediction barrier on emulated VM-exit, to ensure that the predicted targets of indirect branches executed in L1 cannot be controlled by software that was executed in L2.

Since we typically don't intercept guest writes to IA32_SPEC_CTRL, perform the IBPB at emulated VM-exit regardless of the current IA32_SPEC_CTRL.IBRS value, even though the IBPB could technically be deferred until L1 sets IA32_SPEC_CTRL.IBRS, if IA32_SPEC_CTRL.IBRS is clear at emulated VM-exit.

This is CVE-2022-2196.

---
 arch/x86/kvm/vmx/nested.c | 11 +++++++++++
 arch/x86/kvm/vmx/vmx.c    |  6 ++++--
 2 files changed, 15 insertions(+), 2 deletions(-)

index 00f3336194a96..d3a8ee0ef988a 100644
@@ -4118,6 +4118,17 @@ void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 exit_reason,
 
 	vmx_switch_vmcs(vcpu, &vmx->vmcs01);
 
+	/*
+	 * If IBRS is advertised to the vCPU, KVM must flush the indirect
+	 * branch predictors when transitioning from L2 to L1, as L1 expects
+	 * hardware (KVM in this case) to provide separate predictor modes.
+	 * Bare metal isolates VMX root (host) from VMX non-root (guest), but
+	 * doesn't isolate different VMCSs, i.e. in this case, doesn't provide
+	 * separate modes for L2 vs L1.
+	 */
+	if (guest_cpuid_has(vcpu, X86_FEATURE_SPEC_CTRL))
+		indirect_branch_prediction_barrier();
+
 	/* Update any VMCS fields that might have changed while L2 ran */
 	vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, vmx->msr_autoload.host.nr);
 	vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, vmx->msr_autoload.guest.nr);

index a8c8073654cf1..e6dd6a7e86893 100644
@@ -1397,8 +1397,10 @@ void vmx_vcpu_load_vmcs(struct kvm_vcpu *vcpu, int cpu,
 
 		/*
 		 * No indirect branch prediction barrier needed when switching
-		 * the active VMCS within a guest, e.g. on nested VM-Enter.
-		 * The L1 VMM can protect itself with retpolines, IBPB or IBRS.
+		 * the active VMCS within a vCPU, unless IBRS is advertised to
+		 * the vCPU.  To minimize the number of IBPBs executed, KVM
+		 * performs IBPB on nested VM-Exit (a single nested transition
+		 * may switch the active VMCS multiple times).
 		 */
 		if (!buddy || WARN_ON_ONCE(buddy->vmcs != prev))
 			indirect_branch_prediction_barrier();

2.39.0

From: Marc Kleine-Budde <[email protected]>

[ Upstream commit f006229135b7debf4037adb1eb93e358559593db ]

Debian's gcc-13 [1] throws the following error in
kvaser_usb_hydra_cmd_size():

[1] gcc version 13.0.0 20221214 (experimental) [master r13-4693-g512098a3316] (Debian 13-20221214-1)

| drivers/net/can/usb/kvaser_usb/kvaser_usb_hydra.c:502:65: error:
| array subscript ‘struct kvaser_cmd_ext[0]’ is partly outside array
| bounds of ‘unsigned char[32]’ [-Werror=array-bounds=]
|   502 |                 ret = le16_to_cpu(((struct kvaser_cmd_ext *)cmd)->len);

kvaser_usb_hydra_cmd_size() returns the size of given command. It depends on the command number (cmd->header.cmd_no). For extended commands (cmd->header.cmd_no == CMD_EXTENDED) the above shown code is executed.

Help gcc to recognize that this code path is not taken in all cases, by calling kvaser_usb_hydra_cmd_size() directly after assigning the command number.

---
 .../net/can/usb/kvaser_usb/kvaser_usb_hydra.c | 33 ++++++++++++++-----
 1 file changed, 24 insertions(+), 9 deletions(-)

index 2764fdd7e84b3..233bbfeaa771e 100644
@@ -518,6 +518,7 @@ static int kvaser_usb_hydra_send_simple_cmd(struct kvaser_usb *dev,
 					    u8 cmd_no, int channel)
 {
 	struct kvaser_cmd *cmd;
+	size_t cmd_len;
 	int err;
 
 	cmd = kcalloc(1, sizeof(struct kvaser_cmd), GFP_KERNEL);

@@ -525,6 +526,7 @@ static int kvaser_usb_hydra_send_simple_cmd(struct kvaser_usb *dev,
 		return -ENOMEM;
 
 	cmd->header.cmd_no = cmd_no;
+	cmd_len = kvaser_usb_hydra_cmd_size(cmd);
 	if (channel < 0) {
 		kvaser_usb_hydra_set_cmd_dest_he
 				(cmd, KVASER_USB_HYDRA_HE_ADDRESS_ILLEGAL);

@@ -541,7 +543,7 @@ static int kvaser_usb_hydra_send_simple_cmd(struct kvaser_usb *dev,
 	kvaser_usb_hydra_set_cmd_transid
 				(cmd, kvaser_usb_hydra_get_next_transid(dev));
 
-	err = kvaser_usb_send_cmd(dev, cmd, kvaser_usb_hydra_cmd_size(cmd));
+	err = kvaser_usb_send_cmd(dev, cmd, cmd_len);
 	if (err)
 		goto end;
 

@@ -557,6 +559,7 @@ kvaser_usb_hydra_send_simple_cmd_async(struct kvaser_usb_net_priv *priv,
 {
 	struct kvaser_cmd *cmd;
 	struct kvaser_usb *dev = priv->dev;
+	size_t cmd_len;
 	int err;
 
 	cmd = kcalloc(1, sizeof(struct kvaser_cmd), GFP_ATOMIC);

@@ -564,14 +567,14 @@ kvaser_usb_hydra_send_simple_cmd_async(struct kvaser_usb_net_priv *priv,
 		return -ENOMEM;
 
 	cmd->header.cmd_no = cmd_no;
+	cmd_len = kvaser_usb_hydra_cmd_size(cmd);
 
 	kvaser_usb_hydra_set_cmd_dest_he
 		(cmd, dev->card_data.hydra.channel_to_he[priv->channel]);
 	kvaser_usb_hydra_set_cmd_transid
 				(cmd, kvaser_usb_hydra_get_next_transid(dev));
 
-	err = kvaser_usb_send_cmd_async(priv, cmd,
-					kvaser_usb_hydra_cmd_size(cmd));
+	err = kvaser_usb_send_cmd_async(priv, cmd, cmd_len);
 	if (err)
 		kfree(cmd);
 

@@ -715,6 +718,7 @@ static int kvaser_usb_hydra_get_single_capability(struct kvaser_usb *dev,
 {
 	struct kvaser_usb_dev_card_data *card_data = &dev->card_data;
 	struct kvaser_cmd *cmd;
+	size_t cmd_len;
 	u32 value = 0;
 	u32 mask = 0;
 	u16 cap_cmd_res;

@@ -726,13 +730,14 @@ static int kvaser_usb_hydra_get_single_capability(struct kvaser_usb *dev,
 		return -ENOMEM;
 
 	cmd->header.cmd_no = CMD_GET_CAPABILITIES_REQ;
+	cmd_len = kvaser_usb_hydra_cmd_size(cmd);
 	cmd->cap_req.cap_cmd = cpu_to_le16(cap_cmd_req);
 
 	kvaser_usb_hydra_set_cmd_dest_he(cmd, card_data->hydra.sysdbg_he);
 	kvaser_usb_hydra_set_cmd_transid
 				(cmd, kvaser_usb_hydra_get_next_transid(dev));
 
-	err = kvaser_usb_send_cmd(dev, cmd, kvaser_usb_hydra_cmd_size(cmd));
+	err = kvaser_usb_send_cmd(dev, cmd, cmd_len);
 	if (err)
 		goto end;
 

@@ -1555,6 +1560,7 @@ static int kvaser_usb_hydra_get_busparams(struct kvaser_usb_net_priv *priv,
 	struct kvaser_usb *dev = priv->dev;
 	struct kvaser_usb_net_hydra_priv *hydra = priv->sub_priv;
 	struct kvaser_cmd *cmd;
+	size_t cmd_len;
 	int err;
 
 	if (!hydra)

@@ -1565,6 +1571,7 @@ static int kvaser_usb_hydra_get_busparams(struct kvaser_usb_net_priv *priv,
 		return -ENOMEM;
 
 	cmd->header.cmd_no = CMD_GET_BUSPARAMS_REQ;
+	cmd_len = kvaser_usb_hydra_cmd_size(cmd);
 	kvaser_usb_hydra_set_cmd_dest_he
 		(cmd, dev->card_data.hydra.channel_to_he[priv->channel]);
 	kvaser_usb_hydra_set_cmd_transid

@@ -1574,7 +1581,7 @@ static int kvaser_usb_hydra_get_busparams(struct kvaser_usb_net_priv *priv,
 
 	reinit_completion(&priv->get_busparams_comp);
 
-	err = kvaser_usb_send_cmd(dev, cmd, kvaser_usb_hydra_cmd_size(cmd));
+	err = kvaser_usb_send_cmd(dev, cmd, cmd_len);
 	if (err)
 		return err;
 

@@ -1601,6 +1608,7 @@ static int kvaser_usb_hydra_set_bittiming(const struct net_device *netdev,
 	struct kvaser_cmd *cmd;
 	struct kvaser_usb_net_priv *priv = netdev_priv(netdev);
 	struct kvaser_usb *dev = priv->dev;
+	size_t cmd_len;
 	int err;
 
 	cmd = kcalloc(1, sizeof(struct kvaser_cmd), GFP_KERNEL);

@@ -1608,6 +1616,7 @@ static int kvaser_usb_hydra_set_bittiming(const struct net_device *netdev,
 		return -ENOMEM;
 
 	cmd->header.cmd_no = CMD_SET_BUSPARAMS_REQ;
+	cmd_len = kvaser_usb_hydra_cmd_size(cmd);
 	memcpy(&cmd->set_busparams_req.busparams_nominal, busparams,
 	       sizeof(cmd->set_busparams_req.busparams_nominal));
 

@@ -1616,7 +1625,7 @@ static int kvaser_usb_hydra_set_bittiming(const struct net_device *netdev,
 	kvaser_usb_hydra_set_cmd_transid
 				(cmd, kvaser_usb_hydra_get_next_transid(dev));
 
-	err = kvaser_usb_send_cmd(dev, cmd, kvaser_usb_hydra_cmd_size(cmd));
+	err = kvaser_usb_send_cmd(dev, cmd, cmd_len);
 
 	kfree(cmd);
 

@@ -1629,6 +1638,7 @@ static int kvaser_usb_hydra_set_data_bittiming(const struct net_device *netdev,
 	struct kvaser_cmd *cmd;
 	struct kvaser_usb_net_priv *priv = netdev_priv(netdev);
 	struct kvaser_usb *dev = priv->dev;
+	size_t cmd_len;
 	int err;
 
 	cmd = kcalloc(1, sizeof(struct kvaser_cmd), GFP_KERNEL);

@@ -1636,6 +1646,7 @@ static int kvaser_usb_hydra_set_data_bittiming(const struct net_device *netdev,
 		return -ENOMEM;
 
 	cmd->header.cmd_no = CMD_SET_BUSPARAMS_FD_REQ;
+	cmd_len = kvaser_usb_hydra_cmd_size(cmd);
 	memcpy(&cmd->set_busparams_req.busparams_data, busparams,
 	       sizeof(cmd->set_busparams_req.busparams_data));
 

@@ -1653,7 +1664,7 @@ static int kvaser_usb_hydra_set_data_bittiming(const struct net_device *netdev,
 	kvaser_usb_hydra_set_cmd_transid
 				(cmd, kvaser_usb_hydra_get_next_transid(dev));
 
-	err = kvaser_usb_send_cmd(dev, cmd, kvaser_usb_hydra_cmd_size(cmd));
+	err = kvaser_usb_send_cmd(dev, cmd, cmd_len);
 
 	kfree(cmd);
 

@@ -1781,6 +1792,7 @@ static int kvaser_usb_hydra_get_software_info(struct kvaser_usb *dev)
 static int kvaser_usb_hydra_get_software_details(struct kvaser_usb *dev)
 {
 	struct kvaser_cmd *cmd;
+	size_t cmd_len;
 	int err;
 	u32 flags;
 	struct kvaser_usb_dev_card_data *card_data = &dev->card_data;

@@ -1790,6 +1802,7 @@ static int kvaser_usb_hydra_get_software_details(struct kvaser_usb *dev)
 		return -ENOMEM;
 
 	cmd->header.cmd_no = CMD_GET_SOFTWARE_DETAILS_REQ;
+	cmd_len = kvaser_usb_hydra_cmd_size(cmd);
 	cmd->sw_detail_req.use_ext_cmd = 1;
 	kvaser_usb_hydra_set_cmd_dest_he
 				(cmd, KVASER_USB_HYDRA_HE_ADDRESS_ILLEGAL);

@@ -1797,7 +1810,7 @@ static int kvaser_usb_hydra_get_software_details(struct kvaser_usb *dev)
 	kvaser_usb_hydra_set_cmd_transid
 				(cmd, kvaser_usb_hydra_get_next_transid(dev));
 
-	err = kvaser_usb_send_cmd(dev, cmd, kvaser_usb_hydra_cmd_size(cmd));
+	err = kvaser_usb_send_cmd(dev, cmd, cmd_len);
 	if (err)
 		goto end;
 

@@ -1913,6 +1926,7 @@ static int kvaser_usb_hydra_set_opt_mode(const struct kvaser_usb_net_priv *priv)
 {
 	struct kvaser_usb *dev = priv->dev;
 	struct kvaser_cmd *cmd;
+	size_t cmd_len;
 	int err;
 
 	if ((priv->can.ctrlmode &

@@ -1928,6 +1942,7 @@ static int kvaser_usb_hydra_set_opt_mode(const struct kvaser_usb_net_priv *priv)
 		return -ENOMEM;
 
 	cmd->header.cmd_no = CMD_SET_DRIVERMODE_REQ;
+	cmd_len = kvaser_usb_hydra_cmd_size(cmd);
 	kvaser_usb_hydra_set_cmd_dest_he
 		(cmd, dev->card_data.hydra.channel_to_he[priv->channel]);
 	kvaser_usb_hydra_set_cmd_transid

@@ -1937,7 +1952,7 @@ static int kvaser_usb_hydra_set_opt_mode(const struct kvaser_usb_net_priv *priv)
 	else
 		cmd->set_ctrlmode.mode = KVASER_USB_HYDRA_CTRLMODE_NORMAL;
 
-	err = kvaser_usb_send_cmd(dev, cmd, kvaser_usb_hydra_cmd_size(cmd));
+	err = kvaser_usb_send_cmd(dev, cmd, cmd_len);
 	kfree(cmd);
 
 	return err;

2.39.0

From: Sean Anderson <[email protected]>

[ Upstream commit 8d8bee13ae9e316443c6666286360126a19c8d94 ]

There aren't enough resources to run these ports at 10G speeds. Disable 10G for these ports, reverting to the previous speed.

---
 arch/powerpc/boot/dts/fsl/t2081si-post.dtsi | 16 ++++++++++++++++
 1 file changed, 16 insertions(+)

index 74e17e134387d..27714dc2f04a5 100644
@@ -659,3 +659,19 @@
 		interrupts = <16 2 1 9>;
 	};
 };
+
+&fman0_rx_0x08 {
+	/delete-property/ fsl,fman-10g-port;
+};
+
+&fman0_tx_0x28 {
+	/delete-property/ fsl,fman-10g-port;
+};
+
+&fman0_rx_0x09 {
+	/delete-property/ fsl,fman-10g-port;
+};
+
+&fman0_tx_0x29 {
+	/delete-property/ fsl,fman-10g-port;
+};

2.39.0

From: Thomas Gleixner <[email protected]>

commit d125d1349abeb46945dc5e98f7824bf688266f13 upstream.

syzbot reported a RCU stall which is caused by setting up an alarmtimer with a very small interval and ignoring the signal. The reproducer arms the alarm timer with a relative expiry of 8ns and an interval of 9ns. Not a problem per se, but that's an issue when the signal is ignored because then the timer is immediately rearmed because there is no way to delay that rearming to the signal delivery path. See posix_timer_fn() and commit 58229a189942 ("posix-timers: Prevent softirq starvation by small intervals and SIG_IGN") for details.

The reproducer does not set SIG_IGN explicitely, but it sets up the timers signal with SIGCONT. That has the same effect as explicitely setting SIG_IGN for a signal as SIGCONT is ignored if there is no handler set and the task is not ptraced.

The log clearly shows that:

[pid 5102] --- SIGCONT {si_signo=SIGCONT, si_code=SI_TIMER, si_timerid=0, si_overrun=316014, si_int=0, si_ptr=NULL} ---

It works because the tasks are traced and therefore the signal is queued so the tracer can see it, which delays the restart of the timer to the signal delivery path. But then the tracer is killed:

[pid 5087] kill(-5102, SIGKILL <unfinished ...>
...
./strace-static-x86_64: Process 5107 detached

and after it's gone the stall can be observed:

syzkaller login: [ 79.439102][ C0] hrtimer: interrupt took 68471 ns

   [  184.460538][    C1] rcu: INFO: rcu_preempt detected stalls on CPUs/tasks:
   ...
   [  184.658237][    C1] rcu: Stack dump where RCU GP kthread last ran:
   [  184.664574][    C1] Sending NMI from CPU 1 to CPUs 0:
   [  184.669821][    C0] NMI backtrace for cpu 0
   [  184.669831][    C0] CPU: 0 PID: 5108 Comm: syz-executor192 Not tainted 6.2.0-rc6-next-20230203-syzkaller #0
   ...
   [  184.670036][    C0] Call Trace:
   [  184.670041][    C0]  <IRQ>
   [  184.670045][    C0]  alarmtimer_fired+0x327/0x670

posix_timer_fn() prevents that by checking whether the interval for timers which have the signal ignored is smaller than a jiffie and artifically delay it by shifting the next expiry out by a jiffie. That's accurate vs. the overrun accounting, but slightly inaccurate vs. timer_gettimer(2).

The comment in that function says what needs to be done and there was a fix available for the regular userspace induced SIG_IGN mechanism, but that did not work due to the implicit ignore for SIGCONT and similar signals. This needs to be worked on, but for now the only available workaround is to do exactly what posix_timer_fn() does:

Increase the interval of self-rearming timers, which have their signal ignored, to at least a jiffie.

Interestingly this has been fixed before via commit ff86bf0c65f1 ("alarmtimer: Rate limit periodic intervals") already, but that fix got lost in a later rework.

---
 kernel/time/alarmtimer.c |   33 +++++++++++++++++++++++++++++----
 1 file changed, 29 insertions(+), 4 deletions(-)

@@ -479,11 +479,35 @@ u64 alarm_forward(struct alarm *alarm, k
 }
 EXPORT_SYMBOL_GPL(alarm_forward);
 
-u64 alarm_forward_now(struct alarm *alarm, ktime_t interval)
+static u64 __alarm_forward_now(struct alarm *alarm, ktime_t interval, bool throttle)
 {
 	struct alarm_base *base = &alarm_bases[alarm->type];
+	ktime_t now = base->gettime();
+
+	if (IS_ENABLED(CONFIG_HIGH_RES_TIMERS) && throttle) {
+		/*
+		 * Same issue as with posix_timer_fn(). Timers which are
+		 * periodic but the signal is ignored can starve the system
+		 * with a very small interval. The real fix which was
+		 * promised in the context of posix_timer_fn() never
+		 * materialized, but someone should really work on it.
+		 *
+		 * To prevent DOS fake @now to be 1 jiffie out which keeps
+		 * the overrun accounting correct but creates an
+		 * inconsistency vs. timer_gettime(2).
+		 */
+		ktime_t kj = NSEC_PER_SEC / HZ;
+
+		if (interval < kj)
+			now = ktime_add(now, kj);
+	}
+
+	return alarm_forward(alarm, now, interval);
+}
 
-	return alarm_forward(alarm, base->gettime(), interval);
+u64 alarm_forward_now(struct alarm *alarm, ktime_t interval)
+{
+	return __alarm_forward_now(alarm, interval, false);
 }
 EXPORT_SYMBOL_GPL(alarm_forward_now);
 

@@ -557,9 +581,10 @@ static enum alarmtimer_restart alarm_han
 	if (posix_timer_event(ptr, si_private) && ptr->it_interval) {
 		/*
 		 * Handle ignored signals and rearm the timer. This will go
-		 * away once we handle ignored signals proper.
+		 * away once we handle ignored signals proper. Ensure that
+		 * small intervals cannot starve the system.
 		 */
-		ptr->it_overrun += alarm_forward_now(alarm, ptr->it_interval);
+		ptr->it_overrun += __alarm_forward_now(alarm, ptr->it_interval, true);
 		++ptr->it_requeue_pending;
 		ptr->it_active = 1;
 		result = ALARMTIMER_RESTART;

From: Zheng Wang <[email protected]>

commit 4a61648af68f5ba4884f0e3b494ee1cabc4b6620 upstream.

If intel_gvt_dma_map_guest_page failed, it will call ppgtt_invalidate_spt, which will finally free the spt. But the caller function ppgtt_populate_spt_by_guest_entry does not notice that, it will free spt again in its error path.

Fix this by canceling the mapping of DMA address and freeing sub_spt. Besides, leave the handle of spt destroy to caller function instead of callee function when error occurs.

---
 drivers/gpu/drm/i915/gvt/gtt.c |   17 +++++++++++++----
 1 file changed, 13 insertions(+), 4 deletions(-)

@@ -1186,10 +1186,8 @@ static int split_2MB_gtt_entry(struct in
 	for_each_shadow_entry(sub_spt, &sub_se, sub_index) {
 		ret = intel_gvt_hypervisor_dma_map_guest_page(vgpu,
 				start_gfn + sub_index, PAGE_SIZE, &dma_addr);
-		if (ret) {
-			ppgtt_invalidate_spt(spt);
-			return ret;
-		}
+		if (ret)
+			goto err;
 		sub_se.val64 = se->val64;
 
 		/* Copy the PAT field from PDE. */

@@ -1208,6 +1206,17 @@ static int split_2MB_gtt_entry(struct in
 	ops->set_pfn(se, sub_spt->shadow_page.mfn);
 	ppgtt_set_shadow_entry(spt, se, index);
 	return 0;
+err:
+	/* Cancel the existing addess mappings of DMA addr. */
+	for_each_present_shadow_entry(sub_spt, &sub_se, sub_index) {
+		gvt_vdbg_mm("invalidate 4K entry\n");
+		ppgtt_invalidate_pte(sub_spt, &sub_se);
+	}
+	/* Release the new allocated spt. */
+	trace_spt_change(sub_spt->vgpu->id, "release", sub_spt,
+		sub_spt->guest_page.gfn, sub_spt->shadow_page.type);
+	ppgtt_free_spt(sub_spt);
+	return ret;
 }
 
 static int split_64KB_gtt_entry(struct intel_vgpu *vgpu,

From: Pavel Skripkin <[email protected]>

commit 8b5cb7e41d9d77ffca036b0239177de123394a55 upstream.

Syzbot hit NULL deref in rhashtable_free_and_destroy(). The problem was in mesh_paths and mpp_paths being NULL.

mesh_pathtbl_init() could fail in case of memory allocation failure, but nobody cared, since ieee80211_mesh_init_sdata() returns void. It led to leaving 2 pointers as NULL. Syzbot has found null deref on exit path, but it could happen anywhere else, because code assumes these pointers are valid.

Since all ieee80211_*_setup_sdata functions are void and do not fail, let's embedd mesh_paths and mpp_paths into parent struct to avoid adding error handling on higher levels and follow the pattern of others setup_sdata functions

---
 net/mac80211/ieee80211_i.h  |   24 ++++++++++-
 net/mac80211/mesh.h         |   22 ----------
 net/mac80211/mesh_pathtbl.c |   91 +++++++++++++++-----------------------------
 3 files changed, 55 insertions(+), 82 deletions(-)

@@ -632,6 +632,26 @@ struct mesh_csa_settings {
 	struct cfg80211_csa_settings settings;
 };
 
+/**
+ * struct mesh_table
+ *
+ * @known_gates: list of known mesh gates and their mpaths by the station. The
+ * gate's mpath may or may not be resolved and active.
+ * @gates_lock: protects updates to known_gates
+ * @rhead: the rhashtable containing struct mesh_paths, keyed by dest addr
+ * @walk_head: linked list containing all mesh_path objects
+ * @walk_lock: lock protecting walk_head
+ * @entries: number of entries in the table
+ */
+struct mesh_table {
+	struct hlist_head known_gates;
+	spinlock_t gates_lock;
+	struct rhashtable rhead;
+	struct hlist_head walk_head;
+	spinlock_t walk_lock;
+	atomic_t entries;		/* Up to MAX_MESH_NEIGHBOURS */
+};
+
 struct ieee80211_if_mesh {
 	struct timer_list housekeeping_timer;
 	struct timer_list mesh_path_timer;

@@ -706,8 +726,8 @@ struct ieee80211_if_mesh {
 	/* offset from skb->data while building IE */
 	int meshconf_offset;
 
-	struct mesh_table *mesh_paths;
-	struct mesh_table *mpp_paths; /* Store paths for MPP&MAP */
+	struct mesh_table mesh_paths;
+	struct mesh_table mpp_paths; /* Store paths for MPP&MAP */
 	int mesh_paths_generation;
 	int mpp_paths_generation;
 };

@@ -127,26 +127,6 @@ struct mesh_path {
 	u32 path_change_count;
 };
 
-/**
- * struct mesh_table
- *
- * @known_gates: list of known mesh gates and their mpaths by the station. The
- * gate's mpath may or may not be resolved and active.
- * @gates_lock: protects updates to known_gates
- * @rhead: the rhashtable containing struct mesh_paths, keyed by dest addr
- * @walk_head: linked list containging all mesh_path objects
- * @walk_lock: lock protecting walk_head
- * @entries: number of entries in the table
- */
-struct mesh_table {
-	struct hlist_head known_gates;
-	spinlock_t gates_lock;
-	struct rhashtable rhead;
-	struct hlist_head walk_head;
-	spinlock_t walk_lock;
-	atomic_t entries;		/* Up to MAX_MESH_NEIGHBOURS */
-};
-
 /* Recent multicast cache */
 /* RMC_BUCKETS must be a power of 2, maximum 256 */
 #define RMC_BUCKETS		256

@@ -306,7 +286,7 @@ int mesh_path_error_tx(struct ieee80211_
 void mesh_path_assign_nexthop(struct mesh_path *mpath, struct sta_info *sta);
 void mesh_path_flush_pending(struct mesh_path *mpath);
 void mesh_path_tx_pending(struct mesh_path *mpath);
-int mesh_pathtbl_init(struct ieee80211_sub_if_data *sdata);
+void mesh_pathtbl_init(struct ieee80211_sub_if_data *sdata);
 void mesh_pathtbl_unregister(struct ieee80211_sub_if_data *sdata);
 int mesh_path_del(struct ieee80211_sub_if_data *sdata, const u8 *addr);
 void mesh_path_timer(struct timer_list *t);

From: Dave Hansen <[email protected]>

commit 74e19ef0ff8061ef55957c3abd71614ef0f42f47 upstream.

The results of "access_ok()" can be mis-speculated. The result is that you can end speculatively:

	if (access_ok(from, size))
		// Right here

even for bad from/size combinations. On first glance, it would be ideal to just add a speculation barrier to "access_ok()" so that its results can never be mis-speculated.

But there are lots of system calls just doing access_ok() via "copy_to_user()" and friends (example: fstat() and friends). Those are generally not problematic because they do not _consume_ data from userspace other than the pointer. They are also very quick and common system calls that should not be needlessly slowed down.

"copy_from_user()" on the other hand uses a user-controller pointer and is frequently followed up with code that might affect caches. Take something like this:

	if (!copy_from_user(&kernelvar, uptr, size))
		do_something_with(kernelvar);

If userspace passes in an evil 'uptr' that *actually* points to a kernel addresses, and then do_something_with() has cache (or other) side-effects, it could allow userspace to infer kernel data values.

Add a barrier to the common copy_from_user() code to prevent mis-speculated values which happen after the copy.

Also add a stub for architectures that do not define barrier_nospec(). This makes the macro usable in generic code.

Since the barrier is now usable in generic code, the x86 #ifdef in the BPF code can also go away.

---
 include/linux/nospec.h |    4 ++++
 kernel/bpf/core.c      |    2 --
 lib/usercopy.c         |    7 +++++++
 3 files changed, 11 insertions(+), 2 deletions(-)

@@ -9,6 +9,10 @@
 
 struct task_struct;
 
+#ifndef barrier_nospec
+# define barrier_nospec() do { } while (0)
+#endif
+
 /**
  * array_index_mask_nospec() - generate a ~0 mask when index < size, 0 otherwise
  * @index: array element index

@@ -1567,9 +1567,7 @@ out:
 		 * reuse preexisting logic from Spectre v1 mitigation that
 		 * happens to produce the required code on x86 for v4 as well.
 		 */
-#ifdef CONFIG_X86
 		barrier_nospec();
-#endif
 		CONT;
 #define LDST(SIZEOP, SIZE)						\
 	STX_MEM_##SIZEOP:						\

@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <linux/uaccess.h>
 #include <linux/bitops.h>
+#include <linux/nospec.h>
 
 /* out-of-line parts */
 

@@ -10,6 +11,12 @@ unsigned long _copy_from_user(void *to,
 	unsigned long res = n;
 	might_fault();
 	if (likely(access_ok(from, n))) {
+		/*
+		 * Ensure that bad access_ok() speculation will not
+		 * lead to nasty side effects *after* the copy is
+		 * finished:
+		 */
+		barrier_nospec();
 		kasan_check_write(to, n);
 		res = raw_copy_from_user(to, from, n);
 	}

From: Lukas Wunner <[email protected]>

commit 36dd7a4c6226133b0b7aa92b8e604e688d958d0c upstream.

Commit e3fffc1f0b47 ("devicetree: document new marvell-8xxx and pwrseq-sd8787 options") documented a compatible string for SD8787 in the devicetree bindings, but neglected to add it to the mwifiex driver.

---
 drivers/net/wireless/marvell/mwifiex/sdio.c |    1 +
 1 file changed, 1 insertion(+)

@@ -58,6 +58,7 @@ static struct memory_type_mapping mem_ty
 };
 
 static const struct of_device_id mwifiex_sdio_of_match_table[] = {
+	{ .compatible = "marvell,sd8787" },
 	{ .compatible = "marvell,sd8897" },
 	{ .compatible = "marvell,sd8997" },
 	{ }

From: Kees Cook <[email protected]>

commit 118901ad1f25d2334255b3d50512fa20591531cd upstream.

With clang's kernel control flow integrity (kCFI, CONFIG_CFI_CLANG), indirect call targets are validated against the expected function pointer prototype to make sure the call target is valid to help mitigate ROP attacks. If they are not identical, there is a failure at run time, which manifests as either a kernel panic or thread getting killed.

ext4_feat_ktype was setting the "release" handler to "kfree", which doesn't have a matching function prototype. Add a simple wrapper with the correct prototype.

This was found as a result of Clang's new -Wcast-function-type-strict flag, which is more sensitive than the simpler -Wcast-function-type, which only checks for type width mismatches.

Note that this code is only reached when ext4 is a loadable module and it is being unloaded:

CFI failure at kobject_put+0xbb/0x1b0 (target: kfree+0x0/0x180; expected type: 0x7c4aa698)
...

 RIP: 0010:kobject_put+0xbb/0x1b0
 ...
 Call Trace:
  <TASK>
  ext4_exit_sysfs+0x14/0x60 [ext4]
  cleanup_module+0x67/0xedb [ext4]

---
 fs/ext4/sysfs.c |    7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

@@ -383,6 +383,11 @@ static void ext4_sb_release(struct kobje
 	complete(&sbi->s_kobj_unregister);
 }
 
+static void ext4_feat_release(struct kobject *kobj)
+{
+	kfree(kobj);
+}
+
 static const struct sysfs_ops ext4_attr_ops = {
 	.show	= ext4_attr_show,
 	.store	= ext4_attr_store,

@@ -397,7 +402,7 @@ static struct kobj_type ext4_sb_ktype =
 static struct kobj_type ext4_feat_ktype = {
 	.default_groups = ext4_feat_groups,
 	.sysfs_ops	= &ext4_attr_ops,
-	.release	= (void (*)(struct kobject *))kfree,
+	.release	= ext4_feat_release,
 };
 
 static struct kobject *ext4_root;

From: Vladimir Oltean <[email protected]>

commit af7b29b1deaac6da3bb7637f0e263dfab7bfc7a3 upstream.

taprio_attach() has this logic at the end, which should have been removed with the blamed patch (which is now being reverted):

	/* access to the child qdiscs is not needed in offload mode */
	if (FULL_OFFLOAD_IS_ENABLED(q->flags)) {
		kfree(q->qdiscs);
		q->qdiscs = NULL;
	}

because otherwise, we make use of q->qdiscs[] even after this array was deallocated, namely in taprio_leaf(). Therefore, whenever one would try to attach a valid child qdisc to a fully offloaded taprio root, one would immediately dereference a NULL pointer.

$ tc qdisc replace dev eno0 handle 8001: parent root taprio \
	num_tc 8 \
	map 0 1 2 3 4 5 6 7 \
	queues 1@0 1@1 1@2 1@3 1@4 1@5 1@6 1@7 \
	max-sdu 0 0 0 0 0 200 0 0 \
	base-time 200 \
	sched-entry S 80 20000 \
	sched-entry S a0 20000 \
	sched-entry S 5f 60000 \
	flags 2
$ max_frame_size=1500
$ data_rate_kbps=20000
$ port_transmit_rate_kbps=1000000
$ idleslope=$data_rate_kbps
$ sendslope=$(($idleslope - $port_transmit_rate_kbps))
$ locredit=$(($max_frame_size * $sendslope / $port_transmit_rate_kbps))
$ hicredit=$(($max_frame_size * $idleslope / $port_transmit_rate_kbps))
$ tc qdisc replace dev eno0 parent 8001:7 cbs \
	idleslope $idleslope \
	sendslope $sendslope \
	hicredit $hicredit \
	locredit $locredit \
	offload 0

Unable to handle kernel NULL pointer dereference at virtual address 0000000000000030
pc : taprio_leaf+0x28/0x40
lr : qdisc_leaf+0x3c/0x60
Call trace:
 taprio_leaf+0x28/0x40
 tc_modify_qdisc+0xf0/0x72c
 rtnetlink_rcv_msg+0x12c/0x390
 netlink_rcv_skb+0x5c/0x130
 rtnetlink_rcv+0x1c/0x2c

The solution is not as obvious as the problem. The code which deallocates q->qdiscs[] is in fact copied and pasted from mqprio, which also deallocates the array in mqprio_attach() and never uses it afterwards.

Therefore, the identical cleanup logic of priv->qdiscs[] that mqprio_destroy() has is deceptive because it will never take place at qdisc_destroy() time, but just at raw ops->destroy() time (otherwise said, priv->qdiscs[] do not last for the entire lifetime of the mqprio root), but rather, this is just the twisted way in which the Qdisc API understands error path cleanup should be done (Qdisc_ops :: destroy() is called even when Qdisc_ops :: init() never succeeded).

Side note, in fact this is also what the comment in mqprio_init() says:

	/* pre-allocate qdisc, attachment can't fail */

Or reworded, mqprio's priv->qdiscs[] scheme is only meant to serve as data passing between Qdisc_ops :: init() and Qdisc_ops :: attach().

[ this comment was also copied and pasted into the initial taprio
commit, even though taprio_attach() came way later ]

The problem is that taprio also makes extensive use of the q->qdiscs[] array in the software fast path (taprio_enqueue() and taprio_dequeue()), but it does not keep a reference of its own on q->qdiscs[i] (you'd think that since it creates these Qdiscs, it holds the reference, but nope, this is not completely true).

To understand the difference between taprio_destroy() and mqprio_destroy() one must look before commit 13511704f8d7 ("net: taprio offload: enforce qdisc to netdev queue mapping"), because that just muddied the waters.

In the "original" taprio design, taprio always attached itself (the root Qdisc) to all netdev TX queues, so that dev_qdisc_enqueue() would go through taprio_enqueue().

It also called qdisc_refcount_inc() on itself for as many times as there were netdev TX queues, in order to counter-balance what tc_get_qdisc() does when destroying a Qdisc (simplified for brevity below):

	if (n->nlmsg_type == RTM_DELQDISC)
		err = qdisc_graft(dev, parent=NULL, new=NULL, q, extack);

qdisc_graft(where "new" is NULL so this deletes the Qdisc):

	for (i = 0; i < num_q; i++) {
		struct netdev_queue *dev_queue;

		dev_queue = netdev_get_tx_queue(dev, i);

		old = dev_graft_qdisc(dev_queue, new);
		if (new && i > 0)
			qdisc_refcount_inc(new);

		qdisc_put(old);
		~~~~~~~~~~~~~~
		this decrements taprio's refcount once for each TX queue
	}

	notify_and_destroy(net, skb, n, classid,
			   rtnl_dereference(dev->qdisc), new);
			   ~~~~~~~~~~~~~~~~~~~~~~~~~~~~
			   and this finally decrements it to zero,
			   making qdisc_put() call qdisc_destroy()

The q->qdiscs[] created using qdisc_create_dflt() (or their replacements, if taprio_graft() was ever to get called) were then privately freed by taprio_destroy().

This is still what is happening after commit 13511704f8d7 ("net: taprio
offload: enforce qdisc to netdev queue mapping"), but only for software mode.

In full offload mode, the per-txq "qdisc_put(old)" calls from qdisc_graft() now deallocate the child Qdiscs rather than decrement taprio's refcount. So when notify_and_destroy(taprio) finally calls taprio_destroy(), the difference is that the child Qdiscs were already deallocated.

And this is exactly why the taprio_attach() comment "access to the child qdiscs is not needed in offload mode" is deceptive too. Not only the q->qdiscs[] array is not needed, but it is also necessary to get rid of it as soon as possible, because otherwise, we will also call qdisc_put() on the child Qdiscs in qdisc_destroy() -> taprio_destroy(), and this will cause a nasty use-after-free/refcount-saturate/whatever.

In short, the problem is that since the blamed commit, taprio_leaf() needs q->qdiscs[] to not be freed by taprio_attach(), while qdisc_destroy() -> taprio_destroy() does need q->qdiscs[] to be freed by taprio_attach() for full offload. Fixing one problem triggers the other.

All of this can be solved by making taprio keep its q->qdiscs[i] with a refcount elevated at 2 (in offloaded mode where they are attached to the netdev TX queues), both in taprio_attach() and in taprio_graft(). The generic qdisc_graft() would just decrement the child qdiscs' refcounts to 1, and taprio_destroy() would give them the final coup de grace.

However the rabbit hole of changes is getting quite deep, and the complexity increases. The blamed commit was supposed to be a bug fix in the first place, and the bug it addressed is not so significant so as to justify further rework in stable trees. So I'd rather just revert it. I don't know enough about multi-queue Qdisc design to make a proper judgement right now regarding what is/isn't idiomatic use of Qdisc concepts in taprio. I will try to study the problem more and come with a different solution in net-next.

---
 net/sched/sch_taprio.c |    8 +++-----
 1 file changed, 3 insertions(+), 5 deletions(-)

@@ -1908,14 +1908,12 @@ start_error:
 
 static struct Qdisc *taprio_leaf(struct Qdisc *sch, unsigned long cl)
 {
-	struct taprio_sched *q = qdisc_priv(sch);
-	struct net_device *dev = qdisc_dev(sch);
-	unsigned int ntx = cl - 1;
+	struct netdev_queue *dev_queue = taprio_queue_get(sch, cl);
 
-	if (ntx >= dev->num_tx_queues)
+	if (!dev_queue)
 		return NULL;
 
-	return q->qdiscs[ntx];
+	return dev_queue->qdisc_sleeping;
 }
 
 static unsigned long taprio_find(struct Qdisc *sch, u32 classid)